Claude Code 2.1.288：Ctrl+C 清空輸入框後，按向上鍵找回草稿

繁體中文

新功能

Ctrl+C 清空輸入框後，按向上鍵找回草稿

打字到一半如果不小心按到快捷鍵洗掉輸入內容，現在不必再對著空白終端機抱頭嘆氣、全部重打。只要在空白提示詞輸入框直接按下鍵盤向上鍵（Up），就能立刻把剛才被清空的草稿完整救回來。不管是先前貼上的文字還是附加圖片，都會一併回到輸入框。

新功能

/code-review 支援自訂問題清單上限

想要一次看完整份程式碼審查的細節，或是只想控制回報的問題數量，現在你可以自己決定上限。在 Claude 的互動介面輸入 /code-review --max-findings <n> 可指定數量，輸入 /code-review --max-findings all 可列出所有找到的問題。這項選擇會一直沿用，直到你輸入 /code-review --max-findings default 恢復預設值。

新功能

工作階段清單支援快捷鍵搜尋，按 Enter 直達最佳相符項目

手邊同時開著好幾個背景工作時，在代理人總覽畫面尋找特定任務變得省時許多。現在你可以直接按 Ctrl+F 依名稱搜尋工作階段（session，指與 AI 互動的獨立對話流程），並用 Alt+↑ 或 Alt+↓ 在不同分組之間快速跳轉。這些快速鍵與重新命名功能，都能在 keybindings.json 自訂按鍵對應。透過 n: 篩選或 Ctrl+F 搜尋時，按下 Enter 鍵會直接開啟關聯度最高的工作階段，不再機械式地點開清單最頂端的第一列。

新功能

螢幕閱讀器模式強化提示語音，權限清單支援數字直選

依賴語音輔助軟體操作終端機時，多項提示變得更加清楚。當你核准執行計畫時，螢幕閱讀器會即時朗讀目前套用的新權限模式，即使使用 Shift+Tab 快速切換也能正確發聲。在 /permissions 權限管理頁面中，直接按下數字鍵就能選取對應規則，不會再誤觸搜尋框。單字刪除等簡短提示會持續停留在畫面上，直到按下任意鍵或畫面上方內容變動；對話框中已回答的題目旁也會明確標註 answered 字樣，方便確認填答狀態。以上調整都只作用於螢幕閱讀器模式。

問題修復

終端機搜尋游標跟隨打字移動，修復多項輸入與提示異常

在全螢幕模式下翻找歷史紀錄或挑選主題配色時，游標位置現在能即時跟隨打字動態前進。以前在全螢幕歷程檢視器搜尋文字，或是使用 /theme 自訂色彩時，終端機游標常停在原地不動；現在游標會準確跟隨輸入位置移動。在 Windows 系統上，當軟體因首次登入閘道、設定服務提供商或切換 /tui 介面而自動重啟後，鍵盤無法打字的問題已經排除。透過 ctrl+enter 發送佇列訊息後，中斷提示列也不會再出現多餘的替代操作提示。

問題修復

對話歷程恢復更穩定，自動壓縮設定依模型獨立保存

長時間跨工作階段接續處理同一項專案時，對話紀錄與上下文現在能完整保留。以前如果最後一則回覆的 token（AI 處理與計費的文字單位）回報為零，超長對話會直接跳出提示詞過長錯誤；現在會正常觸發自動壓縮。使用 --resume 恢復工作階段時，修正了剛還原的檔案上下文遺失、最後一則回覆未儲存導致看起來像沒回答，以及載入期間檔案被覆寫造成歷程截斷的狀況；恢復由 2.1.286 或更早版本建立的對話時，也不會再遺失模型先前的思考歷程。另外，/autocompact 自動壓縮視窗大小改為依模型各自獨立儲存，切換模型時會自動套用該模型的專屬設定。

新功能

自動模式安全分類機制升級，超長對話優先自動壓縮

讓 AI 自行執行一系列指令時，本機安全檢查機制現在更加平穩可靠。當自動模式阻擋非 Bash 工具的呼叫時，不會再錯誤提示設定 Bash 權限規則。在 Bedrock 與 Mantle 雲端環境中，自動模式遇到網頁擷取摘要或 sonnet 子代理這類請求舊模型的操作後，不會再讓剩餘的工作階段都改用本機分類器。當對話長度超出客戶端安全分類器的檢查上限時，對話歷程會優先自動壓縮，避免後續每個工具呼叫都跳出確認或直接失敗；客戶端分類器也改為：當 ANTHROPIC_DEFAULT_SONNET_MODEL 鎖定為 Claude Sonnet 5.5 或 Opus 5.5 時忽略該鎖定，改用 Claude Sonnet 5。

新功能

雲端環境內建 GitHub API，支援長清單自動分頁

在尚未預裝 GitHub 工具的雲端映像檔中執行任務時，現在可以直接呼叫內建的 API 轉發功能。雲端工作階段現在內建了 gh api 工具，並修正了檔名、篩選條件或錯誤訊息夾帶終端機控制字元的問題。在自行託管的執行環境中，這套內建工具進一步獲得增強：當一般 gh 指令被拒絕時，會直接印出對應的 gh api 語法；使用 --paginate 參數時能自動完整抓取儲存庫多頁清單；在巢狀呼叫 claude 時也不會意外將內建工具移除。

問題修復

Cowork 與雲端工作階段修復多項狀態不同步問題

與團隊成員跨裝置協同處理雲端任務時，連線狀態與權限判斷更加準確。以前在 Cowork 雲端工作階段中，未核准的網頁擷取權限提示若閒置五分鐘未回應，工作階段會卡在等待輸入狀態；現在五分鐘未回應後，工作階段不會再一直顯示為等待輸入。手機加入其他裝置發起的 Cowork 工作階段時，提示建議現在能正常顯示；針對在 /compact 壓縮前發送的訊息，編輯並重試功能也不會再遭到拒絕。雲端工作階段重啟後，若伺服器拒絕新選擇的模型，不會再用該模型繼續回覆；重啟時也不會再還原組織強制模型名單所拒絕的模型。

