mirror of
https://github.com/garrytan/gstack.git
synced 2026-05-02 11:45:20 +02:00
5205070299
* refactor: extract command registry to commands.ts, add SNAPSHOT_FLAGS metadata
- NEW: browse/src/commands.ts — command sets + COMMAND_DESCRIPTIONS + load-time validation (zero side effects)
- server.ts imports from commands.ts instead of declaring sets inline
- snapshot.ts: SNAPSHOT_FLAGS array drives parseSnapshotArgs (metadata-driven, no duplication)
- All 186 existing tests pass
* feat: SKILL.md template system with auto-generated command references
- SKILL.md.tmpl + browse/SKILL.md.tmpl with {{COMMAND_REFERENCE}} and {{SNAPSHOT_FLAGS}} placeholders
- scripts/gen-skill-docs.ts generates SKILL.md from templates (supports --dry-run)
- Build pipeline runs gen:skill-docs before binary compilation
- Generated files have AUTO-GENERATED header, committed to git
* test: Tier 1 static validation — 34 tests for SKILL.md command correctness
- test/helpers/skill-parser.ts: extracts $B commands from code blocks, validates against registry
- test/skill-parser.test.ts: 13 parser/validator unit tests
- test/skill-validation.test.ts: 13 tests validating all SKILL.md files + registry consistency
- test/gen-skill-docs.test.ts: 8 generator tests (categories, sorting, freshness)
* feat: DX tools (skill:check, dev:skill) + Tier 2 E2E test scaffolding
- scripts/skill-check.ts: health summary for all SKILL.md files (commands, templates, freshness)
- scripts/dev-skill.ts: watch mode for template development
- test/helpers/session-runner.ts: Agent SDK wrapper for E2E skill tests
- test/skill-e2e.test.ts: 2 E2E tests + 3 stubs (auto-skip inside Claude Code sessions)
- E2E tests must run from plain terminal: SKILL_E2E=1 bun test test/skill-e2e.test.ts
* ci: SKILL.md freshness check on push/PR + TODO updates
- .github/workflows/skill-docs.yml: fails if generated SKILL.md files are stale
- TODO.md: add E2E cost tracking and model pinning to future ideas
* fix: restore rich descriptions lost in auto-generation
- Snapshot flags: add back value hints (-d <N>, -s <sel>, -o <path>)
- Snapshot flags: restore parenthetical context (@e refs, @c refs, etc.)
- Commands: is → includes valid states enum
- Commands: console → notes --errors filter behavior
- Commands: press → lists common keys (Enter, Tab, Escape)
- Commands: cookie-import-browser → describes picker UI
- Commands: dialog-accept → specifies alert/confirm/prompt
- Tips: restore → arrow (was downgraded to ->)
* test: quality evals for generated SKILL.md descriptions
Catches the exact regressions we shipped and caught in review:
- Snapshot flags must include value hints (-d <N>, -s <sel>, -o <path>)
- is command must list all valid states (visible/hidden/enabled/...)
- press command must list example keys (Enter, Tab, Escape)
- console command must describe --errors behavior
- Snapshot -i must mention @e refs, -C must mention @c refs
- All descriptions must be >= 8 chars (no empty stubs)
- Tips section must use → not ->
* feat: LLM-as-judge evals for SKILL.md documentation quality
4 eval tests using Anthropic API (claude-haiku, ~$0.01-0.03/run):
- Command reference table: clarity/completeness/actionability >= 4/5
- Snapshot flags section: same thresholds
- browse/SKILL.md overall quality
- Regression: generated version must score >= hand-maintained baseline
Requires ANTHROPIC_API_KEY. Auto-skips without it.
Run: bun run test:eval (or ANTHROPIC_API_KEY=sk-... bun test test/skill-llm-eval.test.ts)
* chore: bump version to 0.3.3, update changelog
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* docs: add ARCHITECTURE.md, update CLAUDE.md and CONTRIBUTING.md
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: conductor.json lifecycle hooks + .env propagation across worktrees
bin/dev-setup now copies .env from main worktree so API keys carry
over to Conductor workspaces automatically. conductor.json wires up
setup and archive hooks.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* docs: complete CHANGELOG for v0.3.3 (architecture, conductor, .env)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
80 lines
3.0 KiB
TypeScript
80 lines
3.0 KiB
TypeScript
import { describe, test, expect, beforeAll, afterAll } from 'bun:test';
|
|
import { runSkillTest } from './helpers/session-runner';
|
|
import { startTestServer } from '../browse/test/test-server';
|
|
import * as fs from 'fs';
|
|
import * as path from 'path';
|
|
import * as os from 'os';
|
|
|
|
// Skip if SKILL_E2E not set, or if running inside a Claude Code / Agent SDK session
|
|
// (nested Agent SDK sessions hang because the parent intercepts child claude subprocesses)
|
|
const isInsideAgentSDK = !!process.env.CLAUDECODE || !!process.env.CLAUDE_CODE_ENTRYPOINT;
|
|
const describeE2E = (process.env.SKILL_E2E && !isInsideAgentSDK) ? describe : describe.skip;
|
|
|
|
let testServer: ReturnType<typeof startTestServer>;
|
|
let tmpDir: string;
|
|
|
|
describeE2E('Skill E2E tests', () => {
|
|
beforeAll(() => {
|
|
testServer = startTestServer();
|
|
tmpDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-'));
|
|
|
|
// Symlink browse binary into tmpdir for the skill to find
|
|
const browseBin = path.resolve(import.meta.dir, '..', 'browse', 'dist', 'browse');
|
|
const binDir = path.join(tmpDir, 'browse', 'dist');
|
|
fs.mkdirSync(binDir, { recursive: true });
|
|
if (fs.existsSync(browseBin)) {
|
|
fs.symlinkSync(browseBin, path.join(binDir, 'browse'));
|
|
}
|
|
|
|
// Also create browse/bin/find-browse so the SKILL.md setup works
|
|
const findBrowseDir = path.join(tmpDir, 'browse', 'bin');
|
|
fs.mkdirSync(findBrowseDir, { recursive: true });
|
|
fs.writeFileSync(path.join(findBrowseDir, 'find-browse'), `#!/bin/bash\necho "${browseBin}"\n`, { mode: 0o755 });
|
|
});
|
|
|
|
afterAll(() => {
|
|
testServer?.server?.stop();
|
|
// Clean up tmpdir
|
|
try { fs.rmSync(tmpDir, { recursive: true, force: true }); } catch {}
|
|
});
|
|
|
|
test('browse basic commands work without errors', async () => {
|
|
const result = await runSkillTest({
|
|
prompt: `You have a browse binary at ${path.resolve(import.meta.dir, '..', 'browse', 'dist', 'browse')}. 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: 10,
|
|
timeout: 60_000,
|
|
});
|
|
|
|
expect(result.browseErrors).toHaveLength(0);
|
|
expect(result.exitReason).toBe('success');
|
|
}, 90_000);
|
|
|
|
test('browse snapshot flags all work', async () => {
|
|
const result = await runSkillTest({
|
|
prompt: `You have a browse binary at ${path.resolve(import.meta.dir, '..', 'browse', 'dist', 'browse')}. 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: 10,
|
|
timeout: 60_000,
|
|
});
|
|
|
|
expect(result.browseErrors).toHaveLength(0);
|
|
expect(result.exitReason).toBe('success');
|
|
}, 90_000);
|
|
|
|
test.todo('/qa quick completes without browse errors');
|
|
test.todo('/ship completes without browse errors');
|
|
test.todo('/review completes without browse errors');
|
|
});
|