黄奕彬

外部精选

Claude Code · v2.1.295

本文来自外部来源,不是黄奕彬的原创文章。本站提供原文入口,并在采集端生成 AI 结构化摘要、解读与中文翻译(如有),一切以原文为准。

阅读原文(github.com)
来源
Claude Code releases ↗
作者 / 署名
ashwin-ant
来源更新时间
本站收录时间
原文域名
github.com

以上时间均为北京时间;来源更新时间由来源提供,不代表首次发布时间。

结构化摘要 AI 生成

背景与问题

本文是 Claude Code v2.1.295 的版本发布公告,面向该 CLI 及其生态(VS Code 扩展、云会话、Slack 的 Claude Tag、自托管 runner、Claude apps gateway)的使用者与运维,回答"这一版新增、修复、改进、变更了什么"。

问题来自持续迭代中用户报告的缺陷与企业部署场景(网关、云上游、headless/SDK 会话)的新需求。正文按 Added / Fixed / Improved / Changed 及平台标签分节,核心是数量庞大的缺陷修复清单。

方法或内容

发布的是一份逐条变更清单,主要包括:

  • 新增:hooks 的 onFailure: "block"、终端状态协议 OSC 7501、网关上游 timeouts.upstream_ttfb_ms 与可选 models 列表、mods 的 $.ui.notify 与 Button children、CLAUDE_CODE_RETRY_WATCHDOG_MAX_WAIT_MS、forceLoginMethod: "gateway" 等
  • 修复:MCP 重连/分页游标/文件扩展名、claude -p 多轮输出丢失、终端长输出冻结、Windows 驱动器大小写等大量缺陷
  • 改进与变更:Bedrock token 计数改用 AWS CountTokens API、MCP 工具描述截断上限升至 16,384 字符、claude.ai 连接器默认协商 MCP 协议 2026-07-28 等

另有 [VSCode]、[Cloud sessions]、[Claude Tag]、[Code Review]、Self-hosted runner 等平台专属条目。

关键发现 / 结果

  • hooks:新增 onFailure: "block",钩子无法启动、超时或意外退出码时阻断动作而非放行
  • 终端:支持 OSC 7501,实现的终端可显示 Claude Code 正在工作、等待或已完成
  • 网关:timeouts.upstream_ttfb_ms 限制上游流启动耗时,超时则故障转移或返回 502;上游可配 models 白名单(条目内 * 为通配);审计事件加入 upstream_request_id;成功响应带 request-id header
  • 修复:上游拒绝 context-1m beta 时 [1m] 模型请求全败,现重发不带该 beta
  • 修复:远程 MCP 断线超 15 秒不再失联、不再紧密循环重连,重复掉线退避最长 30s
  • 改进:网关后 Bedrock token 计数改用 AWS CountTokens API(需 bedrock:CountTokens 权限)
  • 改进:网关后台请求改用 Haiku 4.5,网关不提供时回退会话模型
  • 变更:WebSocket MCP 消息超 16 MiB 关闭连接;tool search 加载的 MCP 工具描述截断改为 16,384 字符(原 2,048)

结论与意义

原文为变更公告,未给出作者显式结论或适用边界论述。隐含意义:升级到 v2.1.295 即可获得上述修复与行为变化。该发布标记为 Immutable(不可变发布,仅标题与说明可修改),且其后 main 分支已有 1 个新提交。

AI 解读 AI 生成

方法:按「时空变量」分析(时间 / 空间 / 变量,严格区分包含、相关与因果),对象包括原文作者、署名人员与关键技术及其实际原理;结论用「元反空」(元思考、反思考、空思考、综合)整理。

时间:何时发生,现在是否仍成立

来源日期为 2026年10月9日 03:48(北京时间),即北京时间 2026-10-09 03:48:38。发布本身不可变,仅标题与说明可修改,因此该清单内容针对 v2.1.295 恒定成立。正文显示发布后 main 已有 1 个提交,仓库继续演进;对后续版本是否保持这些行为,原文未说明。

空间:谁的环境 / 场景

  • 产品:Claude Code CLI v2.1.295,随附 VS Code 扩展、云会话、Claude Tag(Slack 集成)、Code Review、自托管 runner、Claude apps gateway 等组件
  • 形态:本机会话(macOS/Windows/Linux)、headless 与 SDK 会话、后台会话、企业网关部署(上游含 Amazon Bedrock、Vertex、Foundry 等)
  • 部分条目有明确前提:OSC 7501 仅对实现该协议的终端生效;forceLoginMethod: "gateway" 要求机器无托管设置;Bedrock token 计数改进需 bedrock:CountTokens 权限

变量:实际改变了什么

  • 行为:hooks 失败从放行变为可配阻断;网关后台请求模型从会话模型改为 Haiku 4.5;后台会话空闲时 Ctrl+C 不再取消待执行的 /loop 唤醒
  • 配置:新增 timeouts.upstream_ttfb_ms、上游 models 列表、forceLoginGatewayUrl、CLAUDE_CODE_RETRY_WATCHDOG_MAX_WAIT_MS 等项
  • 数值:MCP 工具描述截断 2,048→16,384 字符;Slack 设置确认卡片 10→30 分钟;子代理最多预载 32 个 skills;MCP 协议默认协商版本改为 2026-07-28
  • 其余为缺陷修复带来的行为修正(MCP 稳定性、终端渲染、Windows 路径大小写等);价格变化原文未说明

区分:包含 ≠ 相关 ≠ 因果

  • 明确因果(原文直接陈述因果链):上游拒绝 context-1m beta 导致 [1m] 模型请求全败,去掉后修复;后台会话继承 FORCE_COLOR=3 导致输出混入颜色转义码;引号逐层嵌套导致终端冻结并占用 GB 级内存
  • 相关而非因果:OSC 7501 与状态显示仅是"实现的终端可以显示",实际显示取决于终端实现
  • 包含:mods、plugins、MCP 服务器、网关上游均为 Claude Code 生态组成部分;[VSCode]、[Cloud sessions] 等标签只是变更的分类归属,不构成因果
  • 页面元信息"1 commit to main"与发布内容仅为同时出现,无因果关系