問題修復

Mod 擴充元件支援選取文字偵測，修復全螢幕按鈕與當機問題

為終端機開發客製化介面擴充元件（mod）時，現在能精準抓取使用者在全螢幕模式下反白選取的內容。新增的 $.ui.selection() 方法可以回傳最後選取的文字；若選取範圍落在單一歷程列中，還會一併回傳該列資料。這次也修復了多項介面異常：在程式重啟前繪製的畫面上點擊按鈕，不會再觸發其他按鈕的動作；在擴充元件於輸入框上方顯示自訂內容時，打開背景工作對話框也不會再引發無法復原的介面錯誤而閃退。

問題修復

外掛套件安裝支援 HTTPS 自動備援，市集連線錯誤完整顯示

在不同作業系統或老舊環境安裝外掛套件（plugin）時，流程現在更具彈性。在 macOS、Linux 上，若機器缺少 GitHub SSH 金鑰，執行 claude plugin install 安裝 GitHub 來源外掛時，複製失敗會自動切換為備援（fallback）的 HTTPS 協定並印出提示。在舊版 Git 中安裝子目錄外掛時，不再發生安裝失敗或快取（把算過或查過的結果暫存起來直接用）不完整的情況。當外掛市集透過 SSH 與 HTTPS 抓取皆失敗時，會顯示兩次嘗試的錯誤訊息，先嘗試的傳輸方式列在上方；透過 --plugin-dir 載入的外掛能在 /plugin 正常顯示設定選項，claude plugin test 也不會再因過期設定而誤判擴充功能被關閉。

問題修復

外掛套件 LSP 支援變數代換，並為延遲請求加上逾時保護

執行包含語言伺服器協定（LSP）或背景計時器的複雜外掛時，執行穩定度獲得顯著提升。外掛的 LSP 設定現在會正確將 ${user_config.*} 與 ${CLAUDE_PLUGIN_ROOT} 替換為實際設定值或預設值，不再直接傳送未解析的文字變數。當語言伺服器使用動態能力註冊或停止回應時，工具呼叫會在 60 秒後自動逾時，避免永久卡住。在工作樹（worktree，Git 讓同一專案平行開多份副本的功能）中執行的子代理，其 tool.call 掛鉤不再導致 Bash 執行失敗或檔案搜尋讀錯目錄。這類掛鉤（hook，特定事件發生時被觸發的小程式）觸發時能維持正確的工作路徑。當外掛的計時器或讀取作業仍在執行時，重新載入或停用外掛也不會強制中斷背景工作階段；若外掛面板遇到無法解析的程式碼差異，會自動改以純文字安全顯示。

新功能

加強危險刪除指令安全防護，簡化權限確認提示

執行包含腳本或自訂變數的終端機指令時，安全把關與操作便利之間取得更好的平衡。在 bash -c 或 sh -c 腳本中若包含針對根目錄或家目錄等危險 rm 刪除操作，即使處於略過權限模式或已設定放行規則，現在都會強制跳出提示要求確認。當指令涉及 BASHPID 算術運算賦值時，也會在執行前主動提示，不再靜默放行。在沙盒（sandbox）自動放行模式下，分隔符未加引號、且僅含純文字與簡單變數的 heredoc 多行文字輸入不會再每次重複要求核准。在啟用工作目錄外部讀取阻擋時，git 設定檔的憑證設定仍會正常生效，未完全檢查的指令也會給出更精簡的提示原因。

問題修復

規則檔改為編輯與新增檔案即觸發載入，掛鉤排程更嚴謹

在多層級目錄架構下編輯專案檔案時，專屬規則的生效時機現在更加精準。以前限定路徑的 .claude/rules 與巢狀 CLAUDE.md 只有在讀取檔案時才會載入；現在當透過寫入或編輯工具建立與修改檔案時，也會立即載入對應範圍的規則。當背景代理人仍在執行時，idle_prompt 閒置通知掛鉤不會再提前觸發。若 PreToolUse 或 PermissionRequest 掛鉤比對失敗或輸入無法轉為 JSON 格式，會直接阻擋工具呼叫以確保安全；子代理因存取檔案而載入規則時，InstructionsLoaded 掛鉤會補齊代理人代碼與型態資訊，並正確回報思考努力程度。

新功能

多代理團隊支援自訂工具與參數，跨工作階段通訊更準確

分派多個子代理（subagent，負責執行特定子任務的獨立 AI 助理）分工協作時，設定與訊息傳遞更加透明。由外掛具名啟動的代理人團隊，現在會確實套用專屬的提示詞、工具清單、禁用工具與思考努力程度，不再退回全域預設值。當跨工作階段訊息被目標階段暫存而未送達時，通知會明確指出未送達並標明該階段名稱；在 SDK 工作階段中，AI 也能在輪次進行中即時得知傳遞狀態。啟動代理人時如果工具清單過長，卡頓問題也已排除；claude mcp serve 能正確回報可用的子代理型態，介面上的提示備註則會根據決策者精準標記為我們、主代理或你。

新功能

MCP 工具呼叫支援權限重新認證，網頁授權流程更順暢

透過 MCP（Model Context Protocol，讓 AI 連接外部工具的協定）串接外部服務時，授權與工具呼叫流程變得更加穩定。當 MCP 伺服器在呼叫工具期間要求更多授權範圍時，會主動跳出重新認證提示。針對無法自行回報授權完成的伺服器，介面會等待使用者點擊完成後才接續執行，讓你有充裕時間在瀏覽器中操作。當遠端伺服器回傳結果超過 16 MB 或無法解析時，不會再引發重複呼叫；桌面版 Code 分頁中的子代理現在能正常使用名為 memory 的 MCP 伺服器工具；雲端工作階段在首輪對話時，也不會再乾等設定為非一律載入的標準輸入輸出伺服器。

