Claude Code has released version 2.1.178, bringing a host of improvements and bug fixes. Key updates include a new syntax for permission rules that allows better control over tool parameters, and enhancements to the auto mode that ensure subagent actions are evaluated before execution. The update also improves error messaging and workflow prompts, making the tool more user-friendly. These changes aim to enhance the overall functionality and reliability of Claude Code for developers.
Read originalThe latest update to Claude Code, version 2.1.175, introduces a new managed setting called enforceAvailableModels. This feature ensures that the Default model selection is constrained by an allowlist, preventing users or projects from expanding the list of available models beyond what is managed. This change enhances control over model usage, ensuring that only approved models are utilized, which could be crucial for maintaining consistency and compliance in development environments.
Claude Code's latest update introduces the Claude Fable 5, a Mythos-class model now safe for general use. This model surpasses previous offerings in capability, marking a significant step forward for developers using Claude Code. Additionally, the update resolves an issue with session transcripts not saving when launched from certain environments. This release enhances both the power and reliability of the Claude Code platform, offering developers a more robust toolset for their projects.
© GitHub ChangelogGitHub has enhanced its Copilot usage metrics by incorporating server-side telemetry, providing a more complete picture of active users. Previously, reports relied solely on client-side data, which could miss users due to network or configuration issues. Now, server-side data fills these gaps, ensuring that all active users are counted, even if client telemetry fails. While this update improves overall user counts, detailed interaction data remains limited to client-side telemetry. This marks a significant step towards more accurate and reliable usage reporting for enterprises.
© GitHub ChangelogGitHub's Copilot code review has introduced new features that enhance customization and control for developers. Teams can now configure runner types at the organization level, allowing a single setting to apply across all repositories, which simplifies the setup process. The removal of the character limit on custom instructions provides more room for detailed guidance, while content exclusion settings ensure that Copilot respects organizational boundaries. These updates make Copilot code review more adaptable to specific team needs, offering greater flexibility and precision in code review processes.