Claude Code v2.1.247

更新内容

• 新增 SendFeedback 工具：当会话中出现问题时，Claude 可以起草一份反馈报告，供你通过 /feedback 审阅并发送（可通过 feedbackDrafts 设置关闭）。
• 为 spinnerTipsOverride 新增 {id, text, cooldownSessions, priority} 条目、tipsFile 和 label，使组织能够将自定义提示与内置提示一同轮换展示。
• 在 Bash 权限提示中新增一条指向自动模式的提示，并提供“一键确认并切换至自动模式”的选项。
• 新增 /claude-api cost-optimize，用于分析现有项目的 Claude API 支出，并一次实施一项可量化的优化措施，包括缓存、Token 卫生、批处理、推理强度和模型选择。
• 更新 /claude-api 技能，覆盖 Admin API 功能，包括组织成员、邀请、工作区、API 密钥、速率限制报告、工作负载身份联合和 CMEK。
• 修复在历史搜索、/config、/mcp、/skills、后台任务和 /model 中快速连续按方向键与 Enter 时，操作会错误作用于导航目标上一行的问题。
• 修复子 Agent 在首次调用模型时遇到 404 后退出的问题：现在会使用会话的后备模型链，返回给父 Agent 的错误信息也包含错误类型、状态码、请求 ID 和模型。
• 修复 Hook 或后台 Agent 输出数 MB 错误信息时可能导致对话溢出，并使会话卡在“Prompt is too long”的问题。
• 修复在使用 kitty 协议终端的非拉丁键盘布局（例如西里尔字母布局）下，Ctrl 键盘快捷键无法触发的问题。
• 修复鼠标报告在转义前缀之后被拆分读取时，可能将 <35;150;7M 等文本插入提示词的问题。
• 修复 Bash 沙箱的命令后清理操作会删除由 dotfile 管理的 ~/.claude/settings.json 符号链接的问题；该问题出现在链接被重新指向沙箱可写区域之外时，例如使用 nix/home-manager 或 stow 的场景。
• 修复 /terminal-setup 会覆盖整个 Zed keymap.json、而非合并其快捷键绑定的问题。
• 修复当会话注册表无法更新时，/rename 会静默确认的问题；现在会提示其他会话可能仍显示旧名称。
• 修复通过 --agent 启动的会话中，/compact 和“Summarize from here”会基于默认系统提示词、而非当前对话自身提示词进行摘要的问题。
• 修复后台会话的终端宿主进程退出后，claude agents 中持续显示“opening…”的问题；现在该行会在数秒内以失败状态显示原因，按 Enter 可重新启动。
• 修复当 Hook 或后台任务的输出文件无法写入时，内存可能无限增长的问题；文件现在会注明输出丢失的位置。
• 修复通过 SSH 使用 /install-github-app 时的问题：复制快捷方式现在会说明登录 URL 是如何被复制的，而不再始终声称复制成功；当无法打开浏览器时，URL 会立即显示。
• 修复从前台继承的 shell 命令在后台会话中完成时，可能记录内部错误或显示误导性 [exited with code -1] 行的问题。
• 修复无版本号的市场插件在第二个作用域安装时，其实时缓存目录会被删除并重新创建的问题；这可能干扰正在使用该插件的运行中会话。
• 修复通过 /remote-control 启动的 Remote Control 会话不会向已连接客户端报告工作树差异的问题。
• 修复自托管 Runner 会话在 Claude Code 实际启动前就报告为 running 的问题；这可能触发 Claude 桌面应用过早发出“Claude 正在等待你的输入”通知。
• 修复首次运行设置在托管设置配置 Claude apps gateway 登录、且 Anthropic 端点不可达时，会以“Unable to connect to Anthropic services”退出的问题。
• 修复云端会话（Web 版 Claude Code、桌面应用和移动应用）在发送消息后立即切换权限模式时，有时仍显示此前权限模式的问题。
• 修复云端会话在回合之间容器重启、且后台 Agent、shell 或监控器仍在运行时可能没有响应的问题；恢复后的会话现在会报告丢失的工作。
• 增强插件市场安全性：拒绝包含控制字符或不可见字符的名称，并确保 /plugin 和 claude plugin 输出中的市场提供文本能够安全转义。
• 改进 Bedrock、Vertex 和 Foundry 会话（以及任何禁用遥测的会话）：当配置的 MCP 服务器连接失败时，Claude 现在会收到通知，而不再断定其工具不存在。
• 将 Sonnet 5 默认自动压缩窗口调整为完整的 1M 上下文；因此，使用 1M 窗口的会话现在会在约 967K Token 时自动压缩，而非约 934K Token。
• 将跨会话对等消息默认折叠为单行预览：Message from @<sender>: <first line>；按 Ctrl+O 可展开完整正文。
• 调整渲染 Markdown 中的终端超链接：目标链接若指向网络路径或自动挂载路径、包含控制字符，或以不可见字符开头，现在将以纯文本形式渲染。
• 调整提示词页脚中的 PR 徽章：若上次 GitHub 检查距今不足一分钟，终端重新获得焦点时将跳过重新检查。
• 调整分析功能：当托管设置强制 gateway 登录，或配置了自定义 OAuth 部署时，分析功能从启动时起即保持关闭，而不再仅在登录后关闭。
• 调整 Claude apps gateway 登录请求的身份标识：请求现在会标识为 Claude Code，包括 surface=claude_code 设备授权参数和 claude-code/<version> User-Agent。
• 调整组织登录强制策略：当无法读取管理员的托管设置时，程序会在启动时退出，即使存在主机提供的设置或按用户配置的 Windows 注册表设置。

1. Releases
2. v2.1.247

Compare

Sorry, something went wrong.

