opção

m365-agents-ts

microsoft/skills microsoft/skills

Construa agentes empresariais para o Microsoft 365, Teams e Copilot Studio usando o SDK de Agentes do Microsoft 365 com hospedagem Express, roteamento do AgentApplication, respostas em streaming e integrações do cliente do Copilot Studio.

...Expandir tudo
4
Tempo atualizado 12 de Setembro de 2026

SDK de Agentes do Microsoft 365 (TypeScript)

Crie agentes empresariais para o Microsoft 365, Teams e Copilot Studio usando o SDK de Agentes do Microsoft 365 com hospedagem Express, roteamento do AgentApplication, respostas em streaming e integrações do cliente do Copilot Studio.

Antes da implementação

  • Use o MCP microsoft-docs para verificar as assinaturas de API mais recentes do AgentApplication, startServer e CopilotStudioClient.
  • Confirme as versões dos pacotes no npm antes de conectar amostras ou modelos.

Instalação

npm install @microsoft/agents-hosting @microsoft/agents-hosting-express @microsoft/agents-activity
npm install @microsoft/agents-copilotstudio-client

Variáveis de Ambiente

PORT=3978
AZURE_RESOURCE_NAME=<azure-openai-resource>
AZURE_API_KEY=<azure-openai-key>
AZURE_OPENAI_DEPLOYMENT_NAME=gpt-4o-mini

TENANT_ID=<tenant-id>
CLIENT_ID=<client-id>
CLIENT_SECRET=<client-secret>

COPILOT_ENVIRONMENT_ID=<environment-id>
COPILOT_SCHEMA_NAME=<schema-name>
COPILOT_CLIENT_ID=<copilot-app-client-id>
COPILOT_BEARER_TOKEN=<copilot-jwt></copilot-jwt></copilot-app-client-id></schema-name></environment-id></client-secret></client-id></tenant-id></azure-openai-key></azure-openai-resource>

Fluxo de Trabalho Principal: AgentApplication hospedado no Express

import {
  AgentApplication,
  TurnContext,
  TurnState,
} from "@microsoft/agents-hosting";
import { startServer } from "@microsoft/agents-hosting-express";

const agent = new AgentApplication<turnstate>();

agent.onConversationUpdate("membersAdded", async (context: TurnContext) => {
  await context.sendActivity("Bem-vindo ao agente.");
});

agent.onMessage("hello", async (context: TurnContext) => {
  await context.sendActivity(`Eco: ${context.activity.text}`);
});

startServer(agent);
</turnstate>

Respostas em streaming com Azure OpenAI

import { azure } from "@ai-sdk/azure";
import {
  AgentApplication,
  TurnContext,
  TurnState,
} from "@microsoft/agents-hosting";
import { startServer } from "@microsoft/agents-hosting-express";
import { streamText } from "ai";

const agent = new AgentApplication<turnstate>();

agent.onMessage("poem", async (context: TurnContext) => {
  context.streamingResponse.setFeedbackLoop(true);
  context.streamingResponse.setGeneratedByAILabel(true);
  context.streamingResponse.setSensitivityLabel({
    type: "https://schema.org/Message",
    "@type": "CreativeWork",
    name: "Interno",
  });

  await context.streamingResponse.queueInformativeUpdate("iniciando um poema...");

  const { fullStream } = streamText({
    model: azure(process.env.AZURE_OPENAI_DEPLOYMENT_NAME || "gpt-4o-mini"),
    system: "Você é um assistente criativo.",
    prompt: "Escreva um poema sobre Apolo.",
  });

  try {
    for await (const part of fullStream) {
      if (part.type === "text-delta" && part.text.length > 0) {
        await context.streamingResponse.queueTextChunk(part.text);
      }
      if (part.type === "error") {
        throw new Error(`Erro de streaming: ${part.error}`);
      }
    }
  } finally {
    await context.streamingResponse.endStream();
  }
});

startServer(agent);
</turnstate>

Manipulação de atividade de invocação

import { Activity, ActivityTypes } from "@microsoft/agents-activity";
import {
  AgentApplication,
  TurnContext,
  TurnState,
} from "@microsoft/agents-hosting";

const agent = new AgentApplication<turnstate>();

agent.onActivity("invoke", async (context: TurnContext) => {
  const invokeResponse = Activity.fromObject({
    type: ActivityTypes.InvokeResponse,
    value: { status: 200 },
  });

  await context.sendActivity(invokeResponse);
  await context.sendActivity("Obrigado por enviar seu feedback.");
});
</turnstate>

