mirror of
https://github.com/garrytan/gstack.git
synced 2026-05-09 22:19:47 +08:00
3aee5a7476
Adds 4 finding-floor tests (one per plan-* skill) that catch the May 2026 transcript-bug class — model wrote a plan and called ExitPlanMode without firing any review-phase AskUserQuestion. Asserts via runPlanSkillFloorCheck that ANY non-permission AUQ render fires before the agent reaches plan_ready. Verified: - Eng floor: passed in 59s - CEO floor: passed in 197s - Design floor: passed - Devex floor: passed - Total ~$2-6 per CI run; only triggers on diff against the 4 plan-* templates, the shared resolver review.ts, the seeds fixture, or the PTY runner helper. Fixtures live in test/fixtures/forcing-finding-seeds.ts, one constant per skill. Each seed is engineered to force at least one obvious finding under that skill's review focus (architectural smell for eng, scope-creep for ceo, UI-slop for design, painful onboarding for devex). Touchfiles wiring: - E2E_TOUCHFILES: 4 plan-*-finding-floor entries with deps on the matching skill template, the shared resolver, the seeds fixture, and the PTY runner helper - E2E_TIERS: all 4 entries marked 'gate' - touchfiles.test.ts: count assertion bumped 21→22 with explicit plan-ceo-finding-floor containment check Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
53 lines
2.2 KiB
TypeScript
53 lines
2.2 KiB
TypeScript
/**
|
|
* /plan-eng-review AskUserQuestion floor regression (gate, paid, real-PTY).
|
|
*
|
|
* Catches the May 2026 transcript bug where /plan-eng-review wrote a
|
|
* multi-section review plan to ~/.claude/plans/ and called ExitPlanMode
|
|
* without firing any AskUserQuestion. See
|
|
* `.context/attachments/pasted_text_2026-05-06_10-25-23.txt`.
|
|
*
|
|
* Uses runPlanSkillFloorCheck — a minimal "did the agent fire ANY AUQ?"
|
|
* observer that exits early on the first non-permission numbered-option
|
|
* render. See claude-pty-runner.ts for why this is separate from the
|
|
* runPlanSkillCounting harness used by periodic finding-count tests.
|
|
*
|
|
* Tier: gate. Budget: 10 min (early exit on success ~30-90s typical).
|
|
* Cost: ~$0.50-$1.50 per run depending on early-exit timing.
|
|
*/
|
|
|
|
import { describe, test } from 'bun:test';
|
|
import { runPlanSkillFloorCheck } from './helpers/claude-pty-runner';
|
|
import { FORCING_FLOOR_ENG } from './fixtures/forcing-finding-seeds';
|
|
|
|
const shouldRun = !!process.env.EVALS && process.env.EVALS_TIER === 'gate';
|
|
const describeE2E = shouldRun ? describe : describe.skip;
|
|
|
|
describeE2E('/plan-eng-review AskUserQuestion floor (gate)', () => {
|
|
test(
|
|
'seeded forcing finding causes the agent to fire at least one AskUserQuestion',
|
|
async () => {
|
|
const obs = await runPlanSkillFloorCheck({
|
|
skillName: 'plan-eng-review',
|
|
slashCommand: '/plan-eng-review',
|
|
followUpPrompt: FORCING_FLOOR_ENG,
|
|
cwd: process.cwd(),
|
|
timeoutMs: 600_000,
|
|
env: { QUESTION_TUNING: 'false', EXPLAIN_LEVEL: 'default' },
|
|
});
|
|
|
|
if (obs.outcome !== 'auq_observed') {
|
|
throw new Error(
|
|
`floor test FAILED: outcome=${obs.outcome} elapsed=${obs.elapsedMs}ms\n` +
|
|
`summary: ${obs.summary}\n` +
|
|
`If outcome is plan_ready or completion_summary, this is the transcript-bug ` +
|
|
`regression — agent reached terminal without firing AskUserQuestion. See ` +
|
|
`.context/attachments/pasted_text_2026-05-06_10-25-23.txt.\n` +
|
|
`If outcome is timeout, agent may just be slow — re-run or increase budget.\n` +
|
|
`--- evidence (last 3KB) ---\n${obs.evidence}`,
|
|
);
|
|
}
|
|
},
|
|
660_000,
|
|
);
|
|
});
|