Skip to content

copilot

Subscribe to all “copilot” posts via RSS or follow GitHub Changelog on Twitter to stay updated on everything we ship.

~ cd github-changelog
~/github-changelog|main git log main
showing all changes successfully

Since the initial beta release of the Copilot User Management API, we’ve heard feedback that obtaining the full set of Copilot seats and their associated activity status has been cumbersome. Many enterprise admins did not have the necessary “write” permissions and needed to iterate over multiple organizations’ data due to the lack of an enterprise endpoint.

With today’s update, we’ve added a centralized enterprise endpoint for listing Copilot seats and associated metadata across the enterprise. We have also updated the necessary scope to read:enterprise. Now, all enterprise admins can quickly gather their enterprise’s Copilot seats details with just one API request!

Likewise, for existing, non-destructive endpoints on the User Management API, we have updated all minimum permission requirements to read from write.

Check out our updated documentation to learn more and try it out today! You can share your feedback with us in this discussion.

See more

GitHub Copilot Enterprise users in Visual Studio Code can now get answers from Copilot Chat enriched with context from Copilot knowledge bases and Bing search results.

To get started, make sure you’re running the latest release of the GitHub Copilot Chat extension for VS Code, and then check out the docs.

Access your Copilot knowledge bases

You can now access your knowledge bases from any Copilot Chat conversation in VS Code by typing @github #kb, selecting a knowledge base from the list, and then entering your question.

Copilot will respond, using the Markdown documentation in your knowledge base as context for its answer. This allows Copilot Enterprise users to combine search results and internal documentation with editor context using existing chat variables like #file and #selection.

Search with the context of the web

GitHub Copilot can now search Bing within chat conversations in VS Code to answer questions and find information outside of its general knowledge or your codebase.

To get answers enriched with Bing search results, start your message with @github. Copilot will intelligently decide when to use Bing – or you can ask it to run a search by adding #web to your query. You can ask questions like @github What is the latest LTS version of Node.js?.

Bing search is only available if enabled by an administrator – for more details, see “Enabling GitHub Copilot Enterprise features”.

See more

GitHub Copilot Enterprise subscribers in Visual Studio can now use Copilot Chat to get answers enriched with context from their entire repository (not just open tabs!) and Bing search results.

To try out this functionality, install Visual Studio 17.11 Preview 2, and then check out the docs.

Get answers from across your entire codebase

Copilot Chat can now answer questions with understanding of your full repository, not just the tabs you have open. Index your repository on GitHub.com, and then ask a question mentioning @github. You can ask questions like @github Where is device detection implemented?.

Search with the context of the web

GitHub Copilot can now search Bing to find information outside of its general knowledge or your codebase. When you mention @github, Copilot will intelligently decide when to use Bing. You can ask questions like @github What are the breaking changes in Next.js v14?.

Bing search is only available if enabled by an administrator – for more details, see “Enabling GitHub Copilot Enterprise features”.

See more

We are excited to announce that compliance reports are now available for GitHub Copilot Business and Copilot Enterprise. Specifically, GitHub has published a SOC 2 Type I report for Copilot Business (including code completion in the IDE, and chat in the IDE, CLI, and Mobile). This Type 1 report demonstrates that Copilot Business has the controls in place necessary to protect the security of the service. We will include Copilot Business and Copilot Enterprise in our next SOC 2 Type 2 report coming in late 2024, covering April 1 to September 30, 2024.

Additionally, Copilot Business and Copilot Enterprise are now included in the scope of GitHub’s Information Security Management System, as reflected in our ISO 27001 certificate updated on May 9, 2024. This certification demonstrates that Copilot Business and Copilot Enterprise are developed and operated using the same security processes and standards as the rest of GitHub’s products.

Together, these reports reflect GitHub’s commitment to demonstrate our high bar for security and compliance to our customers. To learn more, please review our documentation on how to access compliance reports and certifications for your enterprise or for your organization.

See more

We’re excited to introduce a wave of updates this May 🌟 in GitHub Copilot Enterprise!

Copilot Chat in GitHub.com has leveled up 🔋. It can now summarize and answer questions about your repositories, releases, commits and more.