对象:作者/署名与关键技术原理

署名(仅来自结构化作者字段):ashwin-ant。关键技术及原文描述:

  • hooks:命令与 HTTP 钩子机制,新版可配置失败即阻断(onFailure: "block")
  • OSC 7501:程序状态协议,终端据此显示 Claude Code 的工作/等待/完成状态
  • MCP:远程服务器连接协议,涉及 WebSocket 传输、分页游标、协议版本协商(默认 2026-07-28,MCP_PROTOCOL_NEGOTIATION=legacy 可退出)
  • Claude apps gateway:企业网关,接入 Bedrock/Vertex/Foundry 等上游,含审计日志、花费视图、models 白名单、故障转移
  • mods/plugins:可热重载扩展体系,含 $.ui.notify、Button children、guard hook、config.set hook

这些技术的更深实现原理原文未说明。

元反空综合结论

元:本质在解决版本透明度问题——让用户与运维确切知道 v2.1.295 相对上一版的差异,以决定升级与配套调整(授予 bedrock:CountTokens、评估 hooks 阻断语义、留意交互变更)。

反:最可能有边界的主张——OSC 7501 依赖终端实现;网关各项改进依赖部署配置与权限;MCP 协议 2026-07-28 仅对不拉取 flags 的安装默认生效;行为变更(如后台会话 Ctrl+C、claude agents 停止语义)对依赖旧习惯的用户可能构成回归。

空:去掉叙事后剩下的事实是一个不可变发布附逐条差异清单:新增配置项、若干数值阈值调整(16,384 字符、16 MiB、30 分钟等)与大量针对性修复;除"约一分钟""最长 30s"等明确时限外无性能数字宣称。

综合:作为该版本的事实性变更记录可信度高,但适用需对号入座自身形态(CLI/VSCode/网关/云/Slack);条目未覆盖的环境不能推断适用,后续版本行为原文未说明。

