Claude Code v2.1.246 发布：权限、后台会话与插件系统大量修复

更新内容

• 为子命令之前带有通配符的 Bash 允许规则新增启动警告（例如 Bash(git * main)），因为这类规则同样会匹配插入在子命令之前的选项。
• 在 /permissions 中新增 Auto mode 标签页，用于查看和编辑自动模式分类器规则。
• 在回合结束时长行末尾新增该回合的完成时间，例如 ✻ Sautéed for 23s · done 6:05 PM。
• 修复了在调整终端大小并跳转到底部后，全屏模式会显示空白转录内容、直至下一次按键才恢复的问题。
• 修复了当 diff 包含极长的单行内容（例如 base64 字符串）时，转录内容会严重变慢的问题；此类行现在会被截断渲染并显示标记。
• 修复了位于较早消息时全屏滚动异常的问题，包括“跳转到底部”卡在转录内容中间的情况。
• 修复了以下情况下后台会话在 45 秒后无法打开的问题：Claude Code 的启动目录已被删除、机器曾进入睡眠状态，或主机启动进程较慢。
• 修复了当另一个 Claude Code 进程正在重新安装 npm 包时，后台会话无法打开并报错 Couldn't start the background service … EACCES 的问题。
• 修复了当一条消息的前 500 个字符不含 Markdown 时，整条消息的 Markdown 渲染会被禁用的问题；同时修复了 +/N) 列表及 Setext 标题的渲染问题。
• 修复了在无头/远程会话中，MCP 工具调用被传入消息中断时，会向模型报告为“completed with no output”，而非明确的中断错误的问题。
• 修复了当参数 schema 为空（{}）时，MCP 工具参数会以 JSON 字符串而非其真实类型发送的问题。
• 修复了命令在执行过程中被中断时，界面显示为 Ran 1 shell command 且未表明其被截断的问题。
• 修复了在动态工作流期间按下 ← 或运行 /background 会重新启动已完成子 Agent 的问题；现在会先询问确认，并说明将重新启动多少个子 Agent。
• 修复了在 claude agents 中打开刚启动、其 worker 仍在引导的会话（Windows 上较常见）时，会以 was stopped while the respawn was in flight 停止的问题。
• 修复了 claude agents 会将已转入后台的命名会话列出两次的问题；再次将同一对话转入后台时，新行现在会编号（例如 my-session (2)）。
• 修复了后台保留清理任务会删除 .claude/worktrees/ 下由用户自行创建的 Git worktree 的问题；此前旧的后台会话记录可能指向这些 worktree。
• 修复了在超大规模会话中，自动模式工具调用会因安全检查截止时间不足而被以“temporarily unavailable”拒绝的问题；安全检查截止时间现在会随提示词大小扩展。
• 修复了插件缓存会为同一插件创建重复的、以 SHA 命名目录的问题。
• 修复了插件 skill 的 frontmatter name 已包含 <plugin>: 前缀时，斜杠菜单中会重复显示此前缀的问题（例如 /plugin:plugin:skill）。
• 修复了对已安装插件使用裸名称执行 claude plugin update 时失败的问题；此前仅完全限定名称可用。
• 修复了当 plugin.json 使用带 UTF-8 字节顺序标记（BOM）的格式保存时，插件安装失败的问题。
• 修复了对于在 skills/*/SKILL.md 下定义 skill 的插件，/reload-plugins 会报告 0 个 skill 的问题。
• 修复了 hook 错误消息会原样显示 ${CLAUDE_PLUGIN_ROOT}，而非显示解析后的插件路径的问题。
• 修复了 /rename 会将主题的提示边框颜色（包括自定义主题的 promptBorder）替换为默认青色的问题；除非通过 /color 选择颜色，边框现在会保留主题原有颜色。
• 修复了 diff 和 /theme 预览中忽略自定义主题 diff 颜色（diffAdded/diffRemoved 及其暗化变体）的问题。
• 修复了 keybindings.json 中绑定未知操作名称时，该按键会被静默禁用的问题；现在会跳过该绑定以保留默认绑定，并在 --debug 下记录警告。
• 修复了在 UTC 以东时区中，/stats 活动热图会将每天活动错位一个单元格显示的问题（周日的计数显示在周一下面）。
• 修复了从已 fork 或已转入后台的会话运行 /fork 时，新会话会以空对话开始的问题。
• 修复了以 /-- 开头的提示词（例如 Lean 文档注释）会被作为未知斜杠命令拒绝、而非发送给 Claude 的问题。
• 修复了在输入文本不再匹配真实路径后，@ 文件选择器仍保持打开的问题。
• 修复了在导航至 Agent 视图后再返回时，状态行的成本和时长会重置为零的问题。
• 修复了全屏模式中，单击终端窗口只是为了重新获得焦点时，键盘焦点会移动到鼠标指针下方控件的问题。
• 修复了当补全 token 或工作目录包含空字节时，路径补全失败的问题。
