starmen1265
0878535cb8
主要变更： - Capability Evolver 技能大幅升级 - 新增 LLM 审查、叙事记忆、反思机制模块 - 改进 Agent 间通信协议和技能搜索 - 整合 Git 备份到 evolver-run.sh - Agent 配置与日志更新 - dev-assist/haonan/main 认证和会话配置 - 5 个 agent 的 AGENTS.md 文档更新 - haonan 的 MEMORY.md 和 SOUL.md 更新 - 新增功能目录 - hooks/self-improvement 自我改进钩子 - memory/evolution 进化记忆状态 - workspace/.learnings/ 学习记录 - 清理 - 删除 scripts/git-auto-sync.sh（已整合到 evolver） - 删除旧的 _meta.json 配置 - 忽略临时工作空间目录
1.1 KiB
1.1 KiB
Learnings
Corrections, insights, and knowledge gaps captured during development.
Categories: correction | insight | knowledge_gap | best_practice Areas: frontend | backend | infra | tests | docs | config Statuses: pending | in_progress | resolved | wont_fix | promoted | promoted_to_skill
Status Definitions
| Status | Meaning |
|---|---|
pending |
Not yet addressed |
in_progress |
Actively being worked on |
resolved |
Issue fixed or knowledge integrated |
wont_fix |
Decided not to address (reason in Resolution) |
promoted |
Elevated to CLAUDE.md, AGENTS.md, or copilot-instructions.md |
promoted_to_skill |
Extracted as a reusable skill |
Skill Extraction Fields
When a learning is promoted to a skill, add these fields:
**Status**: promoted_to_skill
**Skill-Path**: skills/skill-name
Example:
## [LRN-20250115-001] best_practice
**Logged**: 2025-01-15T10:00:00Z
**Priority**: high
**Status**: promoted_to_skill
**Skill-Path**: skills/docker-m1-fixes
**Area**: infra
### Summary
Docker build fails on Apple Silicon due to platform mismatch
...