GitHub Enterprise Server (GHES) 3.22 is now available and introduces new capabilities across the platform. Here are a few highlights in the 3.22 release:

• Administrators can configure Copilot CLI to work with GHES for enterprises that operate in disconnected or air-gapped environments without connectivity to GitHub Cloud. Set up a model provider once in GHES, and your end users across the enterprise can use Copilot CLI with their GHES credentials. This capability is in technical preview and is subject to change.

• Enterprise Teams, previously in public preview, is now generally available. Enterprise owners can use Enterprise Teams to manage users and their access across the entire enterprise, including organizations and repositories, from a single, centralized team structure. This reduces the operational overhead of managing user access across multiple organizations within an enterprise.

• Security analysts can now sort secret scanning push protection bypass requests and secret scanning alert dismissal requests by date, in ascending or descending order, using the filter bar at the repository, organization, and enterprise levels. Previously, sort order for these requests could not be adjusted, which made it difficult for teams managing high volumes of requests to prioritize their review.

• Repository rulesets now support bypassing by individual users. This gives administrators more granular control over rule bypass permissions, such as adding a service account to a bypass list without needing to create a dedicated role or team.

• Organization owners and repository administrators can require specific reviewers for pull requests by adding a required reviewers rule to a repository ruleset, targeting specific branches, files, and folders using pattern matching, and can set the minimum number of required reviews per team. This rule works alongside CODEOWNERS and is particularly useful when changes need sign-off from teams beyond the code owners (e.g., security, QA, or design). For example, administrators can require a data platform team review on all *.sql changes, security team members on the default branch, or product and design reviewers on feature branches.

• Developers can now see release status directly in the issue sidebar. When a linked pull request has been included in a release, the sidebar displays a “Latest release” or “Pre-release” badge, making it easy to tell whether a fix has shipped without leaving the issue.

• Maintainers can now see contributor role labels, such as “First-time contributor,” “Contributor,” and “Member,” directly in the pull request list view for public repositories. This gives maintainers at-a-glance context about each author’s relationship to the repository without needing to open individual pull requests to check the comment box for this information.

Release candidates are a way for you to try the latest features early and help us gather feedback. Read more about the release candidate process. To learn more about GHES 3.22, check out the release notes, or download the 3.22 release candidate now.

If you have any feedback or questions about the release candidate, please contact our support team.

The post GitHub Enterprise Server 3.22 release candidate appeared first on The GitHub Blog.

This update brings persistent memory, local model access, and more enterprise controls to GitHub Copilot for JetBrains. It also improves everyday chat workflows and resolves reliability issues across MCP servers, terminals, customizations, and cloud agents.

What’s new

Enterprise managed settings

Administrators have more server-based controls for managing GitHub Copilot across their organizations. These enterprise managed settings cover plugin availability, MCP server access, permission bypass behavior, and OpenTelemetry settings.

Read more about enterprise managed settings.

Copilot memory across chat sessions

Copilot memory can now retain and recall useful information across agent chat sessions. This helps you maintain context between conversations instead of repeatedly providing the same project details or preferences.

You can manage the feature with the Copilot Memory toggle in the Copilot settings portal. For more information, see About Copilot memory.

Ollama as a BYOK provider

You can now use Ollama as a BYOK provider in GitHub Copilot for JetBrains. The integration supports provider configuration and model selection throughout the JetBrains experience, giving you another way to work with models that fit your development environment.

Expanded Codex workflows

Codex sessions are now visible in agent debug logs. Codex workflows also support updated permission modes and customizations through instructions and skills, helping you adapt agent behavior to your project.

Easier Copilot CLI setup

GitHub Copilot for JetBrains can now automatically install Copilot CLI from integrated terminals on macOS, Linux, and Windows. This reduces setup steps and makes it easier to start using terminal-based agent workflows directly from your IDE.

User experience enhancements

This release improves common account, model, and agent interactions:

• Account management: Improved account management flows by supporting account switch/removal and polishing account-deletion interactions.
• Model and settings views: Improved model and settings usability by capping long model-name width in the model picker and refining model view/todo list panel behavior.
• Chat references: Restored file and folder # references in Copilot, Claude, and Codex chat inputs.
• Customization: Moved the customization button to the top of Copilot chat.
• Agent debug logs: Moved the agent debug logs button to the Options dropdown at the top of Copilot chat.

Quality improvements

This release improves reliability for MCP execution and approvals, terminal output and auto-approval, customizations, cloud agents, and diff-based editing. It also fixes ANSI escape rendering and makes terminal scrollbars more predictable.

Changed

User-facing product strings now use “Copilot” instead of “Copilot CLI.”

