m365-agents-py

支持材料可用性

此目录副本包含下方的内嵌指南，但不包含以下支持路径。这些是外部前置条件，并非随附文件：

• <support-root>/references/acceptance-criteria.md

使用依赖这些路径的步骤前，请索取原始支持材料或现有安装；此目录未提供经过验证的下载来源。请根据该安装解析每个路径，检查其内容，并确认适用的许可证及执行前提。在所需文件存在之前，不要运行命令，也不要声称已遵循引用的流程。不要伪造缺失的脚本，也不要将名称相同但无关的文件视为等效文件。此处已完整说明的独立步骤，可在用户授权范围内继续执行；对于任何依赖材料的步骤，请报告其当前不可用。

Microsoft 365 Agents SDK (Python)

使用 Microsoft Agents SDK、aiohttp 托管、AgentApplication 路由、流式响应和基于 MSAL 的身份验证，为 Microsoft 365、Teams 和 Copilot Studio 构建企业级 Agent。

实现前

• 使用 microsoft-docs MCP 验证 AgentApplication、start_agent_process 和身份验证选项的最新 API 签名。
• 在 PyPI 上确认计划使用的 microsoft-agents-* 软件包版本。

重要通知 - 导入变更

⚠️ 重大变更：近期更新已将 Python 导入结构从 microsoft.agents 改为 microsoft_agents（使用下划线而非点号）。

安装

pip install microsoft-agents-hosting-core
pip install microsoft-agents-hosting-aiohttp
pip install microsoft-agents-activity
pip install microsoft-agents-authentication-msal
pip install microsoft-agents-copilotstudio-client
pip install python-dotenv aiohttp

环境变量（.env）

CONNECTIONS__SERVICE_CONNECTION__SETTINGS__CLIENTID=<client-id>
CONNECTIONS__SERVICE_CONNECTION__SETTINGS__CLIENTSECRET=<client-secret>
CONNECTIONS__SERVICE_CONNECTION__SETTINGS__TENANTID=<tenant-id>

# Optional: OAuth handlers for auto sign-in
AGENTAPPLICATION__USERAUTHORIZATION__HANDLERS__GRAPH__SETTINGS__AZUREBOTOAUTHCONNECTIONNAME=<connection-name>

# Optional: Azure OpenAI for streaming
AZURE_OPENAI_ENDPOINT=<endpoint>
AZURE_OPENAI_API_VERSION=<version>
AZURE_OPENAI_API_KEY=<key>

# Optional: Copilot Studio client
COPILOTSTUDIOAGENT__ENVIRONMENTID=<environment-id>
COPILOTSTUDIOAGENT__SCHEMANAME=<schema-name>
COPILOTSTUDIOAGENT__TENANTID=<tenant-id>
COPILOTSTUDIOAGENT__AGENTAPPID=<app-id>

代码片段要求使用固定版本的 SDK，并采用各章节所示的设置和导入方式；重复的 /me 处理程序是可选方案，不应同时注册。请使用合成消息和获授权的身份；保留中间件验证，不要通过日志或云端跟踪暴露机密、私密轮次内容或令牌。Azure OpenAI 模型字段应配置为实际部署名称，而非臆测的公开模型 ID。

核心工作流：由 aiohttp 托管的 AgentApplication

import logging
from os import environ

from dotenv import load_dotenv
import aiohttp
from aiohttp.web import Request, Response, Application, run_app

from microsoft_agents.activity import load_configuration_from_env
from microsoft_agents.hosting.core import (
    Authorization,
    AgentApplication,
    TurnState,
    TurnContext,
    MemoryStorage,
)
from microsoft_agents.hosting.aiohttp import (
    CloudAdapter,
    start_agent_process,
    jwt_authorization_middleware,
)
from microsoft_agents.authentication.msal import MsalConnectionManager

# Enable logging
ms_agents_logger = logging.getLogger("microsoft_agents")
ms_agents_logger.addHandler(logging.StreamHandler())
ms_agents_logger.setLevel(logging.INFO)

# Load configuration
load_dotenv()
agents_sdk_config = load_configuration_from_env(environ)

# Create storage and connection manager
STORAGE = MemoryStorage()
CONNECTION_MANAGER = MsalConnectionManager(**agents_sdk_config)
ADAPTER = CloudAdapter(connection_manager=CONNECTION_MANAGER)
AUTHORIZATION = Authorization(STORAGE, CONNECTION_MANAGER, **agents_sdk_config)

# Create AgentApplication
ApplicationType = AgentApplication[TurnState]
AGENT_APP = ApplicationType(
    storage=STORAGE, adapter=ADAPTER, authorization=AUTHORIZATION, **agents_sdk_config
)


@AGENT_APP.conversation_update("membersAdded")
async def on_members_added(context: TurnContext, _state: TurnState):
    await context.send_activity("Welcome to the agent!")


