Claude Code v2.1.215–218: Manual-Only /code-review, Filesystem Sandbox Control, Emoji Autocomplete, Windows Path Fix

What's new

• v2.1.215 (Jul 19): /verify and /code-review no longer run automatically — only when explicitly invoked by command
• v2.1.216 (Jul 20): new sandbox.filesystem.disabled setting to control filesystem isolation; fix for quadratically growing slowdowns during message normalization in long sessions
• v2.1.217 (Jul 21): emoji shortcode autocomplete in the prompt input (e.g. :rocket: → 🚀); default limit of 20 concurrent subagents; MCP tool output memory leak fix
• v2.1.218 (Jul 22): /code-review now runs as a background subagent without interrupting the conversation; fix for Windows path corruption with \u-prefixed segments (e.g. C:\Users\unicorn); /ultrareview fix for descriptive arguments

Why it matters

Version 2.1.215 changes behavior: Claude no longer auto-launches code review, reducing unwanted interruptions. Version 2.1.216 fixes a critical performance issue in long sessions. Version 2.1.218 moves code review to the background — your workflow no longer pauses.

How to try it

Update Claude Code to the latest version (npm update -g @anthropic-ai/claude-code or via IDE extension). The /code-review and /verify commands must now be invoked manually.