microsoft / microsoft/botframework-webchat-embed

Support M365 Agents SDK channel for Copilot Studio

Open
#9 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

enhancement
Dominant language
JavaScript
Stars
0
Forks
2
PR merge metrics
No merged PRs in 30d

Description

Summary

Add support for connecting to Copilot Studio agents via the M365 Agents SDK channel, as an alternative to the current Direct Line channel.

Motivation

The M365 Agents SDK provides a newer protocol for communicating with Copilot Studio agents that supports:

  • Streaming responses (token-by-token)
  • Reasoning/thinking traces
  • Citations and source references
  • Generative search results
  • Activity-based protocol with richer message types

This is the direction Microsoft is moving for Copilot Studio integrations and would provide a significantly richer chat experience compared to the current Direct Line approach.

Possible Approach

  • Add a data-webchat-mode attribute (directline | m365)
  • For M365 mode, require data-webchat-environment-id, data-webchat-agent-id, data-webchat-tenant-id, and data-webchat-client-id
  • Authenticate with Microsoft using MSAL.js
  • Use the M365 Agents SDK client to establish the conversation
  • Render streaming responses, citations, and other rich content in the chat UI

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by locating the embed configuration that handles data-webchat-mode and the existing Direct Line connection, then review how the chat UI renders messages. Define the M365 mode inputs, MSAL.js authentication, and M365 Agents SDK conversation flow; done means Copilot Studio connections support streaming responses, reasoning traces, citations, and other rich content.

Written by the indexing model from the issue text.

Assessment

Tech stack
javascript
Domain
authentication, frontend
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.