deepfish-ai 1.0.28 → 2.0.2

package/README.md

@@ -1,5 +1,5 @@
 <div align="center" style="display:flex;align-items: center;justify-content: center;">
-  <img src="./images/title-img.png" alt="DeepFish" width="300" />
+  <img src="https://github.com/qq306863030/deepfish-ai/blob/master/images/title-img.png" alt="DeepFish" width="300" />
 </div>
 
 ---
@@ -24,80 +24,68 @@
   />
 </div>
 
-<img src="./images/banner.png" alt="banner" style="width:100%;text-align:center;" />
+<img src="https://github.com/qq306863030/deepfish-ai/blob/master/images/banner.png" alt="banner" style="width:100%;text-align:center;" />
 
+- [English](README_EN.md) | [中文](README.md)
 
+## 目录
 
-- [English](README.md) | [中文](README_CN.md)
+- [目录](#目录)
+- [1. 介绍](#1-介绍)
+- [2. 安装](#2-安装)
+  - [前置要求](#前置要求)
+  - [通过npm安装](#通过npm安装)
+  - [从源码安装](#从源码安装)
+- [3. 快速使用](#3-快速使用)
+- [4. 命令说明](#4-命令说明)
+  - [基础对话](#基础对话)
+  - [配置管理](#配置管理)
+  - [模型管理](#模型管理)
+  - [Skill 管理](#skill-管理)
+  - [工具管理](#工具管理)
+  - [会话管理](#会话管理)
+  - [任务管理](#任务管理)
+  - [MCP 管理](#mcp-管理)
+  - [服务管理](#服务管理)
+  - [缓存管理（AI自我学习的缓存）](#缓存管理ai自我学习的缓存)
+- [5. MCP 扩展配置](#5-mcp-扩展配置)
+  - [配置示例](#配置示例)
+- [6. 贡献](#6-贡献)
+- [7. 许可证](#7-许可证)
+- [8. 支持](#8-支持)
 
-## Table of Contents
+## 1. 介绍
 
-- [Table of Contents](#table-of-contents)
-- [1. Introduction](#1-introduction)
-- [2. Installation](#2-installation)
-  - [Prerequisites](#prerequisites)
-  - [Installation via npm](#installation-via-npm)
-  - [Installation from Source](#installation-from-source)
-- [3. Quick Start](#3-quick-start)
-- [4. Configuration](#4-configuration)
-  - [Initial Setup](#initial-setup)
-  - [Configuration Commands](#configuration-commands)
-  - [Configuration File Structure](#configuration-file-structure)
-  - [Directory Structure](#directory-structure)
-- [5. Usage](#5-usage)
-  - [Interactive Mode](#interactive-mode)
-  - [Direct Command Mode](#direct-command-mode)
-  - [Usage Examples](#usage-examples)
-- [6. Extension Development](#6-extension-development)
-  - [Creating an Extension](#creating-an-extension)
-  - [Registering Extensions](#registering-extensions)
-- [7. Recommendations](#7-recommendations)
-  - [AI Service Selection](#ai-service-selection)
-- [8. Usage Notes](#8-usage-notes)
-  - [Using Relative Paths](#using-relative-paths)
-  - [Conversation History](#conversation-history)
-- [9. Troubleshooting](#9-troubleshooting)
-  - [Configuration Issues](#configuration-issues)
-  - [AI Service Connection](#ai-service-connection)
-  - [Extension Not Loading](#extension-not-loading)
-- [10. Contributing](#10-contributing)
-- [11. License](#11-license)
-- [12. Support](#12-support)
+一款高效便捷的AI驱动命令行工具，致力于打破自然语言与操作系统指令、文件操作指令之间的壁垒，让非专业开发者也能通过简单的自然语言描述，快速生成可直接执行的操作指令，大幅提升终端操作效率。
+核心特性：
 
+- 多模型兼容：无缝支持DeepSeek、Ollama，以及所有遵循OpenAI API规范的AI模型，可根据需求灵活切换，适配不同场景下的指令生成需求。
 
+- 自然语言转指令：精准解析自然语言需求，自动转换为对应的操作系统命令（如Linux、Windows、macOS终端指令）和文件操作指令（如创建、删除、修改文件/目录），无需手动编写复杂命令。
 
-## 1. Introduction
+- **Skill 扩展**：Skill 是 AI 的工作流知识包，通过 Markdown 文件定义特定领域的操作流程和最佳实践。安装 Skill 后，AI 能自动遵循其中的规范来执行任务，例如代码审查流程、文档生成模板等。支持兼容 OpenClaw 的 Skill 生态，可通过 `ai skills` 命令进行安装、启用与管理。
 