  • Learn about repositories: Copilot can answer questions about a repository or compare repositories based on its owner, description, stars & forks count, and various timestamps. To learn more, see “Asking exploratory questions about a repository” in the GitHub docs.
  • Try it yourself: Navigate to a repository on GitHub.com, and ask Copilot to Tell me about this repo
  • Ask about releases: Copilot can now tell you about a release or retrieve the most recent release in a repository. Ask Copilot to summarize the latest release from your favorite open source projects and use Copilot to dig into issues or changes tied to the release notes. To learn more, see “Asking exploratory questions about a repository” in the GitHub docs.

  • Try it yourself: Navigate to an open source repository on GitHub.com, and ask Copilot to Tell me about the latest release

  • Understand changes happening in your codebase: Copilot can now list changes (commits) related to a pull request and dig into specific commits if you need to understand a change in detail. To learn more, see “Asking a question about a specific commit” in the GitHub docs.

  • Try it yourself: Navigate to a commit on GitHub.com, and ask Copilot to Summarize the changes in this commit

Don’t know where to begin? Copilot Chat on GitHub.com now makes suggestions when you open a new conversation based on where you are. Whether you’re summarizing issues, creating unit tests, or discovering what Copilot can do, Chat already knows your GitHub context and what you might be trying to achieve.

With these latest updates for Copilot Enterprise, it’s now easier for you to get up to speed on your repos, their releases and latest changes faster and more seamlessly. You can learn more in our docs.

See more

GitHub Copilot Extensions Limited Beta announcement

GitHub Copilot Extensions is now in Limited Public Beta. With extensions, you can now extend the capabilities of GitHub Copilot Chat and enhance the experience to perform a wide range of actions across third-party tools, services, and data. Create feature flags, check log errors, access API documentation, and even deploy your application to the cloud all through natural language.

We’re starting with GitHub Copilot Extensions from DataStax, Docker, Lambda Test, LaunchDarkly, McKinsey & Company, Octopus Deploy, Pangea, Pinecone, Product Science, ReadMe, Sentry, and Teams Toolkit on the GitHub Marketplace. In the coming weeks, all users will be able to access extensions from Stripe, MongoDB, and Microsoft (including Teams Toolkit and Office) on Visual Studio Marketplace for VS Code as well.

Sixteen GitHub Copilot Extensions from GitHub Copilot partners laid out as grid of tiles

Currently, access to Copilot Extensions is limited to a small set of users and we are planning to gradually roll out larger-scale access as we learn more & gather feedback. To learn more about Copilot Extensions and how to use them, check out the documentation and the GitHub Marketplace.

If you’re looking to build a GitHub Copilot Extension, there are several ways. Join the Copilot Partner Program to explore opportunities to bring your developer tools and services into the GitHub Copilot ecosystem and have extensions light up across all supported clients (VS Code, Visual Studio, and Github.com). If you’re looking to build a VS Code extension specifically, documentation is available here.

Questions or suggestions? Join the conversation in the community discussion.

See more

We’ve updated how we calculate Last Activity to give you better clarity and are pausing access to the Team endpoint in the Metrics API.

Updating the Last Activity calculation

Ahead of the GitHub Copilot Metrics API launch, we made an update to how we calculate Last Activity in order to provide more useful information for admins. Previously, this data point indicated the last time a user generated a Copilot authentication token, which happened automatically if the user’s editor was active. This did not mean the user was engaging with Copilot but rather, the extension was ensuring it could provide completions or chat access if needed.

To align this data point with actual usage, we updated our system to grab the most recent instance where the user deliberately engaged with the Copilot system. These actions include but are not limited to:
– Code completion suggestions show
– Chatting with Copilot Chat in IDEs
– Creating or updating a knowledge base
– Creating a pull request summary
– Interacting with Copilot on GitHub.com

As part of this update, we also needed to perform system cleanup on the vast amount of previous token generated events that were no longer relevant to providing this data point. Some data was erroneously removed but has since been restored.

The Last Activity date should be consistent across the CSV generated via Get Report in Copilot Access settings as well as through the Seats Management API.

Pausing access to Team slicing in the GitHub Copilot Metrics API.

