Changelog

Subscribe to all Changelog 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

GitHub’s Payment Card Industry Data Security Standard (PCI DSS) v4.0 service provider Attestation of Compliance (AoC) as well as the corresponding shared responsibility matrix has been completed. This report is the first time GitHub has provided a PCI DSS service provider report for our customers. This enables customers to meet their own PCI DSS compliance needs using GitHub as part of their development environment.

Going forward, GitHub intends to provide this attestation of compliance each year.

If you’re an Enterprise customer and need to obtain copies of GitHub’s AoC or Shared Responsibility Matrix, please reach out to your account manager.

See more

Performance Metrics for GitHub Actions are now generally available for repositories and organizations. Repository members can view workflow and job performance data including queue times and failure rates going back as far as one year. Organization members can also view this data aggregated across all repositories in their organization. These metrics are available on all GitHub Cloud plans.

In addition, usage and performance metrics aggregated at the Enterprise level are now available in public preview to Enterprise admins. This includes usage metrics (ex. jobs run and minutes used), as well as performance metrics (ex. job failure rates and queue times) across all repositories and organizations in an enterprise. These metrics can be found in the Enterprise UI under the “Insights” tab.

Screenshot of Enterprise Actions usage metrics in the Enterprise Admin UI

See more

Developers can now use Dependabot to automatically keep their uv dependencies up to date. For projects that use uv as a package manager, Dependabot version updates can now ensure dependencies stay current with the latest releases.

See more

GitHub Copilot now features instant semantic code search indexing, dramatically reducing the time it takes for Copilot to understand and reference your codebase.

What’s changed

Previously, when you wanted GitHub Copilot to reference your repository’s code in its responses, the semantic code search indexing process would take approximately five minutes to complete. With this update, indexing now completes in just a few seconds in most cases, though it may take up to 60 seconds. This means you can get contextually-aware Copilot assistance almost immediately after opening a repository.

Why this matters

Semantic Code Search is one of GitHub Copilot’s most powerful capabilities, enabling GitHub Copilot to:

  • Provide responses specific to your codebase’s architecture and patterns.
  • Reference existing functions, classes, and implementations in your repo.
  • Suggest code that aligns with your project’s style and conventions.
  • Answer questions about your codebase with accurate, context-aware information.

With instant semantic code search indexing, there’s virtually no waiting period between opening a repository and receiving codebase-aware AI assistance, making your development workflow more efficient and interruption-free.

How it works

Semantic code search indexing is automatically triggered when you open GitHub Copilot Chat on github.com. For VS Code users with the GitHub Copilot extension, you can also manually trigger indexing through the Copilot UI if needed.

Availability

This feature is available to all GitHub Copilot users across all tiers, including the free tier. There are no limits on how many repositories can be indexed.

Learn more

For detailed information about repository indexing for GitHub Copilot, check out our documentation.

Join the discussion within GitHub Community.

See more

GitHub Enterprise users will now see a horizontal navigation bar at the top of their enterprise account. This update is designed to improve the user experience by providing a consistent, intuitive navigation structure that mirrors the rest of the GitHub experience.

Screenshot of the new enterprise account navigation

These changes are expected to come to GitHub Enterprise Server customers in release version 3.17.

To learn more about enterprise accounts, read our documentation.

See more

The refreshed commit details page is now generally available!

This improved page lets you view and navigate the changes within a commit with improvements to filtering, commenting, and keyboard navigation.

Screen shot of the new commit details page that shows the metadata about the commit, a file tree showing the three files changed by the commit, diff snippets for each of the changed files, and a floating comment

What’s new 🎉

  • Comment counts in tree: Easily spot files with comments by seeing the number of comments directly in the file tree.
  • Floating comments: Code comments now float on top of the diff to improve readability of the diffs. Click the commenter’s avatar on the right side of the line to open.
  • Instantly switch views: Switch between unified and split views without waiting for the page to reload.
  • Keyboard navigation in diffs: You can now navigate around changed lines in the diff using the up and down keys on your keyboard. A new context menu also makes it easier to comment, copy, and select.
  • Filtering: You can filter changes by file name or extension. Also, the diffs for filtered out files are hidden to help reduce distractions.

