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

Organization custom instructions now available

Image of organization custom instructions on github.com

Copilot Chat on github.com now supports organization custom instructions! This feature allows Copilot Enterprise customers to set default instructions for all users in their organization, ensuring a consistent experience across teams.

Getting started

  • Navigate to your organization settings on github.com.
  • Select the Copilot tab.
  • Click Custom Instructions in the left sidebar.
  • Add your custom instructions in the provided text box.

That’s it! Copilot will now apply custom instructions to all chats by members of your organization.

Looking for inspiration? 💡

Here are some suggestions to get you started.

  • Set consistent standards: For questions related to security, always redirect to #ask-security on Slack.
  • Establish information architecture: Always refer to the Primer Knowledge Base when answering questions about frontend theming and components.
  • Steer response style: Never include code blocks in responses.
See more

Share Copilot Chat conversations in public preview

Share Copilot Chat conversation is in public preview

Sharing a Copilot Chat used to mean screenshots and copy-paste. Now it’s as easy as sending a link. Shared conversations are now available in public preview.

Sharing Copilot Chats makes it easier to:

  • 🕵 Troubleshoot with teammates—like this chat digging into a React onClick issue.
  • 🧠 Showcase learning workflows with a friend. Here’s an example walking through Python interview prep, step by step.
  • 🤗 Drop useful insights into a pull request review or team chat—like this example that clears up an open team debate.
  • 🎬️ Demo cool Copilot tricks on social—like this one where Copilot asks smart follow-up questions before jumping in.

How sharing works

  • Start a conversation. Once you enter your first prompt, the Share button will appear.
  • Click Share and copy the generated link. Anyone with the link can view the conversation.
  • If the chat includes private repository content or other restricted GitHub data, viewers will need the appropriate permissions to see it.
  • As the conversation continues, recipients will see new messages appear in real time.
  • You can unshare a conversation at any time to revoke access.

Who can use it

Shared conversations are currently in public preview for individual users (not members of organizations or enterprises). We’re actively working on expanding access to all Copilot users soon.

Learn more about sharing Copilot Chat conversations and send us your feedback

See more

Copilot commit message generation now in public preview on GitHub Desktop

Introducing AI-powered commit message generation with Copilot—available in the latest GitHub Desktop Beta. With a click of a new button in the commit message box, get your changes to upstream with speed, confidence, and an AI-crafted summary.

Screenshot of Copilot Commit Message Generation on GitHub Desktop

Copilot commit message generation is available to Copilot Free and all paid Copilot subscribers. Organizations and enterprises can enable it through the “Copilot in GitHub Desktop” policy.

Try it out today—download the GitHub Desktop v3.4.19-beta3 and see how Copilot can supercharge your commit process. Tell us what you think in the GitHub Desktop open source repo.

See more

OpenAI o3 and o4-mini are now available in public preview for GitHub Copilot and GitHub Models

o3 and o4-mini release in GitHub Copilot and GitHub Models

OpenAI’s latest reasoning models, o3 and o4-mini, are now available in GitHub Copilot and GitHub Models bringing next-generation problem-solving, structured reasoning, and coding intelligence directly into your development workflow.

These models represent a major leap forward in capability and efficiency:

  • o3 is the most capable reasoning model in the o-series, ideal for deep coding workflows and complex technical problem solving.

  • o4-mini is the most efficient model in the series, combining low latency with high-quality output, full tools support, and multimodal inputs.

Both models are optimized for real-world development and support advanced features like function calling, structured outputs, and long-context handling (up to 200K tokens). Whether you’re building agentic tools, analyzing contracts, writing algorithms, or debugging across multiple layers, these models are designed to help you move faster with more accuracy and insight.

Availability in GitHub Copilot

o4-mini is now rolling out across all GitHub Copilot plans and o3 is available to Enterprise and Pro+ plans. You can access them through the model picker in Visual Studio Code and in GitHub Copilot Chat on github.com. To accelerate your workflow, whether you’re debugging, refactoring, modernizing, testing, or just getting started, select “o3” or “o4-mini” to begin using a new model. Stay tuned for updates on additional availability.

Enabling access

Copilot Enterprise administrators will need to enable access to these models through a new policy in Copilot settings. As an administrator, you can verify availability by checking your individual Copilot settings and confirming that policy is set to enabled for the specific model. Once enabled, you’ll see the model in the Copilot Chat model selector in VS Code and on github.com.

To learn more about the models available in Copilot, see our documentation on models and get started with Copilot today.

