As of today, September 1, 2026, we have deprecated the following models across most GitHub Copilot experiences (including Copilot Chat, inline edits, ask and agent modes, and code completions). Note that Claude Sonnet 4.6 is still available to individual GitHub Copilot subscribers on annual plans.
This week’s updates give you more control over how Copilot runs, from team sessions in Slack and Teams to customization across the app, CLI, and your IDE. GitHub Copilot in Slack and Microsoft Teams Turn team conversations into shared agent sessions.
We’re making it easier to keep labels organized and find the right one, especially in repositories with long and growing label lists. Suggested Labels You can now find the right label faster with suggestions based on what a repository has been using recently.
You can now opt individual plugin marketplaces into automatic updates by setting autoUpdate: true on an extraKnownMarketplaces entry in enterprise managed settings. Supported clients automatically check the marketplace and update installed plugins sourced from it, reducing manual maintenance for organization customizations.
Starting October 1, 2026, checks, workflow runs, and statuses will be governed by the same Actions retention setting that already controls how long artifacts and logs are kept, with a default of 90 days. Until now, checks, workflow runs, and statuses were retained for 400+ days regardless of your retention configuration.
Enterprise owners can now grant a GitHub App access to enterprise billing data. When you create or configure a GitHub App, you can select the enterprise billing permission and choose one of two levels: read or read and write.
In July, we announced a default model policy for generally available GitHub Copilot models on Copilot Business and Copilot Enterprise plans. Starting today, we’re gradually rolling out enforcement of the policy through September 1, so it will take effect at different times for different enterprises.
This update brings Copilot harness to generally availability. You also get more stable account, model, and MCP experiences. What’s new Copilot harness generally available Copilot harness is now generally available, providing faster feature delivery and better code quality.
You can now configure push rules more granularly by exempting specific file paths, so a rule applies everywhere in scope except the paths you choose. Path exceptions are in public preview. Push rules give you strong control over what enters a repository.
You can now block a user directly from a security advisory page in public repositories owned by either an organization or a personal account. This brings the streamlined moderation experience available for issues and pull requests to security advisories.
The GitHub integration in Slack now brings the agentic capabilities of GitHub Copilot CLI and the GitHub Copilot app into Slack in public preview. You can work with @GitHub to plan changes, investigate problems, and hand off coding tasks from the conversations where your team coordinates work.
Managing blocked users is now faster and clearer for personal accounts and organizations. With this update, you can: Search by username, full name, or email. Sort and paginate long lists. Filter by block reason (e.g., Spam , Misconduct , or Harassment ). Add private notes to preserve moderation context. View and edit block settings.
Pinning saved views to the repository issues sidebar You can now pin saved views to the repository issues sidebar, making the views you use most just one click away, even when the sidebar is collapsed. Other Improvements You can now see profile avatars for reactions on issues.
The organization-level Code Quality dashboard now includes a Trends tab that shows how code quality has changed across your repositories over time. Instead of a point-in-time snapshot, you can see whether open findings are trending up or down and which repositories are driving the change.
CodeQL 2.26.3 adds JavaScript, TypeScript, and Vue source modeling and improves the accuracy of several GitHub Actions queries. CodeQL is the static analysis engine behind GitHub code scanning , which helps you find and remediate security issues in your code.
Building on our self-service credential revocation experiences for incident response, you can now take token-type and user-specific actions to deauthorize and revoke user credentials during a security incident. This gives you finer-grained control when responding to a compromise.
GitHub Copilot for JetBrains now supports enterprise managed settings for plugin governance, MCP server access, OpenTelemetry, and permission modes. Administrators can now apply consistent controls for everyone on your enterprise’s Copilot plan.
From new models and portable plugins to smoother agent workflows, this week’s updates make GitHub Copilot more flexible across editors, the command line, and the Copilot app. GitHub Copilot, general Kimi K3 is rolling out to Copilot Pro, Pro+, Max, Business, and Enterprise plans.