• Windows/macOS：修复了无头会话不会清理 ~/.claude/sessions 中由未正常退出会话遗留的过期条目的问题。
• 修复了当第三方 Anthropic 兼容端点（ANTHROPIC_BASE_URL）流式传输不带 id 的 tool_use 块时，首次工具调用会导致 UI 因渲染错误停止的问题。
• 修复了覆盖非常大的现有文件后，Write 工具尽管已写入文件仍报告“Out of memory”或长时间冻结的问题。
• 修复了当 ~/.claude/plugins/known_marketplaces.json 为空或损坏时，claude plugin install <name> 会静默退出（或在终端中挂起）而非报告错误的问题。
• 修复了恢复的会话中，若保存历史包含 Anthropic API 不接受的工具块（通常由第三方 API 代理写入），每个回合都会以 400 错误失败的问题。
• 修复了部分采用服务器托管设置的 Team/Enterprise 用户运行 curl -fsSL https://claude.ai/install.sh | bash 时，因 Raw mode is not supported 而失败的问题。
• 修复了在 VS Code 扩展中，以 plan mode 结束的会话恢复后会退出 plan mode 的问题；也修复了未设置权限模式时，在 claude -p --continue/--resume 且使用权限提示工具时出现的相同问题。
• 修复了当沙箱的“Network request outside of sandbox”权限提示正在等待时，Notification hook 不会触发的问题。
• 修复了 Bash 权限检查对于带有悬空 && 或 || 运算符的格式错误命令未始终要求审批的问题。
• 修复了 --strict-mcp-config 会话会提示批准其永远不会加载的 .mcp.json 服务器、导致后台会话在启动时等待的问题。
• 修复了发送至 Anthropic 的遥测和指标请求会携带为第三方网关（ANTHROPIC_BASE_URL）配置的 API 密钥的问题；现在凭据仅会发送至其所属主机。
• 修复了当 apiKeyHelper 返回短生命周期 JWT 时，空闲后的首个提示词会显示可见 API 错误的问题：现会在发送前刷新过期的缓存 token，并静默重试 401/403 认证错误。
• 修复了全屏和 Ctrl+O 转录视图中的内存会随会话长度增长的问题：每个渲染的消息行不再保留完整的、覆盖整个转录内容的工具查找副本。
• 修复了从同一仓库（例如多个 worktree）同时启动 /ultrareview 运行和云端会话时，有时会携带另一启动任务的未提交更改的问题。
• 修复了后台云端会话（如 /autofix-pr）显示的任务进度计数（例如 3/5）偶尔遗漏一个任务的问题。
• 修复了 Remote Control 会话在第二个提示词之前，会在 claude.ai 和 Claude 应用中保留占位名称的问题；自动生成的标题现在会在第一个提示词后出现。
• 修复了标记为 requiresUserInteraction 的 MCP 工具仍会在权限提示中提供“是，并且不再询问”选项的问题；该选项会写入一个随后被工具忽略的允许规则。
• 修复了自托管 runner 在工作轮询响应格式错误时（例如拦截代理返回 HTML 页面）会结束实时会话或退出的问题；现在会重试轮询。
• 改进了 /cd：切换目录后，新目录的项目设置、hook、.mcp.json 服务器（仍受常规审批提示保护）、skill 和 Agent 将立即生效，而不再需要使用 --resume。
• 改进了 Bash shell 中 Bash 工具的延迟：通过重放快照函数，避免每个函数都启动一个 base64 子 shell。
• 改进了子 Agent 结果：达到 maxTurns 限制而停止的子 Agent，现在会返回标注为部分结果的输出，并提示可通过 SendMessage 继续它，而不再看起来像已完成。
• 改进了非交互式会话（-p、SDK、云端会话）：当响应因服务器错误、连接丢失或停滞而在流传输中途被截断时，现在会自动继续响应，而不再以错误结束。
• 改进了以下场景中使用遥测对组织的归因：工作负载身份联合会话、启动时 apiKeyHelper 运行期间发送的事件，以及空闲期间登录 token 过期后的事件。
• 修改了 /code-review：Claude 现在也可以在 Bedrock、Vertex AI 和 Foundry 上、通过 Claude apps gateway，以及在禁用遥测或非必要流量时自行启动该功能。
• /goal：调整为对于每个目标，空闲会话最多对长期运行的后台工作发起三次 check-in；用户发送下一条消息后，还可再进行三次。
• 修改了 claude install 和 claude update：对于待处理的托管设置同意提示，改为推迟到下一次交互式会话处理，而非在命令执行中途提示。
• 修改了从 claude.ai 同步的插件所产生的 OpenTelemetry 插件事件：plugin_id_hash 现在反映插件真实的 marketplace；对于管理员安装的插件，enabled_via 为 admin-install。
• 修复了命令沙箱的文件系统配置不遵守 --setting-sources 的问题。