Based on trends in feedback, the product team has learned that the Teams route of the Metrics API returns data that is not meeting the goals of our intended customer experience. In light, they have made the decision to temporarily pull the Teams route from production as of May 9th, 2024. During this time, the team will implement a collection of fixes intended to improve end users’ data experience and plan to re-enable the route by the end of June, at latest.

We understand this may be disappointing but the team is working to restore access as soon as possible. You can provide feedback and follow along for updates via this Discussion.

See more

GitHub Copilot Enterprise banner

Another month means more exciting updates to GitHub Copilot Enterprise! 📆 Check out what’s new below:

  • Ask Copilot Chat in GitHub.com to summarize and answer questions about specific issues: Copilot can read an issue and answer questions based on its title, author, status, body, linked pull requests, comments, and timestamps. To learn more, see “Asking a question about a specific issue” in the GitHub Docs.
    • Try it yourself: Navigate to an issue on GitHub.com, and ask Copilot to Summarize this issue
  • Stop Copilot Chat in GitHub.com mid-response with the “Stop” button: If your question wasn’t quite right, you’ve already got your answer, or Copilot isn’t heading in the right direction, you can now stop Copilot mid-response with the “Stop” button, like you can in your IDE.

Got feedback on any of these updates or Copilot Enterprise more generally? Join the discussion within GitHub Community.

See more

We’re excited to announce the public beta of the GitHub Copilot Metrics API, available to all customers of GitHub Copilot Business and GitHub Copilot Enterprise starting today.

The GitHub Copilot Metrics API is designed to supply you with information about Copilot’s usage within your organizations. The data from the API is intended to be consumed and combined with your organization’s own data to create greater visibility into how Copilot fits into the bigger picture of your software development cycle.

What functionality will be included in the Public Beta?

  • Historical data will be automatically loaded, giving you the ability to overlay data with any previous sources from day one.
  • The endpoint will supply data for the previous 28 days of usage history, on a rolling basis.

  • Data is summarized by day, and is refreshed at day end.

  • Date ranges and pagination are now available.

  • This iteration of the GitHub Copilot Metrics API is focused on serving metrics for Copilot Chat and code completions that take place in the IDE.

  • Code completion metrics: Lines of Code Suggested, Lines of Code Accepted, Number of Suggestions, Number of Acceptances, and Active Users with slices on language, and IDE.

  • Copilot Chat metrics: Number of Chats, Chat Suggestions Accepted, and Active Users. The endpoint does not currently feature slices on language or IDE for Chat metrics.

  • Team-level aggregates for GitHub teams with five or more members are also available.

Documentation and Resources

To help you get started, we have prepared comprehensive documentation and resources:

  • API Documentation: Explore the detailed API documentation, including metrics definitions here.
  • Visualization: You can find an open source tool for consuming and visualizing data from the endpoint here.

  • Metrics Export: Generate a flattened CSV from the endpoint using GitHub Actions here.

  • Learning Pathway: You can find an extended article on measuring the impact of GitHub Copilot here.

Participate in the Public Beta!

Your feedback during this beta phase is invaluable to us. We encourage you to share your experiences, which will be instrumental in refining and enhancing the API as we look toward the future.

Stay tuned for updates and enhancements throughout the beta period. We’re committed to delivering a robust and feature-rich API that meets your needs and expectations.**

See more

GitHub Copilot Enterprise banner

It’s been a little over a month since GitHub Copilot Enterprise became generally available. Check out what’s new below!

Enhanced contextual understanding and more relevant suggestions in GitHub.com

Copilot Chat in GitHub.com now uses faster and smarter embedding models to power content retrieval, giving Copilot higher quality and more relevant context when searching code and knowledge bases.

Copilot Chat in GitHub.com now knows about the programming languages used in the repository you’re looking at: Copilot could sometimes give answers based on a programming language not used by your project. Copilot now knows what programming languages a repository uses, so it can give code examples more tailored to your context.

Faster help with understanding pull request changes

It’s now easier to ask Copilot about the changed files in a diff: From the files changed view, you can now pick the files you’re most interested in asking Copilot about.

