GitHub Copilot

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. Mention @GitHub to investigate problems, plan work, and make changes your team can follow and guide together. GitHub Copilot app
• The Customize tab is now generally available, bringing MCP servers, plugins, skills, and canvases together in one place.
• Turn Azure DevOps issues and pull requests into Copilot sessions from the Customize tab.
• Work in your Linux environment with experimental support for Windows Subsystem for Linux (WSL).
• Split and move any tab to keep related work side by side.
• Send any browser preview straight to your external browser from the tab's context menu. Try the Copilot app . GitHub Copilot CLI
• Start every new session with your preferred execution and permission modes using defaultMode and defaultPermissionMode .
• Manage plugins, MCP servers, and skills more easily with new experiences in /plugin , /mcp , and /skills .

August 2026 brought more control over how GitHub Copilot reasons, which models you use, how teams share specialized agents, and when you ask for a code review. Highlights Here's what's new with GitHub Copilot in Visual Studio 2026. Check the Insiders channel for the latest:

• Organization-level custom agents : GitHub organization and enterprise owners can publish custom agents for use across repositories in their organization. Visual Studio automatically detects these agents and shows both their descriptions and organization source in the agent picker. This functionality requires a GitHub organization.
• Access your Copilot usage : Open the context window from the Copilot prompt box, then select View all Copilot usage to see your full plan details. Refined notifications also make it clearer when you are approaching a limit and what options are available.
• Adjust model thinking effort to match your task : Supported models now offer Low , Medium , and High thinking effort controls. Use lower effort for straightforward work or higher effort for complex debugging, algorithms, and architecture decisions. This enables you to balance reasoning depth with token usage.

Copilot code review can now review two types of pull requests it didn't cover before:

• Reviews requested automatically on pull requests authored by bots, including Copilot cloud agent
• Very large pull requests Additionally, you can now submit the reason for why you're resolving a particular Copilot code review comment. 🤖 Expanded capabilities Pull requests authored by bots When a pull request is authored by a bot and requested automatically, there's no Copilot-licensed account to attribute the review to. With the "Allow members without a Copilot license to use Copilot code review in GitHub.com" policy enabled, Copilot code review can now review these pull requests and bill the usage directly to your organization. To learn more, see Copilot code review without a Copilot license . Copilot cloud agent pull requests Previously, when Copilot code review was automatically requested due to automatic review settings on pull requests authored by Copilot cloud agent, Copilot code review would fall back to a limited experience. Copilot code review can now give pull requests opened by Copilot cloud agent a full agentic review. Large pull requests

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. Previously unconfigured and new generally available models will inherit the global policy state. Administrators can make durable decisions for individual models at their discretion. Open-weight models and any models that require data retention are disabled by default. What's changing Once the policy takes effect for your organization or enterprise:

• Models you haven't previously configured will change their state to "Delegate to default policy", and they'll begin following your policy setting. If your policy is enabled — which is the default — those models will become available to your users.
• "Delegate to default policy" is a live, dynamic state that always tracks your policy. You can change the policy at any time, and all applicable models follow that state change.

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. The marketplace must still be permitted by the effective strictKnownMarketplaces allowlist. This capability is generally available with Copilot Business and Copilot Enterprise in the GitHub Copilot app, Copilot CLI, and Visual Studio Code. Learn more in our docs about enterprise managed settings , or join the discussion in the GitHub Community . client apps copilot enterprise management tools Share Copied Shared Related Posts Aug.26 Improvement Global model policy generally available copilot enterprise management tools ... +1 Aug.26 Release GitHub Apps can now access enterprise billing data account management ecosystem & accessibility enterprise management tools ... +2 Aug.25 Release GitHub Copilot app Customize tab is generally available copilot Aug.21 Release The new GitHub Copilot experience in Slack collaboration tools copilot ... +1 Aug.21 Release

GitHub Copilot is more useful when it works with the tools, knowledge, and workflows your team already relies on. The new Customize tab in the GitHub Copilot app brings MCP servers, plugins, skills, and canvases together in one place. Explore featured customizations, browse by type, and find new ways to tailor Copilot to how you and your team work. With the Customize tab, you can:

• Discover more ways to customize Copilot across MCP servers, plugins, skills, and canvases.
• Start with featured customizations selected from each section.
• Find MCP servers faster by exploring trending options and browsing by category. Bring the tools your team uses into Copilot Featured canvases help you move from understanding work to acting on it while keeping the relevant context visible. Delegate backlog work from Azure DevOps Triage issues, prioritize backlogs, assign follow-ups, and hand work to Copilot to investigate, implement, or prepare for review. Explore every type of customization The Featured view brings selected customizations from across the GitHub Copilot app into one place, giving you a simpler starting point when you do not already know which MCP server, plugin, skill, or canvas

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. Built-in JetBrains MCP server support The built-in JetBrains MCP server support is now in public preview. This makes it easier to expose IDE capabilities through MCP-driven agent workflows without relying only on external server setup. Better post-update release discovery After you update the Copilot for JetBrains plugin, a What's New tab will open so you can immediately see what changed. This helps you adopt new capabilities faster and reduces guesswork after each upgrade. Expanded Copilot harness integrations You can use Copilot harness /review integrations directly in JetBrains, reducing context switching when you want review guidance during development. User experience enhancements This release improves daily interaction quality across model controls, debug workflows, long outputs, and workspace customizations.

