外部精选
Claude Code · v2.1.317
本文来自外部来源,不是黄奕彬的原创文章。本站提供原文入口,并在采集端生成 AI 结构化摘要、解读与中文翻译(如有),一切以原文为准。
阅读原文(github.com)结构化摘要 AI 生成
背景与问题
这是 Claude Code 的版本发布公告,面向使用 Claude Code 及其关联产品(Claude Desktop、VSCode 扩展、cloud sessions、自托管 runner、Claude apps gateway、Remote Control、Slack 集成)的用户与运维者。
它要解决的问题是:明确告知 v2.1.317 这一版本具体新增、修复、改进、变更了什么,便于用户判断是否升级或排查已知故障。该 release 标注为不可变,仅标题与说明可修改。
方法或内容
发布版本 v2.1.317 的完整变更清单,对应 commit 964d695。
内容按 Added / Fixed / Improved / Changed / Removed 组织,另含平台专项条目:Windows、Gateway、Self-hosted runner、Remote Control、VSCode、Cloud sessions、Claude Tag(Slack)。
范围覆盖安全确认提示、Agent SDK 钩子、OpenTelemetry 指标、成本报表 API 与数十项跨形态缺陷修复。
关键发现 / 结果
新增:
/schedule在云任务出现未请求的 connectors 时告警- web 或 shell 工具调用外发账户邮箱前先询问
- Agent SDK 钩子支持
onFailure: "block" - OTel 新增
anthropic.plan、anthropic.seat_type、anthropic.provider、anthropic.custom_base_url - 成本报表 API
GET /v1/organizations/analytics/cost - 新环境变量
CLAUDE_CODE_DISABLE_NESTED_SESSION_ID
修复(节选):
claude -p磁盘满时改为报错并退出 1(原为 0)- OTel 经代理挂起改为 10 秒超时,或
OTEL_EXPORTER_OTLP_TIMEOUT最长 30 秒 - Windows 修复部分卷上全部工具调用被拒、临时路径触发 260 字符限制
- VSCode 修复 fork 会话丢消息;Gateway 修复共享预算耗尽误显 100% 已用
原文未说明性能等量化数据。
结论与意义
本版本重点在三类改进:安全可见性(邮箱外发确认、connector 告警)、可观测性与成本管理(OTel 属性、成本报表、IdP 分组记录)、跨形态稳定性(会话、runner、网关、代理环境的大量修复)。适用边界:所有条目仅针对所列产品与该版本,原文未说明其他版本或未列出场景是否受影响,也未给出总体评价性结论。
AI 解读 AI 生成
方法:按「时空变量」分析(时间 / 空间 / 变量,严格区分包含、相关与因果),对象包括原文作者、署名人员与关键技术及其实际原理;结论用「元反空」(元思考、反思考、空思考、综合)整理。
时间:何时发生,现在是否仍成立
按来源日期,该发布于北京时间 2026-11-03 09:25:46(对应 UTC 2026年11月3日 09:25(北京时间))。页面标注 Immutable,即发布内容已定版,仅标题与说明可修改。全部条目描述的是该版本当次的变更;这些行为现在是否仍成立取决于后续版本是否再次改动,原文未说明后续版本情况。
空间:谁的环境 / 场景
适用于 Claude Code v2.1.317 及其关联使用形态:Claude Desktop 的 Code 标签、VSCode 扩展、claude.ai 与移动端应用、cloud sessions、自托管 runner、Claude apps gateway、Remote Control(claude remote-control)、Slack 中的 artifact 链接展示、Microsoft Foundry/Azure 凭证场景、TLS 检查代理与 OTel 导出环境。
未提及的产品、部署方式或版本不在本清单范围内。
变量:实际改变了什么
- 新环境变量
CLAUDE_CODE_DISABLE_NESTED_SESSION_ID:设为 1 时claude -p在会话内运行沿用该会话的 ID 与 transcript,恢复旧版行为 - Agent SDK 钩子新增
onFailure: "block":回调失败即阻断动作而非放行 - 网关新增成本报表端点,并每日记录开发者的 IdP 分组、保留
admin.identity_retention_days天供报表分组 - 行为变化:
claude -p磁盘满退出码由 0 改为 1;Read 工具移除「文件未变」占位、重读返回内容;SendMessage改为将运行中命令转入后台以便更早送达;子代理与队友改用其自身模型的 effort level;stdio MCP 的空AWS_BEARER_TOKEN_BEDROCK改为 unset
区分:包含 ≠ 相关 ≠ 因果
有明确因果证据的:多数 Fixed 条目给出症状—修复的对应关系,例如网关隐藏 Bedrock 的 "Input is too long." 错误导致会话每轮失败、现改为触发压缩;OTel 经代理挂起现改为按超时处理;claude -p 磁盘满现打印错误并退出 1。
仅并列或相关的:OTel 新属性与成本报表 API 同版本新增,原文未说明二者存在数据互通或因果;各条目之间无相互因果主张。CLAUDE_CODE_DISABLE_NESTED_SESSION_ID 与会话 ID 复用属同一条目内的设置与效果说明。
对象:作者/署名与关键技术原理
署名(仅来自结构化作者字段):ashwin-ant。
涉及的关键技术(按原文的行为层描述):Agent SDK 钩子回调及 onFailure: "block" 阻断机制;OpenTelemetry 指标/事件/span 及经代理导出的超时控制;apps gateway 管理端 API GET /v1/organizations/analytics/cost,支持按日期范围、按开发者、按天或按 IdP 分组读取历史花费;stdio MCP 服务器对 AWS_BEARER_TOKEN_BEDROCK 空值改为 unset 以回退机器自身 AWS 凭证;自托管 runner 在 5xx(除 501/529)后新开连接、心跳无响应后重建连接;Windows 260 字符路径限制;会话 transcript 与自动压缩。
原文仅描述行为效果,未展开底层实现原理。
元反空综合结论
元——这条内容本质在回答「v2.1.317 改了什么、我遇到的问题是否被修复」,是一份面向运维者与重度用户的可追溯变更记录,核心价值是逐条的症状—修复对应。
反——最可能失效或有边界的部分:依赖第三方环境的行为(TLS 检查代理、Microsoft Foundry、Slack 卡片样式、Bedrock 错误透传),且原文自己注明残留边界如「Full NFS exports may be missed」;后续版本可能再次改动这些行为,时效以本版本为限。
