Claude Code v2.1.246 发布:修复终端与MCP集成问题,增强后台会话稳定性
评分
75本次为维护性更新,修复大量已知问题,但未引入重大新功能,对多数用户而言信息增量中等。
发布说明非常详细,逐条列出修复项,便于用户了解具体改进。
修复了后台会话、MCP工具调用等影响实际使用的关键问题,升级价值明显。
作为最新版本发布,信息及时,能够反映当前产品状态。
信息来自Anthropic官方GitHub Releases,信源权威可靠。
基础分 78.5 × T1.5 信源权重 ×0.95 = 75
精选线 65已入选精选
精选理由
版本修复了涵盖终端、MCP、插件、主题等多方面的问题,实用性高,但以维护性更新为主,信息增益中等。
AI 点评
「这次更新虽然以修复为主,但其中的MCP和后台会话修复对自动化和远程开发场景至关重要。特别是之前误报完成的问题可能掩盖真实的错误,升级后能少踩很多坑。建议所有使用Claude Code的开发者尽快更新,尤其是那些依赖headless模式或第三方API网关的用户。」
速览
Claude Code v2.1.246 发布,重点修复了多项影响稳定性的问题。新增对Bash允许规则通配符的启动警告,避免子命令前的选项被意外匹配;新增Auto模式权限标签页。修复了全屏模式调整终端大小后显示空白、长行导致严重卡顿、后台会话在多种场景下无法打开、MCP工具调用中断被误报为完成等问题。同时改进了/cd切换目录后的配置生效、子代理达到上限时返回部分结果,并优化了Bash工具延迟和会话内存占用。
- 新增Bash allow规则通配符警告及Auto模式权限编辑标签页。
- 修复后台会话在目录被删、睡眠或进程缓慢时无法打开的问题。
- 修复MCP工具调用中断被误报为“已完成”,并修复参数类型错误。
- 改进子代理结果标记为部分输出,支持通过SendMessage继续。
正文
以下为原文,中文全文翻译生成中
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
/permissionsfor 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
/backgroundduring 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 agentswhile its worker was still booting (common on Windows) stopping it with "was stopped while the respawn was in flight" - Fixed
claude agentslisting 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
namealready includes the<plugin>:prefix showing it doubled in the slash menu (e.g./plugin:plugin:skill) - Fixed
claude plugin updatefailing for an installed plugin given its bare name (only the fully-qualified name worked) - Fixed plugin installation failing when
plugin.jsonwas saved with a UTF-8 byte-order mark (BOM) - Fixed
/reload-pluginsreporting 0 skills for plugins that define skills underskills/*/SKILL.md - Fixed hook error messages showing a literal
${CLAUDE_PLUGIN_ROOT}instead of the resolved plugin path - Fixed
/renamereplacing the theme's prompt border color (including a custom theme'spromptBorder) with the default cyan; the border now keeps your theme's color unless you pick one with/color - Fixed custom theme diff colors (
diffAdded/diffRemovedand their dimmed variants) being ignored in diffs and the/themepreview - Fixed a
keybindings.jsonbinding 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
/statsactivity heatmap showing each day's activity one cell off (Sunday's count under Monday) in timezones east of UTC - Fixed
/forkfrom 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/sessionsleft 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 atool_useblock without anid - 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.jsonis 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 | bashfailing 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/--resumewith a permission prompt tool, when no permission mode was set - Fixed the
Notificationhook 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-configsessions prompting to approve.mcp.jsonservers 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
apiKeyHelperreturns 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
/ultrareviewruns 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-proccasionally 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
requiresUserInteractionstill 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.jsonservers (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
maxTurnslimit now returns its output marked as partial, with a hint to continue it viaSendMessage, 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
apiKeyHelperruns at startup, and after a login token expired while idle - Changed
/code-reviewso 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 installandclaude updateto 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_hashnow reflects the plugin's real marketplace, andenabled_viaisadmin-installfor admin-installed plugins - Fixed the command sandbox's filesystem configuration not respecting
--setting-sources
相关条目
92
精选OpenRouter 推出提示缓存与粘性路由,大幅降低多轮对话成本
对于高频调用 AI API 的开发者,这个功能堪称直接省钱利器。粘性路由保证了缓存命中率,配合 session_id 零配置接入,值得所有使用 OpenRouter 的团队立即尝试。
91
精选ChatGPT Work:可在跨应用和文件中执行操作的AI Agent
我认为这是AI助手从问答走向执行的关键一步。对需要自动化复杂工作流的专业人士尤其值得关注。ChatGPT Work可能成为生产力工具的新范式。
90
精选前沿实验室代理入侵事件技术时间线:2026年7月事件剖析
这篇技术时间线值得所有AI安全研究员和代理开发者细读——它不只是描述一次攻击,而是为整个行业敲响了代理系统防御体系薄弱的警钟。对正在部署自主代理的团队来说,这是必读的灾难预防手册。
90
精选更好的工具反而让Copilot代码审查更糟?GitHub这样改进
这篇博客值得所有AI产品工程师和ML从业者仔细阅读——它打破了'更强大的工具=更好的AI'的直觉,转而强调与Agent推理模式匹配的工程哲学。对正在优化代码审查或类似Agent产品的团队尤其重要。
88
精选OpenRouter 推出统一多模态 API:单端点支持图像、视频、音频、嵌入与转录
这条消息值得所有做多模态AI应用的开发者关注:OpenRouter用联合API解决了模型切换的痛点,特别适合初创团队或快速原型开发。如果你正被多个API密钥和SDK折磨,这个接口可能是你需要的统一层。
87
精选Anthropic 推出 Claude for Teachers:面向教师的教育 AI 工具
这条消息对教育工作者和AI行业观察者都很有价值。Anthropic没有选择通用聊天机器人,而是专门为教师设计了安全可控的工具,这显示出AI在垂直场景落地的正确思路——不是技术炫技,而是切实解决用户痛点。同时,产品内置的安全护栏也值得其他AI公司参考,尤其是在面向儿童或青少年的场景中。
86
精选OpenRouter发布全新Auto Router:用市场智慧优化模型路由
这条更新值得所有用API开发AI应用的人关注。以前选模型靠经验和测试,现在市场数据帮你选。虽然细节不多,但方向很对。对依赖聚合模型服务的团队尤其重要。
86
精选Claude Code v2.1.211 发布:多项修复与改进
作为一个经常使用 Claude Code 进行自动化编码的开发者,我特别关注这次的安全修复,尤其是权限预览字符绕过和自动模式覆盖钩子决策的问题——这些直接关系到团队协作时的安全边界。后台代理报告的改进也让长时间运行的任务更可靠。建议所有使用者尽快升级。