CalvinBackup/gstack
1
0
Fork 0
mirror of https://github.com/garrytan/gstack.git synced 2026-09-16 18:05:31 +02:00
Code Issues Packages Projects Releases Wiki Activity

test: cover first-run detection + repoint browse-content assertions to /browse

Browse Source 
- New unit tests for every detection bucket, the eval-safe enum contract, and the
  first-run gating (test/preamble-first-task-scaffold.test.ts); periodic E2E that runs
  the detector through the real harness (test/skill-e2e-first-task-scaffold.test.ts).
- Repoint browse-content assertions (gen-skill-docs, audit-compliance, skill-validation,
  LLM-judge eval) from the root skill to browse/SKILL.md following the router split;
  add a regression pinning that the router carries no browse body.
- Register first-task-scaffold touchfiles + periodic tier; bump parity/carve size caps
  ~1-2KB per skill for the shared first-run-guidance preamble section.
- Refresh ship golden fixtures for the preamble addition.
This commit is contained in:
Garry Tan
2026-06-21 07:16:24 -07:00
parent 938fa4a035
commit 866159861d
12 changed files with 438 additions and 51 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/gen-skill-docs.test.ts
+16 -12
View File
@@ -108,7 +108,7 @@ const CLAUDE_GENERATED_SKILLS = ALL_SKILLS.filter(skill => !CLAUDE_SKIPPED_SKILL
describe('gen-skill-docs', () => {
test('generated SKILL.md contains all command categories', () => {
const content = fs.readFileSync(path.join(ROOT, 'SKILL.md'), 'utf-8');
const content = fs.readFileSync(path.join(ROOT, 'browse', 'SKILL.md'), 'utf-8');
const categories = new Set(Object.values(COMMAND_DESCRIPTIONS).map(d => d.category));
for (const cat of categories) {
expect(content).toContain(`### ${cat}`);
@@ -116,7 +116,7 @@ describe('gen-skill-docs', () => {
});
test('generated SKILL.md contains all commands', () => {
const content = fs.readFileSync(path.join(ROOT, 'SKILL.md'), 'utf-8');
const content = fs.readFileSync(path.join(ROOT, 'browse', 'SKILL.md'), 'utf-8');
for (const [cmd, meta] of Object.entries(COMMAND_DESCRIPTIONS)) {
const display = meta.usage || cmd;
expect(content).toContain(display);
@@ -124,7 +124,7 @@ describe('gen-skill-docs', () => {
});
test('command table is sorted alphabetically within categories', () => {
const content = fs.readFileSync(path.join(ROOT, 'SKILL.md'), 'utf-8');
const content = fs.readFileSync(path.join(ROOT, 'browse', 'SKILL.md'), 'utf-8');
// Extract command names from the Navigation section as a test
const navSection = content.match(/### Navigation\n\|.*\n\|.*\n([\s\S]*?)(?=\n###|\n## )/);
expect(navSection).not.toBeNull();
@@ -149,7 +149,7 @@ describe('gen-skill-docs', () => {
});
test('snapshot flags section contains all flags', () => {
const content = fs.readFileSync(path.join(ROOT, 'SKILL.md'), 'utf-8');
const content = fs.readFileSync(path.join(ROOT, 'browse', 'SKILL.md'), 'utf-8');
for (const flag of SNAPSHOT_FLAGS) {
expect(content).toContain(flag.short);
expect(content).toContain(flag.description);
@@ -284,10 +284,12 @@ describe('gen-skill-docs', () => {
});
test('templates contain placeholders', () => {
// P2 (v1.2.0): the root template is a pure router — only {{PREAMBLE}}.
// The browse command/snapshot placeholders live in browse/SKILL.md.tmpl now.
const rootTmpl = fs.readFileSync(path.join(ROOT, 'SKILL.md.tmpl'), 'utf-8');
expect(rootTmpl).toContain('{{COMMAND_REFERENCE}}');
expect(rootTmpl).toContain('{{SNAPSHOT_FLAGS}}');
expect(rootTmpl).toContain('{{PREAMBLE}}');
expect(rootTmpl).not.toContain('{{COMMAND_REFERENCE}}');
expect(rootTmpl).not.toContain('{{SNAPSHOT_FLAGS}}');
const browseTmpl = fs.readFileSync(path.join(ROOT, 'browse', 'SKILL.md.tmpl'), 'utf-8');
expect(browseTmpl).toContain('{{COMMAND_REFERENCE}}');
@@ -592,7 +594,7 @@ describe('GitLab support in generated skills', () => {
describe('description quality evals', () => {
// Regression: snapshot flags lost value hints (-d <N>, -s <sel>, -o <path>)
test('snapshot flags with values include value hints in output', () => {
const content = fs.readFileSync(path.join(ROOT, 'SKILL.md'), 'utf-8');
const content = fs.readFileSync(path.join(ROOT, 'browse', 'SKILL.md'), 'utf-8');
for (const flag of SNAPSHOT_FLAGS) {
if (flag.takesValue) {
expect(flag.valueHint).toBeDefined();
@@ -659,11 +661,13 @@ describe('description quality evals', () => {
// Guard: generated output uses → not ->
test('generated SKILL.md uses unicode arrows', () => {
const content = fs.readFileSync(path.join(ROOT, 'SKILL.md'), 'utf-8');
// Check the Tips section specifically (where we regressed -> from →)
const tipsSection = content.slice(content.indexOf('## Tips'));
expect(tipsSection).toContain('→');
expect(tipsSection).not.toContain('->');
// P2 (v1.2.0): the browse body moved out of the top-level router into
// browse/SKILL.md. Guard arrow style on the browse body (sliced from its
// H1 so the auto-generated `-->` header comments are excluded).
const content = fs.readFileSync(path.join(ROOT, 'browse', 'SKILL.md'), 'utf-8');
const body = content.slice(content.indexOf('# browse: QA Testing'));
expect(body).toContain('→');
expect(body).not.toContain('->');
});
});