JetBrains IDE に Claude エージェントプロバイダーのプレビューと新機能を追加

This update adds support for organization and enterprise agents from GitHub, lets you queue and steer messages in Copilot CLI sessions, introduces a new agent debug logs summary view, and brings Claude as agent provider into public preview in GitHub Copilot for JetBrains IDEs.

It also includes model picker enhancements, a per-turn AI credits indicator, and a set of user experience and reliability improvements. Cloud agent is now generally available.

New features

Support for organization and enterprise agents from GitHub

You can now use custom agents defined at the GitHub organization and enterprise level directly inside JetBrains IDEs. Administrators can publish a curated set of agents that are automatically available to everyone in the organization or enterprise. This makes it easier to share, standardize, and govern agent workflows across your team.

In order to use it:

Administrators define agents in GitHub: An organization or enterprise admin creates custom agents and publishes them so they are available to members. Once published, these agents are automatically distributed to all eligible users.

Open the agent picker in Copilot Chat: In your JetBrains IDE, open the Copilot Chat panel and click the agent picker.

Select an organization or enterprise agent: Available agents are grouped and you can choose the one that fits your task.

Start working: The selected agent runs with the configuration defined by your admin, helping ensure consistent behavior and standards across your team.

For more details, see Preparing to use custom agents in your organization and Preparing to use custom agents in your enterprise.

Send messages while a request is running (CLI)

When working on longer tasks in Copilot CLI sessions, you had to wait for a response to complete or previously cancel it. Now you can send follow-up messages while a request is still running.

While a request is in progress, the Send button changes to a dropdown with three options:

Add to Queue: Queue a message to be processed after the current response completes.

Steer with Message: Tell the current request to yield once the active tool execution finishes, then process your new message immediately. Use this to redirect the agent when it’s heading in the wrong direction.

Stop and Send: Stop the current turn and immediately send your new message.

Agent debug logs summary view

We’ve enhanced the Agent Debug panel with a new logs summary view that gives you a consolidated overview of agent activity, making it easier to review and debug session behavior.

You can select the session name from the session list to navigate to the summary view. It will show aggregate stats for the session.

Claude as agent provider in public preview

Claude as agent provider is now available in public preview, giving you more flexibility to pick the agent that best fits your task, all without leaving your JetBrains IDE.

To use it, first install the Claude Code CLI on your machine. Then go to Settings > Tools > GitHub Copilot > Chat and set the Claude Code CLI path. Once configured, select Claude from the agent picker in the Copilot Chat panel to start a session.

Note: The Claude agent currently runs in bypass permissions mode, so all file edits and tool calls are automatically approved. Configurable permissions are coming in a future release. Also, if you’re a Copilot Business or Copilot Enterprise subscriber, an administrator will need to enable the Editor preview features policy before you can use this feature.

Model picker enhancements

We’ve made several improvements to the model picker:

/models slash command: Open the model picker directly, with support for both Copilot CLI and Claude agent.

Larger context window selection: Select a larger context window directly from the model picker, giving you more room for context-heavy tasks.

Recently used models: The local agent model picker now includes a recently used model section, so you can quickly select the models you use the most.

Per-turn AI credits indicator

Local, CLI, and Claude agent sessions now display a per-turn AI credits indicator, giving you clearer visibility into how many AI credits each turn consumes as you work.

To learn more about how GitHub AI Credits work, see Usage-based billing for individuals and Usage-based billing for organizations and enterprises.

User experience

We have made several refinements to improve day-to-day workflows and responsiveness across JetBrains IDEs:

Improved chat input layout for better reliability

Improved the inline chat experience by ensuring state resets when closed during a response

Improved code block rendering performance

Improved next edit suggestions by adding richer code diagnostic information for better suggestions

Bug fixes

This release also includes important reliability and stability fixes:

Fixed an issue where diff views would open for every agent edit

Fixed an issue that could cause no completion models to be shown in settings

Fixed multiple UI freeze issues

Availability updates

Cloud agent is now generally available (no longer behind the Editor Preview feature flag).

Try it out

We encourage you to try out the latest version of the GitHub Copilot plugin and share your feedback. Your input is invaluable in helping us refine and improve the product.

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.

Community feedback: Share your thoughts in the GitHub Copilot for JetBrains IDEs issues, or take our short survey.

The post New features and Claude as agent provider preview in JetBrains IDEs appeared first on The GitHub Blog.