> ## Documentation Index
> Fetch the complete documentation index at: https://cndoc-langchain.site/llms.txt
> Use this file to discover all available pages before exploring further.

# 代理客户端协议 (ACP)

> 通过代理客户端协议 (ACP) 暴露深度代理，以与代码编辑器和 IDE 集成。

[代理客户端协议 (ACP)](https://agentclientprotocol.com/get-started/introduction) 标准化了编码代理与代码编辑器或 IDE 之间的通信。
通过 ACP 协议，您可以将自定义的深度代理与任何兼容 ACP 的客户端一起使用，让您的代码编辑器能够提供项目上下文并接收丰富的更新。

<Note>
  ACP
  专为代理-编辑器集成而设计。如果您希望您的代理调用由外部服务器托管的工具，请参阅[模型上下文协议
  (MCP)](/oss/javascript/langchain/mcp/)。
</Note>

## 快速开始

安装 ACP 集成包：

<CodeGroup>
  ```bash npm theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  npm install deepagents-acp
  ```

  ```bash yarn theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  yarn add deepagents-acp
  ```

  ```bash pnpm theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  pnpm add deepagents-acp
  ```
</CodeGroup>

然后通过 ACP 暴露一个深度代理。

这将启动一个 stdio 模式的 ACP 服务器（它从 stdin 读取请求并将响应写入 stdout）。在实践中，您通常将其作为由 ACP 客户端（例如您的编辑器）启动的命令来运行，然后通过 stdio 与服务器通信。

```typescript icon="server" theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
import { startServer } from "deepagents-acp";

await startServer({
  agents: {
    name: "coding-assistant",
    description: "AI coding assistant with filesystem access",
  },
  workspaceRoot: process.cwd(),
});
```

您也可以使用 CLI 而无需编写任何代码：

```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
npx deepagents-acp
```

<Card title="npm 上的 DeepAgents ACP" icon="brand-npm" href="https://www.npmjs.com/package/deepagents-acp">
  `deepagents-acp` 包提供了 CLI 和编程 API，用于通过 ACP 暴露深度代理。
</Card>

## 客户端

深度代理可在任何可以运行 ACP 代理服务器的地方工作。一些知名的 ACP 客户端包括：

* [Zed](https://zed.dev/docs/ai/external-agents)
* [JetBrains IDEs](https://www.jetbrains.com/help/ai-assistant/acp.html)
* Visual Studio Code (通过 [vscode-acp](https://github.com/formulahendry/vscode-acp))
* Neovim (通过兼容 ACP 的插件)

### Zed

通过将您的深度代理添加到 Zed 设置中（Linux 上为 `~/.config/zed/settings.json`，macOS 上为 `~/Library/Application Support/Zed/settings.json`），在 [Zed](https://zed.dev/docs/ai/external-agents) 中注册它：

**简单设置（无需代码）：**

```json theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
{
  "agent": {
    "profiles": {
      "deepagents": {
        "name": "DeepAgents",
        "command": "npx",
        "args": ["deepagents-acp"],
        "env": {
          "ANTHROPIC_API_KEY": "sk-ant-..."
        }
      }
    }
  }
}
```

**使用 CLI 选项：**

```json theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
{
  "agent": {
    "profiles": {
      "deepagents": {
        "name": "DeepAgents",
        "command": "npx",
        "args": [
          "deepagents-acp",
          "--name",
          "my-assistant",
          "--skills",
          "./skills",
          "--debug"
        ],
        "env": {
          "ANTHROPIC_API_KEY": "sk-ant-..."
        }
      }
    }
  }
}
```

**自定义服务器脚本：**

为了获得更多控制权，创建一个 TypeScript 服务器脚本：

```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
// server.ts
import { startServer } from "deepagents-acp";

await startServer({
  agents: {
    name: "my-agent",
    description: "My custom coding agent",
    skills: ["./skills/"],
  },
});
```

然后将 Zed 指向它：

```json theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
{
  "agent": {
    "profiles": {
      "my-agent": {
        "name": "My Agent",
        "command": "npx",
        "args": ["tsx", "./server.ts"]
      }
    }
  }
}
```

