refactor(test): mechanical sweep — 298 paid-test timeouts onto eval-budget tiers

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>
This commit is contained in:
Garry Tan
2026-08-29 05:25:06 +00:00
co-authored by Claude Fable 5
parent 74ae357e0f
commit 6841183c35
69 changed files with 367 additions and 298 deletions
+5 -4
View File
@@ -10,6 +10,7 @@
*/
import { test, expect } from 'bun:test';
import { CAPTURE_MS, CAPTURE_LONG_MS } from './helpers/eval-budgets';
import { describeE2ETier } from './helpers/e2e-gate';
import {
runPlanSkillObservation,
@@ -46,7 +47,7 @@ describeE2E('plan-design-review plan-mode smoke (periodic)', () => {
const obs = await runPlanSkillObservation({
skillName: 'plan-design-review',
inPlanMode: true,
timeoutMs: 300_000,
timeoutMs: CAPTURE_MS,
});
if (obs.outcome === 'silent_write' || obs.outcome === 'exited' || obs.outcome === 'timeout') {
@@ -59,7 +60,7 @@ describeE2E('plan-design-review plan-mode smoke (periodic)', () => {
}
expect(['asked', 'plan_ready']).toContain(obs.outcome);
assertReportAtBottomIfPlanWritten(obs);
}, 360_000);
}, CAPTURE_LONG_MS);
// Plan-mode scope-gate bypass: with a seeded UI-heavy plan in plan mode,
// the gate must NOT render its "What should I review?" menu — it
@@ -71,7 +72,7 @@ describeE2E('plan-design-review plan-mode smoke (periodic)', () => {
skillName: 'plan-design-review',
inPlanMode: true,
initialPlanContent: SEED_PLAN_UI_HEAVY,
timeoutMs: 300_000,
timeoutMs: CAPTURE_MS,
});
if (
@@ -95,5 +96,5 @@ describeE2E('plan-design-review plan-mode smoke (periodic)', () => {
// though the seed arrives as a pasted user message).
expect(obs.scopeGateQuestionObserved ?? false).toBe(false);
expect(obs.scopeGateAutoSelectObserved ?? false).toBe(true);
}, 360_000);
}, CAPTURE_LONG_MS);
});