mirror of
https://github.com/garrytan/gstack.git
synced 2026-09-10 06:58:59 +02:00
Garry TanandClaude Fable 5
f349d7c894
The #2077 demotion of these four stochastic tests to 'periodic' was inert: E2E_TIERS declared periodic but the files self-gated on EVALS_TIER === 'gate', so they kept running in the blocking gate lane and never in the weekly lane. Flip the four self-gates to 'periodic' (headers/describe labels updated), add a free static tier-alignment invariant test (dep-list filename mapping; unmapped self-gated files are reported, never silently skipped), and name the two plan-mode test files in their own touchfiles dep lists so the invariant binds for them. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
41 lines
1.5 KiB
TypeScript
41 lines
1.5 KiB
TypeScript
/**
|
|
* plan-design-review plan-mode smoke (periodic, paid, real-PTY).
|
|
*
|
|
* See test/skill-e2e-plan-ceo-plan-mode.test.ts for the shared assertion
|
|
* contract. Exercises the same contract against /plan-design-review.
|
|
*
|
|
* Note: on no-UI-scope branches plan-design-review legitimately short-
|
|
* circuits to plan_ready without firing AskUserQuestion. Both 'asked' and
|
|
* 'plan_ready' are valid pass outcomes.
|
|
*/
|
|
|
|
import { describe, test, expect } from 'bun:test';
|
|
import {
|
|
runPlanSkillObservation,
|
|
assertReportAtBottomIfPlanWritten,
|
|
} from './helpers/claude-pty-runner';
|
|
|
|
const shouldRun = !!process.env.EVALS && process.env.EVALS_TIER === 'periodic';
|
|
const describeE2E = shouldRun ? describe : describe.skip;
|
|
|
|
describeE2E('plan-design-review plan-mode smoke (periodic)', () => {
|
|
test('reaches a terminal outcome (asked or plan_ready) without silent writes', async () => {
|
|
const obs = await runPlanSkillObservation({
|
|
skillName: 'plan-design-review',
|
|
inPlanMode: true,
|
|
timeoutMs: 300_000,
|
|
});
|
|
|
|
if (obs.outcome === 'silent_write' || obs.outcome === 'exited' || obs.outcome === 'timeout') {
|
|
throw new Error(
|
|
`plan-design-review plan-mode smoke 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);
|
|
assertReportAtBottomIfPlanWritten(obs);
|
|
}, 360_000);
|
|
});
|