繁體中文

新功能

記憶體緊繃即時示警,背景指令不再提早中斷

當電腦記憶體(RAM,負責暫存執行中程式的空間)吃緊時,終端機會直接跳出明顯警示,並附上釋放記憶體或安全重啟的引導步驟。以前在一般記憶體壓力下閒置三十分鐘就會被停止的背景指令,現在只有在記憶體極度不足時才會停下,除錯日誌也會清楚記錄停用原因。

新功能

MCP 連線協定全面升級,啟動等待時間靈活設定

非互動模式現在能透過 CLAUDE_CODE_MCP_STARTUP_WAIT_MS 設定首輪等待 MCP(Model Context Protocol,讓 AI 連接外部工具的協定)伺服器連線的上限時間。搭配空的 --mcp-config 使用 --strict-mcp-config 時,首輪不再因無關伺服器苦等逾時。在串流 JSON 的工作階段中,延後搜尋的工具不再卡住首輪啟動。Bedrock、Vertex 與 Foundry 等安裝環境預設改採第二版用戶端與最新協定交涉。設定檔中無效的 SDK 伺服器項目會直接跳過並發出警告。

問題修復

MCP 工具權限清晰回報,敏感變數安全隱藏

呼叫外部擴充工具時,若因權限不足遭伺服器拒絕,錯誤訊息現在會明確列出缺少的權限項目並提示使用 /mcp 重新驗證,不再誤報為登入過期。連線錯誤日誌與登入工具說明中,不再洩漏環境變數解析後的機密字串。使用傳統 HTTP 與 SSE 協定的伺服器回傳錯誤代碼時已能正確連線。可串流的工具呼叫不再受限於固定時間而提早逾時。當伺服器推送清單變更時,提示詞與資源項目會即時更新。

新功能

OpenTelemetry 遙測記錄升級,請求溯源更透明

系統遙測(telemetry,收集軟體運作數據以利分析的機制)現在於大型語言模型請求追蹤中新增了 effort 思考程度屬性。透過新增的受管設定解析事件,管理者能清楚掌握設定來源與策略狀態,設定環境變數 OTEL_LOG_MANAGED_SETTINGS=1,即可在記錄中自動遮蔽敏感的設定值與摘要。當你將原始請求內容輸出至本機檔案時,新產生的 index.jsonl 索引檔與關聯識別碼能將每次模型回覆精確連結至對應的請求檔案與對話訊息。

新功能

企業網關連線逾時可調,關機等待請求消化

管理 Claude 企業應用的應用程式網關(Gateway,負責轉發與管理連線的中繼伺服器)現在支援在設定中加入 store.connect_timeout_seconds,用以延長資料庫連線逾時秒數。開機時若資料庫連線稍有延遲,網關會主動重試連線最多三次,無法連線時也會明確指出設定位置。當伺服器收到關機訊號時,不再強制切斷進行中的連線,會最多等待二十五秒讓處理中的請求順利傳輸完成。

新功能

網關負載警示強化,額度檢查省時省力

企業應用網關現在會在連線數量超過二百五十六筆時主動發出負載警示,並於遙測資料中納入身分識別資訊。在高承載狀態下,花費用量檢查從原本的四次資料庫往返簡化為一次,有效減少逾時風險;若在檢查期間資料庫連線中斷,系統也能妥善捕捉異常。當使用者在 /login 觸發登入頻率限制時,介面會清楚說明拒絕原因,伺服器日誌也會同步標記觸發的規則與建議修改的設定項。

問題修復

對話記錄智慧修復,目標與掛鉤工作階段不中斷

當對話記錄損毀導致工具呼叫錯誤時,工作階段會嘗試自我修復,或提示使用 /rewind 結束重試迴圈。由掛鉤(hook,特定事件發生時被觸發的小程式)驅動的長任務,在篇幅再次超出上限時會自動壓縮對話。例如執行中的 /goal 在接續已壓縮的工作階段時,不會遺失進行中的目標。對話中輸入的自訂編號清單不再被強制重新排序。阻擋對話的掛鉤重複觸發時改以精簡標籤呈現。