@AGENT_APP.activity("message")
async def on_message(context: TurnContext, _state: TurnState):
    await context.send_activity(f"You said: {context.activity.text}")


@AGENT_APP.error
async def on_error(context: TurnContext, error: Exception):
    await context.send_activity("The agent encountered an error.")


# Server setup
async def entry_point(req: Request) -> Response:
    agent: AgentApplication = req.app["agent_app"]
    adapter: CloudAdapter = req.app["adapter"]
    return await start_agent_process(req, agent, adapter)


APP = Application(middlewares=[jwt_authorization_middleware])
APP.router.add_post("/api/messages", entry_point)
APP["agent_configuration"] = CONNECTION_MANAGER.get_default_connection_configuration()
APP["agent_app"] = AGENT_APP
APP["adapter"] = AGENT_APP.adapter

if __name__ == "__main__":
    run_app(APP, host="localhost", port=environ.get("PORT", 3978))

AgentApplication 路由

import re
from microsoft_agents.hosting.core import (
    AgentApplication, TurnState, TurnContext, MessageFactory
)
from microsoft_agents.activity import Activity, ActivityTypes

ApplicationType = AgentApplication[TurnState]
AGENT_APP = ApplicationType(
    storage=STORAGE, adapter=ADAPTER, authorization=AUTHORIZATION, **agents_sdk_config
)

# Welcome handler
@AGENT_APP.conversation_update("membersAdded")
async def on_members_added(context: TurnContext, _state: TurnState):
    await context.send_activity("Welcome!")

# Regex-based message handler
@AGENT_APP.message(re.compile(r"^hello$", re.IGNORECASE))
async def on_hello(context: TurnContext, _state: TurnState):
    await context.send_activity("Hello!")

# Simple string message handler
@AGENT_APP.message("/status")
async def on_status(context: TurnContext, _state: TurnState):
    await context.send_activity("Status: OK")

# Auth-protected message handler
@AGENT_APP.message("/me", auth_handlers=["GRAPH"])
async def on_profile(context: TurnContext, state: TurnState):
    token_response = await AGENT_APP.auth.get_token(context, "GRAPH")
    if token_response and token_response.token:
        # Use token to call Graph API
        await context.send_activity("Profile retrieved")

# Invoke activity handler
@AGENT_APP.activity(ActivityTypes.invoke)
async def on_invoke(context: TurnContext, _state: TurnState):
    invoke_response = Activity(
        type=ActivityTypes.invoke_response, value={"status": 200}
    )
    await context.send_activity(invoke_response)

# Fallback message handler
@AGENT_APP.activity("message")
async def on_message(context: TurnContext, _state: TurnState):
    await context.send_activity(f"Echo: {context.activity.text}")

# Error handler
@AGENT_APP.error
async def on_error(context: TurnContext, error: Exception):
    await context.send_activity("An error occurred.")

使用 Azure OpenAI 的流式响应

from openai import AsyncAzureOpenAI
from microsoft_agents.activity import SensitivityUsageInfo

CLIENT = AsyncAzureOpenAI(
    api_version=environ["AZURE_OPENAI_API_VERSION"],
    azure_endpoint=environ["AZURE_OPENAI_ENDPOINT"],
    api_key=environ["AZURE_OPENAI_API_KEY"]
)

@AGENT_APP.message("poem")
async def on_poem_message(context: TurnContext, _state: TurnState):
    # Configure streaming response
    context.streaming_response.set_feedback_loop(True)
    context.streaming_response.set_generated_by_ai_label(True)
    context.streaming_response.set_sensitivity_label(
        SensitivityUsageInfo(
            type="https://schema.org/Message",
            schema_type="CreativeWork",
            name="Internal",
        )
    )
    context.streaming_response.queue_informative_update("Starting a poem...\n")

    # Stream from Azure OpenAI
    streamed_response = await CLIENT.chat.completions.create(
        model="gpt-4o",
        messages=[
            {"role": "system", "content": "You are a creative assistant."},
            {"role": "user", "content": "Write a poem about Python."}
        ],
        stream=True,
    )
    
    try:
        async for chunk in streamed_response:
            if chunk.choices and chunk.choices[0].delta.content:
                context.streaming_response.queue_text_chunk(
                    chunk.choices[0].delta.content
                )
    finally:
        await context.streaming_response.end_stream()

OAuth / 自动登录

@AGENT_APP.message("/logout")
async def logout(context: TurnContext, state: TurnState):
    await AGENT_APP.auth.sign_out(context, "GRAPH")
    await context.send_activity(MessageFactory.text("You have been logged out."))


