Claude Code v2.1.238:修复长会话内存泄漏,新增插件 headersHelper 与运行器代理认证
评分
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。
基础分 84.5 × T1.5 信源权重 ×0.95 = 80
精选线 65已入选精选
精选理由
官方高频迭代,修复覆盖面广且包含安全加固,对生产环境使用者价值显著。
AI 点评
「这次补丁看似琐碎,但「内存无界增长」和「Remote Control 403 容错」直击生产环境痛点,团队运维应优先升级;对个人开发者,新的 keybindingFlavor 和更快的 macOS 启动是体验上的明显加分项。」
速览
Claude Code v2.1.238 发布,新增 readline 风格按键绑定(Ctrl+W 按空白删除)、插件市场 headersHelper 动态生成短时 HTTP 头、自托管运行器延迟关闭与代理授权命令等能力。修复了长交互会话中无界内存增长、Remote Control 断连与 403 容错、MCP 初始化顺序、权限提示显示裁剪等问题,并强化了 MCP headersHelper 的目录信任安全要求。macOS 启动速度更快。
- 新增 keybindingFlavor 设置,可切换为 Bash 风格 Ctrl+W 按空白删除;全屏 Ctrl+L/Cmd+K 改为纯重绘,移除双击清屏快捷键
- 插件市场支持 headersHelper 动态签发短时 HTTP 头;自托管运行器新增 --defer-shutdown-max-min 与代理授权命令/文件参数
- 修复长交互会话内存无界增长、Remote Control 断连/403 抖动容错、MCP 初始化顺序等多处稳定性问题
- MCP headersHelper 现要求目录信任对话框通过,且不再继承凭据环境变量,安全门槛提升
正文
以下为原文,中文全文翻译生成中
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
相关条目
92
精选OpenRouter 推出提示缓存与粘性路由,大幅降低多轮对话成本
对于高频调用 AI API 的开发者,这个功能堪称直接省钱利器。粘性路由保证了缓存命中率,配合 session_id 零配置接入,值得所有使用 OpenRouter 的团队立即尝试。
91
精选ChatGPT Work:可在跨应用和文件中执行操作的AI Agent
我认为这是AI助手从问答走向执行的关键一步。对需要自动化复杂工作流的专业人士尤其值得关注。ChatGPT Work可能成为生产力工具的新范式。
90
精选前沿实验室代理入侵事件技术时间线:2026年7月事件剖析
这篇技术时间线值得所有AI安全研究员和代理开发者细读——它不只是描述一次攻击,而是为整个行业敲响了代理系统防御体系薄弱的警钟。对正在部署自主代理的团队来说,这是必读的灾难预防手册。
90
精选更好的工具反而让Copilot代码审查更糟?GitHub这样改进
这篇博客值得所有AI产品工程师和ML从业者仔细阅读——它打破了'更强大的工具=更好的AI'的直觉,转而强调与Agent推理模式匹配的工程哲学。对正在优化代码审查或类似Agent产品的团队尤其重要。
88
精选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
这条消息值得所有做多模态AI应用的开发者关注:OpenRouter用联合API解决了模型切换的痛点,特别适合初创团队或快速原型开发。如果你正被多个API密钥和SDK折磨,这个接口可能是你需要的统一层。
87
精选Anthropic 推出 Claude for Teachers:面向教师的教育 AI 工具
这条消息对教育工作者和AI行业观察者都很有价值。Anthropic没有选择通用聊天机器人,而是专门为教师设计了安全可控的工具,这显示出AI在垂直场景落地的正确思路——不是技术炫技,而是切实解决用户痛点。同时,产品内置的安全护栏也值得其他AI公司参考,尤其是在面向儿童或青少年的场景中。
86
精选OpenRouter发布全新Auto Router:用市场智慧优化模型路由
这条更新值得所有用API开发AI应用的人关注。以前选模型靠经验和测试,现在市场数据帮你选。虽然细节不多,但方向很对。对依赖聚合模型服务的团队尤其重要。
86
精选Claude Code v2.1.211 发布:多项修复与改进
作为一个经常使用 Claude Code 进行自动化编码的开发者,我特别关注这次的安全修复,尤其是权限预览字符绕过和自动模式覆盖钩子决策的问题——这些直接关系到团队协作时的安全边界。后台代理报告的改进也让长时间运行的任务更可靠。建议所有使用者尽快升级。