空——去掉发布叙事后剩余的必要事实:一次不可变发布,commit 964d695,包含新增 API 端点、环境变量、钩子选项与数十项跨平台缺陷修复,署名 ashwin-ant。
综合结论:该清单逐条对应症状与修复、内部一致性好,可用于判断升级收益与排查故障;但不应外推到未列出的产品形态或版本,原文不含性能数据、定价信息与总体结论。
中文译文 AI 生成
不可变的 release。只有发布标题和发布说明可以被修改。
964d695
更新内容
- 为
/schedule新增警告:当新建的云端定时任务获得了你未请求的 connector 时,会提示如何移除它们 - 新增一项检查:当 web 或 shell 工具调用要把你的账户邮箱地址发送到网络时,会先询问你
- 为 Agent SDK 的 hook 回调新增
onFailure: "block",使失败的回调会阻止该操作,而不是放其继续运行 - 在 Claude Desktop 的 Code 标签页新增提示:当组织的远程托管设置尚未为当前会话加载时显示一条,加载完成后再显示一条
- 新增提示:当 auto mode 的检查对子代理的工具调用没有结果时予以显示,此前这种情况不会在主视图中留下任何内容
- 在 OTel 指标、事件和 span 中新增
anthropic.plan、anthropic.seat_type、anthropic.provider和anthropic.custom_base_url - 为 Claude apps gateway 的管理 API 新增费用报告
GET /v1/organizations/analytics/cost,可按日期范围读取过去的支出,支持按总额、按开发者、按天或按 IdP 组查看 - 在设置了
admin: set的 Claude apps gateway 上,新增每个开发者 IdP 组的每日记录,保留时长为admin.identity_retention_days,费用报告即按该记录分组 - 新增
CLAUDE_CODE_DISABLE_NESTED_SESSION_ID:在自托管 runner 上将其设为 1,可使会话内运行的claude -p使用该会话的 ID 和 transcript,与早期版本的行为一致 - 修复了在某些 Claude desktop 会话中,项目级和本地 MCP 服务器在第一轮之后断开连接的问题
- 修复了 auto mode 在作为 base URL 的 LLM gateway 对其服务端安全检查返回 403 或 422 时每轮都失败的问题(配置了
apiKeyHelper时的 403 情况不变) - 修复了
claude auth status在缓慢的 token 刷新尚未保存完成前就退出的问题,该问题可能导致下次运行时被登出 - 修复了由应用提前启动、随后在项目中打开的会话忽略项目
effortLevel设置的问题,例如桌面应用 Code 标签页中的新会话 - 修复了在会话很多的项目中,当关联会话早于第一页时
claude --from-pr报告 "No conversations found" 的问题 - 修复了 claude.ai 和移动应用上,两个同时出现的权限提示中第二个不显示文件路径或命令的问题
- 修复了 Remote Control 和 SDK host 在 mod 的工具调用上提供 "don't ask again" 选项的问题
- 修复了云会话和 SDK 会话中,标题正在生成时收到新消息或
Stop会导致话标题丢失的问题 - 修复了当 Claude 在请求中遗漏某个字段时,自定节奏的
/loop唤醒有时不会被调度的问题 - 修复了云会话中 auto mode 在 Artifact 工具执行上传、写入数据库或通过 outputs 文件夹保存文件时停下等待批准的问题
- 修复了从 claude.ai 同步的 skills 在无法写入磁盘时丢失、或每十分钟被重新下载的问题
- 修复了
/schedule在创建或更新云端定时任务后,其结果中不包含该任务下次运行时间和链接的问题 - 修复了在屏幕阅读器模式下,运行中子代理的已用时间和 token 数量在每次变化时都被屏幕阅读器读出的问题
- 修复了地区或网络封锁(HTTP 403)被显示为登录失败的问题;现在该错误会说明这一封锁
- 修复了当同步的插件包含相同服务器时,Claude 在云会话中声称某个可正常工作的 claude.ai connector 需要授权或已失败的问题
- 修复了磁盘已满或配额用尽导致 transcript 或
~/.claude.json写入丢失时claude -p以退出码 0 退出的问题;现在会打印错误,并在 text 和 json 输出下以退出码 1 退出。NFS 导出已满的情况可能被漏掉 - 修复了启动后大约第一秒内对设置文件所做的修改,直到某个设置文件再次变更才生效的问题
- 修复了某些运行跳过清理(例如使用
--setting-sources的运行)的机器上旧 transcript 未被清理的问题 - 修复了已删除的 agent 团队收件箱被队友较晚到达的消息重新创建的问题
- 修复了重新创建的 agent 队友因更早的关闭批准而被移出其团队的问题
- 修复了定时任务功能被关闭后,已存储的定时任务无法列出或删除的问题
- 修复了当被要求删除某个指南但未指明是哪一个时,Claude 删除你最近更新的
/team-onboarding指南的问题 - 修复了当服务器拒绝删除时,Claude 声称
/team-onboarding指南已被删除的问题 - 修复了 Claude apps gateway 隐藏 Amazon Bedrock 的 "Input is too long." 错误的问题,该问题导致会话每轮都以 "upstream rejected the request" 失败,而不是执行压缩
- 修复了自托管 runner 会话在某个 plan 等待批准期间被重启时丢失最近几轮或整个对话的问题
- 修复了其超大
CLAUDE.md自上次发送后发生变化的会话,在自动压缩后出现 "Prompt is too long" 的问题 - 修复了加载许多注册命令的插件的无头会话中内存占用高、启动缓慢的问题
- 修复了 stdio MCP 服务器在其环境配置把
AWS_BEARER_TOKEN_BEDROCK设为空值时收到空值的问题;现在该变量会被取消设置,因此服务器可以使用机器自身的 AWS 凭证 - 修复了在某些 TLS 检查代理后、根证书更新之后,API 请求以 "unable to get local issuer certificate" 失败的问题
- 修复了压缩不得不缩短其自身请求时,超长对话丢失较早摘要的问题
- 修复了 PDF 自身的元数据可能导致
Read和@-mentions少计其页数的问题 - 修复了
DISABLE_PROMPT_CACHING_OPUS和DISABLE_PROMPT_CACHING_SONNET对默认模型的[1m]、其他区域以及无日期写法无效的问题 - 修复了当你的自有 artifact 达到 200 个或更多时,