-An efficient and convenient AI-driven command-line tool designed to break down the barrier between natural language and operating system commands or file operation instructions. It enables non-professional developers to quickly generate directly executable operation instructions through simple natural language descriptions, significantly improving terminal operation efficiency.
-Core Features:
+- **Tool 扩展**：Tool 是 AI 可调用的自定义函数工具，通过 TypeScript 文件定义。你可以编写 Tool 来扩展 AI 的能力边界，例如调用第三方 API、操作数据库、处理特定文件格式等。支持通过 `ai tools generate` 命令让 AI 自动生成 Tool，降低开发门槛。
 
-- Multi-model Compatibility: Seamlessly supports DeepSeek, Ollama, and all AI models that comply with the OpenAI API specification. It can be flexibly switched according to needs to adapt to instruction generation requirements in different scenarios.
+- **MCP 扩展**：MCP（Model Context Protocol）是一种标准化的模型上下文协议，允许 AI 连接外部工具和数据源。通过配置 MCP Server，AI 可以获得浏览器自动化、数据库查询、文件系统访问等能力。DeepFish 内置 MCP 支持，只需简单配置即可接入各类 MCP 服务。
 
-- OpenClaw Skill Compatibility: Supports the OpenClaw Skill ecosystem. Skills can be installed, enabled, and managed through the existing Skill commands to quickly expand workflow capabilities.
+- 高度可扩展：支持通过扩展机制拓展功能边界，除基础的终端、文件操作外，可轻松实现翻译、小说创作、文件格式转换、数据处理等复杂任务，满足多样化使用需求。
 
-- Natural Language to Instructions: Precisely parses natural language requirements and automatically converts them into corresponding operating system commands (such as Linux, Windows, and macOS terminal commands) and file operation instructions (such as creating, deleting, and modifying files/directories), eliminating the need to manually write complex commands.
 
-- Highly Extensible: Supports expanding functional boundaries through an extension mechanism. In addition to basic terminal and file operations, it can easily implement complex tasks such as translation, novel writing, file format conversion, and data processing to meet diverse usage needs.
+## 2. 安装
 
-- AI Automatic Extension Generation: There is no need to manually develop complex extension tools. Custom extensions can be directly generated through AI, reducing the threshold for extension development and making function expansion more efficient and flexible.[Extensions-Example](https://github.com/qq306863030/deepfish-extensions)
+### 前置要求
 
-Suitable for various groups such as developers, operation and maintenance personnel, and daily terminal users. Whether it is quickly executing terminal operations, batch processing files, or realizing personalized needs through extensions, this tool can simplify the operation process, improve work efficiency, and empower every terminal operation with AI.
+- Node.js（v22.14.0或更高版本）
+- npm或yarn
 
-
-## 2. Installation
-
-### Prerequisites
-
-- Node.js (v22.14.0 or higher)
-- npm or yarn
-
-### Installation via npm
+### 通过npm安装
 
 ```bash
 npm install -g deepfish-ai
 ```
 
-### Installation from Source
+### 从源码安装
 
 ```bash
 git clone https://github.com/qq306863030/deepfish-ai.git
@@ -106,359 +94,129 @@ npm install
 npm link
 ```
 
-## 3. Quick Start
+## 3. 快速使用
 
 ```bash
-ai config add # Enter a name, then select deepseek, and enter your DeepSeek API key
-ai config use [the_name_you_entered]
-ai "Help me write an article about future technology in the current directory, output in markdown format"
+ai models add # 输入名称, 输入你的模型配置
+ai config use 你输入的名称
+ai ”帮我在当前目录写一篇关于未来科技的文章，用markdown格式输出“
 ```
 
-## 4. Configuration
-
-### Initial Setup
+## 4. 命令说明
 
-Run the configuration wizard to set up your AI service:
+### 基础对话
 
 ```bash
-ai config add
+ai "你的问题或指令"
 ```
 
-This will prompt you to configure the following:
+直接输入自然语言，AI 将自动解析并执行对应操作。
 
-- **AI Service Type**: Choose DeepSeek, MiniMax, Qwen, Ollama, or OpenAI
-- **API Base URL**: Default URL provided for each service
-- **Model Name**: Choose the AI model to use
-- **API Key**: Required for DeepSeek and OpenAI
-- **Temperature**: Controls response randomness (0-2)
-- **Max Tokens**: Maximum response length
-- **Streaming Output**: Enable/disable streaming response
+### 配置管理
 