Fixes and enhancements

Feedback during the public preview really helped us improve this page. Some of the more notable enhancements:

  • Compact line height: New user setting that controls the height of lines in the diff, which can help reduce scrolling and improve readability.
  • Submodule changes: The files changed when updating a submodule reference are now listed again.
  • Full commit message: The full commit message was previously hidden behind “Show More”, but is now fully shown.

Some of the more notable bugs that were addressed:

  • Fixed: The native browser context menu replaced by a custom menu when right-clicking on a diff.
  • Fixed: Tab indents not rendering correctly on some browsers.
  • Fixed: Missing “no newline at end of file” indicator.
  • Fixed: Performance issues on some browsers when interacting with the page.

See the full list of fixes and enhancements in the public preview feedback discussion.

Get help

To learn more about viewing commits, see About commits.

To give feedback, ask questions, or report a bug join us in the GitHub Community.

See more

Code completion in GitHub Copilot for Eclipse is now generally available

Code completion in GitHub Copilot for Eclipse is now generally available

GitHub Copilot’s code completion is now generally available for Eclipse! If you’re an Eclipse user, you can now leverage AI-powered suggestions directly within your IDE to write code faster and with greater ease.

Smarter coding with AI-powered assistance development

With GitHub Copilot in Eclipse, you’ll receive real-time code suggestions as you type, helping you complete functions, write boilerplate code, and even generate entire lines or blocks of code. Copilot’s AI-powered completions work seamlessly within the Eclipse environment, enabling a more efficient development workflow.

Key features of GitHub Copilot in Eclipse code completion

  • Code completions: Copilot is now seamlessly integrated into Eclipse, offering real-time, context-aware code suggestions as you type.
  • Multi-language support: GitHub Copilot for Eclipse supports a wide range of programming languages, including Java, Python, C++, and more. This enables developers across different tech stacks to leverage Copilot’s AI-powered assistance.
  • Content filtering: Copilot incorporates advanced filtering mechanisms to screen out harmful or inappropriate content, helping ensure professional and responsible code recommendations.
  • Free Tier: Get 2,000 code completions and 50 chat messages per month, simply by signing in with your personal GitHub account or by creating a new one.

Get started with GitHub Copilot in Eclipse

To try out Copilot in Eclipse, install the GitHub Copilot plugin from the Eclipse Marketplace and sign in with your GitHub account. Once enabled, you can start using AI-powered code suggestions right away.

Experience the future of AI-assisted development

GitHub Copilot is transforming the way developers write code by providing intelligent suggestions and automation. Whether you’re working on a small project or a large-scale application, Copilot helps streamline your workflow and boost productivity.

For more details, visit our GitHub Copilot documentation and start leveraging AI-driven coding assistance in Eclipse.

Feedback

We’re continuing to refine Copilot’s experience in Eclipse based on your feedback. Let us know what works well and where we can improve by sharing your thoughts in the GitHub Copilot feedback forum.

Ready to start coding faster in Eclipse? Install the GitHub Copilot plugin today and experience the future of AI-powered development!

See more

Alerts for non-provider patterns and Copilot-detected passwords are now categorized as generic instead of experimental. This change applies to alert filters and the secondary inbox in your alert list views.

Non-provider patterns and Copilot secret scanning were made generally available in October 2024, after careful iteration to reach the level of quality you’ve come to know and expect from provider-based patterns. These alerts are not considered experimental and should be remediated in accordance with your organization’s standard policies.

Detection for these secret types are available for repositories with a GitHub Advanced Security license. They can be enabled through your repository settings or organization and enterprise code security configurations.

Learn more about how to secure your repositories with our documentation on secret scanning.

See more

GitHub Copilot Chat for Eclipse now in public preview

GitHub Copilot Chat for Eclipse now in public preview

GitHub Copilot Chat for Eclipse is now in public preview! You can enable GitHub Copilot in Eclipse with any  GitHub account and experience both code completions and in-editor chat assistance today.

What’s new

  • Chat view: Ask Copilot for help with coding tasks directly in the chat view. Learn More.

  • Model Selector for Chat: GitHub Copilot allows you to change the model during a chat. Learn More.

  • Slash commands: Use quick commands, like /explain for code explanations.

  • Reference code: Scope chats to specific files for more relevant assistance.

  • Free access: Get 2,000 code completions and 50 chat messages per month for free, simply by signing in with your GitHub account or by creating a new one.

Try it out

To access GitHub Copilot Chat for Eclipse, you’ll need a Copilot license.

