Claude Code v2.1.221 发布说明

更新内容

• [VSCode] 新增 Focus view：聊天菜单中的切换项，可将工具活动隐藏在每轮可展开的摘要后，并显示正在运行工具的实时指示器。可通过 Ctrl+Alt+F 或“Claude Code: Toggle Focus view”命令切换。
• 在 Linux 和 WSL 上为沙箱凭据文件新增 mode: "mask"：沙箱内命令读取的是哨兵副本（整个文件，或仅由 extract 正则表达式捕获的片段），而沙箱代理会在出口处替换为真实值；在 macOS 上，文件遮蔽会回退为 deny。
• 当市场或插件名称会被 Claude Desktop 的托管市场同步拒绝时，claude plugin validate 现在会发出警告。
• 为 claude-api skill 新增 prompt-audit 子命令，用于审计针对旧版模型编写的 Prompt 和工具描述模式。
• 修复 Bash 工具权限检查可被绕过的问题：zsh 可在 [[ ]] 正则条件中执行隐藏命令；受影响的命令现在会请求权限。
• 修复 Windows 上 PowerShell 权限检查无法正确处理含引号字符路径的问题；此类路径现在会请求批准。
• 修复在关闭 thinking 的状态下启动会话后，thinking 切换对该会话其余时间段无效的问题；在连接过程中禁用 MCP 服务器也不再会被静默还原。
• 修复在打印模式（-p）下，来自 --mcp-config 的 MCP 服务器未在首轮前连接的问题；该问题曾导致模型将工具调用输出为字面文本。
• 修复按 Esc 撤回 Prompt 后重新提交时，使用 @ 提及的文件被静默丢弃的问题。
• 修复为名称与 constructor 等内置对象属性相同的 SDK MCP 工具准备 API 请求时发生的崩溃。
• 修复关闭 thinking 时，WebSearch 在 xhigh/max effort 下出现 400 错误的问题。
• 修复通过沙箱代理进行大型上传时出现 TLS 错误的问题。
• 修复 Team 和 Enterprise 的支出限额消息错误归因于组织月度限额、而非个人支出限额的问题。
• 修复在设置了多余 HOME 环境变量的 Windows 机器上，桌面端托管会话中使用 AWS SSO 命名配置文件的 Bedrock 认证失败问题。
• 修复 CLAUDE_CODE_RESUME_INTERRUPTED_TURN=0 未能禁用中断轮次自动恢复的问题；现在会正确识别 falsy 值。
• 修复一种罕见的休眠唤醒竞态：两个 Claude Code 进程可能同时刷新同一 MCP 连接器或 WIF OAuth Token，导致被迫重新认证。
• 修复从 Claude Code Desktop 或 claude.ai 重命名会话时，CLI 会话名称未更新的问题；现在所有重命名入口产生的会话名称都会经过清理。
• 修复由插件或组织分发、且名称与仅终端内置命令相同的 skill（例如 /help、/feedback）无法在非交互会话中调用的问题。
• 修复插件重新加载后“Plugins changed”通知仍然保留而未清除的问题。
• 修复 Vim 模式：yank 寄存器现在可在对话框、历史搜索和转录视图之间保留，不再被静默清空。
• 修复 Vim 模式：撤销至空 Prompt 时，现在会在返回 Agent 视图前启用“再次按 ← 确认”。
• 改进 Google Vertex AI 上的工具搜索：重新为 Claude 4.5 代及更新模型启用该功能。
• 改进自动模式：并行工具调用的权限检查现在更高效地使用缓存；在检查等待期间切换模式时，会可靠地重新请求权限，而非应用过期结果。
• 通过在多次决策间复用缓存的对话前缀，降低自动模式权限检查的 Prompt 缓存成本。
• 改进 Stats 面板：Token 总数现在计入缓存 Token，并按输入、输出、缓存读取和缓存写入提供明细。
• 改进 /ultrareview 在仓库与其基准没有共同历史时的错误信息：现在会提前拒绝没有分支的 checkout，并建议创建分支；对于已完整克隆的仓库，拒绝提示也不再建议执行 git fetch --unshallow。
• 改进 Windows 启动流程：现在通过原生 kernel32 调用读取进程创建时间，而不再启动 PowerShell，因此会拦截 powershell.exe 的终端安全工具不再弹出提示。
• 调整后台会话行为：提交并推送以保留工作成果；仅在任务需要时创建草稿 PR；遵循 CLAUDE.md 中的 Git 指令；并始终在结束时报告工作所在位置。
• 调整 /plugin install：在报告找不到插件前，会刷新过期的市场目录并重试。
• 调整通过 /plugin 安装的插件：在安全时立即激活，而不再总是要求执行 /reload-plugins。
• 调整插件配置：skills 路径现在接受 "."；根目录 SKILL.md 验证错误现在会建议使用插件根目录。
• 调整 /status：显示会话类型，即 interactive，或处于 attached 或 unattended 状态的后台任务。
• 调整 Emoji 自动补全：接受常见替代短代码，例如 :thumbsup:、:thumbsdown: 和 :love:。
• 调整通过 /fork 创建的会话：现在会创建各自独立的新 worktree，而不再使用原会话的 checkout。
• 调整 Claude in Chrome：在不再需要时关闭其打开的浏览器标签页。
• 调整快速模式：当会话中途用量额度耗尽时，现在会在流中报告，而非静默失败。
• 调整 Monitor：不产生任何输出即退出的 watch，现在会明确说明这一情况，而不再报告“stream ended”。
• 调整 Gateway 的 model 字段验证：非字符串值现在会被以 400 拒绝，而不再向后转发。
• 移除审批提示中重复出现的“Permission mode changed while the auto-mode classifier call was queued”通知。

1. Releases
2. v2.1.221

Compare

Sorry, something went wrong.

