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-conductor-prose.test.ts

@@ -21,6 +21,7 @@
  */
 
 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';
 
@@ -46,7 +47,7 @@ describeE2E('Conductor renders decisions as prose (periodic)', () => {
       extraArgs: ['--disallowedTools', 'AskUserQuestion'],
       env: { CONDUCTOR_WORKSPACE_PATH: '/tmp/conductor-prose-e2e' },
       initialPlanContent: FLAWED_PLAN,
-      timeoutMs: 300_000,
+      timeoutMs: CAPTURE_MS,
     });
 
     // The decision must reach the human as prose. 'silent_write' (wrote findings
@@ -65,5 +66,5 @@ describeE2E('Conductor renders decisions as prose (periodic)', () => {
     }
     // A prose-rendered decision brief was observed at some point in the run.
     expect(obs.proseAUQEverObserved).toBe(true);
-  }, 360_000);
+  }, CAPTURE_LONG_MS);
 });