中文译文 AI 生成

自本发布以来已有 1 个提交进入 main

不可变的发布。只有发布标题和说明可以被修改。

602df92

变更内容

  • 为命令和 HTTP hooks 新增 onFailure: "block":无法启动、超时或以意外代码退出的 hook 会阻止该操作,而不是放行
  • 新增 Program Status Protocol(OSC 7501)支持:实现了该协议的终端可以显示 Claude Code 是正在工作、正在等待你,还是已完成
  • /copy 选择器新增引用文本的处理,使起草的消息在复制时不含其 > 标记
  • 为 claude plugin install、enable、disable 和 marketplace add 新增警告:当它们要写入的设置文件无法加载时给出警告
  • 当 stderr 是终端时新增一行输出,说明 claude -p 运行在最后一轮结束后仍保持打开时正在等待什么
  • 为 Claude apps gateway 的 Bedrock、Vertex、Foundry 及其他云上游新增对 timeouts.upstream_ttfb_ms 的支持:你设置的值现在会限制一个流在那里开始所允许的最长时间,超时后将故障转移或返回 502
  • 当你在 ← 正在等待当前工具完成时停止该轮,新增一条 "Backgrounding cancelled" 消息
  • 为每个 Claude apps gateway 上游新增可选的 models 列表:只有列出的模型会被发送到那里,故障转移时也是如此,条目中的一个 * 是通配符
  • 在没有 managed settings 的机器上,新增对在你自己的用户设置中使用 forceLoginMethod: "gateway" 和 forceLoginGatewayUrl 的支持,使 /login 在该 Claude apps gateway 上打开
  • 当插件的 README 没有安装行时,为 claude plugin validate 新增建议:它会打印可粘贴的那一行,且绝不更改退出代码,即使带有 --strict
  • 为 Claude apps gateway 的推理审计事件新增 upstream_request_id:来自 Amazon Bedrock、Anthropic API 或其他上游的请求 ID,用于支持工单
  • 为 mods 新增 $.ui.notify:通过你自己的通知设置触发原生通知,并说明是哪个频道发送的
  • 为 mod 的 Button 新增 children:字符串和 Text,使列表的一行成为单个可按压的整体,内部可包含 chip 或暗淡的细节
  • 新增 CLAUDE_CODE_RETRY_WATCHDOG_MAX_WAIT_MS,用于限制无人值守重试模式(CLAUDE_CODE_RETRY_WATCHDOG)等待 429 和 529 错误结束的时长
  • 为 Claude apps gateway 的成功推理响应新增 request-id header,使 Claude Code 遥测中的 request_id 与网关的审计日志一致
  • 修复了当 gateway、Bedrock、Vertex 或 Foundry 拒绝 context-1m beta 时,[1m] 模型上的每个请求都失败的问题;Claude Code 现在会在不带它的情况下重新发送
  • 修复了当后台工作开始另一轮时,claude -p 文本输出丢弃较早响应的问题;现在每轮的响应该轮结束时打印
  • 修复了 headless 和 SDK 会话中的远程 MCP 服务器在超过 15 秒的中断后保持断开连接,或以紧密循环不断重连到一个在连接建立后立即断开每个连接的服务器的问题;重复断开现在会退避,最长 30 秒
  • 修复了当服务器的错误回复恰好包含某个网络错误名称时,远程 MCP 连接被断开的问题
  • 修复了重复返回同一分页 cursor 的 MCP 服务器在每次连接时被请求同一页面多达 20 次的问题
  • 修复了 MCP 工具返回的 CSS、JavaScript 和 XML 文件被保存为 Read 工具会拒绝的 .bin 的问题;字体和图标文件现在也会获得自己的扩展名
  • 修复了当模型传入 command_description 而非 description 时 Bash 工具调用失败的问题
  • 修复了 Claude in Chrome 不将以端口 80(host:80)写成的站点拒绝规则应用到该主机上普通 http:// 页面的问题
  • 修复了 /plugin 的 Errors 标签页在按下 Enter 时未经事先询问就移除加载失败的 marketplace 并卸载其插件的问题
  • 修复了 claude plugin marketplace add 对某个其名称下无法安装任何插件的 marketplace 报告成功的问题;此类 add 现在会被拒绝
  • 修复了 CLAUDE_AUTO_BACKGROUND_TASKS 在某次编辑或 shell 命令排在 subagent 之后等待时,将该 subagent 移到后台,导致该调用在 subagent 完成之前就开始的问题
  • 修复了在 claude remote-control 会话中,紧随一条手机消息之后、未设置 /config 开关,或从 Claude Code 内部启动时,PushNotification 提示 push 未发送的问题
  • 修复了从远程会话发送的文件在一次发送超过 256 个时被以 "could not be vouched for" 为由拒绝的问题
  • 修复了在登录刷新之后紧接着启动时,偶发的 managed settings 加载失败
  • 修复了当 Claude Code 无法再次启动时,/tui 无消息退出或以原始系统错误退出的问题
  • 修复了以文本显示的链接地址被某条回复遗留的颜色或 conceal 样式隐藏的问题,包括其在表格或问题预览中折行的情况
  • 修复了在登录到 Claude apps gateway 的会话中,列在 availableModels 里的 Fable 模型不出现在 /model 选择器中的问题;此类模型现在显示其内置行,以替代为同一模型添加的 modelPicker 行
  • 修复了 Claude apps gateway 的管理员支出视图在开发者的会话不再携带 groups 后,仍显示该开发者的旧 groups 和 group 上限的问题
  • 修复了 CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC 在 /usage 和状态行中隐藏 Claude apps gateway 支出限额的问题。支出限额请求会发送到会话所登录的网关
  • 修复了位于自身 linked worktree 中的 subagent 被显示父会话的 git 分支、状态和最近提交的问题
  • 修复了当在提示框中输入的文本取消了以 ← 进行的后台化时,Claude 在当前工具结束时停止的问题;Claude 现在会继续在前台工作
  • 修复了 --tools 和 --restricted 不适用于启动后注册的内置工具,以及已弃用的工具名到达调用者工具集之外的工具的问题
  • 修复了在 Claude 等待 MCP 服务器的资源列表时,一个中断要等到超时才结束该轮的问题
  • 修复了 mod 的 hook 被交给一个被无提示截断的深层嵌套工具输入的问题,这可能导致 guard 放过它从未看到的内容
  • 修复了 Esc 无法停止被以 ← 移到后台的自定步调 /loop 的问题;取消一个待处理的唤醒现在会显示一条提示
  • 修复了后台会话中的命令和钩子继承 FORCE_COLOR=3 的问题,该设置会把颜色转义码写入 Claude 读取的输出中
  • 修复了当两者在有会话打开时被一同停止(例如重启时),claude 代理在退出之际启动一个新的后台服务的问题,这可能延迟关机并重启被中断的会话
  • 修复了名为 worker 的自定义代理在自动模式拒绝通知中和任务详情视图的活动列表中显示为 “Agent” 的问题
  • 修复了针对遍历 glob 模式的 for 循环的 Bash 权限检查,提升了权限检查的准确性