1. Releases
2. v2.1.246

Compare

Sorry, something went wrong.

No results found

What's changed

• Added a startup warning for Bash allow rules with a wildcard before the subcommand (e.g. Bash(git * main)), since they also match options inserted before the subcommand
• Added an Auto mode tab to /permissions for viewing and editing auto mode classifier rules
• Added the turn's completion time to the end-of-turn duration line, e.g. ✻ Sautéed for 23s · done 6:05 PM
• Fixed fullscreen mode showing a blank transcript after resizing the terminal and jumping to the bottom until the next keypress
• Fixed a severe transcript slowdown when a diff contained a very long single line (e.g. a base64 string); such lines now render truncated with a marker
• Fixed erratic fullscreen scrolling when positioned at an earlier message, including jump-to-bottom getting stuck mid-transcript
• Fixed background sessions failing to open after 45 seconds when Claude Code's starting directory had been deleted, the machine had slept, or the host is slow to start processes
• Fixed background sessions failing to open with "Couldn't start the background service … EACCES" when another Claude Code process was re-installing the npm package at that moment
• Fixed markdown rendering being disabled for a whole message when its first 500 characters contained no markdown, and for +/N) lists and setext headings
• Fixed MCP tool calls interrupted by an incoming message in headless/remote sessions being reported to the model as "completed with no output" instead of an explicit interrupted error
• Fixed MCP tool arguments being sent as JSON strings when the parameter's schema is empty ({}), instead of their real type
• Fixed a command interrupted mid-run showing as "Ran 1 shell command" with no sign it was cut
• Fixed pressing ← or running /background during a dynamic workflow restarting its finished subagents; it now asks first and says how many subagents would restart
• Fixed opening a just-started session in claude agents while its worker was still booting (common on Windows) stopping it with "was stopped while the respawn was in flight"
• Fixed claude agents listing a backgrounded named session twice; backgrounding the same conversation again now numbers the new row (e.g. my-session (2))
• Fixed the background retention sweep removing git worktrees under .claude/worktrees/ that you created yourself when an old background-session record pointed at them
• Fixed auto mode tool calls being denied as "temporarily unavailable" on very large sessions by scaling the safety-check deadline with prompt size
• Fixed the plugin cache creating duplicate SHA-named directories for the same plugin
• Fixed plugin skills whose frontmatter name already includes the <plugin>: prefix showing it doubled in the slash menu (e.g. /plugin:plugin:skill)
• Fixed claude plugin update failing for an installed plugin given its bare name (only the fully-qualified name worked)
• Fixed plugin installation failing when plugin.json was saved with a UTF-8 byte-order mark (BOM)
• Fixed /reload-plugins reporting 0 skills for plugins that define skills under skills/*/SKILL.md
• Fixed hook error messages showing a literal ${CLAUDE_PLUGIN_ROOT} instead of the resolved plugin path
• Fixed /rename replacing the theme's prompt border color (including a custom theme's promptBorder) with the default cyan; the border now keeps your theme's color unless you pick one with /color
• Fixed custom theme diff colors (diffAdded/diffRemoved and their dimmed variants) being ignored in diffs and the /theme preview
• Fixed a keybindings.json binding with an unknown action name silently deadening that key; it is now skipped so the default binding keeps working, and a warning is logged under --debug
• Fixed /stats activity heatmap showing each day's activity one cell off (Sunday's count under Monday) in timezones east of UTC
• Fixed /fork from an already-forked or backgrounded session starting the new session with an empty conversation
• Fixed prompts beginning with /-- (e.g. Lean doc comments) being rejected as an unknown slash command instead of being sent to Claude
• Fixed the @ file picker staying open after the typed text stopped matching a real path
• Fixed the status line's cost and duration resetting to zero after navigating to the agents view and back
• Fixed fullscreen mode moving keyboard focus onto the control under the pointer when you clicked the terminal window only to bring it back into focus
• Fixed path completion failing when the completion token or working directory contained a null byte