@AGENT_APP.message("/me", auth_handlers=["GRAPH"])
async def profile_request(context: TurnContext, state: TurnState):
    user_token_response = await AGENT_APP.auth.get_token(context, "GRAPH")
    if user_token_response and user_token_response.token:
        # Use token to call Microsoft Graph
        async with aiohttp.ClientSession() as session:
            headers = {
                "Authorization": f"Bearer {user_token_response.token}",
                "Content-Type": "application/json",
            }
            async with session.get(
                "https://graph.microsoft.com/v1.0/me", headers=headers
            ) as response:
                if response.status == 200:
                    user_info = await response.json()
                    await context.send_activity(f"Hello, {user_info['displayName']}!")

Copilot Studio 客户端（直连引擎）

import asyncio
from msal import PublicClientApplication
from microsoft_agents.activity import ActivityTypes, load_configuration_from_env
from microsoft_agents.copilotstudio.client import (
    ConnectionSettings,
    CopilotClient,
)

# Token cache (local file for interactive flows)
class LocalTokenCache:
    # See samples for full implementation
    pass

def acquire_token(settings, app_client_id, tenant_id):
    pca = PublicClientApplication(
        client_id=app_client_id,
        authority=f"https://login.microsoftonline.com/{tenant_id}",
    )
    
    token_request = {"scopes": ["https://api.powerplatform.com/.default"]}
    accounts = pca.get_accounts()
    
    if accounts:
        response = pca.acquire_token_silent(token_request["scopes"], account=accounts[0])
        return response.get("access_token")
    else:
        response = pca.acquire_token_interactive(**token_request)
        return response.get("access_token")


async def main():
    settings = ConnectionSettings(
        environment_id=environ.get("COPILOTSTUDIOAGENT__ENVIRONMENTID"),
        agent_identifier=environ.get("COPILOTSTUDIOAGENT__SCHEMANAME"),
    )
    
    token = acquire_token(
        settings,
        app_client_id=environ.get("COPILOTSTUDIOAGENT__AGENTAPPID"),
        tenant_id=environ.get("COPILOTSTUDIOAGENT__TENANTID"),
    )
    
    if not token:
        raise RuntimeError("Token acquisition failed")
    copilot_client = CopilotClient(settings, token)
    
    # Start conversation
    conversation_id = None
    act = copilot_client.start_conversation(True)
    async for action in act:
        if action.conversation:
            conversation_id = action.conversation.id
        if action.text:
            print(action.text)
    
    # Ask question
    if not conversation_id:
        raise RuntimeError("No conversation ID returned")
    replies = copilot_client.ask_question("Hello!", conversation_id)
    async for reply in replies:
        if reply.type == ActivityTypes.message:
            print(reply.text)


asyncio.run(main())

最佳实践

1. 使用 microsoft_agents 导入前缀（使用下划线而非点号）。
2. MemoryStorage 仅用于开发；生产环境请使用 BlobStorage 或 CosmosDB。
3. 始终使用 load_configuration_from_env(environ) 加载 SDK 配置。
4. 在 aiohttp Application 中间件中加入 jwt_authorization_middleware。
5. 使用 MsalConnectionManager 进行基于 MSAL 的身份验证。
6. 使用流式响应时，在 finally 代码块中调用 end_stream()。
7. 对受 OAuth 保护的路由，在消息装饰器上使用 auth_handlers 参数。
8. 将机密保存在环境变量中，而不是源代码中。

参考文件

文件	内容
references/acceptance-criteria.md	导入路径、托管管道、流式响应、OAuth 和 Copilot Studio 模式

参考链接

资源	URL
Microsoft 365 Agents SDK	https://learn.microsoft.com/en-us/microsoft-365/agents-sdk/
GitHub 示例（Python）	https://github.com/microsoft/Agents-for-python
PyPI 软件包	https://pypi.org/search/?q=microsoft-agents
与 Copilot Studio 集成	https://learn.microsoft.com/en-us/microsoft-365/agents-sdk/integrate-with-mcs

适用场景

当需要执行概述中描述的工作流或操作时，可使用此技能。

限制

• 仅当任务明确符合上述范围时，才使用此技能。
• 不要将输出视为环境特定验证、测试或专家审核的替代品。
• 如果缺少必需的输入、权限、安全边界或成功标准，请停止并请求澄清。