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
@@ -31,6 +31,7 @@
*/
import { test, expect } from 'bun:test';
import { CAPTURE_MS, CAPTURE_LONG_MS } from './helpers/eval-budgets';
import { describeE2ETier } from './helpers/e2e-gate';
import { runPlanSkillObservation } from './helpers/claude-pty-runner';
@@ -62,7 +63,7 @@ describeE2E('plan-mode-info no-op outside plan mode (gate regression)', () => {
const obs = await runPlanSkillObservation({
skillName,
inPlanMode: false,
timeoutMs: 300_000,
timeoutMs: CAPTURE_MS,
// eng/design: force the prose-fallback path. The unconditional
// gate-must-ask assert below pins the render shape the detector
// anchors on, and only the --disallowedTools prose fallback makes
@@ -115,7 +116,7 @@ describeE2E('plan-mode-info no-op outside plan mode (gate regression)', () => {
);
}
}
}, 360_000);
}, CAPTURE_LONG_MS);
}
// Named-target exception (outside plan mode): a pasted draft IS an
@@ -130,7 +131,7 @@ describeE2E('plan-mode-info no-op outside plan mode (gate regression)', () => {
inPlanMode: false,
initialPlanContent: NAMED_TARGET_SEED,
trackTokens: [SEED_TOKEN],
timeoutMs: 300_000,
timeoutMs: CAPTURE_MS,
});
if (
@@ -159,5 +160,5 @@ describeE2E('plan-mode-info no-op outside plan mode (gate regression)', () => {
// unreachable outside plan mode (extractPlanFilePath only matches
// plan-mode save renders).
expect(obs.tokensObserved?.[SEED_TOKEN] ?? false).toBe(true);
}, 360_000);
}, CAPTURE_LONG_MS);
});