-### Configuration Commands
+| 命令 | 说明 |
+|------|------|
+| `ai config edit` | 编辑配置文件 |
+| `ai config view` | 查看当前配置 |
+| `ai config reset` | 重置配置 |
+| `ai config dir` | 查看配置目录 |
 
-```bash
-# Configuration commands
-ai config add # Add a new AI configuration
-ai config ls # List all AI configurations
-ai config use <name> # Set the specified AI configuration as the current one
-ai config del <name> # Delete the specified AI configuration
-ai config view [name] # View details of the specified AI configuration
-ai config edit # Edit the configuration file manually
-ai config dir # Open the configuration file directory
-ai config reset # Reset configuration
-
-# Skill commands
-ai skill ls # List all registered skills
-ai skill add <name> # Add a local skill directory or zip file from the current directory
-ai skill del <name|index> # Remove a skill by name or index, exp: ai skill del 1
-ai skill install <url> # Install a skill from ClawHub，exp: ai skill install https://clawhub.ai/TheSethRose/agent-browser
-ai skill enable <name|index> # Enable a skill by name or index, exp: ai skill enable 1
-ai skill disable <name|index> # Disable a skill by name or index, exp: ai skill disable 1
-ai skill dir # Open the skill directory
-
-# Memory commands
-ai memory clear # Clear the history messages for the current directory
-ai memory dir # Open the memory directory
-```
+### 模型管理
 
-### Configuration File Structure
-
-The configuration file (`~/.deepfish-ai/config.js`) has the following structure:
-
-```javascript
-export default {
-  ai: [
-    {
-      name: "default", // AI configuration name
-      type: "deepseek", // AI service type: "ollama", "deepseek", or "openai"
-      baseUrl: "https://api.deepseek.com", // API base URL
-      model: "deepseek-reasoner", // AI model name
-      apiKey: "", // API key (required for DeepSeek and OpenAI)
-      temperature: 0.7, // Response randomness (0-2)
-      maxTokens: 8, // Maximum response length (KB)
-      maxContextLength: 64, // Maximum context length (KB)
-      stream: true, // Enable/disable streaming output
-    }
-  ],
-  currentAi: "default", // Name of the currently active AI configuration
-  maxIterations: -1, // Maximum iterations for AI to complete the workflow, -1 for unlimited
-  maxMemoryExpireTime: 30, // Maximum session expiration time in days, -1 for unlimited, 0 to disable recording
-  maxLogExpireTime: 3, // Log expiration time in days, -1 for unlimited, 0 to disable recording
-  maxBlockFileSize: 20, // Maximum block file size in KB; files exceeding this size need to be processed in blocks
-  isThinkPrint: true, // Whether to print the thinking process
-  encoding: "auto", // Command line encoding format, can be set to utf-8, gbk, etc., or auto/empty for auto-detection
-  EMBEDDING_API: "", // Embedding API endpoint URL
-  EMBEDDING_API_KEY: "", // Embedding API key
-};
-```
+| 命令 | 说明 |
+|------|------|
+| `ai models add` | 添加新模型 |
+| `ai models ls` | 列出所有模型 |
+| `ai models use <name>` | 切换使用的模型 |
+| `ai models del <name>` | 删除指定模型 |
 
-### Directory Structure
+### Skill 管理
 
-DeepFish uses `.deepfish-ai` as the default working directory. You can open it directly with:
-
-```bash
-ai config dir
-```
+| 命令 | 说明 |
+|------|------|
+| `ai skills ls` | 列出所有 Skill |
+| `ai skills add <name>` | 添加 Skill |
+| `ai skills del <index>` | 删除指定 Skill |
+| `ai skills enable <name\|index>` | 启用 Skill |
+| `ai skills disable <name\|index>` | 禁用 Skill |
+| `ai skills dir` | 查看 Skill 目录 |
+| `ai skills generate xxx` | 通过 AI 生成 Skill |
 
-Default paths:
-
-- Windows: `C:/Users/<username>/.deepfish-ai`
-- macOS/Linux: `~/.deepfish-ai`
-
-Based on the structure in DevPlan, the directory layout is:
-
-```text
-.deepfish-ai/
-├─ config.js                           # Global configuration
-├─ user-info/
-│  └─ user.md                          # User profile data
-├─ clawSkills/
-│  ├─ clawSkills.json                  # OpenClaw skill index
-│  └─ <skill>/
-│     └─ SKILL.md                      # Single skill definition
-└─ memery/
-   ├─ agentRecord.json                 # Workspace to main-agent mapping
-   └─ <main-agent-id>/
-      ├─ memery.json                   # Main agent memory
-      ├─ memery-<sub-agent-id>.json    # Sub-agent memory
-      ├─ agentTree.json                # Agent hierarchy
-      ├─ bakup/
-      │  └─ <timestamp>/
-      │     ├─ record.json             # Backup operation record
-      │     └─ <uuid>.*                # Backup files
-      └─ logs/
-         └─ log-{YYYY-MM-DD HH}.txt    # Hourly rolling logs
-```
+### 工具管理
 
