mirror of
https://github.com/garrytan/gstack.git
synced 2026-05-01 19:25:10 +02:00
8115951284
* refactor: remove dead contributor mode, replace with operational self-improvement slot Contributor mode never fired in 18 days of heavy use (required manual opt-in via gstack-config, gated behind _CONTRIB=true, wrote disconnected markdown). Removes: generateContributorMode(), _CONTRIB bash var, 2 E2E tests, touchfile entry, doc references. Cleans up skip-lists in plan-ceo-review, autoplan, review resolver, and document-release templates. The operational self-improvement system (next commit) replaces this slot with automatic learning capture that requires no opt-in. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * feat: operational self-improvement — every skill learns from failures Adds universal operational learning capture to the preamble completion protocol. At the end of every skill session, the agent reflects on CLI failures, wrong approaches, and project quirks, logging them as type "operational" to the learnings JSONL. Future sessions surface these automatically. - generateCompletionStatus(ctx) now includes operational capture section - Preamble bash shows top 3 learnings inline when count > 5 - New "operational" type in generateLearningsLog alongside pattern/pitfall/etc - Updated unit tests + operational seed entry in learnings E2E Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * feat: wire learnings into all insight-producing skills Adds LEARNINGS_SEARCH and/or LEARNINGS_LOG to 10 skill templates that produce reusable insights but were previously disconnected from the learning system: - office-hours, plan-ceo-review, plan-eng-review: add LOG (had SEARCH) - plan-design-review: add both SEARCH + LOG (had neither) - design-review, design-consultation, cso, qa, qa-only: add both - retro: add SEARCH (had LOG) 13 skills now fully participate in the learning loop (read + write). Every review, QA, investigation, and design session both consults prior learnings and contributes new ones. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * test: add operational-learning E2E test (gate-tier) Validates the write path: agent encounters a CLI failure, logs an operational learning to JSONL via gstack-learnings-log. Replaces the removed contributor-mode E2E test. Setup: temp git repo, copy bin scripts, set GSTACK_HOME. Prompt: simulated npm test failure needing --experimental-vm-modules. Assert: learnings.jsonl exists with type=operational entry. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix: learnings-show E2E slug mismatch — seed at computed slug, not hardcoded The test seeded learnings at projects/test-project/ but gstack-slug computes the slug from basename(workDir) when no git remote exists. The agent's search looked at the wrong path and found nothing. Fix: compute slug the same way gstack-slug does (basename + sanitize) and seed the learnings there. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * chore: bump version and changelog (v0.13.8.0) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
359 lines
14 KiB
TypeScript
359 lines
14 KiB
TypeScript
import { describe, test, expect, beforeAll, afterAll } from 'bun:test';
|
|
import { runSkillTest } from './helpers/session-runner';
|
|
import {
|
|
ROOT, browseBin, runId, evalsEnabled,
|
|
describeIfSelected, testConcurrentIfSelected,
|
|
copyDirSync, setupBrowseShims, logCost, recordE2E,
|
|
createEvalCollector, finalizeEvalCollector,
|
|
} from './helpers/e2e-helpers';
|
|
import { startTestServer } from '../browse/test/test-server';
|
|
import { spawnSync } from 'child_process';
|
|
import * as fs from 'fs';
|
|
import * as path from 'path';
|
|
import * as os from 'os';
|
|
|
|
const evalCollector = createEvalCollector('e2e-browse');
|
|
|
|
let testServer: ReturnType<typeof startTestServer>;
|
|
let tmpDir: string;
|
|
|
|
describeIfSelected('Skill E2E tests', [
|
|
'browse-basic', 'browse-snapshot', 'skillmd-setup-discovery',
|
|
'skillmd-no-local-binary', 'skillmd-outside-git', 'session-awareness',
|
|
'operational-learning',
|
|
], () => {
|
|
beforeAll(() => {
|
|
testServer = startTestServer();
|
|
tmpDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-'));
|
|
setupBrowseShims(tmpDir);
|
|
|
|
// Pre-warm the browse server so Chromium is already launched for tests.
