Chat participant API

[roblourens]

We have finalized the Language Model and Chat Participant API 🚀
Thus, you can now publish your extensions to the VS Marketplace. This API is finalized in VS Code Insiders, and will be finalized in VS Code Stable in July. In your package.json, you should set

"engines": {
	"vscode": "^1.90.0"
},

and VS Code Stable will gracefully handle your extensions and ignore your usage of Language Model and Chat API until the API gets finalized in Stable in July. Full docs https://code.visualstudio.com/api/extension-guides/chat

We are excited to see what you build ✨

---

-- Proposal dts: https://github.com/microsoft/vscode/blob/main/src/vscode-dts/vscode.proposed.chatParticipant.d.ts

• Sample: https://github.com/microsoft/vscode-extension-samples/tree/main/chat-sample
• Docs: https://code.visualstudio.com/api/extension-guides/chat

Extension authors can subscribe to this issue to get updates about the proposed chat agent API. There may still be breaking changes coming, and I will post here whenever a breaking change is made.

I'm also interested in feedback about how you might use this API.

Current TODOs

• Need to enable agents to identify sessions uniquely and store state, including across a window reload
• Should be able to use shouldRepopulate for agents
  • Maybe this should be the default behavior for agents
• ChatAgentReplyFollowup should parameterize the agent and slash command names, don't require the agent to include them in the prompt as text
  • Maybe this goes for variables too, but variables like #file are complex
• Enable references and progress messages from chat variable resolvers #204539
• ChatAgentContentReference needs to support https URIs #203822
• Change the history context shape to be a flat list of messages, instead of request/response pairs
• Understand how duplicate agent IDs should be handled
• Enable agents to resolve a variable value on-demand, instead of resolving all variables before invoking the agent

---

• Add a persist flag to ChatAgentProgressMessage for it to stay visible with a ✔️ even when more content has been added.
  • This would be useful when you want the progress message to remain and show what happened, eg in representing a function call. I've seen multiple extension authors add their own version of this just with text.
• Better support for /help with chat agents #197081

---

• ChatAgentCommandFollowup should become a progress message instead of a followup
• In history, agents have to parse agent names and slash commands from the raw ChatMessage. They shouldn't have to understand the input syntax- the type in history should be related to the request and progress/result types that we already have.
• Add generic type parameter for the type of the result, which can include custom properties
• 'variables' proposal is referenced from chatAgents2, need to merge it in
• Merge ChatAgentTask and ChatAgentProgressMessage #200598

[roblourens]

November additions

• Send a ChatAgentProgressMessage to show progress steps on your response. @workspace uses this.

  vscode/src/vscode-dts/vscode.proposed.chatAgents2.d.ts

  Lines 261 to 266 in e4cb2cf

  	/**
  	* Is displayed in the UI to communicate steps of progress to the user. Should be used when the agent may be slow to respond, e.g. due to doing extra work before sending the actual request to the LLM.
  	*/
  	export interface ChatAgentProgressMessage {
  	message: string;
  	}

• Implement a ChatAgentCompletionItemProvider for variables to show up that are only for this agent. Other chat variables are global.

  vscode/src/vscode-dts/vscode.proposed.chatAgents2Additions.d.ts

  Lines 58 to 60 in e4cb2cf

  	export interface ChatAgentCompletionItemProvider {
  	provideCompletionItems(query: string, token: CancellationToken): ProviderResult<ChatAgentCompletionItem[]>;
  	}

[bionicles]

any comment on this https://archive.ph/N5iVq#selection-1895.0-1897.140 ?

why does github copilot think i need to talk to a lawyer to know if it's OK to use github copilot to develop AI?

[ntindle]

Has any research been done into the agent protocol for this?

[InTheCloudDan]

Do you have any example use cases of ChatAgentCompletionItemProvider?

[pelikhan]

• Do you have more information about the options to access.makeRequest?
• Do you have more information about ChatAgentUsedContext and MappedEditsProvider?

[roblourens]

@bionicles I wouldn't rely on Copilot Chat for legal advice, talking to a lawyer may be a good idea.

@ntindle I think that's a different use of the term "agent" than how we're using it here, where it's just a UX paradigm for an extension that can execute a chat query. That might continue to be a point of confusion as people work more on AI agents that plan and use tools to accomplish a task in multiple steps.

@InTheCloudDan Not a good example, sorry, I'll try to add one to the API sample this month. The API might need a little more polish.

@pelikhan The current concept is that those options could be used differently by different chat providers. The copilot chat provider takes a numeric option n.

Re: MappedEditsProvider- I think this is sort of in an experimental state, there is one that is implemented by the Copilot Chat extension and just tries to fix the indentation of pasted codeblocks based on the indentation in ChatAgentUsedContext.

[ntindle]

How would you feel about calling it one of the following then sidekick, partner, assistant, or tool?

The name confusion I can see continuing

[bionicles]

@roblourens duh