Cliente do Copilot Studio (Direto para o Mecanismo)

import { CopilotStudioClient } from "@microsoft/agents-copilotstudio-client";

const settings = {
  environmentId: process.env.COPILOT_ENVIRONMENT_ID!,
  schemaName: process.env.COPILOT_SCHEMA_NAME!,
  clientId: process.env.COPILOT_CLIENT_ID!,
};

const tokenProvider = async (): Promise<string> => {
  return process.env.COPILOT_BEARER_TOKEN!;
};

const client = new CopilotStudioClient(settings, tokenProvider);

const conversation = await client.startConversationAsync();
const reply = await client.askQuestionAsync("Olá!", conversation.id);
console.log(reply);
</string>

Integração do WebChat do Copilot Studio

import { CopilotStudioWebChat } from "@microsoft/agents-copilotstudio-client";

const directLine = CopilotStudioWebChat.createConnection(client, {
  showTyping: true,
});

window.WebChat.renderWebChat(
  {
    directLine,
  },
  document.getElementById("webchat")!,
);

Melhores Práticas

  1. Use o AgentApplication para roteamento e mantenha os manipuladores focados em uma única responsabilidade.
  2. Prefira streamingResponse para conclusões de longa duração e chame endStream em blocos finally.
  3. Mantenha segredos fora do código-fonte; carregue tokens de variáveis de ambiente ou repositórios seguros.
  4. Reutilize instâncias do CopilotStudioClient e armazene tokens em cache no seu provedor de tokens.
  5. Valide cargas úteis de invoke antes de registrar ou persistir o feedback.

Links de Referência

RecursoURL
SDK de Agentes do Microsoft 365https://learn.microsoft.com/en-us/microsoft-365/agents-sdk/
Visão geral do SDK JavaScripthttps://learn.microsoft.com/en-us/javascript/api/overview/agents-overview?view=agents-sdk-js-latest
@microsoft/agents-hosting-expresshttps://learn.microsoft.com/en-us/javascript/api/%40microsoft/agents-hosting-express?view=agents-sdk-js-latest
@microsoft/agents-copilotstudio-clienthttps://learn.microsoft.com/en-us/javascript/api/%40microsoft/agents-copilotstudio-client?view=agents-sdk-js-latest
Integrar com o Copilot Studiohttps://learn.microsoft.com/en-us/microsoft-365/agents-sdk/integrate-with-mcs
Amostras do GitHubhttps://github.com/microsoft/Agents/tree/main/samples/nodejs
Ver no GitHub
---
name: m365-agents-ts
description: Build enterprise agents for Microsoft 365, Teams, and Copilot Studio using the Microsoft 365 Agents SDK with Express hosting, AgentApplication routing, streaming responses, and Copilot Studio client integrations.
license: MIT
---

# Microsoft 365 Agents SDK (TypeScript)

Build enterprise agents for Microsoft 365, Teams, and Copilot Studio using the Microsoft 365 Agents SDK with Express hosting, AgentApplication routing, streaming responses, and Copilot Studio client integrations.

## Before implementation

- Use the microsoft-docs MCP to verify the latest API signatures for AgentApplication, startServer, and CopilotStudioClient.
- Confirm package versions on npm before wiring up samples or templates.

## Installation

```bash
npm install @microsoft/agents-hosting @microsoft/agents-hosting-express @microsoft/agents-activity
npm install @microsoft/agents-copilotstudio-client
```

## Environment Variables

```bash
PORT=3978
AZURE_RESOURCE_NAME=<azure-openai-resource>
AZURE_API_KEY=<azure-openai-key>
AZURE_OPENAI_DEPLOYMENT_NAME=gpt-4o-mini

TENANT_ID=<tenant-id>
CLIENT_ID=<client-id>
CLIENT_SECRET=<client-secret>

COPILOT_ENVIRONMENT_ID=<environment-id>
COPILOT_SCHEMA_NAME=<schema-name>
COPILOT_CLIENT_ID=<copilot-app-client-id>
COPILOT_BEARER_TOKEN=<copilot-jwt>
```

## Core Workflow: Express-hosted AgentApplication

```typescript
import {
  AgentApplication,
  TurnContext,
  TurnState,
} from "@microsoft/agents-hosting";
import { startServer } from "@microsoft/agents-hosting-express";

const agent = new AgentApplication<TurnState>();

agent.onConversationUpdate("membersAdded", async (context: TurnContext) => {
  await context.sendActivity("Welcome to the agent.");
});

agent.onMessage("hello", async (context: TurnContext) => {
  await context.sendActivity(`Echo: ${context.activity.text}`);
});

startServer(agent);
```