GitHub Copilot in Pull Request files changed view

You can also now ask Copilot about specific lines in a diff more easily by clicking on the Copilot icon when you hover on a line of code.

GitHub Copilot icon when hovering on a line in a diff

Usability improvements

A big thank you to all of our customers for the great feedback you’ve been providing. We’ve made a whole bunch of small fixes, including:

You can now start typing your next question to Copilot while the current response is still generating: Previously you had to wait for Copilot’s message to complete generating before a follow-up question could be composed.

Keyboard up/down arrows can now be used to cycle through past messages: Perhaps you want to ask a similar question from earlier in the conversation history? Hitting the up key on your keyboard will now enable you to cycle through previous messages.

Copilot Chat in GitHub.com now has better support for Japanese and Chinese characters: Previously the message could be submitted to Copilot after the IME conversion selection but before the user was ready to send the message to Copilot.

See more

GitHub Copilot in the CLI banner demonstrating "ghcs" alias for supporting command execution

GitHub Copilot in the CLI is now generally available

We are excited to announce Copilot in the CLI is now generally available (GA) for all our Copilot Individual, Business, and Enterprise customers.

Copilot in the CLI allows users to access the power of GitHub Copilot to get command suggestions and explanations without leaving the terminal. Starting today, developers can also use GitHub Copilot to execute suggested commands based on feedback shared during the public beta.

GitHub Copilot in the CLI has also gained a couple of helper aliases for Bash, PowerShell, and Zsh. The new gh copilot alias command generates shell-specific configuration for ghcs and ghce aliases. These aliases use fewer keystrokes to jump into the gh copilot experience. Additionally, the new ghcs alias streamlines the process for executing commands suggested while making them available for later reuse!

How to get started?

If you were already using Public Beta:

  • Update the extension to v1.0.0 by running gh extension upgrade gh-copilot.

If you haven’t enabled Copilot in the CLI yet or coming from the GitHub Next technical preview

  • Copilot Individual users: You automatically have access to the Copilot in the CLI.
  • Copilot Business and Enterprise users: Your organization admins will need to grant you access to Copilot in the CLI.

After receiving access to Copilot in the CLI, consult our guide on how to install the tool and get started.

How to give us your feedback?

We are dedicated to continuous improvement and innovation. Your feedback remains a crucial part of our development process, and we look forward to hearing more about your experiences with GitHub Copilot in the CLI. Please use our public repository to provide feedback or ideas on how to improve the product.

See more

GitHub Copilot Chat in JetBrains IDEs is now generally available

Following our Private Beta, we are thrilled to announce Copilot Chat in JetBrains IDEs is now generally available (GA) for all our Copilot Individual, Business, and Enterprise customers.

Driven by GPT-4, GitHub Copilot Chat provides instant guidance directly within various JetBrains IDEs, such as PyCharm, IntelliJ IDEA, WebStorm, Rider, and more. This contextually-aware tool tailors suggestions to your specific coding tasks and even allows explicitly adding files for reference. It empowers developers to innovate efficiently by assisting with complex concepts, code explanations, unit testing, and many more use cases, all while effortlessly adjusting to your preferred language style.

How to get started?

If you were already using Private Beta:
– No further action is required. You can continue using the chat feature as usual.

If you haven’t enabled Chat and want to use GitHub Copilot Chat in JetBrains IDEs

  • Copilot Individual users: You automatically have access to the chat within JetBrains IDEs.
  • Copilot Business and Enterprise users: Your organization admins will need to grant you access to Copilot chat in IDEs. Once you have access, please consult our getting started guide

How to give us your feedback?

We are dedicated to continuous improvement and innovation. Your feedback remains a crucial part of our development process, and we look forward to hearing more about your experiences with GitHub Copilot Chat for JetBrains IDEs. Please use this link to share your feedback or ideas on how to improve the product.

Join the discussion within GitHub Community.