Follow the steps outlined in the Getting Started guide.

Feedback

Your feedback drives improvements. Let us know what you think using the in-product feedback option, or share your thoughts with the GitHub Community.
Join us on this journey as we continue to enhance GitHub Copilot for Eclipse and deliver a smoother developer workflow!

See more

GitHub Copilot for Xcode Chat is now generally available

GitHub Copilot for Xcode Chat is now generally available

GitHub Copilot Chat is now generally available for Xcode! If you’re an Xcode user, you can now take advantage of AI-powered assistance with both code completions and in-editor chat assistance today.

AI-powered chat for coding assistance

With GitHub Copilot Chat in Xcode, you can ask questions, get explanations for code, receive debugging help, and even generate suggestions for complex implementations. This interactive experience allows developers to work more efficiently without leaving their coding environment.

Key features of GitHub Copilot for Xcode Chat

  • Chat view: Ask Copilot for help with coding tasks directly in the chat view.

  • Model Selector for Chat: GitHub Copilot allows you to change the model during a chat.

  • Slash commands: Use quick commands, like /releaseNotes for the latest update information.

  • Reference code: Scope chats to specific files for more relevant assistance.

  • Multiple conversations: Maintain different threads, each with their own context.

  • Extended version support: Currently supported the macOS version from macOS 12.0 to macOS 15.0.

  • Free access: Get 2,000 code completions and 50 chat messages per month for free, simply by signing in with your GitHub account or by creating a new one.

Get started with GitHub Copilot in Xcode

To try out Copilot Chat in Xcode, install GitHub Copilot for Xcode and sign in with your GitHub account. Once enabled, you can start interacting with Copilot Chat to receive intelligent coding assistance instantly.

Experience the future of AI-assisted development

GitHub Copilot is redefining software development by providing AI-driven guidance, improving code quality, and speeding up problem-solving. Whether you’re working on an iOS app or macOS software, Copilot Chat helps you stay focused and productive.

For more details, visit our GitHub Copilot documentation and start leveraging AI-driven coding assistance in Xcode. 

Feedback

We’re continuously improving Copilot Chat in Xcode based on user feedback. Let us know how it’s working for you and share your suggestions in the GitHub Copilot feedback forum.

Ready to enhance your development workflow? Try GitHub Copilot Chat in Xcode today and experience the future of AI-assisted coding!

See more

CodeQL is the static analysis engine behind GitHub code scanning, which finds and remediates security issues in your code. We’ve recently released CodeQL 2.20.6, which brings support for a new version of Java and a variety of other improvements that improve the accuracy of your code scanning results:

Java

  • CodeQL now supports Java version 24
  • We’ve improved the accuracy of the (java/xss) query when javax.servlet.http.HttpServletResponse is used without an exploitable content type

JavaScript / TypeScript

  • We’ve added support for the response threat model, which can be enabled with advanced setup. When enabled, the response data coming back from an outgoing HTTP request is considered a tainted source.
  • We’ve improved the precision of data flow through arrays and call resolution logic, both resulting in improved analysis results

C/C++

  • We’ve improved the accuracy of the cpp/static-buffer-overflow query, resulting in improved results

C#

  • We’ve improved the precision of the cs/call-to-object-tostring query, resulting in improved analysis results

GitHub Actions (Public Preview)

  • We’ve removed the query actions/unversioned-immutable-action from the public suite of queries, which will close any alerts triggered from it

For a full list of changes, please refer to the complete changelog for version 2.20.6. Every new version of CodeQL is automatically deployed to users of GitHub code scanning on GitHub.com. The new functionality in CodeQL 2.20.6 will also be included in GitHub Enterprise Server (GHES) version 3.17. If you use an older version of GHES, you can manually upgrade your CodeQL version.

See more

GitHub Enterprise Server 3.16 enhances deployment efficiency, monitoring capabilities, code security, and policy management. Here are a few highlights in the 3.16 release:

  • The reliability, observability, and efficiency of ghe-config-apply have been improved. As a result, you may experience reduced downtime when ghe-config-apply is run.

  • The monitor dashboard has been optimized with concise, actionable metrics, providing a quick overview of the appliance’s operational health. For more details, see the monitor dashboard.

  • When reviewing code security configurations, you can now filter repositories more easily with new options that sort by the status of specific GHAS features. For more details, see new advanced filters for code security configurations.