Try it out

Try the latest version of the GitHub Copilot plugin and share your feedback.

Share your feedback

Your feedback drives improvements. We’d love to hear about your experience in the following channels:

• In-product feedback: Use the feedback options within your IDE.
• Feedback repository: Share your thoughts in the GitHub Copilot for JetBrains IDEs issues.

The post Copilot memory and Ollama in GitHub Copilot for JetBrains appeared first on The GitHub Blog.

You can now convert your existing branch protection rules to repository rulesets directly from your repository settings. This helps you migrate to GitHub’s more flexible and scalable policy framework without manually recreating each rule.

As we continue investing in rulesets as the foundation for repository governance on GitHub, this tool makes it easy to bring your existing policies forward.

How it works

Navigate to Settings → Branches in your repository, find the classic rule under Branch protection rules, and click Convert to ruleset. GitHub maps your existing branch protection configuration including required reviews, status checks, and push restrictions into equivalent ruleset rules.

Why migrate to rulesets?

Rulesets offer several advantages over classic branch protections:

• Apply rules across multiple branches with pattern matching.
• Layer multiple rulesets for granular policy control.
• Manage rulesets at the organization or enterprise level.
• Configure fine-grained bypass permissions for users, teams, and apps.

Availability

This feature is available for all repositories where rulesets are available. Learn more about repository rulesets.

Join the discussion within GitHub Community.

The post Automatically migrate branch protection rules to repository rulesets appeared first on The GitHub Blog.

With the launch of MAI-Code-1.1-Flash, we will deprecate MAI-Code-1-Flash across all GitHub Copilot experiences on September 10, 2026:

Please update your workflows and integrations to use the new model before September 10. Copilot Enterprise administrators may need to enable access to the alternative model through their model policies in Copilot settings. As an administrator, you can verify availability by checking your individual Copilot settings and confirming that the policy is 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. No action is required to remove the older model once it has been deprecated.

GitHub Enterprise customers with questions or concerns are encouraged to reach out to their account manager for further assistance.

Share your feedback

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

Join the GitHub Community to share your feedback.

The post Upcoming deprecation of MAI-Code-1-Flash appeared first on The GitHub Blog.

MAI-Code-1.1-Flash, Microsoft’s latest small-tier coding model, is now rolling out in GitHub Copilot. Building on MAI-Code-1-Flash, it adds native vision support for image understanding and delivers improvements across coding quality, instruction following, tool use, and performance.

Alongside these model enhancements, continued advances in model and serving efficiency have enabled a 73% lower list price than MAI-Code-1-Flash, making it a cost-effective option for lightweight coding workflows that require a balance of capability and cost efficiency. For annual GitHub Copilot subscribers, the model is charged at a 0.25× premium request multiplier.

Read the MAI-Code-1.1-Flash announcement for a deeper look at the model’s vision support, coding performance improvements, and efficiency gains.

This model is billed at provider list pricing under usage-based billing. See GitHub Copilot’s pricing for models and requests for details.

Availability in GitHub Copilot

MAI-Code-1.1-Flash will be available to Copilot Free and Student users through auto model selection. Copilot Pro, Pro+, Max, Business, and Enterprise SKUs will be able to manually select this model in addition to having auto model select it.

You’ll be able to select the model in the model picker in:

• Copilot CLI
• Copilot cloud agent
• GitHub Copilot app
• Copilot Chat on GitHub
• Visual Studio Code
• Visual Studio
• GitHub Mobile
• JetBrains IDEs
• Eclipse
• Xcode

Enabling access

Copilot Enterprise and Copilot Business plan administrators must enable the MAI-Code-1.1-Flash policy in Copilot settings. The policy is off by default.

Learn more

To explore all models available in GitHub Copilot, see our documentation on models and get started with Copilot.

Share your feedback

Share your feedback on this model in the GitHub Community Discussion.

The post MAI-Code-1.1-Flash available in GitHub Copilot appeared first on The GitHub Blog.

You can now see a per-model breakdown of the tokens behind your AI credits in the usage report. For each model, the AI usage report shows the input, output, cache read, and cache write tokens alongside the AI credits it consumed.

Before, the report showed AI credits without the token detail underneath them, so it was hard to explain a charge or find ways to bring it down. Now you can trace exactly how input, output, and cached tokens add up to each model’s cost, and share those details with your stakeholders.

The token breakdown is available to admins on Copilot Business and Copilot Enterprise, and to anyone on Copilot for individuals.

To get the breakdown, download the AI usage report from the AI usage page in your billing settings. For more information, see Billing reports reference.