/artifacts和 Artifact 工具的共享列表不显示共享 artifact 的问题 - 修复了当搜索达到时间限制时,Claude 将不完整的
Grep和Glob结果当作完整结果的问题 - 修复了通过代理向
https://端点导出的 OpenTelemetry 导出任务,当其在另一个导出仍在进行时启动,则永远不会被发送的问题 - 修复了向阻止(HTTP 403)OpenTelemetry 导出到
http://端点的代理发起大量连接尝试的问题 - 修复了 OpenTelemetry 导出在不响应的代理后无限挂起的问题;现在会在 10 秒后超时,或按
OTEL_EXPORTER_OTLP_TIMEOUT的设置(上限 30 秒)超时 - 修复了恢复的会话再次向 Claude 告知它已知道的文件变更的问题
- 修复了此前的调用因工具被关闭而失败后,Claude 在恢复的会话中有时不使用某个内置工具的问题
- 修复了
/remote-control回答 "Unknown command" 而非提示 Remote Control 已被disableRemoteControl设置关闭的问题 - 修复了当主导会话处于手动模式时,tmux 或
iTerm2面板中的 agent team 队友以自动模式启动的问题 - 修复了后台会话在被升级或退役时有时会丢失刚刚做出的权限模式更改的问题
- 修复了在提示符处按 Ctrl+C 清除已输入文本时会停止所有正在运行的后台 agent 的问题
- 修复了
/feedback在报告发送期间仍显示 "Enter to confirm" 的问题 - 修复了已停止的 shell 命令的子进程有时被发送两次 SIGTERM 的问题,这可能导致某些程序跳过其清理操作
- 修复了在云或自托管 runner 会话中运行的
claude -p共享该会话 ID 的问题:它会写入该会话的 transcript,且重启后可能恢复错误的对话 - 修复了在云或自托管 runner 会话中运行的
claude -p自行生成标题并将其发送到该会话的问题 - 改进了在 Microsoft Foundry 上无法加载 Azure 凭据时显示的错误:现在会提示检查或刷新凭据,并以
cloud_credential_error进行报告 - 改进了
/design-sync:当你的设计系统已迁移到 Claude 时会提前告知,并在构建前停止,而不是在上传时失败 - 改进了无法连接所需的 Claude apps 网关时的启动错误:现在指向网络问题而非登录问题,并会在网关的 TLS 证书无法验证时说明
- 改进了退出时显示的 "Resume this session with" 提示:现在会在
--resume之前重复显示你启动时所用的标志(例如--chrome --debug) - 改进了自托管 runner 从服务器错误中恢复的方式:在出现除 501 或 529 之外的 5xx 错误后,runner 的下一次轮询现在会打开新连接,而不是复用失败的那个连接
- 改进了自托管 runner 会话从服务器错误中恢复的方式:在出现除 501 或 529 之外的 5xx 错误后,会话现在会打开新连接,而不是复用失败的那个连接
- 改进了自托管 runner 会话在连接停止响应时的恢复方式:心跳得不到响应后,会话现在会打开新连接,而不是依次尝试每个空闲连接
- 更改了
SendMessage,使发送给正在运行的后台 agent 的消息更早到达:其正在运行的命令会移入后台,而不会被停止 - 更改了与主对话使用不同模型的 subagent 和队友的行为:现在使用该模型保存的 effort 级别或其默认值,而不是会话的 effort 级别
- 更改了退出行为:对插件监视器跳过 "Background work is running" 提示
- 更改了内置的 plugin-authoring 技能:在你构建的 mod 可正常工作后,仅提供一次帮助分享该 mod 的提议
- 移除了
Read工具的 "file unchanged since your last Read" 占位内容:再次读取未更改的文件会返回其内容 - Windows:修复了在某些原生路径查找失败的卷上所有工具调用都被拒绝的问题;工作目录检查现在改为比较文件夹的标识
- Windows:修复了在非 Claude Desktop 启动的会话中,会话 scratchpad 及其他临时路径随项目路径长度增长的问题,这会使克隆到其中的仓库触及 260 字符的路径限制
- 网关:修复了在其组的池化预算用尽后,状态栏和
/usage将开发者自己的支出限额显示为已用 100% 的问题 - 自托管 runner:修复了当会话迁移到新 runner 且该轮次早于
CLAUDE_CODE_RESUME_INTERRUPTED_TURN_MAX_AGE_MS时,Claode 看不到被中断的工具调用的问题 - 自托管 runner:修复了在会话服务曾拒绝保存该关闭操作的情况下,已被关闭的 MCP 服务器在会话迁移到新机器后重新启用的问题
- Remote Control:改进了应用未设置 fork 名称时的命名:长名称保留其 "(fork)" 结尾,且在以
claude remote-control启动的会话中,"Name (fork)" 的 fork 为 "Name (fork 2)" - [VSCode] 修复了分叉对话丢失消息的问题:Claude 并行运行的多个工具调用只保留了一个,压缩所保留的最后几条消息会丢失,这可能使 Claude 的回答缺少它所回答的问题
- [VSCode] 修复了 Claude 未能在时限内完成启动时消息丢失的问题:扩展现在会在显示错误前再启动一次 Claude
- [VSCode] 修复了请求因其地区或网络被阻止时打开登录界面的问题
- [VSCode] 修复了 Account 面板显示的套餐名称第二个单词为小写的问题
- [VSCode] 修复了 Claude 标签页中的文件链接在聊天之上打开而非在另一个编辑器组中打开的问题
- [VSCode] 修复了提高
chat.fontSize时 Claude 面板中的附件标签、菜单、横幅和对话框保持较小尺寸的问题 - [VSCode] 修复了遥测关闭时
ultrathink不提升其轮次的 effort 或不显示其彩虹效果的问题 - [Cloud sessions] 为云会话添加了链接卡片,使你可以打开或拒绝 MCP 服务器要求你访问的链接,而不是让该请求无人察觉
- [Cloud sessions] 将管理设置中的组织环境对话框改为个人对话框的简短布局:每个分区从一行展开打开,未保存的输入在关闭前会进行询问
- [Cloud sessions] 修复了为已有网络密钥的主机添加网络密钥时静默替换原有密钥的问题;"Add secret" 表单现在会拒绝并指向已有的密钥
- [Cloud sessions] 修复了新建定时任务忽略组织默认环境的问题:表单现在以管理员所选的环境开始,而非 Anthropic 托管的默认环境
[Remote Control] 修复了以下问题:重启 claude remote-control 后,如果你在上一条消息发出后一分钟内发送了消息,发往空闲会话的下一条消息会得不到回复
