Claude Code v2.1.271 发布：Remote 会话新增快速模式与大量权限、MCP 和 Artifact 改进

更新内容

• 为 Claude Code Remote 会话（云端及自托管 runner）加入快速模式：在组织允许的情况下，主机的快速模式设置或在会话中输入的 /fast 均会生效
• 为全屏模式下的 /config 面板加入鼠标支持：滚轮可滚动设置列表，点击某项设置的值即可更改，鼠标指针所在行将高亮显示
• 新增 claude self-hosted-runner --drain-marker-file <path>：当 SIGTERM 排空期间该文件存在时，runner 会将退出情况作为主机排空报告给服务器（仅用于遥测）
• 在启用沙箱的自动模式中，为 Bash、PowerShell 和 Monitor 新增按命令设置的 allowed_domains：命令所需访问的主机会与命令一同接受审核，并仅为该命令开放；其他主机将被拒绝
• 在 agent frontmatter 和 --agents JSON 中新增 omitClaudeMd，允许自定义及插件子代理在不加载用户、项目和本地 CLAUDE.md 文件的情况下运行；受管策略文件仍会加载
• 为 claude plugin install 和 claude plugin update 新增 --accept-command <sha256>，可精确确认先前 --json 运行所显示的命令，而无需使用 -y
• 在 modelPricing 受管设置及 Claude apps gateway 的 pricing 配置块中，新增大于 1、最高为 10 的 multiplier 支持，用于设定加价后的内部成本分摊费率
• 新增加载动画提示，引导 Bedrock、Vertex AI、Foundry 和 LLM gateway 用户使用 Claude 桌面应用；claude.ai 桌面应用提示现在建议使用 /desktop，该命令可提供应用下载
• 修复切换账户、组织或 API 密钥后继续复用缓存组织策略的问题，以及会话中途凭据变更后策略要等到每小时检查才刷新的问题
• 修复启动后组织策略加载完成或会话中途策略发生变化时，工具和命令列表未更新的问题
• 修复无法读取或解析企业 managed-mcp.json 时被忽略的问题：现在该文件仍会保持 MCP 的排他控制权（不会加载用户、项目和插件服务器），并在启动时发出警告
• 修复通过由 ANTHROPIC_UNIX_SOCKET 配置的第三方本地代理获取组织策略并遭拒绝的问题；这些代理现在会再次与其他自定义 gateway 一样处理，包括用于 Remote Control
• 修复在会话 worker 重启后应用工作流或 agent 审批时，云端会话拒绝所有子代理工具调用（updatedInput … failed schema validation）的问题
• 修复当组织禁用快速模式时，/fast off 返回“Fast mode unavailable”而非关闭快速模式的问题
• 修复以 CLAUDE_CODE_SKIP_FAST_MODE_ORG_CHECK 启动的会话，在 API 拒绝快速模式后每一轮都重新发送快速请求的问题；现在拒绝结果将持续生效，并显示其原因
• 修复在 CLAUDE_CODE_RETRY_WATCHDOG 下，快速模式遇到使用额度上限时导致该轮失败，或在服务过载时仍以快速速度重试而非回退至标准速度的问题
• 修复 Bash 权限检查遗漏 fmt、column 等命令读取的文件的问题，该问题发生在文件参数位于检查器无法识别的选项之后时
• 修复 Bash 权限检查跳过通配符展开文件的问题，当通配符位于命令的模式或选项值中时会出现该问题，例如 grep -v dir/* file
• 修复 Bash 权限检查，使 shell 变量声明标志无法错误描述实际运行的命令
• 修复在 bypass 和自动模式下，具有两次目录切换、子 shell 或 cd+git 链的 Bash 命令，会绕过 permissions.blockReadsOutsideWorkingDirectories 提示的问题
• 修复沙箱命令启动失败后，残留的 .git/config.lock 会在后续整个会话中破坏 git checkout -b、git push -u 和 git config 的问题（Linux）
• 修复系统文件事件服务饱和的 macOS 设备未能发现会话外设置文件变更的问题；监视器现会回退至轮询机制
• 修复恢复的 claude -p 会话在其工具全部来自 MCP 服务器时，因 “At least one tool must have defer_loading=false” 而失败的问题
• 修复当 LLM gateway 以 text/plain 返回非流式响应时，回合因 “API returned an empty or malformed response” 失败的问题
• 修复 MCP 服务器高频循环发送 list_changed 通知时，持续占用大量 CPU 并反复请求工具列表的问题
