Skip to content

Latest commit

 

History

History

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

README.md

Devin Sample Agent - Node.js

This sample demonstrates how to build an agent using Devin in Node.js with the Microsoft Agent 365 SDK. It covers:

  • Observability: End-to-end tracing, caching, and monitoring for agent applications
  • Notifications: Services and models for managing user notifications
  • Tools: Model Context Protocol tools for building advanced agent solutions
  • Hosting Patterns: Hosting with Microsoft 365 Agents SDK

This sample uses the Microsoft Agent 365 SDK for Node.js.

For comprehensive documentation and guidance on building agents with the Microsoft Agent 365 SDK, including how to add tooling, observability, and notifications, visit the Microsoft Agent 365 Developer Documentation.

Prerequisites

  • Node.js 24.x or higher
  • Microsoft Agent 365 SDK
  • Devin API credentials

Working with User Identity

On every incoming message, the A365 platform populates activity.from with basic user information — always available with no API calls or token acquisition:

Field Description
activity.from.id Channel-specific user ID (e.g., 29:1AbcXyz... in Teams)
activity.from.name Display name as known to the channel
activity.from.aadObjectId Azure AD Object ID — use this to call Microsoft Graph

The sample logs these fields at the start of every message turn.

Sending Multiple Messages in Teams

Agent365 agents can send multiple discrete messages in response to a single user prompt in Teams. This is achieved by calling sendActivity multiple times within a single turn.

Important: Streaming responses are not supported for agentic identities in Teams. The SDK detects agentic identity and buffers the stream into a single message. Use sendActivity directly to send immediate, discrete messages to the user.

The sample demonstrates this in the message activity handler (agent.ts):

// Message 1: immediate ack — reaches the user right away
await context.sendActivity('Got it — working on it…');

// ... LLM processing ...

// Message 2: the LLM response (sent from within handleAgentMessageActivity)
await turnContext.sendActivity(chunk);

Each sendActivity call produces a separate Teams message. You can call it as many times as needed to send progress updates, partial results, or a final answer.

Typing Indicators

The agent sends typing indicators in a loop every ~4 seconds to keep the ... animation alive while the LLM processes the request:

let typingInterval: ReturnType<typeof setInterval> | undefined;
const startTypingLoop = () => {
  typingInterval = setInterval(async () => {
    await context.sendActivity(Activity.fromObject({ type: 'typing' }));
  }, 4000);
};
const stopTypingLoop = () => { clearInterval(typingInterval); };

startTypingLoop();
try {
  // ... LLM processing ...
} finally {
  stopTypingLoop();
}

Note: Typing indicators are only visible in 1:1 chats and small group chats — not in channels.

Running the Agent

To set up and test this agent, refer to the Configure Agent Testing guide for complete instructions.

Deploying the Agent

Refer to the Deploy and publish agents guide for complete instructions.

Support

For issues, questions, or feedback:

Contributing

This project welcomes contributions and suggestions. Most contributions require you to agree to a Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us the rights to use your contribution. For details, visit https://cla.opensource.microsoft.com.

When you submit a pull request, a CLA bot will automatically determine whether you need to provide a CLA and decorate the PR appropriately (e.g., status check, comment). Simply follow the instructions provided by the bot. You will only need to do this once across all repos using our CLA.

This project has adopted the Microsoft Open Source Code of Conduct. For more information see the Code of Conduct FAQ or contact opencode@microsoft.com with any additional questions or comments.

Additional Resources

Trademarks

Microsoft, Windows, Microsoft Azure and/or other Microsoft products and services referenced in the documentation may be either trademarks or registered trademarks of Microsoft in the United States and/or other countries. The licenses for this project do not grant you rights to use any Microsoft names, logos, or trademarks. Microsoft's general trademark guidelines can be found at http://go.microsoft.com/fwlink/?LinkID=254653.

License

Copyright (c) Microsoft Corporation. All rights reserved.

Licensed under the MIT License - see the LICENSE file for details.