Files
aiagent/docs/gitea平台资料.md
renjianbo 495eafcd78 feat: virtual company M2 control + tier-3/4 capabilities + per-dept session fix
- M2-a/b/c: stop/pause/resume/skip dept, plan/rework approval gates,
  budget & timeout circuit breakers, per-dept cancel and on-demand rework
- tier-3: batched event persistence (_EventBuffer), project/dept
  concurrency semaphores, company_ws event streaming
- tier-4: cross-dept deliverable handoff, CEO memory feedback loop,
  per-dept model override, one-click Markdown report export (RFC5987)
- fix: per-department independent SQLAlchemy session in parallel waves
  (shared Session race across asyncio tasks in company_orchestrator)
- fix: rename process_open_fds gauge to app_process_open_fds
  (collides with prometheus_client ProcessCollector on Linux)
- fix: dept role resolution ladder, real token usage & cost tracking,
  deliverable file capture (mtime scan of dept workspace)
- tests: test_company_orchestrator.py 22 cases with mocked LLM
- frontend: CompanyControlRoom, companyExecution store, EChart,
  dept model config dialog, ws proxy, build/typecheck decoupling
- docs: virtual company design/usage docs, M2 control plan,
  deepseek4pro handover docs

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-07-26 18:16:39 +08:00

3.6 KiB
Raw Blame History

平台资料

工单平台(Gitea)

项目 值
平台 Gitea 1.25.2
地址 http://101.43.95.130:3001
用户名 admin
密码 123456
仓库 admin/aiagent
工单页 http://101.43.95.130:3001/admin/aiagent/issues
分支 rjb_win_dev
API Token fbc9ee7f96635793f4844187eac5c0e573480721
API 文档 http://101.43.95.130:3001/api/swagger

项目(aiagent)

项目 值
名称 天工智能体平台
前端 D:\aaa\aiagent\frontend (Vue 3 + Vite + Element Plus)
后端 D:\aaa\aiagent\backend (FastAPI + SQLAlchemy + Celery)
前端端口 3001 (Vite dev)
后端端口 8037 (Uvicorn)

测试账号

项目 值
用户名 admin
密码 123456
角色 管理员

前端项目结构

frontend/src/
├── api/index.ts          # API 封装 (axios),DEV 走 Vite 代理到 8037
├── main.ts               # 入口
├── router/index.ts       # 路由 (/agent-chat, /agents, /workflow 等)
├── stores/
│   ├── agent.ts          # Agent Store (Pinia)
│   ├── user.ts           # 用户 Store
│   └── ...
├── views/
│   ├── AgentChat.vue     # Agent 对话页 (核心)
│   ├── AgentConfig.vue   # Agent 配置页
│   ├── Agents.vue        # Agent 列表
│   └── ...
└── components/
    ├── AgentChatPreview.vue  # Agent 预览对话组件
    └── ...

后端项目结构

backend/app/
├── main.py               # FastAPI 入口
├── api/
│   ├── agent_chat.py     # Agent 对话 API
│   ├── agents.py         # Agent CRUD API
│   ├── auth.py           # 认证 API (login/register)
│   └── ...
├── agent_runtime/
│   ├── core.py           # Agent 运行时核心
│   ├── context.py        # 上下文管理
│   ├── memory.py         # 记忆系统
│   └── orchestrator.py   # 多 Agent 编排
├── core/
│   ├── config.py         # 配置
│   ├── database.py       # 数据库 (MySQL)
│   └── error_handler.py  # 异常处理
└── models/               # SQLAlchemy 模型

API 端点(agent-chat 相关)

方法 路径 说明
POST /api/v1/agent-chat/bare 默认 Agent 对话(无配置)
POST /api/v1/agent-chat/bare/stream 默认 Agent 流式对话(SSE)
POST /api/v1/agent-chat/{agent_id} 指定 Agent 对话
POST /api/v1/agent-chat/{agent_id}/stream 指定 Agent 流式对话(SSE)
POST /api/v1/agent-chat/orchestrate 多 Agent 编排
GET /api/v1/agents Agent 列表
GET /api/v1/agents/{id} Agent 详情
POST /api/v1/auth/login 登录(form-encoded)

快速验证命令

# 登录获取 token
curl -s -X POST http://localhost:8037/api/v1/auth/login \
  -H "Content-Type: application/x-www-form-urlencoded" \
  -d 'username=admin&password=123456'

# 测试 bare 对话
curl -s -X POST http://localhost:8037/api/v1/agent-chat/bare \
  -H "Authorization: Bearer <TOKEN>" \
  -H "Content-Type: application/json" \
  -d '{"message":"你好"}'

# 测试流式对话
curl -s -X POST http://localhost:8037/api/v1/agent-chat/bare/stream \
  -H "Authorization: Bearer <TOKEN>" \
  -H "Content-Type: application/json" \
  -d '{"message":"你好"}'

SSH / Git

项目 值
SSH Clone ssh://git@101.43.95.130:222/admin/aiagent.git
HTTP Clone http://101.43.95.130:3001/admin/aiagent.git