問題修復

子代理參數完整保留,對話紀錄與進度精確呈現

使用 claude agents 指令管理代理時,自動更新重啟後不會再遺失 --model、--effort 或權限模式等啟動參數。在 Bedrock、Vertex 與 Foundry 平台上,指定 Opus 模型的子代理能正確辨識並保留模型設定。子代理回傳給主工作階段的訊息,在桌面版重啟後依然完整保留在對話記錄中;子代理的精簡進度摘要也不會再被冗長的多段回覆意外覆蓋。

問題修復

背景任務接續更流暢,通知彙整省下模型輪次

在無頭模式(headless,沒有終端機視窗的背景執行模式)與 SDK 工作階段中,多個同時完成的背景任務現在會合併為單次模型呼叫處理,不再逐一分次發送請求。恢復執行被中斷的背景代理時,不會殘留不完整的批次工具呼叫;使用 CLAUDE_CODE_RESUME_INTERRUPTED_TURN 接續工作時,也能正確回報先前未完成的背景任務。背景代理等待任務時的狀態通知更加準確。監視工具的腳本輸出與結束狀態合併為單一通知送達。

問題修復

外掛管理效能升級,設定載入不再頻繁重讀

外掛套件(Plugin,擴充系統功能的附加模組)原則由遠端集中管理時,系統啟動時不再頻繁重寫清單檔案,避免桌面版重複重新載入所有工作階段的外掛。外掛重新載入後,執行終端機指令時只有在執行檔目錄變更時才會重新讀取設定檔,有效消除指令執行時的停頓。獨立外掛目錄不再錯誤繼承外部的 Git 版本號;從壓縮檔載入的外掛在多次重載後不會讀取到舊解壓檔案;複製套件庫時預設保留大檔案指標以節省頻寬。

新功能

成果工件讀寫更順暢,團隊協作與發布防覆蓋

成果工件(Artifact,由 AI 產生的獨立檔案或程式碼成果)工具現在於更新前會先確保工作階段讀取最新內容,不再出現確認更新後又被拒絕的窘境。在團隊協作與雲端環境中,讀取隊友工件不再被誤判為網路連線關閉。若尚未登入雲端帳號,首次執行即會明確告知並減少無效重試。發布舊版本時會主動攔截並提供最新頁面以便合併;本機環境中遠端發布的新版本也不會無故打斷目前對話。

問題修復

指令權限把關更嚴密,工作樹隔離與編輯預覽修正

執行包含特殊變數指派或迴圈的終端機指令時,系統現在會正確觸發權限確認提示。在工作樹(worktree,Git 讓同一專案平行開多份副本的功能)隔離的工作階段中,帶有巢狀指令擴展的潛在危險操作會被直接拒絕。在包含多位元組字元(例如中文字)的檔案中,檔案編輯權限提示中的預覽位置不再與實際修改處產生偏差。此外,在移除包含子模組簽出的代理工作樹前,系統會執行更嚴謹的安全檢查以防資料遺失。

問題修復

全螢幕訊息點擊展開,問答預覽與檔案連結修復

在全螢幕模式下,原本摺疊的隊友與代理訊息現在支援點擊展開完整閱讀。終端機中指向本機檔案路徑的可點擊連結,已修正為符合 file:// 協定標準,在 VS Code 等終端機中點擊即可順利開啟檔案。在互動問答工具的預覽模式下,輸入的備註文字會精準附加在當前反白的選項上,按下 Enter 送出時也不會遺失選取的項目。在 Linux Wayland 環境的編輯器終端機中啟動時,不再異常開啟額外的空白編輯器視窗。

問題修復

斜線指令提示精準對齊,程式碼審查更輕量

桌面版工作階段中的錯誤提示現在會引導使用 /usage-credits 等斜線指令,不再推薦無效的命令列參數。當組織政策禁用快速模式時,非互動環境輸入 /fast on 會明確告知已被停用。/schedule 儲存例行排程時能完整保留提示詞角色。/status 指令會正確顯示金鑰輔助程式的失敗細節,並將相關雲端功能統一標示為雲端工作階段。/code-review 改為使用輕量化的內嵌提示詞,不再為一般模型繁衍過多審查子代理。