新功能

登入憑證儲存失敗即時告警，休眠喚醒避免重複觸發驗證

進行帳號登入或雲端金鑰換發時，憑證庫（credential store，存登入證明的地方）的狀態回報更加準確。以前執行 /login 時，若憑證無法寫入安全儲存區仍會顯示登入成功；現在會如實回報失敗原因，並在登入未生效時提供重試選項。在 --bare 純淨工作階段下，不會再執行無效的登入流程以避免覆蓋已儲存的認證，並會告訴你哪些憑證可用。當筆記型電腦自休眠喚醒且背景已有行程正在驗證時，不會重複彈出第二個瀏覽器登入視窗；在 Bedrock 查詢憑證途中按下停止，會直接結束請求而不會誤將工作階段切換至備援模型；對於關閉額度申請的 Team 與 Enterprise 方案成員，/usage-credits 也會顯示清楚的說明訊息。

問題修復

API 逾時支援部分回覆接續，背景指令時間限制依環境分流

在自動化排程或無頭模式（headless，沒有終端機視窗或視覺介面的執行模式）中執行長任務時，例外處理更加周全。當 API 在回覆途中發生逾時，非互動式工作階段與子代理現在會從已接收的部分回覆繼續往下執行，純思考階段的逾時則會自動重試。看門狗機制在長串流中斷後會重新串流，並在逾時 3 次後停止重試。背景指令的執行時間限制改為只套用於無人值守的工作階段（-p、Agent SDK、CI、雲端），終端機、桌面版與 VS Code 工作階段都不受限；無頭模式在監控行程同時送出 SIGCONT 時忽略終止訊號的問題也已修復。在 -p、SDK 工作階段及 PreToolUse 掛鉤核准時，遙測追蹤原先會將工具受阻的來源或決策顯示為 unknown；在 -p 或遭中斷的輪次中，未回答的權限詢問會漏記 tool_decision 事件，這兩項都已修復。

新功能

遠端操控工作階段在金鑰換發時保持連線，避免誤歸檔

使用遠端操控（Remote Control）功能長期間接管理任務時，連線穩定度與工作階段保留機制獲得強化。當伺服器憑證過期時，工作階段會在憑證換發期間維持連線狀態；即便伺服器故障而停止重試，原本的工作階段也會妥善保留而不被清除。在背景清理程序執行時，仍處於連線中或剛被另一個行程重新接上的工作階段，不會再被錯誤歸檔。

問題修復

支援關閉結構化輸出以相容特製閘道，修復長篇 PDF 讀取問題

在 Mantle 或拒絕結構化輸出的閘道後方，工作階段標題、記憶回想與提示掛鉤（收到提示時觸發的小程式）原本會失敗，現可用 CLAUDE_CODE_DISABLE_STRUCTURED_OUTPUTS 環境變數關閉結構化輸出。Claude 3 Opus 與 Sonnet 載入完整 PDF 後每輪對話出錯的問題已修復。Chrome 擴充在無法使用自動模式時，已核准網站的截圖與讀取不再反覆詢問；打字、導覽及執行 JavaScript 仍會詢問。在 Team 與 Enterprise 方案或受管理機器上，以 Artifact 製作投影片或設計時會套用組織設計系統；Artifact 資料庫達到容量上限時會提示大小限制與釋放空間方法；全新環境或切換模型後的首輪請求會套用伺服器設定的輸出上限與壓縮視窗，可能最多等待 1.5 秒。

問題修復

[VSCode] 修正新對話快捷鍵觸發範圍，歸檔後自動開啟空白聊天

在 VS Code 編輯器內使用 Claude 擴充介面時，分頁操作與對話管理變得更加俐落。啟用新對話快捷鍵後，按下 Cmd+N 或 Ctrl+N 時，現在只會在當前作用中的檢視建立新對話，不會再讓畫面上所有可見的 Claude 視窗同時開出新工作階段。在聊天畫面將當前對話歸檔後，介面會乾淨開啟全新的空白對話，不再自動載入下一筆已儲存的紀錄。在授權 claude.ai 連接器後，若狀態仍停留在需要驗證，MCP 伺服器對話框中現在提供了檢查連線選項以手動重新確認狀態。

新功能

[Cloud sessions] 雲端管理開關解除非關聯設定鎖定，啟動中停止可取消佇列

在後台管理介面調整雲端功能或管理自託管執行節點時，設定與排程控制更加即時。在管理員設定頁面中，雲端工作階段開關不會再因為其他無關的安全性設定正在載入或載入失敗而卡在關閉狀態無法開啟。在自託管執行器（runner）啟動期間若按下停止按鈕，現在會確實取消已進入佇列的訊息，避免執行器就緒後又意外執行原本想取消的任務。

新功能

[Claude Tag] 跨頻道討論串智慧追蹤，頻道設定儲存回報更具體

在 Slack 團隊通訊軟體中使用 Claude Tag 標記功能協作時，跨頻道資訊同步更加即時。當 AI 正在處理的任務依賴另一個頻道中 Claude 曾讀取、但未追蹤的相關討論串時，它現在會主動追蹤該討論串，確保最新補充的上下文能即時傳遞至當前對話中。在頻道設定管理方面，自動建立設定的頻道不再顯示必定失敗的移除範圍選項；在頻道設定頁面儲存失敗時，若自訂指示過長會明確要求縮短，因權限遺失而被拒絕儲存時也不會再誤導提示重試。

問題修復

claude purge 指令名稱縮短，安裝套件驗證更確實

日常整理專案或更新工具版本時，指令輸入變得更短，安裝檢驗也更嚴謹。claude project purge 已更名為 claude purge；舊名稱依然可用，並會印出更名提示。在透過 npm 自動更新套件時，如果原生執行檔下載失敗且系統僅安裝了佔位的存根程式（stub），更新程序會如實回報失敗，不會再誤報更新成功。

English

FEATURE

After Ctrl+C clears the input box, press Up to recover your draft

If you accidentally hit a shortcut mid-typing and wipe out your input, you no longer have to stare at a blank terminal in despair and retype everything. Just press the Up arrow key in the empty prompt input box, and the draft you just cleared comes back intact. Previously pasted text and attached images return to the input box along with it.