• 修复 MCP OAuth 对客户端注册处理不当的问题：拒绝同意会强制创建新的注册、其他重定向 URI 的注册会被复用，以及并发写入可能删除有效注册或保留不匹配注册的问题
• 修复当 Claude 以 MCP 工具的裸名称而非完整 mcp__server__tool 名称选择工具时，工具搜索不返回匹配项的问题
• 修复 Ctrl+O 取消待处理 MCP 服务器重连的问题，以及在转录视图打开时从 Remote Control 发送 /mcp 失败的问题
• 修复 Claude in Chrome 在 ToolSearch 不可用时仍提示模型通过 ToolSearch 加载工具的问题
• 修复由接收会话权限模式策略暂存的跨会话消息没有留下任何痕迹的问题：无头发送方现在会收到送达通知，且 SendMessage 结果不再暗示消息已被阅读
• 修复在对话被压缩后，Claude 会启动仍在运行的后台命令（如 watch 任务或开发服务器）的第二个副本的问题
• 修复 /model 在切回对话实际运行的模型时，错误警告会丢失对话缓存的问题
• 修复 /reload-skills 在执行 /cd 后报告的技能数量与斜杠菜单不一致的问题
• 修复短终端中的全屏模式下，/resume 和 /continue 仅显示 1—2 个会话的问题
• 修复 /resume 和 /teleport 保留前一段对话的文件读取追踪记录的问题，此前 Claude 因此可以编辑恢复后的对话从未读取过的文件
• 修复当恢复会话的模型系列与配置的默认模型不同，--resume 会丢失 100 万上下文窗口（[1m]）的问题
• 修复通过 /artifacts 附加的 Artifact 在执行 --resume 后从会话中消失的问题
• 修复后台会话（claude --bg、claude agents）不监视其已发布 Artifact 在其他位置重新发布的情况
• 修复在报告 inode 为 0 的虚拟驱动器中（例如作为 Windows 驱动器挂载的加密保险库），除第一个之外的自定义 Agent、斜杠命令和输出样式无法加载的问题
• 修复自托管 runner 会话在主机配置目录超过 64 MiB 时静默丢失全部主机配置（设置、技能、插件、MCP 服务器）的问题；新增 --host-config-snapshot disk|memory
• 修复从 claude.ai 同步的技能在退出登录后无限期保留在磁盘上的问题；未在 cleanupPeriodDays 内刷新的副本将在下次启动时移至可恢复的废纸篓
• 修复加载动画提示推荐当前账户类型不可用或在当前会话中被禁用命令的问题
• 修复 /add-dir 路径输入：左右方向键现在可移动光标，Enter 只会添加输入的路径，不会同时添加高亮的补全项
• 修复主提示框之外的文本字段会将开头 ! 移至输入内容末尾的问题（!foo 会变成 foo!）
• 修复当 hook 匹配器以继承对象属性命名（如 __proto__ 或 constructor）时，交互式 /hooks 菜单崩溃的问题
• 修复全屏渲染故障：文本周围的框失去背景后，文本仍保留过期背景颜色
• 修复附加的后台会话中，st 终端的 Delete 键和 rxvt-unicode 中 Alt+方向键无法工作的问题
• 修复当 Claude Code 退出、被挂起，或启动后立即打开编辑器时，终端对能力查询（^[[?1;2c）的回复出现在 shell 提示符或编辑器中的问题
• 改进终端渲染性能：大型 diff 和长转录内容渲染更快，卡顿帧更少
• 通过跳过每次启动时对内置模型数据的冗余验证，略微改善启动时间
• 改进 hook 反馈：在 SessionStart、UserPromptSubmit、PreToolUse 或 SessionEnd hook 运行期间，加载动画会显示相应状态及耗时；Esc 可取消正在等待 SessionStart hook 的提示
• 改进长时间思考时的加载动画状态：45 秒后显示“deep in thought”，在从输出 token 限制中恢复时显示“picking the thought back up”
• 改进动态工作流：达到使用额度上限时会暂停，并在额度重置后自动继续，而不再丢弃受影响的 Agent
• 改进 Remote Control：在不稳定网络下设置失败时，减少在 claude.ai 上留下的空会话
• 改进云端会话中的 Claude in Chrome 信息：当无法连接浏览器时，现在会先说明计算机可能处于休眠状态，再建议安装
• 改进 claude mcp serve：正在运行的工具调用现在每 30 秒发送一次进度更新，使客户端显示其仍在运行，并防止空闲超时中止不输出内容的长命令
• 改进 Foundry 和 Claude Platform on AWS 会话：在对话中途完成连接的 alwaysLoad MCP 服务器，可在下一轮直接使用，无需经过工具搜索往返
• 改进以 Artifact 发布的 Markdown 文件：现在会渲染为带样式的文档页面，包括标题页眉、文档排版和语法高亮代码
• 改进 Artifact 工具的发布错误提示：没有文件的发布现在会提示先将页面写入文件；不支持的文件类型会先于缺少 favicon 的问题进行报告