The post Per-model token breakdown in the usage report appeared first on The GitHub Blog.

We’ve made improvements to Copilot Chat on github.com that make it easier to use. These include easier access to your recent conversations in chat, the ability to minimize the chat window and return to an in-progress conversation, and indicators that help you track your Copilot token spend.

Minimize and resume conversations

We’ve improved the chat overlay experience by adding two new features.

The first is the ability to minimize the screen during a conversation. This allows you to browse GitHub while waiting for a Copilot response.

The second is the ability to more easily view and continue your recent conversations.

Monitor your token usage

We’ve also added token spend indicators in chat. Clicking on the token spend icon lets you see your per-session and per-message quota, allowing you greater visibility into your token spend and budget.

These features are generally available to all Copilot plans.

Try it out at github.com/copilot.

The post Copilot on web expands conversation controls appeared first on The GitHub Blog.

Customers in India can now use eligible saved credit cards for automatic recurring payments on monthly and annual GitHub bills.

This update uses a payment mandate, also known in the payments industry as an electronic mandate, to authorize future charges in line with Reserve Bank of India requirements. This helps reduce manual payment steps during each billing cycle while keeping payment method management unchanged.

There are no changes to how you save or remove a payment method. This applies to paid GitHub products for customers in India where recurring card payments are supported.

To learn more, see our documentation about one-time payments in India.

The post GitHub billing in India now supports automatic recurring payments appeared first on The GitHub Blog.

You’ll no longer be able to configure custom thread subscriptions for GitHub notifications.

What’s changing

As part of this rollout, GitHub will remove support for custom thread subscription settings.

If you currently rely on this feature, please note that the Customize option in the thread-level notification settings will be completely removed. After this change, only Subscribed and Not subscribed options will be available for a thread.

All existing custom subscriptions will be converted to Subscribed, and users will receive notifications for all events in those threads. If this becomes too noisy, users can unsubscribe from any affected thread.

Why we’re making this change

This change simplifies your notifications experience by:

• Simplifying notification behavior.
• Reducing subscription complexity.

What you need to do

No immediate action is required for most users.

If your workflow depends on custom thread subscription behavior, we recommend reviewing your notification settings and team communication patterns as this rollout progresses.

The post Custom thread subscriptions are being deprecated appeared first on The GitHub Blog.

This week’s updates across GitHub Copilot in the desktop app, CLI, and VS Code help you resume and organize work, review changes, and ask questions without losing context.

GitHub Copilot app

• Auto now shows which model handled each completed request, plus AI credit and cache details when they’re available.
• Jump directly into shared sessions, or use /side to explore a parallel question without disrupting your main task.
• Apply the updated Impeccable skill to mobile interfaces, diagnose its setup, and run more focused design reviews.
• Sessions now start and switch more efficiently.

Try the Copilot app.

GitHub Copilot CLI

• Easily manage multiple concurrent sessions from the Sessions sidebar. Simply click < (left arrow) to open the Sessions sidebar and use shortcuts to open new sessions (n), close current ones (x), and move between sessions with ease. Click > right arrow to close the sidebar.
• Create an isolated worktree and begin a separate conversation with the new experimental /worktree command. This gives you another workspace for exploring changes without disrupting your current work.
• Use /rewind without Git to restore the conversation and files Copilot changed while preserving subsequent edits.
• See live tool-call durations in the timeline to identify slow commands.

Install the Copilot CLI.

VS Code 1.132 Release updates

• The integrated browser now supports element-level feedback. Select specific elements on a web page, attach a comment to each one, and send that precise visual feedback to the agent. You can select and annotate multiple elements before submitting your message.
  Editor’s note (August 11, 2026): Removed an inaccurate reference to the Agents window.

• Dictate in multiple languages. Dictation now uses a multilingual on-device model by default, keeping audio on your device. It can follow your configured language, use your system or browser locale, or automatically detect the language. A new onboarding experience also helps you select and test your microphone.

• Ask side questions with /btw. Open a side chat without interrupting the agent’s current turn. The side chat shares the context and prompt cache from your primary conversation, so you can ask about the work already in progress. You can also select text from a response and ask a contextual question about it. This is supported in VS Code’s Agents window.
  Editor’s note (August 10, 2026): Clarified that this works in the Agents window.
• Review Markdown changes in context. Markdown diffs can now open in the experimental hybrid Markdown editor. The modified document remains editable, while gutter indicators identify added, changed, and deleted content. You can switch between the text diff and hybrid Markdown views from the editor type dropdown.

Explore everything that’s new in the full release notes

The post GitHub Copilot weekly releases — August 3 appeared first on The GitHub Blog.