[Claude Tag] 更改了 Slack 中新粘贴的 artifact 链接的显示方式:现在会展示一个更简洁的卡片,带有一个可在 Claude 中打开该 artifact 的 Open 按钮,而不再使用 Slack 的侧边面板
展开原文提取正文(采集端自动提取,可能有缺失)
Immutable release. Only release title and notes can be modified.
964d695
What's changed
Added a warning to /schedule when a new cloud scheduled task gets connectors you did not ask for, with how to remove them Added a check that asks before a web or shell tool call sends your account email address to the network Added onFailure: "block" for Agent SDK hook callbacks, so a callback that fails blocks the action instead of letting it run Added a notice in Claude Desktop's Code tab when your organization's remote managed settings haven't loaded for the session, and another once they do Added a notice when auto mode's check has no answer for a subagent's tool call, which used to leave nothing in the main view Added anthropic.plan, anthropic.seat_type, anthropic.provider and anthropic.custom_base_url to OTel metrics, events and spans Added a cost report to the Claude apps gateway admin API, GET /v1/organizations/analytics/cost, for reading past spend over a date range in total, per developer, per day or per IdP group Added a daily record of each developer's IdP groups on Claude apps gateways with admin: set, kept for admin.identity_retention_days, which the cost report groups by Added CLAUDE_CODE_DISABLE_NESTED_SESSION_ID: set it to 1 on a self-hosted runner to have claude -p run inside a session use that session's ID and transcript, as in earlier versions Fixed project and local MCP servers disconnecting after the first turn in some Claude desktop sessions Fixed auto mode failing every turn when an LLM gateway set as the base URL answers 403 or 422 to its server-side safety check (a 403 with an apiKeyHelper is unchanged) Fixed claude auth status exiting before a slow token refresh was saved, which could sign you out on the next run Fixed a project's effortLevel setting being ignored by sessions that an app starts ahead of time and then opens in the project, such as new sessions in the desktop app's Code tab Fixed claude --from-pr reporting "No conversations found" in projects with many sessions when the linked session was older than the first page Fixed the second of two simultaneous permission prompts showing no file path or command on claude.ai and the mobile apps Fixed Remote Control and SDK hosts offering "don't ask again" on a mod's tool calls Fixed session titles being lost in cloud and SDK sessions when a new message or Stop arrived while the title was generating Fixed self-paced /loop wakeups sometimes not being scheduled when Claude left a field out of its request Fixed auto mode in cloud sessions stopping for approval when the Artifact tool uploaded, wrote to a database or saved a file through the outputs folder Fixed skills synced from claude.ai being lost or downloaded again every ten minutes when they can't be written to disk Fixed /schedule leaving a cloud scheduled task's next run time and link out of its results after creating or updating it Fixed screen readers