|
|
// In CI, Chromium can take 10-20s to launch (Docker + --no-sandbox).
|
|
spawnSync(browseBin, ['goto', testServer.url], { cwd: tmpDir, timeout: 30000, stdio: 'pipe' });
|
|
}, 45_000);
|
|
|
|
afterAll(() => {
|
|
testServer?.server?.stop();
|
|
try { fs.rmSync(tmpDir, { recursive: true, force: true }); } catch {}
|
|
});
|
|
|
|
testConcurrentIfSelected('browse-basic', async () => {
|
|
const result = await runSkillTest({
|
|
prompt: `You have a browse binary at ${browseBin}. Assign it to B variable and run these commands in sequence:
|
|
1. $B goto ${testServer.url}
|
|
2. $B snapshot -i
|
|
3. $B text
|
|
4. $B screenshot /tmp/skill-e2e-test.png
|
|
Report the results of each command.`,
|
|
workingDirectory: tmpDir,
|
|
maxTurns: 7,
|
|
timeout: 60_000,
|
|
testName: 'browse-basic',
|
|
runId,
|
|
});
|
|
|
|
logCost('browse basic', result);
|
|
recordE2E(evalCollector, 'browse basic commands', 'Skill E2E tests', result);
|
|
expect(result.browseErrors).toHaveLength(0);
|
|
expect(result.exitReason).toBe('success');
|
|
}, 90_000);
|
|
|
|
testConcurrentIfSelected('browse-snapshot', async () => {
|
|
const result = await runSkillTest({
|
|
prompt: `You have a browse binary at ${browseBin}. Assign it to B variable and run:
|
|
1. $B goto ${testServer.url}
|
|
2. $B snapshot -i
|
|
3. $B snapshot -c
|
|
4. $B snapshot -D
|
|
5. $B snapshot -i -a -o /tmp/skill-e2e-annotated.png
|
|
Report what each command returned.`,
|
|
workingDirectory: tmpDir,
|
|
maxTurns: 7,
|
|
timeout: 60_000,
|
|
testName: 'browse-snapshot',
|
|
runId,
|
|
});
|
|
|
|
logCost('browse snapshot', result);
|
|
recordE2E(evalCollector, 'browse snapshot flags', 'Skill E2E tests', result);
|
|
// browseErrors can include false positives from hallucinated paths (e.g. "baltimore" vs "bangalore")
|
|
if (result.browseErrors.length > 0) {
|
|
console.warn('Browse errors (non-fatal):', result.browseErrors);
|
|
}
|
|
expect(result.exitReason).toBe('success');
|
|
}, 90_000);
|
|
|
|
testConcurrentIfSelected('skillmd-setup-discovery', async () => {
|
|
const skillMd = fs.readFileSync(path.join(ROOT, 'SKILL.md'), 'utf-8');
|
|
const setupStart = skillMd.indexOf('## SETUP');
|
|
const setupEnd = skillMd.indexOf('## IMPORTANT');
|
|
const setupBlock = skillMd.slice(setupStart, setupEnd);
|
|
|
|
// Guard: verify we extracted a valid setup block
|
|
expect(setupBlock).toContain('browse/dist/browse');
|
|
|
|
const result = await runSkillTest({
|
|
prompt: `Follow these instructions to find the browse binary and run a basic command.
|
|
|
|
${setupBlock}
|
|
|
|
After finding the binary, run: $B goto ${testServer.url}
|
|
Then run: $B text
|
|
Report whether it worked.`,
|
|
workingDirectory: tmpDir,
|
|
maxTurns: 10,
|
|
timeout: 60_000,
|
|
testName: 'skillmd-setup-discovery',
|
|
runId,
|
|
});
|
|
|
|
recordE2E(evalCollector, 'SKILL.md setup block discovery', 'Skill E2E tests', result);
|
|
expect(result.browseErrors).toHaveLength(0);
|
|
expect(result.exitReason).toBe('success');
|
|
}, 90_000);
|
|
|
|
testConcurrentIfSelected('skillmd-no-local-binary', async () => {
|
|
// Create a tmpdir with no browse binary — no local .claude/skills/gstack/browse/dist/browse
|
|
const emptyDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-empty-'));
|
|
|
|
const skillMd = fs.readFileSync(path.join(ROOT, 'SKILL.md'), 'utf-8');
|
|
const setupStart = skillMd.indexOf('## SETUP');
|
|
const setupEnd = skillMd.indexOf('## IMPORTANT');
|
|
const setupBlock = skillMd.slice(setupStart, setupEnd);
|
|
|
|
const result = await runSkillTest({
|
|
prompt: `Follow these instructions exactly. Run the bash code block below and report what it outputs.