問題修復

語言伺服器診斷不卡頓,自託管執行器穩定續航

若是語言伺服器(LSP,在背景分析程式碼語法與錯誤的工具)對數千個檔案發布專案診斷時,系統不再於每一輪對話產生明顯延遲。自託管 Runner 執行器在更新 token(驗證身分的授權令牌)遇到短期失敗時會持續重試,遇到授權錯誤時也會主動重新取得憑證,不再讓工作階段頻繁中斷。在程式碼託管平台存取檢查被拒絕的唯讀套件庫,執行器會主動略過而非直接導致啟動失敗。雲端工作階段首輪對話也不會遺漏連線中的 MCP 工具。

新功能

[VSCode] 視窗重載接續執行,自訂選單管理記憶與指示

在 VS Code 中重新載入視窗後,系統會自動接續中斷的步驟並於對話中加上標籤;執行工具期間送出的訊息也不會再因重新載入而遺失。自訂選單中新增了記憶與指示管理項目,方便檢視自動記憶開關與編輯指示檔案。透過新增的 claudeCode.lockEditorGroups 設定,可防止擴充套件鎖定編輯器分組,解決重新開啟分頁或建立新工作階段時版面意外分割的問題。

新功能

[VSCode] 設定寫入防衝突,快捷鍵開啟分頁即刻輸入

在 VS Code 中使用快捷鍵開啟新分頁時,輸入框會自動取得焦點,無需手動點擊即可直接打字。擴充套件並行寫入設定時增加防護,避免 ~/.claude/settings.json 損毀或遺漏設定項。新對話剛建立時使用 /btw 提問,不再錯誤顯示其他工作階段的歷史問答。首次查詢全域忽略檔案時的短暫卡頓已消除,並支援標準的 XDG 設定路徑。在環境變數設定中修改設定目錄後,終端機內的登入與登出狀態會即時反映。

問題修復

[VSCode] 差異比對完整呈現,無障礙與高對比主題修復

對話中的檔案修改差異比對框現在會完全貼合內容行數,即使在長行折行或特殊面板寬度下也不再被底部截斷。在高對比主題下,行內代碼與程式碼區塊已恢復清晰可讀。螢幕報讀軟體現在會清楚朗讀訊息發送者(例如「You」或「Claude」)與執行的工具名稱。計畫審查卡片支援留言清單捲動,不再遮擋意見回饋按鈕。外掛管理與 MCP 對話框支援完整鍵盤操作。工作階段選擇器在搜尋時名稱不再橫向晃動。

新功能

[網頁版] 雲端分支靈活比對,Git 操作與認證更穩定

網頁版雲端工作階段的差異比對檢視中,新增了分支選擇器,讓你自由比對變更與任何分支的差異,不再受限於基準分支。當 GitHub 的 token(用於存取服務的授權令牌)短期更新失敗時,Git 操作不再直接跳出服務不可用的錯誤;認證憑證重新整理後,程式碼提交也不會再出現短暫的簽章失敗。標記已讀的工作階段不會再跳回未讀狀態。

問題修復

[網頁版] 例行排程穩定度提升,連線異常支援長效重試

編輯例行排程(Routine,在雲端定時或依事件觸發的自動化任務)時,不再發生意外觸發兩次或自動重新啟用已暫停排程的狀況。儲存排程若因達到觸發上限等原因無法連結 GitHub,提示訊息會具體指出失敗原因。當擁有者的 GitHub 連線遺失時,排程會跳過當次執行並持續重試長達七十二小時,不再於首次檢查失敗時直接關閉排程。當訂閱暫停導致排程擱置時,通知會清楚引導在恢復訂閱後手動重新開啟排程。

新功能

[Claude Tag] 頻道訪客權限預先設定,機器人標記即時喚醒

在 Claude Tag 管理設定中新增了訪客權限選項,讓管理員在新增頻道時預先指定存取規範。當其他 Slack 應用程式或機器人標記 @Claude 時,即使頻道閒置多日也能正確喚醒並回覆;新頻道建立時的標記訊息也會在加入後順利送達。隔數分鐘後發送的重要後續更新會發布為新的通知訊息,不再靜默修改舊訊息。跨工作區共享頻道監控與環境名稱顯示也已修正。