-## 5. Usage
+| 命令 | 说明 |
+|------|------|
+| `ai tools dir` | 查看工具目录 |
+| `ai tools generate xxx` | 通过 AI 生成工具 |
 
-### Interactive Mode
+### 会话管理
 
-Start an interactive session (multi-turn dialogue):
+| 命令 | 说明 |
+|------|------|
+| `ai session clear` | 清除会话历史 |
+| `ai session dir` | 查看会话目录 |
 
-```bash
-ai
-```
+### 任务管理
 
-Or explicitly specify:
+| 命令 | 说明 |
+|------|------|
+| `ai task ls` | 列出所有任务 |
+| `ai task add <task>` | 添加任务 |
+| `ai task del <index>` | 删除指定任务 |
+| `ai task clear` | 清除所有任务 |
 
-```bash
-ai -i or ai -interactive
-```
+### MCP 管理
 
-### Direct Command Mode
+| 命令 | 说明 |
+|------|------|
+| `ai mcp edit` | 编辑 MCP 配置 |
 
-Execute a single command:
+### 服务管理
 
-```bash
-ai "Create a file named hello.txt with the content 'Hello World'"
-```
+| 命令 | 说明 |
+|------|------|
+| `ai serve` | 启动服务 |
+| `ai serve start` | 启动服务 |
+| `ai serve stop` | 停止服务 |
+| `ai serve restart` | 重启服务 |
 
-### Usage Examples
+### 缓存管理（AI自我学习的缓存）
 
-**File Operations:**
+| 命令 | 说明 |
+|------|------|
+| `ai cache ls` | 列出缓存 |
+| `ai cache edit <index\|id>` | 编辑缓存项 |
+| `ai cache del <index\|id>` | 删除缓存项 |
 
-```bash
-ai "Create 10 text documents, each with 100 random characters"
-ai "Clear the current directory"
-```
+## 5. MCP 扩展配置
 
-**Code Generation:**
+MCP（Model Context Protocol）允许 AI 连接外部工具和服务。通过 `ai mcp edit` 命令编辑 MCP 配置文件，添加你需要的 MCP Server。
 
-```bash
-ai "Create a simple Express server with a /hello endpoint"
-ai "Create a browser-based airplane shooting game"
-```
-
-**System Commands:**
-
-```bash
-ai "List all files in the current directory with their sizes"
-ai "Check disk usage for the current directory"
-```
-
-**Extension Tool Generation:**
-
-```bash
-ai "Create a weather.js extension tool for querying weather"
-```
-
-**Skill Management:**
-
-```bash
-ai skill install https://clawhub.ai/TheSethRose/agent-browser
-ai skill install https://clawhub.ai/steipete/weather
-ai skill ls
-ai skill enable 1
-ai skill disable 0
-```
-
-**OpenClaw Skill Generation:**
-
-```bash
-ai "Create a weather query skill"
-ai skill add weather-query
-ai skill enable weather-query
-```
-
-**Media Processing:**
-
-```bash
-ai "I have ffmpeg5 installed on my system, help me convert all MP4 files in the directory to AVI format"
-```
+### 配置示例
 