FEATURE

/code-review supports a custom cap on the findings list

Whether you want to see every detail of a full code review at once or just control how many issues get reported, you can now set the limit yourself. In Claude's interactive interface, type /code-review --max-findings <n> to specify a count, or /code-review --max-findings all to list every issue found. This choice carries over until you type /code-review --max-findings default to restore the default.

FEATURE

Session list supports shortcut search; press Enter to jump straight to the best match

When you have several background tasks running at once, finding a specific task in the agent overview screen is now much faster. You can press Ctrl+F to search sessions by name (a session is an independent conversation flow with the AI), and use Alt+↑ or Alt+↓ to jump quickly between groups. These shortcuts, along with the rename function, can all be remapped in keybindings.json. When filtering with n: or searching with Ctrl+F, pressing Enter opens the most relevant session directly, instead of mechanically opening the first row at the top of the list.

FEATURE

Screen reader mode strengthens prompt announcements; permissions list supports number-key selection

When operating the terminal with voice assistance software, several prompts are now clearer. When you approve an execution plan, the screen reader immediately reads out the new permission mode being applied, and it speaks correctly even when you switch quickly with Shift+Tab. On the /permissions management page, pressing a number key directly selects the corresponding rule, without accidentally triggering the search box. Brief prompts such as word deletion stay on screen until you press any key or the content above changes; questions already answered in a dialog are also clearly marked with the word answered, making it easy to confirm their status. All of these adjustments apply only to screen reader mode.

BUGFIX

Terminal search cursor follows your typing; multiple input and prompt glitches fixed

When digging through history or picking a theme color in full-screen mode, the cursor position now follows your typing in real time. Previously, when searching text in the full-screen history viewer or customizing colors with /theme, the terminal cursor often stayed frozen in place; now it accurately follows the input position. On Windows, the issue where the keyboard could not type after the software auto-restarted due to first-time gateway login, setting up a service provider, or switching the /tui interface has been resolved. After sending a queued message with ctrl+enter, the interrupt prompt line no longer shows a redundant alternative-action hint.

BUGFIX

Conversation history restore is more stable; auto-compact settings saved per model

When continuing the same project across sessions over a long period, conversation records and context are now fully preserved. Previously, if the last reply reported zero tokens (the unit of text the AI processes and bills), an overlong conversation would immediately throw a prompt-too-long error; now auto-compaction triggers normally. When resuming a session with --resume, fixes cover restored file context going missing, the last reply not being saved so it looked unanswered, and history being truncated because files were overwritten during loading; restoring conversations created by version 2.1.286 or earlier no longer loses the model's prior thinking either. In addition, the /autocompact auto-compact window size is now stored independently per model, and switching models automatically applies that model's own setting.

FEATURE

Auto mode safety classification upgraded; overlong conversations auto-compact first

When letting the AI run a series of commands on its own, the local safety check mechanism is now steadier and more reliable. When auto mode blocks a non-Bash tool call, it no longer wrongly prompts you to set a Bash permission rule. In the Bedrock and Mantle cloud environments, after auto mode encounters operations that request older models—such as web fetch summarization or a sonnet subagent—the rest of the session no longer falls back to the local classifier. When conversation length exceeds the client safety classifier's checking limit, the conversation history is auto-compacted first, avoiding a confirmation prompt or outright failure on every subsequent tool call; the client classifier also now ignores the lock when ANTHROPIC_DEFAULT_SONNET_MODEL is pinned to Claude Sonnet 5.5 or Opus 5.5, and uses Claude Sonnet 5 instead.

FEATURE

Cloud environments get a built-in GitHub API with automatic pagination for long lists

When running tasks in cloud images that do not have GitHub tooling preinstalled, you can now call the built-in API forwarding directly. Cloud sessions now ship with the gh api tool built in, and the issue of filenames, filter conditions, or error messages carrying terminal control characters has been fixed. In self-hosted runners, this built-in tool is further enhanced: when a regular gh command is denied, it prints the corresponding gh api syntax directly; the --paginate flag automatically fetches multi-page repository lists in full; and nested claude invocations no longer accidentally remove the built-in tool.

BUGFIX

Cowork and cloud sessions fix multiple state sync issues

When collaborating with teammates on cloud tasks across devices, connection state and permission judgments are now more accurate. Previously in Cowork cloud sessions, if an unapproved web fetch permission prompt sat unanswered for five minutes, the session got stuck in a waiting-for-input state; now, after five minutes without a response, the session no longer keeps showing as waiting for input. When a phone joins a Cowork session started from another device, prompt suggestions now display properly; and for messages sent before a /compact compression, the edit-and-retry function is no longer denied. After a cloud session restarts, if the server rejects the newly selected model, replies no longer continue with that model; on restart, models rejected by the organization-enforced model list are no longer restored either.

BUGFIX

Mod extensions support selected-text detection; full-screen button and crash issues fixed

When building custom interface extensions (mods) for the terminal, you can now precisely capture what the user has highlighted in full-screen mode. The new $.ui.selection() method returns the last selected text; if the selection falls within a single history row, it also returns that row's data. This release also fixes several interface glitches: clicking a button on a screen drawn before the program restarted no longer triggers another button's action; and when an extension displays custom content above the input box, opening the background-task dialog no longer causes an unrecoverable interface error that crashes the app.

