GitHub Copilot

Computer use is now available in public preview in GitHub Copilot CLI and the GitHub Copilot app on macOS and Windows. Copilot can interact with desktop applications on your behalf (e.g., reading accessible app content and visual context, clicking controls, entering and editing text, pressing keys, scrolling, dragging, and navigating workflows across applications). This expands the tasks Copilot can help automate, including workflows in legacy and GUI-only software that do not provide an API, command-line interface, or MCP integration. Copilot uses computer-use tools to navigate an expense-report workflow in Safari. You remain in control. Copilot asks for approval before controlling an app, and you can review or reset apps that you have chosen to always allow. On macOS, computer use also guides you through the required Accessibility and Screen Recording permissions. Organization-managed settings can disable the feature. To get started:

• In Copilot CLI, run /computer on . Use /computer show to check its status and /computer off to disable it.
• In the GitHub Copilot app, open Settings , select Computer Use , and turn on Enable Computer Use . You can also use /computer on .

The HydraFusion research preview is now available in Visual Studio Code and the GitHub Copilot app, expanding beyond Copilot CLI. HydraFusion appears in the model picker, but rather than being a single model, it orchestrates multiple models. HydraFusion treats workflow selection as an optimization problem. It uses capability signals for reasoning, code generation, debugging, and tool use to select the most efficient execution pattern to meet the quality bar. HydraFusion uses one of three workflows:

• Single: One selected model directly solves the task.
• Cascade: An efficient model drafts a solution and a quality gate decides whether to accept it or escalate to a stronger model.
• Critique: One model drafts a result, an independent read-only critic from a different model family reviews it—following the same review pattern as Rubber Duck —and the drafting model revises once. Get started In VS Code (version 1.140 or later, or VS Code Insiders):
• Select HydraFusion from the Copilot Chat model picker.

GPT-6.1 Sol, the latest model from OpenAI, is now generally available and rolling out in GitHub Copilot. You can use it for agentic coding and terminal workflows with strong multistep coding performance and efficient token use. In early testing, it reliably completed tasks while using noticeably fewer tokens and steps than earlier models in the GPT-6 and GPT-5.6 families. This model is billed at provider list pricing under usage-based billing. See Models and pricing for GitHub Copilot for details. Availability in GitHub Copilot GPT-6.1 Sol is available to Copilot Pro+, Max, Business, and Enterprise users. You can select it in the model picker in:

• Visual Studio Code
• Visual Studio
• Copilot CLI
• GitHub Copilot coding agent
• GitHub Copilot app
• github.com
• GitHub Mobile on iOS and Android
• JetBrains IDEs
• Xcode
• Eclipse Rollout will be gradual. Check back soon if you don't see it yet. Enabling access Copilot Business and Enterprise administrators can manage access to GPT-6.1 Sol through the model policy in Copilot settings. Under default model enablement, new models are automatically enabled unless an administrator has turned off the global default or explicitly disables

Claude Sonnet 5.5, Anthropic's newest Sonnet model, is now generally available in GitHub Copilot. It is designed for well-scoped everyday work like building features and fixing bugs. In our early testing, Sonnet 5.5 stood out for its efficiency, matching Claude Sonnet 5 on coding tasks while using significantly fewer steps, tokens, and tool calls. It also finished tasks noticeably faster. This model is billed at provider list pricing under usage-based billing. See Models and pricing for GitHub Copilot for details. Availability in GitHub Copilot Claude Sonnet 5.5 is available to Copilot Pro, Pro+, Max, Business, and Enterprise users. You can select the model in the model picker in:

• Visual Studio Code
• Visual Studio
• Copilot CLI
• GitHub Copilot coding agent
• GitHub Copilot app
• github.com
• GitHub Mobile on iOS and Android
• JetBrains IDEs
• Xcode
• Eclipse Rollout will be gradual. Check back soon if you don't see it yet. Enabling access Copilot Enterprise and Copilot Business plan administrators can manage access to Claude Sonnet 5.5 through the model policy in Copilot settings. Under default model enablement, new models are automatically enabled unless an administrator has

GitHub Copilot in Slack and Microsoft Teams now gives you more context, more control, and a clearer path from conversation to GitHub work. Whether you're sharing files in Slack or images and forwarded messages in Teams, Copilot can use more of the context already in your conversation. We've also improved how Copilot creates GitHub work and connects it back to the source discussion, so teams can more quickly see the context behind a decision. Better context for the work you're already doing You can now use supported Slack files, attachments, and message links as context. In Teams, Copilot can work with inline images, forwarded-message context, and channel and thread history. Copilot also checks for similar issues before creating a new one, includes direct links to the resulting work, and keeps a link back to the originating conversation so the context remains easy to trace. More control over how you work You can switch models for the next message and keep that choice throughout the conversation. In Slack, you can also set default owners and repositories. This makes it easier to keep work moving across repositories and shared conversations. Bug fixes and reliability improvements

