Use Copilot Chat in VS Code

With Copilot Chat in Visual Studio Code, ask questions via chat to get code suggestions, increase your code understanding, and even configure your editor. Instead of searching for answers in documentation or online forums, ask Copilot directly in VS Code and immediately apply the suggestions to your codebase.

Instead of using chat to get suggestions, Copilot can also directly make edits across multiple files in your project. In this case, you might consider using Copilot Edits. You can easily move an existing chat conversation to Copilot Edits.

Access Copilot Chat in VS Code

You can submit prompts to Copilot in VS Code in several ways, depending on your workflow.

• Chat view: have an AI assistant on the side to help with your questions and to provide code suggestions (⌃⌘I (Windows, Linux Ctrl+Alt+I)).
• Inline Chat: start an inline chat conversation directly from the editor or integrated terminal to get suggestions in-place (⌘I (Windows, Linux Ctrl+I)).
• Quick Chat: ask a quick question and get back into what you're doing (⇧⌥⌘L (Windows, Linux Ctrl+Shift+Alt+L)).

To access the chat experiences, use the corresponding keyboard shortcuts or use the Copilot menu in the VS Code title bar.

Submit your first prompt

You can ask Copilot Chat to give code suggestions, increase your code understanding, set up debugging for your project, or help with configuring VS Code.

1. Open the Chat view with the (⌃⌘I (Windows, Linux Ctrl+Alt+I)) keyboard shortcut or select Open Chat in the Copilot menu in the title bar.

   If you want to use chat to make edits directly in the active editor, use Inline Chat instead (⌘I (Windows, Linux Ctrl+I)).

2. Enter your prompt in the chat input field or choose one of the prompt suggestions.

   Some example prompts:

   • Ask questions about coding and technology concepts ("What is a linked list?", "top 10 popular web frameworks")
   • Brainstorm ideas on how to best solve a coding problem ("How to add auth to my project?")
   • Explain a block of code ("@workspace /explain", "What does this code do?")
   • Propose code fixes ("@workspace /fix", "This method gives a FileNotFoundException")
   • Generate unit test cases or code documentation ("@workspace /tests", "@workspace /doc")
   • Ask about VS Code settings (@vscode how do I disable the minimap?)

   For more prompt examples, see the Copilot Chat Cookbook in the GitHub documentation.

3. Review the response from Copilot.

   The response may contain text, code blocks, buttons, links to code symbols, file trees, or other rich content. Get more information about how to apply code suggestions to your codebase.

   To see which resources Copilot used for the response, select the Used n resources dropdown in the chat response. You can help Copilot give more relevant answers by attaching the context to your chat prompt.

4. Optionally, ask follow-up questions to refine the response.

   As you keep the conversation going, Copilot maintains the history of your chat messages and responses.

   To start over with a new chat session, use the New Chat (+) button (⌃L (Windows, Linux Ctrl+L)) in the Chat view.

Change the AI model

Different Large Language Models (LLMs) are trained on different types of data and might have different capabilities and strengths. With Copilot, you can choose between different models to get the best results for your needs.

Use the model picker in the chat input field to change the model that Copilot uses for generating a response.

The list of available models might vary based on your Copilot subscription and might change over time. See the GitHub Copilot documentation for more information about the available language models.

Add context to your chat prompt

Copilot tries to determine the intent and scope of your question based on your natural language chat prompt. In the chat response, select the Used n resources dropdown to see which resources Copilot used to generate the response.

To help Copilot give you the best and most relevant answers, add context to your chat prompt. For example, attach specific files, specific code symbols, the current editor selection, and more. Get more details about adding context to your chat prompt.

Chat participants

Chat participants are like domain experts who have a specialty that they can help you with. You can invoke a chat participant by typing '@' in the chat input field, followed by the participant name. There are several built-in chat participants, and extensions can also contribute chat participants.

To list all installed chat participants, type @ in the chat input field.

Extension-contributed chat participants

You can install additional chat participants from either the Visual Studio Code Marketplace or from the GitHub Marketplace.

