宜博 / lemonboss

Phase 1 核心改进:

1. Pipeline↔Task 系统打通:
   - task/report 回调自动推进 Pipeline 步骤
   - findActiveRunStep() 按 agentId 定位活跃步骤
   - 扫描所有公司的 Pipeline Runs 实现跨公司桥接

2. Pipeline 循环执行:
   - 新增 pipeline.loop 配置项
   - Run 完成后自动启动下一轮 (最大 maxLoops=365)
   - loopCount 计数器追踪循环轮次

3. COO 质量门控:
   - 新增 rejectStep() 驳回方法，含驳回历史记录
   - POST /api/agent/task/reject API 端点
   - POST /api/company/:id/pipelines/runs/:runId/reject 路由
   - node bin/lemon.js task reject CLI 命令
   - 驳回后自动唤醒 Agent 重做，注入改进意见

4. COO 模板全面强化:
   - agent.md: 4维度评分体系、质量审核流程图
   - soul.md: 性格、价值观、决策原则
   - tools.md: 新增 task reject 核心工具
   - heartbeat.md: 结构化巡检清单 + 升级规则

1. Rewrote master/agent.md: strict anti-overreach rules, cleaned git merge conflicts
2. Enhanced agent-creator/agent.md: force Write tool for new files, mandatory task report
3. Implemented task/report callback: auto-wakes sender agent to continue next steps
   - Added .tasks/ metadata persistence for dispatch→report traceability
   - task/report sends [TASK_CALLBACK] to dispatching agent on done/failed

- company.js: call heartbeatService._setupAgentHeartbeat after hire
- CEO agent.md: enforce 3-step continuous execution in same turn
- All CXO heartbeat intervals: 5 minutes
- task dispatch message: self-drive directive, use lemon CLI
- bin/lemon.js: add 'task report' command

…ter Agent cognitive auto-recovery loop

- Refactored CompanyDashboard into read-only Observer UI
- Enforced strict companyId:roleId namespacing across Node APIs and AgentManager
- Added dynamic <env_status> injection to PromptBuilder for robust context
- Introduced bin/lemon.js CLI for structured LLM tool execution
- Implemented in-stream error interceptors for implicit silent retry loop

…nti-confirmation prompts, cron dedup fix

- Extracted HeartbeatService to periodically wake up agents flagged with 'heartbeat.enabled'
- Sends a silent [SYSTEM HEARTBEAT] message to trigger self-checks (e.g. OKR state validation)
- Automatically integrated service dispatch hook in server startup sequence
- Configured qa-judge to run autonomous heartbeat every 10 min

…ze Chinese keyword extraction

- Fix: The long trailing history in todo.md drowned out the actual current task keywords because English tokens (e.g. TASK, P2, from) padded the 30-keyword limit beforehand.
- Updated extractKeywords: Process Chinese characters first as they carry more weight for NLP context intent.
- Added userMessage prefix to searchText in buildSystemPrompt so newly dispatched tasks dominate keyword extraction.
- End-to-end e2e test created and passed (27/27 asserts passed)

Phase 3 features:
- autoReflect: auto-trigger on complex conversations (toolCount>=3 or duration>=60s)
  - Extracts patterns from successful conversations
  - Extracts lessons from failed conversations
  - Auto-solidifies cerebellum plans from 5+ tool-call successes
  - Writes reflection logs to memory/reflections/
  - Updates memory.md 'verified patterns' and 'lessons learned' sections
- consolidateMemory: merge short-term sessions older than 7 days into long-term/
  - Extracts frequent keywords across merged sessions
  - Writes consolidated summary to long-term/consolidate-{date}.md
  - Updates long-term/patterns.md with high-frequency patterns
- generateDailyReport: aggregate today's sessions and reflections into daily/{date}.md
- API endpoints: POST /:agentId/memory/consolidate, POST /:agentId/memory/daily-report

Test results: 16/16 passed (Phase 3 test suite)

- Hippocampus keyword matching engine (extractKeywords + score)
- Cerebellum plan storage (saveCerebellumPlan)
- Auto-sync hippocampus-index.json + hippocampus.md
- POST /:agentId/memory/cerebellum API endpoint
- buildSystemPrompt injects matched plans from hippocampus
- Use count & lastUsed tracking on plan access
- Chinese n-gram + English word tokenizer with stop words
- Fix: score formula uses entry keyword count as denominator
- Fix: useCount updates original index entry not spread copy
- Verified: OKR plan matched + injected into CEO prompt

- New: server/services/memory-service.js
  - saveSessionSummary(): auto-save session summary to short-term/
  - loadRecentMemory(): inject last 5 sessions into system prompt
  - appendToMemoryMd(): auto-append key facts with size control
- Modified: server/routes/agent-chat.js
  - buildSystemPrompt() now loads recent short-term sessions
  - Conversation completion triggers auto memory save
- Verified: CEO Agent conversation creates session file + updates memory.md

- Fix loadIdentity regex to handle **bold** markdown formatting
- Add fallback to config.json name when identity.md has no 名称 field
- Add 名称 field to Digester/Evolver/Innovator identity.md

- Implement OKR GoalsService with hierarchical node tracking
- Add /api/goals routes and integrate with dispatch/report APIs
- Create Innovator agent with Hunt→Digest→Evolving pipeline
- Create Hunter (l3-hunt), Digester (l2-digest), Evolver (evolving) meta agents
- Copy L1/L2 dependency skills into each agent's .claude/skills/
- Fix buildSystemPrompt to scan ALL skill subdirectories (critical)
- Fix agent list sorting: master pinned top, rest by lastActiveAt
- Rename master-001→master, innovator-001→innovator
- Establish meta agent output convention: write to target agent dir
- Add CXO agent base class for management agents
- Update CEO agent with delegation-first management model

- Agent as Micro-Container: each agent lives in data/agents/{id}/ with full encapsulation
- Persona vs Capability split: agent.md (identity) + .claude/skills/main_skill/SKILL.md (workflow)
- Conversations co-located: data/agents/{id}/conversations/ replaces global dir
- Meta Skills renamed: meta_hunt, meta_digest, meta_creator, meta_evolving, meta_benchmark, meta_research
- Dynamic Hot-Reload: AgentManager.getAgentConfig() falls back to filesystem scan
- Parallel Sub-Agent orchestration via Promise.all with multi-terminal UI
- Removed SQLite dependency, global skills/ directory, and legacy conversations/
- Full architecture docs: 18-local-filesystem-first-agent-encapsulation.md