CalvinBackup/gstack
1
0
Fork 0
mirror of https://github.com/garrytan/gstack.git synced 2026-09-15 01:15:29 +02:00
Code Issues Packages Projects Releases Wiki Activity

fix: repair frontier eval budgets and workflow instructions

Browse Source 
Preserve frontier models and quality thresholds while fixing truncated judge output, ordered section expansion, consent checks, QA scoring, and ship audit gates. Add regression coverage and refresh generated docs.

Co-Authored-By: OpenAI Codex <noreply@openai.com>
This commit is contained in:
Garry Tan
2026-09-09 04:11:19 +00:00
co-authored by OpenAI Codex
parent 0cbccc1c6c
commit a9f9ec5f08
43 changed files with 916 additions and 518 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/skill-ceo-section-ordering.test.ts
+9
View File
@@ -51,6 +51,15 @@ describe('plan-ceo-review carve — static ordering', () => {
expect(stop).toBeGreaterThan(step0); // STOP fires only after Step 0
});
test('mode selection precedes mode-specific analysis after approach approval', () => {
const approach = at('### 0C-bis.');
const mode = at('### 0F. Mode Selection');
const analysis = at('### 0D. Mode-Specific Analysis');
expect(approach).toBeGreaterThan(-1);
expect(mode).toBeGreaterThan(approach);
expect(analysis).toBeGreaterThan(mode);
});
test('the heavy review body (Sections 1-11) is NOT in the skeleton', () => {
expect(skeleton).not.toContain('### Section 1: Architecture Review');
expect(skeleton).not.toContain('### Section 11:');