Claude Code v2.1.293 发布:新增 Claude Haiku 5.5 并修复大量问题

来源:Claude Code:GitHub Releases(RSS) 2026年10月7日 02:10 AIHOT 评分:60 精选
摘要:Claude Code 发布 v2.1.293,新增 Claude Haiku 5.5(claude-haiku-5-5)作为 Anthropic API 默认 Haiku 模型,支持 1M 上下文,价格为 $0.10/$0.50 每百万 token(超 100K 提示为 $0.50/$2.50)。
推荐理由:发布说明列出了新增默认 Haiku 模型、脚本接口扩展和大量稳定性修复,读者可据此判断是否升级及影响现有工作流。
# Claude Code v2.1.293 发布:新增 Claude Haiku 5.5 并修复大量问题 > 原标题:v2.1.293 - 来源:Claude Code:GitHub Releases - 发布时间:2026-10-07T18:10:20.000Z - AIHOT:https://aihot.news/items/vd2lvzvjz4tujiqupl30ifq3k - 原文:https://github.com/anthropics/claude-code/releases/tag/v2.1.293 ## 摘要 Claude Code 发布 v2.1.293,新增 Claude Haiku 5.5(claude-haiku-5-5)作为 Anthropic API 默认 Haiku 模型,支持 1M 上下文,价格为 $0.10/$0.50 每百万 token(超 100K 提示为 $0.50/$2.50)。 ## 推荐理由 发布说明列出了新增默认 Haiku 模型、脚本接口扩展和大量稳定性修复,读者可据此判断是否升级及影响现有工作流。 ## 正文 · 中文译文 ## 变更内容 - 新增 Claude Haiku 5.5(`claude-haiku-5-5`),现为 Anthropic API 上的默认 Haiku 模型——100 万上下文,每百万 token $0.10/$0.50(超过 10 万 token 的提示词为 $0.50/$2.50) - 在 `subagentStatusLine` 载荷中新增 `agentType`,以便脚本区分自定义子代理类型 - 为 mod 在 `$.tool.register` 中新增 `isDeferred`:`false` 从一开始就在提示词中列出工具的 schema,而不是隐藏在工具搜索之后 - 修复了 Claude 有时在上下文压缩后,将自己压缩前的最后操作视为已完成,并撤回或重做已完成工作的问题 - 修复了一个内存泄漏问题:HTTP MCP 连接会保留其发送过的每个请求,直到连接关闭 - 修复了在 Claude 工作时发送的消息,在 `←` 将会话移至后台时丢失的问题;如果排队的消息无法移动,`←` 现在会保持原位并说明情况 - 修复了 `/model` 的 effort ←/→ 越过最高或最低级别循环的问题,该问题可能意外将 Low 保存为模型的默认 effort - 修复了 `/tui` 在以 `--chrome` 启动的会话中,断开 Claude in Chrome 并忽略 `--no-chrome` 的问题 - 修复了在会话(包括恢复的会话)中,当宿主、权限规则或 `--tools` 列表移除了该工具时,Claude 仍被告知使用 `SendMessage` 继续或向子代理发送消息的问题 - 修复了子代理和 `--agent` 会话被告知某个内置工具在整个会话中被禁用的问题,而实际上只是它们自己的工具列表未包含该工具 - 修复了 claude.ai 同步的技能,其编辑后的描述有时要等到新对话或 `/clear` 后才能到达模型的问题 - 修复了 `claude logs`、`stop`、`kill`、`rm` 和 `claude daemon status`、`stop`、`uninstall` 在登录已过期或即将过期时,有时会将你登出的问题 - 修复了页脚的代理计数在短暂读取会话文件夹失败(例如打开文件过多)后消失的问题 - 修复了名为 `worker` 的自定义代理在启动时显示为“Agent”,以及代理详情对话框的标题在代理完成后丢失代理类型的问题 - 修复了 Artifact 工具的转录行在发布调用仍在流式传输时短暂显示为 `Artifact("(unprintable path)")` 的问题 - 修复了 Linux 上的 `/ultrareview` 上传错误拒绝某些仓库的问题,例如位于另一个检出目录内的仓库,原因是沙盒命令运行时某个设置文件“无法解析” - 修复了 `/ultrareview` 上传因拆分索引文件而拒绝的问题,该拒绝建议的 git 命令可能导致 git 无法读取其索引 - 修复了在非常长的 Remote Control 和云会话中,回复仍可能一次显示一个块而不是流式传入的问题 - 修复了 Remote Control 在每次凭据恢复后重新上传会话起始历史的问题 - 修复了 PushNotification 在以 `claude remote-control` 启动的会话中报告“Remote Control inactive”的问题 - 修复了 mod 在 `classic.*` 事件上的钩子在插件钩子工作进程重启期间被跳过的问题,这导致设置钩子在没有它们的情况下进行响应 - 修复了调用 `$.session.append` 的 mod 的 `claude plugin test` 失败的问题;测试可以使用新的 `mock.session` 读回追加的行 - 修复了在装有 Docker Desktop 的 Mac 上(`~/.docker/bin` 下的链接),`claude plugin eval` 拒绝每次授予 Bash 的运行的问题;现在拒绝信息会指明凭据存储的哪一部分持有该链接 - 修复了当 `desktop` 策略设置 Claude Desktop 的内置浏览器键(例如 `builtinBrowserEnabled`)时,Claude 应用网关拒绝启动的问题 - 修复了 `claude agents` 提供绕过权限,但后台会话在同意仅保存在 `.claude/settings.local.json` 或 `--settings` 文件中时忽略该权限的问题;现在它会先请求同意,而忽略绕过的会话会显示一条持续存在的简短通知 - 修复了 `←` 在提示词包含未发送文本时(现在会取消移动)或在问题等待你回答时,于 10 秒后将会话置于后台的问题 - 修复了权限提示中按 Esc 或选择 No 且无反馈时,在刚按下 `←` 将会话移至后台后未能停止回合的问题 - 修复了当会话文件夹无法读取时(例如打开文件过多),代理视图会短暂用占位行替换会话列表的问题 - 修复了当 Claude 在 Bash 工具中使用单文件 cat、head、tail、sed -n 或 grep 命令而非 Read 工具查看文件时,路径作用域规则和嵌套 CLAUDE.md 文件未加载的问题 - 修复了粘贴的文本以相同词语开头和结尾时,有时会被当作手动输入发送给 Claude 的问题 - 修复了粘贴文本中的技能名称被当作手动输入的问题:当粘贴后紧接着输入或粘贴重音符号并合并到其最后一个字母时 - 修复了在报告发送期间按 Ctrl+O 或 Ctrl+Z 后 `/feedback` 返回草稿列表,导致发送无法取消的问题 - 修复了当文件或文件夹无法删除时 `claude purge` 静默停止(退出码 0,或在终端中挂起)的问题;现在它会删除其余部分,列出无法删除的内容,并以退出码 1 退出 - 修复了 keybindings.json 检查:单独的 " "(空格键)不再被报告为错误,而像 "ctrl+ k" 这样的键现在会收到警告 - 修复了 vim 模式下在仅含空格的行上使用 `>>` 和 `<<` 时,光标停留在行尾之后,导致随后的 `x` 未删除任何内容的问题 - 修复了 vim 模式:在可视模式下删除整行(先 `V` 再 `d`)后,光标落在第一个非空白字符上,之后的 `.