code-review-adversarialA
Deep code review via a committee of specialized reviewers with PR-type-aware playbooks and convergence. Feature PRs → evaluate better alternatives; bugfix PRs → verify fix correctness + regression; design-heavy PRs (proto/contract only) → AIP/compatibility audit. Dispatches 2-4 reviewers from distinct stances, converges via collaborative arbiter, outputs structured verdict. Use for high-stakes PRs (concurrency, security, contract changes) or when the user asks for "深度评审", "对抗复核", "adversarial...
ai-agentsgojava