See more

⏫ Copilot Code Completion model updated with more improvements

We’re excited to announce a new update to the model powering Copilot Code Completion across all IDEs! This update includes improved instruction following and performance improvement for our users. Here are the details:

  • Improved instruction following: Copilot can better understand and follow instructions given by the user. This means that Copilot is now better at generating code that matches the user’s intent and requirements.
  • Performance improvement: Finally, this model update includes a performance improvement for Copilot users. While this may not be noticeable in all cases, it can help make Copilot even faster and more efficient for certain tasks.
See more

GitHub Copilot Enterprise is now generally available

GitHub Copilot Enterprise, our most advanced AI offering to date, is now generally available. With GitHub Copilot Enterprise, you can:

  • Gain a deeper understanding of your organization’s unique codebase: Copilot Chat in GitHub.com understands your code and streamlines code navigation and comprehension for developers.
  • Quickly access organizational knowledge and best practices: By letting developers attach knowledge bases (formerly known as docsets) to conversations, Copilot Chat in GitHub.com can answer questions based on your Markdown documentation stored on GitHub.
  • Review pull requests faster: With pull request summaries generated by GitHub Copilot and the ability to chat about changes in a pull request, reviewers can get up to speed on a pull request quickly and spend more time providing valuable feedback.

Following on from our limited public beta, we are bringing the following improvements to GitHub Copilot Enterprise today to make Copilot even smarter:

  • GitHub Copilot can now search Bing within chat conversations in GitHub.com to answer questions and find information outside of its general knowledge or your codebase (public beta).
  • You can now access your knowledge bases (formerly known as docsets) from any Copilot Chat conversation in GitHub.com with the “Attach knowledge” button. Organization owners can create knowledge bases from an organization’s settings.
  • GitHub Copilot knows about code as you browse, so you no longer have to be explicit about exactly what file, symbol or snippet you want to chat about.

Example conversation demonstrating how GitHub Copilot can access the code you are currently looking at

  • GitHub Copilot generates pull request summaries that are now more structured, with a “Summary” section that gives a high-level overview, and an “Outline” section that walks through the code.
  • GitHub Copilot can now analyze and explain any pull request diff, making it easier for pull request reviewers to understand changes and share great feedback.

Example conversation demonstrating how GitHub Copilot can explain and improve pull request diffs

Ready to give Copilot Chat in GitHub.com a try? Here are some suggested prompts to get you started:

  • Ask a question about recent events to trigger a Bing search: What updates were there in Node.js v20?
  • Open GitHub Copilot Chat on a repository and ask a question about the repository: Where is the turnOn function defined?
  • Open a file on GitHub.com and ask a question about that file: Draft unit test cases for each of the functions in the file I’m currently viewing
See more

We are excited to announce the GA release of Copilot in GitHub Support, a faster way to find answers to your GitHub-related questions! Copilot in GitHub Support is an AI-powered assistant that answers questions based on our official GitHub documentation.
It will help you get instant answers to some of your basic questions without needing to create a support ticket.

This tool is part of our ongoing efforts to make GitHub the best place for all developers to collaborate, innovate, and ship great software. We believe that Copilot in GitHub Support will enhance your experience and productivity.

We look forward to hearing from you and learning from your feedback. Try out Copilot in GitHub Support today!

See more

We have introduced two new powerful features to the latest Visual Studio Copilot Chat extension: slash commands (/) that allow you to direct Copilot to perform specific tasks, and context Variables (#) that allow you to specify a file for Copilot to focus its answer on. These features are available on the latest Chat extension that is compatible with Visual Studio 2022 version 17.8 and higher.

Slash Commands

Slash commands are special commands that you can use in chat to receive targeted assistance, including explanations, documentation, test creation, and various other forms of support related to your code. For example, you can use:

  • /doc to add a documentation comment
  • /explain to explain the code
  • /fix to propose a fix for the problems in the selected code
  • /generate to generate code to answer your question
  • /help to get help with Copilot Chat
  • /optimize to analyze and improve the running time of the selected code
  • /tests to create unit tests for the selected code

VS Code Slash Commands

Context Variables

The context variables feature enables you to add files from your solution into your questions using the # symbol. By referencing a file in this way, you allow Copilot to access the content of the file and provide more targeted answers about it. For example, you can ask “How does the #file:’Main.cs’ file work?” or “What is the purpose of the #file:’Calculator.cs’ file?” and get relevant answers from Copilot Chat. You can add multiple files to one question.