` 作用于光标所在行 - Windows:修复了停止状态栏、钩子或 shell 命令时,有时会终止被分配了相同进程 ID 的无关进程的问题 - 回退了 2.1.281 中自动模式拒绝消息的更改,该更改曾告知 Claude 拒绝涵盖结果,而不仅是确切的命令 - 回退了 2.1.290 中针对容器重启后云会话保持休眠的修复,该修复丢失了待处理的 `/loop` 唤醒或计划任务;现在不再告知 Claude,会话保持休眠 - 改进了 Team 和 Enterprise 组织的启动:策略和托管设置会更早获取,停滞的请求会在 3 秒后重试 - 改进了 Chrome 中的 Claude:当浏览器报告标签页缓慢时,更少的页面操作被拒绝 - 改进了云会话中当浏览器无法访问时 Chrome 中的 Claude 消息:如果您属于多个组织,现在会说明扩展必须登录到同一个组织,以及如何更改 - 改进了 Bash 编辑差异说明,指出所列文件在命令运行期间发生了更改,这可能包括其他进程的写入 - 改进了工件:Claude 将库固定到两周或更早的精确版本 - 将 claude.ai 技能同步更改为在没有会话使用时大约每 40 分钟检查一次更改,而不是每 10 分钟 - 更改了向模型公布的代理列表和 MCP 服务器顺序:包含非 ASCII 字符的名称现在排在 ASCII 名称之后 - 更改了 OpenTelemetry `claude_code.at_mention` 日志记录,每次读取提示时最多发出 100 个代理事件和 100 个 MCP 资源事件 - 自托管运行器:更改了编排器在轮询之间休眠 4 到 6 秒,而不是固定的 5 秒,以便一个环境的多个副本不会在同一时刻停止轮询 - \[Claude Tag\] 修复了 Claude 在 Slack 中,当 Slack 用未连接的工作区标记消息时,在跨工作区共享的 Enterprise Grid 频道中错误提示工作区未设置的问题 - \[Claude Tag\] 修复了当管理员更改频道的连接器、插件、技能或规则时,Slack 中的 Claude 在频道中任务执行到一半停止的问题;该更改现在会在 Claude 完成后生效 - \[Claude Tag\] 修复了在 Slack 中要求 Claude 立即运行某个话题的例程并附带额外备注时,会启动一个无法回帖的独立运行的问题;该运行现在会在该话题中继续 - \[Claude Tag\] 修复了 Claude Tag 管理设置中访问捆绑包的“添加连接器”对话框在一次 Google 登录后将所有 Google 连接器都显示为已连接的问题 - \[Claude Tag\] 改进了 Claude Tag 管理设置,可列出尚未连接的 Enterprise Grid,并提供“连接”按钮 - \[Claude Tag\] 更改了 Slack 中的 Claude,使其可加入仅管理员可发帖的公告频道,且不会发布其介绍信息 - \[Claude Tag\] 将 Claude Tag 管理设置中频道规则的限制从 20 条提高到 50 条,适用于每个工作区以及组织范围的 Slack 页面 - \[Code Review\] 改进了 Code Review 的“添加仓库”对话框,可列出每个无法添加的仓库及其原因,例如缺少 GitHub 写入权限 ## 正文 · 原文 ## What's changed - Added Claude Haiku 5.5 (`claude-haiku-5-5`), now the default Haiku model on the Anthropic API — 1M context, $0.10/$0.50 per Mtok ($0.50/$2.50 for prompts over 100K) - Added `agentType` to the `subagentStatusLine` payload, so scripts can tell custom subagent types apart - Added `isDeferred` to `$.tool.register` for mods: `false` lists the tool's schema in the prompt from the start instead of behind tool search - Fixed Claude sometimes treating its own last actions before a context compaction as done after it, and retracting or redoing finished work - Fixed a memory leak where an HTTP MCP connection kept every request it had sent until it closed - Fixed a message sent while Claude was working being lost when `←` moved the session to the background; if a queued message can't move, `←` now stays put and says so - Fixed `/model` effort ←/→ wrapping past the highest or lowest level, which could accidentally save Low as a model's default effort - Fixed `/tui` disconnecting Claude in Chrome in a session started with `--chrome`, and ignoring `--no-chrome` - Fixed Claude being told to continue or message subagents with `SendMessage` in sessions, including resumed ones, where a host, a permission rule or a `--tools` list removed that tool - Fixed subagents and `--agent` sessions being told a built-in tool was disabled for the whole session when only their own tool list left it out - Fixed a claude.ai-synced skill's edited description sometimes not reaching the model until a new conversation or `/clear` - Fixed `claude logs`, `stop`, `kill`, `rm` and `claude daemon status`, `stop`, `uninstall` sometimes signing you out when your login had expired or was about to - Fixed the footer's agents count