mirror of
https://github.com/garrytan/gstack.git
synced 2026-08-31 18:30:39 +02:00
Garry TanandClaude Fable 5
6841183c35
69 files, both shapes (trailing bun-test budgets and runner timeout/timeoutMs options), ROUND-UP ONLY so nothing that passed can start failing: 75 → JUDGE_MS, 137 → CAPTURE_MS, 74 → CAPTURE_LONG_MS, 9 → PTY_MS, 3 → PTY_LONG_MS. Raw >=60s literal count in the paid scope: 395 → 97, of which 51 are non-timeout noise (fixture dates, run IDs) and 46 are enumerated justified holds (comment-carrying calibrated budgets, poll-loop constants, utility spawn waits, and the seven physical-ceiling 1_500_000 sites). The eval-budgets policy ratchet keeps the residue from regrowing. Known collapse: where an inner runner budget and its enclosing test budget now share a tier, the old stagger is gone — an overrun surfaces as a bun test timeout instead of a graceful runner timeout (diagnosability trade, not a correctness one). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
41 lines
1.4 KiB
TypeScript
41 lines
1.4 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 { test } from 'bun:test';
|
|
import { CAPTURE_LONG_MS, PTY_MS } from './helpers/eval-budgets';
|
|
import { describeE2ETier } from './helpers/e2e-gate';
|
|
import { runPlanSkillFloorCheck } from './helpers/claude-pty-runner';
|
|
import { FORCING_FLOOR_DESIGN } from './fixtures/forcing-finding-seeds';
|
|
|
|
const describeE2E = describeE2ETier('periodic');
|
|
|
|
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,
|
|
// LIVE-REPO CWD: PTY session needs the repo cwd — gstack skill
|
|
// registry + hermetic pre-trusted dir (hermetic-env trustedDirs).
|
|
cwd: process.cwd(),
|
|
timeoutMs: CAPTURE_LONG_MS,
|
|
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}`,
|
|
);
|
|
}
|
|
},
|
|
PTY_MS,
|
|
);
|
|
});
|