RomanNum3ral
/
gstack
mirror of https://github.com/garrytan/gstack.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

evals: split skill-e2e-review into three per-file CI shards 

Bun runs describe blocks as concurrency barriers, so the e2e-review CI
job executed its tests serially: 741s of an 860s PR critical path for
tests whose slowest member is 224s. The per-file matrix is the repo's
parallelism unit, so the split moves:

- Retro E2E + retro-base-branch  -> test/skill-e2e-retro.test.ts
- review/ship base-branch + Review Dashboard Via Attribution
                                  -> test/skill-e2e-review-attribution.test.ts
- sql-injection / enum-completeness / design-lite stay in
  test/skill-e2e-review.test.ts

One 741s job becomes three ~180-250s jobs. Locally the worst paid shard
drops from 1705s (94.7% of the 1800s kill) to under 700s. Test names,
bodies, suite strings, and eval-store collectors are unchanged, so
baselines carry over. Matrix rows added to both eval workflows
(attribution is gate-only, so no periodic row); the report job's
hardcoded runner count is gone (drift-proof).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Garry Tan 2026-08-15 08:03:41 -07:00
parent ac9291b146
commit b63608099c
No known key found for this signature in database
GPG Key ID: C1F69E85C74EFE1D
5 changed files with 478 additions and 410 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
.github/workflows/evals-periodic.yml vendored
View File

@ -84,6 +84,11 @@ jobs:
file: test/skill-e2e-qa-workflow.test.ts
- name: e2e-review
file: test/skill-e2e-review.test.ts
- name: e2e-retro
file: test/skill-e2e-retro.test.ts
# e2e-review-attribution is gate-only (all three of its tests are
# gate-tier) — deliberately absent here; an all-skip shard would just
# burn a container boot weekly.
- name: e2e-workflow
file: test/skill-e2e-workflow.test.ts
- name: e2e-routing

8
.github/workflows/evals.yml vendored
View File

@ -106,6 +106,10 @@ jobs:
file: test/skill-e2e-qa-workflow.test.ts
- name: e2e-review
file: test/skill-e2e-review.test.ts
- name: e2e-retro
file: test/skill-e2e-retro.test.ts
- name: e2e-review-attribution
file: test/skill-e2e-review-attribution.test.ts
- name: e2e-workflow
file: test/skill-e2e-workflow.test.ts
- name: e2e-routing
@ -357,14 +361,14 @@ jobs:
BODY="## E2E Evals: ${STATUS}
**${PASSED}/${TOTAL}** tests passed | **\$${COST}** total cost | **13 parallel runners**
**${PASSED}/${TOTAL}** tests passed | **\$${COST}** total cost
| Suite | Result | Status | Cost |
|-------|--------|--------|------|
$(echo -e "$SUITE_LINES")
---
*13x ubicloud-standard-8 (Docker: pre-baked toolchain + deps) | wall clock ≈ slowest suite*"
*ubicloud-standard-8 runners (Docker: pre-baked toolchain + deps) | wall clock ≈ slowest suite*"
if [ "$FAILED" -gt 0 ]; then
FAILURES=""

181
test/skill-e2e-retro.test.ts Normal file
View File

@ -0,0 +1,181 @@
import { expect, beforeAll, afterAll } from 'bun:test';
import { runSkillTest } from './helpers/session-runner';
import {
ROOT, runId,
describeIfSelected, testConcurrentIfSelected,
logCost, recordE2E,
createEvalCollector, finalizeEvalCollector,
} from './helpers/e2e-helpers';
import { spawnSync } from 'child_process';
import * as fs from 'fs';
import * as path from 'path';
import * as os from 'os';
const evalCollector = createEvalCollector('e2e-retro');
// --- Retro base branch detection smoke test ---
describeIfSelected('Base branch detection', ['retro-base-branch'], () => {
let baseBranchDir: string;
const run = (cmd: string, args: string[], cwd: string) =>
spawnSync(cmd, args, { cwd, stdio: 'pipe', timeout: 5000 });
beforeAll(() => {
baseBranchDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-basebranch-'));
});
afterAll(() => {
try { fs.rmSync(baseBranchDir, { recursive: true, force: true }); } catch {}
});
testConcurrentIfSelected('retro-base-branch', async () => {
const dir = path.join(baseBranchDir, 'retro-base');
fs.mkdirSync(dir, { recursive: true });
// Create git repo with commit history
run('git', ['init'], dir);
run('git', ['config', 'user.email', 'dev@example.com'], dir);
run('git', ['config', 'user.name', 'Dev'], dir);
fs.writeFileSync(path.join(dir, 'app.ts'), 'console.log("hello");\n');
run('git', ['add', 'app.ts'], dir);
run('git', ['commit', '-m', 'feat: initial app', '--date', '2026-03-14T09:00:00'], dir);
fs.writeFileSync(path.join(dir, 'auth.ts'), 'export function login() {}\n');
run('git', ['add', 'auth.ts'], dir);
run('git', ['commit', '-m', 'feat: add auth', '--date', '2026-03-15T10:00:00'], dir);
fs.writeFileSync(path.join(dir, 'test.ts'), 'test("it works", () => {});\n');
run('git', ['add', 'test.ts'], dir);
run('git', ['commit', '-m', 'test: add tests', '--date', '2026-03-16T11:00:00'], dir);
// Copy retro skill
fs.mkdirSync(path.join(dir, 'retro'), { recursive: true });
fs.copyFileSync(path.join(ROOT, 'retro', 'SKILL.md'), path.join(dir, 'retro', 'SKILL.md'));
const result = await runSkillTest({
prompt: `Read retro/SKILL.md for instructions on how to run a retrospective.
