Claude Code v2.1.228 Released: Fixes Layout, Session, and Self-Hosted Runner Issues
Score
75作为常规补丁版本，修复内容多为已知问题，但涉及安全强化和 Runner 稳定性，仍有一定信息增量。
发布说明详尽，覆盖多个修复和增强，描述清晰，质量较高。
修复了影响实际开发流程的多个关键问题，对使用 Claude Code 的开发者有直接帮助。
发布说明来自 GitHub Releases 最新条目，时效性高。
来自 Anthropic 官方 GitHub Release 页面，信源权威可靠。
Base 78.5 × T1.5 Source weight ×0.95 = 75
Curation line 65Selected
Why selected
This release fixes several critical issues affecting real-world usage, especially self-hosted runners and security hardening, offering high practical value, but as a routine patch release the information gain is moderate.
AI commentary
「The most notable parts of this patch are that self-hosted runners are no longer brought down by checkout failures on unrelated repositories, and the hardening of claude.ai skills against leaks — these two directly reduce interruptions and security incidents for teams using Claude Code in CI or multi-machine remote collaboration. The fast-fail Vertex AI credential handling also avoids long development stalls, so users on Google Cloud should upgrade promptly.」
Quick overview
Anthropic has released Claude Code v2.1.228, which fixes several session and layout anomalies, including rare internal layout errors causing UI redraws to stop, Git/Git Bash not being found on Windows, /tui reverting to an older model, and cross-session messaging anomalies. Self-hosted runners no longer abort on checkout failures for repositories the session doesn't push to, instead skipping with a warning. Skills synced from claude.ai are now hardened to prevent shadowing local commands or MCP prompts, and Vertex AI credential failures now fail fast within seconds.
- Fixed interactive sessions that could stop redrawing entirely after a rare internal layout error while the process kept running
- Fixed git/Git Bash not being found on Windows when launched from a parent folder of the git installation
- Self-hosted runners now skip repositories they don't push to with a warning on checkout hook failure instead of failing the session
- Hardened skills synced from claude.ai: they no longer shadow local commands or MCP prompts, and don't run ! commands or expand @ files
Full text
Showing the source text; the full translation is being generated.
What's changed
- Fixed interactive sessions that could stop redrawing entirely, while the process kept running, after a rare internal layout error
- Fixed
git/ Git Bash not being found on Windows when Claude Code is launched from a parent folder of the git installation - Fixed
/tuireverting the session to an earlier model when/modelhad been changed since the last response - Fixed cross-session messaging sometimes starting without an inbox in the first session after install or upgrade
- Fixed Remote Control
/resumewhile connected leaking the resumed conversation's title or history into the connected session - Fixed
claude self-hosted-runnersessions failing on every fresh runner when thecheckouthook fails for a repository the session doesn't push to; that repository is now skipped with a warning - Fixed self-hosted runners ending sessions in the gap between a background task finishing and the follow-up turn starting
- Fixed session cleanup deleting contents inside a project's memory folder
- Fixed background plugin-cache cleanup deleting a plugin's cache when its only version is a symlinked development checkout
- Fixed a settings-merge issue where a marketplace entry redefined in a higher-precedence settings tier could inherit another tier's custom headers; marketplace entries now merge as whole entries
- Fixed the deferred-tools reminder occasionally being sent to the model twice after a skill invocation
- Hardened skills synced from claude.ai: they no longer shadow local commands or MCP prompts, their descriptions are sanitized and labeled, and on your machine their bodies don't run
!commands or expand@files - Improved cross-session messages: the sender and body now display inline instead of a collapsed line, and messages to Remote Control sessions on other machines show your Remote Control session name as the sender
- Improved Vertex AI credential handling: expired or missing Google Cloud credentials now fail within seconds instead of retrying for minutes
- Improved compaction progress: the retry countdown and stall hint now appear during compaction instead of only a progress bar
- Updated terminal title busy-spinner glyphs to reduce tab-bar jitter on some terminals
- Changed the Write tool so newer models can overwrite an existing file they haven't read this session, matching the Edit tool's rules; older models still require the read first
- Removed the outdated note about auto mode sessions costing slightly more from the first-use notice for Pro, Max, and Team plans
Related items
92
FeaturedOpenRouter Launches Prompt Caching with Sticky Routing to Drastically Reduce Multi-Turn Costs
OpenRouter 推出提示缓存与粘性路由，大幅降低多轮对话成本
For developers making frequent AI API calls, this feature is a direct money-saver. Sticky routing guarantees cache hit rates, and session_id requires zero configuration—every OpenRouter user should try it immediately.
91
FeaturedChatGPT Work: An AI Agent That Takes Action Across Apps and Files
ChatGPT Work：可在跨应用和文件中执行操作的AI Agent
I think this is a key step for AI assistants moving from Q&A to execution. Especially noteworthy for professionals who need to automate complex workflows. ChatGPT Work could become a new paradigm for productivity tools.
90
FeaturedAnatomy of a Frontier Lab Agent Intrusion: A Technical Timeline of the July 2026 Incident
前沿实验室代理入侵事件技术时间线：2026年7月事件剖析
This technical timeline is a must-read for all AI security researchers and agent developers—it doesn't just describe one attack but sounds an alarm on the weak defense systems of agent architectures. For teams deploying autonomous agents, this is an essential disaster prevention manual.
90
FeaturedBetter Tools Made Copilot Code Review Worse? Here's How GitHub Improved It
更好的工具反而让Copilot代码审查更糟？GitHub这样改进
This blog post deserves close reading by all AI product engineers and ML practitioners—it breaks the intuition that 'more powerful tools = better AI' and instead emphasizes an engineering philosophy aligned with agent reasoning patterns. Especially important for teams optimizing code review or similar agent-based products.
88
FeaturedOpenRouter Launches Unified Multimodal API: Single Endpoint for Image, Video, Audio, Embeddings, and Transcription
OpenRouter 推出统一多模态 API：单端点支持图像、视频、音频、嵌入与转录
This news is worth attention from all developers building multimodal AI applications: OpenRouter's unified API solves the pain of model switching, especially for startups or rapid prototyping. If you're struggling with multiple API keys and SDKs, this interface could be the unified layer you need.
87
FeaturedAnthropic Launches Claude for Teachers: AI Tools Designed for Educators
Anthropic 推出 Claude for Teachers：面向教师的教育 AI 工具
This announcement is valuable for educators and AI industry watchers alike. Instead of a generic chatbot, Anthropic designed a safety-first tool specifically for teachers, demonstrating the right approach for AI vertical deployment: solving real pain points rather than showing off technology. The built-in guardrails also set a reference for other AI companies, especially when serving scenarios involving children or teenagers.
86
FeaturedOpenRouter Introduces New Auto Router: Model Routing Powered by Market Wisdom
OpenRouter发布全新Auto Router：用市场智慧优化模型路由
This update is worth attention for anyone using APIs to build AI apps. Instead of guessing or testing model selection, market data now does the heavy lifting. Though sparse on details, the direction is right, especially for teams relying on aggregated model services.
86
FeaturedClaude Code v2.1.211 Release: Multiple Fixes and Improvements
Claude Code v2.1.211 发布：多项修复与改进
As a developer who frequently uses Claude Code for automated coding, I'm particularly interested in the security fixes, especially the permission preview character bypass and auto mode overriding hook decisions—these directly affect the security boundaries during team collaboration. The improvement in background agent reporting also makes long-running tasks more reliable. I recommend all users upgrade as soon as possible.