Files
gstack/test/skill-e2e-plan-mode-no-op.test.ts
Rocky 834c6db075
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
Initial import from garrytan/gstack@026751e (main snapshot via local relay)
Source: https://github.com/garrytan/gstack/commit/026751e
2026-05-19 21:18:17 +02:00

49 lines
2.1 KiB
TypeScript

/**
* Plan-mode-info no-op regression (gate tier, paid, real-PTY).
*
* Asserts: when /plan-ceo-review is invoked OUTSIDE plan mode (no
* --permission-mode plan flag, no plan-mode reminder injected), the skill
* still reaches a terminal outcome ('asked' or 'plan_ready'). This is the
* negative coverage to the per-skill plan-mode smokes — if the
* plan-mode-info preamble section ever starts misfiring for non-plan-mode
* sessions (e.g., gating questions on a phrase that isn't there), this
* test catches it.
*
* Why this matters: outside plan mode, claude doesn't render a native
* confirmation UI. The skill must drive its own AskUserQuestion. Same
* runner, same outcome contract — just `inPlanMode: false`.
*/
import { describe, test, expect } from 'bun:test';
import { runPlanSkillObservation } from './helpers/claude-pty-runner';
const shouldRun = !!process.env.EVALS && process.env.EVALS_TIER === 'gate';
const describeE2E = shouldRun ? describe : describe.skip;
describeE2E('plan-mode-info no-op outside plan mode (gate regression)', () => {
test('skill reaches a terminal outcome outside plan mode', async () => {
const obs = await runPlanSkillObservation({
skillName: 'plan-ceo-review',
inPlanMode: false,
timeoutMs: 300_000,
});
if (obs.outcome === 'silent_write' || obs.outcome === 'exited' || obs.outcome === 'timeout') {
throw new Error(
`plan-mode no-op regression FAILED: outcome=${obs.outcome}\n` +
`summary: ${obs.summary}\n` +
`elapsed: ${obs.elapsedMs}ms\n` +
`--- evidence (last 2KB visible) ---\n${obs.evidence}`,
);
}
expect(['asked', 'plan_ready']).toContain(obs.outcome);
// Negative regression: the rendered output must NOT echo the plan-mode
// distinctive reminder phrase. If it does, the plan-mode preamble
// section is leaking outside plan mode.
const PLAN_MODE_REMINDER =
'Plan mode is active. The user indicated that they do not want you to execute yet';
expect(obs.evidence).not.toContain(PLAN_MODE_REMINDER);
}, 360_000);
});