We’ve released multiple updates to the OAuth app and GitHub App platforms to support more secure app development: OAuth apps can opt in to expiring access tokens and refresh tokens. OAuth apps can have multiple redirect URIs. Both GitHub Apps and OAuth apps can enable wildcard matching for redirect URIs if needed.
Gemini 3.7 Flash, Google’s latest Flash model, is now rolling out in GitHub Copilot. From our early testing, the model has made improvements in web and app development and agentic coding workflows over it’s previous version.
You can now block or unblock users directly from comments on pull requests and issues in repositories owned by personal GitHub accounts. To block or unblock a user: Open the More menu on their comment. Select Block user or Unblock user . Optionally add a private note explaining why you’re blocking the user. Confirm your selection.
GitHub now uses package registries like npmjs.org and PyPI to determine license information for software components in the dependency graph. This improves the accuracy and completeness of the licenses shown in dependency insights, software bills of materials (SBOMs), the open source license compliance feature in GitHub Advanced Security, and the dependency...
You can now build a plugin once and use it across all compatible agent clients. We published Agent Plugins 1.0 on August 6 with AWS, Anysphere, Microsoft, OpenAI, and Vercel. Google also joined as a core maintainer on the same day.
The rule insights dashboard is now in public preview at the organization level. You get a visual, high-level view of how GitHub evaluates and enforces your GitHub repository rulesets, so you can spot trends and report on governance without stitching data together by hand.
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: Model Deprecation date Suggested alternative MAI-Code-1-Flash 9-10-2026 MAI-Code-1.1-Flash Please update your workflows and integrations to use the new model before September 10.
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.
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.
Update (August 14, 2026): Pausing the custom thread subscriptions deprecation We’re pausing the planned deprecation of custom thread subscriptions. Your feedback highlighted how integral this feature is to many developers’ notification workflows.
Lite and Balanced effort levels for GitHub Copilot code review are now generally available. They let you match the depth of a review to the complexity and risk of a pull request. Not every pull request needs the same scrutiny.
GitHub is making it easier to connect related work and manage multiple field values across issues and projects. Connect related issues The new “Relates to” issue relationship is available in public preview. You can connect two issues without implying that one blocks, duplicates, contains, or closes the other.
This release expands secret scanning’s coverage with more secrets blocked by push protection, one new secret scanning partner, and richer metadata on alerts. Secret scanning partnership program Lovable Labs is now a GitHub secret scanning partner. Secret scanning now automatically detects the following new secret type in your repositories.
Editor’s note (August 6, 2026): We have resumed rolling out Kimi K3 in GitHub Copilot. This model is billed at provider list pricing under usage-based billing. See GitHub Copilot’s pricing for models and requests for details. Editor’s note (August 6, 2026): We have temporarily paused the roll-out of Kimi K3 while we mitigate an incident with GitHub Actions.
You can now set pull request limits at the organization level. Pull request limits let you define how many open pull requests a user without write access can have at one time. If a user reaches that limit, they must close or merge an existing pull request before opening another.
We’re making code coverage setup faster and simpler. You’ll now see a new option in your repository’s Code Quality settings that lets GitHub generate your coverage workflow automatically with AI. We’ll open a pull request so you can review the changes before you merge them. Setting up code coverage has traditionally felt disconnected and manual.
We’ve retired the GitHub Copilot Billing Preview app, and it’s no longer available. You can review and manage your Copilot spend directly in your GitHub billing settings. The app helped you understand your bill during the move to usage-based billing.
Migrations from gitlab.com and GitLab Self-Managed to GitHub Enterprise Cloud with GitHub Enterprise Importer (GEI) are now generally available. You can now self-serve these migrations using GEI and the gh gl2gh command-line extension.
When you delegate a task to GitHub Copilot cloud agent, you can now set the reasoning level for models that support it. This allows you to control how much the model reasons before it responds. A higher level can improve answers to complex problems, but it consumes more tokens, and therefore more credits.
Releasesby Glyph