speaking a running subagent's elapsed time and token count on every change in screen reader mode Fixed a region or network block (HTTP 403) being shown as a sign-in failure; the error now explains the block Fixed Claude saying a working claude.ai connector needed authorization or had failed in cloud sessions when a synced plugin included the same server Fixed claude -p exiting 0 when a full disk or quota lost its transcript or ~/.claude.json writes; it now prints an error and, in text and json output, exits 1. Full NFS exports may be missed Fixed edits to settings files made in the first second or so after launch not taking effect until a settings file changed again Fixed old transcripts not being cleaned up on machines where some runs skip cleanup, such as runs using --setting-sources Fixed deleted agent team inboxes being re-created by a teammate's late message Fixed a re-created agent teammate being removed from its team by an earlier shutdown approval Fixed stored scheduled tasks being impossible to list or delete after scheduled tasks were turned off Fixed Claude deleting your most recently updated /team-onboarding guide when asked to delete one without naming which Fixed Claude saying a /team-onboarding guide was deleted when the server refused the delete Fixed the Claude apps gateway hiding Amazon Bedrock's "Input is too long." error, which left sessions failing every turn with "upstream rejected the request" instead of compacting Fixed self-hosted runner sessions losing recent turns or the whole conversation when restarted while a plan waited for approval Fixed "Prompt is too long" after automatic compaction in sessions whose very large CLAUDE.md changed since it was last sent Fixed high memory use and slow startup in headless sessions with many plugins that register commands Fixed stdio MCP servers receiving an empty AWS_BEARER_TOKEN_BEDROCK when their env config sets it to empty; the variable is now unset, so the server can use the machine's own AWS credentials Fixed API requests failing with "unable to get local issuer certificate" behind some TLS-inspecting proxies after a root certificate renewal Fixed very long conversations losing their earlier summary when compaction had to shorten its own request Fixed a PDF's own metadata being able to make Read and @-mentions under-count its pages Fixed DISABLE_PROMPT_CACHING_OPUS and DISABLE_PROMPT_CACHING_SONNET having no effect on [1m], other-region and undated spellings of the default model Fixed /artifacts and the Artifact tool's shared list showing no shared artifacts when you have 200 or more of your own Fixed Claude treating partial Grep and Glob results as complete when a search hit its time limit Fixed OpenTelemetry exports to an https:// endpoint through a proxy never being sent when they started while another export was still in progress Fixed a flood of connection attempts to a proxy that blocks (HTTP 403) OpenTelemetry exports to an http:// endpoint Fixed OpenTelemetry exports hanging indefinitely behind a proxy that never answers; they now time out after 10 seconds, or