Availability in GitHub Models

Both o3 and o4-mini will also be available through GitHub Models, enabling developers to experiment, build, and deploy AI-powered features faster than ever. In the GitHub Models playground, you can experiment with sample prompts, refine your ideas, and iterate as you build. You can also try them alongside other models, including those from Cohere, DeepSeek, Meta, and Microsoft.

To learn more about GitHub Models, check out the GitHub Models documentation.

Share your feedback

Have feedback or questions? Join the community discussion to share feedback and tips.

See more

Using vision input in Copilot Chat with Claude and Gemini is now in public preview

Copilot looking at Claude and Gemini models

You now have more choices when chatting with Copilot about images in VS Code, Visual Studio, and on the immersive mode on github.com. Starting today, you can use the vision capability with the Claude Sonnet 3.5, Claude Sonnet 3.7, Gemini 2.0 Flash, Gemini 2.5 Pro, and GPT-4o models.

Some ideas to get you started:

  • Add screenshots of errors with Copilot to have it interpret the image and suggest solutions for the issue.
  • Share mockups of new designs, and Vision will help you bring them to life.
  • Ask questions about architecture diagrams.

Currently, the supported image types are JPEG/JPG, PNG, GIF, and WEBP.

When using Vision on VS Code and Visual Studio, make sure you have the Copilot Editor Preview Features policy enabled to get access. On github.com, get started simply by selecting a Claude or Gemini model from the model picker.

This feature was previously only available for GPT-4o in VS Code and Visual Studio and on github.com.

To learn more, read the documentation about using Vision in Copilot Chat.

Please share your feedback in our community discussions.

See more

GitHub Copilot Chat for Eclipse is now generally available

GitHub Copilot Chat for Eclipse is now generally available

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

Key features of GitHub Copilot Chat for Eclipse

  • Chat view: Ask Copilot for help with coding tasks directly in the chat view.  To learn more about this, see our documentation.

  • Model Selector for Chat: GitHub Copilot allows you to change the model during a chat. To learn more about this, see our documentation.

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

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

  • ABAP Enablement: GitHub Copilot for Eclipse has introduced enablement for ABAP, allowing users to leverage Copilot’s capabilities while working with ABAP code. GitHub Copilot for Eclipse uses the currently available models described in the documentation, without any specific fine-tuning for ABAP.

Try it out

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

Once you have a 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

Upcoming breaking changes and releases for GitHub Actions

We’re introducing new controls for automation workflows, enhancing security and flexibility for teams. Additionally, we’ve released updates to Actions runner controller designed to improve performance, customization, and compatibility with evolving deployment strategies. As part of our commitment to maintaining up-to-date infrastructure, we’re retiring older images and encouraging users to transition to newer, more efficient options.

Copilot events not automatically triggering GitHub Actions workflows is in public preview

Copilot authored events will no longer automatically trigger GitHub Actions workflows – administrators will now need to approve these workflows to run.

The approval mechanism is the same as approving runs from forks. This means that a run requiring approval will be given the action_required conclusion before any jobs are started. Users with write access in the UI or actions:write fine-grained access through the API can approve any action_required run. Any triggered workflow runs associated with the same PR in the action_required state will show up in the PR merge box for approval.

If a run is not approved after 30 days, it will be deleted.

Join the discussion within GitHub Community.

Windows Server 2019 is closing down

We’re beginning the process of closing down the Windows server 2019 hosted runner image, following our N-1 OS support policy. This image will be fully retired by June 30, 2025. We recommend updating workflows use windows-2022 or windows-2025.

To raise awareness of the upcoming removal, we’ll temporarily fail jobs using the windows-2019 label starting in June 2025. The brownouts will occur on the following dates and times:

  • June 3 13:00 – 21:00 UTC
  • June 10 13:00-21:00 UTC
  • June 17 13:00-21:00 UTC
  • June 24 13:00-21:00 UTC

Actions runner controller release 0.11.0

The latest ARC release (0.11.0) includes two major product enhancements and numerous quality-of-life improvements.

Customers can now set custom annotations and resources, enabling them to use deployment methods like ArgoCD and Helm.

In addition, ARC customers experienced performance issues due to high cardinality metrics, particularly around labels such as runner name, ID, job workflow ref, and others. This significantly impacted resource consumption in Prometheus instances. With this release, customers can now configure metrics, enabling them to choose elements relevant to their reporting strategy.

All included changes in this release can be found in the release notes.

Updates to the network allow list for Azure private networking

GitHub previously reported the network communication requirements for Azure private networks as they relate to the upcoming release of immutable actions. Please use the IPs listed in the NSG template within our documentation, as previous changelog communications contained overlapping CIDR ranges.