  • You can now apply code security configurations to archived repositories, simplifying rollouts and ensuring features like Dependabot, code scanning, and secret scanning are automatically reapplied if a repository is unarchived. Additionally, you can now create and manage code security settings at the enterprise level, reducing repetitive setup at the organization level. For more details, see enterprise-level code security configurations.

  • Monitor prevention metrics alongside detection and remediation metrics for Dependabot and GitHub Advanced Security features, including secret scanning and code scanning. This expanded visibility is now available in the enhanced security overview dashboard at both the organization and enterprise levels. For more information, see enhanced security overview dashboard.

  • Organization owners can now allow their users to set custom properties during repository creation. This ensures appropriate rules are enforced from the moment of creation and improves discoverability of new repositories. For more information, see custom properties.

  • Organization owners can now configure policies to restrict the usage of deploy keys across all the repositories of your organizations, giving you more control and greater security over your deploy keys. For more information, see enforcing a policy for deploy keys.

To learn more about GHES 3.16, check out the release notes or download it now. If you have any issues upgrading to version 3.16 or experience any issues using these new features, please contact our support team.

Join the community discussion to share your feedback and ask questions.

See more

You can now use Quick Action Tasks in the GitHub Models playground . This is a new feature that streamlines your experimentation process by helping you choose faster or more cost-effective models, and even includes sources in your responses. This allows you to find the model that best fits your goals, whether you prioritize speed, cost-efficiency, or clarity of information.

Try it out today and take your experimentation to the next level!

GitHub Models makes it easy for every developer to build AI features and products on GitHub.

To learn more about GitHub Models, check out the docs. You can also join our community discussions.

See more

The general availability of enterprise-owned GitHub Apps brings several updates based on feedback from the public preview.

Most significantly, organizations and users can now transfer private visibility Apps to their enterprise, where they will become usable by the entire enterprise.

In addition, permission updates made to an enterprise-owned App are now automatically accepted by all of the organizations in the enterprise.

These updates allow enterprise owners to consolidate multiple per-organization Apps into a single registration that is managed efficiently at the enterprise level.

image

For enterprise-managed (EMU) users and organizations, both private and internal Apps can be transferred to the enterprise. Private Apps are those that only the owning account can use, while internal Apps are those that any organization and user in the enterprise can use. However, Enterprise Classic organizations and standard user accounts can only transfer private Apps, as internal Apps are not supported in Enterprise Classic.

At this time, internal is the only visibility setting allowed for enterprise-owned Apps, which means that only organizations in that enterprise can install it, and only users in the enterprise can authorize it. Any App that is transferred to an enterprise will be updated to be internal and uninstalled from the user account that owned it, if applicable.

To reduce abuse vectors, enterprises cannot transfer Apps to another enterprise, and organizations and users cannot transfer an App to an enterprise that they are not part of.

As in the preview, only an enterprise owner can manage Apps owned by the enterprise. However, we are actively working on App manager roles and permissions that will allow users and teams to manage specific Apps, as well as manage all of the Apps in an enterprise. These new fine-grained permissions will be introduced for both the enterprise and the organization—keep an eye out for these in the middle of the year.

For more information about enterprise-owned Apps, see our docs page. These updates will be available in GHES 3.17.

To share feedback, ask questions, and more, please join our discussion in the GitHub Community.

See more

DeepSeek-V3 release on GitHub Models

DeepSeek-V3 is now available in GitHub Models.

DeepSeek-V3 is a 671B parameter Mixture-of-Experts model that excels in mathematics and coding, making it suitable for tasks like solving advanced math problems and generating complex code.

GitHub Models makes it easy for every developer to build AI features and products on GitHub.

Try, compare, and implement this model in your code for free in the playground or via the GitHub API. Compare it to other models using side-by-side comparisons in GitHub Models.

To learn more about GitHub Models, check out the docs. You can also join our community discussions.

See more

Today’s changelog announces API support for issues advanced search, timeline events for issue types, and an update on issue types settings.

You can now use GraphQL and the REST API to perform advanced queries for issues using the AND and OR keywords and nested searches.

