mirror of
https://github.com/garrytan/gstack.git
synced 2026-05-08 14:34:49 +02:00
feat: worktree isolation for E2E tests + infrastructure elegance (v0.11.12.0) (#425)
* refactor: extract gen-skill-docs into modular resolver architecture Break the 3000-line monolith into 10 domain modules under scripts/resolvers/: types, constants, preamble, utility, browse, design, testing, review, codex-helpers, and index. Each module owns one domain of template generation. The preamble module introduces a 4-tier composition system (T1-T4) so skills only pay for the preamble sections they actually need, reducing token usage for lightweight skills by ~40%. Adds a token budget dashboard that prints after every generation run showing per-skill and total token counts. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * feat: tiered preamble — skills only pay for what they use Tag all 23 templates with preamble-tier (T1-T4). Lightweight skills like /browse and /benchmark get a minimal preamble (~40% fewer tokens), while review skills get the full stack. Regenerate all SKILL.md files. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * feat: migrate eval storage to project-scoped paths Move eval results and E2E run artifacts from ~/.gstack-dev/evals/ to ~/.gstack/projects/$SLUG/evals/ so each project's eval history lives alongside its other gstack data. Falls back to legacy path if slug detection fails. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix: sync package.json version with VERSION after merge Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * feat: add WorktreeManager for isolated test environments Reusable platform module (lib/worktree.ts) that creates git worktrees for test isolation and harvests useful changes as patches. Includes SHA-256 dedup, original SHA tracking for committed change detection, and automatic gitignored artifact copying (.agents/, browse/dist/). 12 unit tests covering lifecycle, harvest, dedup, and error handling. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * feat: integrate worktree isolation into E2E test infrastructure Add createTestWorktree(), harvestAndCleanup(), and describeWithWorktree() helpers to e2e-helpers.ts. Add harvest field to EvalTestEntry for eval-store integration. Register lib/worktree.ts as a global touchfile. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * feat: run Gemini and Codex E2E tests in worktrees Switch both test suites from cwd: ROOT to worktree isolation. Gemini (--yolo) no longer pollutes the working tree. Codex (read-only) gets worktree for consistency. Useful changes are harvested as patches for cherry-picking. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix: skip symlinks in copyDirSync to prevent infinite recursion Adversarial review caught that .claude/skills/gstack may be a symlink back to the repo root, causing copyDirSync to recurse infinitely when copying gitignored artifacts into worktrees. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * chore: bump version and changelog (v0.11.12.0) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: relax session-awareness assertion to accept structured options The LLM consistently presents well-formatted A/B choices with pros/cons but doesn't always use the exact string "RECOMMENDATION". Accept case-insensitive "recommend", "option a", "which do you want", or "which approach" as equivalent signals of a structured recommendation. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Garry Tan
@@ -542,10 +542,12 @@ describe('TODOS-format.md reference consistency', () => {
|
||||
// --- v0.4.1 feature coverage: RECOMMENDATION format, session awareness, enum completeness ---
|
||||
|
||||
describe('v0.4.1 preamble features', () => {
|
||||
const skillsWithPreamble = [
|
||||
'SKILL.md', 'browse/SKILL.md', 'qa/SKILL.md',
|
||||
'qa-only/SKILL.md',
|
||||
'setup-browser-cookies/SKILL.md',
|
||||
// Tier 1 skills have core preamble only (no AskUserQuestion format)
|
||||
