mirror of
https://github.com/garrytan/gstack.git
synced 2026-10-01 00:49:39 +02:00
Garry Tan
a84b0b5b6d
* 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
18 lines
1.1 KiB
TypeScript
18 lines
1.1 KiB
TypeScript
import { readFileSync } from 'node:fs';
|
|
import { resolve } from 'node:path';
|
|
import type { EvalTestEntry } from './eval-store';
|
|
import { buildCookieWorkflowJudgeInput } from './cookie-workflow-judge-input';
|
|
import { COOKIE_MANUAL_REVIEW_FILE } from './cookie-workflow-manual-review';
|
|
|
|
export function manualReviewFixture(root = resolve(import.meta.dir, '../..')): EvalTestEntry {
|
|
const approval = JSON.parse(readFileSync(resolve(root, COOKIE_MANUAL_REVIEW_FILE), 'utf8'));
|
|
return {
|
|
name: 'setup-browser-cookies/SKILL.md workflow', suite: 'Cookie setup workflow quality', tier: 'llm-judge',
|
|
passed: false, execution: 'executed', exit_reason: 'provider_refusal', attempt: 1, duration_ms: 1, cost_usd: 0,
|
|
model: approval.model, prompt: buildCookieWorkflowJudgeInput(root).prompt,
|
|
error: 'Synthetic provider refusal fixture, not live model evidence',
|
|
manual_review: { approval, refusal: { stop_reason: 'refusal', response_id: 'msg_synthetic_fixture',
|
|
request_id: 'req_synthetic_fixture', model: approval.model, input_tokens: 1, output_tokens: 0, text_blocks: 0 } },
|
|
};
|
|
}
|