BUGFIX

Plugin installs get automatic HTTPS fallback, and marketplace connection errors are shown in full

Installing plugins on different operating systems or older environments is now more flexible. On macOS and Linux, if the machine lacks a GitHub SSH key, running claude plugin install for a GitHub-sourced plugin will automatically fall back to the HTTPS protocol when cloning fails and print a notice. Installing subdirectory plugins with older Git versions no longer fails or leaves the cache (previously computed or looked-up results stored for direct reuse) incomplete. When a plugin marketplace fails to fetch over both SSH and HTTPS, the error messages from both attempts are shown, with the transport tried first listed on top. Plugins loaded via --plugin-dir now display their settings options properly in /plugin, and claude plugin test no longer misjudges an extension as disabled because of stale settings.

BUGFIX

Plugin LSP support gains variable substitution, plus timeout protection for stalled requests

Running complex plugins that include a Language Server Protocol (LSP) server or background timers is now significantly more stable. Plugin LSP settings now correctly substitute ${user_config.*} and ${CLAUDE_PLUGIN_ROOT} with actual setting values or defaults, instead of sending unresolved text variables. When a language server uses dynamic capability registration or stops responding, tool calls automatically time out after 60 seconds instead of hanging forever. For subagents running in a worktree (a Git feature that opens multiple parallel copies of the same project), tool.call hooks no longer cause Bash execution to fail or file searches to read the wrong directory. When these hooks (small programs triggered when specific events occur) fire, they maintain the correct working path. Reloading or disabling a plugin while its timers or read operations are still running no longer forcefully interrupts the background session; if a plugin panel encounters a code diff it cannot parse, it safely falls back to plain-text display.

FEATURE

Stronger safeguards for dangerous delete commands, simpler permission prompts

When running terminal commands that contain scripts or custom variables, safety checks and convenience are now better balanced. If a bash -c or sh -c script contains a dangerous rm deletion targeting the root or home directory, a confirmation prompt is now forced even in bypass-permissions mode or when an allow rule is configured. Commands involving BASHPID arithmetic assignment also proactively prompt before execution instead of silently passing. In sandbox auto-allow mode, heredoc multi-line input with an unquoted delimiter that contains only plain text and simple variables no longer asks for approval every time. When blocking reads outside the working directory is enabled, credential settings in git config files still take effect normally, and commands that were not fully checked now give a more concise reason in the prompt.

BUGFIX

Rules files now load on edit and file creation, and hook scheduling is stricter

When editing project files in a multi-level directory structure, scoped rules now take effect at more precise moments. Previously, path-scoped .claude/rules and nested CLAUDE.md files only loaded when a file was read; now they also load immediately for the corresponding scope when files are created or modified through the write or edit tools. The idle_prompt idle-notification hook no longer fires early while a background agent is still running. If a PreToolUse or PermissionRequest hook fails to match or its input cannot be converted to JSON, the tool call is blocked outright for safety; when a subagent loads rules by accessing files, the InstructionsLoaded hook now fills in the agent ID and type information and correctly reports the thinking effort level.

FEATURE

Agent teams support custom tools and parameters, with more accurate cross-session messaging

When dispatching multiple subagents (independent AI assistants that handle specific subtasks) to work together, configuration and message delivery are more transparent. Agent teams launched by name from a plugin now properly apply their own prompts, tool lists, disallowed tools, and thinking effort levels, instead of falling back to global defaults. When a cross-session message is held by the target session and not delivered, the notification clearly states it was undelivered and names that session; in SDK sessions, the AI can also learn the delivery status in real time mid-turn. The lag when launching an agent with an overly long tool list has been fixed; claude mcp serve correctly reports the available subagent types, and prompt annotations in the interface are precisely labeled as us, the main agent, or you depending on the decision maker.

FEATURE

MCP tool calls support re-authorization, and the web authorization flow is smoother

Connecting to external services through MCP (Model Context Protocol, the protocol that lets AI connect to external tools) is now more stable for authorization and tool calls. When an MCP server requests additional authorization scopes during a tool call, a re-authorization prompt now appears proactively. For servers that cannot report authorization completion on their own, the interface waits for you to click done before continuing, giving you plenty of time to work in the browser. When a remote server returns a result over 16 MB or one that cannot be parsed, it no longer triggers repeated calls; subagents in the desktop Code tab can now properly use tools from an MCP server named memory; and cloud sessions no longer wait idly on the first turn for stdio servers configured not to load automatically.

FEATURE

Immediate alerts when credential storage fails, and no duplicate verification after wake from sleep

When logging in or rotating cloud keys, status reporting from the credential store (where login proofs are kept) is more accurate. Previously, running /login would still show success even if the credential could not be written to secure storage; now it honestly reports the failure reason and offers a retry option when the login did not take effect. In a --bare clean session, the ineffective login flow no longer runs, avoiding overwriting saved credentials, and you are told which credentials are available. When a laptop wakes from sleep and a background process is already verifying, a second browser login window no longer pops up; pressing stop while Bedrock is querying credentials now ends the request directly instead of mistakenly switching the session to a fallback model; and for Team and Enterprise plan members with credit requests disabled, /usage-credits also shows a clear explanatory message.

BUGFIX

API timeouts support resuming from partial replies, and background command time limits are split by environment

Exception handling is more thorough when running long tasks in automated schedules or headless mode (an execution mode with no terminal window or visual interface). When the API times out mid-reply, non-interactive sessions and subagents now continue from the partial reply already received, while timeouts during a pure thinking phase are automatically retried. The watchdog mechanism restarts the stream after a long stream breaks and stops retrying after 3 timeouts. The execution time limit for background commands now applies only to unattended sessions (-p, Agent SDK, CI, cloud); terminal, desktop, and VS Code sessions are unrestricted; and the issue where headless mode ignored termination signals while sending SIGCONT to a monitored process has been fixed. In -p, SDK sessions, and PreToolUse hook approvals, telemetry previously showed the source or decision of a blocked tool as unknown; in -p or interrupted turns, unanswered permission prompts failed to log the tool_decision event. Both have been fixed.

