
GitHub has announced the general availability of Copilot code review features, including agent skills and MCP server integration, for Pro, Business, and Enterprise users. These features, previously in public preview, allow teams to incorporate their internal tools and coding standards into the code review process. By connecting to third-party platforms, Copilot can provide additional context during reviews. This development enhances the precision and relevance of AI-assisted code reviews, making them more tailored to specific team needs.
Read original
© GitHub ChangelogGitHub is making it easier for Business and Enterprise users to access new Copilot models by implementing a default enablement policy. This change means that new models will automatically be available unless administrators decide to opt out, reducing the need for manual activation. The policy will be effective from August 26, giving organizations a 28-day period to adjust their settings if they prefer manual control. This approach minimizes the administrative workload and ensures users can quickly benefit from the latest AI advancements, while still allowing organizations to maintain oversight by opting out if necessary.
© GitHub ChangelogThe latest update to CodeQL, version 2.26.1, brings significant improvements to the static analysis engine used in GitHub code scanning. This release enhances framework coverage for languages like Go, Java/Kotlin, and JavaScript/TypeScript, while also reducing false positives in Rust analysis. Notably, it introduces better modeling for Go's structured logging and recognizes Angular decorators in JavaScript/TypeScript. These updates mean developers can expect more accurate security issue detection and remediation, making CodeQL a more reliable tool for maintaining secure codebases.
© GitHub ChangelogGitHub has enhanced its Copilot usage metrics API, now offering more granular insights into individual user activity within the Copilot app. Previously, Copilot app usage was only visible at an enterprise or organization level, but now it includes detailed breakdowns by feature, model, and language. This allows enterprise owners and billing managers to better understand how the Copilot app is being used, who is using it, and what it produces. The update makes it easier to compare Copilot app activity with other surfaces like IDEs and coding agents, providing a comprehensive view of AI-assisted coding within organizations.
© Matt WolfeAnthropic has introduced a sandboxed in-app browser for Claude Code on desktop, enhancing its research and debugging capabilities.
The latest update to Claude Code, v2.1.218, introduces several improvements and fixes that enhance user experience and functionality. Notably, the /code-review feature now operates as a background subagent, preventing conversation clutter and improving workflow efficiency. The update also addresses various bugs, such as Windows path corruption and session stability issues, ensuring smoother operations. These changes make Claude Code more robust and user-friendly, particularly for developers relying on its tools for code review and management.
© Lev SelectorGoogle has launched TurboQuant, a new tool for vector compression.