打开 Zed 的代理面板并启动一个 DeepAgents 线程。

### ACP 注册表

DeepAgents 可在 [ACP 代理注册表](https://agentclientprotocol.com/registry/index) 中找到，支持在 Zed 和 JetBrains IDE 中一键安装。当 ACP 客户端支持注册表时，用户可以发现并安装深度代理，无需任何手动配置。

## CLI 参考

CLI 是启动 ACP 服务器的最快方式。它不需要任何代码——只需运行 `npx deepagents-acp` 并连接您的编辑器。

```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
npx deepagents-acp [options]
```

| 选项                     | 简写   | 描述                                        |
| ---------------------- | ---- | ----------------------------------------- |
| `--name <name>`        | `-n` | 代理名称（默认：`"deepagents"`）                   |
| `--description <desc>` | `-d` | 代理描述                                      |
| `--model <model>`      | `-m` | LLM 模型（默认：`"claude-sonnet-4-5-20250929"`） |
| `--workspace <path>`   | `-w` | 工作区根目录（默认：当前工作目录）                         |
| `--skills <paths>`     | `-s` | 逗号分隔的技能路径                                 |
| `--memory <paths>`     |      | 逗号分隔的 AGENTS.md 路径                        |
| `--debug`              |      | 启用调试日志输出到 stderr                          |
| `--help`               | `-h` | 显示帮助信息                                    |
| `--version`            | `-v` | 显示版本                                      |

### 环境变量

| 变量                  | 描述                              |
| ------------------- | ------------------------------- |
| `ANTHROPIC_API_KEY` | Anthropic/Claude 模型的 API 密钥（必需） |
| `OPENAI_API_KEY`    | OpenAI 模型的 API 密钥               |
| `DEBUG`             | 设置为 `"true"` 以启用调试日志            |
| `WORKSPACE_ROOT`    | `--workspace` 标志的替代方案           |

## 编程 API

### `startServer`

便捷函数，用于一步创建并启动服务器：

```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
import { startServer } from "deepagents-acp";

const server = await startServer({
  agents: {
    name: "coding-assistant",
    description: "AI coding assistant with filesystem access",
  },
  workspaceRoot: process.cwd(),
});
```

### `DeepAgentsServer`

如需完全控制，可直接使用 `DeepAgentsServer` 类：

```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
import { DeepAgentsServer } from "deepagents-acp";

const server = new DeepAgentsServer({
  agents: [
    {
      name: "code-agent",
      description: "Full-featured coding assistant",
      model: "claude-sonnet-4-5-20250929",
      skills: ["./skills/"],
      memory: ["./.deepagents/AGENTS.md"],
    },
    {
      name: "reviewer",
      description: "Code review specialist",
      systemPrompt: "You are a code review expert...",
    },
  ],
  serverName: "my-deepagents-acp",
  serverVersion: "1.0.0",
  workspaceRoot: process.cwd(),
  debug: true,
});

await server.start();
```

#### 服务器选项

| 选项              | 类型                                     | 默认值                | 描述        |
| --------------- | -------------------------------------- | ------------------ | --------- |
| `agents`        | `DeepAgentConfig \| DeepAgentConfig[]` | 必需                 | 代理配置      |
| `serverName`    | `string`                               | `"deepagents-acp"` | ACP 服务器名称 |
| `serverVersion` | `string`                               | `"0.0.1"`          | 服务器版本     |
| `workspaceRoot` | `string`                               | `process.cwd()`    | 工作区根目录    |
| `debug`         | `boolean`                              | `false`            | 启用调试日志    |

#### 代理配置

| 选项             | 类型                                             | 描述                                        |
| -------------- | ---------------------------------------------- | ----------------------------------------- |
| `name`         | `string`                                       | 唯一的代理名称（必需）                               |
| `description`  | `string`                                       | 代理描述                                      |
| `model`        | `string`                                       | LLM 模型（默认：`"claude-sonnet-4-5-20250929"`） |
| `tools`        | `StructuredTool[]`                             | 自定义 LangChain 工具                          |
| `systemPrompt` | `string`                                       | 自定义系统提示                                   |
| `middleware`   | `AgentMiddleware[]`                            | 自定义中间件                                    |
| `backend`      | `AnyBackendProtocol`                           | 文件系统后端                                    |
| `skills`       | `string[]`                                     | 技能源路径                                     |
| `memory`       | `string[]`                                     | 记忆源路径 (AGENTS.md)                         |
| `interruptOn`  | `Record<string, boolean \| InterruptOnConfig>` | 需要用户批准的工具 (HITL)                          |
| `commands`     | `Array<{ name, description, input? }>`         | 自定义斜杠命令                                   |