This week's releases add new models to Copilot, local sandboxing in the Copilot app, and updates to Copilot in Slack, Microsoft Teams, JetBrains, and VS Code. GitHub Copilot

• Claude Opus 5.5 is available to Copilot Pro+, Max, Business, and Enterprise plans.
• GPT-6 Sol is available to Copilot Pro+, Max, Business, and Enterprise plans.
• GPT-6 Luna is available to Copilot Pro, Pro+, Max, Business, and Enterprise plans.
• Grok 4.7 is available to Copilot Pro, Pro+, Max, Business, and Enterprise plans. GitHub Copilot app
• Limit agents' access to files, networks, and credentials with local sandboxing, now in public preview.
• Track agent activity in your existing monitoring tools with OpenTelemetry, configured through enterprise-managed settings. Download the Copilot app . GitHub Copilot in Slack and Microsoft Teams
• Choose the best model for each task. Switch models mid-conversation, and Copilot keeps your choice for the rest of the thread. In Slack, you can also set channel defaults.
• Avoid duplicate issues since Copilot now checks for similar existing issues before creating a new one.

Agentic autofix now uses Copilot Memory for customers who've enabled it. When you use agentic autofix, it reviews existing memories for context that can help resolve security alerts. When it creates a fix, it stores the fix pattern as a memory for future use. These memories can help agentic autofix resolve additional security alerts and teach other GitHub Copilot features (e.g., Copilot code review, Copilot cloud agent) about secure development patterns unique to your repository. Both agentic autofix and Copilot Memory are available in public preview. Learn more in our docs about GitHub Copilot Memory . application security copilot Share Copied Shared Related Posts Oct.01 Release GitHub Copilot can now interact with desktop apps with computer use client apps copilot ... +1 Oct.01 Release GitHub Copilot in VS Code, September 2026 releases copilot Oct.01 Improvement Scheduled code scanning skips inactive repositories application security Oct.01 Improvement Code coverage uploads no longer fail CI for new branches application security Oct.01 Release Dynamic workflows in Copilot CLI and the Copilot app copilot Sep.30 Release GitHub Advanced Security trials for GitHub Team

The enterprise and organization repository-level Copilot usage metrics reports now break down how long pull requests spend in each stage of review. A new pull_request_review_times array on each repos-1-day row reports a median and a 90th percentile for the time from ready for review to first review, first review to final review, and final review to merge. What's new Each entry in pull_request_review_times includes:

• authored_by and reviewed_by : Who opened and who reviewed the pull requests in this entry. Both are human in this release.
• total_merged : The number of qualifying pull requests merged in the repository that day.
• median_minutes_ready_to_first_review and p90_minutes_ready_to_first_review : Time from the pull request becoming ready for review to its first review.
• median_minutes_first_to_final_review and p90_minutes_first_to_final_review : Time between the first and final review.
• median_minutes_final_review_to_merge and p90_minutes_final_review_to_merge : Time from the final review to merge. Durations are in minutes and attributed to the day the pull request merged. The existing pull_requests fields are unchanged. Why this matters

You can now use an in-product validator for enterprise managed settings for GitHub Copilot. The validator detects malformed JSON, unsupported configurations, invalid team mappings, and other errors that can prevent policies from being enforced. Review and correct errors in the "Copilot settings validation" section of the enterprise AI controls page. Each issue identifies the affected file and JSON path, helping you make corrections to ensure that policies are enforced as intended. Validation covers:

• copilot/managed-settings.json
• copilot/team-mappings.json and any team settings files referenced by the team mappings file After correcting an issue, commit the change to the default branch of your .github-private repository, reload the Agents page, and review the validator results to confirm that your configuration is valid. To learn more, see our documentation on enterprise managed client settings . copilot enterprise management tools Share Copied Shared Related Posts Sep.29 Release GPT-6.1 Sol in GitHub Copilot copilot Sep.28 Release Claude Sonnet 5.5 in GitHub Copilot copilot Sep.25 Improvement Usage metrics API adds pull request review stages account management copilot

We're introducing a new global default policy for generally available GitHub Copilot features and supported client capabilities in enterprise and organization Copilot settings. For the next 28 days, you can configure this policy, but it won't affect feature access for your users yet. What's changing Today, you can configure the new policy by going to the "AI Controls" page, opening the "Copilot" subpage, and selecting an option under "Default policy for new features". This policy applies to eligible features managed on your enterprise's "Features & clients" page (i.e., https://github.com/enterprises/YOUR-ENTERPRISE-SLUG/ai-controls/copilot/features), as well as the Copilot Code Review policy on the "Agents" page and the MCP servers in Copilot policy. For feature eligibility and exceptions, see our docs on default availability . You can choose from the following settings:

• Enabled : Current and future eligible features will be available to users by default.
• Disabled : Current eligible features will remain unavailable, and future eligible features will require administrator approval.