Chat participants contributed via a VS Code extension are client-side extensions that have full access to the VS Code extension API surface.

Chat participants contributed via a GitHub App do not run on your local machine and must explicitly request access to your local editor context. After you install a GitHub App that contributes a chat participant, the first time you @-mention the participant in VS Code, you are asked to authorize its access to your local editor context.

These are some examples of VS Code extensions that contribute a chat participant. Go to the Marketplace or use the integrated Extensions view (⇧⌘X (Windows, Linux Ctrl+Shift+X)) and search by tag chat-participant (tag:chat-participant).

Slash commands

Slash commands provide a shortcut to specific instructions to avoid that you have to write complex prompts. To use a slash command in your prompt, type the / character, followed by a command. Chat participants can contribute their own slash commands.

For example, @workspace /new Express app with pug and typescript is a shortcut for generating a new workspace and scaffold a new Express app in TypeScript that uses the Pug view engine.

Some common built-in slash commands are:

• /clear: start a new chat session
• /help: get help about using GitHub Copilot
• @workspace /explain (or /explain): explain how the selected code works
• @workspace /fix (or /fix): propose a fix for the problems in the selected code
• @workspace /new (or /new): scaffold code for a new workspace or new file

To list all available slash commands, type / in the chat input field.

Chat variables

Use chat variables to include specific context in your prompt. To use a chat variable, type # in the chat prompt box, followed by a chat variable. For example, #codebase to let Copilot find the relevant files to add as context, or #selection to add the current editor selection to your chat prompt.

Get more information about adding context to your chat prompt.

Inline Chat

To make edits directly in the editor, use Inline Chat to submit a prompt. Copilot provides code suggestions in-place with your code in the editor. If you have a block of code selected in the editor, Copilot scopes your question to that selection.

To bring up Editor Inline Chat:

• In any file, use the ⌘I (Windows, Linux Ctrl+I) keyboard shortcut.
• Alternatively, open a file and then select Editor Inline Chat from the Copilot menu in the title bar.

After receiving a code suggestion, you can accept (⌘Enter (Windows, Linux Ctrl+Enter)) or discard (Escape) the changes. If you're not happy with the suggestion, enter a new prompt and Copilot provides a new suggestion.

You're not limited to asking for code changes. Use Inline Chat to ask more exploratory questions that emerge as you work with your codebase. For example, use prompts such as Explain this piece of code, or How do I add functionality to do X?.

Chat view

The Chat view is a dedicated view that is useful to keep open while you work on your code, and where you can have multi-turn conversations with Copilot.

To open the Chat view:

• Use the ⌃⌘I (Windows, Linux Ctrl+Alt+I) keyboard shortcut.
• Alternatively, select Open Chat in the Copilot menu in the title bar.

By default, the Chat view is located in the Secondary Side Bar. The Secondary Side Bar is always positioned opposite the Primary Side Bar, so you can have the Chat view open at the same time as the Explorer, Source Control, or other views in the Primary Side Bar.

Apply a code block from chat

Chat responses could contain one or more code blocks. Depending on the language extension, the code block in the chat response might support IntelliSense, which enables you get information about methods and symbols by hovering over them, or to go to their definition.

To apply a code block to your codebase, hover over the code block and select the Apply in Editor button. Copilot tries to apply the proposed changes to your existing code.

Other actions that are available for code blocks are:

• Insert the code block at the current cursor position
• Copy the code block to the clipboard
• Insert the code block into the integrated terminal
• Insert the code block into a new file

If Copilot Chat detects that a code block contains a shell command, you can run it directly in the integrated terminal with Insert into Terminal (⌃⌥Enter (Windows, Linux Ctrl+Alt+Enter)). This option creates or opens the active terminal and inserts the command text, ready for you to run.