• 改进当页面声明的能力超出其 contract 版本支持范围时，Artifact 工具的错误信息：现在会列出所有受支持能力，并标注哪些能力可由更新的 contract 版本提供
• 改进 Artifact 监视：一个会话现在最多可同时监视 10 个已发布 Artifact 在其他位置的重新发布情况，高于此前的 5 个
• 改进 PDF @ 提及：当 pdfinfo 无法计算页数时，现在显示“page count unknown”，而非根据文件大小猜测页数
• 改进 /mobile：现在显示一个指向 claude.ai/mobile 的二维码，可根据手机打开正确的应用商店
• 更改自动模式：技能或斜杠命令内联的 ! shell 命令现在遵循默认模式的权限规则，而不是分类器；没有规则决定的命令将作为已审核的工具调用运行
• 更改自动模式：子代理现在通过专用的回传调用向调用方报告，该调用将由安全分类器审核；此前会在其最后一条消息发出后再进行审核
• 更改 Monitor 监视：现在始终设有截止时间（最长 30 分钟；单提示 -p 运行中为 10 分钟），并通知 Claude 重新启用监视，取代无超时的 persistent 选项
• 将提示中的 IDE 选区指示符改为 [⧉ …] 标签：该标签会随文本换行而非挤压多行提示；可使用 Backspace 删除以不包含选区
• 将 Pro 方案的默认动态工作流规模改为 small，并将 medium 规模的建议阈值从 15 个 Agent 降至 10 个
• 更改 Claude apps gateway、Bedrock、Vertex AI 和 Foundry 会话：不再刷新该会话未使用的残留 claude.ai 登录状态
• 更新内置 claude-api 技能：为流式自定义工具启用 eager_input_streaming，并使用 user.define_outcome 启动交付物导向的 Managed Agents 工作
• [VSCode] 新增“Attach Open File”设置：关闭后，打开的文件将不再添加至消息，但选中文本仍会附加
• [VSCode] 修复 Hooks 和 Permission rules 对话框将实际成功的保存报告为失败的问题，以及 Hooks 对话框在仅插件策略锁定下变为空白或在保存错误中显示颜色代码的问题
• [VSCode] 修复 Hooks 对话框保存：替换时不再产生重复 hook；以不同大小写重新输入 header 名称仍会保留其 secret；并会在保存返回前将 settings.local.json 加入 gitignore
• [VSCode] 修复当工作区位于 Windows 映射网络驱动器或 SUBST 驱动器上时，会话历史仅显示当前会话的问题
• [VSCode] 修复会话列表的 Active 筛选器在筛选菜单同时勾选 Open 时，隐藏处于空闲状态的打开会话的问题
• [VSCode] 修复会话列表刷新时，新聊天会切换回上一聊天的问题
• [VSCode] 修复当 environmentVariables 设置中的 CLAUDE_CONFIG_DIR 变更后，打开的标签页和侧边栏在窗口重新加载前仍保留旧配置目录的问题
• [VSCode] 修复扩展运行 git、ripgrep 和登录状态检查等后台命令时，Windows 上控制台窗口闪烁的问题
• [VSCode] 修复提示缓存时钟的悬停文本仅在延迟后出现的问题，以及自动压缩图标在弹窗旁显示浏览器自身工具提示的问题
• [VSCode] 改进 Hooks 对话框：因设置文件自身问题而被拒绝的保存，现在会打开一个弹窗，提供“Open settings file”按钮，并在“Copy error”后显示原因
• [VSCode] 将开关的开启状态颜色从 Claude 橙色改为编辑器主题的按钮颜色
• [Claude Code on the web] 修复云端会话在进程退出、但会话仍显示在线时，有时约需十分钟才响应的问题；现在发送消息会立即重启该会话
• [Claude Code on the web] 将 claude.ai/code 上的 Routines 页面改为新布局：提供 Yours 和 Templates 标签页，以及显示运行状态的双栏 routine 卡片；移除了日历视图
• [Claude Code on the web] 在管理设置的 Cloud environments 编辑器中新增 Custom network access 选项，提供与 claude.ai/code 环境对话框相同的允许域名列表
• [Claude Code on the web] 改进 Cloud environments 管理页面：显示 Claude Tag 和 Claude Code 的默认环境及用于更改的链接，并标记建议创建的环境类型
• [Claude Tag] 修复 Claude 在保持活跃状态的频道中丢失其工作上下文的问题（原文在此处截断）

1. Releases
2. v2.1.271

Compare

Sorry, something went wrong.