問題修復

[Claude Tag] 單一頻道搜尋修復,即時進度清單排版最佳化

在 Slack 單一頻道內搜尋訊息時,已修復搜尋失敗的問題並能正確回傳符合的結果。當觸發安全過濾機制而停止時,系統會明確告知原因且不再取消執行中的背景工作。回覆中的電子郵件地址不再顯示多餘的 mailto: 前綴。在熱門討論串中,即時進度檢查清單限制於二千字以內並最多每十五分鐘更新一次,同時自動更新舊的清單連結。在特定頻道編輯 Slack 畫布時,不再反覆附加多餘的訪客註記。

新功能

[Code Review] 審查意見直白易懂,錯誤重試與連結指引完善

自動代碼審查(Code Review)現在以簡短平實的語句發布每條審查結果,讓開發者一眼看懂問題所在。當 GitHub 或內部服務啟動時短暫異常時,系統會自動等待並重試,避免審查意外中斷。重新審查時,已修復的討論串會正常關閉,不再因附加次要備註而維持開啟。若因組織配額限制跳過審查,狀態卡片與留言會直接附上管理頁面連結以利排除限制。

English

FEATURE

Critical Memory Warnings Alert in Real Time, Background Commands No Longer Stop Prematurely

When system memory is running critically low, the terminal now displays a visible warning with guided steps to free memory or restart safely. Background commands that were previously stopped after idling for thirty minutes under mild memory pressure now only stop when memory is critically low, with the debug log clearly recording the reason.

FEATURE

MCP Connection Protocol Upgrades and Flexible Startup Wait Time Configuration

Non-interactive mode can now set the maximum wait time for connecting MCP (Model Context Protocol) servers during the first turn via CLAUDE_CODE_MCP_STARTUP_WAIT_MS. When using --strict-mcp-config with an empty --mcp-config, the first turn no longer gets held up waiting to time out on incidental servers. In streaming JSON sessions, deferred tool search tools no longer stall first-turn startup. Environments such as Bedrock, Vertex, and Foundry now adopt the v2 client and the latest protocol negotiation by default. Invalid SDK server entries in configuration files are skipped with a warning.

BUGFIX

Clear Reporting for MCP Tool Permissions and Safe Masking of Sensitive Variables

When calling external extension tools, if a request is refused by the server due to insufficient permissions, the error message now clearly names the missing permissions and points to /mcp re-authentication instead of misreporting an expired sign-in. Connection error logs and the login tool description no longer leak resolved secret strings from environment variables. Servers using legacy HTTP and SSE protocols now connect properly even when returning error codes. Streamable tool calls are no longer bound to a fixed timeout and won't time out early. Prompts and resources update immediately when a server sends list-changed notifications.

FEATURE

OpenTelemetry Telemetry Logging Upgrades for More Transparent Request Tracing

System telemetry now adds an effort attribute to LLM request traces. Through the new managed settings resolved event, administrators can clearly track configuration sources and policy status, and setting the environment variable OTEL_LOG_MANAGED_SETTINGS=1 automatically redacts sensitive setting values and digests in logs. When exporting raw request bodies to local files, the newly generated index.jsonl file and event attributes accurately link each model response to its corresponding request file and transcript message.

FEATURE

Configurable Timeout for Enterprise Apps Gateway and Graceful Shutdown for In-Flight Requests

The Claude apps gateway now supports adding store.connect_timeout_seconds in its configuration to lengthen the database connection timeout. If the database connection experiences a slight delay during boot, the gateway actively retries the connection up to three times, and clearly points to the configuration location if unreachable. When the server receives a shutdown signal, it no longer forcefully cuts open streams, instead waiting up to twenty-five seconds for in-flight requests to complete transmission smoothly.

FEATURE

Enhanced Gateway Load Warnings and Streamlined Spend Limit Checks

The Claude apps gateway now issues an active load warning when open connections exceed two hundred and fifty-six, and includes identity information in telemetry data. Under high load, the spend-limit check is simplified from four database round trips to one, effectively reducing timeout risks; if the database drops a connection during the check, the system properly handles the exception. When a user triggers sign-in rate limits at /login, the interface clearly explains the refusal reason, while gateway logs flag which limit was hit and suggest which setting to change.

