← 返回
精选AI产品发布/更新#Anthropic#Claude Code#MCP#稳定性修复

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

Claude Code:GitHub Releases(RSS)T1.5
06:3108/26 06:31GitHub Release阅读原文 ↗导出 MD ↓

评分

75
信息增量6 ×0.3

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。

内容质量8 ×0.2

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。

实用价值8 ×0.2

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。

时效性9 ×0.15

作为最新版本发布,信息及时,能够反映当前产品状态。

信源可信度10 ×0.15

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 /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

相关条目

92

五维评分

信息增量8 ×0.3

首次系统介绍 OpenRouter 缓存与路由协同策略,信息增量较高。

内容质量9 ×0.2

官方教程,结构清晰,包含原理、示例和实测效果。

实用价值10 ×0.2

直接明确降低 API 成本,开发者可立即应用。

时效性10 ×0.15

刚刚发布,且对当前 Agent 开发热潮具有及时指导意义。

信源可信度10 ×0.15

来源为 OpenRouter 官方 RSS 和官网,信源权威可靠。

基础分 92 × T1 信源权重 ×1 = 92

精选线 60已入选精选

08:00OpenRouter:Announcements(RSS)T1RSS

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。

AI产品#OpenRouter#会话ID#成本优化
91

五维评分

信息增量9 ×0.3

首次公开ChatGPT Work的Agent能力,信息增量高。

内容质量8 ×0.2

官方发布,内容清晰,但细节较少。

实用价值9 ×0.2

为用户提供可直接使用的Agent能力,实用价值高。

时效性10 ×0.15

刚刚发布,时效性极强。

信源可信度10 ×0.15

来自OpenAI官方,信源权威可靠。

基础分 91 × T1 信源权重 ×1 = 91

精选线 60已入选精选

18:00OpenAI:News(RSS)T1RSS

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。

AI产品#Agent#AI 生产力#ChatGPT Work
90

五维评分

信息增量9 ×0.3

首次公开前沿实验室代理入侵的完整技术时间线,信息增量极高。

内容质量8 ×0.2

结构严谨、技术细节丰富,但缺乏部分原始日志数据佐证。

实用价值9 ×0.2

提供了缓解建议和自检工具,对AI安全从业者具有直接指导意义。

时效性10 ×0.15

事件发生仅数月后即发布分析,时效性极佳。

信源可信度9 ×0.15

Hugging Face 作为顶级开源AI平台,其技术博客可信度极高。

基础分 89.5 × T1 信源权重 ×1 = 90

精选线 60已入选精选

08:00Hugging Face:Blog(RSS)T1RSS

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。

科技产品#AI代理安全#Hugging Face#入侵时间线
90

五维评分

信息增量8 ×0.3

文章揭示了工具增强反而导致AI性能下降的反直觉发现,并提供了具体工程改进方案,信息增量高。

内容质量9 ×0.2

来自GitHub官方工程博客,有数据支撑(成本下降40%),论证清晰,质量上乘。

实用价值9 ×0.2

对AI产品团队、代码审查工具开发者、以及依赖AI辅助编程的团队有直接借鉴意义。

时效性10 ×0.15

2024年发布的工程实践,符合当前AI产品优化趋势,时效性强。

信源可信度10 ×0.15

信源为GitHub官方博客,具有高度权威性和技术可信度。

基础分 90 × T1 信源权重 ×1 = 90

精选线 60已入选精选

23:57GitHub Blog(网页)T1网页

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。

AI产品#Agent工作流#Copilot#GitHub
88

五维评分

信息增量9 ×0.3

披露了OpenRouter产品的新能力,对关注多模态开发的用户有较高信息增量。

内容质量8 ×0.2

内容清晰,准确描述了API功能与优势,但缺少性能数据对比。

实用价值9 ×0.2

直接解决多模态API碎片化问题,开发者可立即降低集成成本。

时效性10 ×0.15

该API为新近发布,具有很高时效性。

信源可信度8 ×0.15

OpenRouter官方博客,权威性高,但未提及其他第三方验证。

基础分 88 × T1 信源权重 ×1 = 88

精选线 60已入选精选

08:00OpenRouter:Announcements(RSS)T1RSS

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。

AI产品#OpenRouter#多模态API#模型集成
87

五维评分

信息增量8 ×0.3

介绍了全新的教育产品,填补了AI安全公司在教育垂直领域的空白,信息增量较高。

内容质量8 ×0.2

内容简洁清晰,准确概括产品功能、安全理念和试点情况,无冗余信息。

实用价值9 ×0.2

直接解决教师备课负担痛点,且强调安全合规,对教育工作者具有实际参考价值。

时效性10 ×0.15

消息发布时间接近当前日期,属于最新产品发布动态。

信源可信度9 ×0.15

来源为Anthropic官方新闻页面,权威性高,内容可靠。

基础分 86.5 × T1 信源权重 ×1 = 87

精选线 60已入选精选

23:40Anthropic:News(网页)T1网页

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。

AI产品#AI安全#Anthropic#Claude
86

五维评分

信息增量9 ×0.3

全新路由机制,市场智慧概念为行业带来较高信息增量。

内容质量8 ×0.2

官方公告内容清晰,但技术细节不足,略有扣分。

实用价值8 ×0.2

对开发者选型有直接实用价值,可降低试错成本。

时效性9 ×0.15

产品刚发布,时效性极强。

信源可信度9 ×0.15

来自OpenRouter官方RSS公告,信源可靠。

基础分 86 × T1 信源权重 ×1 = 86

精选线 60已入选精选

08:00OpenRouter:Announcements(RSS)T1RSS

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。

AI产品#Auto Router#OpenRouter#市场智慧
86

五维评分

信息增量8 ×0.3

包含大量具体修复细节和安全改进,信息密度高。

内容质量9 ×0.2

内容详尽,结构清晰,覆盖新功能、修复、改进多个方面。

实用价值9 ×0.2

修复了多个实际开发中遇到的问题,对用户有直接帮助。

时效性10 ×0.15

刚刚发布的版本,时效性极强。

信源可信度10 ×0.15

来自 Anthropic 官方 GitHub Release,信源权威可靠。

基础分 90 × T1.5 信源权重 ×0.95 = 86

精选线 65已入选精选

07:02Claude Code:GitHub Releases(RSS)T1.5GitHub Release

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。

AI产品#Anthropic#Claude Code#代码生成工具

引用前请核对原文