IMPORTANT: Follow the "Detect default branch" step first. Since there is no remote, gh will fail — fall back to main.
Then use the detected branch name for all git queries.
Run /retro for the last 7 days of this git repo. Skip any AskUserQuestion calls — this is non-interactive.
This is a local-only repo so use the local branch (main) instead of origin/main for all git log commands.
Write your retrospective to ${dir}/retro-output.md`,
workingDirectory: dir,
maxTurns: 25,
// 360s, not 240s: same runner-contention class as review-dashboard-via.
// /retro is a long multi-step flow — a clean pass measured 225s and the
// next CI run timed out at the 240s line (exitReason "timeout", 3/3
// attempts). Outer bun timeout below rises to 480s for headroom.
timeout: 360_000,
testName: 'retro-base-branch',
runId,
});
logCost('/retro base-branch', result);
recordE2E(evalCollector, '/retro default branch detection', 'Base branch detection', result, {
passed: ['success', 'error_max_turns'].includes(result.exitReason),
});
expect(['success', 'error_max_turns']).toContain(result.exitReason);
// Verify retro output was produced
const retroPath = path.join(dir, 'retro-output.md');
if (fs.existsSync(retroPath)) {
const content = fs.readFileSync(retroPath, 'utf-8');
expect(content.length).toBeGreaterThan(100);
}
}, 480_000);
});
// --- Retro E2E ---
describeIfSelected('Retro E2E', ['retro'], () => {
let retroDir: string;
beforeAll(() => {
retroDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-retro-'));
const run = (cmd: string, args: string[]) =>
spawnSync(cmd, args, { cwd: retroDir, stdio: 'pipe', timeout: 5000 });
// Create a git repo with varied commit history
run('git', ['init', '-b', 'main']);
run('git', ['config', 'user.email', 'dev@example.com']);
run('git', ['config', 'user.name', 'Dev']);
// Day 1 commits
fs.writeFileSync(path.join(retroDir, 'app.ts'), 'console.log("hello");\n');
run('git', ['add', 'app.ts']);
run('git', ['commit', '-m', 'feat: initial app setup', '--date', '2026-03-10T09:00:00']);
fs.writeFileSync(path.join(retroDir, 'auth.ts'), 'export function login() {}\n');
run('git', ['add', 'auth.ts']);
run('git', ['commit', '-m', 'feat: add auth module', '--date', '2026-03-10T11:00:00']);
// Day 2 commits
fs.writeFileSync(path.join(retroDir, 'app.ts'), 'import { login } from "./auth";\nconsole.log("hello");\nlogin();\n');
run('git', ['add', 'app.ts']);
run('git', ['commit', '-m', 'fix: wire up auth to app', '--date', '2026-03-11T10:00:00']);
fs.writeFileSync(path.join(retroDir, 'test.ts'), 'import { test } from "bun:test";\ntest("login", () => {});\n');
run('git', ['add', 'test.ts']);
run('git', ['commit', '-m', 'test: add login test', '--date', '2026-03-11T14:00:00']);
// Day 3 commits
fs.writeFileSync(path.join(retroDir, 'api.ts'), 'export function getUsers() { return []; }\n');
run('git', ['add', 'api.ts']);
run('git', ['commit', '-m', 'feat: add users API endpoint', '--date', '2026-03-12T09:30:00']);
fs.writeFileSync(path.join(retroDir, 'README.md'), '# My App\nA test application.\n');
run('git', ['add', 'README.md']);
run('git', ['commit', '-m', 'docs: add README', '--date', '2026-03-12T16:00:00']);
// Copy retro skill
fs.mkdirSync(path.join(retroDir, 'retro'), { recursive: true });
fs.copyFileSync(
path.join(ROOT, 'retro', 'SKILL.md'),
path.join(retroDir, 'retro', 'SKILL.md'),
);
});
afterAll(() => {
try { fs.rmSync(retroDir, { recursive: true, force: true }); } catch {}
});
testConcurrentIfSelected('retro', async () => {
const result = await runSkillTest({
prompt: `Read retro/SKILL.md for instructions on how to run a retrospective.
Run /retro for the last 7 days of this git repo. Skip any AskUserQuestion calls — this is non-interactive.
