宜博 / lemonboss

hire() now checks system_agents (source_kind='template') before provisioning a new
company agent: if the role has a shared template row, skip copying agent.md and
instead let AgentManager.getAgentConfig()/PromptBuilder.build() resolve the prompt
from the shared legacy_path at call time, with per-company context assembled from a
new company-context.md. Roles without a template row (including the 6 ids that exist
in both system/agents/ and system/templates/, e.g. evolver-youtube-crawler) fall back
to the existing full-copy behavior unchanged.

- server/services/graph-service.js (new): lookupSharedAgentMd(), upsertOrgGraphNode()
- server/services/company-service.js: hire() reference-mode branch, _provisionReferenceAgent()
- server/src/core/agent-manager.js: getAgentConfig() resolves prompt/companyContextPath
- server/src/core/prompt-builder.js: build() concatenates company-context.md
- unit + integration tests covering all 6 acceptance criteria from
  docs/todo/system-design/27-p1-virtual-reference.md §6, including a regression test
  against the real idearun:evolver-youtube-crawler naming-collision case

Full regression suite (587 tests) passes; independent adversarial review found 0
blocking/major issues.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

Adds server/services/graph-db.js (new data/graph.sqlite: system_agents,
org_graph_nodes, org_graph_edges) and graph-seed-service.js, which scans
system/agents/, system/templates/, and data/companies/*/company.json into
seed rows without touching company-service.js's existing hire/copy path.

Real repo data diverged from the design doc's original estimates (8 not 10
global agents; 39 not 34 template dirs; system/agents/ and system/templates/
turn out to share 6 ids describing the "same" agent from two different
files) — documented in docs/todo/system-design/27-graph-agent-architecture.md
section 7 for P1/P2 to resolve.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

First concrete code commit for DevLoop. Implements all 7 services that
P0.A tools will depend on, per plan-migration P0.0.

Services (server/services/devloop/, ~900 lines):
- path-resolver.js   foundation — resolveProjectRoot + 12 derived paths;
                     sandbox + linked-new mode support; sensitive path
                     blacklist (with /tmp + os.tmpdir() exemptions);
                     ~/.devloop/linked-projects.json registry
- doc-store.js       PRD/SDD multi-file site IO + cheerio validateHTML +
                     validateUnitsSchema + canonical-JSON hashContract
                     + automatic history/ archival
- unit-registry.js   FSM (M-2: pending→coding→testing→passed/failed/blocked);
                     l2GateOpen; diffUnits (added/changed/removed);
                     reset semantics for L2 + L3
- bug-tracker.js     bugs.ndjson append-only + dedupKey + P-9 transition
                     state machine + list/stats/history aggregation
- timeline-logger.js M-13 ProcessTimeline — append/read/tail;
                     summary truncate to 280; payload oversize → ref form
- changelog-writer.js M-15 — append/read/latest for prd/sdd/units revs
- sse-broker.js      per-pid pub/sub + 25s heartbeat + stream.log replay
                     via Last-Event-ID; emit returns monotonic id
- git-vault.js       spawn-git wrapper — init/commit/tag/log/diff/status/
                     resetWorkingTree/revert/archive; per-pid mutex;
                     nothing-to-commit returns {skipped:true} not throw

Tests (server/tests/devloop/, 71 passing):
- path-resolver.test.js  (17 cases) — sensitive path · sandbox alloc · linked-new
- doc-store.test.js      (12 cases) — validateHTML · validateUnitsSchema · hashContract
- unit-registry.test.js  (15 cases) — FSM transitions · l2GateOpen · diffUnits
- bug-tracker.test.js    (10 cases) — open dedup · transition · list filter · history
- timeline-logger.test.js (9 cases) — append/read/tail · summary truncate · oversize
- git-vault.test.js      (8 cases)  — init idempotent · commit · tag · status · archive

vitest config (`globals: true`) means tests use describe/it/expect globally,
no `require('vitest')` needed (and would fail under vitest 4).

Dep added: cheerio@^1.0.0 (used by docStore.validateHTML; HTML parsing).