  • 修复了从 Workflow 子代理调用的分叉技能把结果交付给主对话而非发起调用的代理的问题
  • 修复了进程内代理队友在通过工具搜索加载该工具之前,首次调用 SendMessage 会失败的问题
  • 修复了恢复时向 Claude 告知某个未完成的后台工作流可能已被 TaskStop 停止的问题;TaskStop 绝不可能是原因
  • 修复了当你从任务面板或已连接的客户端停止长时间运行的 MCP 工具调用时,Claude 未被告知的问题
  • 修复了后台会话的 /loop 在其下一次唤醒到期而会话进程已停止时无提示地停止的问题;现在会话会说明这一点,并且 Claude 会被告知
  • 修复了回复或队友消息中的原始终端超链接字节被绘制为带隐藏地址的可点击链接的问题
  • 修复了仓库包含大型 git 子模块的插件市场无法添加或刷新的问题:现在只获取包含插件文件的子模块
  • 修复了 /advisor 对话框在已保存的 advisor 模型不再可用时仍显示勾选标记的问题;现在它会在 “No advisor” 处打开
  • 修复了移入后台的 MCP 工具调用的通知显示截短的任务 id 的问题
  • 修复了 vim 模式中 ~ 把光标移过一行最后一个字符的问题,此前在其后执行 x 毫无作用,且 3~ 会继续进入下一行
  • 修复了把从 macOS 复制的带重音文本(例如文件名)粘贴到提示中间后,光标多落一个字符的问题
  • 修复了响应长达数万行时终端冻结且 ctrl+c 被忽略的问题
  • 修复了在插件 hooks worker 重启期间某个 mod 重新加载时发出的调用绕过另一个 mod 的带 .catch 的 guard 钩子的问题;此类调用现在会被拒绝
  • 修复了 hooks 模块嵌套代码达数千层深的插件加载或校验失败、仅给出裸 stack-overflow 消息的问题
  • 修复了 claude plugin test 通过一个 session.append 钩子的问题,该钩子会删除真实会话会保留的 tool call、tool result 或 thinking 块
  • 修复了会话被终止并第二次恢复后,Claude 未被告知可以用 SendMessage 恢复后台子代理的问题
  • 修复了在诸如 cat 的 Bash 命令运行却未打印该文件后,此文件被当作已读取的问题
  • 修复了名为 constructor 或 prototype 的插件选项总是读出其默认值、编辑后从不重新加载插件的问题
  • 修复了 mod 的热重载遗漏在 /reload-plugins 或会话启动正在读取该 mod 的文件期间所做的保存的问题
  • 修复了在未选择答案就批准 mod 热重载问题时,该问题在整个会话中每一轮都被再次询问的问题
  • 修复了 /model、/fast 和 /output-style 保存设置时未询问插件 config.set 钩子的问题
  • 修复了管道输出中粗体文本紧跟暗淡文本时被绘制得偏淡的问题
  • 修复了引号每几行就更深嵌套一层的回复使终端冻结数秒并占用数 GB 内存的问题
  • 修复了 mod 的热重载遗漏距其上次重载仅几毫秒内所做的保存的问题,这会使 mod 停留在旧版本直到下一次保存
  • 修复了 claude mcp serve 的后台 Bash 结果未指明输出文件名的问题,以及其工具描述承诺一个永不到来的通知的问题
  • 修复了异步 SessionStart 钩子未变化的上下文在每次恢复时被再次添加到对话的问题
  • 修复了 SessionStart 钩子写入 CLAUDE_ENV_FILE 的变量在应用内执行 /resume 或 /branch 之后无法到达 Bash 工具的问题
  • 修复了 Skill 工具在响应流结束前完成时,技能的 allowed-tools 和 effort 被丢弃的问题,这会在 -p 运行中拒绝该技能的 Bash 命令
  • 修复了被篡改的服务器管理设置缓存导致一个人自己的插件在托管设置列出或启用插件的机器上被计为组织管理的问题
  • 修复了在功能标志不可用时向 Claude 3 Opus 和 Claude 3.x Sonnet 会话提供工具搜索的问题,而这些模型会拒绝工具搜索
  • 修复了在 -p 和 SDK 会话中生成的类型文件被写入 --plugin-dir 插件文件夹的问题;现在它们只被写入正在开发 mod 的地方
  • 修复了带制表符或双向控制字符的文本在屏幕边缘丢失其结尾或绘制到相邻行上的问题
  • 修复了 /model 显示所选 Max 档位已被保存为新会话默认值的问题;Max 仅适用于当前会话
  • 修复了异步钩子的 JSON 输出分多行打印时被忽略的问题
  • 修复了 Read 工具拒绝带空 pages 参数的调用而不是将其视为省略的问题
  • 修复了 Windows 上 VS Code 中项目作用域插件因盘符大小写而无法加载的问题 (#74612)
  • 修复了 Windows 上在项目或本地作用域安装和卸载插件时,仅因盘符大小写不同而丢失安装记录或添加第二条记录的问题
  • 修复了在 ← 之后立即用 ↑ 或 Esc 把排队消息拉回提示时该消息丢失的问题:提示历史现在会保留它
  • 修复了当 SDK 宿主在任何人回答之前关闭其启用问题时,mod 热重载对整个会话关闭的问题;现在该问题最多会被询问三次
  • 修复了被 mod 的 prompt.submit 钩子改写或丢弃的提示仍按输入原样保存到提示历史和转录的排队提示记录中的问题
  • 修复了非交互式会话在你的请求并未用到需要认证的 MCP 服务器时仍向你告知这些服务器的问题
  • 修复了在 Claude apps gateway 登录时 claude_code.auth OpenTelemetry 登录事件未发出的问题。当机器上配置了 OpenTelemetry 或会话已登录到网关时,该事件会被导出
  • 修复了当 plugin hooks worker 停滞时,添加超大接口的插件导致另一个插件被卸载的问题
  • 修复了当文件内容发生变化但其修改时间未前进时,Edit 将其视为已完整读取的问题
  • 修复了带有 Windows 换行符(CRLF)的短命令输出被绘制在单行上的问题
  • 修复了已停止的定时任务在回退(rewind)后恢复时重新出现的问题,以及定时任务在压缩(compaction)后按 Esc 或回退再恢复时丢失的问题
  • 修复了在对包含超长行、连续多行空行或未闭合字符串和 heredoc 的代码进行语法高亮时终端冻结数秒或数分钟的问题
  • 修复了被中断的 /ultrareview 上传遗留在 ~/.claude/seed-admin 下的临时文件永远不会被保留清理(retention cleanup)删除的问题
  • 修复了从设置中移除 disableAutoMode 后,Desktop 和 SDK 会话在重启前拒绝切换回 auto 模式的问题
  • 修复了在另一个会话同步插件更新后,长时间运行的会话中 claude.ai 同步的 plugin hooks 报错 "Plugin directory does not exist" 而失败的问题
  • 修复了当会话被移到后台或被杀死后恢复时,/rewind 之后发送的提示丢失以及被移除的轮次重新出现的问题
  • 修复了当 mod 的 session.receive hook 在转发消息前请求权限时云会话挂起的问题
  • 修复了更新后一起重启的 macOS 后台会话有时在稳定版 app wrapper 之外运行、导致文件夹访问提示可能重新出现的问题
  • 修复了在 headless 和 SDK 会话中较晚完成的 MCP 登录或重连会把通过 setMcpServers() 设置的服务器重新列出为你自己的服务器的问题
  • 修复了在 /config 中更改自动更新通道时,在询问插件的 config.set hook 之前就保存的问题
  • macOS:修复了会话启动时的文件计数可能触及其他应用数据的问题——当会话在主目录(home folder)或其上层目录启动时会弹出 "access data from other apps" 提示