For the REST API, you can set the advanced_search parameter to true. Check out the REST API documentation for more details.

http://api.github.com/search/issues?q={query}&advanced_search=true

For GraphQL, you can use the ISSUE_ADVANCED type. Check out the GraphQL documentation for more details.

query {
search(query: "is:issue AND assignee:@me AND (label:support OR comments:>5)", type: ISSUE_ADVANCED, first: 10) {
nodes {
... on Node {
id
}
}
issueCount
}
}

Note that on September 4, 2025, all issue queries will use advanced search by default. This means that after this date:

  • You will no longer need to use the advanced_search parameter for the REST API.
  • The ISSUE GraphQL type will support advanced search.

🕐 Timeline events for issue types

You can now see events in the issue timeline when issue types are added, updated, and removed from an issue.

issue type timeline event

🌇 Issue types for private repositories only will be retired

We are retiring the “Private repositories only” setting for issue types. Over the next week, you will no longer be allowed select this setting to specify an issue type for use only in private repositories. All existing issue types with this setting selected that are marked as Private will be removed on March 26, 2025.

In order to continue using these issue types, you will need to unselect the “Private repositories only” setting in the issue types organization settings page before this date. They can then be edited, disabled, or deleted as needed.

issue types settings

Tell us what you think!

Join the discussion within the GitHub Community.

See how to use GitHub for project planning with GitHub Issues, check out what’s on the roadmap, and learn more in the documentation.

See more

Today, we released an upgrade to the GPT-4o Copilot preview model for code completion.

What’s changing

The GPT-4o Copilot model released last month has been upgraded through reinforcement learning to deliver even more useful code completions.

Availability

This upgraded model is available today in public preview under the same gpt-4o-copilot name, with general availability expected in mid-April 2025.

Getting ready

To get started in Visual Studio Code or JetBrains, follow the instructions for your preferred IDE.

If you’re a Copilot Business or Enterprise user, your administrator first needs to enable this model for your organization by opting in to Editor preview features in the Copilot policy settings on github.com.

See more

Personal instructions in github.com

Personal instructions are now generally available for Copilot Chat on github.com! This means you can provide Copilot with important details about your preferences, such as your preferred language, response style, or even code standards.

To get started, open up Copilot Chat, click ..., and select Personal instructions. That’s it! Copilot will now incorporate your preferences for all chats in github.com.

💡 Looking for ideas? Here are some examples to kick things off:

  • Frameworks: “Use Vue 3 with the composition API.”
  • Language: “Always respond in Portuguese.”
  • Response preferences: “Each message should communicate a singular idea. That idea should be limited to ONE codeblock or paragraph.”
  • Code style and best practices: “Optimize code for readability and performance. Utilize SOLID principles.”
See more

Copilot features can go through different early access stages, which are typically enabled and configured through settings. The possible stages are as follows:

  • Experimental: This feature is still in development and not yet ready for general use.
  • Preview: This feature is still under refinement, but is ready to use. You’re welcome to provide feedback!
  • Stable: This feature is ready for general use.

Copilot Edits

Experimental agent mode improvements

Last month, we introduced agent mode for Copilot Edits in VS Code Insiders. In agent mode, Copilot can automatically search your workspace for relevant context, edit files, check them for errors, and run terminal commands (with your permission) to complete a task end-to-end.

Agent mode is available today in VS Code Insiders, and we just started rolling it out gradually in VS Code Stable. Once you have agent mode enabled, you’ll see a mode dropdown in the Copilot Edits view — simply select Agent.

We made several improvements to the UX of tool usages this month:

  • You can keep track of which commands were run since terminal commands are now shown inline.
  • You can edit the suggested terminal command in the chat response before running it.
  • You can confirm a terminal command with the Ctrl + Enter shortcut.

Agent mode autonomously searches your codebase for relevant context. Expand the message to see the results of which searches were done.

Screenshot that shows the expandable list of search results in Copilot Edits.

We’ve also made various improvements to the prompt and behavior of agent mode:

  • The undo and redo actions in chat now undo or redo the last file edit made in a chat response. This is useful for agent mode, as you can now undo certain steps the model took without rolling back the entire chat response.
  • Agent mode can now run your build tasks automatically or when instructed to do so. You can disable this functionality by using the VS Code setting github.copilot.chat.agent.runTasks if the model runs tasks when it shouldn’t.

Learn more about Copilot Edits agent mode or read the agent mode announcement blog post.

If you are a Copilot Business or Enterprise user, an administrator of your organization must opt in to “Editor Preview Features” for agent mode to be available.