## 自定义

### 多个代理

您可以从单个服务器暴露多个代理。ACP 客户端在创建会话时选择使用哪个代理：

```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
const server = new DeepAgentsServer({
  agents: [
    { name: "code-agent", description: "General coding" },
    { name: "reviewer", description: "Code reviews" },
  ],
});
```

<Note>
  一些 ACP 客户端（如 Zed）目前没有提供用于选择代理的
  UI。在这种情况下，请考虑运行单独的服务器实例，每个实例只包含一个代理。
</Note>

### 斜杠命令

服务器会向 IDE 注册内置的斜杠命令：`/plan`、`/agent`、`/ask`、`/clear` 和 `/status`。您也可以为每个代理定义自定义命令：

```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
const server = new DeepAgentsServer({
  agents: {
    name: "my-agent",
    commands: [
      { name: "test", description: "Run the project's test suite" },
      { name: "lint", description: "Run linter and fix issues" },
      {
        name: "deploy",
        description: "Deploy to staging",
        input: { hint: "environment (staging or production)" },
      },
    ],
  },
});
```

### Human in the Loop

使用 `interruptOn` 在代理运行敏感工具之前，要求在 IDE 中获得用户批准：

```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
const server = new DeepAgentsServer({
  agents: {
    name: "careful-agent",
    interruptOn: {
      execute: { allowedDecisions: ["approve", "edit", "reject"] },
      write_file: true,
    },
  },
});
```

当代理调用受保护的工具时，IDE 会提示用户允许或拒绝该操作，并提供为会话记住该决定的选项。

### 自定义工具

```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
import { DeepAgentsServer } from "deepagents-acp";
import { tool } from "@langchain/core/tools";
import { z } from "zod";

const searchTool = tool(
  async ({ query }) => {
    return `Results for: ${query}`;
  },
  {
    name: "search",
    description: "Search the codebase",
    schema: z.object({ query: z.string() }),
  },
);

const server = new DeepAgentsServer({
  agents: {
    name: "search-agent",
    tools: [searchTool],
  },
});

await server.start();
```

### 自定义后端

```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
import { DeepAgentsServer } from "deepagents-acp";
import { CompositeBackend, FilesystemBackend, StateBackend } from "deepagents";

const server = new DeepAgentsServer({
  agents: {
    name: "custom-agent",
    backend: new CompositeBackend({
      routes: [
        {
          prefix: "/workspace",
          backend: new FilesystemBackend({ rootDir: "./workspace" }),
        },
        { prefix: "/", backend: new StateBackend() },
      ],
    }),
  },
});

await server.start();
```

### 技能和记忆

```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
import { startServer } from "deepagents-acp";

await startServer({
  agents: {
    name: "project-agent",
    description: "Agent with project-specific knowledge",
    skills: ["./skills/", "~/.deepagents/skills/"],
    memory: ["./.deepagents/AGENTS.md"],
  },
  workspaceRoot: process.cwd(),
});
```

<Info>
  有关协议细节和编辑器支持，请参阅上游 ACP 文档： -
  简介：[https://agentclientprotocol.com/get-started/introduction](https://agentclientprotocol.com/get-started/introduction) -
  客户端/编辑器：[https://agentclientprotocol.com/get-started/clients](https://agentclientprotocol.com/get-started/clients)
</Info>

***

<div className="source-links">
  <Callout icon="terminal-2">
    [连接这些文档](/use-these-docs) 到 Claude、VSCode 等，通过 MCP
    获取实时答案。
  </Callout>

  <Callout icon="edit">
    [在 GitHub
    上编辑此页面](https://github.com/langchain-ai/docs/edit/main/src/oss/deepagents/acp.mdx)
    或 [提交问题](https://github.com/langchain-ai/docs/issues/new/choose)。
  </Callout>
</div>