  • 改进了 Claude apps gateway 在 Amazon Bedrock 上的 token 计数(/context 和大文件读取会用到):网关现在通过 AWS 的 CountTokens API 获取计数,而不是发出一次单 token 的模型请求。授予 bedrock:CountTokens 即可使用
  • 改进了 Claude apps gateway:当其 PostgreSQL 数据库为只读时,每 30 秒记录一条警告,说明什么失败了以及如何恢复
  • 改进了在 Remote Control、claude.ai 和桌面应用中为等待权限提示的会话显示的状态:现在用 MCP 工具所属服务器及可读名称来命名该工具,而不是其 mcp__server__tool 标识符
  • 改进了 Claude apps gateway 之后的后台请求使用 Haiku 4.5 而非会话的模型,并在网关不提供 Haiku 4.5 时回退到会话的模型
  • 改进了 Claude apps gateway 处理 models: 下未列出的模型的方式:在 AWS 美国地理区域之外的 Amazon Bedrock 区域。AWS 一直拒绝这些请求;网关现在会在你自己的区域中尝试该模型,被拒绝时会指明需要添加的模型
  • 改进了 headless 的 rate_limit_event 用量限制警告,现在会说明账户是否开启了额外用量
  • 改进了内置的插件编写(plugin-authoring)技能:它不再让没有终端的会话运行终端命令,并且仅在被问到时才解释如何分享 mod
  • 改进了 Grep 的输入处理:现在附带 grep 的 -l、-c 或 -r 标志发送的搜索会正常运行,而不是使调用失败
  • 改进了 claude plugin validate 和插件加载:当 hooks 模块因重新绑定(rebound)的顶层变量被拒绝时,错误现在会指出重新绑定该变量的行、原因和修复方法
  • 改进了 Workflow 工具对 scriptPath 的拒绝提示:现在会说明应通过 script 内联传入脚本,这条路径在没有 Read 工具的会话中可用
  • 改进了当 Claude 发送的大文件上传失败且未给出原因时告知 Claude 的内容,使其报告失败而不是缩小文件
  • 更改了模型通过 tool search 加载的 MCP 工具描述:现在在 16,384 字符处截断,而不是 2,048
  • 更改了子代理:最多从 skills 字段预加载 32 个技能,每个一次;拥有 Skill 工具的子代理仍可调用其余技能
  • 更改了在已附加的后台会话的空闲提示处按 Ctrl+C 的行为:它会放过挂起的 /loop 唤醒,因此按两次即可脱离(detach)且循环继续运行;按 Esc 可停止
  • 更改了随其后台服务一起停止的 claude agents(macOS,或未安装该服务的 Linux):正在运行的会话现在会在约一分钟内停止,除非再次运行它,并且会有通知说明这一点
  • 更改了 claude.ai connectors:在不获取任何 flags 的安装上默认协商 MCP 协议版本 2026-07-28;MCP_PROTOCOL_NEGOTIATION=legacy 可退出该行为
  • 更改了没有自身背景的 Artifact 页面:现在显示为白色而不是米白色
  • 更改了当 mod 在工具已运行后拒绝该工具调用时你和 Claude 读到的内容:现在会说明工具已运行且某个插件扣留了其结果
  • 更改了制表符停靠位(tab stops)的计算方式:从文本开始处算起而不是从屏幕左缘算起:缩进 2 格的回答的第一个停靠位在第 8 格,原来是第 6 格
  • 更改了禁用遥测时 Artifact 工具的权限提示:改为与其他安装相同的五个问题,而不是在每次读取他人 artifact 和每次数据编辑前都询问
  • 更改了禁用遥测的安装中定时和 Run now 例程运行:现在无需询问即可发布新的私有 artifact 并更新你自己的 artifact,与其他安装一致
  • 更改了来自你所在组织的 mod 的 toast:现在显示在其他 mod 的 toast 之前,而不是排在后面等待
  • 更改了 Claude apps gateway:启动时带有警告,并提供其捆绑的 Claude Desktop schema 不认识的桌面策略键,因此新的 Desktop 设置无需升级网关
  • 变更了 WebSocket (ws) MCP 服务器:超过 16 MiB 的消息不再被解析,并会关闭连接,这一限制是其他传输方式此前已有的
  • [VSCode] 为 Claude 发送给你的文件新增了一个聊天行:点击文件名即可在编辑器中打开;Claude 的说明文字显示在下方,且该行在 Focus 视图中保持可见
  • [VSCode] 修复了在后台 agent 的活动或面板自身某条状态行出现之后,“Fork conversation from here” 和 Rewind 的会话恢复失败并报 “Message not found in session” 的问题
  • [VSCode] 修复了聊天输入框中的 Ctrl+Shift+Tab、Cmd+Shift+Tab 和 Alt+Shift+Tab 同时切换了权限模式,以及 Ctrl+Tab 会接受建议提示词的问题
  • [VSCode] 修复了键盘焦点在同时可见的两个 Claude 视图之间来回跳动的问题,这可能导致输入的文字被发送到错误的对话
  • Self-hosted runner:变更了 runner,不再将 CCR_AUTO_MODE_ALLOW、CCR_AUTO_MODE_ENVIRONMENT 和 CCR_AUTO_MODE_SOFT_DENY 传入会话的环境
  • Self-hosted runner:修复了在 git 服务器仍在报告大型仓库进度时 git fetch 被截断的问题;CLAUDE_RUNNER_FETCH_SERVER_PROGRESS_CAP_MS 可调整或关闭该等待
  • [Cloud sessions] 修复了取消归档云会话后立即发送的消息有时因无法为其启动容器而得不到回复的问题
  • [Cloud sessions] 修复了部分较旧的 routines 开始运行却从未将保存的提示词交给 Claude 的问题;这些 routines 现在会重新运行其提示词
  • [Cloud sessions] 改进了云会话在连接断开后补齐进度的速度:你错过的活动现在会一次性全部显示,而不是逐行显示
  • [Cloud sessions] 改进了云环境表单中的安装脚本输入框:它初始高度更高,会随你的脚本增长,并且可以通过拖动调整大小
  • [Claude Tag] 变更了 Claude 在 Slack 频道中发布的设置确认卡片,使其保持打开 30 分钟而不是 10 分钟
  • [Claude Tag] 变更了 Claude 关于跨 Enterprise Grid 工作区共享的频道使用组织默认设置的通知,改为仅在有人提及 Claude 时发布,最多每月一次
  • [Claude Tag] 修复了分叉线程的 “Continued from” 卡片中频道链接和 @-提及显示为原始 Slack 代码的问题
  • [Claude Tag] 修复了在 @Claude !restart 已确认重启后,Slack 的 Working 状态仍在线程下方持续转圈的问题
  • [Claude Tag] 修复了在 Claude 已停止读取未标记消息的繁忙频道中,其他应用或 bot 的 @claude 得不到回复的问题
  • [Claude Tag] 在 Claude Tag 管理设置中新增了确认步骤,出现在添加频道管理员之前;添加频道管理员会将该成员移至 Custom roles,这可能移除该成员的其他访问权限
  • [Code Review] 修复了 Code Review 重新审查时在早期发现的问题仍处于打开状态的情况下却报告未发现任何问题;该评论现在会说明仍有多少处于打开状态
  • [Code Review] 修复了当 pull request 编辑该文件时,Code Review 仍会跳过大型 CLAUDE.md 的规则的问题
  • 修复了在 xhigh 和 max effort 下 web 搜索和 agent hook 评估耗时大幅增加的问题
展开原文提取正文(采集端自动提取,可能有缺失)