disappearing after a momentary failure to read the sessions folder (for example, too many open files) - Fixed a custom agent named `worker` being shown as "Agent" when it starts, and the agent detail dialog's title losing the agent type once the agent finishes - Fixed the Artifact tool's transcript row briefly reading `Artifact("(unprintable path)")` while a publish call was still streaming in - Fixed the `/ultrareview` upload on Linux wrongly refusing some repositories, such as one inside another checkout, over a settings file that "could not be parsed" while a sandboxed command was running - Fixed the `/ultrareview` upload's refusal over split-index files advising a git command that could leave git unable to read its index - Fixed replies in very long Remote Control and cloud sessions that could still appear a block at a time instead of streaming in - Fixed Remote Control uploading a session's starting history again after every credential recovery - Fixed PushNotification reporting "Remote Control inactive" in sessions started with `claude remote-control` - Fixed a mod's hooks on `classic.*` events being skipped while the plugin hooks worker restarts, which left settings hooks to answer without them - Fixed `claude plugin test` failing for mods that call `$.session.append`; tests can read the appended rows back with the new `mock.session` - Fixed `claude plugin eval` refusing every Bash-granting run on Macs with Docker Desktop (links under `~/.docker/bin`); the refusal now names which part of a credential store held the link - Fixed the Claude apps gateway refusing to start when a `desktop` policy sets Claude Desktop's built-in browser keys, such as `builtinBrowserEnabled` - Fixed `claude agents` offering bypass permissions that background sessions then ignored when consent was saved only in `.claude/settings.local.json` or a `--settings` file; it now asks for consent first, and a session that ignores bypass shows a short notice that stays - Fixed `←` backgrounding a session after 10 seconds while the prompt held unsent text (it now cancels the move) or a question was waiting for your answer - Fixed Esc, or No without feedback, on a permission prompt not stopping the turn when `←` had just been pressed to move the session to the background - Fixed the agents view briefly replacing the session list with placeholder rows when the sessions folder could not be read (for example, too many open files) - Fixed path-scoped rules and nested CLAUDE.md files not loading when Claude views a file with a single-file cat, head, tail, sed -n or grep command in the Bash tool instead of the Read tool - Fixed pasted text that begins and ends with the same words sometimes being sent to Claude as if it had been typed - Fixed a skill name in pasted text being treated as typed when an accent typed or pasted right after the paste merged into its last letter - Fixed `/feedback` returning to the drafts list after Ctrl+O or Ctrl+Z while a report was sending, leaving the send impossible to cancel - Fixed `claude purge` stopping silently (exit 0, or a hang in a terminal) when a file or folder could not be deleted; it now deletes the rest, lists what it could not delete, and exits 1 - Fixed keybindings.json checks: a lone " " (space key) is no longer reported as an error, and keys like "ctrl+ k" now get a warning - Fixed vim mode `>>` and `<<` on a line of only spaces leaving the cursor past the end of the line, where a following `x` deleted nothing - Fixed vim mode: after deleting whole lines in Visual mode (`V` then `d`) the cursor lands on the first non-blank, and `.