Notebook support in Copilot Edits in preview

You can now use Copilot to edit notebook files with the same intuitive experience as editing code files. Create new notebooks from scratch, modify content across multiple cells, insert and delete cells, and change cell types. This preview feature provides a seamless workflow when working with data science or documentation notebooks.

We recommend using VS Code Insiders and the pre-release version of GitHub Copilot Chat to get the best notebook editing experience with Copilot.

Refined editor integration

We have polished the integration of Copilot Edits with code and notebook editors:

  • The viewport remains in place, making it easier to focus on what changes while changes are being applied.
  • The edit review actions are now “Keep” and “Undo” to better reflect what’s happening. Copilot Edits applies and saves these changes as users keep or undo them.
  • The next file is automatically revealed after you keep or undo changes to a file.

Refreshed UI

Files that are attached and not yet sent are now rendered as regular chat attachments. Only files that have been modified with AI are added to the changed files list.

You can use the VS Code setting chat.renderRelatedFiles to enable getting suggestions for related files. Related file suggestions are rendered below the chat attachments.

Screenshot that shows the updated Copilot Edits attachments and changed files user experience.

Removed Copilot Edits limits

We removed the limit on the number of files you can attach to your Copilot Edits prompt and the client-side rate limit.

Note that service-side usage rate limits still apply.

Custom instructions generally available

Custom instructions enable you to tailor GitHub Copilot to provide chat responses and code suggestions to the way you and your team work. Describe your specific requirements in a .github/copilot-instructions.md file in your workspace and enable them with the VS Code setting github.copilot.chat.codeGeneration.useInstructionFiles.

Custom instructions are generally available with .github/copilot-instructions.md. Make sure that the github.copilot.chat.codeGeneration.useInstructionFiles setting is enabled to have Copilot use these instructions when generating responses.

Learn more about custom instructions in Copilot.

Smoother authentication flows in chat

If you host your source code in a GitHub repository, you can leverage several features, including advanced code searching, the @github chat participant, and more!

However, for private GitHub repositories, VS Code needs to have permission to interact with your repositories on GitHub. For a while, this was presented with our usual VS Code authentication flow, where a modal dialog showed up when you invoked certain functionality (for example, asking @workspace or @github a question, or using the #codebase tool).

To make this experience smoother, we’ve introduced this confirmation in chat:

Screenshot that shows the authentication confirmation dialog in Chat, showing the three options to continue.

Not only is it not as jarring as a modal dialog, but it also has new functionality:

  1. Grant: you’re taken through the regular authentication flow like before (via the modal).
  2. Not Now: VS Code remembers your choice and won’t bother you again until your next VS Code window session. The only exception to this is if the feature needs this additional permission to function, like @github.
  3. Never Ask Again: VS Code remembers your choice and records it in the VS Code setting github.copilot.advanced.authPermissions. Any feature that needs this additional permission will fail.

It’s important to note that this confirmation does not confirm or deny Copilot (the service) access to your repositories. This is only how VS Code’s Copilot experience authenticates. To configure what Copilot can access, please read the docs on content exclusion.

More advanced codebase search in Copilot Chat

When you add #codebase to your Copilot Chat query, Copilot helps you find relevant code in your workspace for your chat prompt. #codebase can now run tools like text search and file search to pull in additional context from your workspace.

Set the github.copilot.chat.codesearch.enabled VS Code setting to enable this behavior. The full list of tools is:

  • Embeddings-based semantic search
  • Text search
  • File search
  • Git modified files
  • Project structure
  • Read file
  • Read directory
  • Workspace symbol search

Attach problems as chat context

To help with fixing code or other issues in your workspace, you can now attach problems from the Problems panel to your chat as context for your prompt.

Either drag an item from the Problems panel onto the Chat view, type #problems in your prompt, or select the paperclip 📎 button. You can attach specific problems, all problems in a file, or all files in your codebase.

Attach folders as context

Previously, you could attach folders as context by using drag and drop from the Explorer view. Now, you can also attach a folder by selecting the paperclip 📎 icon or by typing #folder: followed by the folder name in your chat prompt.

Collapsed mode for Next Edit Suggestions in preview

We’ve added a collapsed mode for NES. When you enable this mode, only the NES suggestion indicator is shown in the left editor margin. The code suggestion itself is revealed only when you navigate to it by pressing Tab. Consecutive suggestions are shown immediately until a suggestion is not accepted.

