Claude Code v2.1.191: Performance Optimization, MCP Reliability Upgrades, and UX Improvements
Score
68Why selected
Includes multiple critical bug fixes, performance optimizations, and UX improvements with substantive enhancements to core workflows (MCP, sandbox networking), but not a milestone major release, hence score 85.
AI commentary
「This release significantly improves Claude Code's stability and efficiency, especially streaming performance and MCP reliability, directly enhancing developers' daily usage experience.」
Quick overview
Claude Code v2.1.191 brings several important updates: new /rewind command to resume conversation after /clear, fixed scroll position jumping during streaming, permanent stop for background agents, and /login URL truncation in Windows Terminal. MCP server capability discovery and OAuth flow now retry transient network errors, and sandbox network permission prompts are remembered per session. CPU usage during streaming is reduced by ~37%, and long-session memory growth is improved.
- New /rewind command to resume conversation after /clear
- ~37% reduction in CPU usage during streaming responses
- MCP server capability discovery and OAuth now retry on transient errors for improved reliability
- Sandbox network permission prompts remembered for the rest of the session
Full text
Showing the source text; the full translation is being generated.
Uh oh!
There was an error while loading. Please reload this page.
anthropics / claude-code Public- Notifications You must be signed in to change notification settings
- Fork 21.9k
- Star 136k
v2.1.191
CompareChoose a tag to compare
Sorry, something went wrong.
Filter LoadingSorry, something went wrong.
Uh oh!
There was an error while loading. Please reload this page.
No results found
View all tags
ashwin-ant
released this
24 Jun 21:58
v2.1.191
0bd9543
What's changed
- Added
/rewindsupport for resuming a conversation from before/clearwas run - Fixed scroll position jumping to the bottom while reading earlier output during a streaming response
- Fixed background agents resurrecting after being stopped — stopping an agent from the tasks panel is now permanent
- Fixed
/voiceshowing a generic "not available" message when disabled by an organization's policy — it now explains the restriction - Fixed
/loginURL opening truncated in Windows Terminal when it wraps across lines - Fixed Cmd+click on links in fullscreen mode for Ghostty over ssh/tmux
- Fixed
claude agentssending builtin slash commands like/usageto background sessions as prompt text instead of showing a hint - Fixed
claude agentsjob rows showing full filesystem paths for pasted images instead of the[Image #N]placeholder - Fixed hooks with comma-separated matchers (e.g.
"Bash,PowerShell") silently never firing - Fixed
/permissionsRecently-denied tab: approving a denial now persists on close instead of being silently discarded - Fixed the agent panel jumping by one row when scrolling the roster past the overflow cap
- Fixed the welcome splash art overflowing the default 80×24 macOS Terminal window
- Fixed managed settings:
forceRemoteSettingsRefreshnow takes effect when set via MDM or file policy, and the fetch sendsCache-Control: no-cacheto prevent proxies from serving stale responses - Improved sandbox network permission dialog: hosts you allow with "Yes" are now remembered for the rest of the session instead of re-prompting on every connection
- Improved MCP server reliability: capability discovery (
tools/list,prompts/list,resources/list) now retries transient network errors with short backoff - Improved MCP OAuth: discovery and token requests now retry once after transient network errors, and headless environments skip the browser popup and go straight to the paste-the-URL prompt
- Improved MCP error messages: HTTP 404 errors now show the URL and point to your MCP config
- Improved vim mode prompt-history search (NORMAL
/) to hint how to reach slash commands - Reduced CPU usage during streaming responses by ~37% by coalescing text updates to 100ms
- Reduced long-session memory growth from terminal output cache
Uh oh!
There was an error while loading. Please reload this page.
👍 5 mike1858, ytsssun, saita08, loradmyself, and distinguished-sre reacted with thumbs up emoji 😄 4 mike1858, saita08, loradmyself, and RamGam0o0 reacted with laugh emoji 🎉 5 mike1858, saita08, tanakornrawee-dev, JRAVILES, and simono reacted with hooray emoji ❤️ 5 mike1858, saita08, JRAVILES, loradmyself, and meng-hhh reacted with heart emoji 🚀 3 mike1858, saita08, and JRAVILES reacted with rocket emoji 👀 2 mike1858 and saita08 reacted with eyes emoji All reactions- 👍 5 reactions
- 😄 4 reactions
- 🎉 5 reactions
- ❤️ 5 reactions
- 🚀 3 reactions
- 👀 2 reactions
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.