OTEL_EXPORTER_OTLP_TIMEOUT up to 30 seconds Fixed resumed sessions telling Claude again about a file change it already knew about Fixed Claude sometimes not using a built-in tool in a resumed session after an earlier call failed because the tool was switched off Fixed /remote-control answering "Unknown command" instead of saying that Remote Control is turned off by the disableRemoteControl setting Fixed agent team teammates in tmux or iTerm2 panes starting in auto mode when the lead session was in manual mode Fixed a background session sometimes losing a just-made change of permission mode when it was upgraded or retired Fixed Ctrl+C stopping all running background agents when pressed to clear typed text at the prompt Fixed /feedback showing "Enter to confirm" while a report is being sent Fixed child processes of a stopped shell command sometimes being sent SIGTERM twice, which could make some programs skip their cleanup Fixed claude -p run inside a cloud or self-hosted runner session sharing that session's ID: it wrote into the session's transcript, and a restart could resume the wrong conversation Fixed claude -p run inside a cloud or self-hosted runner session generating a title of its own and sending it to that session Improved the error shown on Microsoft Foundry when Azure credentials can't be loaded: it now says to check or refresh them, and reports as cloud_credential_error Improved /design-sync to say up front when your design system has moved to Claude, and stop before building instead of failing at upload Improved the startup error when a required Claude apps gateway can't be reached: it points to the network instead of a sign-in, and says when the gateway's TLS certificate can't be verified Improved the "Resume this session with" hint shown at exit to repeat the flags you launched with (for example --chrome --debug) ahead of --resume Improved how self-hosted runners recover from server errors: after a 5xx other than 501 or 529, a runner's next poll now opens a new connection instead of reusing the one that failed Improved how self-hosted runner sessions recover from server errors: after a 5xx other than 501 or 529, a session now opens new connections instead of reusing the one that failed Improved how self-hosted runner sessions recover when connections stop answering: after a heartbeat gets no answer, a session now opens new connections instead of trying each idle one in turn Changed SendMessage so a message to a running background agent arrives earlier: its running command moves to the background, without being stopped Changed subagents and teammates on a different model from the main conversation to use that model's saved effort level or its default, instead of the session's effort level Changed exit to skip the "Background work is running" prompt for plugin monitors Changed the built-in plugin-authoring skill to offer once, after a mod you built works, to help share the mod Removed the Read tool's "file unchanged since your last Read" stub: reading an unchanged file again returns its content Windows: Fixed every