The collapsed mode is disabled by default and can be enabled by configuring editor.inlineSuggest.edits.showCollapsed:true, or you can toggle it in the NES gutter indicator menu.

Screenshot that shows the Next Edit Suggestions context menu in the editor left margin, highlighting the Show Collapsed option.

Change completions model

You can now change the model providing code completions by using the Change Completions Model command in the Command Palette or the Configure Code Completions item in the Copilot menu in the title bar.

If you’re a Copilot Business or Enterprise user, your Administrator needs to enable certain models for your organization by opting in to Editor Preview Features in the Copilot policy settings on github.com.

Model availability

This release, we added more models to choose from when using Copilot. The following models are now available in the model picker in Visual Studio Code and Copilot Chat on github.com:

  • GPT 4.5 (Preview): OpenAI’s latest model, GPT-4.5, is now available in GitHub Copilot Chat to Copilot Enterprise users. GPT-4.5 is a large language model designed with advanced capabilities in intuition, writing style, and broad knowledge. Learn more about the GPT-4.5 model availability in the GitHub blog post.

  • Claude 3.7 Sonnet: Claude 3.7 Sonnet is now in preview for all customers on paid Copilot plans. This new Sonnet model supports both thinking and non-thinking modes in Copilot. In initial testing, we’ve seen particularly strong improvements in agentic scenarios. Learn more about the Claude 3.7 Sonnet model availability in the GitHub blog post.

Copilot Vision in preview

We’re quickly rolling out end-to-end Copilot Vision support in this version of Copilot Chat. This lets you attach images and interact with images in chat prompts. For example, if you encounter an error while debugging, attach a screenshot of VS Code, and ask Copilot to help you resolve the issue. You could also use it to attach a UI mockup and let Copilot provide some HTML and CSS to implement the mockup.

Animation that shows an attached image in a Copilot Chat prompt. Hovering over the image shows a preview of it.

You can attach images in multiple ways:

  • Drag and drop images from your OS or from the Explorer view
  • Paste an image from your clipboard
  • Attach a screenshot of the VS Code window (select the paperclip 📎 button > Screenshot Window)

A warning is shown if the selected model currently does not have the capability to handle the file type. GPT 4o is the only model currently supporting images. You can provide JPEG/JPG, PNG, GIF, and WEBP image types. Claude 3.5 Sonnet and Gemini 2.0 Flash will soon support images as well.

Experimental Copilot status overview

We are experimenting with a new centralized Copilot status overview that provides a quick overview of your Copilot status and key editor settings. You can enable the Copilot status overview with the VS Code setting chat.experimental.statusIndicator.enabled. It includes the following changes:

  • Quota information if you are a Copilot Free user
  • Editor related settings such as Code Completions
  • Useful keyboard shortcuts to use other Copilot features

This Copilot status overview is accessible via the Copilot icon in the Status Bar.

Screenshot that shows the Copilot status overview in the Status Bar.

Experimental TypeScript context for inline completions

We are experimenting with enhanced context for inline completions and /fix commands for TypeScript files. The experiment is currently scoped to Insider releases and can be enabled with the chat.languageContext.typescript.enabled setting.

Custom instructions for pull request title and description

You can provide custom instructions for generating pull request title and description with the setting github.copilot.chat.pullRequestDescriptionGeneration.instructions. You can point the setting to a file in your workspace, or you can provide instructions inline in your settings. Get more details about customizing Copilot in VS Code.

The following sample shows how to provide a custom instruction inline in settings.

{
 "github.copilot.chat.pullRequestDescriptionGeneration.instructions": [
   {
     "text": "Prefix every PR title with an emoji."
   }
 ]
}

You need to have the GitHub Pull Requests extension installed to generate a title and description.

Accessibility

Copilot Edits accessibility

We made Copilot Edits more accessible.

  • Files with modifications and changed regions (insertions, modifications, and deletions) have audio signals.
  • The accessible diff viewer is now available for modified files. Just like in diff editors, select F7 to enable it.

activeEditorState window title variable

We have a new window.title variable, activeEditorState, to indicate editor information such as modified state, the number of problems, and when a file has pending Copilot Edits to screen reader users. When in Screen Reader Optimized mode, this is appended by default and can be disabled with accessibility.windowTitleOptimized:false.

See more