← All posts

Claude Agent SDK

為什麼需要 CLAUDE AGENT SDK

  • 內建工具鏈，如 Read, Write, Edit, Bash, Glob, Grep, WebSearch）。你只要給它一個方向，它自己就會在後台不斷進行「觀察環境 $\rightarrow$ 採取行動 $\rightarrow$ 驗證結果」的自主循環。
  • 具備 subagent 功能，不會互相污染環境，可以並行。
  • 自動化 compact contextd

Quick Start - 建立一個自動 fix bugs 的 agent

  1. 安裝 Claude Agent SDK
  2. 建立 utils.py
// utils.py

def calculate_average(numbers):
    total = 0
    for num in numbers:
        total += num
    return total / len(numbers)


def get_user_name(user):
    return user["name"].upper()

3.建立 agent.py

// agent.py

import asyncio
from claude_agent_sdk import query, ClaudeAgentOptions, AssistantMessage, ResultMessage


async def main():
    # Agentic loop: streams messages as Claude works
    async for message in query(
        prompt="Review utils.py for bugs that would cause crashes. Fix any issues you find.",
        options=ClaudeAgentOptions(
            allowed_tools=["Read", "Edit", "Glob"],  # Tools Claude can use
            permission_mode="acceptEdits",  # Auto-approve file edits
        ),
    ):
        # Print human-readable output
        if isinstance(message, AssistantMessage):
            for block in message.content:
                if hasattr(block, "text"):
                    print(block.text)  # Claude's reasoning
                elif hasattr(block, "name"):
                    print(f"Tool: {block.name}")  # Tool being called
        elif isinstance(message, ResultMessage):
            print(f"Done: {message.subtype}")  # Final result


asyncio.run(main())
  1. 運行 agent sdk
python3 -m venv .venv && source .venv/bin/activate
pip3 install claude-agent-sdk


5. agent 自動會開始呼叫 agent sdk，並針對 utils.py 中的 bug 進行分析