See more

OpenAI GPT-4.1 now available in public preview for GitHub Copilot and GitHub Models

GPT-4.1 release in GitHub Copilot and GitHub Models

OpenAI’s latest model, GPT-4.1, is now available in GitHub Copilot and GitHub Models, bringing OpenAI’s newest model to your coding workflow. This model outperforms GPT-4o across the board, with major gains in coding, instruction following, and long-context understanding. It has a larger context window and features a refreshed knowledge cutoff of June 2024.

OAI has optimized GPT-4.1 for real-world use based on direct developer feedback about: frontend coding, making fewer extraneous edits, following formats reliably, adhering to response structure and ordering, consistent tool usage, and more. This model is a strong default choice for common development tasks that benefit from speed, responsiveness, and general-purpose reasoning.

Copilot

OpenAI GPT-4.1 is rolling out for all Copilot Plans, including Copilot Free. You can access it through the model picker in Visual Studio Code and on github.com chat. To accelerate your workflow, whether you’re debugging, refactoring, modernizing, testing, or just getting started, select “GPT-4.1 (Preview)” to begin using it.

Enabling access

Copilot Enterprise administrators will need to enable access to GPT-4.1 through a new policy in Copilot settings. As an administrator, you can verify availability by checking your individual Copilot settings and confirming the policy for GPT-4.1 is set to enabled. Once enabled, users will see GPT-4.1 in the Copilot Chat model selector in VS Code and on github.com.

To learn more about the models available in Copilot, see our documentation on models and get started with Copilot today.

GitHub Models

GitHub Models users can now harness the power of GPT-4.1 to enhance their AI applications and projects. In the GitHub Models playground, you can experiment with sample prompts, refine your ideas, and iterate as you build. You can also try it alongside other models including those from Cohere, DeepSeek, Meta, and Microsoft.

To learn more about GitHub Models, check out the GitHub Models documentation.

Share your feedback

Join the Community discussion to share feedback and tips.

See more

VSCode Copilot agent mode in Codespaces

GitHub Codespaces has introduced a new Agentic AI feature—you can now open a Codespace running VSCode’s Copilot agent mode, directly from a GitHub issue. With a single click, you can go from issue to implementation!

When you’re in a GitHub issue, the right-hand side of the view now displays a Code with Copilot Agent Mode button in the Development section. Clicking this button initializes a new Codespace, opens the Codespace in a new tab, and enables VSCode’s Copilot agent mode, using the issue body as context. Copilot will then get to work on the issue, thoroughly analyzing the codebase and considering dependencies to suggest appropriate file changes. You can then work with Copilot to fine tune your code and make modifications as required.

VSCode Agent Mode in Codespaces is in public preview, and we’ll be iterating on the experience over the upcoming months. Stay tuned for updates!

See more

Copilot Chat users can use the Gemini 2.5 Pro model in public preview

Gemini 2.5 Pro is now available to all GitHub Copilot customers. The latest Gemini model from Google is their most advanced model for complex tasks. It shows strong reasoning and code capabilities. It also leads on common coding, math, and science benchmarks.

Google Gemini 2.5 Pro announcement

Get started today!

Copilot Pro/Pro+ users

You can start using the new Gemini 2.5 Pro model today through the model selectors in Copilot Chat in VS Code and immersive chat on github.com.

Copilot Business or Enterprise users

Copilot Business and Enterprise organization administrators will need to grant access to Gemini 2.5 Pro in Copilot through a new policy in Copilot settings. Once enabled, users will see the model selector in VS Code and chat on github.com. You can confirm the model’s availability by checking individual Copilot settings and confirming the policy for Gemini 2.5 Pro is set to enabled.

Share your feedback

Join the Community discussion to share feedback and tips.

For additional information, check out the docs on Gemini 2.5 Pro in Copilot.

Learn more about the models available in Copilot in our documentation on models and get started with Copilot today.

See more

Copilot Chat now supports pasting GitHub URLs as explicit references

An illustration of a GitHub issue link with a purple and blue background. A URL is displayed in a browser bar at the top, with a dark notification box shows below it, all next to the Copilot logo.

Issues, discussions, and pull requests – these are all important pieces of context when building in GitHub. Now, you can reference these within Copilot Chat. Simply paste a link into the chat and Copilot will do the rest!

How it helps you

  • 📂 Multi-repository support: want to compare a pull request from one project with a discussion from another? No problem!
  • 🏷️ Intuitive navigation: maybe you pasted a link, got up to make a coffee, and forgot what you were doing. With chips in the chat context, you don’t need to worry – it will always be clear what you’ve added.
  • ⌨️ Context-building at your fingertips: let Copilot support you and integrate your work by focusing on the specific problems you want to address.