tool call being refused on some volumes where the native path lookup fails; the working-directory check now compares the folder's identity instead Windows: Fixed the session scratchpad and other temporary paths growing with your project's path length in sessions not started by Claude Desktop, which made repositories cloned into them hit the 260-character path limit Gateway: Fixed the status line and /usage showing a developer's own spend limit as 100% used after their group's pooled budget ran out Self-hosted runner: Fixed Claude not seeing the interrupted tool call when a session moves to a new runner and the turn is older than CLAUDE_CODE_RESUME_INTERRUPTED_TURN_MAX_AGE_MS Self-hosted runner: Fixed an MCP server that was switched off coming back on after the session moved to a new machine, when the session service had refused to save the switch Remote Control: Improved fork names when the app doesn't set one: a long name keeps its "(fork)" ending, and in sessions started with claude remote-control a fork of "Name (fork)" is "Name (fork 2)" [VSCode] Fixed forked conversations dropping messages: only one of the tool calls Claude ran in parallel was kept, and the last messages a compaction kept were lost, which could leave Claude's answer without the question it answered [VSCode] Fixed a message being lost when Claude did not finish starting in time: the extension now starts Claude once more before showing the error [VSCode] Fixed the sign-in screen opening when a request is blocked for its region or network [VSCode] Fixed the Account panel showing the plan name with a lower-cased second word [VSCode] Fixed file links in a Claude tab opening on top of the chat instead of in another editor group [VSCode] Fixed attachment chips, menus, banners and dialogs in the Claude panel staying small when chat.fontSize is raised [VSCode] Fixed ultrathink not raising effort for its turn or showing its rainbow when telemetry is off [Cloud sessions] Added a link card to cloud sessions, so you can open or decline a link an MCP server asks you to visit instead of the request going unseen [Cloud sessions] Changed the organization environment dialog in admin settings to the personal dialogs' short layout: each section opens from a row, and unsaved input asks before closing [Cloud sessions] Fixed adding a network secret for a host that already has one silently replacing it; the Add secret form now refuses and points you to the existing secret [Cloud sessions] Fixed new scheduled tasks ignoring your organization's default environment: the form now starts on the one an admin chose instead of the Anthropic-hosted default [Remote Control] Fixed the next message to an idle session going unanswered after you restart claude remote-control, when you sent it within a minute of your previous message [Claude Tag] Changed newly pasted artifact links in Slack to show a simpler card with an Open button that opens the artifact in Claude, instead of Slack's side panel
原文入口
阅读原文(github.com)原文将在新窗口打开。收录时间不是内容更新时间;正文、译文与解读的版权归原作者/来源所有,本站仅作个人阅读辅助并保留原文入口;页面时间均为北京时间。
了解来源批准与收录规则