Write your retrospective report to ${retroDir}/retro-output.md
Analyze the git history and produce the narrative report as described in the SKILL.md.`,
workingDirectory: retroDir,
maxTurns: 30,
timeout: 300_000,
testName: 'retro',
runId,
model: 'claude-opus-4-7',
});
logCost('/retro', result);
recordE2E(evalCollector, '/retro', 'Retro E2E', result, {
passed: ['success', 'error_max_turns'].includes(result.exitReason),
});
// Accept error_max_turns — retro does many git commands to analyze history
expect(['success', 'error_max_turns']).toContain(result.exitReason);
// Verify the retro was written
const retroPath = path.join(retroDir, 'retro-output.md');
if (fs.existsSync(retroPath)) {
const retro = fs.readFileSync(retroPath, 'utf-8');
expect(retro.length).toBeGreaterThan(100);
}
}, 420_000);
});
// Module-level afterAll — finalize eval collector after all tests complete
afterAll(async () => {
await finalizeEvalCollector(evalCollector);
});

282
test/skill-e2e-review-attribution.test.ts Normal file
View File

@ -0,0 +1,282 @@
import { expect, beforeAll, afterAll } from 'bun:test';
import { runSkillTest } from './helpers/session-runner';
import {
ROOT, runId,
describeIfSelected, testConcurrentIfSelected,
logCost, recordE2E,
createEvalCollector, finalizeEvalCollector,
} from './helpers/e2e-helpers';
import { spawnSync } from 'child_process';
import * as fs from 'fs';
import * as path from 'path';
import * as os from 'os';
const evalCollector = createEvalCollector('e2e-review-attribution');
// --- Base branch detection smoke tests ---
describeIfSelected('Base branch detection', ['review-base-branch', 'ship-base-branch'], () => {
let baseBranchDir: string;
const run = (cmd: string, args: string[], cwd: string) =>
spawnSync(cmd, args, { cwd, stdio: 'pipe', timeout: 5000 });
beforeAll(() => {
baseBranchDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-basebranch-'));
});
afterAll(() => {
try { fs.rmSync(baseBranchDir, { recursive: true, force: true }); } catch {}
});
testConcurrentIfSelected('review-base-branch', async () => {
const dir = path.join(baseBranchDir, 'review-base');
fs.mkdirSync(dir, { recursive: true });
// Create git repo with a feature branch off main
run('git', ['init'], dir);
run('git', ['config', 'user.email', 'test@test.com'], dir);
run('git', ['config', 'user.name', 'Test'], dir);
fs.writeFileSync(path.join(dir, 'app.rb'), '# clean base\nclass App\nend\n');
run('git', ['add', 'app.rb'], dir);
run('git', ['commit', '-m', 'initial commit'], dir);
// Create feature branch with a change
run('git', ['checkout', '-b', 'feature/test-review'], dir);
fs.writeFileSync(path.join(dir, 'app.rb'), '# clean base\nclass App\n def hello; "world"; end\nend\n');
run('git', ['add', 'app.rb'], dir);
run('git', ['commit', '-m', 'feat: add hello method'], dir);
// Extract only Step 0 (base branch detection) + minimal review instructions
// Full SKILL.md is ~1500 lines — copying it causes the agent to spend all turns reading
const full = fs.readFileSync(path.join(ROOT, 'review', 'SKILL.md'), 'utf-8');
const step0Start = full.indexOf('## Step 0: Detect platform and base branch');
const step1Start = full.indexOf('## Step 1: Check branch');
const step1End = full.indexOf('---', step1Start + 10);
const extracted = full.slice(step0Start, step1End > step1Start ? step1End : step1Start + 500);
fs.writeFileSync(path.join(dir, 'review-SKILL.md'), extracted);
const result = await runSkillTest({
prompt: `You are in a git repo on a feature branch with changes.
Read review-SKILL.md for the base branch detection instructions.
IMPORTANT: Follow Step 0 to detect the base branch. Since there is no remote, gh commands will fail — fall back to main.
Then run git diff against the detected base branch and write a brief review.
Write your findings to ${dir}/review-output.md`,
workingDirectory: dir,
maxTurns: 15,
timeout: 90_000,
testName: 'review-base-branch',
runId,
});
logCost('/review base-branch', result);
recordE2E(evalCollector, '/review base branch detection', 'Base branch detection', result);
expect(result.exitReason).toBe('success');
// Verify the review used "base branch" language (from Step 0)
const toolOutputs = result.toolCalls.map(tc => tc.output || '').join('\n');
const allOutput = (result.output || '') + toolOutputs;
// The agent should have run git diff against main (the fallback)
const usedGitDiff = result.toolCalls.some(tc => {
if (tc.tool !== 'Bash') return false;
const cmd = typeof tc.input === 'string' ? tc.input : tc.input?.command || JSON.stringify(tc.input);
return cmd.includes('git diff');
});
expect(usedGitDiff).toBe(true);
}, 120_000);
testConcurrentIfSelected('ship-base-branch', async () => {
const dir = path.join(baseBranchDir, 'ship-base');
fs.mkdirSync(dir, { recursive: true });
// Create git repo with feature branch
run('git', ['init'], dir);
run('git', ['config', 'user.email', 'test@test.com'], dir);
run('git', ['config', 'user.name', 'Test'], dir);
fs.writeFileSync(path.join(dir, 'app.ts'), 'console.log("v1");\n');
run('git', ['add', 'app.ts'], dir);
run('git', ['commit', '-m', 'initial'], dir);
run('git', ['checkout', '-b', 'feature/ship-test'], dir);
fs.writeFileSync(path.join(dir, 'app.ts'), 'console.log("v2");\n');
run('git', ['add', 'app.ts'], dir);
run('git', ['commit', '-m', 'feat: update to v2'], dir);
// Extract only Step 0 (base branch detection) from ship/SKILL.md
// (copying the full 1900-line file causes agent context bloat and flaky timeouts)
const fullShipSkill = fs.readFileSync(path.join(ROOT, 'ship', 'SKILL.md'), 'utf-8');
const step0Start = fullShipSkill.indexOf('## Step 0: Detect platform and base branch');
const step0End = fullShipSkill.indexOf('## Step 1: Pre-flight');
const shipSection = fullShipSkill.slice(step0Start, step0End > step0Start ? step0End : undefined);
fs.writeFileSync(path.join(dir, 'ship-SKILL.md'), shipSection);
const result = await runSkillTest({
prompt: `Read ship-SKILL.md. It contains Step 0 (Detect base branch) from the ship workflow.
