Files
gstack/test/skill-e2e-plan-design-finding-floor.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

38 lines
1.3 KiB
TypeScript

/**
* /plan-design-review AskUserQuestion floor regression (gate, paid, real-PTY).
*
* See test/skill-e2e-plan-eng-finding-floor.test.ts for the contract.
*/
import { describe, test } from 'bun:test';
import { runPlanSkillFloorCheck } from './helpers/claude-pty-runner';
import { FORCING_FLOOR_DESIGN } from './fixtures/forcing-finding-seeds';
const shouldRun = !!process.env.EVALS && process.env.EVALS_TIER === 'gate';
const describeE2E = shouldRun ? describe : describe.skip;
describeE2E('/plan-design-review AskUserQuestion floor (gate)', () => {
test(
'seeded forcing finding causes the agent to fire at least one AskUserQuestion',
async () => {
const obs = await runPlanSkillFloorCheck({
skillName: 'plan-design-review',
slashCommand: '/plan-design-review',
followUpPrompt: FORCING_FLOOR_DESIGN,
cwd: process.cwd(),
timeoutMs: 600_000,
env: { QUESTION_TUNING: 'false', EXPLAIN_LEVEL: 'default' },
});
if (obs.outcome !== 'auq_observed') {
throw new Error(
`floor test FAILED: outcome=${obs.outcome} elapsed=${obs.elapsedMs}ms\n` +
`summary: ${obs.summary}\n` +
`--- evidence (last 3KB) ---\n${obs.evidence}`,
);
}
},
660_000,
);
});