BUGFIX

Smart Transcript Self-Healing and Uninterrupted Goal and Hook Sessions

When a corrupted transcript leads to tool call errors, sessions attempt to self-heal or provide a hint to use /rewind to end retry loops. Long-running tasks driven by hooks automatically compact the conversation when context overflows again after previous compaction. For instance, an active /goal will not lose its ongoing objective when resuming a compacted session. Ordered lists entered in messages are no longer forcefully renumbered. Stop prompt hooks that trigger repeatedly now display with a concise label.

BUGFIX

Subagent Parameters Preserved and Accurate Transcript and Progress Display

When managing agents using the claude agents command, launch parameters such as --model, --effort, and permission modes are no longer lost after an auto-update relaunch. On Bedrock, Vertex, and Foundry platforms, subagents configured with the Opus model correctly recognize and retain their model settings. Messages sent by a subagent to the main session remain fully preserved in the desktop transcript after a relaunch, and a subagent's concise progress summary is no longer accidentally overwritten by a runaway multi-paragraph reply.

BUGFIX

Smoother Background Task Resumption and Notification Batching to Save Model Turns

In headless mode and SDK sessions, multiple background tasks finishing concurrently are now handled in a single model call rather than sending individual requests one by one. Resuming an interrupted background agent avoids leaving behind incomplete batched tool calls, and resuming work with CLAUDE_CODE_RESUME_INTERRUPTED_TURN properly reports previously unfinished background tasks. Status notifications when background agents wait on tasks are more accurate. Script output and exit status from the Monitor tool are delivered merged into a single notification.

BUGFIX

Plugin Management Performance Upgrades and Elimination of Redundant Configuration Reloads

When plugin policy is centrally managed remotely, the system no longer frequently rewrites the manifest file on startup, preventing the desktop version from repeatedly reloading plugins across all open sessions. After plugins reload, terminal commands only re-source the profile if executable directories changed, effectively eliminating command execution stalls. Standalone plugin directories no longer mistakenly inherit version numbers from enclosing Git repositories; plugins loaded from archive files avoid stale extracted files after multiple reloads; and repository clones retain Git LFS pointers by default to save bandwidth.

FEATURE

Smoother Artifact Operations and Overwrite Protection for Team Collaboration and Publishing

The Artifact tool now ensures the session reads the latest content before updating, eliminating the dilemma where an approved update is subsequently refused. In team collaboration and cloud environments, reading a teammate's artifact is no longer misjudged as disabled network access. If not signed in to a cloud account, the terminal clearly notifies on the first attempt and stops futile retries sooner. Publishing based on an older version is proactively intercepted with the newer page provided to merge, and new versions published remotely in local environments no longer interrupt current conversation turns.

BUGFIX

Stricter Command Permission Checks and Fixes for Worktree Isolation and Edit Previews

When executing terminal commands involving special variable assignments or loops, the system now properly triggers permission prompts. In worktree-isolated sessions, potentially dangerous operations with nested shell expansions are directly refused. In files containing multi-byte characters, the preview position in Edit permission prompts no longer drifts from the actual modification location. Furthermore, the system performs stricter safety checks before removing an agent worktree containing submodule checkouts to prevent data loss.

BUGFIX

Click-to-Expand Fullscreen Messages and Fixes for Question Previews and File Links

In fullscreen mode, collapsed teammate and agent messages now support click-to-expand for full reading. Clickable links pointing to local file paths in the terminal have been corrected to adhere to the file:// protocol standard, opening files smoothly when clicked inside terminals like VS Code. In AskUserQuestion preview mode, entered notes attach accurately to the currently highlighted option, and pressing Enter to submit no longer drops the selected item. Launching inside editor terminals on Linux under Wayland no longer unexpectedly opens extra blank editor windows.