-**File Organization:**
+以下示例配置了 Chrome DevTools MCP Server，使 AI 能够操控浏览器进行自动化操作：
 
-```bash
-ai "Classify all files under the 'model' directory into the 'model2' directory by month, date format YYYY-MM"
-```
-
-**Task List Execution:**
-
-```bash
-ai "Create a task list: 1.xxxx; 2.xxxx; ..."
-ai "Execute task list" # Start execution
-
-ai "I want to implement an extension tool for long-form novel writing that supports large-scale writing, maintains contextual logic coherence, and avoids AI context explosion issues. This extension tool may be a bit complex to implement. You need to carefully read the extension tool generation rules first, then create a task list"
-ai "Execute task list" # Start execution
-```
-
-## 6. Extension Development
-
-Extensions allow you to add custom functions that AI can use in its workflows. For complex processes, you can develop them yourself or try generating extensions using this program, then register the extension with the program and use the command line to complete tasks.
-
-### Creating an Extension
-
-1. Extensions should export an object containing `descriptions` (an array of tool descriptions) and `functions` (an object of functions).
-2. Tip: You can generate extensions via AI, e.g., `ai "Create a weather.js extension tool for querying weather"`
-3. View [example extensions](https://github.com/qq306863030/deepfish-extensions).
-
-```javascript
-// Example extension: Weather Extension
-const axios = require('axios');
-
-const descriptions = [
-  {
-    type: 'function',
-    function: {
-      name: 'getWeather',
-      description: 'Get current weather information for a city',
-      parameters: {
-        type: 'object',
-        properties: {
-          city: { type: 'string' }
-        },
-        required: ['city']
-      }
+```json
+{
+  "mcpServers": {
+    "chrome-devtools": {
+      "command": "npx",
+      "args": ["-y", "chrome-devtools-mcp@latest"]
     }
   }
-];
-
-const functions = {
-  async getWeather(city) {
-    // Implement weather API call
-    const response = await axios.get(`https://api.weatherapi.com/v1/current.json?key=YOUR_KEY&q=${city}`);
-    return `${city} weather: ${response.data.current.temp_c}°C, ${response.data.current.condition.text}`;
-  }
-};
-
-module.exports = {
-  descriptions,
-  functions
-};
-```
-
-### Registering Extensions
-
-**Method 1: Manual Configuration**
-
-1. ai config edit
-2. Add it to your configuration:
-
-```javascript
-export default {
-  // ... other configurations
-  extensions: [
-    '/path/to/weather-extension.js'
-  ],
-};
-```
-
-**Method 2: Automatic Scanning**
-
-Rules for automatic scanning of extension modules upon program startup:
-
-1. Scanning locations:
-  - the DeepFish installation directory (where `deepfish-ai` is located)
-  - `node_modules` under the current working directory
-  - the current working directory itself
-
-2. Scanned files:
-  - scoped packages under `@deepfish-ai/*` in the locations above
-  - packages starting with `deepfish-` in the locations above (excluding `deepfish-ai` itself)
-  - top-level `.js` / `.mjs` files in the current working directory are scanned additionally; files containing `module.exports`, `descriptions`, and `functions` are treated as auto-loadable extensions
-  
-## 7. Recommendations
-
-### AI Service Selection
-
-**Recommendation: Use online AI services (DeepSeek/OpenAI) for best results**
-
-While local AI services (like Ollama) offer privacy and offline capabilities, they may have the following limitations:
-
-- **Response Accuracy**: Local models may not be as rigorous and precise as online models
-- **Code Quality**: Generated code may require more manual review and correction
-- **Complex Task Handling**: May encounter difficulties with multi-step or complex operations
-- **Language Understanding**: Online services provide better language models
-
-For production environments or complex tasks, we recommend using DeepSeek, OpenAI services, or cloud services within Ollama for more reliable and accurate results.
-
-## 8. Usage Notes
-
-### Using Relative Paths
-
-AI always uses paths relative to the current working directory.
-
-### Conversation History
-
-Conversation history is created on a per-directory basis — each execution directory corresponds to its own Agent context. This means that conversations started in different directories are independent of each other.
-
-> **⚠️ Important Note:** AI context is directory-based — each directory corresponds to one context. **Please do not open two command-line dialogs in the same directory**, as this may cause context conflicts and unexpected behavior.
-
-Conversation history will be automatically cleared after a configurable period (controlled by the `maxMemoryExpireTime` field in the configuration file, default is 30 days). You can also manage it manually:
-
-- `ai memory dir` — Open the memory directory to view stored conversation contexts
-- `ai memory clear` — Manually clear the conversation history for the current directory
-
-## 9. Troubleshooting
-
-### Configuration Issues
-
-If you encounter configuration errors, try resetting:
-
-```bash
-ai config reset
+}
 ```
 
-### AI Service Connection
-
-- **Ollama**: Ensure Ollama is running locally on port 11434
-- **DeepSeek/MiniMax/Qwen/OpenAI**: Verify your API key is correct and you have sufficient quota
-
-### Extension Not Loading
-
-- Check the file path in the configuration
-- Ensure the file exports the correct object
-- Verify the file has no syntax errors
+配置完成后，AI 将自动加载 MCP Server 提供的工具，你可以在对话中直接让 AI 使用这些能力。
 
-## 10. Contributing
+## 6. 贡献
 
-Contributions are welcome! Please feel free to submit a Pull Request.
+欢迎贡献！请随时提交Pull Request。
 
-## 11. License
+## 7. 许可证
 
-This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
+本项目采用MIT许可证 - 详见[LICENSE](LICENSE)文件。
 
-## 12. Support
+## 8. 支持
 
-For issues and questions, please submit an issue on the GitHub repository.
+如有问题和疑问，请在GitHub仓库上提交issue。