We’ve enhanced the fullscreen Copilot chat experience on github.com/copilot with a streamlined UI and an even easier way to handle context:
Check out the updates, and let us know what you think using the in-product feedback option.
Network requests for Copilot are routed based on a user’s Copilot subscription. Requests for Copilot Individual, Copilot Business, and Copilot Enterprise users now route through different endpoints.
This change enables Copilot Business and Copilot Enterprise customers to make sure all Copilot users on their networks are accessing Copilot through their Copilot Business or Copilot Enterprise subscription, and that all Copilot user data is handled according to the terms of their Copilot Business or Copilot Enterprise agreement. In essence, customers will be able to use their network firewall to explicitly allow access to Copilot Business or Copilot Enterprise, and/or block access to Copilot Individual.
Today we enabled enforcement of the user’s subscription on the new endpoints, ensuring only Copilot Business users can connect to Copilot Business endpoints and only Copilot Enterprise users can connect to Copilot Enterprise endpoints.
Announced at GitHub Universe 2024, Claude 3.5 Sonnet is now available to all GitHub Copilot customers. To see Claude 3.5 Sonnet in action in Visual Studio Code check out the video below.
You can start using the new Claude 3.5 Sonnet today via the model selector in Copilot Chat in VS Code and immersive chat on GitHub.com.
Copilot Business and Enterprise organization administrators will need to grant access to Claude 3.5 Sonnet in Copilot via a new policy in Copilot settings. Once enabled, you will see the model selector in VS Code and chat on GitHub.com. You can confirm availability by checking individual Copilot settings and confirming the policy for Claude 3.5 Sonnet is set to enabled.
We’re excited to hear from you! Please use our Community Discussions to provide feedback and share tips with others.
For additional information, check out the docs on Claude 3.5 Sonnet in Copilot.
We’re excited to announce the GA release of the GitHub Copilot Metrics API, available to all customers of GitHub Copilot Business and GitHub Copilot Enterprise.
The GitHub Copilot Metrics API is designed to supply you with information about Copilot’s usage within your GitHub enterprise, organizations, and teams. 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. It offers visibility into utilization of individual Copilot features and the volume of daily active users.
The GA release of the Copilot Metrics API introduces a newly revised schema. To ensure that your existing reports are not interrupted, the Beta route will remain online through the end of the calendar year.
You can now access the power of GitHub Copilot to get command suggestions and explanations without leaving the terminal with Terminal Chat in Windows Terminal Canary. This is available for all Copilot Individual, Business, and Enterprise customers.
GitHub Copilot is available in Windows Terminal Canary. Consult the Terminal Chat documentation to learn how to connect Copilot and get started.
If you are a Copilot Business or Enterprise user
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 Windows Terminal. Please use the Windows Terminal repository to provide feedback or ideas on how to improve the product.
Join our dedicated Community Discussions to discuss this update and share tips with others.
GitHub Copilot Chat in VS Code, Visual Studio, and GitHub.com now supports web search, enabling you to easily chat about recent events, new developments, trends, and technologies. This feature is already available for Copilot Business and Copilot Enterprise.
To get started, first enable the “Copilot Access to Bing” policy in your Copilot Settings.
Then try it out with Copilot Chat by asking a question that would benefit from web search. Here are some examples:
What's the latest release of node.jsWhat are some recent articles about SAT tokens securing against vulnerabilities in Node?For more information, check out our documentation and join the discussion within the GitHub Community!
With Copilot code review in GitHub.com, you get fast, AI-powered feedback on your code, so you can start iterating while you wait for a human review.
Copilot code review on GitHub.com is launching in public preview today for Copilot Individual, Copilot Business and Copilot Enterprise subscribers. Sign up to the waitlist to request access.
You can request a review on your pull request by picking “Copilot” from the Reviewers menu. Administrators can configure automatic reviews for every pull request using repository rules.
Copilot will review your changes and attach its comments to specific lines of your code, including one-click fixes where possible.
