CalvinBackup/gstack
1
0
Fork 0
mirror of https://github.com/garrytan/gstack.git synced 2026-05-02 03:35:09 +02:00
Code Issues Packages Projects Releases Wiki Activity

test: update adversarial + add scope drift assertions

Browse Source 
Rename adversarial tests to reflect always-on behavior. Remove tier
threshold assertions. Add scope drift content assertions for both
/review and /ship generated SKILL.md files.
This commit is contained in:
Garry Tan
2026-03-30 20:14:12 -07:00
parent 8775470fa6
commit c2837dba93
1 changed files with 28 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/skill-validation.test.ts
+28 -17
View File
@@ -1305,38 +1305,49 @@ describe('Codex skill', () => {
expect(content).toContain('mktemp');
});
test('adversarial review in /review auto-scales by diff size', () => {
test('adversarial review in /review always runs both passes', () => {
const content = fs.readFileSync(path.join(ROOT, 'review', 'SKILL.md'), 'utf-8');
expect(content).toContain('Adversarial review (auto-scaled)');
// Diff size thresholds
expect(content).toContain('< 50');
expect(content).toContain('50–199');
expect(content).toContain('200+');
// All three tiers present
expect(content).toContain('Small');
expect(content).toContain('Medium tier');
expect(content).toContain('Large tier');
expect(content).toContain('Adversarial review (always-on)');
// Always-on: both Claude and Codex adversarial
expect(content).toContain('Claude adversarial subagent (always runs)');
expect(content).toContain('Codex adversarial challenge (always runs when available)');
// Claude adversarial subagent dispatch
expect(content).toContain('Agent tool');
expect(content).toContain('FIXABLE');
expect(content).toContain('INVESTIGATE');
// Codex fallback logic
// Codex availability check
expect(content).toContain('CODEX_NOT_AVAILABLE');
expect(content).toContain('fall back to the Claude adversarial subagent');
// Review log uses new skill name
// OLD_CFG only gates Codex, not Claude
expect(content).toContain('skip Codex passes only');
// Review log
expect(content).toContain('adversarial-review');
expect(content).toContain('reasoning_effort="high"');
expect(content).toContain('ADVERSARIAL REVIEW SYNTHESIS');
// Large diff structured review still gated
expect(content).toContain('Codex structured review (large diffs only');
expect(content).toContain('200');
});
test('adversarial review in /ship auto-scales by diff size', () => {
test('adversarial review in /ship always runs both passes', () => {
const content = fs.readFileSync(path.join(ROOT, 'ship', 'SKILL.md'), 'utf-8');
expect(content).toContain('Adversarial review (auto-scaled)');
expect(content).toContain('< 50');
expect(content).toContain('200+');
expect(content).toContain('Adversarial review (always-on)');
expect(content).toContain('adversarial-review');
expect(content).toContain('reasoning_effort="high"');
expect(content).toContain('Investigate and fix');
expect(content).toContain('Claude adversarial subagent (always runs)');
});
test('scope drift detection in /review and /ship', () => {
const reviewContent = fs.readFileSync(path.join(ROOT, 'review', 'SKILL.md'), 'utf-8');
const shipContent = fs.readFileSync(path.join(ROOT, 'ship', 'SKILL.md'), 'utf-8');
// Both should contain scope drift from the shared resolver
for (const content of [reviewContent, shipContent]) {
expect(content).toContain('Scope Check:');
expect(content).toContain('DRIFT DETECTED');
expect(content).toContain('SCOPE CREEP');
expect(content).toContain('MISSING REQUIREMENTS');
expect(content).toContain('stated intent');
}
});
test('codex-host ship/review do NOT contain adversarial review step', () => {