Run the base branch detection. Since there is no remote, gh commands will fail — fall back to main.
Then run git diff and git log against the detected base branch.
Write a summary to ${dir}/ship-preflight.md including:
- The detected base branch name
- The current branch name
- The diff stat against the base branch`,
workingDirectory: dir,
maxTurns: 18,
timeout: 150_000,
testName: 'ship-base-branch',
runId,
});
logCost('/ship base-branch', result);
recordE2E(evalCollector, '/ship base branch detection', 'Base branch detection', result);
expect(result.exitReason).toBe('success');
// Verify preflight output was written
const preflightPath = path.join(dir, 'ship-preflight.md');
if (fs.existsSync(preflightPath)) {
const content = fs.readFileSync(preflightPath, 'utf-8');
expect(content.length).toBeGreaterThan(20);
// Should mention the branch name
expect(content.toLowerCase()).toMatch(/main|base/);
}
// Verify no destructive actions — no push, no PR creation
const destructiveTools = result.toolCalls.filter(tc =>
tc.tool === 'Bash' && typeof tc.input === 'string' &&
(tc.input.includes('git push') || tc.input.includes('gh pr create'))
);
expect(destructiveTools).toHaveLength(0);
}, 180_000);
});
// --- Review Dashboard Via Attribution E2E ---
describeIfSelected('Review Dashboard Via Attribution', ['review-dashboard-via'], () => {
let dashDir: string;
beforeAll(() => {
dashDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-dashboard-via-'));
const run = (cmd: string, args: string[], cwd = dashDir) =>
spawnSync(cmd, args, { cwd, stdio: 'pipe', timeout: 5000 });
// Create git repo with feature branch
run('git', ['init', '-b', 'main']);
run('git', ['config', 'user.email', 'test@test.com']);
run('git', ['config', 'user.name', 'Test']);
fs.writeFileSync(path.join(dashDir, 'app.ts'), 'console.log("v1");\n');
run('git', ['add', 'app.ts']);
run('git', ['commit', '-m', 'initial']);
run('git', ['checkout', '-b', 'feature/dashboard-test']);
fs.writeFileSync(path.join(dashDir, 'app.ts'), 'console.log("v2");\n');
run('git', ['add', 'app.ts']);
run('git', ['commit', '-m', 'feat: update']);
// Get HEAD commit for review entries
const headResult = spawnSync('git', ['rev-parse', '--short', 'HEAD'], { cwd: dashDir, stdio: 'pipe' });
const commit = headResult.stdout.toString().trim();
// Pre-populate review log with autoplan-sourced entries
// gstack-review-read reads from ~/.gstack/projects/$SLUG/$BRANCH-reviews.jsonl
// For the test, we'll write a mock gstack-review-read script that returns our test data
const timestamp = new Date().toISOString().replace(/\.\d{3}Z$/, 'Z');
const reviewData = [
`{"skill":"plan-eng-review","timestamp":"${timestamp}","status":"clean","unresolved":0,"critical_gaps":0,"issues_found":0,"mode":"FULL_REVIEW","via":"autoplan","commit":"${commit}"}`,
`{"skill":"plan-ceo-review","timestamp":"${timestamp}","status":"clean","unresolved":0,"critical_gaps":0,"mode":"SELECTIVE_EXPANSION","via":"autoplan","commit":"${commit}"}`,
`{"skill":"codex-plan-review","timestamp":"${timestamp}","status":"clean","source":"codex","commit":"${commit}"}`,
].join('\n');
// Write a mock gstack-review-read that returns our test data
const mockBinDir = path.join(dashDir, '.mock-bin');
fs.mkdirSync(mockBinDir, { recursive: true });
fs.writeFileSync(path.join(mockBinDir, 'gstack-review-read'), [
'#!/usr/bin/env bash',
`echo '${reviewData.split('\n').join("'\necho '")}'`,
'echo "---CONFIG---"',
'echo "false"',
'echo "---HEAD---"',
`echo "${commit}"`,
].join('\n'));
fs.chmodSync(path.join(mockBinDir, 'gstack-review-read'), 0o755);
// Extract only the Review Readiness Dashboard section from ship/SKILL.md
// (copying the full 1900-line file causes agent context bloat and timeouts)
const fullSkill = fs.readFileSync(path.join(ROOT, 'ship', 'SKILL.md'), 'utf-8');
const dashStart = fullSkill.indexOf('## Review Readiness Dashboard');
const dashEnd = fullSkill.indexOf('\n---\n', dashStart);
const dashSection = fullSkill.slice(dashStart, dashEnd > dashStart ? dashEnd : undefined);
fs.writeFileSync(path.join(dashDir, 'ship-SKILL.md'), dashSection);
});
afterAll(() => {
try { fs.rmSync(dashDir, { recursive: true, force: true }); } catch {}
});
testConcurrentIfSelected('review-dashboard-via', async () => {
const mockBinDir = path.join(dashDir, '.mock-bin');
const result = await runSkillTest({
prompt: `Read ship-SKILL.md. You only need to run the Review Readiness Dashboard section.