Local sandboxing helps reduce the potential impact of unintended commands by limiting access to files, network resources, and credentials on your machine. In the GitHub Copilot app, you configure it per project for local repository and working tree sessions. The project's sandbox settings include:

• Filesystem: Additional read/write, additional read-only, and denied folder lists.
• Network: Outbound internet and local network settings.
• Credentials: Git credentials for authenticated HTTPS git operations, and GitHub CLI credentials for GitHub CLI authentication. These project settings describe the policy that the app requests when a sandboxed session starts. The effective policy can be more restrictive when enterprise-managed settings apply. If your operating system cannot enforce the requested policy, the sandboxed shell fails with an error rather than running without a sandbox. Get started Local sandboxing is off by default. Open the app settings, select your project, and turn on Sandbox new sessions under "Sandbox". This applies to new sessions in the project, not sessions already running. Changes to filesystem, network, and credential settings apply to new sessions or when an

GitHub Copilot code review now offers additional personal configurations to an expanded set of Copilot plans and an enterprise-level default setting. These improvements are now generally available:

• A dedicated personal settings page for automatic review and your default review effort
• An enterprise-wide default review effort setting for organization-owned repositories ⚙️ Manage your personal review settings Previously, personal Copilot code review settings were available only with Copilot Pro, Pro+, and Max on the "Copilot features" page. They covered a single automatic review setting without separate controls for draft pull requests or new pushes. Under your profile → Copilot settings , a dedicated "code review" page under Copilot is now available on every Copilot plan, including Copilot Business and Copilot Enterprise. From this page you can:
• Turn on automatic reviews from Copilot, which will trigger when you create a pull request, coauthor a pull request, or move a pull request out of draft state.
• Turn on automatic review for new pushes and for draft pull requests you create or coauthor.
• Set your default review effort, shown today as Lite or Balanced .

OpenAI's GPT-6 family is expanding in GitHub Copilot with two additional models: GPT-6 Sol, and GPT-6 Luna. Joining the previously released GPT-6 Astra, these new options let you select the model that best fits your task, whether that's everyday agentic coding or fast, cost-efficient assistance.

• GPT-6 Sol: A balanced model for interactive and agentic coding. A strong all-round choice for development tasks that benefit from careful, multistep validation.
• GPT-6 Luna: A lightweight, cost-efficient model for smaller, faster tasks and the lowest-cost option in the GPT-6 family. These models are billed under usage-based billing. See pricing for GitHub Copilot models and requests for details. Availability in GitHub Copilot GPT-6 Sol is available to Copilot Pro+, Max, Business, and Enterprise plans. GPT-6 Luna is available to Copilot Pro, Pro+, Max, Business, and Enterprise plans. You can select the models in the model picker in:
• Visual Studio Code
• Visual Studio
• Copilot CLI
• GitHub Copilot cloud agent
• GitHub Copilot app
• github.com
• GitHub Mobile iOS and Android
• JetBrains
• Xcode
• Eclipse Rollout will be gradual. Check back soon if you don't see the models yet.

Claude Opus 5.5, Anthropic's newest Opus model, is now available in GitHub Copilot. You can use it for agentic coding, long-running agentic tasks, and knowledge work. In early testing, Opus 5.5 resolved tasks comparably to Claude Opus 5 while using significantly fewer steps and tokens. It also quickly recovered from errors in multistep tasks. Claude Opus 5.5 watermarks its text outputs. The watermark doesn't change the meaning, quality, or readability of outputs, nor does it add any tokens or cost. To learn more visit Anthropics's How Claude's text watermark works . This model is billed at provider list pricing under usage-based billing. See Models and pricing for GitHub Copilot for details. Availability in GitHub Copilot Claude Opus 5.5 is available to Copilot Pro+, Max, Business, and Enterprise users. You can select the model in the model picker in:

• Visual Studio Code
• Visual Studio
• Copilot CLI
• GitHub Copilot coding agent
• GitHub Copilot app
• github.com
• GitHub Mobile on iOS and Android
• JetBrains IDEs
• Xcode
• Eclipse Rollout will be gradual. Check back soon if you don't see it yet. Enabling access

C++ code intelligence in GitHub Copilot CLI is now faster with support for whole codebase indexing. C++ repositories can contain millions of lines of code across deeply connected source files and headers. Without a reusable index, code-intelligence requests may need to rediscover project information as you navigate, making it slower to find a definition, locate references, or understand unfamiliar code. Whole codebase indexing (WCI) creates a persistent index of symbols across your C++ project, including files that aren't currently open. The Microsoft C++ Language Server uses your project's compilation information to resolve types, symbols, includes, and relationships between files. WCI makes that symbol information available for reuse instead of rediscovering it for each request. You spend less time waiting for definitions, references, implementations, and symbol search results, and more time reviewing, understanding, and changing code. Configure indexing Whole codebase indexing is enabled by default because its persistent symbol index helps the Microsoft C++ Language Server efficiently understand relationships across your entire project. The language server loads the index when