文档索引

在此处获取完整文档索引：https://code.claude.com/docs/llms.txt 使用此文件发现所有可用页面，然后再进一步探索。

流式输入

了解 Claude Agent SDK 的两种输入模式及各自的使用场景

概述

Claude Agent SDK 支持两种不同的输入模式来与智能体交互：

流式输入模式（默认且推荐）- 持久化的交互式会话
单消息输入 - 使用会话状态和恢复的一次性查询

本指南解释了每种模式的差异、优势和用例，帮助你为应用选择正确的方法。

流式输入模式（推荐）

流式输入模式是使用 Claude Agent SDK 的首选方式。它提供对智能体功能的完全访问，并支持丰富的交互式体验。

它允许智能体作为长时间运行的进程运行，接收用户输入、处理中断、显示权限请求并管理会话。

工作原理

sequenceDiagram
    participant App as Your Application
    participant Agent as Claude Agent
    participant Tools as Tools/Hooks
    participant FS as Environment/<br/>File System

    App->>Agent: Initialize with AsyncGenerator
    activate Agent

    App->>Agent: Yield Message 1
    Agent->>Tools: Execute tools
    Tools->>FS: Read files
    FS-->>Tools: File contents
    Tools->>FS: Write/Edit files
    FS-->>Tools: Success/Error
    Agent-->>App: Stream partial response
    Agent-->>App: Stream more content...
    Agent->>App: Complete Message 1

    App->>Agent: Yield Message 2 + Image
    Agent->>Tools: Process image & execute
    Tools->>FS: Access filesystem
    FS-->>Tools: Operation results
    Agent-->>App: Stream response 2

    App->>Agent: Queue Message 3
    App->>Agent: Interrupt/Cancel
    Agent->>App: Handle interruption

    Note over App,Agent: Session stays alive
    Note over Tools,FS: Persistent file system<br/>state maintained

    deactivate Agent

优势

◆图片上传

将图片直接附加到消息中进行视觉分析和理解

◆排队消息

发送多个顺序处理的消息，并能够中断

◆工具集成

在会话期间完全访问所有工具和自定义 MCP 服务器

◆钩子支持

使用生命周期钩子在各个点自定义行为

◆实时反馈

在生成时查看响应，而不仅仅是最终结果

◆上下文持久化

自然地在多轮对话中维护对话上下文

实现示例

import { query, type SDKUserMessage } from "@anthropic-ai/claude-agent-sdk";
import { readFile } from "fs/promises";

async function* generateMessages(): AsyncGenerator<SDKUserMessage> {
  // First message
  yield {
    type: "user",
    message: {
      role: "user",
      content: "Analyze this codebase for security issues"
    },
    parent_tool_use_id: null
  };

  // Wait for conditions or user input
  await new Promise((resolve) => setTimeout(resolve, 2000));

  // Follow-up with image
  yield {
    type: "user",
    message: {
      role: "user",
      content: [
        {
          type: "text",
          text: "Review this architecture diagram"
        },
        {
          type: "image",
          source: {
            type: "base64",
            media_type: "image/png",
            data: await readFile("diagram.png", "base64")
          }
        }
      ]
    },
    parent_tool_use_id: null
  };
}

// Process streaming responses
for await (const message of query({
  prompt: generateMessages(),
  options: {
    maxTurns: 10,
    allowedTools: ["Read", "Grep"]
  }
})) {
  if (message.type === "result" && message.subtype === "success") {
    console.log(message.result);
  }
}

from claude_agent_sdk import (
    ClaudeSDKClient,
    ClaudeAgentOptions,
    AssistantMessage,
    TextBlock,
)
import asyncio
import base64


async def streaming_analysis():
    async def message_generator():
        # First message
        yield {
            "type": "user",
            "message": {
                "role": "user",
                "content": "Analyze this codebase for security issues",
            },
        }

        # Wait for conditions
        await asyncio.sleep(2)

        # Follow-up with image
        with open("diagram.png", "rb") as f:
            image_data = base64.b64encode(f.read()).decode()

        yield {
            "type": "user",
            "message": {
                "role": "user",
                "content": [
                    {"type": "text", "text": "Review this architecture diagram"},
                    {
                        "type": "image",
                        "source": {
                            "type": "base64",
                            "media_type": "image/png",
                            "data": image_data,
                        },
                    },
                ],
            },
        }

    # Use ClaudeSDKClient for streaming input
    options = ClaudeAgentOptions(max_turns=10, allowed_tools=["Read", "Grep"])

    async with ClaudeSDKClient(options) as client:
        # Send streaming input
        await client.query(message_generator())

        # Process responses
        async for message in client.receive_response():
            if isinstance(message, AssistantMessage):
                for block in message.content:
                    if isinstance(block, TextBlock):
                        print(block.text)


asyncio.run(streaming_analysis())

单消息输入

单消息输入更简单但限制更多。

何时使用单消息输入

在以下情况下使用单消息输入：

你需要一次性响应
你不需要图片附件、钩子等
你需要在无状态环境中运行，例如 lambda 函数

限制

Warning

单消息输入模式不支持：

消息中的直接图片附件
动态消息排队
实时中断
钩子集成
自然的多轮对话

实现示例

import { query } from "@anthropic-ai/claude-agent-sdk";

// Simple one-shot query
for await (const message of query({
  prompt: "Explain the authentication flow",
  options: {
    maxTurns: 1,
    allowedTools: ["Read", "Grep"]
  }
})) {
  if (message.type === "result" && message.subtype === "success") {
    console.log(message.result);
  }
}

// Continue conversation with session management
for await (const message of query({
  prompt: "Now explain the authorization process",
  options: {
    continue: true,
    maxTurns: 1
  }
})) {
  if (message.type === "result" && message.subtype === "success") {
    console.log(message.result);
  }
}

from claude_agent_sdk import query, ClaudeAgentOptions, ResultMessage
import asyncio


async def single_message_example():
    # Simple one-shot query using query() function
    async for message in query(
        prompt="Explain the authentication flow",
        options=ClaudeAgentOptions(max_turns=1, allowed_tools=["Read", "Grep"]),
    ):
        if isinstance(message, ResultMessage):
            print(message.result)

    # Continue conversation with session management
    async for message in query(
        prompt="Now explain the authorization process",
        options=ClaudeAgentOptions(continue_conversation=True, max_turns=1),
    ):
        if isinstance(message, ResultMessage):
            print(message.result)


asyncio.run(single_message_example())