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-opus-47.test.ts

@@ -18,6 +18,7 @@
  */
 
 import { describe, test, expect, afterAll } from 'bun:test';
+import { JUDGE_MS, CAPTURE_MS, CAPTURE_LONG_MS } from './helpers/eval-budgets';
 import { runSkillTest } from './helpers/session-runner';
 import { EvalCollector } from './helpers/eval-store';
 import { extractSkillHead } from './helpers/skill-fixture';
@@ -204,7 +205,7 @@ describeE2E('Opus 4.7 overlay behavior evals', () => {
             workingDirectory: armA,
             maxTurns: 5,
             allowedTools: ['Read', 'Bash', 'Glob', 'Grep'],
-            timeout: 90_000,
+            timeout: JUDGE_MS,
             testName: 'fanout-arm-overlay-on',
             runId,
             model: OPUS_47,
@@ -214,7 +215,7 @@ describeE2E('Opus 4.7 overlay behavior evals', () => {
             workingDirectory: armB,
             maxTurns: 5,
             allowedTools: ['Read', 'Bash', 'Glob', 'Grep'],
-            timeout: 90_000,
+            timeout: JUDGE_MS,
             testName: 'fanout-arm-overlay-off',
             runId,
             model: OPUS_47,
@@ -262,7 +263,7 @@ describeE2E('Opus 4.7 overlay behavior evals', () => {
         fs.rmSync(armB, { recursive: true, force: true });
       }
     },
-    240_000,
+    CAPTURE_MS,
   );
 
   test(
@@ -281,7 +282,7 @@ describeE2E('Opus 4.7 overlay behavior evals', () => {
               workingDirectory: root,
               maxTurns: 3,
               allowedTools: ['Skill', 'Read', 'Bash', 'Glob', 'Grep'],
-              timeout: 90_000,
+              timeout: JUDGE_MS,
               testName: `routing-${c.name}`,
               runId,
               model: OPUS_47,
@@ -348,6 +349,6 @@ describeE2E('Opus 4.7 overlay behavior evals', () => {
         fs.rmSync(root, { recursive: true, force: true });
       }
     },
-    360_000,
+    CAPTURE_LONG_MS,
   );
 });