CalvinBackup/gstack
1
0
Fork 0
mirror of https://github.com/garrytan/gstack.git synced 2026-05-05 05:05:08 +02:00
Code Issues Packages Projects Releases Wiki Activity

fix: harden codex-review E2E — extract SKILL.md section, bump maxTurns to 25

Browse Source 
The test was copying the full 55KB/1075-line codex SKILL.md into the fixture,
requiring 8 Read calls just to consume it and exhausting the 15-turn budget
before reaching the actual codex review command. Now extracts only the
review-relevant section (~6KB/148 lines), reducing Read calls from 8 to 1.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Garry Tan
2026-04-06 22:41:26 -07:00
parent a3307f04fb
commit 3856689b10
1 changed files with 15 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/skill-e2e-workflow.test.ts
+15 -5
View File
@@ -467,8 +467,18 @@ describeIfSelected('Codex skill E2E', ['codex-review'], () => {
run('git', ['add', 'user_controller.rb']);
run('git', ['commit', '-m', 'add vulnerable controller']);
// Copy the codex skill file
fs.copyFileSync(path.join(ROOT, 'codex', 'SKILL.md'), path.join(codexDir, 'codex-SKILL.md'));
// Extract only the review-relevant section from codex SKILL.md (~120 lines vs 1075).
// Full SKILL.md is 55KB / ~14K tokens — takes 8 Read calls to consume, exhausting turns.
const full = fs.readFileSync(path.join(ROOT, 'codex', 'SKILL.md'), 'utf-8');
const startMarker = '# /codex — Multi-AI Second Opinion';
const endMarker = '## Plan File Review Report';
const start = full.indexOf(startMarker);
const end = full.indexOf(endMarker, start);
const reviewSection = full.slice(
start >= 0 ? start : 0,
end > start ? end : undefined,
);
fs.writeFileSync(path.join(codexDir, 'codex-SKILL.md'), reviewSection);
});
afterAll(() => {
@@ -485,11 +495,11 @@ describeIfSelected('Codex skill E2E', ['codex-review'], () => {
const result = await runSkillTest({
prompt: `You are in a git repo on branch feature/add-vuln with changes against main.
Read codex-SKILL.md for the /codex skill instructions.
Run /codex review to review the current diff against main.
Read codex-SKILL.md for the /codex review instructions (it's short — ~120 lines).
Follow those instructions to run codex review against the diff on this branch.
Write the full output (including the GATE verdict) to ${codexDir}/codex-output.md`,
workingDirectory: codexDir,
maxTurns: 15,
maxTurns: 25,
timeout: 300_000,
testName: 'codex-review',
runId,