人类代理

即将推出……

先决条件

安装 Microsoft Agent Framework Anthropic 包。

pip install agent-framework-anthropic --pre

配置

环境变量

为人类身份验证设置所需的环境变量：

# Required for Anthropic API access
ANTHROPIC_API_KEY="your-anthropic-api-key"
ANTHROPIC_CHAT_MODEL_ID="claude-sonnet-4-5-20250929"  # or your preferred model

或者，可以在项目根目录中使用 .env 文件：

ANTHROPIC_API_KEY=your-anthropic-api-key
ANTHROPIC_CHAT_MODEL_ID=claude-sonnet-4-5-20250929

可以从 人类控制台获取 API 密钥。

入门

从代理框架导入所需的类：

import asyncio
from agent_framework.anthropic import AnthropicClient

创建人类代理

基本代理创建

创建人类代理的最简单方法：

async def basic_example():
    # Create an agent using Anthropic
    agent = AnthropicClient().create_agent(
        name="HelpfulAssistant",
        instructions="You are a helpful assistant.",
    )

    result = await agent.run("Hello, how can you help me?")
    print(result.text)

使用显式配置

可以提供显式配置，而不是依赖于环境变量：

async def explicit_config_example():
    agent = AnthropicClient(
        model_id="claude-sonnet-4-5-20250929",
        api_key="your-api-key-here",
    ).create_agent(
        name="HelpfulAssistant",
        instructions="You are a helpful assistant.",
    )

    result = await agent.run("What can you do?")
    print(result.text)

在 Foundry 上使用人类学

在 Foundry 上设置人类学后，请确保设置了以下环境变量：

ANTHROPIC_FOUNDRY_API_KEY="your-foundry-api-key"
ANTHROPIC_FOUNDRY_RESOURCE="your-foundry-resource-name"

然后创建代理，如下所示：

from agent_framework.anthropic import AnthropicClient
from anthropic import AsyncAnthropicFoundry

async def foundry_example():
    agent = AnthropicClient(
        anthropic_client=AsyncAnthropicFoundry()
    ).create_agent(
        name="FoundryAgent",
        instructions="You are a helpful assistant using Anthropic on Foundry.",
    )

    result = await agent.run("How do I use Anthropic on Foundry?")
    print(result.text)

注意：需要安装 anthropic>=0.74.0。

代理功能

函数工具

为代理配备自定义功能：

from typing import Annotated

def get_weather(
    location: Annotated[str, "The location to get the weather for."],
) -> str:
    """Get the weather for a given location."""
    conditions = ["sunny", "cloudy", "rainy", "stormy"]
    return f"The weather in {location} is {conditions[randint(0, 3)]} with a high of {randint(10, 30)}°C."

async def tools_example():
    agent = AnthropicClient().create_agent(
        name="WeatherAgent",
        instructions="You are a helpful weather assistant.",
        tools=get_weather,  # Add tools to the agent
    )

    result = await agent.run("What's the weather like in Seattle?")
    print(result.text)

流式处理响应

对即时生成的响应进行获取，以提升用户体验。

async def streaming_example():
    agent = AnthropicClient().create_agent(
        name="WeatherAgent",
        instructions="You are a helpful weather agent.",
        tools=get_weather,
    )

    query = "What's the weather like in Portland and in Paris?"
    print(f"User: {query}")
    print("Agent: ", end="", flush=True)
    async for chunk in agent.run_stream(query):
        if chunk.text:
            print(chunk.text, end="", flush=True)
    print()

托管工具

人类代理支持托管的工具，例如 Web 搜索、MCP（模型上下文协议）和代码执行：

from agent_framework import HostedMCPTool, HostedWebSearchTool

async def hosted_tools_example():
    agent = AnthropicClient().create_agent(
        name="DocsAgent",
        instructions="You are a helpful agent for both Microsoft docs questions and general questions.",
        tools=[
            HostedMCPTool(
                name="Microsoft Learn MCP",
                url="https://learn.microsoft.com/api/mcp",
            ),
            HostedWebSearchTool(),
        ],
        max_tokens=20000,
    )

    result = await agent.run("Can you compare Python decorators with C# attributes?")
    print(result.text)

扩展思维（推理）

Anthropic通过thinking功能支持扩展思维能力，使模型能够展示其推理过程。

from agent_framework import TextReasoningContent, UsageContent

async def thinking_example():
    agent = AnthropicClient().create_agent(
        name="DocsAgent",
        instructions="You are a helpful agent.",
        tools=[HostedWebSearchTool()],
        max_tokens=20000,
        additional_chat_options={
            "thinking": {"type": "enabled", "budget_tokens": 10000}
        },
    )

    query = "Can you compare Python decorators with C# attributes?"
    print(f"User: {query}")
    print("Agent: ", end="", flush=True)

    async for chunk in agent.run_stream(query):
        for content in chunk.contents:
            if isinstance(content, TextReasoningContent):
                # Display thinking in a different color
                print(f"\033[32m{content.text}\033[0m", end="", flush=True)
            if isinstance(content, UsageContent):
                print(f"\n\033[34m[Usage: {content.details}]\033[0m\n", end="", flush=True)
        if chunk.text:
            print(chunk.text, end="", flush=True)
    print()

使用代理

代理是标准 BaseAgent 代理，支持所有标准代理操作。

有关如何运行和与代理交互的详细信息，请参阅 代理入门教程 。