` after it acts on the cursor's line - Windows: Fixed stopping a status line, hook, or shell command sometimes terminating an unrelated process that had been given the same process ID - Reverted the auto mode denial message change from 2.1.281 that told Claude a denial covers the outcome, not only the exact command - Reverted the 2.1.290 fix for cloud sessions staying asleep after a container restart lost a pending `/loop` wakeup or scheduled task; Claude is no longer told, and the session stays asleep - Improved startup for Team and Enterprise organizations: policy and managed settings are fetched earlier, and a stalled request is retried after 3 seconds - Improved Claude in Chrome: fewer page actions are refused when the browser is slow to report its tabs - Improved the Claude in Chrome message in cloud sessions when the browser can't be reached: if you belong to more than one organization, it now says the extension must be signed in to the same one, and how to change that - Improved the Bash edit diff note to say the listed files changed while the command ran, which can include writes by other processes - Improved artifacts: Claude pins libraries to exact versions two weeks old or older - Changed claude.ai skill syncing to check for changes about every 40 minutes, instead of every 10, while no session is in use - Changed the order of agent lists and of MCP servers announced to the model: names with non-ASCII characters now sort after ASCII names - Changed OpenTelemetry `claude_code.at_mention` logging to emit at most 100 agent and 100 MCP-resource events each time a prompt is read - Self-hosted runner: Changed the orchestrator to sleep 4 to 6 seconds between polls instead of a constant 5, so several replicas for one environment stop polling at the same moment - \[Claude Tag\] Fixed Claude in Slack saying a workspace isn't set up in Enterprise Grid channels shared across workspaces when Slack labels a message with a workspace that isn't connected - \[Claude Tag\] Fixed Claude in Slack stopping mid-task in a channel when an admin changed the channel's connectors, plugins, skills or rules; the change now applies once Claude finishes - \[Claude Tag\] Fixed asking Claude in Slack to run a thread's routine now with extra notes starting a separate run that couldn't post back; the run now continues in that thread - \[Claude Tag\] Fixed an access bundle's Add a connector dialog in Claude Tag admin settings showing every Google connector as connected after one Google sign-in - \[Claude Tag\] Improved Claude Tag admin settings to list an Enterprise Grid that isn't connected yet, with a Connect button - \[Claude Tag\] Changed Claude in Slack to join announcement channels, where only admins can post, without posting its intro - \[Claude Tag\] Changed the limit on channel rules in Claude Tag admin settings from 20 to 50 for each workspace and for the organization-wide Slack page - \[Code Review\] Improved Code Review's Add a repository dialog to list each repository that couldn't be added and why, such as missing GitHub write access