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

Layer 1 (P0): Per-agent session mutex
- heartbeat-service.js: skip heartbeat if previous session still active (30min safety valve)
- agent-chat.js: reject concurrent /chat requests for same agentId with different convId (429)
  Multi-turn conversations on same convId still work normally

Layer 2 (P1): Advisory file lock utility
- server/utils/file-lock.js: O_EXCL-based .lock file mechanism
  Auto-cleanup stale locks, graceful degradation on timeout

Root cause: HeartbeatService creates new convId per heartbeat, spawning
independent Claude CLI processes that concurrently write config.json and
SKILL.md, causing rollbacks and FRAUDULENT scores.

…to prevent EADDRINUSE

Fixed 4 hidden bugs where path.join(DATA_ROOT, "system", ...) was used instead
of direct path.resolve to root-level system/:

- agent-chat.js: billing log scan (line 804) and agent list scan (line 909)
- company-service.js: TEMPLATES_DIR and GLOBAL_AGENTS_DIR constants
- heartbeat-service.js: system agents scan directory

These were missed because they used path.join with a variable (DATA_ROOT)
rather than the literal string "data/system" that sed caught.

- Moved data/system/ → system/ (agents, templates, skills, data, workspace)
- Updated all server route/service path references
- Updated all script path references
- Updated all documentation references
- Restructured .gitignore for cleaner system/ vs data/ boundary

system/ = platform-shared assets (system agents, template library)
data/ = tenant-specific company instance data

- Add TaskTimeline.vue: two-pane dashboard with task list + message timeline
- Add task-service.js: aggregate cross-agent conversations into task tree
  - 4-strategy parent-child inference (explicit meta, time-overlap, conv→tpl, master→T)
  - Read messages.log for full tool call details (not just history.json)
- Add tasks.js API routes: GET /api/tasks, GET /api/tasks/:taskId/timeline
- Mount /api/tasks in agent-server.js
- Add 'Task Logs' nav entry in AppNav.vue after Templates
- Support taskId in URL (/tasks/:taskId?) for sharing/bookmarking
- Add --parent flag to CLI task dispatch for explicit parentTaskId
- Auto-detect parentTaskId in task/dispatch from sender's active task
- Add --instructions flag to template train CLI command
- Update master tools.md with new parameters

…ictly enforce empty shell company creation

- System agents: 只保留 master (data/system/agents/master)
- Templates: 所有可复用 agent 模板 (data/system/templates/)
- Companies: 公司创建时自动部署 5 个元 Agent (innovator/hunter/digester/evolver/agent-creator)

路径修复:
- agent-chat.js: /list 扫描路径修正 (system/agents + companies/*/agents)
- agent-manager.js: 动态 agent 查找路径修正
- skill-config-loader.js: 修正 agents root
- pipeline-service.js: pipelines 输出到 companies/{id}/pipelines/
- billing.log: 移至 companies/{id}/logs/ 下

Skills 标准化:
- 所有 template agent 建立 .claude/skills/main_skill/SKILL.md
- company-service._copyTemplate() 新增 .claude/ 目录复制
- innovator SKILL.md v3.0: 移除旧 l3-hunt/l2-digest 命名
- 清理重复 agent_creator, 统一为 agent-creator

清理:
- 移除 data/agents, data/workspace, data/logs, data/goals 旧目录
- 清除所有未使用的 DATA_DIR 声明
- 清除 template 中的 conversations/logs/memory 运行态数据

- Add task transition CLI and API for Context Flush & Hot Swap
- Enforce strict bash-only tool policy for Base Agents
- Inject  into system prompt for self-retrying loop
- Implement Goal node updates on transitions
- Add P0 Execute pre-approval block (Human-in-the-loop)
- Track token metrics to billing.log

- Add Company Overview tab as default landing page
- Show company info: status, uptime, agent count, heartbeat status
- Start/Stop company buttons (activate/deactivate all agent heartbeats)
- Per-agent heartbeat controls: interval dropdown, start/stop buttons
- Backend APIs: GET status, POST start/shutdown, PUT/POST agent heartbeat
- Track startedAt timestamp for uptime calculation
- Update CEO agent.md with mandatory 5-step startup workflow
- Fix company nav to default to overview tab

Phase 3 反馈进化闭环:

