GitHub Copilot

Gemini 4 Argon, Google's newest frontier model, is now generally available in GitHub Copilot. It is designed for complex coding, agentic, and reasoning tasks. In early testing, Gemini 4 Argon solved more tasks than previous Gemini models on every coding benchmark, with its largest gains in Copilot CLI. It also thoroughly checks its work, testing edge cases before it finishes. 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 Gemini 4 Argon 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
• 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 Gemini 4 Argon 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 this model.

Enterprise administrators can now use telemetry in managed settings to attribute GitHub Copilot activity to a user without collecting their prompts, responses, or tool content. The telemetry.capture.identity setting adds three attributes to OpenTelemetry (OTel) data:

• user.name : The authenticated Copilot account name, currently the GitHub login.
• process.user.name : The local operating-system account.
• host.name : The local machine name. Identity capture is off by default and remains separate from the existing pseudonymous user identifier. Fine-grained capture controls are available in Copilot CLI, the GitHub Copilot app, and VS Code sessions using Agent Host. Administrators can also independently control five additional capture classes:
• prompts : User, system, and developer prompts and supported input context.
• responses : Assistant responses and supported reasoning content.
• toolArguments : Raw tool arguments, commands, tool schemas, and identifiers for tools, MCP servers, plugins, and hooks.
• toolOutput : Tool results and execution-error details.
• policyDetail : Raw policy details such as sandbox filesystem paths.

This update brings more control over default models and MCP server in GitHub Copilot for JetBrains. It also makes diagnostics easier to address, improves chat navigation and account controls, and strengthens reliability across agent sessions, customizations, and worktrees. What's new Enterprise-managed default models Enterprise administrators can now use managed settings to choose any available Copilot agent model as the default for new conversations. This gives organizations more control over the starting model while still preserving an explicit model picker choice. Faster fixes from diagnostics Diagnostic intention menus now include a Fix action that opens inline chat and asks Copilot to repair the issue. The action uses agent mode when it is available and ask mode otherwise, helping you move from a reported problem to a proposed fix with fewer steps. More control over MCP server startup A new MCP setting lets you disable automatic server startup for Copilot and Claude, giving you more control over when configured tools become active. User experience enhancements This release makes everyday chat, account, and navigation workflows clearer:

This week's updates make Copilot easier to use across accounts and environments, with more control over what agents can access and how you manage their work. GitHub Copilot

• Claude Haiku 5.5 is available to Copilot Pro, Pro+, Max, Business, and Enterprise users.
• Limit agents' access to files, networks, and credentials with local sandboxing, now generally available in Copilot CLI, the Copilot app, and VS Code sessions using Agent Host. This is included with Copilot at no extra cost. Learn more about local sandboxing . GitHub Copilot app The Copilot app now lets you use separate GitHub accounts for your Copilot license and your repositories. For example, use an enterprise-provided Copilot license while accessing repositories through another account. Download the Copilot app . GitHub Copilot CLI GitHub Copilot CLI makes it easier to choose a local model without leaving your existing workflow. Use /model to discover supported models from a running local Ollama instance, alongside your configured models and cloud models provided by GitHub Copilot. Discover local models in GitHub Copilot CLI . GitHub Copilot in VS Code (1.141 release)

This release adds new billing and license controls for Copilot code review admins:

• Billing: Organization owners can bill Copilot code reviews from members with a Copilot license to the organization's cost center instead of using up those members' Copilot quotas.
• Review request controls: Organization owners and repository admins can control whether people with external licenses can request a review. 💳 Choose how members with a Copilot license are billed By default, Copilot code review bills requests associated with members who have a Copilot license to that member's own Copilot entitlement. Organization owners can now choose to bill the organization that owns the repository instead in order to avoid consuming or exhausting member quotas. The Choose how members with a Copilot license are billed setting has two options:
• Member (default): Bills the member's own Copilot entitlement. If the member's quota is exhausted, the code review fails.
• Organization : Bills the organization that owns the repository. This requires AI Credits paid usage to be enabled for the organization, and you can optionally set a budget.