|
|
|
|
${setupBlock}
|
|
|
|
Report the exact output. Do NOT try to fix or install anything — just report what you see.`,
|
|
workingDirectory: emptyDir,
|
|
maxTurns: 5,
|
|
timeout: 30_000,
|
|
testName: 'skillmd-no-local-binary',
|
|
runId,
|
|
});
|
|
|
|
// Setup block should either find the global binary (READY) or show NEEDS_SETUP.
|
|
// On dev machines with gstack installed globally, the fallback path
|
|
// ~/.claude/skills/gstack/browse/dist/browse exists, so we get READY.
|
|
// The important thing is it doesn't crash or give a confusing error.
|
|
const allText = result.output || '';
|
|
recordE2E(evalCollector, 'SKILL.md setup block (no local binary)', 'Skill E2E tests', result);
|
|
expect(allText).toMatch(/READY|NEEDS_SETUP/);
|
|
expect(result.exitReason).toBe('success');
|
|
|
|
// Clean up
|
|
try { fs.rmSync(emptyDir, { recursive: true, force: true }); } catch {}
|
|
}, 60_000);
|
|
|
|
testConcurrentIfSelected('skillmd-outside-git', async () => {
|
|
// Create a tmpdir outside any git repo
|
|
const nonGitDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-nogit-'));
|
|
|
|
const skillMd = fs.readFileSync(path.join(ROOT, 'SKILL.md'), 'utf-8');
|
|
const setupStart = skillMd.indexOf('## SETUP');
|
|
const setupEnd = skillMd.indexOf('## IMPORTANT');
|
|
const setupBlock = skillMd.slice(setupStart, setupEnd);
|
|
|
|
const result = await runSkillTest({
|
|
prompt: `Follow these instructions exactly. Run the bash code block below and report what it outputs.
|
|
|
|
${setupBlock}
|
|
|
|
Report the exact output — either "READY: <path>" or "NEEDS_SETUP".`,
|
|
workingDirectory: nonGitDir,
|
|
maxTurns: 5,
|
|
timeout: 30_000,
|
|
testName: 'skillmd-outside-git',
|
|
runId,
|
|
});
|
|
|
|
// Should either find global binary (READY) or show NEEDS_SETUP — not crash
|
|
const allText = result.output || '';
|
|
recordE2E(evalCollector, 'SKILL.md outside git repo', 'Skill E2E tests', result);
|
|
expect(allText).toMatch(/READY|NEEDS_SETUP/);
|
|
|
|
// Clean up
|
|
try { fs.rmSync(nonGitDir, { recursive: true, force: true }); } catch {}
|
|
}, 60_000);
|
|
|
|
testConcurrentIfSelected('operational-learning', async () => {
|
|
const opDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-oplearn-'));
|
|
const gstackHome = path.join(opDir, '.gstack-home');
|
|
|
|
// Init git repo
|
|
const run = (cmd: string, args: string[]) =>
|
|
spawnSync(cmd, args, { cwd: opDir, stdio: 'pipe', timeout: 5000 });
|
|
run('git', ['init', '-b', 'main']);
|
|
run('git', ['config', 'user.email', 'test@test.com']);
|
|
run('git', ['config', 'user.name', 'Test']);
|
|
fs.writeFileSync(path.join(opDir, 'app.ts'), 'console.log("hello");\n');
|
|
run('git', ['add', '.']);
|
|
run('git', ['commit', '-m', 'initial']);
|
|
|
|
// Copy bin scripts
|
|
const binDir = path.join(opDir, 'bin');
|
|
fs.mkdirSync(binDir, { recursive: true });
|
|
for (const script of ['gstack-learnings-log', 'gstack-slug']) {
|
|
fs.copyFileSync(path.join(ROOT, 'bin', script), path.join(binDir, script));
|
|
fs.chmodSync(path.join(binDir, script), 0o755);
|
|
}
|
|
|
|
// gstack-learnings-log will create the project dir automatically via gstack-slug
|
|
|
|
const result = await runSkillTest({
|
|
prompt: `You just ran \`npm test\` in this project and it failed with this error:
|
|
|
|
Error: --experimental-vm-modules flag is required for ESM support in this project.
