@vegamo/deepcode-cli - npm Package Compare versions

Comparing version 0.1.22 to 0.1.23

package.json

 {
   "name": "@vegamo/deepcode-cli",
-  "version": "0.1.22",
+  "version": "0.1.23",
   "description": "Deep Code CLI - Vibe coding for the deepseek-v4 model in your terminal",
@@ -5,0 +5,0 @@ "license": "MIT",

README.md

@@ -1,7 +0,20 @@
-# Deep Code CLI
+<div align="center">
+<br/>
+<br/>
+<p align="center">
+  <a href='https://deepcode.vegamo.cn/'>
+    <img src='https://avatars.githubusercontent.com/u/118287711?s=200&v=4' width='100' alt="deepcode-cli"/>
+  </a>
+</p>
+<h1>Deep Code CLI</h1>
 
-[Deep Code](https://github.com/lessweb/deepcode-cli) is a terminal AI coding assistant optimized for the `deepseek-v4` model, with support for deep thinking, reasoning effort control, Agent Skills, and MCP (Model Context Protocol) integration.
+[English](README-en.md) · 中文
 
-## Installation
+<br/>
+</div>
 
+[Deep Code](https://github.com/lessweb/deepcode-cli) 是专为 `deepseek-v4` 模型优化的终端 AI 编码助手，支持深度思考、推理强度控制、Agent Skills 以及 MCP 集成。
+
+## 安装
+
 ```bash
@@ -11,9 +24,9 @@ npm install -g @vegamo/deepcode-cli
 
-Run `deepcode` inside any project directory to get started.
+在任意项目目录下运行 `deepcode` 即可启动。
 
 ![intro2](resources/intro2.png)
 
-## Configuration
+## 配置
 
-Create `~/.deepcode/settings.json`:
+创建 `~/.deepcode/settings.json` 文件，内容如下：
 
@@ -32,68 +45,77 @@ ```json
 
-The configuration file is shared with the [Deep Code VSCode extension](https://github.com/lessweb/deepcode) — configure once, use everywhere.
+配置文件与 [Deep Code VSCode 插件](https://github.com/lessweb/deepcode) 共享，无需重复配置。
 
-For complete configuration details (multi-level priority, environment variables, etc.), see [docs/configuration.md](docs/configuration.md).
+完整配置说明（多层级优先级、环境变量等）请参阅 [docs/configuration.md](docs/configuration.md)。
 
-## Key Features
+## 主要功能
 
 ### **Skills**
-Deep Code CLI supports agent skills that allow you to extend the assistant's capabilities:
+Deep Code CLI 支持 agent skills，允许您扩展助手的能力：
 
-- **User-level Skills**: discovered and activated from `~/.agents/skills/`.
-- **Project-level Skills**: loaded from `./.agents/skills/` for project-specific workflows, with legacy `./.deepcode/skills/` compatibility.
+- **User-level Skills**：从 `~/.agents/skills/` 目录中发现并激活 skills。
+- **Project-level Skills**：从 `./.agents/skills/` 目录中加载项目专属 skills，并兼容旧的 `./.deepcode/skills/` 目录。
 
-### **Optimized for DeepSeek**
-- Specifically tuned for DeepSeek model performance.
-- Reduce costs by using [Context Caching](https://api-docs.deepseek.com/guides/kv_cache).
-- Natively supports [Thinking Mode](https://api-docs.deepseek.com/guides/thinking_mode) and Effort Control.
+### **为 DeepSeek 优化**
+- 专门为 DeepSeek 模型性能调优。
+- 通过使用[上下文缓存](https://api-docs.deepseek.com/guides/kv_cache)来降低成本。
+- 原生支持[思考模式](https://api-docs.deepseek.com/guides/thinking_mode)和思考强度控制。
 
-## Slash Commands & Keyboard Shortcuts
+## 斜杠命令与按键功能
 
-| Slash Command    | Action                                                   |
-|------------------|----------------------------------------------------------|
-| `/`              | Open the skills / commands menu                          |
-| `/new`           | Start a fresh conversation                               |
-| `/resume`        | Choose a previous conversation to continue               |
-| `/model`         | Switch model, thinking mode, and reasoning effort        |
-| `/init`          | Initialize an AGENTS.md file (LLM project instructions)  |
-| `/skills`        | List available skills                                    |
-| `/mcp`           | View MCP server status and available tools               |
-| `/exit`          | Quit (also `Ctrl+D` twice)                               |
+| 斜杠命令         | 操作                                        |
+|-----------------|---------------------------------------------|
+| `/`             | 打开 skills / 命令菜单                      |
+| `/new`          | 开始新对话                                  |
+| `/resume`       | 选择历史对话继续                            |
+| `/model`        | 切换模型、思考模式和推理强度                |
+| `/raw`          | 切换显示模式（Normal / Lite / Raw 滚动回溯）|
+| `/init`         | 初始化 AGENTS.md 文件                      |
+| `/skills`       | 列出可用 skills                             |
+| `/mcp`          | 查看 MCP 服务器状态和可用工具               |
+| `/exit`         | 退出（也可用连续 `Ctrl+D`）                 |
 
-| Key              | Action                                                   |