GitHub Copilot CLI makes it easier to choose a local model without leaving your existing workflow. Starting in CLI version 1.0.94-0, use /model to discover supported models from a running local Ollama instance, alongside your configured models and cloud models provided by GitHub Copilot. Discovery doesn't automatically add models. Choose a discovered model, review its provider and endpoint, then confirm Add and use for this session or Add without switching . You can use the model in your current session without restarting the CLI. Ollama and the model must already be installed—this flow doesn't install a runtime or download models. Models must support tool calling and streaming. Provider connection failures appear in the picker with an explanation, helping you identify what needs attention. This CLI update builds on the same idea as the GitHub Copilot app's provider experience: choose the model that fits your work. In the app, add a supported provider in Settings > Model providers .

Local sandboxing for GitHub Copilot is now generally available in GitHub Copilot CLI, the GitHub Copilot app, and VS Code sessions using Agent Host. Local sandboxes give developers a secure execution boundary for agentic workflows on their own machines. Tools and commands initiated by Copilot run with restricted access to the filesystem, network, credentials, and other system capabilities, based on policies defined by the developer or their organization. Local sandboxing is powered by Microsoft eXecution Container (MXC) , which translates a common sandbox policy into native operating-system controls across Windows, macOS, and Linux. With local sandboxing, developers and organizations can:

• Limit the files and directories that agent-run commands can read or modify.
• Control access to the internet, local networks, Git credentials, and GitHub CLI credentials.
• Apply sandboxing to local tools and services, including local MCP and language servers where supported.
• Use enterprise-managed settings to require sandboxing and enforce policies that developers cannot weaken.
• Adopt more autonomous agent workflows while maintaining clear boundaries around what Copilot can access.

Secret protection should keep pace with the way you build software, whether you write code yourself or work with an AI agent. With our new purpose-built model, we're bringing context-aware detection into more developer workflows to help you catch secrets before they're exposed. What's new Today, we're sharing plans for AI secret detection across secret scanning alerts, push protection, and GitHub Copilot security reviews. These features leverage GitHub's fine-tuned model for secret detection. It reads surrounding code to identify likely credentials, including passwords without a recognizable token format, without generating code or prose. Model availability:

• Customers with AI-detected Password alerts have automatically been upgraded to the new model.
• AI-detected secrets in push protection is available in private preview.
• AI-based secret scanning with the GitHub Copilot /security-review command for the Copilot CLI and Copilot app available soon in private preview. Billing notice and availability

Claude Haiku 5.5, Anthropic's newest lightweight model, is now generally available in GitHub Copilot. It is designed for fast, high-volume work like subagents, quick edits, and terminal tasks. In early testing, Haiku 5.5 matched Claude Sonnet 5 on many coding tasks while using significantly fewer tokens and steps. 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 Haiku 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 cloud 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 Haiku 5.5 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 this model. Learn more

If your Copilot usage metrics have shown agent activity or agent lines of code falling while Copilot usage kept growing, we've found the cause, and a fix is rolling out to each IDE. Several IDEs recently moved Copilot agent sessions to the Copilot SDK. Those sessions didn't identify which IDE they came from, so usage metrics couldn't attribute them correctly. Most of that activity was left out of reports, and some was counted as Copilot CLI activity. Only IDE versions that use the Copilot SDK for agent mode are affected. Developers on earlier versions are still counted. The fix is available now in Visual Studio Code. Other IDEs will receive it in upcoming releases, which we expect to finish rolling out by November 2026. Once developers update, their agent activity is counted again in the Copilot usage metrics dashboard and API. Update your IDE Agent activity is counted again once developers are on these versions. If your developers are on an affected version, update as soon as the fixed version is available, because their activity can't be recovered later. If you manage IDE versions centrally and rely on agent metrics, you can plan your rollout to move developers directly to these

This week, put Copilot to work with new models, reusable workflows and desktop app automation, plus Azure canvases and VS Code improvements. GitHub Copilot