You can jump from these suggestions into the new Copilot Workspace experience in the context of the pull request to refine and validate Copilot’s suggestions. Learn more in the changelog.
Copilot can also review your code in Visual Studio Code before you push; see the changelog for more details.
To learn more about GitHub Copilot Code review, head over to the docs. To ask questions or share feedback, head to our discussion on the GitHub Community.
Copilot Autofix for Dependabot is now available in private preview for TypeScript repositories.
This new feature combines the power of GitHub Copilot with Dependabot, making it easier than ever to automatically fix breaking changes introduced by dependency updates. With Copilot Autofix, you can save time and minimize disruptions by receiving AI-generated fixes to resolve breaking changes caused by dependency upgrades in Dependabot-authored pull requests.
Dependency updates can introduce breaking changes that lead to failing CI tests and deployment delays. Identifying the exact cause of these breaks and implementing the correct fix can require significant time and effort, making it challenging to stay on the most up-to-date and secure version of a dependency.
Dependabot can now leverage the power of Copilot Autofix to analyze dependency updates that fail CI tests and suggest fixes, all within the pull request. Copilot Autofix for Dependabot not only helps keep your dependencies up to date, but also keeps your CI green. Staying up-to-date on dependencies upgrades with breaking changes is now easier and faster than ever.
To sign up for the feature waitlist, fill out the form to express your interest. We’ll notify selected participants as we roll out the feature over the coming weeks.
This feature is available in private preview to GitHub Advanced Security customers on cloud deployments. Starting today, we support TypeScript repos with tests set up in GitHub Actions. As we continue to develop this feature, we will expand coverage for additional languages and testing requirements.
Please keep an eye on future changelogs for more updates as the feature moves to public preview and general availability.
To learn more, please join the waitlist or check out the latest GitHub feature previews.
To hear what others are saying and offer your own take, join the discussion in the GitHub Community.
Security campaigns with Copilot Autofix are now in public preview. Available as part of GitHub Advanced Security, security campaigns rapidly reduce your backlog of application security debt. By using Copilot Autofix to generate contextual explanations and code suggestions for up to 1,000 historical code scanning alerts at a time, security campaigns help developers and security teams collaborate to fix vulnerabilities with speed and confidence.
Code scanning detection engines such as GitHub’s CodeQL are incredibly effective at automatically notifying developers about potential security vulnerabilities in their code in the form of code scanning alerts. Most developers fix these vulnerabilities with the help of Copilot Autofix when they’re flagged pull requests. However, in situations where these alerts aren’t remediated in a timely manner, security debt can build up and pose a serious risk to deployed applications. Using security campaigns, security teams and developers can easily collaborate to remediate and eradicate security debt at scale, with the help of Copilot Autofix.
A security campaign on GitHub can contain a large number of code scanning alerts, prioritized by your security team to be fixed within a chosen timeframe. When a campaign is created, Copilot Autofix automatically suggests fixes for all supported alerts, and developers who are most familiar with the code are notified. From there, they can review the fixes, open pull requests, and remediate the security debt.
Security teams can monitor the progress of the campaign and track the number of alerts that have been fixed. Using security campaigns, security and developer teams work together with Copilot Autofix to remove security debt in targeted efforts aimed at maximizing impact by focusing on the alerts that matter.
Security campaigns are available for users of GitHub Advanced Security on GitHub Enterprise Cloud. For more information about security campaigns, see About security campaigns in the GitHub documentation.
If you have any feedback on security campaigns: join the discussion in the GitHub Community.
We are excited to announce that GitHub Copilot for Xcode is now available in public preview. This is a major milestone in our ongoing mission to make Copilot an essential tool for developers across a wide variety of platforms. Now, Apple developers can enjoy the same intelligent coding assistance, seamlessly integrated into their favorite IDE. With this public beta, Xcode users can boost productivity, speed up development, and enhance their overall coding experience using Copilot. We’re excited to bring the power of Copilot to even more developers, empowering them to innovate and build faster.
