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>

test/skill-e2e-plan-eng-plan-mode.test.ts

@@ -6,6 +6,7 @@
  */
 
 import { test, expect } from 'bun:test';
+import { CAPTURE_MS, CAPTURE_LONG_MS } from './helpers/eval-budgets';
 import { describeE2ETier } from './helpers/e2e-gate';
 import {
   runPlanSkillObservation,
@@ -50,7 +51,7 @@ describeE2E('plan-eng-review plan-mode smoke (periodic)', () => {
     const obs = await runPlanSkillObservation({
       skillName: 'plan-eng-review',
       inPlanMode: true,
-      timeoutMs: 300_000,
+      timeoutMs: CAPTURE_MS,
     });
 
     if (obs.outcome === 'silent_write' || obs.outcome === 'exited' || obs.outcome === 'timeout') {
@@ -63,7 +64,7 @@ describeE2E('plan-eng-review plan-mode smoke (periodic)', () => {
     }
     expect(['asked', 'plan_ready']).toContain(obs.outcome);
     assertReportAtBottomIfPlanWritten(obs);
-  }, 360_000);
+  }, CAPTURE_LONG_MS);
 
   // D3-B / D4-B: when a plan with guaranteed-finding-triggering complexity
   // is seeded, the skill MUST fire AskUserQuestion (or fall back to a
@@ -79,7 +80,7 @@ describeE2E('plan-eng-review plan-mode smoke (periodic)', () => {
       // must use mcp__*__AskUserQuestion (outcome='asked') or fall back to
       // writing Decisions ('plan_ready').
       extraArgs: ['--disallowedTools', 'AskUserQuestion'],
-      timeoutMs: 300_000,
+      timeoutMs: CAPTURE_MS,
     });
 
     if (
@@ -118,5 +119,5 @@ describeE2E('plan-eng-review plan-mode smoke (periodic)', () => {
     // question.
     expect(obs.scopeGateQuestionObserved ?? false).toBe(false);
     expect(obs.scopeGateAutoSelectObserved ?? false).toBe(true);
-  }, 360_000);
+  }, CAPTURE_LONG_MS);
 });