mirror of
https://github.com/garrytan/gstack.git
synced 2026-09-10 15:09:00 +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>
38 lines
1.3 KiB
TypeScript
38 lines
1.3 KiB
TypeScript
/**
|
|
* /plan-design-review AskUserQuestion floor regression (periodic, 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 === 'periodic';
|
|
const describeE2E = shouldRun ? describe : describe.skip;
|
|
|
|
describeE2E('/plan-design-review AskUserQuestion floor (periodic)', () => {
|
|
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,
|
|
);
|
|
});
|