v2.1.112

2025-02-22 · Source: Claude Code Changelog · Field: Technology & Digital — Software Development & Engineering, Artificial Intelligence & Machine Learning, Cybersecurity & Data Privacy · Depth: Intermediate, long

Summary

The Claude Code CLI has received multiple updates across versions 2.1.105 through 2.1.114, focusing on stability, security, and user experience. Key enhancements include fixing a crash in the permission dialog (v2.1.114), changing the CLI to spawn a native Claude Code binary for improved performance, and adding `sandbox.network.deniedDomains` for granular network control (v2.1.113). Version 2.1.111 introduced Claude Opus 4.7 xhigh effort level, auto mode for Max subscribers, and new `/ultrareview` and `/less-permission-prompts` skills. Security improvements across versions include stricter handling of dangerous removal targets on macOS and enhanced Bash deny rules. Numerous bug fixes address issues ranging from UI rendering and command-line behavior to plugin management and remote control client functionality.

Key takeaway

For NLP Engineers or CTOs evaluating or deploying Claude Code, these updates signify a commitment to robust security and enhanced productivity. The introduction of Opus 4.7 xhigh and auto mode, alongside `/ultrareview`, offers more powerful and efficient AI-driven development workflows. You should review the new security features, especially `Bash` deny rules and `deniedDomains` settings, to ensure your deployments align with organizational security policies and leverage the new `/effort` and `/ultrareview` commands for optimized performance and code quality.

Key insights

Recent Claude Code CLI updates enhance security, performance, and user experience through new features and bug fixes.

Principles

• Prioritize security by hardening sandbox rules and permission handling.
• Improve user workflow through intuitive command-line interactions.

Method

The CLI development process involves iterative bug fixing, security hardening, and feature additions based on user feedback and performance optimization goals.

In practice

• Utilize `/effort` with Opus 4.7 for speed vs. intelligence tuning.
• Employ `/ultrareview` for comprehensive, parallelized code analysis.

Topics

• Claude Opus 4.7
• Multi-Agent Code Review
• CLI Performance
• Sandbox Security
• Remote Control

Best for: NLP Engineer, CTO, VP of Engineering/Data, AI Engineer, Machine Learning Engineer, Software Engineer

Related on AIssential

• v2.1.110 — Recent Claude Code updates enhance security, user experience, and model capabilities, notably with Opus 4.7 xhigh and advanced code review.
• v2.1.109 — Claude Code updates enhance security, user experience, and model capabilities, notably with Opus 4.7 xhigh and improved CLI.
• Claude Security is now in public beta — Claude Security uses Opus 4.7 to find and fix code vulnerabilities, accelerating security workflows for enterprises.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Claude Code Changelog.