|
|
Run: npm test --experimental-vm-modules
|
|
|
|
Per the Operational Self-Improvement instructions below, log an operational learning about this failure.
|
|
|
|
## Operational Self-Improvement
|
|
|
|
Before completing, reflect on this session:
|
|
- Did any commands fail unexpectedly?
|
|
|
|
If yes, log an operational learning for future sessions:
|
|
|
|
\`\`\`bash
|
|
GSTACK_HOME="${gstackHome}" ${binDir}/gstack-learnings-log '{"skill":"qa","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
|
|
\`\`\`
|
|
|
|
Replace SHORT_KEY with a kebab-case key like "esm-vm-modules-flag".
|
|
Replace DESCRIPTION with a one-sentence description of what you learned.
|
|
Replace N with a confidence score 1-10.
|
|
|
|
Log the operational learning now. Then say what you logged.`,
|
|
workingDirectory: opDir,
|
|
maxTurns: 5,
|
|
timeout: 30_000,
|
|
testName: 'operational-learning',
|
|
runId,
|
|
});
|
|
|
|
logCost('operational learning', result);
|
|
|
|
const exitOk = ['success', 'error_max_turns'].includes(result.exitReason);
|
|
|
|
// Check if learnings file was created with an operational entry
|
|
// The slug is derived from the git repo (dirname), so search all project dirs
|
|
let hasOperational = false;
|
|
const projectsDir = path.join(gstackHome, 'projects');
|
|
if (fs.existsSync(projectsDir)) {
|
|
for (const slug of fs.readdirSync(projectsDir)) {
|
|
const lPath = path.join(projectsDir, slug, 'learnings.jsonl');
|
|
if (fs.existsSync(lPath)) {
|
|
const jsonl = fs.readFileSync(lPath, 'utf-8').trim();
|
|
if (jsonl) {
|
|
const entries = jsonl.split('\n').map(l => { try { return JSON.parse(l); } catch { return null; } }).filter(Boolean);
|
|
const opEntry = entries.find(e => e.type === 'operational');
|
|
if (opEntry) {
|
|
hasOperational = true;
|
|
console.log(`Operational learning logged: key="${opEntry.key}" insight="${opEntry.insight}" (slug: ${slug})`);
|
|
break;
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
recordE2E(evalCollector, 'operational learning', 'Skill E2E tests', result, {
|
|
passed: exitOk && hasOperational,
|
|
});
|
|
|
|
expect(exitOk).toBe(true);
|
|
expect(hasOperational).toBe(true);
|
|
|
|
// Clean up
|
|
try { fs.rmSync(opDir, { recursive: true, force: true }); } catch {}
|
|
}, 90_000);
|
|
|
|
testConcurrentIfSelected('session-awareness', async () => {
|
|
const sessionDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-session-'));
|
|
|
|
// Set up a git repo so there's project/branch context to reference
|
|
const run = (cmd: string, args: string[]) =>
|
|
spawnSync(cmd, args, { cwd: sessionDir, stdio: 'pipe', timeout: 5000 });
|
|
run('git', ['init', '-b', 'main']);
|
|
run('git', ['config', 'user.email', 'test@test.com']);
|
|
run('git', ['config', 'user.name', 'Test']);
|
|
fs.writeFileSync(path.join(sessionDir, 'app.rb'), '# my app\n');
|
|
run('git', ['add', '.']);
|
|
run('git', ['commit', '-m', 'init']);
|
|
run('git', ['checkout', '-b', 'feature/add-payments']);
|
|
// Add a remote so the agent can derive a project name
|
|
run('git', ['remote', 'add', 'origin', 'https://github.com/acme/billing-app.git']);
|
|
|
|
// Extract AskUserQuestion format instructions from generated SKILL.md
|
|
const skillMd = fs.readFileSync(path.join(ROOT, 'SKILL.md'), 'utf-8');
|
|
const aqStart = skillMd.indexOf('## AskUserQuestion Format');
|
|
const aqEnd = skillMd.indexOf('\n## ', aqStart + 1);
|
|
const aqBlock = skillMd.slice(aqStart, aqEnd > 0 ? aqEnd : undefined);
|
|
|
|
const outputPath = path.join(sessionDir, 'question-output.md');
|
|
|
|
const result = await runSkillTest({
|
|
prompt: `You are running a gstack skill. The session preamble detected _SESSIONS=4 (the user has 4 gstack windows open).
