v1.90.0.0 feat: make browser cookie imports explicit and safe (#2964)

* fix(browse): prepare reliable cookie import wave for validation

* ci: sequence quality and behavior for validation branch

* fix(browse): isolate Windows qualification and preserve native diagnostics

* test(browse): cover cookie workflow quality and isolate Windows user paths

* test(browse): trace native member startup and initialize fresh folders

* fix(browse): keep Windows member stdin alive through EOF

* fix(browse): latch native timeouts and compare contained Edge startup

* test(browse): verify native version metadata and actual Windows argv

* test(browse): qualify Dia import on isolated macOS CI

* fix(browse): require picker origin for session mutations

* fix(browse): bound credential reads through stream completion

* test(browse): inspect owned Windows process arguments natively

* test(evals): preserve passing coverage during cookie repair reruns

* test(browse): isolate Dia qualification in a fresh macOS account

* test(browse): pass bounded integer timeouts to native Mac probes

* test(browse): distinguish Windows profile initialization from containment

* test(browse): await descendant pipe readiness before parent exit

* test(browse): initialize and restore isolated macOS Keychain state

* test(browse): initialize Windows fixture folders before qualification

* test(ci): pin the same Node runtime across Windows checks

* test(browse): distinguish native macOS browser preflight stages

* test(browse): isolate Windows descendant console lifetime

* test(browse): preserve native receipts and identify fixture lock holders

* test(browse): prepare dependency resolution before native Mac worker startup

* test(ci): include lock and close checks in native diagnostics

* test(browse): preserve native owner probe stages and subprocess deadlines

* fix(browse): classify Chromium profile-in-use exit precisely

* test(browse): retain Mac qualification evidence through cleanup failures

* test(browse): bound Mac fixture paths and retire its owned user domain

* test(browse): accept vanished fixture entries without weakening cleanup

* test(browse): identify probe-created macOS user domains safely

* test(browse): observe Mac user domains without targeting them first

* test(browse): use passive fresh-user ownership throughout Mac qualification

* test(browse): distinguish profile and registered-home Keychain lookups

* test(browse): qualify Dia under one registered account home

* test(browse): identify Dia startup and owned process-group failures

* test(browse): classify bounded Dia startup diagnostics without leaking output

* fix(test): preserve native Mac sandboxing and reap owned browser children

* fix(browse): preserve Chromium sandboxing for native profile imports

* test(browse): inspect signed Mach-O architecture without launching Xcode tools

* test(browse): sample pending Dia startup and reap on all cleanup paths

* test(browse): compare protected Dia launches in fresh Bun and Node accounts

* test(browse): inspect isolated Mac GUI readiness without browser access

* v1.90.0.0 fix: bind cookie picker actions to their document

* test: validate cookie guards and fit nested launch fixtures

* ci: configure the bundled Chromium sandbox helper

* fix(browse): classify Playwright authentication timeouts

* test: retain bounded Windows lifecycle diagnostics

* test(cso): reuse bounded NTFS precision candidates

* test(review): handle explicit preservation choices safely

* test(browse): remove owned fixture directories with explicit primitives

* test(review): distinguish descriptive reuse from edit commitments

* test: admit only the approved unscored cookie workflow refusal

* test: keep the Office Hours judge mock export-complete

* fix: keep dependency-free CI planners independent of the model SDK

* test: observe the exact holder after a native fixture unlink failure

* fix: start seeded PTY observations at owned readiness

* test: acquire identity-bound Windows deletion admission before profile resets

* test: preserve qualified Git index bits without authorizing mutations

test/helpers/llm-judge.ts

@@ -13,7 +13,8 @@ import Anthropic from '@anthropic-ai/sdk';
 import type { JSONOutputFormat } from '@anthropic-ai/sdk/resources/messages';
 import { setTimeout as delay } from 'node:timers/promises';
 
-import { CLAUDE_FRONTIER_EVAL_MODEL, resolveEvalModel } from '../../lib/eval-model';
+import { CLAUDE_FRONTIER_EVAL_MODEL, DEFAULT_JUDGE_MAX_TOKENS, resolveEvalModel } from '../../lib/eval-model';
+export { DEFAULT_JUDGE_MAX_TOKENS } from '../../lib/eval-model';
 
 export interface JudgeScore {
   clarity: number;       // 1-5
@@ -22,6 +23,35 @@ export interface JudgeScore {
   reasoning: string;
 }
 
+export interface JudgeRefusalEvidence {
+  stop_reason: 'refusal';
+  response_id: string | null;
+  request_id: string | null;
+  model: string | null;
+  input_tokens: number | null;
+  output_tokens: number | null;
+  text_blocks: number;
+}
+
+export class JudgeRefusalError extends Error {
+  readonly refusal: JudgeRefusalEvidence;
+
+  constructor(response: { id?: unknown; _request_id?: unknown; model?: unknown;
+    usage?: { input_tokens?: unknown; output_tokens?: unknown }; content: Array<{ type: string }> }) {
+    super('Judge provider refused the evaluation; no automated score');
+    this.name = 'JudgeRefusalError';
+    this.refusal = {
+      stop_reason: 'refusal',
+      response_id: typeof response.id === 'string' ? response.id : null,
+      request_id: typeof response._request_id === 'string' ? response._request_id : null,
+      model: typeof response.model === 'string' ? response.model : null,
+      input_tokens: typeof response.usage?.input_tokens === 'number' ? response.usage.input_tokens : null,
+      output_tokens: typeof response.usage?.output_tokens === 'number' ? response.usage.output_tokens : null,
+      text_blocks: response.content.filter(block => block.type === 'text').length,
+    };
+  }
+}
+
 export interface OutcomeJudgeResult {
   detected: string[];
   missed: string[];
@@ -89,7 +119,7 @@ export async function callJudge<T>(
   // Thinking and answer text share max_tokens. The old 1024-token budget
   // could be exhausted before a frontier judge emitted any JSON.
   const resolvedModel = resolveEvalModel('judge', model);
-  const maxTokens = opts?.max_tokens ?? 8192;
+  const maxTokens = opts?.max_tokens ?? DEFAULT_JUDGE_MAX_TOKENS;
   const client = new Anthropic();
 
   const makeRequest = () => client.messages.create({
@@ -134,6 +164,7 @@ export async function callJudge<T>(
     .map(block => block.text)
     .join('\n');
   try {
+    if (response.stop_reason === 'refusal') throw new JudgeRefusalError(response);
     if (opts?.jsonSchema !== undefined) {
       if (response.stop_reason !== 'end_turn') throw new Error(`Structured judge did not complete: stop_reason=${response.stop_reason}`);
       return JSON.parse(text) as T;