BUGFIX

Accurate Slash Command Guidance and Leaner Code Review Execution

Error hints in desktop sessions now suggest slash commands such as /usage-credits instead of invalid command-line flags. When organization policy disables fast mode, entering /fast on in non-interactive environments explicitly reports that it has been disabled. The /schedule command preserves prompt message roles when saving routines. The /status command correctly displays failure details for the API key helper and unifies terminology for related features under cloud sessions. The /code-review command switches to leaner inline review prompts, avoiding spawning excessive review subagents for standard models.

BUGFIX

Fluid Language Server Diagnostics and Reliable Persistence for Self-Hosted Runners

When a language server publishes project-wide diagnostics across thousands of files, the system no longer causes noticeable per-turn slowdowns. Self-hosted runners now keep retrying upon transient failures during token refreshes, and actively fetch new tokens following authentication errors, preventing sessions from frequently breaking. The runner skips read-only repositories refused by the git host during access checks rather than failing session startup. The first turn of a cloud session no longer misses tools from connecting MCP servers.

FEATURE

[VSCode] Resuming Steps Across Window Reloads and Managing Memories and Instructions from Customize Menu

After reloading the window in VS Code, the system automatically continues interrupted steps with a label in chat, and messages sent while running a tool are no longer lost upon reload. The Customize menu adds Memory and Instructions entries to view auto-memory toggles and edit instruction files. A new claudeCode.lockEditorGroups setting prevents the extension from locking editor groups, resolving unintended layout splitting when reopening tabs or starting new sessions.

FEATURE

[VSCode] Conflict-Free Settings Writes and Immediate Focus on New Tab Shortcut

When opening a new tab via shortcut in VS Code, the input box automatically gains focus so you can type immediately without clicking. Overlapping settings writes from the extension now include safeguards to prevent ~/.claude/settings.json corruption or dropped settings. Asking side questions with /btw right after starting a conversation no longer mistakenly displays another session's history. The brief freeze when first querying global gitignore files is resolved, with standard XDG config paths supported. Sign-in and sign-out states in terminals reflect immediately after changing configuration directories in environment variables.

BUGFIX

[VSCode] Full Diffs Display and Fixes for Accessibility and High Contrast Themes

Edit diff boxes in chat now fit the exact number of rows displayed, no longer getting cut off at the bottom under wrapped lines or specific panel widths. Under High Contrast themes, inline code and code blocks are once again clearly readable. Screen readers now clearly announce message senders (such as "You" or "Claude") along with the names of executed tools. The plan review card supports scrolling through comments, preventing the feedback button from being obstructed. Plugin management and MCP dialogs now support full keyboard navigation. Session names no longer shift horizontally when typing queries in the session picker.

FEATURE

[Claude Code on the web] Flexible Cloud Branch Diffing and More Stable Git Operations and Authentication

In the diff view for cloud sessions on the web, a new branch picker lets you freely compare changes against any branch instead of being restricted to the base branch. When GitHub token renewals briefly fail, git operations no longer throw service unavailable errors; and after credentials refresh, commits no longer experience temporary signing errors. Sessions marked as read no longer revert back to an unread status.

BUGFIX

[Claude Code on the web] Improved Routine Reliability and Long-Term Retry for Disconnected Accounts

Editing a routine no longer triggers unintended double firing or automatically re-enables a paused routine. When saving a routine fails to link with GitHub due to repository trigger limits, the toast message explicitly details the failure cause. When the owner's GitHub connection is lost, the routine skips the current run and continues retrying for up to seventy-two hours instead of disabling the routine on the first failed check. When subscription pauses place a routine on hold, the notice clearly guides users to manually re-enable it after restoring the subscription.

FEATURE

[Claude Tag] Upfront Channel Guest Permissions and Prompt Bot Mention Wakeups

A Guests setting has been added to Claude Tag admin settings, allowing administrators to specify access rules upfront when adding channels. When other Slack apps or bots mention @Claude, Claude wakes up and replies properly even after days of channel inactivity; and mentions during new channel creation are delivered smoothly once Claude joins. Significant follow-up updates sent minutes later are posted as new notification replies instead of silently editing previous messages. Monitoring for cross-workspace shared channels and environment name displays have also been resolved.