Turn a Microsoft Teams discussion into a collaborative agent session everyone can see and help direct. Mention @GitHub in a channel, thread, or direct message to start a GitHub Copilot cloud agent session. Anyone in the conversation can ask questions, add context, and help plan or steer the work. Participants with write access to the repository can trigger Copilot to make changes. Turn meeting decisions into ready work When a meeting produces an action item, hand it to Copilot during a discussion or in the meeting chat before it ends. For example, ask Copilot to investigate a problem while you discuss it in your team's standup and start resolving it before the meeting ends. Everyone can see the agent's investigation and direct it further if needed. Editor's note (August 21, 2026): Updated the language to align with Teams terminology. Continue work across GitHub Copilot surfaces Start a task from Teams and let Copilot work asynchronously in a secure cloud sandbox. Follow progress in the channel thread, then continue working with the agent-generated artifacts from your terminal, the GitHub Copilot app, or your preferred IDE. For more information, see our documentation about cloud

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. GitHub is also a launch partner for Slack Code, a new type of channel designed for agents. Bringing Copilot into the flow of conversation helps your team turn shared intent into shippable work. What you can now do with @GitHub Mention @GitHub in a direct message, channel, or thread to start an agent session. Copilot can use the conversation and permitted GitHub context to:

• Answer questions about your code and GitHub activity.
• Triage bug reports, update existing issues, or create and label new issues.
• Investigate failures, implement changes, and validate its work in a secure cloud sandbox.
• Open a pull request and provide a link to the conversation for review. GitHub Copilot continues working asynchronously while you're in a meeting, commuting, or focused on something else. You can direct the session from Slack as it works, then continue from the pull request in your terminal, the

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. Enterprise-managed plugin governance Administrators can manage Copilot plugins and their marketplaces in JetBrains IDEs. The supported settings provide three controls:

• Enabled plugins: Use enabledPlugins to require a plugin to be enabled or disabled.
• Additional marketplaces: Use extraKnownMarketplaces to make approved plugin sources available.
• Restricted marketplaces: Use strictKnownMarketplaces to limit installation to approved sources. MCP server allowlist Administrators can use allowedMcpServers and deniedMcpServers to centrally control which MCP servers developers can connect to from GitHub Copilot for JetBrains. This brings centrally managed MCP governance into JetBrains IDEs and prevents connections to servers outside the enterprise allowlist. Managed OpenTelemetry

Grok 4.6, xAI's latest reasoning model, is now rolling out in GitHub Copilot. It is designed for agentic coding and complex multi-step workflows. In our internal testing, Grok 4.6 showed strong results across terminal-based coding tasks in Visual Studio Code and Copilot CLI. It performed especially well on longer-horizon tasks requiring sustained reasoning and tool use, making it a strong fit for complex coding workflows. 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 Grok 4.6 will be available to Copilot Pro, Pro+, Max, Business, and Enterprise SKUs. You'll be able to select the model in the model picker in:

• Visual Studio Code
• Visual Studio
• Copilot CLI
• GitHub Copilot cloud agent
• GitHub Copilot app
• JetBrains
• 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 must enable the Grok 4.6 policy in Copilot settings. The policy is off by default. Learn more

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.
• MAI-Code-1.1-Flash is rolling out in GitHub Copilot with native image understanding and improvements to coding quality, instruction following, tool use, and performance.
• Build a plugin once and use it across compatible agent tools with Agent Plugins 1.0, now generally available in VS Code, Copilot CLI, the GitHub Copilot SDK, and the GitHub Copilot app. GitHub Copilot app
• Installed plugins are now easier to manage. See each plugin's current version, update plugins individually, or update them all at once from Customize or Settings .
• Talk through an agent's question before answering by opening it in a side chat while the original question waits for your response. Try the Copilot app . GitHub Copilot CLI
• Manage all your subagents and their tasks in /tasks .
• Queue prompts, shell commands, and supported slash commands while an agent turn is running.

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. The model also delivers improvements in code quality, final-output presentation, codebase research, and verification during complex coding tasks. 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 Gemini 3.7 Flash will be available to Copilot Pro, Pro+, Max, Business, and Enterprise users. You'll be able to select the model in the model picker in:

• Visual Studio Code
• Visual Studio
• Copilot CLI
• GitHub Copilot cloud agent
• GitHub Copilot app
• JetBrains
• 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 must enable the Gemini 3.7 Flash Preview policy in Copilot settings before anyone in their organization can select it. Learn more

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. Agent Plugins 1.0 is an open standard that packages agent skills and MCP servers into one installable plugin that is governed independently of any single vendor. Publishing a plugin for several agents was already possible, but it cost you duplication. A plugin can bundle a skill with an MCP server, such as a deployment runbook and its tool integration. While the skill and the server underneath were the same for every client, the packaging around them wasn't, so you maintained a separate manifest and directory layout for each one. Support is generally available in VS Code, Copilot CLI, the GitHub Copilot SDK, and the GitHub Copilot app, on all Copilot plans. What you can do

• Install spec plugins from a marketplace. You can find plugins in the Awesome Copilot marketplace , available by default in VS Code, Copilot CLI, and the Copilot app.

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