No results found

What's changed

• Added fast mode in Claude Code Remote sessions (cloud and self-hosted runners): the host's fast-mode setting or /fast typed in the session applies where your organization allows it
• Added mouse support to the /config panel in fullscreen mode: the wheel scrolls the settings list, a click on a setting's value changes it, and the row under the pointer is highlighted
• Added claude self-hosted-runner --drain-marker-file <path>: when that file exists at a SIGTERM drain, the runner reports its exit to the server as a host drain (telemetry only)
• Added per-command allowed_domains to Bash, PowerShell and Monitor in auto mode with sandboxing: the hosts a command needs are reviewed with it and opened for it alone; other hosts are refused
• Added omitClaudeMd to agent frontmatter and --agents JSON, letting custom and plugin subagents run without user, project and local CLAUDE.md files; managed policy files still load
• Added --accept-command <sha256> to claude plugin install and claude plugin update to accept exactly the command a previous --json run displayed, instead of -y
• Added support for a multiplier above 1, up to 10, in the modelPricing managed setting and the Claude apps gateway pricing block, for marked-up internal chargeback rates
• Added a spinner tip pointing Bedrock, Vertex AI, Foundry and LLM gateway users to the Claude desktop app; the claude.ai desktop app tip now suggests /desktop, which offers to download the app
• Fixed a cached organization policy being reused after switching accounts, organizations, or API keys, and the policy not refreshing until the hourly check when the credential changes mid-session
• Fixed the tool and command lists not updating when the organization policy finishes loading after startup or changes mid-session
• Fixed an enterprise managed-mcp.json that can't be read or parsed being ignored: it now keeps exclusive MCP control (user, project and plugin servers don't load) and warns at startup
• Fixed org policy being fetched through, and rejected by, third-party local proxies set via ANTHROPIC_UNIX_SOCKET; they are again treated like other custom gateways, including for Remote Control
• Fixed cloud sessions rejecting every subagent tool call ("updatedInput … failed schema validation") when a workflow or agent approval was applied after the session's worker restarted
• Fixed /fast off answering "Fast mode unavailable" instead of turning fast mode off when the organization has fast mode disabled
• Fixed sessions started with CLAUDE_CODE_SKIP_FAST_MODE_ORG_CHECK re-sending fast requests every turn after the API rejected fast mode; the rejection now stands and its reason is shown
• Fixed fast mode under CLAUDE_CODE_RETRY_WATCHDOG failing the turn on a usage-credits limit, or retrying an overload at fast speed, instead of falling back to standard speed
• Fixed Bash permission checks missing the file that fmt, column and similar commands read when it follows an option the checker doesn't recognize
• Fixed Bash permission checks skipping files a wildcard expands to when the wildcard sits in a command's pattern or option value (for example grep -v dir/* file)
• Fixed Bash permission checks so that shell variable declaration flags cannot misrepresent the command being run
• Fixed Bash commands with two directory changes, a subshell, or a cd+git chain skipping the prompt under permissions.blockReadsOutsideWorkingDirectories in bypass and auto mode
• Fixed a stale .git/config.lock breaking git checkout -b, git push -u and git config for the rest of a session after a sandboxed command failed to start (Linux)
• Fixed settings file changes made outside the session going unnoticed on macOS machines whose system file-event service is saturated; the watcher now falls back to polling
• Fixed resumed claude -p sessions whose tools all come from MCP servers failing with "At least one tool must have defer_loading=false"
• Fixed turns failing with "API returned an empty or malformed response" when an LLM gateway returns the non-streaming reply as text/plain
• Fixed sustained high CPU usage and repeated tool-list requests when an MCP server sends list_changed notifications in a tight loop
• Fixed MCP OAuth mishandling client registrations: denying consent forced a new one, one for another redirect URI was reused, and a concurrent write could delete a valid one or keep a mismatched one
• Fixed tool search returning no match when Claude selects an MCP tool by its bare name instead of its full mcp__server__tool name
• Fixed Ctrl+O cancelling pending MCP server reconnects, and /mcp sent from Remote Control failing while the transcript view is open
• Fixed the Claude in Chrome prompt telling the model to load tools through ToolSearch when ToolSearch is unavailable
• Fixed cross-session messages held by the receiving session's permission-mode policy leaving no trace: headless senders now get a delivery notice, and SendMessage results no longer imply it was read
• Fixed Claude starting a second copy of a background command (such as a watch task or dev server) that was still running after the conversation was compacted