• Windows/macOS: Fixed headless sessions not cleaning up stale entries in ~/.claude/sessions left by sessions that exited uncleanly
• Fixed the UI stopping with a render error on the first tool call when a third-party Anthropic-compatible endpoint (ANTHROPIC_BASE_URL) streams a tool_use block without an id
• Fixed the Write tool reporting "Out of memory" or freezing for a long time after overwriting a very large existing file, even though the file had been written
• Fixed claude plugin install <name> exiting silently (or hanging in a terminal) instead of reporting an error when ~/.claude/plugins/known_marketplaces.json is empty or corrupted
• Fixed resumed sessions failing every turn with a 400 when the saved history contains tool blocks the Anthropic API does not accept (typically written by a third-party API proxy)
• Fixed curl -fsSL https://claude.ai/install.sh | bash failing with "Raw mode is not supported" for some Team/Enterprise users with server-managed settings
• Fixed sessions that ended in plan mode resuming outside plan mode in the VS Code extension, and in claude -p --continue/--resume with a permission prompt tool, when no permission mode was set
• Fixed the Notification hook not firing while the sandbox "Network request outside of sandbox" permission prompt is waiting
• Fixed Bash permission checks to always require approval for malformed commands with a dangling && or || operator
• Fixed --strict-mcp-config sessions prompting to approve .mcp.json servers they would never load, which left background sessions waiting at startup
• Fixed telemetry and metrics requests to Anthropic carrying the API key configured for a third-party gateway (ANTHROPIC_BASE_URL); a credential is now only sent to its own host
• Fixed a visible API error on the first prompt after idle when apiKeyHelper returns short-lived JWTs: an expired cached token is now refreshed before sending, and 401/403 auth errors retry quietly
• Fixed memory growing with session length in the fullscreen and Ctrl+O transcript views: each rendered message row no longer retains a full copy of the transcript-wide tool lookups
• Fixed /ultrareview runs and cloud sessions launched at the same time from one repository (e.g. from several worktrees) sometimes starting with another launch's uncommitted changes
• Fixed the task progress count (e.g. 3/5) shown for background cloud sessions such as /autofix-pr occasionally missing a task
• Fixed Remote Control sessions keeping their placeholder name in claude.ai and the Claude app until the second prompt; the auto-generated title now appears after the first prompt
• Fixed MCP tools marked requiresUserInteraction still offering "Yes, and don't ask again" in their permission prompt; the option wrote an allow rule the tool then ignored
• Fixed the self-hosted runner ending its live sessions or exiting when a work-poll response is malformed (e.g. an intercepting proxy's HTML page); it now retries the poll
• Improved /cd: the new directory's project settings, hooks, .mcp.json servers (behind the usual approval prompt), skills, and agents now take effect right after the move instead of on --resume
• Improved Bash tool latency on bash shells by replaying snapshot functions without a base64 subshell per function
• Improved subagent results: a subagent that stops at its maxTurns limit now returns its output marked as partial, with a hint to continue it via SendMessage, instead of appearing finished
• Improved non-interactive sessions (-p, SDK, cloud sessions) to automatically continue a response cut off mid-stream by a server error, connection loss, or stall instead of ending with an error
• Improved attribution of usage telemetry to your organization for workload identity federation sessions, events sent while apiKeyHelper runs at startup, and after a login token expired while idle
• Changed /code-review so Claude can also start it on its own on Bedrock, Vertex AI, and Foundry, through the Claude apps gateway, and when telemetry or non-essential traffic is disabled
• /goal: Changed idle sessions to start at most three check-ins on long-running background work per goal; your next message allows three more
• Changed claude install and claude update to defer a pending managed-settings consent prompt to the next interactive session instead of prompting mid-command
• Changed OpenTelemetry plugin events for plugins synced from claude.ai: plugin_id_hash now reflects the plugin's real marketplace, and enabled_via is admin-install for admin-installed plugins
• Fixed the command sandbox's filesystem configuration not respecting --setting-sources

You can’t perform that action at this time.