No results found

What's changed

• [VSCode] Added Focus view: a chat-menu toggle that hides tool activity behind an expandable per-turn summary with a live running-tool indicator, toggled with Ctrl+Alt+F or the "Claude Code: Toggle Focus view" command
• Added mode: "mask" for sandbox credential files on Linux and WSL — sandboxed commands read a sentinel copy (the whole file, or just the spans captured by an extract regex) while the sandbox proxy substitutes the real value on egress; on macOS file masking falls back to deny
• Added warnings to claude plugin validate when a marketplace or plugin name would be rejected by Claude Desktop's managed marketplace sync
• Added a prompt-audit subcommand to the claude-api skill for auditing prompts and tool descriptions for patterns written for older models
• Fixed a Bash tool permission-check bypass where zsh could execute hidden commands in [[ ]] regex conditionals; affected commands now prompt for permission
• Fixed PowerShell permission checks mishandling paths containing quote characters on Windows; such paths now prompt for approval
• Fixed the thinking toggle having no effect for the rest of a session that started with thinking off; disabling an MCP server mid-connect no longer silently reverts
• Fixed MCP servers from --mcp-config not being connected before the first turn in print mode (-p), which made the model emit tool calls as literal text
• Fixed @-mentioned files being silently dropped when pressing Esc to retract a prompt and resubmitting it
• Fixed a crash when preparing API requests for SDK MCP tools named after built-in object properties such as constructor
• Fixed WebSearch failing with a 400 error at effort xhigh/max when thinking is disabled
• Fixed sandboxed large uploads failing with TLS errors through the sandbox proxy
• Fixed Team and Enterprise spend-limit message incorrectly blaming the org's monthly limit instead of your individual spend limit
• Fixed Bedrock authentication with AWS SSO named profiles failing in desktop-managed sessions on Windows machines that set a stray HOME environment variable
• Fixed CLAUDE_CODE_RESUME_INTERRUPTED_TURN=0 not disabling interrupted-turn auto-resume; falsy values are now honored
• Fixed a rare wake-from-sleep race where two Claude Code processes could both refresh the same MCP connector or WIF OAuth token at once, forcing re-authentication
• Fixed renaming a session from Claude Code Desktop or claude.ai not updating the CLI's session name; session names from every rename surface are now sanitized
• Fixed plugin- and org-delivered skills named after terminal-only built-ins (e.g. /help, /feedback) being un-invocable in non-interactive sessions
• Fixed the "Plugins changed" notification lingering after plugins were reloaded instead of clearing
• Fixed Vim mode: the yank register now survives dialogs, history search, and the transcript view instead of being silently emptied
• Fixed Vim mode: undoing back to an empty prompt now arms the "press ← again" confirm before returning to the agent view
• Improved tool search on Google Vertex AI: re-enabled for Claude 4.5-generation and newer models
• Improved auto mode: permission checks for parallel tool calls are now cache-efficient, and switching modes while a check is pending reliably prompts instead of applying the stale result
• Reduced prompt-cache costs for auto-mode permission checks by reusing the cached conversation prefix across decisions
• Improved Stats panel to count cache tokens in its token totals, with a breakdown by input, output, cache read, and cache write
• Improved /ultrareview error messages when a repo shares no history with its base: a checkout with no branches is now refused up front with advice to create one, and refusal hints no longer suggest git fetch --unshallow on clones that are already complete
• Improved Windows startup: process creation times are now read via a native kernel32 call instead of spawning PowerShell, so endpoint security tools that gate powershell.exe no longer prompt
• Changed background sessions to commit and push to preserve work, open a draft PR only when the task calls for one, follow your CLAUDE.md git instructions, and always end by reporting where the work lives
• Changed /plugin install to refresh a stale marketplace catalog and retry before reporting a plugin not found
• Changed plugins installed from /plugin to activate immediately when safe, instead of always requiring /reload-plugins
• Changed plugins to accept "." as a skills path, and the root-level SKILL.md validation error now suggests using the plugin root
• Changed /status to show the session kind: interactive, or a background job that is attached or unattended
• Changed emoji autocomplete to accept common alternate shortcodes like :thumbsup:, :thumbsdown:, and :love:
• Changed sessions forked with /fork to create a new worktree of their own instead of working in the original session's checkout
• Changed Claude in Chrome to close the browser tabs it opens once it no longer needs them
• Changed fast mode to report on the stream when usage credits run out mid-session, instead of failing silently
• Changed Monitor: a watch that exits without producing any output now says so instead of reporting "stream ended"
• Changed the Gateway model field validation: non-string values are rejected with a 400 instead of being forwarded
• Removed the repeated "Permission mode changed while the auto-mode classifier call was queued" notice from approval prompts

You can’t perform that action at this time.