·

1 commit

to main since this release

Immutable release. Only release title and notes can be modified.

602df92

What's changed

Added onFailure: "block" for command and HTTP hooks: a hook that can't start, times out, or exits with an unexpected code blocks the action instead of letting it through Added Program Status Protocol (OSC 7501) support: terminals that implement it can show whether Claude Code is working, waiting on you, or done Added quoted text to the /copy picker, so a drafted message copies without its > markers Added a warning to claude plugin install, enable, disable and marketplace add when the settings file they write to does not load Added a line on stderr, when it is a terminal, that says what a claude -p run is waiting for when it stays open after its last turn Added support for timeouts.upstream_ttfb_ms on the Claude apps gateway's Bedrock, Vertex, Foundry and other cloud upstreams: a value you set now limits how long a stream may take to start there, after which it fails over or gets a 502 Added a "Backgrounding cancelled" message when you stop the turn while ← is waiting for the current tool to finish Added an optional models list to every Claude apps gateway upstream: only the listed models are sent there, on failover too, and one * in an entry is a wildcard Added support for forceLoginMethod: "gateway" and forceLoginGatewayUrl in your own user settings on machines with no managed settings, so /login opens on that Claude apps gateway Added advice to claude plugin validate when a plugin's README has no install line: it prints the line to paste and never changes the exit code, even with --strict Added upstream_request_id to the Claude apps gateway's inference audit event: the request ID from Amazon Bedrock, the Anthropic API or another upstream, for support cases Added $.ui.notify for mods: raises a native notification through your own notification setting and says which channel sent it Added children to a mod's Button: strings and Text, so a row of a list is one pressable with a chip or a dim detail inside Added CLAUDE_CODE_RETRY_WATCHDOG_MAX_WAIT_MS to limit how long unattended retry mode (CLAUDE_CODE_RETRY_WATCHDOG) waits out 429 and 529 errors Added a request-id header to the Claude apps gateway's successful inference responses, so request_id in Claude Code telemetry matches the gateway's audit log Fixed every request failing on a [1m] model when a gateway, Bedrock, Vertex or Foundry refuses the context-1m beta; Claude Code now resends without it Fixed claude -p text output dropping earlier responses when background work started another turn; each turn's response now prints when the turn ends Fixed remote MCP servers in headless and SDK sessions staying disconnected after an outage longer than 15 seconds, or reconnecting in a tight loop to a server that drops each connection right after it connects; repeated drops now back off, up to 30s Fixed remote MCP connections being dropped when a server's error reply happened to contain a network error name Fixed MCP servers that repeat a pagination cursor being asked for the same page up to 20 times at every connect Fixed CSS, JavaScript and XML files returned by MCP tools being saved as .bin, which the Read tool refuses; font and icon files now get their own extension too Fixed Bash tool calls failing when the model passes command_description instead of description Fixed Claude in Chrome not applying a site deny rule written with port 80 (host:80) to plain http:// pages on that host Fixed /plugin's Errors tab removing a marketplace that failed to load, and uninstalling its plugins, on Enter without asking first Fixed claude plugin marketplace add reporting success for a marketplace whose name no plugin can be installed under; such an add is now refused Fixed CLAUDE_AUTO_BACKGROUND_TASKS moving a subagent to the background while an edit or shell command waited behind it, which started that call before the subagent finished Fixed PushNotification saying a push was not sent in claude remote-control sessions right after a phone message, without the /config toggle, or when started from inside Claude Code Fixed files sent from remote sessions being refused as "could not be vouched for" when more than 256 were sent at once Fixed a rare failure to load managed settings at startup right after a login refresh Fixed /tui exiting without a message, or with a raw system error, when Claude Code could not be started again Fixed a link address shown as text being hidden by a colour or conceal style a reply left on, including where it wraps in a table or a question preview Fixed Fable models listed in availableModels not appearing in the /model picker for sessions signed in to a Claude apps gateway; such a model now shows its built-in row in place of a modelPicker row added for the same model Fixed the Claude apps gateway's admin spend view showing a developer's old groups and group cap after their session stopped carrying groups Fixed CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC hiding the Claude apps gateway spend limit in /usage and the status line. The spend limit request goes to the gateway the session is signed in to Fixed subagents in their own linked worktree being shown the parent session's git branch, status and recent commits Fixed Claude stopping at the end of the current tool when text typed in the prompt cancelled backgrounding with ←; Claude now keeps working in the foreground Fixed --tools and --restricted not applying to built-in tools that register after launch, and deprecated tool names reaching tools outside the caller's tool set Fixed an interrupt not ending the turn until a timeout while Claude waited for an MCP server's resource list Fixed a mod's hook being handed a deeply nested tool input cut short with no error, so a guard could pass content it never saw Fixed Esc not stopping a self-paced /loop that was moved to the background with ←; cancelling a pending wakeup now shows a notice Fixed commands and hooks in background sessions inheriting FORCE_COLOR=3, which put color escape codes into the output Claude reads Fixed claude agents starting a new background service as it exited when both were stopped with a session open (for example at a reboot), which could delay shutdown and restart an interrupted session Fixed a custom agent named worker being shown as "Agent" in auto-mode denial notices and in the activity lists of task detail views Fixed Bash permission checks for for-loops over glob patterns, improving permission-check accuracy Fixed forked skills invoked from Workflow subagents delivering their results to the main conversation instead of the invoking agent Fixed in-process agent teammates failing their first SendMessage call until they loaded the tool through tool search Fixed Claude being told on resume that an unfinished background workflow may have been stopped by TaskStop, which can never be the cause Fixed Claude not being told when you stop a