1. DataSourceService (运营数据接入):
   - 新增 datasource-service.js: 抽象适配器模式
   - MockAdapter: 模拟运营数据 (开发调试)
   - FileAdapter: 从本地 JSON 文件读取数据
   - 可扩展: 预留 WechatAdapter/DouyinAdapter 接口
   - API: GET /data/metrics, /data/trending, /data/attribution

2. 归因分析引擎:
   - analyzeAttribution(): 自动对比两个时间段指标
   - 计算变化百分比和趋势方向
   - 自动提取显著变化维度并生成洞察文本
   - API: GET /api/company/:id/data/attribution

3. Know-how 自动更新 (memory-service.js):
   - 新增 updateAgentKnowhow() 函数
   - autoReflect 产出的 patterns/lessons 自动写回 SKILL.md
   - 在 SKILL.md 末尾维护'经验教训(自动沉淀)'段落
   - 保留最近 20 条记录，自动清理过旧条目
   - 闭环: Agent执行 → 反思 → 经验写入SKILL → 下次读取改进行为

Phase 2 改进:

1. 工作日历系统 (ScheduleService):
   - 新增 schedule-service.js: 公司级日程管理
   - 支持按小时调度、按周几过滤、时区感知
   - 心跳触发时自动检查到期 slots 并触发 Agent
   - 执行去重（同日同 slot 不重复触发）
   - CRUD API: GET/POST/PUT/DELETE /api/company/:id/schedule/slots
   - CLI: schedule add / schedule list

2. 告警通道 (Alert Channel):
   - Pipeline 步骤超时自动告警 Master Agent
   - 心跳异常自动告警 Master Agent
   - _sendAlertToMaster() 统一告警接口

3. CEO → Pipeline 自动生成:
   - CEO 模板从 3 步升级为 5 步工作流
   - 新增 Step 2: Pipeline JSON 设计（含 loop/cron/steps 结构)
   - 新增 Step 4: OKR 创建
   - Pipeline 设计输出为 CTO 搭建流水线的蓝图

4. Master 晨会日报:
   - 每天 08:00 自动生成全公司运营日报
   - 包含公司状态、Pipeline 运行、OKR 进度、Agent 活跃度
   - 自动推送给 Master Agent
   - 防重复机制（每天只生成一次）

5. Pipeline 驳回信息注入:
   - 驳回步骤被心跳重新触发时，__rejection 信息注入 prompt
   - 让 Agent 知道被驳回的原因和重做次数
   - 替换原有 curl 汇报指令为 task report CLI

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

…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

- CompanyHeartbeatService: company-level heartbeat with timer registration
- Auto-trigger: cron-based pipeline scheduling (intervalHours)
- Active run driving: dispatch tasks to agents, timeout detection
- CEO heartbeat: periodic company status check
- Pipeline cron field support in definitions
- Registered in server startup alongside agent heartbeat
- E2E test: 113/113 passed (all phases + autonomous loop)

- PipelineService: define pipelines with ordered agent-assigned steps
- Run lifecycle: start → markStepStarted → advanceStep → complete
- Step output automatically flows as next step input
- Pipeline CRUD + Run management REST API routes
- E2E test: 106/106 passed (Phase 1 + 2 + 3 + 4)

- GoalsService refactored: constructor accepts optional companyId
  - With companyId: goals stored in data/{companyId}/goals/
  - Without: backward-compatible data/goals/ (global)
- Company Goals REST API: full OKR CRUD under /api/company/:id/goals
- OKR isolation verified: different companies have independent goal spaces
- E2E test: 81/81 passed (Phase 1 + 2 + 3)

- scaffoldNewAgent: create agent skeleton via AgentScaffold directly
- depositTemplate: benchmark gating (≥95) + auto-deposit to templates/
- hireWithTraining: full flow (template lookup → scaffold fallback)
- Company route: /hire uses hireWithTraining, new /deposit-template endpoint
- E2E test: 69/69 passed (Phase 1 + Phase 2)

- CompanyService: CRUD (create/get/list/update/shutdown)
- Agent Hiring Pipeline: template lookup → copy → context injection
- Template registry (_registry.json) with CEO and qa-judge initial templates
- resolveAgentDir(companyId, agentId) unified agent directory resolution
- Company REST API routes (/api/company/*)
- E2E test: 46/46 passed

- 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

- 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