You can control the font for code blocks in chat with the following settings:

• chat.editor.fontFamily
• chat.editor.fontSize
• chat.editor.fontWeight
• chat.editor.lineHeight

Chat history

At any time, you can start a new chat session by using the New Chat button (⌃L (Windows, Linux Ctrl+L)) in the Chat view. This can be useful to ask Copilot about a different topic and avoid the previous context and history.

Copilot Chat maintains the history of your previous chat sessions, which you can access by using the Show Chats... button in the Chat view or by using the Chat: Show Chats... command in the Command Palette.

A Quick Pick shows the list of previous chats, order by most recent. You can select a chat to open it in the Chat view.

Within a chat session, you can remove a specific prompt and the corresponding response from the conversation history of that session. Hover over the prompt and select the x control. It might be useful to delete one or more prompts to get more relevant responses.

You can export all prompts and responses for a chat session in a JSON file with the Chat: Export Chat... command in the Command Palette.

Quick Chat

If you want to ask Copilot a quick question and don't want to start a full Chat view session or open Inline Chat in your editor, you can use the Quick Chat dropdown.

Press ⇧⌥⌘L (Windows, Linux Ctrl+Shift+Alt+L) on your keyboard to bring up Quick Chat. Alternatively, select Quick Chat in the Copilot menu in the title bar.

If you want to keep the conversation going, promote a Quick Chat conversation to a full Chat view session with the Open in Chat View button in the upper right of the dropdown.

Terminal Inline Chat

Similar to Inline Chat in the editor, you can bring up Copilot Inline Chat in the terminal to help you answer questions related to the terminal and shell commands.

The terminal Inline Chat uses the @terminal chat participant, which has context about the integrated terminal's shell and its contents. For example, you can ask questions such as "how to install npm packages", or "list the top 5 largest files in the src directory".

To start Inline Chat in the terminal, press the ⌘I (Windows, Linux Ctrl+I) keyboard shortcut while you're in the terminal.

Once a command is suggested, use Run (⌘Enter (Windows, Linux Ctrl+Enter)) to run the command in the terminal, or Insert (⌥Enter (Windows, Linux Alt+Enter)) to insert the command into the terminal.

Smart actions

For several common scenarios, you can use smart actions to get help from Copilot without having to write a prompt. Examples of these smart actions are for tasks, such as generating commit messages, generating documentation, fixing code, explaining code, or reviewing code changes.

These smart actions are available throughout the VS Code UI. For example, you can access Copilot smart actions from the editor context menu or through Quick Fix actions.

In the editor, you can access smart actions by selecting a block of code, right-clicking, and then choosing Copilot.

The most powerful smart action is the Fix action that helps you correct coding issues. Select the sparkle icon in the editor, and then choose Fix using Copilot. There is a corresponding /fix slash command.

Similarly, there's a Copilot > Generate Docs smart action (/doc slash command) to generate documentation for your code.

Use voice interactions

With the voice control capabilities in VS Code, provided by the VS Code Speech extension, you can initiate a chat conversation by using your voice:

• Use your voice to dictate your chat prompt
• Use the "Hey Code" voice command to start a voice session with Copilot Chat
• Accelerate voice input for chat by using the "hold to speak" mode

Learn more about how to use voice interactions in VS Code.

Privacy and transparency

To enable more workspace search features for private repositories, we require additional permissions. If we detect that we don't have these permissions already, we will ask for them at startup. Once granted, we'll securely store the session for the future.

Learn more about security, privacy, and transparency in the GitHub Copilot Trust Center.

Frequently asked questions

How do I choose between Copilot Edits, Inline Chat, Chat view, and Quick Chat?

The following table provides a comparison of the capabilities of each interface.

* code blocks are included in the chat conversation and need to be applied to the right file manually

Additional resources

You can read more about GitHub Copilot and how to use it in VS Code in the GitHub Copilot documentation.

Or check out the VS Code Copilot Series on YouTube, where you can find more introductory content and programming-specific videos for using Copilot with Python, C#, Java, PowerShell, C++, and more.

Next steps

• Get started with the introductory Copilot Chat tutorial.

• Make edits across multiple files with Copilot Edits.