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

feat: auto-scaled adversarial review (v0.9.5.0) (#297)

Browse Source 
* feat: auto-scaled adversarial review by diff size

Replace config-driven Codex review step with automatic adversarial review
that scales by diff size: small (<50 lines) skips adversarial, medium
(50-199) gets cross-model adversarial, large (200+) gets all 4 passes.

Adds Claude adversarial subagent as fallback when Codex unavailable.
Review log uses new "adversarial-review" skill name with source/tier fields.
Dashboard updated to read both adversarial-review and legacy codex-review.

* chore: regenerate SKILL.md files for auto-scaled adversarial review

* chore: bump version and changelog (v0.9.5.0)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* feat: allow user override of adversarial review tier

Users can now say "paranoid review", "run all passes", "full adversarial",
etc. to force the large tier regardless of diff size.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Garry Tan
2026-03-21 12:12:56 -07:00
committed by GitHub
parent f075cb757f
commit 6c69febf11
15 changed files with 398 additions and 329 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/skill-validation.test.ts
+29 -16
View File
@@ -1256,35 +1256,48 @@ describe('Codex skill', () => {
expect(content).toContain('mktemp');
});
test('codex integration in /review has config-driven review step', () => {
test('adversarial review in /review auto-scales by diff size', () => {
const content = fs.readFileSync(path.join(ROOT, 'review', 'SKILL.md'), 'utf-8');
expect(content).toContain('Codex review');
expect(content).toContain('codex_reviews');
expect(content).toContain('codex review');
expect(content).toContain('adversarial');
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');
// Claude adversarial subagent dispatch
expect(content).toContain('Agent tool');
expect(content).toContain('FIXABLE');
expect(content).toContain('INVESTIGATE');
// Codex fallback logic
expect(content).toContain('CODEX_NOT_AVAILABLE');
expect(content).toContain('fall back to the Claude adversarial subagent');
// Review log uses new skill name
expect(content).toContain('adversarial-review');
expect(content).toContain('xhigh');
expect(content).toContain('Investigate and fix');
expect(content).toContain('CROSS-MODEL');
expect(content).toContain('ADVERSARIAL REVIEW SYNTHESIS');
});
test('codex integration in /ship has config-driven review step', () => {
test('adversarial review in /ship auto-scales by diff size', () => {
const content = fs.readFileSync(path.join(ROOT, 'ship', 'SKILL.md'), 'utf-8');
expect(content).toContain('Codex review');
expect(content).toContain('codex_reviews');
expect(content).toContain('codex review');
expect(content).toContain('codex-review');
expect(content).toContain('Adversarial review (auto-scaled)');
expect(content).toContain('< 50');
expect(content).toContain('200+');
expect(content).toContain('adversarial-review');
expect(content).toContain('xhigh');
expect(content).toContain('Investigate and fix');
});
test('codex-host ship/review do NOT contain codex review step', () => {
test('codex-host ship/review do NOT contain adversarial review step', () => {
const shipContent = fs.readFileSync(path.join(ROOT, '.agents', 'skills', 'gstack-ship', 'SKILL.md'), 'utf-8');
expect(shipContent).not.toContain('codex review --base');
expect(shipContent).not.toContain('Investigate and fix');
const reviewContent = fs.readFileSync(path.join(ROOT, '.agents', 'skills', 'gstack-review', 'SKILL.md'), 'utf-8');
expect(reviewContent).not.toContain('codex review --base');
expect(reviewContent).not.toContain('codex_reviews');
expect(reviewContent).not.toContain('adversarial-review');
expect(reviewContent).not.toContain('Investigate and fix');
});
@@ -1294,9 +1307,9 @@ describe('Codex skill', () => {
expect(content).toContain('codex exec');
});
test('Review Readiness Dashboard includes Codex Review row', () => {
test('Review Readiness Dashboard includes Adversarial Review row', () => {
const content = fs.readFileSync(path.join(ROOT, 'ship', 'SKILL.md'), 'utf-8');
expect(content).toContain('Codex Review');
expect(content).toContain('Adversarial');
expect(content).toContain('codex-review');
});
});