mirror of
https://github.com/garrytan/gstack.git
synced 2026-05-01 19:25:10 +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>
164 lines
5.6 KiB
TypeScript
164 lines
5.6 KiB
TypeScript
#!/usr/bin/env bun
|
|
/**
|
|
* Generate SKILL.md files from .tmpl templates.
|
|
*
|
|
* Pipeline:
|
|
* read .tmpl → find {{PLACEHOLDERS}} → resolve from source → format → write .md
|
|
*
|
|
* Supports --dry-run: generate to memory, exit 1 if different from committed file.
|
|
* Used by skill:check and CI freshness checks.
|
|
*/
|
|
|
|
import { COMMAND_DESCRIPTIONS } from '../browse/src/commands';
|
|
import { SNAPSHOT_FLAGS } from '../browse/src/snapshot';
|
|
import * as fs from 'fs';
|
|
import * as path from 'path';
|
|
|
|
const ROOT = path.resolve(import.meta.dir, '..');
|
|
const DRY_RUN = process.argv.includes('--dry-run');
|
|
|
|
// ─── Placeholder Resolvers ──────────────────────────────────
|
|
|
|
function generateCommandReference(): string {
|
|
// Group commands by category
|
|
const groups = new Map<string, Array<{ command: string; description: string; usage?: string }>>();
|
|
for (const [cmd, meta] of Object.entries(COMMAND_DESCRIPTIONS)) {
|
|
const list = groups.get(meta.category) || [];
|
|
list.push({ command: cmd, description: meta.description, usage: meta.usage });
|
|
groups.set(meta.category, list);
|
|
}
|
|
|
|
// Category display order
|
|
const categoryOrder = [
|
|
'Navigation', 'Reading', 'Interaction', 'Inspection',
|
|
'Visual', 'Snapshot', 'Meta', 'Tabs', 'Server',
|
|
];
|
|
|
|
const sections: string[] = [];
|
|
for (const category of categoryOrder) {
|
|
const commands = groups.get(category);
|
|
if (!commands || commands.length === 0) continue;
|
|
|
|
// Sort alphabetically within category
|
|
commands.sort((a, b) => a.command.localeCompare(b.command));
|
|
|
|
sections.push(`### ${category}`);
|
|
sections.push('| Command | Description |');
|
|
sections.push('|---------|-------------|');
|
|
for (const cmd of commands) {
|
|
const display = cmd.usage ? `\`${cmd.usage}\`` : `\`${cmd.command}\``;
|
|
sections.push(`| ${display} | ${cmd.description} |`);
|
|
}
|
|
sections.push('');
|
|
}
|
|
|
|
return sections.join('\n').trimEnd();
|
|
}
|
|
|
|
function generateSnapshotFlags(): string {
|
|
const lines: string[] = [
|
|
'The snapshot is your primary tool for understanding and interacting with pages.',
|
|
'',
|
|
'```',
|
|
];
|
|
|
|
for (const flag of SNAPSHOT_FLAGS) {
|
|
const label = flag.valueHint ? `${flag.short} ${flag.valueHint}` : flag.short;
|
|
lines.push(`${label.padEnd(10)}${flag.description}`);
|
|
}
|
|
|
|
lines.push('```');
|
|
lines.push('');
|
|
lines.push('Combine flags: `$B snapshot -i -a -C -o /tmp/annotated.png`');
|
|
lines.push('');
|
|
lines.push('After snapshot, use @refs everywhere:');
|
|
lines.push('```bash');
|
|
lines.push('$B click @e3 $B fill @e4 "value" $B hover @e1');
|
|
lines.push('$B html @e2 $B css @e5 "color" $B attrs @e6');
|
|
lines.push('$B click @c1 # cursor-interactive ref (from -C)');
|
|
lines.push('```');
|
|
lines.push('');
|
|
lines.push('Refs are invalidated on navigation — run `snapshot` again after `goto`.');
|
|
|
|
return lines.join('\n');
|
|
}
|
|
|
|
const RESOLVERS: Record<string, () => string> = {
|
|
COMMAND_REFERENCE: generateCommandReference,
|
|
SNAPSHOT_FLAGS: generateSnapshotFlags,
|
|
};
|
|
|
|
// ─── Template Processing ────────────────────────────────────
|
|
|
|
const GENERATED_HEADER = `<!-- AUTO-GENERATED from {{SOURCE}} — do not edit directly -->\n<!-- Regenerate: bun run gen:skill-docs -->\n`;
|
|
|
|
function processTemplate(tmplPath: string): { outputPath: string; content: string } {
|
|
const tmplContent = fs.readFileSync(tmplPath, 'utf-8');
|
|
const relTmplPath = path.relative(ROOT, tmplPath);
|
|
const outputPath = tmplPath.replace(/\.tmpl$/, '');
|
|
|
|
// Replace placeholders
|
|
let content = tmplContent.replace(/\{\{(\w+)\}\}/g, (match, name) => {
|
|
const resolver = RESOLVERS[name];
|
|
if (!resolver) throw new Error(`Unknown placeholder {{${name}}} in ${relTmplPath}`);
|
|
return resolver();
|
|
});
|
|
|
|
// Check for any remaining unresolved placeholders
|
|
const remaining = content.match(/\{\{(\w+)\}\}/g);
|
|
if (remaining) {
|
|
throw new Error(`Unresolved placeholders in ${relTmplPath}: ${remaining.join(', ')}`);
|
|
}
|
|
|
|
// Prepend generated header (after frontmatter)
|
|
const header = GENERATED_HEADER.replace('{{SOURCE}}', path.basename(tmplPath));
|
|
const fmEnd = content.indexOf('---', content.indexOf('---') + 3);
|
|
if (fmEnd !== -1) {
|
|
const insertAt = content.indexOf('\n', fmEnd) + 1;
|
|
content = content.slice(0, insertAt) + header + content.slice(insertAt);
|
|
} else {
|
|
content = header + content;
|
|
}
|
|
|
|
return { outputPath, content };
|
|
}
|
|
|
|
// ─── Main ───────────────────────────────────────────────────
|
|
|
|
function findTemplates(): string[] {
|
|
const templates: string[] = [];
|
|
const candidates = [
|
|
path.join(ROOT, 'SKILL.md.tmpl'),
|
|
path.join(ROOT, 'browse', 'SKILL.md.tmpl'),
|
|
];
|
|
for (const p of candidates) {
|
|
if (fs.existsSync(p)) templates.push(p);
|
|
}
|
|
return templates;
|
|
}
|
|
|
|
let hasChanges = false;
|
|
|
|
for (const tmplPath of findTemplates()) {
|
|
const { outputPath, content } = processTemplate(tmplPath);
|
|
const relOutput = path.relative(ROOT, outputPath);
|
|
|
|
if (DRY_RUN) {
|
|
const existing = fs.existsSync(outputPath) ? fs.readFileSync(outputPath, 'utf-8') : '';
|
|
if (existing !== content) {
|
|
console.log(`STALE: ${relOutput}`);
|
|
hasChanges = true;
|
|
} else {
|
|
console.log(`FRESH: ${relOutput}`);
|
|
}
|
|
} else {
|
|
fs.writeFileSync(outputPath, content);
|
|
console.log(`GENERATED: ${relOutput}`);
|
|
}
|
|
}
|
|
|
|
if (DRY_RUN && hasChanges) {
|
|
console.error('\nGenerated SKILL.md files are stale. Run: bun run gen:skill-docs');
|
|
process.exit(1);
|
|
}
|