Safety in auto mode has been enhanced, making development even smoother!
New Features and Fixes in Claude Code v2.1.183
Original: v2.1.183
Importance: 安全性向上と便利な機能追加があり、開発者に影響を与える。
Summary
The latest version of Claude Code, v2.1.183, enhances safety in auto mode by blocking certain destructive git commands. A warning feature for deprecated models and improved toggle behavior for settings have been added, along with various bug fixes. This allows developers to work more safely and efficiently.
Key Points
- Enhanced safety in auto mode
- Blocking of destructive git commands
- Warning feature for deprecated models added
- Improved behavior for setting changes
- Multiple bug fixes implemented
View developer notes (APIs, breaking changes, migration)
In Claude Code v2.1.183, safety in auto mode has been enhanced by blocking destructive commands like `git reset --hard`, and operations like `terraform destroy` are now only executable when a specific stack is requested. A warning for deprecated models is shown in stderr, and the `attribution.sessionUrl` setting allows omitting the claude.ai session link from commits and PRs. Improvements in `/config` behavior and various bug fixes have also been implemented for a better developer experience.
Source: https://github.com/anthropics/claude-code/releases/tag/v2.1.183
Outlet: Claude Code Releases
This article is an AI-generated summary (OpenAI GPT-4o-mini) of publicly available information from Anthropic, OpenAI, Google, Meta, Mistral, DeepSeek, Sakana, and other vendors. The original source URL is always provided in accordance with fair-use citation requirements. Summaries are AI-generated and may contain mistranslations or misinterpretations. Always verify details with the original source.