long-running MCP tool call from the tasks panel or a connected client Fixed a background session's /loop stopping without notice when its next wakeup came due while the session's process was down; the session now says so and Claude is told Fixed raw terminal hyperlink bytes in a reply or a teammate's message being drawn as a clickable link with a hidden address Fixed plugin marketplaces whose repository has large git submodules failing to add or refresh: only the submodules that hold plugin files are now fetched Fixed the /advisor dialog showing a checkmark on a saved advisor model that is no longer available; it now opens on "No advisor" Fixed the notification for an MCP tool call that moved to the background showing a shortened task id Fixed vim mode's ~ moving the cursor past the last character of a line, so x after it did nothing, and 3~ running on into the next line Fixed the cursor landing one character too far after pasting accented text copied from macOS (such as a file name) into the middle of the prompt Fixed the terminal freezing, with ctrl+c ignored, when a response ran to tens of thousands of lines Fixed calls a mod makes while it reloads during a plugin hooks worker restart getting past another mod's guard hook that has a .catch; such calls are now refused Fixed plugins whose hooks module nests code thousands of levels deep failing to load or validate with a bare stack-overflow message Fixed claude plugin test passing a session.append hook that removes tool call, tool result or thinking blocks that a real session keeps Fixed Claude not being told it can resume background subagents with SendMessage after a session was killed and resumed a second time Fixed a file being treated as already read after a Bash command such as cat ran without printing it Fixed plugin options named constructor or prototype always reading as their default and never reloading the plugin when edited Fixed a mod's hot reload missing a save made while /reload-plugins or session start was reading the mod's files Fixed the mod hot-reloading question being asked again every turn for the whole session when it is approved without picking an answer Fixed /model, /fast and /output-style saving their setting without asking a plugin's config.set hook Fixed bold text being drawn faint in piped output when it directly follows dim text Fixed replies whose quotes nest deeper every few lines freezing the terminal for seconds and using gigabytes of memory Fixed a mod's hot reload missing a save made within a few milliseconds of its last reload, which left the mod on its old version until the next save Fixed claude mcp serve background Bash results not naming the output file, and its tool description promising a notification that never arrives Fixed an async SessionStart hook's unchanged context being added to the conversation again on every resume Fixed variables a SessionStart hook writes to CLAUDE_ENV_FILE not reaching the Bash tool after an in-app /resume or /branch Fixed a skill's allowed-tools and effort being dropped when the Skill tool finished before the response stream ended, which denied the skill's Bash commands in -p runs Fixed a tampered cache of server-managed settings making a person's own plugin count as organization-managed on machines whose managed settings list or enable plugins Fixed Claude 3 Opus and Claude 3.x Sonnet sessions being offered tool search, which those models reject, where feature flags are unavailable Fixed generated type files being written into a --plugin-dir plugin's folder in -p and SDK sessions; they are now written only where a mod is being developed Fixed text with tabs or bidirectional control characters losing its end at the edge of the screen or drawing over nearby rows Fixed /model saying a Max effort pick was saved as your default for new sessions; Max applies to the current session only Fixed an async hook's JSON output being ignored when it is printed over several lines Fixed the Read tool rejecting calls with an empty pages parameter instead of treating it as omitted Fixed project-scope plugins not loading in VS Code on Windows due to drive-letter casing (#74612) Fixed plugin install and uninstall at project or local scope on Windows missing the install record, or adding a second one, when only the drive letter's case differs Fixed a queued message being lost when pulled back into the prompt with ↑ or Esc just after ←: prompt history now keeps it Fixed mod hot-reloading turning off for the whole session when an SDK host closed its enable question before anyone answered; the question is now asked up to three times Fixed a prompt that a mod's prompt.submit hook rewrote or dropped still being saved as typed to prompt history and to the transcript's queued-prompt records Fixed non-interactive sessions telling you about MCP servers that need authentication when your request doesn't use them Fixed the claude_code.auth OpenTelemetry login event not being emitted on Claude apps gateway sign-in. The event is exported when OpenTelemetry is configured on the machine or the session is already signed in to the gateway Fixed a plugin that adds very large interfaces getting another plugin unloaded when the plugin hooks worker stalls Fixed Edit treating a file as fully read when its contents changed without its modification time advancing Fixed short command output with Windows line endings (CRLF) being drawn on a single line Fixed a stopped scheduled task coming back on resume after a rewind, and a scheduled task being lost on resume after Esc or a rewind following a compaction Fixed the terminal freezing for seconds or minutes while syntax highlighting code with very long lines, long runs of blank lines, or unclosed strings and heredocs Fixed temporary files left under ~/.claude/seed-admin by an interrupted /ultrareview upload never being removed by the retention cleanup Fixed Desktop and SDK sessions refusing to switch back to auto mode until restart after disableAutoMode was removed from settings Fixed claude.ai-synced plugin hooks failing with "Plugin directory does not exist" in long-running sessions after another session synced a plugin update Fixed the prompt sent after a /rewind being lost, and the removed turns coming back, when the session was moved to the background or resumed after being killed Fixed cloud sessions hanging when a mod's session.receive hook asked for permission before passing a message on Fixed macOS background sessions that restart together after an update sometimes running outside the stable app wrapper, so folder-access prompts could reappear Fixed an MCP sign-in or reconnect that finishes late in headless and SDK sessions relisting a server set with setMcpServers() as your own Fixed changing the auto-update channel in /config saving before a plugin's config.set hook was asked macOS: Fixed a file count at session start that could reach other apps' data and raise the "access data from other apps" prompt when a session