CalvinBackup/gstack
1
0
Fork 0
mirror of https://github.com/garrytan/gstack.git synced 2026-06-07 10:33:55 +02:00
Code Issues Packages Projects Releases Wiki Activity

fix: resolve merge conflicts — bump to v0.14.5.0, keep both CHANGELOG entries

Browse Source 
Main shipped v0.14.4.0 (Review Army). Our branch's GStack Browser entry
bumps to v0.14.5.0. Both entries preserved in chronological order.
This commit is contained in:
Garry Tan
2026-03-30 21:12:03 -07:00
parent 151d68b08f a4a181ca92
commit 8ccb30d516
24 changed files with 1667 additions and 309 deletions
Download Patch File Download Diff File Expand all files Collapse all files
CHANGELOG.md
+21 -1
View File
@@ -1,6 +1,6 @@
# Changelog
## [0.14.4.0] - 2026-03-31 — GStack Browser: Double-Click AI Browser
## [0.14.5.0] - 2026-03-31 — GStack Browser: Double-Click AI Browser
GStack Browser is a macOS .app you can double-click to launch an AI-controlled browser. Chromium opens with the sidebar baked in, Claude Code ready to go. No terminal needed. Sites like Google and NYTimes work without captchas because the browser now has anti-bot stealth patches. The menu bar says "GStack Browser" instead of "Google Chrome for Testing."
@@ -21,6 +21,26 @@ GStack Browser is a macOS .app you can double-click to launch an AI-controlled b
- **Extension auth bootstrap.** `background.js` now reads token from `/health` instead of `chrome.runtime.getURL('.auth.json')`. Simpler, works everywhere.
- **Security test updated.** `server-auth.test.ts` updated to verify token IS present in `/health` (localhost-only, safe) instead of verifying it was removed.
## [0.14.4.0] - 2026-03-31 — Review Army: Parallel Specialist Reviewers
Every `/review` now dispatches specialist subagents in parallel. Instead of one agent applying one giant checklist, you get focused reviewers for testing gaps, maintainability, security, performance, data migrations, API contracts, and adversarial red-teaming. Each specialist reads the diff independently with fresh context, outputs structured JSON findings, and the main agent merges, deduplicates, and boosts confidence when multiple specialists flag the same issue. Small diffs (<50 lines) skip specialists entirely for speed. Large diffs (200+ lines) activate the Red Team for adversarial analysis on top.
### Added
- **7 specialist reviewers** running in parallel via Agent tool subagents. Always-on: Testing + Maintainability. Conditional: Security (auth scope), Performance (backend/frontend), Data Migration (migration files), API Contract (controllers/routes), Red Team (large diffs or critical findings).
- **JSON finding schema.** Specialists output structured JSON objects with severity, confidence, path, line, category, fix, and fingerprint fields. Reliable parsing, no more pipe-delimited text.
- **Fingerprint-based dedup.** When two specialists flag the same file:line:category, the finding gets boosted confidence and a "MULTI-SPECIALIST CONFIRMED" marker.
- **PR Quality Score.** Every review computes a 0-10 quality score: `10 - (critical * 2 + informational * 0.5)`. Logged to review history for trending via `/retro`.
- **3 new diff-scope signals.** `gstack-diff-scope` now detects SCOPE_MIGRATIONS, SCOPE_API, and SCOPE_AUTH to activate the right specialists.
- **Learning-informed specialist prompts.** Each specialist gets past learnings for its domain injected into the prompt, so reviews get smarter over time.
- **14 new diff-scope tests** covering all 9 scope signals including the 3 new ones.
- **7 new E2E tests** (5 gate, 2 periodic) covering migration safety, N+1 detection, delivery audit, quality score, JSON schema compliance, red team activation, and multi-specialist consensus.
### Changed
- **Review checklist refactored.** Categories now covered by specialists (test gaps, dead code, magic numbers, performance, crypto) removed from the main checklist. Main agent focuses on CRITICAL pass only.
- **Delivery Integrity enhanced.** The existing plan completion audit now investigates WHY items are missing (not just that they're missing) and logs plan-file discrepancies as learnings. Commit-message inference is informational only, never persisted.
## [0.14.3.0] - 2026-03-31 — Always-On Adversarial Review + Scope Drift + Plan Mode Design Tools
Every code review now runs adversarial analysis from both Claude and Codex, regardless of diff size. A 5-line auth change gets the same cross-model scrutiny as a 500-line feature. The old "skip adversarial for small diffs" heuristic is gone... diff size was never a good proxy for risk.