Initial import from garrytan/gstack@026751e (main snapshot via local relay)
Some checks failed
Workflow Lint / actionlint (push) Has been cancelled
Build CI Image / build (push) Has been cancelled
Skill Docs Freshness / check-freshness (push) Has been cancelled
Periodic Evals / build-image (push) Has been cancelled
Periodic Evals / evals (map[file:test/codex-e2e.test.ts name:e2e-codex]) (push) Has been cancelled
Periodic Evals / evals (map[file:test/gemini-e2e.test.ts name:e2e-gemini]) (push) Has been cancelled
Periodic Evals / evals (map[file:test/skill-e2e-design.test.ts name:e2e-design]) (push) Has been cancelled
Periodic Evals / evals (map[file:test/skill-e2e-plan.test.ts name:e2e-plan]) (push) Has been cancelled
Periodic Evals / evals (map[file:test/skill-e2e-qa-bugs.test.ts name:e2e-qa-bugs]) (push) Has been cancelled
Periodic Evals / evals (map[file:test/skill-e2e-qa-workflow.test.ts name:e2e-qa-workflow]) (push) Has been cancelled
Periodic Evals / evals (map[file:test/skill-e2e-review.test.ts name:e2e-review]) (push) Has been cancelled
Periodic Evals / evals (map[file:test/skill-e2e-workflow.test.ts name:e2e-workflow]) (push) Has been cancelled
Periodic Evals / evals (map[file:test/skill-routing-e2e.test.ts name:e2e-routing]) (push) Has been cancelled
Some checks failed
Workflow Lint / actionlint (push) Has been cancelled
Build CI Image / build (push) Has been cancelled
Skill Docs Freshness / check-freshness (push) Has been cancelled
Periodic Evals / build-image (push) Has been cancelled
Periodic Evals / evals (map[file:test/codex-e2e.test.ts name:e2e-codex]) (push) Has been cancelled
Periodic Evals / evals (map[file:test/gemini-e2e.test.ts name:e2e-gemini]) (push) Has been cancelled
Periodic Evals / evals (map[file:test/skill-e2e-design.test.ts name:e2e-design]) (push) Has been cancelled
Periodic Evals / evals (map[file:test/skill-e2e-plan.test.ts name:e2e-plan]) (push) Has been cancelled
Periodic Evals / evals (map[file:test/skill-e2e-qa-bugs.test.ts name:e2e-qa-bugs]) (push) Has been cancelled
Periodic Evals / evals (map[file:test/skill-e2e-qa-workflow.test.ts name:e2e-qa-workflow]) (push) Has been cancelled
Periodic Evals / evals (map[file:test/skill-e2e-review.test.ts name:e2e-review]) (push) Has been cancelled
Periodic Evals / evals (map[file:test/skill-e2e-workflow.test.ts name:e2e-workflow]) (push) Has been cancelled
Periodic Evals / evals (map[file:test/skill-routing-e2e.test.ts name:e2e-routing]) (push) Has been cancelled
Source: https://github.com/garrytan/gstack/commit/026751e
This commit is contained in:
59
test/skill-e2e-office-hours-auto-mode.test.ts
Normal file
59
test/skill-e2e-office-hours-auto-mode.test.ts
Normal file
@@ -0,0 +1,59 @@
|
||||
/**
|
||||
* office-hours AskUserQuestion-blocked regression (gate, paid, real-PTY).
|
||||
*
|
||||
* v1.21+ regression: Conductor launches Claude Code with
|
||||
* `--disallowedTools AskUserQuestion --permission-mode default` (verified
|
||||
* by inspecting the parent claude process via `ps`). office-hours' first
|
||||
* step issues a startup-vs-builder mode AskUserQuestion
|
||||
* (office-hours/SKILL.md.tmpl:69); when AskUserQuestion is disallowed at
|
||||
* the tool-registry level the model cannot ask and silently picks one mode,
|
||||
* breaking the whole interactive premise. This test asserts that question
|
||||
* still surfaces — fix must route through mcp__conductor__AskUserQuestion
|
||||
* (when present) or plan-file + ExitPlanMode flow.
|
||||
*
|
||||
* Filename keeps `auto-mode` for branch-history continuity. Auto-mode (the
|
||||
* AUTO_DECIDE preamble path when QUESTION_TUNING=true) is a related but
|
||||
* distinct silencing mechanism; both share the same fix surface.
|
||||
*/
|
||||
|
||||
import { describe, test, expect } from 'bun:test';
|
||||
import { runPlanSkillObservation, planFileHasDecisionsSection } from './helpers/claude-pty-runner';
|
||||
|
||||
const shouldRun = !!process.env.EVALS && process.env.EVALS_TIER === 'gate';
|
||||
const describeE2E = shouldRun ? describe : describe.skip;
|
||||
|
||||
describeE2E('office-hours AskUserQuestion-blocked smoke (gate)', () => {
|
||||
// Pass envelope is ['asked', 'plan_ready']; failure signals are
|
||||
// 'auto_decided' + silent_write/exited/timeout.
|
||||
test('AskUserQuestion surfaces when --disallowedTools AskUserQuestion is set', async () => {
|
||||
const obs = await runPlanSkillObservation({
|
||||
skillName: 'office-hours',
|
||||
inPlanMode: true,
|
||||
extraArgs: ['--disallowedTools', 'AskUserQuestion'],
|
||||
timeoutMs: 300_000,
|
||||
});
|
||||
|
||||
if (
|
||||
obs.outcome === 'auto_decided' ||
|
||||
obs.outcome === 'silent_write' ||
|
||||
obs.outcome === 'exited' ||
|
||||
obs.outcome === 'timeout'
|
||||
) {
|
||||
throw new Error(
|
||||
`office-hours AskUserQuestion-blocked regression: outcome=${obs.outcome}\n` +
|
||||
`summary: ${obs.summary}\n` +
|
||||
`elapsed: ${obs.elapsedMs}ms\n` +
|
||||
`--- evidence (last 2KB visible) ---\n${obs.evidence}`,
|
||||
);
|
||||
}
|
||||
if (obs.outcome === 'plan_ready') {
|
||||
if (!obs.planFile || !planFileHasDecisionsSection(obs.planFile)) {
|
||||
throw new Error(
|
||||
`office-hours AskUserQuestion-blocked regression: plan_ready without a "## Decisions" section in ${obs.planFile ?? '<no plan file detected>'} — startup-vs-builder mode question was silently skipped.\n` +
|
||||
`--- evidence (last 2KB visible) ---\n${obs.evidence}`,
|
||||
);
|
||||
}
|
||||
}
|
||||
expect(['asked', 'plan_ready']).toContain(obs.outcome);
|
||||
}, 360_000);
|
||||
});
|
||||
Reference in New Issue
Block a user