feat: Codex second opinion in /office-hours (v0.11.4.0) (#353)

* feat: add Codex second opinion to /office-hours (Phase 3.5)

New generateCodexSecondOpinion resolver that adds an opt-in cross-model
cold read between premise challenge and alternatives generation.
Codex independently reviews the session's problem statement, answers,
and premises without seeing Claude's reasoning.

Includes: temp file prompt assembly (shell injection safe), two mode-
specific prompt variants (startup/builder), cross-model synthesis,
premise revision check, and 7 unit tests.

* chore: regenerate office-hours SKILL.md files

* chore: bump version and changelog (v0.11.4.0)

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
2026-03-22 20:53:13 -07:00
committed by GitHub
parent 4cd4d11cb0
commit 5aee6db702
6 changed files with 245 additions and 1 deletions
+44
View File
@@ -705,6 +705,50 @@ describe('DESIGN_SKETCH resolver', () => {
});
});
// --- {{CODEX_SECOND_OPINION}} resolver tests ---
describe('CODEX_SECOND_OPINION resolver', () => {
const content = fs.readFileSync(path.join(ROOT, 'office-hours', 'SKILL.md'), 'utf-8');
const codexContent = fs.readFileSync(path.join(ROOT, '.agents', 'skills', 'gstack-office-hours', 'SKILL.md'), 'utf-8');
test('Phase 3.5 section appears in office-hours SKILL.md', () => {
expect(content).toContain('Phase 3.5: Cross-Model Second Opinion');
});
test('contains codex exec invocation', () => {
expect(content).toContain('codex exec');
});
test('contains opt-in AskUserQuestion text', () => {
expect(content).toContain('second opinion from a different AI model');
});
test('contains cross-model synthesis instructions', () => {
expect(content).toMatch(/[Ss]ynthesis/);
expect(content).toContain('Where Claude agrees with Codex');
});
test('contains premise revision check', () => {
expect(content).toContain('Codex challenged premise');
});
test('contains error handling for auth, timeout, and empty', () => {
expect(content).toMatch(/[Aa]uth.*fail/);
expect(content).toMatch(/[Tt]imeout/);
expect(content).toMatch(/[Ee]mpty response/);
});
test('Codex host variant does NOT contain the Phase 3.5 resolver output', () => {
// The resolver returns '' for codex host, so the interactive section is stripped.
// Static template references to "Phase 3.5" in prose/conditionals are fine.
// Other resolvers (design review lite) may contain CODEX_NOT_AVAILABLE, so we
// check for Phase 3.5-specific markers only.
expect(codexContent).not.toContain('Phase 3.5: Cross-Model Second Opinion');
expect(codexContent).not.toContain('TMPERR_OH');
expect(codexContent).not.toContain('gstack-codex-oh-');
});
});
// --- {{BENEFITS_FROM}} resolver tests ---
describe('BENEFITS_FROM resolver', () => {