Instead of running ~/.claude/skills/gstack/bin/gstack-review-read, run this mock: ${mockBinDir}/gstack-review-read
Parse the output and display the dashboard table. Pay attention to:
1. The "via" field in entries — show source attribution (e.g., "via /autoplan")
2. The codex-plan-review entry — it should populate the Outside Voice row
3. Since Eng Review IS clear, there should be NO gate blocking — just display the dashboard
Skip the preamble, lake intro, telemetry, and all other ship steps.
Write the dashboard output to ${dashDir}/dashboard-output.md`,
workingDirectory: dashDir,
maxTurns: 12,
// 300s, not 180s: on a saturated CI runner this file's concurrent
// sessions queue behind each other and session STARTUP can eat the
// whole budget — observed as deterministic timeout at 0 turns/$0.00
// for exactly 180s across 3 attempts (PR #2472 CI + its baseline),
// while the 240s-budget tests in the same job passed. Outer bun
// timeout below rises to 360s to keep headroom over the inner budget.
timeout: 300_000,
testName: 'review-dashboard-via',
runId,
});
logCost('/ship dashboard-via', result);
recordE2E(evalCollector, '/ship review dashboard via attribution', 'Dashboard via field', result);
expect(result.exitReason).toBe('success');
// Check dashboard output for via attribution
const dashPath = path.join(dashDir, 'dashboard-output.md');
const allOutput = [
result.output || '',
...result.toolCalls.map(tc => tc.output || ''),
].join('\n').toLowerCase();
// Verify via attribution appears somewhere (conversation or file)
let dashContent = '';
if (fs.existsSync(dashPath)) {
dashContent = fs.readFileSync(dashPath, 'utf-8').toLowerCase();
}
const combined = allOutput + dashContent;
// Should mention autoplan attribution
expect(combined).toMatch(/autoplan/);
// Should show eng review as CLEAR (it has a clean entry)
expect(combined).toMatch(/clear/i);
// Should NOT contain AskUserQuestion gate (no blocking)
const gateQuestions = result.toolCalls.filter(tc =>
tc.tool === 'mcp__conductor__AskUserQuestion' ||
(tc.tool === 'AskUserQuestion')
);
// Ship dashboard should not gate when eng review is clear
expect(gateQuestions).toHaveLength(0);
}, 360_000);
});
// Module-level afterAll — finalize eval collector after all tests complete
afterAll(async () => {
await finalizeEvalCollector(evalCollector);
});

412
test/skill-e2e-review.test.ts
View File

@ -252,414 +252,10 @@ Important: The design checklist should catch issues like blacklisted fonts, smal
}, 300_000);
});
// --- Base branch detection smoke tests ---
describeIfSelected('Base branch detection', ['review-base-branch', 'ship-base-branch', 'retro-base-branch'], () => {
let baseBranchDir: string;
const run = (cmd: string, args: string[], cwd: string) =>
spawnSync(cmd, args, { cwd, stdio: 'pipe', timeout: 5000 });
beforeAll(() => {
baseBranchDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-basebranch-'));
});
afterAll(() => {
try { fs.rmSync(baseBranchDir, { recursive: true, force: true }); } catch {}
});
testConcurrentIfSelected('review-base-branch', async () => {
const dir = path.join(baseBranchDir, 'review-base');
fs.mkdirSync(dir, { recursive: true });
// Create git repo with a feature branch off main
run('git', ['init'], dir);
run('git', ['config', 'user.email', 'test@test.com'], dir);
run('git', ['config', 'user.name', 'Test'], dir);
fs.writeFileSync(path.join(dir, 'app.rb'), '# clean base\nclass App\nend\n');
run('git', ['add', 'app.rb'], dir);
run('git', ['commit', '-m', 'initial commit'], dir);
// Create feature branch with a change
run('git', ['checkout', '-b', 'feature/test-review'], dir);
fs.writeFileSync(path.join(dir, 'app.rb'), '# clean base\nclass App\n def hello; "world"; end\nend\n');
run('git', ['add', 'app.rb'], dir);
run('git', ['commit', '-m', 'feat: add hello method'], dir);
// Extract only Step 0 (base branch detection) + minimal review instructions
// Full SKILL.md is ~1500 lines — copying it causes the agent to spend all turns reading
const full = fs.readFileSync(path.join(ROOT, 'review', 'SKILL.md'), 'utf-8');
const step0Start = full.indexOf('## Step 0: Detect platform and base branch');
const step1Start = full.indexOf('## Step 1: Check branch');
const step1End = full.indexOf('---', step1Start + 10);
const extracted = full.slice(step0Start, step1End > step1Start ? step1End : step1Start + 500);
fs.writeFileSync(path.join(dir, 'review-SKILL.md'), extracted);
const result = await runSkillTest({
prompt: `You are in a git repo on a feature branch with changes.
Read review-SKILL.md for the base branch detection instructions.
IMPORTANT: Follow Step 0 to detect the base branch. Since there is no remote, gh commands will fail — fall back to main.
Then run git diff against the detected base branch and write a brief review.
