CalvinBackup/gstack
1
0
Fork 0
mirror of https://github.com/garrytan/gstack.git synced 2026-09-10 15:09:00 +02:00
Code Issues Packages Projects Releases Wiki Activity

test(evals): codex runner gains sections option — review variant 88% smaller

Browse Source 
runCodexSkill/installSkillToTempHome accept sections?: string[] routed
through extractSkillSections; codex-review-findings wired (1465->181
lines). codex-discover-skill deliberately keeps the FULL copy — its
stderr assertions validate that the real generated artifact loads.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Garry Tan
2026-08-15 08:50:03 -07:00
co-authored by Claude Fable 5
parent 9963deac37
commit 5338834654
2 changed files with 29 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/codex-e2e.test.ts
+11 -2
View File
@@ -16,6 +16,7 @@
import { describe, test, expect, beforeAll, afterAll } from 'bun:test';
import { runCodexSkill, parseCodexJSONL, installSkillToTempHome } from './helpers/codex-session-runner';
import type { CodexResult } from './helpers/codex-session-runner';
import { CODEX_REVIEW_E2E_SECTIONS } from './helpers/skill-fixture';
import { EvalCollector } from './helpers/eval-store';
import type { EvalTestEntry } from './helpers/eval-store';
import { selectTests, detectBaseBranch, getChangedFiles, E2E_TOUCHFILES, GLOBAL_TOUCHFILES } from './helpers/touchfiles';
@@ -139,7 +140,11 @@ describeCodex('Codex E2E', () => {
});
testIfSelected('codex-discover-skill', async () => {
// Install gstack-review skill to a temp HOME and ask Codex to list skills
// Install gstack-review skill to a temp HOME and ask Codex to list skills.
// Deliberately installs the FULL generated SKILL.md (no `sections`): this
// test's purpose is to prove the real artifact loads under Codex — the
// stderr assertions below ('invalid' / 'Skipped loading') would be
// meaningless against an extracted fixture.
const skillDir = path.join(testWorktree, '.agents', 'skills', 'gstack-review');
const result = await runCodexSkill({
@@ -172,7 +177,10 @@ describeCodex('Codex E2E', () => {
// code review, and produce structured review output with findings/issues.
// Accepts Codex timeout (exit 124/137) as non-failure since that's a CLI perf issue.
testIfSelected('codex-review-findings', async () => {
// Install gstack-review skill and ask Codex to review the worktree
// Install gstack-review and ask Codex to review the worktree. The skill
// fixture is EXTRACTED to the core review-workflow sections — the full
// Codex host variant is ~1460 lines and this test only exercises the
// diff-review flow (CLAUDE.md: "E2E test fixtures: extract, don't copy").
const skillDir = path.join(testWorktree, '.agents', 'skills', 'gstack-review');
const result = await runCodexSkill({
@@ -181,6 +189,7 @@ describeCodex('Codex E2E', () => {
timeoutMs: 540_000,
cwd: testWorktree,
skillName: 'gstack-review',
sections: CODEX_REVIEW_E2E_SECTIONS,
});
logCodexCost('codex-review-findings', result);