You need to have a Copilot license to get access to Copilot for Xcode. All Copilot individual, business, and enterprise users have access to the public beta. To install the extension, simply follow the steps outlined in our getting started guide.
To provide feedback or report issues, please open an issue on GitHub at https://github.com/github/CopilotForXcode/issues. If you’re experiencing a similar problem, please check existing issues and add a comment to share your experience or ask questions.
Connect with other developers, share tips, and discuss other updates to Copilot in our dedicated Copilot Community Discussions.
With GitHub Copilot code review in Visual Studio Code, you can now get fast, AI-powered feedback on your code as you write it, or request a review of all your changes before you push.
There are two ways to use Copilot code review in VS Code:
Copilot’s feedback shows up as comments in the editor, attached to lines of your code. Where possible, the comments include actionable code suggestions, which you can apply in one click.
To learn more about Copilot code review, head to the docs.
Copilot Autofix now supports fix suggestions for problems detected by ESLint, a partner code scanning tool. Autofixes are available both in pull requests and for historical alerts.
ESLint is the first partner tool supported by Copilot Autofix. Support for additional partner tools, such as JFrog SAST and Black Duck’s Polaris™ platform powered by Coverity®, will be announced by future changelogs when available. To opt out of fix suggestions for third-party tools, you can disable this feature from the code scanning settings page.
In order for Copilot Autofix to pick up ESLint alerts, you need to enable ESLint as a code scanning tool in the target repository. For reference, you can select an updated starter workflow when setting up a new GitHub Actions workflow in your repository. You can use both ESLint scanning and the CodeQL analysis in the same repository.
For more information, see: Responsible use of Copilot Autofix for code scanning. If you have feedback for Copilot Autofix for code scanning, please join the discussion here.
GitHub Copilot Extensions are now available in public preview for GitHub Mobile!
With Copilot Extensions, you can extend GitHub Copilot’s capabilities on the go with GitHub Mobile. Use extensions to query third-party tools or private data in natural language.
How to join the preview program:
• On iOS: Install TestFlight and follow the prompts to join the GitHub Mobile beta program.
• On Android: Become a beta tester on Google Play and follow the prompts to download the beta version of GitHub Mobile.
You can also build your own private extensions for internal use or publish extensions to the GitHub Marketplace. For more info, see our docs on building Copilot Extensions.
Notice: We have temporarily rolled back support for GitHub Copilot Extensions on JetBrains IDEs to perform maintenance. Extensions are not currently supported on JetBrains, but we’re working to restore access as soon as possible. Further updates will be posted to the GitHub Changelog.
Learn more about GitHub Mobile and share your feedback to help us improve.
OpenAI o1-preview and o1-mini are now available to all users in GitHub Copilot Chat in VS Code, Visual Studio, and on github.com/copilot.
OpenAI o1 is a new series of AI models equipped with advanced reasoning capabilities, trained to think through complex tasks using an internal thought process. During our exploration of o1-preview with GitHub Copilot, we found the models better understood code constraints and edge cases, producing more efficient and higher quality results.
Now, you can test these models for yourself. You can power GitHub Copilot Chat with o1-preview, o1-mini, or the default GPT-4o model. By switching models during a conversation, you can quickly move from explaining APIs or generating boilerplate code to designing complex algorithms or analyzing logic bugs.
With this preview, we’re excited to bring OpenAI’s latest advancements to you, whether you’re developing software with Copilot or building the next great LLM-based product. We can’t wait to see what you build!
Join the discussion within GitHub Community.
Code reviews and suggestions from colleagues, integrators, and AI agents like Copilot code review and Copilot autofix increase your code’s quality, but at times they can get overwhelming. You can now use Copilot Workspace directly in the context of your pull request to quickly refine, test, and incorporate code review feedback and suggestions from teammates and AI agents. Ship faster without compromising quality.
To get access, sign up for the waitlist here. This will also give you access to Copilot code review.
Using Copilot Workspace in your PRs, you can:
For more information see our documentation, or join the discussion within GitHub Community.