mirror of
https://github.com/garrytan/gstack.git
synced 2026-09-09 22:48:57 +02:00
Garry TanandClaude Fable 5
290c71046b
Mechanical two-liner swap in 34 files (each keeping its declared tier — all 36 predicates verified against E2E_TIERS before migrating); the two files with compound gates (overlay-harness's EvalCollector feed, codex-e2e's CODEX_AVAILABLE) keep their extra conditions via e2eTierEnabled. Tier rationale comments preserved. codex-e2e/gemini-e2e/benchmark-providers keep their distinct stderr-message gate shapes by design. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
38 lines
1.2 KiB
TypeScript
38 lines
1.2 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 { 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,
|
|
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,
|
|
);
|
|
});
|