No results found

What's changed

• Added the SendFeedback tool: when something goes wrong in a session, Claude can draft a feedback report for you to review and send from /feedback (turn off with the feedbackDrafts setting)
• Added {id, text, cooldownSessions, priority} entries, tipsFile, and label to spinnerTipsOverride, so organizations can rotate their own tips alongside the built-in ones
• Added a tip on Bash permission prompts pointing to auto mode, with a one-keystroke "Yes, and switch to auto mode" option
• Added /claude-api cost-optimize to profile an existing project's Claude API spend and work through cost levers (caching, token hygiene, batch, effort, model choice) one measured change at a time
• Updated the /claude-api skill with Admin API coverage (organization members, invites, workspaces, API keys, rate limit reports, workload identity federation, CMEK)
• Fixed fast arrow-key + Enter sequences acting on the row above the one you navigated to in history search, /config, /mcp, /skills, background tasks, and /model
• Fixed sub-agents dying on a first-call model 404: they now use the session's fallback model chain, and the error returned to the parent includes the error type, status, request id, and model
• Fixed a hook or background agent that printed megabytes of error output being able to overflow the conversation and wedge the session on "Prompt is too long"
• Fixed Ctrl keyboard shortcuts not firing under non-Latin (e.g. Cyrillic) keyboard layouts in kitty-protocol terminals
• Fixed text like <35;150;7M being inserted into the prompt when a mouse report arrived split across reads right after the escape prefix
• Fixed the Bash sandbox's after-command cleanup deleting a dotfile-managed ~/.claude/settings.json symlink (nix/home-manager, stow) when it is repointed outside the sandbox's writable area
• Fixed /terminal-setup overwriting your entire Zed keymap.json instead of merging in its keybinding
• Fixed /rename silently confirming when the session registry could not be updated; it now says other sessions may still show the old name
• Fixed /compact and "Summarize from here" in sessions started with --agent summarizing under the default system prompt instead of the conversation's own
• Fixed a background session showing "opening…" forever in claude agents after its terminal host process died; the row now fails within seconds with the reason, and Enter restarts it
• Fixed unbounded memory growth when a hook's or background task's output file could not be written; the file now notes where output was lost
• Fixed /install-github-app over SSH: the copy shortcut now says how the sign-in URL was copied instead of always claiming success, and the URL appears immediately when no browser can open
• Fixed shell commands carried over from the foreground logging an internal error or showing a misleading [exited with code -1] line when they finish in background sessions
• Fixed a version-less marketplace plugin's live cache directory being deleted and recreated on a second-scope install, which could disrupt a running session using it
• Fixed Remote Control sessions started with /remote-control not reporting the working-tree diff to connected clients
• Fixed self-hosted runner sessions reporting running before Claude Code had started, which could trigger a premature "Claude is waiting for your input" notification from the Claude desktop app
• Fixed first-run setup exiting with "Unable to connect to Anthropic services" when managed settings configure Claude apps gateway sign-in and Anthropic endpoints are unreachable
• Fixed cloud sessions (Claude Code on the web, desktop and mobile apps) sometimes showing the previous permission mode when you switch modes right after sending a message
• Fixed cloud sessions going silent when the session's container restarts between turns while a background agent, shell, or monitor is still running — the resumed session now reports the lost work
• Improved plugin marketplace hardening: names containing control or invisible characters are rejected, and marketplace-supplied text in /plugin and claude plugin output is escape-safe
• Improved Bedrock, Vertex, and Foundry sessions (and any with telemetry disabled): Claude is now told when a configured MCP server failed to connect, instead of concluding its tools don't exist
• Changed Sonnet 5's default auto-compact window to its full 1M context, so sessions on the 1M window now auto-compact at about 967K tokens instead of about 934K
• Changed cross-session peer messages to collapse by default to a one-line Message from @<sender>: <first line> preview; Ctrl+O expands the full body
• Changed terminal hyperlinks in rendered markdown: link targets that point at a network or automounter path, contain a control character, or lead with an invisible character now render as plain text
• Changed the prompt-footer PR badge to skip its GitHub re-check on terminal refocus when the last check is under a minute old
• Changed analytics to stay off from startup, not only after login, when managed settings force gateway login or a custom OAuth deployment is configured
• Changed Claude apps gateway sign-in requests to identify Claude Code (a surface=claude_code device-authorization parameter and a claude-code/<version> User-Agent)
• Changed organization sign-in enforcement to exit at start when the administrator's managed settings cannot be read, even if host-supplied or per-user Windows registry settings exist

You can’t perform that action at this time.