-|------------------|----------------------------------------------------------|
-| `Enter`          | Send the prompt                                          |
-| `Shift+Enter`    | Insert a newline (also `Ctrl+J`)                         |
-| `Ctrl+V`         | Paste an image from the clipboard                        |
-| `Esc`            | Interrupt the current model turn                         |
-| `Ctrl+D` twice   | Quit Deep Code                                           |
+| 按键             | 操作                                        |
+|-----------------|---------------------------------------------|
+| `Enter`         | 发送消息                                    |
+| `Shift+Enter`   | 插入换行（也可用 `Ctrl+J`）                 |
+| `Ctrl+V`        | 从剪贴板粘贴图片                            |
+| `Esc`           | 中断当前模型回复                            |
+| 连续 `Ctrl+D`    | 退出                                        |
 
-## Supported Models
+## 支持的模型
 
-- `deepseek-v4-pro` (Recommended)
+- `deepseek-v4-pro`（推荐使用）
 - `deepseek-v4-flash`
-- Any other OpenAI-compatible model
+- 任何其他 OpenAI 兼容模型
 
-## FAQ
 
-### Does Deep Code have a VSCode extension?
+## 常见问题
 
-Yes. Deep Code offers a full-featured VSCode extension, available on the [VSCode Marketplace](https://marketplace.visualstudio.com/items?itemName=vegamo.deepcode-vscode). The extension shares the `~/.deepcode/settings.json` configuration file with the CLI, so you can switch seamlessly between the terminal and the editor.
+### Deep Code 是否有 VSCode 插件？
 
-### Does Deep Code support understanding images?
+有的。Deep Code 提供功能完整的 VSCode 插件，可在 [VSCode Marketplace](https://marketplace.visualstudio.com/items?itemName=vegamo.deepcode-vscode) 安装。插件与 CLI 共享 `~/.deepcode/settings.json` 配置文件，可以在终端和编辑器之间无缝切换。
 
-Deep Code supports multimodal input — you can paste images from the clipboard with `Ctrl+V`. However, `deepseek-v4` does not support multimodal yet. Some models have multimodal capabilities but impose strict limits on multi-turn dialogue requests. For multimodal input, we recommend using the Volcano Ark `Doubao-Seed-2.0-pro` model, which has the best integration.
+### Deep Code 是否支持理解图片？
 
-### How to automatically send a Slack message after a task completes?
+Deep Code 支持多模态，可使用ctrl+v从剪贴板粘贴图片。但目前 deepseek-v4 不支持多模态。有些模型虽然有多模态能力，但对多轮对话请求的限制太严。目前多模态输入推荐使用火山方舟的 Doubao-Seed-2.0-pro 模型，适配效果最好。
 
-Write a shell notification script that calls a Slack webhook, then set the `notify` field in `~/.deepcode/settings.json` to the full path of the script. For detailed steps, refer to: https://binfer.net/share/jby5xnc-so6g
+### 怎样在任务完成后自动给 Slack 发消息？
 
-### How do I enable web search?
+编写一个调用 Slack webhook 的 Shell 通知脚本，然后在 `~/.deepcode/settings.json` 中将 `notify` 字段设为该脚本的完整路径即可。详细步骤请参考 [docs/notify.md](docs/notify.md)。
 
-Deep Code comes with a built-in, free Web Search tool that works well for most use cases. If you prefer to use a custom script for web search, set the `webSearchTool` field in `~/.deepcode/settings.json` to the full path of your script. For detailed steps, refer to: https://github.com/qorzj/web_search_cli
+### 怎样启用联网搜索功能？
 
-### Does it support Coding Plan?
+Deep Code自带免费的、且大部分情况够用的Web Search工具。如果你希望使用自定义脚本进行联网搜索，可以在 `~/.deepcode/settings.json` 中将 `webSearchTool` 设为脚本的完整路径即可。详细步骤可参考：https://github.com/qorzj/web_search_cli
 
-Yes. Just set `env.BASE_URL` in `~/.deepcode/settings.json` to an OpenAI-compatible API endpoint. Take Volcano Ark's Coding Plan as an example:
+### 如何配置 MCP？
 
+Deep Code 支持 MCP（Model Context Protocol），可以连接 GitHub、浏览器、数据库等外部服务。在 `settings.json` 中配置 `mcpServers` 字段即可启用，启动后使用 `/mcp` 命令查看已配置的 MCP 服务器状态和可用工具。
+
+详细配置指南：[docs/mcp.md](docs/mcp.md)
+
+
+### 是否支持 Coding Plan？
+
+支持。只要把 `~/.deepcode/settings.json` 的 `env.BASE_URL` 配置为 OpenAI 兼容的接口地址就行。以火山方舟的 Coding Plan 为例：
+
 ```json
@@ -109,48 +131,41 @@ {
 ```
+## 贡献
 
-### How do I configure MCP?
+欢迎贡献代码！以下是参与方式：
 
-Deep Code supports MCP (Model Context Protocol) to connect external services such as GitHub, browsers, databases, and more. Configure the `mcpServers` field in `settings.json` to enable it, then use the `/mcp` command to view MCP server status and available tools.
-
-For detailed setup instructions, see: [docs/mcp.md](docs/mcp.md)
-
-## Contributing
-
-Contributions are welcome! Here's how to get started:
-
 ```bash
-# Clone the repository
+# 克隆仓库
 git clone https://github.com/lessweb/deepcode-cli.git
 cd deepcode-cli
 
