Claude Code v2.1.238: Fixes Memory Leak in Long Sessions, Adds Plugin headersHelper and Runner Proxy Auth
Score
80针对内存增长、Remote Control 稳定性和 MCP 初始化等已知痛点的修复与新参数，信息增量明确。
官方 release notes 结构清晰、改动条目完整，便于开发团队评估升级。
内存泄漏修复与代理认证参数对生产环境用户直接有用，新设置即时生效。
发布即刻同步，覆盖当前版本使用者。
来自 Anthropic 官方 GitHub Releases，信源权威。
Base 84.5 × T1.5 Source weight ×0.95 = 80
Curation line 65Selected
Why selected
Official high-frequency iteration with broad fixes and security hardening; valuable for production users.
AI commentary
「This patch looks granular, but the unbounded memory growth fix and Remote Control 403 resilience hit real production pain points—team operators should prioritize upgrading. For individual developers, the new keybindingFlavor and faster macOS startup are clear quality-of-life wins.」
Quick overview
Claude Code v2.1.238 ships with a new keybindingFlavor setting for readline-style Ctrl+W deletion, plugin marketplaces supporting headersHelper to mint short-lived HTTP headers, and self-hosted runner flags for deferred shutdown and proxy authorization. This patch fixes unbounded memory growth in long interactive sessions, Remote Control disconnection and 403 resilience, MCP initialization ordering, and prompt display clipping. Security hardening now requires folder trust for MCP headersHelper helpers. Startup is faster on macOS. A notable change: fullscreen Ctrl+L/Cmd+K now only repaints, removing the double-press clear shortcut.
- Added keybindingFlavor setting for Bash-style Ctrl+W whitespace deletion; fullscreen Ctrl+L/Cmd+K now only repaints, removing the double-press clear shortcut
- Plugin marketplaces support headersHelper to mint short-lived HTTP headers; self-hosted runners gain --defer-shutdown-max-min and proxy authorization command/file flags
- Fixed unbounded memory growth in long sessions, Remote Control disconnection/403 tolerance, MCP initialization ordering, and other stability issues
- MCP headersHelper now requires folder trust and no longer inherits credential env vars, raising the security bar
Full text
Showing the source text; the full translation is being generated.
What's changed
- Added a
keybindingFlavorsetting: set it to"readline"to make Ctrl+W in the prompt delete back to the previous whitespace, as in Bash; the default ("classic") is unchanged - Plugin marketplaces:
headersHelperon a url marketplace or a catalog entry runs a command that mints HTTP headers (e.g. a short-lived token) for catalog and same-origin archive fetches - A catalog entry's
headersHelperruns only when you install or update that plugin, after its command is shown;claude plugin install/updateask[y/N](or pass-y) - Added
claude self-hosted-runner --defer-shutdown-max-min <minutes>: on SIGTERM, keep serving attached sessions, park what is left after that many minutes, then exit - Added
claude self-hosted-runner --proxy-authorization-command/--proxy-authorization-filefor egress proxies that require a freshly issuedProxy-Authorizationheader on every connection - Fixed unbounded memory growth in long interactive sessions: subagent tool results are now released once they leave the recent display window
- Fixed custom, project, and plugin output styles drifting back to the default voice mid-session
- Fixed
CLAUDE_CODE_ENABLE_PROMPT_SUGGESTION=truenot keeping prompt suggestions on when your account is near, but not over, its usage limit - Fixed worktree-isolation Bash refusals telling you to remove a redirect when the command had none
- Fixed self-hosted runners occasionally being removed by the server after a single slow or lost poll request, handing their healthy session to another runner
- Fixed MCP elicitation dialogs showing nothing for URLs longer than 4,096 characters, and permission prompts dropping the "don't ask again" option when the project path didn't fit the terminal width
- Fixed leftover
/tmp/claude-*-cwdfiles when a Bash command is killed, times out, or is interrupted - Fixed held Backspace being ignored on terminals that send Ctrl+H for Backspace when keystrokes arrive in large bursts (slow SSH/mosh links)
- Fixed text-wrapping in permission prompt diffs: lines containing wide multi-code-point characters (such as emoji) or tabs are no longer clipped
- Fixed killing a suspended (Ctrl+Z) session sometimes leaving the terminal in bracketed-paste mode with the cursor hidden
- Fixed stdio MCP servers receiving a
server/discoverrequest beforeinitialize, forcing lazy servers to start their backend on every session open - Fixed a proxy's refusal of a connection being reported as a generic network error instead of naming the proxy
- Fixed the
/modeland/effortcache-miss warning appearing when the prompt cache had already expired - Fixed per-task Stop from the Remote Control tasks panel doing nothing on CLI-hosted sessions
- Fixed remote sessions exiting when a client delivered a user message without a valid role
- Fixed Remote Control sessions started by
claude remote-controlinheriting session-scoped environment variables from the launching shell - Fixed a Remote Control session whose process crashed staying unavailable until
claude remote-controlwas restarted; it can now be reused when you next message it - Fixed Remote Control messages sent from the web or Desktop while Claude is mid-turn disappearing from the transcript after the turn finishes
- Fixed Remote Control model picks made on a phone or web not updating the model shown in the terminal
- Fixed Remote Control disconnecting with "login expired" when a brief network hiccup delays renewing your sign-in; it now retries and stays connected
- Fixed Remote Control reporting a failed reconnect on sign-out; signing out now ends the session with a clear message
- Fixed
ListAgents/SendMessagereporting "Remote Control is not connected" in sessions run byclaude remote-control(server mode) or Desktop/IDE hosts; they now list and reach Remote Control peers - Fixed
ListAgentsandSendMessageexposing the idle worker that the agent view pre-warms for your next background session; it now appears only once a task claims it - Cross-session messaging: sending to a session on this machine that refuses inbound messages (e.g.
crossSessionInbound: "refuse") now reports "refused" to the sender instead of a silent success - Cross-session messaging: a session whose inbox drops your messages (rate limit or full queue) now tells your session, instead of the messages vanishing silently
- Improved startup: bare
claudestarts sooner on macOS - Improved Bash tool permission checking for zsh-specific syntax in shell conditionals
- Improved Remote Control connection resilience: brief HTTP 403 refusals from a network edge, VPN, or proxy are now tolerated for up to 3 minutes, with the refusing party named when a block persists
- Improved startup responsiveness: the automatic update check now runs about 10 seconds after launch instead of competing with startup for CPU
- Updated the bundled
claude-apiskill for the Managed Agents Aug 19 release: web search/fetch domain settings and memory stores on self-hosted sandboxes - Changed Ctrl+L and Cmd+K in fullscreen to always just repaint — the double-press
/clearshortcut was removed, and 1-row nvim terminals no longer trigger automatic/clearloops - Changed
claude mcp listandclaude mcp getto show disabled servers as⊘ Disabledinstead of connecting to them for a health check - MCP
headersHelperin a project.mcp.json, and inline MCP servers in project or--add-diragent files, now require that folder's trust dialog to have been accepted (also underclaude -p) - MCP
headersHelperfrom a project.mcp.json, plugin, or agent file runs without inherited credential env vars; user, managed and claude.ai-scope helpers now run from the Claude config dir
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.