• Fixed /model warning about losing the conversation cache when switching back to the model the conversation actually ran on
• Fixed /reload-skills reporting a skill count that disagreed with the slash menu after /cd
• Fixed /resume and /continue showing only 1-2 sessions in fullscreen mode on short terminals
• Fixed /resume and /teleport keeping the previous conversation's file-read tracking, so Claude could edit files the resumed conversation had never read
• Fixed --resume dropping the 1M context window ([1m]) when the resumed session's model family differs from the configured default model
• Fixed artifacts attached with /artifacts disappearing from the session after --resume
• Fixed background sessions (claude --bg, claude agents) not watching the artifacts they publish for republishes made elsewhere
• Fixed custom agents, slash commands and output styles beyond the first not loading from a virtual drive that reports inode 0, such as an encrypted vault mounted as a Windows drive
• Fixed self-hosted runner sessions silently losing all host config (settings, skills, plugins, MCP servers) when the host config directory exceeds 64 MiB; added --host-config-snapshot disk|memory
• Fixed skills synced from claude.ai staying on disk indefinitely after signing out; copies not refreshed within cleanupPeriodDays now move to the recoverable trash at the next launch
• Fixed spinner tips suggesting commands that aren't available for your account type or are disabled in your session
• Fixed the /add-dir path input: the left and right arrow keys now move the cursor, and Enter adds only the typed path instead of also adding the highlighted completion
• Fixed text fields outside the main prompt moving a leading ! to the end of what you typed (!foo came out as foo!)
• Fixed the interactive /hooks menu crashing when a hook matcher is named after an inherited object property such as __proto__ or constructor
• Fixed a fullscreen rendering glitch where text kept a stale background color after the box around it lost its background
• Fixed Delete in st and Alt+arrow keys in rxvt-unicode not working in attached background sessions
• Fixed the terminal's replies to capability queries (^[[?1;2c) appearing at the shell prompt or in an editor when Claude Code exits, is suspended, or opens an editor right after starting
• Improved terminal rendering performance: large diffs and long transcripts render faster, with fewer slow frames
• Improved startup time slightly by skipping a redundant validation of built-in model data on every launch
• Improved hook feedback: while a SessionStart, UserPromptSubmit, PreToolUse or SessionEnd hook runs, the spinner says so with elapsed time, and Esc cancels a prompt waiting on a SessionStart hook
• Improved the spinner status during long thinking: it now reads "deep in thought" after 45s, and shows "picking the thought back up" while recovering from the output-token limit
• Improved dynamic workflows to pause when you hit your usage limit and continue automatically when it resets, instead of dropping the affected agents
• Improved Remote Control to leave fewer empty sessions on claude.ai when setup fails on a flaky network
• Improved the Claude in Chrome message in cloud sessions when the browser can't be reached: it now says the computer may be asleep before it suggests an install
• Improved claude mcp serve: a running tool call now sends a progress update every 30 seconds, so clients show it is still running and idle timeouts don't abort a long command that prints nothing
• Improved Foundry and Claude Platform on AWS sessions: an alwaysLoad MCP server that finishes connecting mid-conversation is usable on the next turn without a tool-search round trip
• Improved Markdown files published as artifacts: they now render as styled document pages (title header, document typography, syntax-highlighted code)
• Improved Artifact tool publish errors: a publish with no file now says to write the page to a file first, and an unsupported file type is reported before a missing favicon
• Improved the Artifact tool's error when a page declares a capability its contract version lacks: it now lists every supported capability and notes when a newer contract version has it
• Improved artifact watching: a session can now watch up to 10 published artifacts at once for republishes made elsewhere, up from 5
• Improved PDF @-mentions to say "page count unknown" instead of a page count guessed from the file size when pdfinfo cannot count the pages
• Improved /mobile to show a single QR code for claude.ai/mobile, which opens the right app store for your phone
• Changed auto mode so that a skill's or slash command's inline ! shell commands follow default-mode permission rules instead of the classifier; a command no rule decides runs as a reviewed tool call
• Changed auto mode so a subagent reports back to its caller through a dedicated hand-back call that the safety classifier reviews, instead of its last message being reviewed after the fact
• Changed Monitor watches to always have a deadline (at most 30 minutes; 10 in single-prompt -p runs) and notify Claude to re-arm, replacing the no-timeout persistent option