Write your findings to ${dir}/review-output.md`,
workingDirectory: dir,
maxTurns: 15,
timeout: 90_000,
testName: 'review-base-branch',
runId,
});
logCost('/review base-branch', result);
recordE2E(evalCollector, '/review base branch detection', 'Base branch detection', result);
expect(result.exitReason).toBe('success');
// Verify the review used "base branch" language (from Step 0)
const toolOutputs = result.toolCalls.map(tc => tc.output || '').join('\n');
const allOutput = (result.output || '') + toolOutputs;
// The agent should have run git diff against main (the fallback)
const usedGitDiff = result.toolCalls.some(tc => {
if (tc.tool !== 'Bash') return false;
const cmd = typeof tc.input === 'string' ? tc.input : tc.input?.command || JSON.stringify(tc.input);
return cmd.includes('git diff');
});
expect(usedGitDiff).toBe(true);
}, 120_000);
testConcurrentIfSelected('ship-base-branch', async () => {
const dir = path.join(baseBranchDir, 'ship-base');
fs.mkdirSync(dir, { recursive: true });
// Create git repo with feature branch
run('git', ['init'], dir);
run('git', ['config', 'user.email', 'test@test.com'], dir);
run('git', ['config', 'user.name', 'Test'], dir);
fs.writeFileSync(path.join(dir, 'app.ts'), 'console.log("v1");\n');
run('git', ['add', 'app.ts'], dir);
run('git', ['commit', '-m', 'initial'], dir);
run('git', ['checkout', '-b', 'feature/ship-test'], dir);
fs.writeFileSync(path.join(dir, 'app.ts'), 'console.log("v2");\n');
run('git', ['add', 'app.ts'], dir);
run('git', ['commit', '-m', 'feat: update to v2'], dir);
// Extract only Step 0 (base branch detection) from ship/SKILL.md
// (copying the full 1900-line file causes agent context bloat and flaky timeouts)
const fullShipSkill = fs.readFileSync(path.join(ROOT, 'ship', 'SKILL.md'), 'utf-8');
const step0Start = fullShipSkill.indexOf('## Step 0: Detect platform and base branch');
const step0End = fullShipSkill.indexOf('## Step 1: Pre-flight');
const shipSection = fullShipSkill.slice(step0Start, step0End > step0Start ? step0End : undefined);
fs.writeFileSync(path.join(dir, 'ship-SKILL.md'), shipSection);
const result = await runSkillTest({
prompt: `Read ship-SKILL.md. It contains Step 0 (Detect base branch) from the ship workflow.
Run the base branch detection. Since there is no remote, gh commands will fail — fall back to main.
Then run git diff and git log against the detected base branch.
Write a summary to ${dir}/ship-preflight.md including:
- The detected base branch name
- The current branch name
- The diff stat against the base branch`,
workingDirectory: dir,
maxTurns: 18,
timeout: 150_000,
testName: 'ship-base-branch',
runId,
});
logCost('/ship base-branch', result);
recordE2E(evalCollector, '/ship base branch detection', 'Base branch detection', result);
expect(result.exitReason).toBe('success');
// Verify preflight output was written
const preflightPath = path.join(dir, 'ship-preflight.md');
if (fs.existsSync(preflightPath)) {
const content = fs.readFileSync(preflightPath, 'utf-8');
expect(content.length).toBeGreaterThan(20);
// Should mention the branch name
expect(content.toLowerCase()).toMatch(/main|base/);
}
// Verify no destructive actions — no push, no PR creation
const destructiveTools = result.toolCalls.filter(tc =>
tc.tool === 'Bash' && typeof tc.input === 'string' &&
(tc.input.includes('git push') || tc.input.includes('gh pr create'))
);
expect(destructiveTools).toHaveLength(0);
}, 180_000);
testConcurrentIfSelected('retro-base-branch', async () => {
const dir = path.join(baseBranchDir, 'retro-base');
fs.mkdirSync(dir, { recursive: true });
// Create git repo with commit history
run('git', ['init'], dir);
run('git', ['config', 'user.email', 'dev@example.com'], dir);
run('git', ['config', 'user.name', 'Dev'], dir);
fs.writeFileSync(path.join(dir, 'app.ts'), 'console.log("hello");\n');
run('git', ['add', 'app.ts'], dir);
run('git', ['commit', '-m', 'feat: initial app', '--date', '2026-03-14T09:00:00'], dir);
fs.writeFileSync(path.join(dir, 'auth.ts'), 'export function login() {}\n');
run('git', ['add', 'auth.ts'], dir);
run('git', ['commit', '-m', 'feat: add auth', '--date', '2026-03-15T10:00:00'], dir);
fs.writeFileSync(path.join(dir, 'test.ts'), 'test("it works", () => {});\n');
run('git', ['add', 'test.ts'], dir);
run('git', ['commit', '-m', 'test: add tests', '--date', '2026-03-16T11:00:00'], dir);
// Copy retro skill
fs.mkdirSync(path.join(dir, 'retro'), { recursive: true });
fs.copyFileSync(path.join(ROOT, 'retro', 'SKILL.md'), path.join(dir, 'retro', 'SKILL.md'));
const result = await runSkillTest({
prompt: `Read retro/SKILL.md for instructions on how to run a retrospective.
IMPORTANT: Follow the "Detect default branch" step first. Since there is no remote, gh will fail — fall back to main.
Then use the detected branch name for all git queries.
Run /retro for the last 7 days of this git repo. Skip any AskUserQuestion calls — this is non-interactive.
This is a local-only repo so use the local branch (main) instead of origin/main for all git log commands.
Write your retrospective to ${dir}/retro-output.md`,
workingDirectory: dir,
maxTurns: 25,
// 360s, not 240s: same runner-contention class as review-dashboard-via.