FEATURE

Remote Control sessions stay connected during key rotation and avoid mistaken archiving

When managing tasks over long periods with the Remote Control feature, connection stability and session retention have been strengthened. When a server credential expires, the session stays connected while the credential is being rotated; even if the server fails and retries stop, the original session is properly preserved instead of being cleared. During background cleanup, sessions that are still connected or were just reattached by another process are no longer mistakenly archived.

BUGFIX

Structured outputs can be disabled for compatibility with custom gateways, and long-PDF reading is fixed

Behind Mantle or gateways that reject structured outputs, session titles, memory recall, and prompt hooks (small programs triggered when a prompt arrives) previously failed; you can now disable structured outputs with the CLAUDE_CODE_DISABLE_STRUCTURED_OUTPUTS environment variable. The issue where Claude 3 Opus and Sonnet errored on every turn after loading a full PDF has been fixed. When the Chrome extension cannot use auto mode, screenshots and reads on approved sites no longer ask repeatedly; typing, navigating, and running JavaScript still prompt. On Team and Enterprise plans or managed machines, creating slides or designs with Artifacts now applies the organization's design system; when the Artifact database reaches its capacity limit, you are told the size limit and how to free up space; and the first request in a fresh environment or after switching models applies the server-configured output limit and compaction window, possibly waiting up to 1.5 seconds.

BUGFIX

[VSCode] New-conversation shortcut now scoped to the active view; archiving opens a blank chat

When using the Claude extension interface inside the VS Code editor, tab handling and conversation management are now tidier. With the new-conversation shortcut enabled, pressing Cmd+N or Ctrl+N now creates a new conversation only in the currently active view, instead of opening a new session in every visible Claude window on screen. After archiving the current conversation in the chat view, the interface cleanly opens a brand-new blank conversation and no longer automatically loads the next saved record. After authorizing a claude.ai connector, if the status remains stuck at needing verification, the MCP server dialog now offers a check-connection option to manually reconfirm the status.

FEATURE

[Cloud sessions] Cloud toggle freed from unrelated settings locks; stopping during startup cancels the queue

When adjusting cloud features in the admin console or managing self-hosted execution nodes, settings and scheduling controls are more responsive. On the admin settings page, the cloud sessions toggle no longer gets stuck in the off position just because other unrelated security settings are still loading or failed to load. If you press the stop button while a self-hosted runner is starting up, queued messages are now actually canceled, preventing the runner from unexpectedly executing tasks you meant to cancel once it becomes ready.

FEATURE

[Claude Tag] Smarter cross-channel thread tracking; channel setting saves report failures more specifically

When collaborating with the Claude Tag feature in the Slack team messaging app, cross-channel information stays in sync more promptly. When a task the AI is working on depends on a relevant thread in another channel that Claude had read but wasn't tracking, it now proactively follows that thread, ensuring newly added context reaches the current conversation in time. For channel settings management, channels whose settings were created automatically no longer show a remove-scope option that was guaranteed to fail; when saving on the channel settings page fails, an overly long custom instruction now triggers a clear request to shorten it, and a save rejected due to lost permissions no longer misleadingly suggests retrying.

BUGFIX

claude purge command name shortened; package install verification more rigorous

For routine project cleanup or tool version updates, commands are shorter to type and installation checks are stricter. claude project purge has been renamed to claude purge; the old name still works and prints a rename notice. When auto-updating packages via npm, if the native binary download fails and the system only has a placeholder stub installed, the update process now honestly reports the failure instead of falsely claiming the update succeeded.

原始 CHANGELOG

Original changelogCtrl+C 清空輸入框後，按向上鍵找回草稿

Added recovery for a prompt cleared with Ctrl+C: pressing Up on the empty prompt brings the draft back, including pasted text and images

Original changelog/code-review 支援自訂問題清單上限

Added `--max-findings <n>|all` to /code-review to report more or fewer findings than the usual limit; the choice is reused until you pass `--max-findings default`

Original changelog工作階段清單支援快捷鍵搜尋，按 Enter 直達最佳相符項目

Added Ctrl+F to find a session by name and Alt+↑/↓ to jump between groups in the agents view; both, and rename, can be rebound in keybindings.json
Changed the agents view `n:` filter (and Ctrl+F search) so Enter opens the session whose name matches best instead of the top row

Original changelog螢幕閱讀器模式強化提示語音，權限清單支援數字直選

Added a screen reader mode announcement of the new permission mode when you approve a plan, including with Shift+Tab
Fixed `/permissions` in screen reader mode: typing a rule's number now picks it instead of opening the search box
Improved screen reader mode: short announcements, such as a deleted word, now stay on screen until your next key press or until something above them on screen changes
Improved screen reader mode: answered questions in question dialogs now say "answered" beside their box

Original changelog終端機搜尋游標跟隨打字移動，修復多項輸入與提示異常

Fixed the keyboard not working on Windows after Claude Code restarts itself (first sign-in to a Claude apps gateway, provider setup, `/tui`)
Fixed the "What should Claude do instead?" hint showing on the Interrupted row after sending queued messages with ctrl+enter
Fixed the terminal cursor not following the typed text in the fullscreen transcript viewer's search and in `/theme`'s custom color search

