ReleaseBytes
github GitHub Changelog ·

GitHub Copilot for JetBrains: Enhanced Config & Model Management

aiinfraengineer
feature patch

GitHub Copilot for JetBrains has been updated with improved OpenTelemetry configuration and model management, offering greater control over agent workflows and cost. This release introduces new options for token limits, disabling/enabling models, and integrating MCP servers and custom agents in Claude flows. The enhancements benefit engineers and architects managing observability, cost control, and custom IDE workflows.

  • →OpenTelemetry export for agent workflows
  • →MCP servers and custom agents in Claude agent flows
  • →Granular control over model behavior and costs
  • →Expanded Copilot CLI session capabilities
  • →AI credit consumption display for enterprise
Features (2) ›
  • OpenTelemetry export for agent workflows

    Configure OpenTelemetry export settings for agent workflows to align plugin behavior with organizational observability requirements. Settings can be adjusted under Settings > Tools > GitHub Copilot > Chat.

  • MCP servers and custom agents in Claude agent flows

    Utilize MCP servers and custom agents directly within Claude agent flows for enhanced flexibility with specialized tools, custom instructions, and team-specific workflows.

Enhancements (3) ›
  • Granular control over model behavior and costs

    Set default token limits (maxInputToken, maxOutputToken) for BYOK and custom endpoints, and enable/disable built-in Copilot models. These features aid in managing costs and model governance.

  • Expanded Copilot CLI session capabilities

    Copilot CLI sessions now include support for forks, the /rubber-duck command, and display a todo list within the harness for better work breakdown and progress tracking.

  • User experience improvements across chat and model selection

    Enhancements include improved consistency in model/action pickers, better usability in customization flows, clearer session prompts, refined inline chat layout, faster MCP diagnostics, and improved URL rendering in the Copilot CLI harness.

Notes (1) ›
  • AI credit consumption display for enterprise

    Enterprise users without a user-level budget configured will now see the number of AI credits consumed. Refer to the documentation for details on user-level budgets.

Read the original announcement →

https://github.blog/changelog/2026-07-27-github-copilot-for-jetbrains-adds-improvved-opentelemetry-configuration-and-model-management

Related releases