• Claude Sonnet 5.5 is available to Copilot Pro, Pro+, Max, Business, and Enterprise users.
• GPT-6.1 Sol is available to Copilot Pro+, Max, Business, and Enterprise users.
• Let Copilot select and coordinate models for your task with HydraFusion , a research preview now available in VS Code and the GitHub Copilot app alongside Copilot CLI. Clearer, more frequent progress updates help you follow its work.
• Save a process for Copilot to follow again. With dynamic workflows, you can ask Copilot to run release checks, investigate failures, and pause for your review, then reuse that workflow next time. Describe the steps and ask Copilot to build it, or write it yourself in code. Now in public preview in Copilot CLI, the Copilot app, and the Copilot SDK. Learn more about dynamic workflows .
• Automate tasks in desktop apps with computer use in Copilot CLI and the Copilot app, now in public preview on macOS and Windows. Copilot can navigate apps, edit content, and move information across workflows, even in software without an API or

As of today, October 2, 2026, we have deprecated the following models across all GitHub Copilot experiences (including Copilot Chat, inline edits, ask and agent modes, and code completions). Model Deprecation date Suggested alternative Gemini 3.5 Flash 2026-10-02 Gemini 3.8 Flash Gemini 3.6 Flash 2026-10-02 Gemini 3.8 Flash Kimi K2.7 Code 2026-10-02 Kimi K3 Claude Opus 4.7 2026-10-02 Claude Opus 5.5 Please update your workflows and integrations to use supported models. Copilot Enterprise administrators may need to enable access to alternative models 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 deprecated models. 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.

You can now request a GitHub Copilot code review through the REST and GraphQL APIs and set the review effort level for each request. Balanced is also now the default review effort level. These changes are generally available to Copilot Pro, Pro+, Max, Business, and Enterprise plans. 🔌 Request Copilot code review with the API You can now request a review from Copilot using the supported REST and GraphQL APIs. When you make a request, you can optionally set the review effort level for that review. This lets you bring Copilot code review into your own scripts, workflows, and internal tools, so reviews can start from the systems your team already uses. ⚖️ Balanced is now the default review effort level As announced on August 28, 2026, the Default review effort level now uses Balanced for new and existing repositories and organizations using Copilot code review. If you explicitly selected Lite in your settings, that selection was respected. This change took effect September 28, 2026. ⚙️ Configure your review effort level If you prefer Lite or want to try out the options available to you, you can change the review effort level from Default to Lite at the level you manage:

Dynamic workflows are now available in Copilot CLI, the GitHub Copilot app, and the GitHub Copilot SDK. These let you define an orchestration in code to get the reliability and observability that complex, multi-agent work demands. What is a dynamic workflow? A dynamic workflow is a program that defines how a task is carried out. It combines automated steps with the work of one or more agents, and those steps can run one after another, in parallel, or both. The steps, when to involve agents, and how to use their results are all defined in code, while agents handle the parts that need analysis or judgment. The program itself lives inside a GitHub Copilot extension, which means it has access to Copilot's powerful extensibility APIs. For example, you could use a dynamic workflow to investigate a service incident: collect logs and telemetry, assign independent agents to analyze different systems, and combine their structured findings into a timeline and root-cause report. The same steps run every time. Dynamic workflows can:

• Run commands, use tools, or call other services.
• Divide a goal into tasks and run independent tasks in parallel.

This changelog covers VS Code v1.136 through v1.140 , shipped throughout September 2026. September's releases streamline agent-driven development from implementation through pull request merge. Automations handle repeatable tasks, agent merge helps land changes, and improved session management keeps work organized. Agents are also more flexible across workspaces, Dev Containers, and apps, while GitHub context helps you collaborate without breaking your flow. Agents window Agents window updates made it easier to automate work, manage sessions, and move changes from implementation to merge.

• Let HydraFusion coordinate models: If eligible, enable preview features and select HydraFusion in the model picker to choose models and workflows for your coding tasks automatically. This feature is in research preview.

Schedule recurring work: Use automations to run tasks on an hourly, daily, or weekly schedule or run them on demand. Start from a template or use your own prompt. This feature is in preview.