Original changelog對話歷程恢復更穩定，自動壓縮設定依模型獨立保存

Fixed long conversations failing with "Prompt is too long" instead of auto-compacting when the last reply reported zero token usage
Fixed `--resume` sometimes dropping files and other context that a compaction had just restored
Fixed a resumed session sometimes not saving the last response of a turn, so that the next `--resume` showed the prompt unanswered
Fixed resume occasionally loading a transcript cut short when the same session rewrote the file during the load
Fixed resuming a conversation started on 2.1.286 or earlier dropping the model's earlier thinking
Changed `/autocompact` to save the auto-compact window per model, so each model keeps its own setting when you switch

Original changelog自動模式安全分類機制升級，超長對話優先自動壓縮

Fixed auto mode denials pointing Claude at a Bash permission rule when the blocked tool was not Bash
Fixed auto mode on Bedrock and Mantle switching to the local classifier for the rest of the session after a request to an older model, such as a WebFetch summary or a `sonnet` subagent
Improved auto mode: when a conversation grows too long for the client-side safety classifier to review, it is now compacted instead of prompting for, or failing, every tool call
Changed the client-side auto mode classifier to ignore an `ANTHROPIC_DEFAULT_SONNET_MODEL` pin that names Claude Sonnet 5.5 or Opus 5.5 and use Claude Sonnet 5 instead

Original changelog雲端環境內建 GitHub API，支援長清單自動分頁

Added a built-in `gh api` to cloud sessions whose image has no GitHub CLI, and fixed the built-in sending control characters from file names, jq filters or GitHub errors to the terminal
Self-hosted runner: Improved the built-in `gh api`: a refused gh command now prints its `gh api` equivalent, `--paginate` follows every page of a repository's lists, and a nested `claude` no longer removes it

Original changelogCowork 與雲端工作階段修復多項狀態不同步問題

Fixed cloud sessions that restarted on a newly picked model replying with that model after the server refused it
Fixed Cowork cloud sessions staying marked as waiting for input after a WebFetch permission prompt for an unapproved URL went unanswered for five minutes
Fixed prompt suggestions not appearing on a phone that joins a Cowork cloud session started on another device
Fixed Edit and Retry in Cowork cloud sessions refusing a message sent before `/compact` even though its history was still saved
Fixed restarted cloud sessions restoring a model that the organization's enforced model list refuses

Original changelogMod 擴充元件支援選取文字偵測，修復全螢幕按鈕與當機問題

Added `$.ui.selection()` for mods: returns the text you last selected in fullscreen mode and, when the selection lies within one transcript row, that row
Fixed a mod's button sometimes running a different button's action when pressed on a view drawn before Claude Code restarted
Fixed fullscreen sessions exiting with "unrecoverable interface error" when opening the background tasks dialog while a plugin or mod showed rows above the prompt

Original changelog外掛套件安裝支援 HTTPS 自動備援，市集連線錯誤完整顯示

Fixed `git-subdir` plugin installs failing, or caching an incomplete plugin, on older git (before 2.39, e.g. Ubuntu 22.04's 2.34)
Fixed plugins loaded with `--plugin-dir` not showing "Configure options" in `/plugin`
Fixed `claude plugin install` failing for GitHub-source plugins on macOS and Linux machines with no GitHub SSH key: the clone now falls back to HTTPS and prints a notice
Fixed `owner/repo` plugin marketplaces showing only the second attempt's error when both the SSH and HTTPS fetch fail; both errors are now shown, with the transport tried first on top
Fixed `claude plugin test` reporting mods as turned off remotely when it had only read an out-of-date saved setting

Original changelog外掛套件 LSP 支援變數代換，並為延遲請求加上逾時保護

Fixed a plugin's pane showing nothing when one `Code` element held a diff that does not parse; it now draws as plain code
Fixed plugin LSP servers receiving literal `${user_config.*}` and `${CLAUDE_PLUGIN_ROOT}` placeholders in `initializationOptions` and `settings` instead of substituted values or manifest defaults
Fixed a plugin's `tool.call` hook making Bash fail and file searches read the wrong folder in subagents that run in a worktree
Fixed background sessions ending when a plugin was reloaded or disabled while one of its timers or reads was still running
Fixed LSP tool calls hanging indefinitely when a language server uses dynamic capability registration or stops responding; requests now time out after 60s (per-server `requestTimeout`)

Original changelog加強危險刪除指令安全防護，簡化權限確認提示

Fixed sandboxed heredocs with an unquoted delimiter (`python3 <<EOF`) asking for approval on every run under sandbox auto-allow when the body holds only plain text and simple `$VAR` references
Fixed Bash tool permission check to prompt before a `BASHPID` assignment whose value the shell would evaluate as arithmetic, instead of allowing it silently
Fixed `sandbox.credentials.files` entries on git config files not taking effect while `permissions.blockReadsOutsideWorkingDirectories` is on
Fixed a dangerous `rm` (such as one on `/` or the home directory) inside a `bash -c` or `sh -c` script running without a prompt in bypassPermissions mode or under a shell allow rule (anthropics/claude-code#96300)
Improved Bash permission prompts to give a shorter reason when part of a command can't be checked before it runs

Original changelog規則檔改為編輯與新增檔案即觸發載入，掛鉤排程更嚴謹

Fixed path-scoped `.claude/rules` and nested CLAUDE.md files not loading when Write or Edit creates or changes a file in their scope (previously only Read loaded them)
Fixed `idle_prompt` notification hooks firing while background agents are still running (anthropics/claude-code#93672)
Fixed PreToolUse and PermissionRequest hooks being skipped when matching them failed or the tool's input could not be serialized to JSON; the call is now blocked
Fixed the InstructionsLoaded hook omitting agent_id and agent_type when a subagent's file access loads a rule or nested CLAUDE.md; rules and nested CLAUDE.md files loaded on file access now also report effort