VS Code Context Variables

Besides these main features, you can also explore our other exciting new preview features

Join the discussion within GitHub Community.

See more

🌐 Upcoming deprecation of Copilot Chat API endpoints

Note: If you are using the latest version of the Copilot extension for Visual Studio or VS Code or you are using the Copilot plugin for JetBrains IDEs, you will not be impacted by this change.

As we announced in September, we updated the API service endpoints used by Copilot Chat. On February 1, 2024, we will deprecate the Copilot Chat API endpoints currently being routed through https://copilot-proxy.githubusercontent.com. Instead, these requests will go through https://api.githubcopilot.com. Versions 0.8.0 and later of the Copilot Chat extension for VS Code and versions 0.1.1817.27579 and later of the Copilot Chat extension for Visual Studio already route chat traffic through https://api.githubcopilot.com. All versions of the Copilot plugin for JetBrains IDEs already route chat traffic through https://api.githubcopilot.com.

To ensure Copilot Chat continues working from February 1, 2024, please update to the most recent version of the Copilot extension and ensure your firewall and network settings allow communication to https://api.githubcopilot.com.

⏫ Update on the Copilot Enterprise Waitlist

On January 19, 2024, we will close the Copilot Enterprise waitlist in anticipation of the general availability release of Copilot Enterprise.

Join the discussion within GitHub Community.

See more

Following our previous communication dated November 8, 2023, regarding the temporary rollback of the Copilot content exclusions feature, we are pleased to announce the re-deployment of this feature with significant enhancements. The rollout will be progressive during the next 10 days as we monitor the behaviour.

With Content Exclusion, GitHub Copilot Business customers will be able to prevent specified files or repositories from being used to inform code completion suggestions made by GitHub Copilot. GitHub Copilot will not be available in excluded files. Organization administrators or repository owners can choose which files or repositories are excluded. Learn more.

Overview of the Issue

Our team observed a critical issue where clients were incorrectly blocked from using Copilot due to the initial implementation of content exclusions. This was primarily caused by errors in fetching content exclusion policies from the client, leading to a temporary suspension of the feature.

Actions Undertaken

In response to this, our engineering team undertook a comprehensive review and rectification process. The issues identified in the client's code were addressed, and additional verifications were implemented on both server and client sides to prevent recurrence.

New Enhancements in the Re-deployed Feature

  • Performance Update: We have optimized the performance of the content exclusions feature, ensuring minimal impact on the user experience.
  • Extended Coverage: The feature now supports all our official Integrated Development Environments: Visual Studio, JetBrains IDEs, Visual Studio Code, and Vim/Neovim.

Current Status

  • Users with pre-existing content exclusion configurations will experience no change.
  • New and returning users can now utilize the enhanced feature across all supported IDEs.

Next Steps

We are closely monitoring the performance and user feedback post-deployment. The support for Copilot Chat is also in progress and will be part of the General Availability.

Join the Discussion

We value your feedback and encourage you to participate in the discussion within the GitHub Community.

See more

The new year brings new features and improvements for the Copilot Enterprise! 🎆 These changes are focused on streamlined onboarding and ease of use.

As a reminder, Copilot Enterprise is currently in limited public beta. Enterprises can request access by signing up to the waitlist.

Semantic search can be enabled on any repository

Developers in an enterprise with access to Copilot Enterprise can now enable semantic search on a repository through the click of a button. Once a repository is indexed, Copilot has a much improved understanding of the code base in that repository and can answer questions via Copilot Chat in GitHub.com.

Create docsets to access your company’s critical knowledge

Organizations with documentation hosted in GitHub repos and written in Markdown (.md, .mdx) can now create “docsets” and enable developers in those organizations to access that critical knowledge via Copilot Chat in GitHub.com.

To get started, admins can create a docset, including the repositories that contain Markdown documentation.

Members of the corresponding organization can start to ask questions about the documentation by selecting the docset from Copilot’s “New conversation” UI in GitHub.com.

An organization can have multiple docsets – so, for example, an admin could create a docset for each team with the repositories that are relevant to them.