• Changed the IDE selection indicator in the prompt to a [⧉ …] pill that wraps with the text instead of squeezing multi-line prompts; delete it with Backspace to leave the selection out
• Changed the default dynamic workflow size to small on Pro plans and lowered the medium size guideline from 15 to 10 agents
• Changed Claude apps gateway, Bedrock, Vertex AI, and Foundry sessions so that they no longer refresh a leftover claude.ai login that the session does not use
• Updated the bundled claude-api skill to enable eager_input_streaming on streaming custom tools, and to start deliverable-shaped Managed Agents work with user.define_outcome
• [VSCode] Added an Attach Open File setting that, when turned off, stops the open file from being added to messages; selected text is still attached
• [VSCode] Fixed the Hooks and Permission rules dialogs reporting a save that landed as failed, and the Hooks dialog going blank under a plugin-only policy lock or showing color codes in save errors
• [VSCode] Fixed Hooks dialog saves: no duplicate hook on replace, a header name retyped in other capitals keeps its secret, and settings.local.json is gitignored before the save returns
• [VSCode] Fixed session history showing only the current session when the workspace is on a Windows mapped network drive or SUBST drive
• [VSCode] Fixed the session list's Active filter hiding open idle sessions when Open is also checked in the filter menu
• [VSCode] Fixed a new chat switching back to the previous chat when the session list refreshed
• [VSCode] Fixed open tabs and the side bar keeping the old config folder until a window reload after CLAUDE_CONFIG_DIR changed in the environmentVariables setting
• [VSCode] Fixed console windows flashing on Windows when the extension runs background commands such as git, ripgrep, and the sign-in status check
• [VSCode] Fixed the prompt cache clock's hover text appearing only after a delay, and the auto-compact icon showing the browser's own tooltip beside its popup
• [VSCode] Improved the Hooks dialog: a save refused because of the settings file itself now opens a popup with an "Open settings file" button and the reason behind "Copy error"
• [VSCode] Changed the on state of toggle switches from Claude orange to the editor theme's button color
• [Claude Code on the web] Fixed a cloud session sometimes taking about ten minutes to respond after its process exited while the session still looked live; sending a message now restarts it right away
• [Claude Code on the web] Changed the Routines page on claude.ai/code to a new layout with Yours and Templates tabs and two-column routine cards that show run status, and removed its calendar view
• [Claude Code on the web] Added a Custom network access option to the Cloud environments editor in admin settings, with the same allowed-domains list the environment dialog on claude.ai/code offers
• [Claude Code on the web] Improved the Cloud environments admin page: it shows the default environment for Claude Tag and Claude Code, with a link to change it, and marks the recommended kind to create
• [Claude Tag] Fixed Claude in a channel where it stays active losing its working context about once an hour when the conversation is mostly in threads; thread activity now keeps it from being reset
• [Claude Tag] Fixed a thread that asked Claude to watch a pull request no longer hearing about CI failures, comments and reviews after Claude was restarted in that thread
• [Claude Tag] Fixed deleting the first message of a thread Claude had already replied in not ending Claude's work there; it now stops, as it did when a message with no replies was deleted
• [Claude Tag] Fixed Claude holding back a post because of an earlier instruction addressed to a different bot or assistant; only instructions addressed to Claude bind it, and it asks when unsure
• [Claude Tag] Fixed the reply-mode card Claude posts on joining a busy channel saying it "sees a lot of automated posts" when the channel is only chatty or large; the card now names the real reason
• [Claude Tag] Improved the Environment picker in Claude Tag admin settings: options are labeled Anthropic-hosted or self-hosted, with links to edit that environment or create one
• [Code Review] Fixed a pull request in a repository reviewed once per PR sometimes getting no review when a commit arrived while its review was waiting to start; it now reviews the requested commit
• [Code Review] Fixed Code Review occasionally posting the same findings two or three times when GitHub reported an error for a review it had in fact created
• [Code Review] Fixed follow-up reviews re-posting a security finding a person had already resolved when a later push moved the lines it was anchored to
• [Code Review] Fixed reopening a finished /ultrareview cloud session in the Claude app starting the whole review over again unprompted
• Windows: Fixed PowerShell commands failing with "Exit code 1" and no output when the session's temp output path reaches 260 characters

You can’t perform that action at this time.