Original changelog多代理團隊支援自訂工具與參數，跨工作階段通訊更準確

Fixed Claude reporting a message to another session as delivered when that session held it: the notice now says it wasn't delivered and names the session, and in SDK sessions Claude can now learn of it mid-turn
Fixed agent teams: a plugin-defined agent spawned by name now runs with its own prompt, tools, disallowedTools and effort instead of the defaults
Fixed a stall when launching an agent whose `tools:` lists very many `Agent(...)` entries
Fixed the Agent tool in `claude mcp serve` always reporting no available agents and rejecting every subagent_type
Improved "You should know" notes to say "we", "the main agent" or "you" depending on who was responsible for a decision

Original changelogMCP 工具呼叫支援權限重新認證，網頁授權流程更順暢

Added a re-authenticate prompt when an MCP server asks for more OAuth scope during a tool call
Fixed MCP tool calls sometimes running twice when a remote server's result was over 16 MB or could not be parsed
Fixed subagents in Claude Desktop's Code tab getting none of the tools of a user-configured MCP server named `memory`
Improved cloud sessions: a new conversation's first turn no longer waits for a stdio MCP server whose config sets `alwaysLoad: false`
Changed MCP URL prompts from servers that can't report when you're done to wait for "I'm done, continue" before the tool call continues, so you can finish in the browser first

Original changelog登入憑證儲存失敗即時告警，休眠喚醒避免重複觸發驗證

Fixed `/login` reporting "Login successful" when credentials could not be saved to secure storage; it now shows the failure, and offers a retry when the new login didn't take effect (anthropics/claude-code#73861)
Fixed a Stop during Bedrock credential lookup sometimes moving the session to a fallback model instead of ending the request
Fixed a second `gcpAuthRefresh`/`awsAuthRefresh` browser sign-in opening when a laptop wakes from sleep while another Claude Code process is signing in
Fixed `/login` in a `--bare` session running a sign-in the session never reads, which could replace your saved login; it now says which credentials work
Improved the `/usage-credits` message shown to Team and Enterprise members whose organization has turned off usage credit requests

Original changelogAPI 逾時支援部分回覆接續，背景指令時間限制依環境分流

Fixed mid-response API timeouts failing the turn: non-interactive sessions and subagents now continue from the partial response, and thinking-only responses are retried
Fixed OpenTelemetry `claude_code.tool.blocked_on_user` spans reporting `unknown` source or decision in `-p` and SDK sessions and for PreToolUse hook approvals
Fixed permission asks that ended unanswered, in `-p` or on an interrupted turn, emitting no `tool_decision` event
Fixed unattended sessions (`CLAUDE_CODE_RETRY_WATCHDOG`) retrying for hours after a very long response stream failed; Claude Code now streams again, and gives up after three timeouts
Fixed headless (`-p` / SDK) sessions occasionally ignoring SIGTERM when a supervisor such as `timeout` or systemd sends SIGCONT alongside it
Changed the background command time limit to apply only in unattended sessions (`-p`, Agent SDK, CI, cloud); terminal, desktop app and VS Code sessions have no limit

Original changelog遠端操控工作階段在金鑰換發時保持連線，避免誤歸檔

Fixed Remote Control cleanup archiving a session that is still connected or was just re-attached by another Claude Code process
Improved Remote Control's recovery from an expired server credential: sessions stay connected during renewal and are kept if it gives up after a server outage

Original changelog支援關閉結構化輸出以相容特製閘道，修復長篇 PDF 讀取問題

Fixed session titles, memory recall and prompt hooks failing on Mantle or behind gateways that reject structured outputs; added `CLAUDE_CODE_DISABLE_STRUCTURED_OUTPUTS` to turn structured outputs off
Fixed Claude in Chrome asking before every screenshot and page read on a site you allowed when auto mode is unavailable (such as with `disableAutoMode` or an older model); typing, navigation and JavaScript still ask
Fixed Claude leaving out your organization's design systems when starting slides or a design with the Artifact tool on Team and Enterprise plans or machines with managed settings
Fixed sessions on Claude 3 Opus and Claude 3 Sonnet failing on every turn after a whole PDF entered the conversation
Fixed the first request in a fresh environment or after a model switch using the built-in output limit and auto-compact window, not the server's; that request may now wait up to 1.5 seconds
Improved the error for an artifact database write refused at the database's size limit: it now states the limit and what frees space

Original changelog[VSCode] 修正新對話快捷鍵觸發範圍，歸檔後自動開啟空白聊天

[VSCode] Fixed a claude.ai connector staying on "Needs authentication" after you authorize it: the MCP servers dialog now offers Check connection
[VSCode] Fixed the opt-in New Conversation shortcut (Cmd/Ctrl+N) starting a conversation in every visible Claude view instead of only the one you are in
[VSCode] Fixed the chat view resuming the next saved session after you archive the one it shows; it now starts a new conversation instead

Original changelog[Cloud sessions] 雲端管理開關解除非關聯設定鎖定，啟動中停止可取消佇列

[Cloud sessions] Fixed the Cloud sessions switch in Claude Code admin settings staying locked off while an unrelated security setting was loading or had failed to load
[Cloud sessions] Fixed pressing Stop while a self-hosted runner was still starting not cancelling the queued message, which could then run once the runner was up

Original changelog[Claude Tag] 跨頻道討論串智慧追蹤，頻道設定儲存回報更具體

[Claude Tag] Fixed Claude Tag admin settings offering a "Remove this scope" option, which always failed, on channels whose settings were created automatically
[Claude Tag] Improved Claude to also follow a related Slack thread in another channel that it only read, so updates there reach the conversation that depends on them
[Claude Tag] Improved save errors on a channel's Configure page: too-long channel instructions now say to shorten them, and a save refused for lost access no longer says to try again

Original changelogclaude purge 指令名稱縮短，安裝套件驗證更確實

Fixed the npm auto-updater reporting success when the platform-native binary failed to download and only the placeholder `claude` stub was installed
Changed `claude project purge` to `claude purge`; the old name still works and prints a notice