## Streaming responses with Azure OpenAI

```typescript
import { azure } from "@ai-sdk/azure";
import {
  AgentApplication,
  TurnContext,
  TurnState,
} from "@microsoft/agents-hosting";
import { startServer } from "@microsoft/agents-hosting-express";
import { streamText } from "ai";

const agent = new AgentApplication<TurnState>();

agent.onMessage("poem", async (context: TurnContext) => {
  context.streamingResponse.setFeedbackLoop(true);
  context.streamingResponse.setGeneratedByAILabel(true);
  context.streamingResponse.setSensitivityLabel({
    type: "https://schema.org/Message",
    "@type": "CreativeWork",
    name: "Internal",
  });

  await context.streamingResponse.queueInformativeUpdate("starting a poem...");

  const { fullStream } = streamText({
    model: azure(process.env.AZURE_OPENAI_DEPLOYMENT_NAME || "gpt-4o-mini"),
    system: "You are a creative assistant.",
    prompt: "Write a poem about Apollo.",
  });

  try {
    for await (const part of fullStream) {
      if (part.type === "text-delta" && part.text.length > 0) {
        await context.streamingResponse.queueTextChunk(part.text);
      }
      if (part.type === "error") {
        throw new Error(`Streaming error: ${part.error}`);
      }
    }
  } finally {
    await context.streamingResponse.endStream();
  }
});

startServer(agent);
```

## Invoke activity handling

```typescript
import { Activity, ActivityTypes } from "@microsoft/agents-activity";
import {
  AgentApplication,
  TurnContext,
  TurnState,
} from "@microsoft/agents-hosting";

const agent = new AgentApplication<TurnState>();

agent.onActivity("invoke", async (context: TurnContext) => {
  const invokeResponse = Activity.fromObject({
    type: ActivityTypes.InvokeResponse,
    value: { status: 200 },
  });

  await context.sendActivity(invokeResponse);
  await context.sendActivity("Thanks for submitting your feedback.");
});
```

## Copilot Studio client (Direct to Engine)

```typescript
import { CopilotStudioClient } from "@microsoft/agents-copilotstudio-client";

const settings = {
  environmentId: process.env.COPILOT_ENVIRONMENT_ID!,
  schemaName: process.env.COPILOT_SCHEMA_NAME!,
  clientId: process.env.COPILOT_CLIENT_ID!,
};

const tokenProvider = async (): Promise<string> => {
  return process.env.COPILOT_BEARER_TOKEN!;
};

const client = new CopilotStudioClient(settings, tokenProvider);

const conversation = await client.startConversationAsync();
const reply = await client.askQuestionAsync("Hello!", conversation.id);
console.log(reply);
```

## Copilot Studio WebChat integration

```typescript
import { CopilotStudioWebChat } from "@microsoft/agents-copilotstudio-client";

const directLine = CopilotStudioWebChat.createConnection(client, {
  showTyping: true,
});

window.WebChat.renderWebChat(
  {
    directLine,
  },
  document.getElementById("webchat")!,
);
```

## Best Practices

1. Use AgentApplication for routing and keep handlers focused on one responsibility.
2. Prefer streamingResponse for long-running completions and call endStream in finally blocks.
3. Keep secrets out of source code; load tokens from environment variables or secure stores.
4. Reuse CopilotStudioClient instances and cache tokens in your token provider.
5. Validate invoke payloads before logging or persisting feedback.

## Reference Links

| Resource                               | URL                                                                                                                 |
| -------------------------------------- | ------------------------------------------------------------------------------------------------------------------- |
| Microsoft 365 Agents SDK               | https://learn.microsoft.com/en-us/microsoft-365/agents-sdk/                                                         |
| JavaScript SDK overview                | https://learn.microsoft.com/en-us/javascript/api/overview/agents-overview?view=agents-sdk-js-latest                 |
| @microsoft/agents-hosting-express      | https://learn.microsoft.com/en-us/javascript/api/%40microsoft/agents-hosting-express?view=agents-sdk-js-latest      |
| @microsoft/agents-copilotstudio-client | https://learn.microsoft.com/en-us/javascript/api/%40microsoft/agents-copilotstudio-client?view=agents-sdk-js-latest |
| Integrate with Copilot Studio          | https://learn.microsoft.com/en-us/microsoft-365/agents-sdk/integrate-with-mcs                                       |
| GitHub samples                         | https://github.com/microsoft/Agents/tree/main/samples/nodejs                                                        |

Todos os arquivos

0 arquivos

Instalar m365-agents-ts

Baixe e extraia os arquivos de habilidade para o diretório .claude/skills/.

Baixar ZIP

Clone o repositório e copie os arquivos da habilidade para o seu projeto.

git clone https://github.com/microsoft/skills/tree/main/.github/plugins/azure-sdk-typescript/skills/m365-agents-ts # Copy SKILL.md to your .claude/skills/ directory

Copiar Copiar
Configuração rápida: Copie a pasta de habilidades para .claude/skills/ O Claude detectará e usará automaticamente a habilidade
Repositório microsoft/skills

Habilidades relacionadas

agentwallet
Tempo atualizado 7 de Julho de 2026
brightdata-cli
Tempo atualizado 29 de Junho de 2026
humanize
Tempo atualizado 7 de Julho de 2026
korean-stock-search
Tempo atualizado 8 de Julho de 2026
OR