// /retro is a long multi-step flow — a clean pass measured 225s and the
// next CI run timed out at the 240s line (exitReason "timeout", 3/3
// attempts). Outer bun timeout below rises to 480s for headroom.
timeout: 360_000,
testName: 'retro-base-branch',
runId,
});
logCost('/retro base-branch', result);
recordE2E(evalCollector, '/retro default branch detection', 'Base branch detection', result, {
passed: ['success', 'error_max_turns'].includes(result.exitReason),
});
expect(['success', 'error_max_turns']).toContain(result.exitReason);
// Verify retro output was produced
const retroPath = path.join(dir, 'retro-output.md');
if (fs.existsSync(retroPath)) {
const content = fs.readFileSync(retroPath, 'utf-8');
expect(content.length).toBeGreaterThan(100);
}
}, 480_000);
});
// --- Retro E2E ---
describeIfSelected('Retro E2E', ['retro'], () => {
let retroDir: string;
beforeAll(() => {
retroDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-retro-'));
const run = (cmd: string, args: string[]) =>
spawnSync(cmd, args, { cwd: retroDir, stdio: 'pipe', timeout: 5000 });
// Create a git repo with varied commit history
run('git', ['init', '-b', 'main']);
run('git', ['config', 'user.email', 'dev@example.com']);
run('git', ['config', 'user.name', 'Dev']);
// Day 1 commits
fs.writeFileSync(path.join(retroDir, 'app.ts'), 'console.log("hello");\n');
run('git', ['add', 'app.ts']);
run('git', ['commit', '-m', 'feat: initial app setup', '--date', '2026-03-10T09:00:00']);
fs.writeFileSync(path.join(retroDir, 'auth.ts'), 'export function login() {}\n');
run('git', ['add', 'auth.ts']);
run('git', ['commit', '-m', 'feat: add auth module', '--date', '2026-03-10T11:00:00']);
// Day 2 commits
fs.writeFileSync(path.join(retroDir, 'app.ts'), 'import { login } from "./auth";\nconsole.log("hello");\nlogin();\n');
run('git', ['add', 'app.ts']);
run('git', ['commit', '-m', 'fix: wire up auth to app', '--date', '2026-03-11T10:00:00']);
fs.writeFileSync(path.join(retroDir, 'test.ts'), 'import { test } from "bun:test";\ntest("login", () => {});\n');
run('git', ['add', 'test.ts']);
run('git', ['commit', '-m', 'test: add login test', '--date', '2026-03-11T14:00:00']);
// Day 3 commits
fs.writeFileSync(path.join(retroDir, 'api.ts'), 'export function getUsers() { return []; }\n');
run('git', ['add', 'api.ts']);
run('git', ['commit', '-m', 'feat: add users API endpoint', '--date', '2026-03-12T09:30:00']);
fs.writeFileSync(path.join(retroDir, 'README.md'), '# My App\nA test application.\n');
run('git', ['add', 'README.md']);
run('git', ['commit', '-m', 'docs: add README', '--date', '2026-03-12T16:00:00']);
// Copy retro skill
fs.mkdirSync(path.join(retroDir, 'retro'), { recursive: true });
fs.copyFileSync(
path.join(ROOT, 'retro', 'SKILL.md'),
path.join(retroDir, 'retro', 'SKILL.md'),
);
});
afterAll(() => {
try { fs.rmSync(retroDir, { recursive: true, force: true }); } catch {}
});
testConcurrentIfSelected('retro', async () => {
const result = await runSkillTest({
prompt: `Read retro/SKILL.md for instructions on how to run a retrospective.
Run /retro for the last 7 days of this git repo. Skip any AskUserQuestion calls — this is non-interactive.
Write your retrospective report to ${retroDir}/retro-output.md
Analyze the git history and produce the narrative report as described in the SKILL.md.`,
workingDirectory: retroDir,
maxTurns: 30,
timeout: 300_000,
testName: 'retro',
runId,
model: 'claude-opus-4-7',
});
logCost('/retro', result);
recordE2E(evalCollector, '/retro', 'Retro E2E', result, {
passed: ['success', 'error_max_turns'].includes(result.exitReason),
});
// Accept error_max_turns — retro does many git commands to analyze history
expect(['success', 'error_max_turns']).toContain(result.exitReason);
// Verify the retro was written
const retroPath = path.join(retroDir, 'retro-output.md');
if (fs.existsSync(retroPath)) {
const retro = fs.readFileSync(retroPath, 'utf-8');
expect(retro.length).toBeGreaterThan(100);
}
}, 420_000);
});
// --- Review Dashboard Via Attribution E2E ---
describeIfSelected('Review Dashboard Via Attribution', ['review-dashboard-via'], () => {
let dashDir: string;
beforeAll(() => {
dashDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-dashboard-via-'));
const run = (cmd: string, args: string[], cwd = dashDir) =>
spawnSync(cmd, args, { cwd, stdio: 'pipe', timeout: 5000 });
// Create git repo with feature branch
run('git', ['init', '-b', 'main']);
run('git', ['config', 'user.email', 'test@test.com']);
run('git', ['config', 'user.name', 'Test']);
fs.writeFileSync(path.join(dashDir, 'app.ts'), 'console.log("v1");\n');
run('git', ['add', 'app.ts']);
run('git', ['commit', '-m', 'initial']);
run('git', ['checkout', '-b', 'feature/dashboard-test']);
fs.writeFileSync(path.join(dashDir, 'app.ts'), 'console.log("v2");\n');
run('git', ['add', 'app.ts']);
run('git', ['commit', '-m', 'feat: update']);
