v2.1.110

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

Summary

Recent updates to Claude Code, spanning versions 2.1.105 through 2.1.114, introduce significant enhancements across user experience, security, and model capabilities. Version 2.1.114 primarily addressed a crash in the permission dialog. Version 2.1.113 brought a native Claude Code binary for the CLI, added `sandbox.network.deniedDomains` for granular network control, and improved UI elements like multiline input navigation and clickable long URLs. Key security fixes include treating macOS `/private` paths as dangerous and hardening `Bash` deny rules against exec wrappers and `find -exec`. Version 2.1.111 made Claude Opus 4.7 xhigh available with an interactive `/effort` slider and introduced `/ultrareview` for parallelized code analysis. It also streamlined auto mode and added a `/less-permission-prompts` skill. Version 2.1.110 added a `/tui` command for flicker-free rendering and a push notification tool, while 2.1.108 introduced a recap feature and prompt caching improvements. Version 2.1.105 added `EnterWorktree` and PreCompact hook support.

Key takeaway

For CTOs or VPs of Engineering evaluating AI development environments, these Claude Code updates offer enhanced security features, including refined sandbox controls and robust Bash rule enforcement. The introduction of Opus 4.7 xhigh and the `/ultrareview` skill provides powerful tools for advanced code analysis and performance tuning, potentially accelerating development cycles and improving code quality. Consider integrating these new capabilities to bolster security postures and optimize AI-assisted workflows.

Key insights

Recent Claude Code updates enhance security, user experience, and model capabilities, notably with Opus 4.7 xhigh and advanced code review.

Principles

• Granular control over network access improves security.
• Proactive code review with multi-agent analysis enhances quality.
• Clear error messaging and UI consistency improve user experience.

Method

The `/ultrareview` skill performs comprehensive cloud-based code review using parallel multi-agent analysis and critique, invokable for current branches or specific GitHub PRs.

In practice

• Use `sandbox.network.deniedDomains` to block specific network access.
• Employ `/effort` to tune Opus 4.7 speed vs. intelligence.
• Run `/ultrareview` for comprehensive code analysis.

Topics

• Claude Opus 4.7
• CLI Enhancements
• Security Features
• Code Review
• Plugin Management

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

Related on AIssential

• v2.1.101 — Recent Claude Code updates enhance security, user experience, and model capabilities, including Opus 4.7 xhigh and advanced code review.
• v2.1.105 — Recent Claude Code updates enhance security, user experience, and model capabilities, notably introducing Opus 4.7 xhigh and advanced review tools.
• Introducing Claude Opus 4.7 — Claude Opus 4.7 offers significant advancements in software engineering, multimodal understanding, and long-running task consistency with enhanced safety.
• 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.