We like to think that GitHub files and Copilot are both great, and they’re even better when they come together. The power of Copilot and the fountain of knowledge in your repositories will collectively help you do amazing things. We know it.

💬 Let us know what you think using the in-product feedback option or pop it into the GitHub Community at any time.

See more

Reload responses with other Copilot models on github.com

Image of Copilot next to a model selection menu

The immersive mode of Copilot Chat now gives you more choices when reloading your responses.

What’s new?

You can now easily regenerate Copilot responses using a different model. Simply click the retry button underneath Copilot’s response. Copilot will process the same prompt by your chosen model while maintaining all previous conversation context. You can also view previous responses and compare model output.

How it helps you

  • 🧩 Stuck on a complex problem? Switch to a more powerful model for deeper reasoning.
  • ⚡ Need a quick response? Reload with a faster model when speed matters.
  • 💻 Working with code? Switch to a model optimized for programming.
  • 🎨 Fine-tuning creative work? Try different models to explore alternative approaches.

This feature is perfect for when you need a different perspective or more specialized capabilities. Seamlessly blend the strengths of various models into a single conversation. Enjoy more intelligence, more flexibility, and more control – all while staying in the flow.

💬 Let us know what you think using the in-product feedback option or pop it into the GitHub Community at any time.

See more

Security campaigns are now generally available to help address security debt at scale

Security campaigns are now generally available

Security campaigns with Copilot Autofix are now generally available. As part of GitHub Code Security, you can use security campaigns to prioritize and rapidly reduce your backlog of application security debt. Copilot Autofix generates contextual explanations and fixes for historical code scanning alerts in a security campaign, which help developers and security teams collaborate to fix vulnerabilities with speed and confidence.

With the help of GitHub’s CodeQL and Copilot Autofix, it has never been easier to prevent new vulnerabilities from being added to your code. However, if you don’t address vulnerabilities discovered in already-merged code, security debt can build up and pose a serious risk to deployed applications.

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, and developers who are most familiar with the code are notified. From there, they can review the fixes, open pull requests, and remediate security debt. Security teams can monitor the progress of the campaign and track the number of fixed alerts. 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.

Starting today, you can also access these new features to plan and manage security campaigns more effectively:

  • Draft security campaigns: Security managers can now iterate on the scope of campaigns and save them as draft campaigns before making them available to developers. With draft campaigns, security managers can ensure that the highest priority alerts are included before the work goes live.
  • Automated GitHub issues: Security managers can optionally create GitHub issues in repositories that have alerts included in the campaign. These issues are created and automatically updated as the campaign progresses and can be used by teams to track, manage, and discuss campaign-related work.
  • Organization-level security campaign statistics: Security managers can now view aggregated statistics showing the progress across all currently-active and past campaigns.

Security campaigns are available for users of GitHub Code 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 GitHub Community.

See more

Copilot code review now generally available

Copilot code review is now generally available!

Code review is one of the most critical parts of software development, but manual code reviews can be time-consuming. Copilot code review helps you offload basic reviews to a Copilot agent that finds bugs, potential performance problems, and even suggests fixes. This means you can start iterating on your code while waiting for a human review, helping you keep your code repositories more maintainable and focused on quality.

In just over a month since we launched the public preview, over 1 million developers have already used Copilot code review, and the response has been incredible.

Check it out in action, in both Visual Studio Code and GitHub:

To request a code review from Copilot, you can set up automatic reviews in a repo through repository rules. Or, you could ask Copilot to review a pull request on demand.

Copilot code review is available to all paid Copilot subscribers. Organizations and enterprises can enable it through the Copilot in github.com policy.

What’s next

We’re continuously improving Copilot code review. Today we’ve added support for C, C++, Kotlin, and Swift in public preview and we’ll add support for HTML and txt early next week.

To learn more, check out our code review docs. We can’t wait for you to try out these improvements, and we’d love your feedback in this GitHub Community discussion!

See more

Announcing GitHub Copilot Pro+

Today, we’re introducing GitHub Copilot Pro+, a new individual tier for developers who want to take their coding experience to the next level.

Enjoy all the features you love from GitHub Copilot Pro along with exclusive access to the latest models (GPT-4.5 is available today), priority access to previews, and 1500 premium requests per month when they go live on May 5th. This is in addition to the unlimited requests for agent mode, context-driven chat, and code completions that all paid plans have when using our base model.

To get started, purchase GitHub Copilot Pro+ today and don’t miss out on the other Copilot updates shared in our announcement blog.

Stay tuned for updates as we work to continuously enhance your developer experience. Also, please share any feedback in GitHub Community.

See more
View more changes