// Get HEAD commit for review entries
const headResult = spawnSync('git', ['rev-parse', '--short', 'HEAD'], { cwd: dashDir, stdio: 'pipe' });
const commit = headResult.stdout.toString().trim();
// Pre-populate review log with autoplan-sourced entries
// gstack-review-read reads from ~/.gstack/projects/$SLUG/$BRANCH-reviews.jsonl
// For the test, we'll write a mock gstack-review-read script that returns our test data
const timestamp = new Date().toISOString().replace(/\.\d{3}Z$/, 'Z');
const reviewData = [
`{"skill":"plan-eng-review","timestamp":"${timestamp}","status":"clean","unresolved":0,"critical_gaps":0,"issues_found":0,"mode":"FULL_REVIEW","via":"autoplan","commit":"${commit}"}`,
`{"skill":"plan-ceo-review","timestamp":"${timestamp}","status":"clean","unresolved":0,"critical_gaps":0,"mode":"SELECTIVE_EXPANSION","via":"autoplan","commit":"${commit}"}`,
`{"skill":"codex-plan-review","timestamp":"${timestamp}","status":"clean","source":"codex","commit":"${commit}"}`,
].join('\n');
// Write a mock gstack-review-read that returns our test data
const mockBinDir = path.join(dashDir, '.mock-bin');
fs.mkdirSync(mockBinDir, { recursive: true });
fs.writeFileSync(path.join(mockBinDir, 'gstack-review-read'), [
'#!/usr/bin/env bash',
`echo '${reviewData.split('\n').join("'\necho '")}'`,
'echo "---CONFIG---"',
'echo "false"',
'echo "---HEAD---"',
`echo "${commit}"`,
].join('\n'));
fs.chmodSync(path.join(mockBinDir, 'gstack-review-read'), 0o755);
// Extract only the Review Readiness Dashboard section from ship/SKILL.md
// (copying the full 1900-line file causes agent context bloat and timeouts)
const fullSkill = fs.readFileSync(path.join(ROOT, 'ship', 'SKILL.md'), 'utf-8');
const dashStart = fullSkill.indexOf('## Review Readiness Dashboard');
const dashEnd = fullSkill.indexOf('\n---\n', dashStart);
const dashSection = fullSkill.slice(dashStart, dashEnd > dashStart ? dashEnd : undefined);
fs.writeFileSync(path.join(dashDir, 'ship-SKILL.md'), dashSection);
});
afterAll(() => {
try { fs.rmSync(dashDir, { recursive: true, force: true }); } catch {}
});
testConcurrentIfSelected('review-dashboard-via', async () => {
const mockBinDir = path.join(dashDir, '.mock-bin');
const result = await runSkillTest({
prompt: `Read ship-SKILL.md. You only need to run the Review Readiness Dashboard section.
Instead of running ~/.claude/skills/gstack/bin/gstack-review-read, run this mock: ${mockBinDir}/gstack-review-read
Parse the output and display the dashboard table. Pay attention to:
1. The "via" field in entries — show source attribution (e.g., "via /autoplan")
2. The codex-plan-review entry — it should populate the Outside Voice row
3. Since Eng Review IS clear, there should be NO gate blocking — just display the dashboard
Skip the preamble, lake intro, telemetry, and all other ship steps.
Write the dashboard output to ${dashDir}/dashboard-output.md`,
workingDirectory: dashDir,
maxTurns: 12,
// 300s, not 180s: on a saturated CI runner this file's concurrent
// sessions queue behind each other and session STARTUP can eat the
// whole budget — observed as deterministic timeout at 0 turns/$0.00
// for exactly 180s across 3 attempts (PR #2472 CI + its baseline),
// while the 240s-budget tests in the same job passed. Outer bun
// timeout below rises to 360s to keep headroom over the inner budget.
timeout: 300_000,
testName: 'review-dashboard-via',
runId,
});
logCost('/ship dashboard-via', result);
recordE2E(evalCollector, '/ship review dashboard via attribution', 'Dashboard via field', result);
expect(result.exitReason).toBe('success');
// Check dashboard output for via attribution
const dashPath = path.join(dashDir, 'dashboard-output.md');
const allOutput = [
result.output || '',
...result.toolCalls.map(tc => tc.output || ''),
].join('\n').toLowerCase();
// Verify via attribution appears somewhere (conversation or file)
let dashContent = '';
if (fs.existsSync(dashPath)) {
dashContent = fs.readFileSync(dashPath, 'utf-8').toLowerCase();
}
const combined = allOutput + dashContent;
// Should mention autoplan attribution
expect(combined).toMatch(/autoplan/);
// Should show eng review as CLEAR (it has a clean entry)
expect(combined).toMatch(/clear/i);
// Should NOT contain AskUserQuestion gate (no blocking)
const gateQuestions = result.toolCalls.filter(tc =>
tc.tool === 'mcp__conductor__AskUserQuestion' ||
(tc.tool === 'AskUserQuestion')
);
// Ship dashboard should not gate when eng review is clear
expect(gateQuestions).toHaveLength(0);
}, 360_000);
});
// Base branch detection tests for review/ship + the Review Dashboard Via
// Attribution describe live in test/skill-e2e-review-attribution.test.ts.
// Retro tests (retro, retro-base-branch) live in test/skill-e2e-retro.test.ts.
// Split so CI's per-file matrix can run them in parallel.
// Module-level afterAll — finalize eval collector after all tests complete
afterAll(async () => {