Introducing Copilot chat for pull request diffs

Developers are now be able to ask Copilot Chat questions about diffs on GitHub.com. To see this in action, simply navigate to a diff and use one of the following two entry points:

  1. Select some of the lines in the diff, and click on the icon on the right. You can click “Explain” to ask Copilot to explain those lines.
  2. You can also ask Copilot to chat about an entire file in the diff by clicking on the three dots at the top-right of the file in the diff. Click on “Ask Copilot about this diff” to start chatting about it.

Improved onboarding and discoverability

  • Enterprise admins have now access to improved onboarding as they enable Copilot Enterprise within their enterprise.
  • GitHub Copilot on GitHub.com can now be accessed via the search bar.
See more

This month, we made some big improvements to GitHub Copilot! Copilot Chat is now powered by GPT-4 and we updated the model used to detect off-topic chat queries. In VS Code, we are announcing the public beta of code referencing. We also introduced “agents” and the ability to generate commit messages with Copilot. In addition, we improved the context for explaining code and updated the Copilot menu UI. In JetBrains IDEs, we introduced partial acceptance of code suggestions.

Copilot Chat is powered by GPT4

We upgraded the Copilot Chat experience, bringing more accurate and useful code suggestions with OpenAI‘s GPT4 model.

Offtopic model improvements for Copilot Chat

As part of our safety featuresweve improved our off-topic model to detect chat queries which do not relate to programming. This should result in significantly fewer filtered responses.

Code referencing in VS Code is now in Public Beta

In August, we announced the Private Beta of code referencing in VS CodeThis feature searches across billions of files on public GitHub repositories for code that matches a Copilot suggestionSince then, we’ve heard your feedback, and we’re shipping with a new and redesigned experience. One of the top points of feedback was that the original flow resulted in too many notifications. To fix this, if theres a matchusers will find its information displayed in the Copilot console log, including where the match occurred, any applicable licensesand a deep link to learn more. If you are interested in code references, you can refer to the window, otherwise, it won’t be in your way.

The deep link will now take you to a navigable page on GitHub.com to browse examples of the code match and their repository licensesand see how many repositories — including ones without licenses — that code appears in, as well as links to those repositories.

Learn more about Copilot code referencing and let us know your thoughts in the GitHub Community!

Introducing “agents” in Copilot Chat in VS Code

We have introduced a new capability called “agents” to enhance your interaction with Copilot Chat. Agents are like specialized experts who can assist you with specific tasks. You can mention them in the chat using the @ symbol. Currently, there are two agents available:

  • @workspace: This agent has knowledge about the code in your workspace and can help you navigate it by finding relevant files or classes. The @workspace agent uses a meta prompt to determine what information to collect from the workspace to help answer your question.
  • @vscode: This agent is knowledgeable about commands and features in the VS Code editor itself, and can assist you in using them.

Each agent also supports slash commandsThe slash commands you may have used before should now be used with an agent. For example, /explain is now @workspace /explain.

Read more in the VS Code release notes.

Improved explanation context in Copilot Chat in VS Code

You can ask Copilot Chat to explain a code selection in your active editor either through the @workspace /explain command or through the “Explain with Copilot” action in the context menu. Copilot Chat has now integrated implementations of referenced symbolssuch as functions and classes, which leads to explanations that are more precise and useful. This works best across files when you have an extension contributing language services installed for one of the following languages: TypeScript/JavaScript, Python, Java, C#, C++, Go, or Ruby.

Commit message generation using Copilot in VS Code

Copilot can now generate commit messages based on the pending changes using the new “sparkle” action in the Source Control input box.

Updated Copilot menu in VS Code

Our Copilot menu in VS Code is now more visible and aligned with our design for JetBrains IDEs. It is now easier to understand the current status of Copilot, access the various settings or documentation.

The new menu is displayed when clicking on the Copilot icon in the lower right corner in the statusbar of VS Code.

JetBrains partial acceptance for code suggestions

The Copilot extension for JetBrains IDEs has leveled up! You now have the flexibility to incorporate code suggestions piece by piece, whether that’s word-by-word or line-by-line. Feel free to customize these shortcuts as you preferHappy coding!

We welcome your feedback on Copilot! Please join the discussion in the GitHub Community.

See more