Claude Code has released version 2.1.175, featuring a new setting called enforceAvailableModels. This setting restricts the Default model to an allowlist, ensuring that only approved models are used. Users and projects can no longer expand the list of available models, which helps maintain consistency and compliance. This update is significant for developers who need to manage model usage tightly.
Read originalThe latest update to Claude Code, version 2.1.178, introduces several enhancements and fixes that improve the tool's usability and functionality. Notably, the update refines permission rules with a new syntax for tool parameters, ensuring better control over subagent actions. It also enhances the auto mode by evaluating subagent spawns before launch, closing potential security gaps. Additionally, improvements in error messaging and workflow prompts make the tool more intuitive for users. These changes collectively enhance the robustness and user experience of Claude Code, making it a more reliable tool for developers.
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.
The latest update to Claude Code, v2.1.172, introduces significant improvements in agent functionality and user experience. Sub-agents can now spawn their own sub-agents up to five levels deep, enhancing automation capabilities. The update also addresses several bugs, such as session handling issues and model picker errors, ensuring smoother operation. Additionally, performance enhancements reduce idle CPU usage and improve tool loading in Chrome. These changes make Claude Code more robust and efficient for developers working with complex agent systems.
© 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.
© The AI Daily BriefOpenAI has launched a new 'Sites' feature in Codex, enabling the creation of interactive, shareable documents.