starts in the home folder or above it Improved token counts behind a Claude apps gateway on Amazon Bedrock, which /context and large file reads use: the gateway now gets them from AWS's CountTokens API instead of a one-token model request. Grant bedrock:CountTokens to use it Improved the Claude apps gateway to log a warning every 30 seconds while its PostgreSQL database is read-only, saying what fails and how to recover Improved the status shown in Remote Control, claude.ai and the desktop app for a session waiting on a permission prompt to name an MCP tool by its server and readable name instead of its mcp__server__tool identifier Improved background requests behind a Claude apps gateway to use Haiku 4.5 instead of the session's model, falling back to the session's model where the gateway does not serve Haiku 4.5 Improved how the Claude apps gateway handles models not listed under models: in Amazon Bedrock regions outside AWS's US geography. AWS always refused those requests; the gateway now tries the model in your own region, and a refusal names the model to add Improved headless rate_limit_event usage-limit warnings to say whether the account has extra usage turned on Improved the built-in plugin-authoring skill: it no longer tells a session with no terminal to run terminal commands, and explains sharing a mod only when asked Improved Grep input handling: a search sent with grep's -l, -c or -r flag now runs instead of failing the call Improved claude plugin validate and plugin loading: when a hooks module is refused over a rebound top-level var, the error now names the line that rebinds it, the cause, and a fix Improved the Workflow tool's scriptPath refusal: it now says to pass the script inline via script, the route that works in sessions without a Read tool Improved what Claude is told when a large file it sends fails to upload with no reason given, so it reports the failure instead of shrinking the file Changed MCP tool descriptions the model loads through tool search to be cut at 16,384 characters instead of 2,048 Changed subagents to preload at most 32 skills from the skills field, each once; a subagent with the Skill tool can still invoke the rest Changed Ctrl+C at the idle prompt of an attached background session to leave a pending /loop wakeup alone, so pressing it twice detaches and the loop keeps running; press Esc to stop it Changed claude agents stopped with its background service (macOS, or Linux without the service installed): running sessions now stop in about a minute unless it is run again, and a notice says so Changed claude.ai connectors to negotiate MCP protocol version 2026-07-28 by default on installs that fetch no flags; MCP_PROTOCOL_NEGOTIATION=legacy opts out Changed Artifact pages with no background of their own to show on white instead of off-white Changed what Claude and you read when a mod denies a tool call after the tool ran: it now says the tool ran and a plugin withheld its result Changed tab stops to count from where a text starts instead of from the screen's left edge: an answer indented by 2 has its first stop 8 cells in, where it was 6 Changed the Artifact tool's permission prompts with telemetry disabled to the same five questions other installs get, instead of asking before each read of someone else's artifact and each data edit Changed scheduled and Run now routine runs in installs with telemetry disabled to publish new private artifacts, and update your own, without asking, as in other installs Changed toasts from your organization's mods to show ahead of other mods' toasts instead of waiting behind them Changed the Claude apps gateway to start with a warning and serve a desktop policy key its bundled Claude Desktop schema doesn't know, so new Desktop settings need no gateway upgrade Changed WebSocket (ws) MCP servers: a message over 16 MiB is no longer parsed and closes the connection, the limit the other transports already have [VSCode] Added a chat row for files Claude sends you: click a file's name to open it in the editor; Claude's caption shows underneath, and the row stays visible in Focus view [VSCode] Fixed "Fork conversation from here" and Rewind's conversation restore failing with "Message not found in session" after a background agent's activity or one of the panel's own status lines [VSCode] Fixed Ctrl+Shift+Tab, Cmd+Shift+Tab and Alt+Shift+Tab in the chat input also switching the permission mode, and Ctrl+Tab accepting the suggested prompt [VSCode] Fixed keyboard focus bouncing between two Claude views visible at once, which could send typed text to the wrong conversation Self-hosted runner: Changed the runner to stop passing CCR_AUTO_MODE_ALLOW, CCR_AUTO_MODE_ENVIRONMENT and CCR_AUTO_MODE_SOFT_DENY into a session's environment Self-hosted runner: Fixed git fetches being cut off while the git server was still reporting progress on a large repository; CLAUDE_RUNNER_FETCH_SERVER_PROGRESS_CAP_MS tunes or turns off the wait [Cloud sessions] Fixed a message sent right after unarchiving a cloud session sometimes getting no reply because no container could start for it [Cloud sessions] Fixed some older routines starting their runs without ever giving Claude their saved prompt; those routines now run their prompt again [Cloud sessions] Improved how quickly a cloud session catches up after its connection drops: activity you missed now appears all at once instead of row by row [Cloud sessions] Improved the setup script box in the cloud environment form: it starts taller, grows with your script, and can be resized by dragging [Claude Tag] Changed the settings confirmation cards Claude posts in a Slack channel to stay open for 30 minutes instead of 10 [Claude Tag] Changed Claude's notice that a channel shared across Enterprise Grid workspaces uses organization defaults to post only when someone mentions Claude, at most once a month [Claude Tag] Fixed channel links and @-mentions in a forked thread's "Continued from" card showing as raw Slack codes [Claude Tag] Fixed Slack's Working status spinning on under a thread after @Claude !restart had already confirmed the restart [Claude Tag] Fixed another app's or bot's @claude going unanswered in a busy channel where Claude had stopped reading untagged messages [Claude Tag] Added a confirmation in Claude Tag admin settings before adding a channel manager moves that member to Custom roles, which can remove their other access [Code Review] Fixed Code Review re-reviews saying no issues were found while earlier findings were still open; the comment now says how many remain open [Code Review] Fixed Code Review still skipping a large CLAUDE.md's rules when the pull request edits that file Fixed web searches and agent hook evaluations taking much longer at xhigh and max effort

原文入口

阅读原文(github.com)

原文将在新窗口打开。收录时间不是内容更新时间;正文、译文与解读的版权归原作者/来源所有,本站仅作个人阅读辅助并保留原文入口;页面时间均为北京时间。

作者/署名来自原文结构化字段(Atom/RSS/HTML meta/JSON-LD;GitHub release 显示的是发布者账号),未经模型补充。

了解来源批准与收录规则