-# Install dependencies
+# 安装依赖
 npm install
 
-# Local development (typecheck + lint + format check + bundle)
+# 本地开发（类型检查 + lint + 格式检查 + 构建）
 npm run build
 
-# Run tests
+# 运行测试
 npm test
 
-# Link globally (local global install)
+# 链接到全局（即本地全局安装）
 npm link
 ```
 
-- Make sure `npm run check` passes before submitting a PR (typecheck + lint + format check)
-- We recommend running `npm run format` before building to avoid errors
+- 提交 PR 前请确保 `npm run check` 通过（类型检查 + lint + 格式检查）
+- 建议在执行构建前，先执行 `npm run format` 自动格式化代码，避免构建报错
 
-## Getting Help
+## 获取帮助
 
-- Report bugs or request features on GitHub Issues (https://github.com/lessweb/deepcode-cli/issues)
+- 在 GitHub Issues 上报告错误或请求功能 (https://github.com/lessweb/deepcode-cli/issues)
 
-## License
+## 协议
 
 - MIT
 
-## Support Us
+## 支持我们
 
-If you find this tool helpful, please consider supporting us by:
+如果你觉得这个工具对你有帮助，请考虑通过以下方式支持我们：
 
-- Giving us a Star on GitHub (https://github.com/lessweb/deepcode-cli)
-- Submitting feedback and suggestions
-- Sharing with your friends and colleagues
+- 在 GitHub 上给我们一个 Star (https://github.com/lessweb/deepcode-cli)
+- 向我们提交反馈和建议
+- 分享给你的朋友和同事

New alerts

Shell access

Supply chain risk

This module accesses the system shell. Accessing the system shell increases the risk of executing arbitrary code.

Found 1 instance in 1 package

Improved metrics

Total package byte prevSize

422945

5.43%

Lines of code

11018

5.71%

Number of lines in readme file

169

9.74%

Worsened metrics

Number of medium supply chain risk alerts

11

10%

No dependency changes