Files
zclaw_openfang/docs/README.md
iven 3ff08faa56 release(v0.2.0): streaming, MCP protocol, Browser Hand, security enhancements
## Major Features

### Streaming Response System
- Implement LlmDriver trait with `stream()` method returning async Stream
- Add SSE parsing for Anthropic and OpenAI API streaming
- Integrate Tauri event system for frontend streaming (`stream:chunk` events)
- Add StreamChunk types: Delta, ToolStart, ToolEnd, Complete, Error

### MCP Protocol Implementation
- Add MCP JSON-RPC 2.0 types (mcp_types.rs)
- Implement stdio-based MCP transport (mcp_transport.rs)
- Support tool discovery, execution, and resource operations

### Browser Hand Implementation
- Complete browser automation with Playwright-style actions
- Support Navigate, Click, Type, Scrape, Screenshot, Wait actions
- Add educational Hands: Whiteboard, Slideshow, Speech, Quiz

### Security Enhancements
- Implement command whitelist/blacklist for shell_exec tool
- Add SSRF protection with private IP blocking
- Create security.toml configuration file

## Test Improvements
- Fix test import paths (security-utils, setup)
- Fix vi.mock hoisting issues with vi.hoisted()
- Update test expectations for validateUrl and sanitizeFilename
- Add getUnsupportedLocalGatewayStatus mock

## Documentation Updates
- Update architecture documentation
- Improve configuration reference
- Add quick-start guide updates

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-24 03:24:24 +08:00

135 lines
6.1 KiB
Markdown
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# ZCLAW 文档中心
## 快速导航
| 文档 | 说明 |
|------|------|
| [快速启动](quick-start.md) | 5 分钟内启动 ZCLAW 开发环境 |
| [开发指南](DEVELOPMENT.md) | 开发环境设置、构建、测试 |
| [用户手册](USER_MANUAL.md) | 终端用户使用指南 |
| [Agent 进化计划](ZCLAW_AGENT_INTELLIGENCE_EVOLUTION.md) | Agent 智能层发展规划 |
## 架构概述
ZCLAW 采用**内部 Kernel 架构**,所有核心能力都集成在 Tauri 桌面应用中:
```
┌─────────────────────────────────────────────────────────────────┐
│ ZCLAW 桌面应用 │
├─────────────────────────────────────────────────────────────────┤
│ │
│ ┌─────────────────┐ ┌─────────────────────────────────┐ │
│ │ React 前端 │ │ Tauri 后端 (Rust) │ │
│ │ ├─ UI 组件 │ │ ├─ zclaw-kernel (核心协调) │ │
│ │ ├─ Zustand │────▶│ ├─ zclaw-runtime (LLM 驱动) │ │
│ │ └─ KernelClient│ │ ├─ zclaw-memory (存储层) │ │
│ └─────────────────┘ │ └─ zclaw-types (基础类型) │ │
│ └─────────────────────────────────┘ │
│ │ │
│ ▼ │
│ ┌─────────────────────────────────┐ │
│ │ 多 LLM 提供商支持 │ │
│ │ Kimi | Qwen | DeepSeek | Zhipu │ │
│ │ OpenAI | Anthropic | Local │ │
│ └─────────────────────────────────┘ │
│ │
└─────────────────────────────────────────────────────────────────┘
```
**关键特性**
- **无外部依赖** - 不需要启动独立的后端进程
- **单安装包运行** - 用户安装后即可使用
- **UI 配置模型** - 在"模型与 API"设置页面配置 LLM 提供商
## 文档结构
```
docs/
├── quick-start.md # 快速启动指南
├── DEVELOPMENT.md # 开发指南
├── USER_MANUAL.md # 用户手册
├── ZCLAW_AGENT_INTELLIGENCE_EVOLUTION.md # Agent 进化计划
├── features/ # 功能文档
│ ├── 00-architecture/ # 架构设计
│ │ ├── 01-communication-layer.md # 通信层
│ │ ├── 02-state-management.md # 状态管理
│ │ └── 03-security-auth.md # 安全认证
│ ├── 01-core-features/ # 核心功能
│ ├── 02-intelligence-layer/ # 智能层
│ └── 06-tauri-backend/ # Tauri 后端
├── knowledge-base/ # 技术知识库
│ ├── troubleshooting.md # 故障排除
│ └── ...
├── archive/ # 归档文档
│ ├── completed-plans/ # 已完成的计划
│ ├── research-reports/ # 研究报告
│ └── openclaw-legacy/ # 历史遗留文档
├── plans/ # 执行计划
│ └── ...
└── test-reports/ # 测试报告
└── ...
```
## Crate 架构
ZCLAW 核心由 8 个 Rust Crate 组成:
| Crate | 层级 | 职责 |
|-------|------|------|
| `zclaw-types` | L1 | 基础类型 (AgentId, Message, Error) |
| `zclaw-memory` | L2 | 存储层 (SQLite, 会话管理) |
| `zclaw-runtime` | L3 | 运行时 (LLM 驱动, 工具, Agent 循环) |
| `zclaw-kernel` | L4 | 核心协调 (注册, 调度, 事件, 工作流) |
| `zclaw-skills` | - | 技能系统 (SKILL.md 解析, 执行器) |
| `zclaw-hands` | - | 自主能力 (Hand/Trigger 注册管理) |
| `zclaw-channels` | - | 通道适配器 (Telegram, Discord, Slack) |
| `zclaw-protocols` | - | 协议支持 (MCP, A2A) |
### 依赖关系
```
zclaw-types (无依赖)
zclaw-memory (→ types)
zclaw-runtime (→ types, memory)
zclaw-kernel (→ types, memory, runtime)
desktop/src-tauri (→ kernel, skills, hands, channels, protocols)
```
## 支持的 LLM 提供商
| Provider | Base URL | 说明 |
|----------|----------|------|
| kimi | `https://api.kimi.com/coding/v1` | Kimi Code |
| qwen | `https://dashscope.aliyuncs.com/compatible-mode/v1` | 百炼/通义千问 |
| deepseek | `https://api.deepseek.com/v1` | DeepSeek |
| zhipu | `https://open.bigmodel.cn/api/paas/v4` | 智谱 GLM |
| openai | `https://api.openai.com/v1` | OpenAI |
| anthropic | `https://api.anthropic.com` | Anthropic Claude |
| local | `http://localhost:11434/v1` | Ollama/LMStudio |
## 项目状态
- **架构迁移**: Phase 5 完成 - 内部 Kernel 集成
- **Agent 智能层**: Phase 1-3 完成
- **测试覆盖**: 161 E2E tests passing, 26 Rust tests passing
## 贡献指南
1. 新文档放在适当的目录中
2. 使用清晰的文件命名(小写、连字符分隔)
3. 计划文件使用日期前缀:`YYYY-MM-DD-description.md`
4. 完成后将计划移动到 `archive/completed-plans/`
---
**最后更新**: 2026-03-22