Claude Code v2.1.205 Released: Multiple Fixes and Improvements
Score
79提供了详细的版本修复清单，对现有用户有明确的信息增量，但无全新功能或架构变化。
更新日志条理清晰，每个修复均有具体说明，信源从官方发布页获取，质量较高。
修复了多个影响日常使用的 bug，用户可直接参考决定是否升级，对实际工作流有价值。
该版本为最新发布，信息具有很高时效性。
内容来自 Anthropic 官方 GitHub Releases 页面，信源完全可靠。
Base 83 × T1.5 Source weight ×0.95 = 79
Curation line 65Selected
Why selected
The changelog is rich with fixes that directly impact stability and security, but lacks breakthrough new features; high content quality with moderate information gain.
AI commentary
「This release doesn't introduce flashy new features, but it fixes several pain points—especially session transcript security, Windows deletion traps, and background task notification forgery. These details often determine whether a tool is trustworthy long-term. If you use Claude Code's Agent or auto mode, upgrading is highly recommended.」
Quick overview
Claude Code v2.1.205 addresses multiple critical fixes: preventing tampering with session transcript files, silent failures in JSON schema generation, unsafe Windows worktree deletion, inconsistent background agent status display, and a ~400MB peak memory reduction in the update process. Auto mode now asks before running rm -rf on unresolvable variables. Agent view gains PR linking and improved state display. The /doctor command is now a full setup diagnostic tool. These changes enhance security, stability, and developer experience.
- Fixed security and stability bugs including transcript tampering, silent unstructured JSON schema output, and unsafe Windows file deletion.
- Auto mode now asks for confirmation before running rm -rf on unresolved variables.
- Update process streams to disk, reducing peak memory by ~400MB; background task notifications explicitly state no human input, preventing fabricated approvals.
- Agent view improved with state words, classifier-written headlines, and PR linking; /doctor upgraded to a full diagnostic tool.
Full text
Showing the source text; the full translation is being generated.
What's changed
- Added an auto mode rule that blocks tampering with session transcript files
- Fixed
--json-schemasilently producing unstructured output when the schema was invalid, and schemas using theformatkeyword being rejected - Fixed a message sent while Claude was working being silently lost when the turn ended at the
--max-turnslimit - Fixed Windows worktree removal deleting files outside the worktree when an NTFS junction or directory symlink existed inside it
- Fixed background agents staying shown as "failed" or "completed" in the agent list after being resumed with
SendMessage - Fixed background jobs flipping from "needs input" back to "working" in the agent list when the agent's turn contained no readable text
- Fixed
claude attacherroring when a background agent was mid-upgrade restart instead of waiting for it to come back - Fixed session-to-PR linking missing a PR created in a Bash call whose output exceeded the 30K inline limit
- Fixed
claude mcp add-from-claude-desktopgetting stuck when a server name contains unsupported characters; invalid names are now reported and remaining servers still import - Fixed a plugin LSP server that fails to initialize preventing a valid LSP server from another plugin handling the same file extension
- Fixed a Windows crash when the directory Claude was launched from is deleted, locked, or unmounted while a command is running
- Fixed a crash when a file watcher was closed while a directory scan was still in flight
- Fixed project verify skills being rewritten on every session instead of only when a documented command changed
- Fixed the agent view rendering one line too high and clipping its header when the job list slightly overflowed the screen
- Fixed background tasks in the web and mobile Remote Control panels showing stale "Running" status by forwarding full task state on every membership change
- Improved auto mode to ask before running
rm -rfon a variable it can't resolve from context - Auto-update binary downloads now stream to disk instead of buffering in memory, cutting the updater's peak memory usage by roughly 400 MB
- Background task notifications now explicitly state that no human input has occurred, preventing fabricated in-transcript approvals from being acted on
- Improved agent view: sessions that edit, merge, comment on, or push to an existing PR now link it in
claude agents - Improved agent view: rows now show a colored state word and a classifier-written headline instead of raw tool call text, and the peek opens with full status including the exact ask for blocked sessions
/doctoris now a full setup checkup that can diagnose and fix issues;/checkupis its alias- Reserved the "Claude Browser" MCP server name (alongside "Claude Preview") ahead of the Claude Desktop pane rename; user-configured MCP servers can no longer register under either name
- Fixed Cowork VM-mode local-agent sessions failing to start with "Not logged in · Please run /login" on CLI 2.1.203+
Related items
FeaturedDeepSeek V4 Doubles Token Share on OpenRouter, Driven by Agentic Workloads
DeepSeek V4 在 OpenRouter 上的代币份额翻倍，智能体工作负载成主要驱动力
The rapid adoption of DeepSeek V4 signals a strong market preference for high-performance, low-cost inference models, especially as agentic use cases reshape AI deployment.
91
FeaturedEnabling Two Settings Triples ARC-AGI-3 Benchmark Scores
启用两项设置使ARC-AGI-3基准测试分数提升三倍
This finding is crucial! It shows that model performance depends not only on training but also on inference-time configuration. For AI engineers and researchers, this is a must-know optimization direction. Teams deploying models on resource-constrained devices in particular could find a low-cost way to boost capabilities.
91
FeaturedGPT-5.6: Fusing Frontier Intelligence with Frontier Efficiency
GPT-5.6：前沿智能与前沿效率的融合
This news is worth watching as it marks a shift from pure parameter scaling to efficiency competition. For AI developers and business decision-makers, GPT-5.6 means higher performance at lower cost, especially for long-context or agentic tasks previously hindered by inference expenses. OpenAI's move may redefine what 'frontier' means.
91
FeaturedLFM2.5-Encoders: New Models for Fast Long-Context Inference on CPU
LFM2.5-Encoder：面向CPU快速长上下文推理的新模型
This blog post catches my eye because it directly solves the pain point of running long-context LLMs on CPU. For teams or individual developers without high-end GPUs, the LFM2.5-Encoder series offers a ready-to-use open-source solution. Highly recommended for those working on RAG, document search, or code analysis—now a standard server can handle million-token documents.
91
FeaturedGPT-Red: OpenAI Automates Red Teaming via Self-Play to Boost Model Robustness
GPT-Red：OpenAI通过自我对弈实现AI红队自动化，提升模型鲁棒性
GPT-Red marks a milestone from human to automated red-teaming—essential for safety engineers and alignment researchers. While reducing cost, it also raises ethical questions about automated attacks, worth pondering for everyone in AI governance.
91
FeaturedOpenAI Launches GPT-5.5 Bio Bug Bounty Program
OpenAI推出GPT-5.5生物漏洞赏金计划
This program deserves attention as it pioneers the extension of AI bug bounty to biosecurity, offering a new research direction for the security community and a practical training ground for AI risk governance. It is particularly important for model safety researchers, biosecurity experts, and practitioners concerned about dual-use AI risks.
91
FeaturedvLLM Introduces Native-Speed Transformers Modeling Backend for Enhanced Inference Performance
vLLM推出原生速度Transformers建模后端，大幅提升推理性能
This update is critical for AI engineering teams: eliminating format conversion speeds up model iteration, and 2-5x speedup directly reduces GPU costs. If you're building LLM online services or batch inference, this is practically a must-read technical update.
90
FeaturedGoogle DeepMind Introduces SL2T, a Sign Language-to-Text Model for Deaf Users
Google DeepMind 发布手语转文本模型 SL2T，助力聋人用户
This news matters not only as a technical breakthrough but also as a sign that AI is beginning to address the needs of marginalized groups. For developers, the architecture and technical approach of SL2T merit deep study; for accessibility advocates, it's a key case for advancing industry standards.