|
|
|
|
${aqBlock}
|
|
|
|
You are on branch feature/add-payments in the billing-app project. You were reviewing a plan to add Stripe integration.
|
|
|
|
You've hit a decision point: the plan doesn't specify whether to use Stripe Checkout (hosted) or Stripe Elements (embedded). You need to ask the user which approach to use.
|
|
|
|
Since this is non-interactive, DO NOT actually call AskUserQuestion. Instead, write the EXACT text you would display to the user (the full AskUserQuestion content) to the file: ${outputPath}
|
|
|
|
Remember: _SESSIONS=4, so ELI16 mode is active. The user is juggling multiple windows and may not remember what this conversation is about. Re-ground them.`,
|
|
workingDirectory: sessionDir,
|
|
maxTurns: 8,
|
|
timeout: 60_000,
|
|
testName: 'session-awareness',
|
|
runId,
|
|
});
|
|
|
|
logCost('session awareness', result);
|
|
recordE2E(evalCollector, 'session awareness ELI16', 'Skill E2E tests', result);
|
|
|
|
// Verify the output contains ELI16 re-grounding context
|
|
if (fs.existsSync(outputPath)) {
|
|
const output = fs.readFileSync(outputPath, 'utf-8');
|
|
const lower = output.toLowerCase();
|
|
// Must mention project name
|
|
expect(lower.includes('billing') || lower.includes('acme')).toBe(true);
|
|
// Must mention branch
|
|
expect(lower.includes('payment') || lower.includes('feature')).toBe(true);
|
|
// Must mention what we're working on
|
|
expect(lower.includes('stripe') || lower.includes('checkout') || lower.includes('payment')).toBe(true);
|
|
// Must have a recommendation or structured options
|
|
expect(
|
|
output.includes('RECOMMENDATION') ||
|
|
lower.includes('recommend') ||
|
|
lower.includes('option a') ||
|
|
lower.includes('which do you want') ||
|
|
lower.includes('which approach')
|
|
).toBe(true);
|
|
} else {
|
|
// Check agent output as fallback
|
|
const output = result.output || '';
|
|
const lowerOut = output.toLowerCase();
|
|
expect(
|
|
output.includes('RECOMMENDATION') ||
|
|
lowerOut.includes('recommend') ||
|
|
lowerOut.includes('option a') ||
|
|
lowerOut.includes('which do you want') ||
|
|
lowerOut.includes('which approach')
|
|
).toBe(true);
|
|
}
|
|
|
|
// Clean up
|
|
try { fs.rmSync(sessionDir, { recursive: true, force: true }); } catch {}
|
|
}, 90_000);
|
|
});
|
|
|
|
// Module-level afterAll — finalize eval collector after all tests complete
|
|
afterAll(async () => {
|
|
await finalizeEvalCollector(evalCollector);
|
|
});
|