Structured self-improvement system for AI agents with confidence decay, cross-agent sharing, and anomaly detection. Use when: (1) After debugging sessions to capture lessons learned, (2) When receiving feedback or corrections from users, (3) Before risky actions to check relevant rules, (4) Weekly to review metrics and promote proven patterns to enforced rules, (5) Setting up persistent memory that survives session compactions.

面向AI代理的结构化自我优化系统，包含置信度衰减、代理间共享和异常检测功能。适用场景：（1）调试结束后记录经验教训，（2）收到用户反馈或修正时，（3）执行高风险操作前核查相关规则，（4）每周审查指标并将有效模式提升为强制规则，（5）建立能抵御会话压缩的持久化内存