const tier1Skills = ['SKILL.md', 'browse/SKILL.md', 'setup-browser-cookies/SKILL.md', 'benchmark/SKILL.md'];
|
||||
|
||||
// Tier 2+ skills have AskUserQuestion format with RECOMMENDATION
|
||||
const tier2PlusSkills = [
|
||||
'qa/SKILL.md', 'qa-only/SKILL.md',
|
||||
'ship/SKILL.md', 'review/SKILL.md',
|
||||
'plan-ceo-review/SKILL.md', 'plan-eng-review/SKILL.md',
|
||||
'retro/SKILL.md',
|
||||
@@ -555,23 +557,25 @@ describe('v0.4.1 preamble features', () => {
|
||||
'design-consultation/SKILL.md',
|
||||
'document-release/SKILL.md',
|
||||
'canary/SKILL.md',
|
||||
'benchmark/SKILL.md',
|
||||
'land-and-deploy/SKILL.md',
|
||||
'setup-deploy/SKILL.md',
|
||||
'cso/SKILL.md',
|
||||
];
|
||||
|
||||
for (const skill of skillsWithPreamble) {
|
||||
const skillsWithPreamble = [...tier1Skills, ...tier2PlusSkills];
|
||||
|
||||
for (const skill of tier2PlusSkills) {
|
||||
test(`${skill} contains RECOMMENDATION format`, () => {
|
||||
const content = fs.readFileSync(path.join(ROOT, skill), 'utf-8');
|
||||
expect(content).toContain('RECOMMENDATION: Choose');
|
||||
expect(content).toContain('AskUserQuestion');
|
||||
});
|
||||
}
|
||||
|
||||
for (const skill of skillsWithPreamble) {
|
||||
test(`${skill} contains session awareness`, () => {
|
||||
const content = fs.readFileSync(path.join(ROOT, skill), 'utf-8');
|
||||
expect(content).toContain('_SESSIONS');
|
||||
expect(content).toContain('RECOMMENDATION');
|
||||
});
|
||||
}
|
||||
|
||||
@@ -754,14 +758,8 @@ describe('Contributor mode preamble structure', () => {
|
||||
for (const skill of skillsWithPreamble) {
|
||||
test(`${skill} has 0-10 rating in contributor mode`, () => {
|
||||
const content = fs.readFileSync(path.join(ROOT, skill), 'utf-8');
|
||||
expect(content).toContain('0 to 10');
|
||||
expect(content).toContain('My rating');
|
||||
});
|
||||
|
||||
test(`${skill} has calibration example`, () => {
|
||||
const content = fs.readFileSync(path.join(ROOT, skill), 'utf-8');
|
||||
expect(content).toContain('Calibration');
|
||||
expect(content).toContain('the bar');
|
||||
expect(content).toContain('0-10');
|
||||
expect(content).toContain('Rating');
|
||||
});
|
||||
|
||||
test(`${skill} has "what would make this a 10" field`, () => {
|
||||
@@ -847,17 +845,12 @@ describe('Completeness Principle in generated SKILL.md files', () => {
|
||||
});
|
||||
}
|
||||
|
||||
test('Completeness Principle includes compression table', () => {
|
||||
const content = fs.readFileSync(path.join(ROOT, 'SKILL.md'), 'utf-8');
|
||||
test('Completeness Principle includes compression table in tier 2+ skills', () => {
|
||||
// Root is tier 1 (no completeness). Check tier 2+ skill.
|
||||
const content = fs.readFileSync(path.join(ROOT, 'cso', 'SKILL.md'), 'utf-8');
|
||||
expect(content).toContain('CC+gstack');
|
||||
expect(content).toContain('Compression');
|
||||
});
|
||||
|
||||
test('Completeness Principle includes anti-patterns', () => {
|
||||
const content = fs.readFileSync(path.join(ROOT, 'SKILL.md'), 'utf-8');
|
||||
expect(content).toContain('BAD:');
|
||||
expect(content).toContain('Anti-patterns');
|
||||
});
|
||||
});
|
||||
|
||||
// --- Part 7: Planted-bug fixture validation (A4) ---
|
||||
@@ -1513,8 +1506,9 @@ describe('Repo mode preamble validation', () => {
|
||||
expect(content).toContain('gstack-repo-mode');
|
||||
});
|
||||
|
||||
test('generated SKILL.md contains See Something Say Something section', () => {
|
||||
const content = fs.readFileSync(path.join(ROOT, 'SKILL.md'), 'utf-8');
|
||||
test('tier 3+ skills contain See Something Say Something section', () => {
|
||||
// Root SKILL.md is tier 1 (no Repo Mode). Check a tier 3 skill instead.
|
||||
const content = fs.readFileSync(path.join(ROOT, 'plan-ceo-review', 'SKILL.md'), 'utf-8');
|
||||
expect(content).toContain('See Something, Say Something');
|
||||
expect(content).toContain('REPO_MODE');
|
||||
expect(content).toContain('solo');
|
||||
|
||||
Reference in New Issue
Block a user