BUGFIX

[Claude Tag] Fixed Single-Channel Search and Optimized Live Progress Checklist Layout

When searching for messages within a single Slack channel, search failures are resolved and matching results are returned accurately. When stopped by a safety filter, the system explicitly explains the reason and no longer cancels running background work. Email addresses in replies no longer show a redundant mailto: prefix. In busy threads, live progress checklists are capped at two thousand characters and updated at most every fifteen minutes, while automatically updating older checklist links. Editing a Slack canvas in specific channels no longer repeatedly appends redundant guest notes.

FEATURE

[Code Review] Clear and Plain Review Findings with Error Retries and Link Guidance

Automated Code Review now posts each finding using short, plain sentences, allowing developers to understand issues at a glance. When GitHub or internal services experience transient startup errors, the system automatically waits and retries to prevent unexpected interruptions. Upon re-review, resolved threads close normally without staying open due to appended lower-severity notes. If a review is skipped due to organization limits, check-run cards and comments directly link to the admin page for prompt resolution.

原始 CHANGELOG

Original changelog記憶體緊繃即時示警,背景指令不再提早中斷
Added a visible warning when memory usage is critical, with steps to free memory or restart safely
Fixed background commands being stopped after 30 idle minutes on machines under mild memory pressure; they're now stopped only when memory is critically low, and the debug log says why
Original changelogMCP 連線協定全面升級,啟動等待時間靈活設定
Added `CLAUDE_CODE_MCP_STARTUP_WAIT_MS` to bound how long the first non-interactive turn waits for connecting MCP servers (`0` = don't wait)
Fixed `--strict-mcp-config` with an empty `--mcp-config` holding the first non-interactive turn for up to `MCP_TIMEOUT` on incidental MCP servers
Improved startup in `--input-format stream-json` sessions: the first turn no longer waits up to 2s for still-connecting MCP servers whose tools tool search defers; they arrive on a later turn
Changed Bedrock, Vertex, Foundry and telemetry-disabled installs to use the v2 MCP client and MCP 2026-07-28 negotiation with direct HTTP servers by default, as other installs already do (opt out: `MCP_SDK_GENERATION=v1` or `MCP_PROTOCOL_NEGOTIATION=legacy`)
Changed `"type": "sdk"` MCP entries in `.mcp.json`, settings, plugins and agent files to be skipped with a warning: only an SDK host application can register in-process servers
Original changelogMCP 工具權限清晰回報,敏感變數安全隱藏
Fixed MCP servers configured as `http` that only speak legacy HTTP+SSE failing to connect when they answer the first request with 422 or another 4xx error
Fixed Streamable HTTP MCP tool calls timing out after about 5 minutes even when a longer per-server `timeout` was set
Fixed MCP prompts and resources not refreshing when a server sends list-changed notifications without declaring `listChanged`
Fixed MCP tool calls refused with 403 insufficient_scope being reported as an expired sign-in: the error now names the missing permissions and points to `/mcp` re-authentication
Fixed MCP connection errors and the MCP login tool's description showing secrets resolved from `${VAR}` placeholders in MCP configs
Original changelogOpenTelemetry 遙測記錄升級,請求溯源更透明
Added `effort` attribute to the `claude_code.llm_request` OpenTelemetry trace span, matching the `api_request` event
Added `claude_code.managed_settings_resolved` OTel event: managed-settings sources and policy helper state; redacted settings and digests with `OTEL_LOG_MANAGED_SETTINGS=1`
Improved `OTEL_LOG_RAW_API_BODIES=file:<dir>` output: a new `index.jsonl` and `request_body_id` / `message.id` event attributes link each response to its request file and transcript message
Original changelog企業網關連線逾時可調,關機等待請求消化
Added `store.connect_timeout_seconds` to the Claude apps gateway config to lengthen the Postgres connect timeout (default 5 seconds), and improved the boot error when the database is unreachable to point to `store.postgres_url` and the configured timeout
Fixed Claude apps gateway cutting every open stream on SIGTERM: it now lets in-flight requests finish for up to 25 seconds before exiting (`CLAUDE_GATEWAY_DRAIN_TIMEOUT_MS`)
Improved Claude apps gateway boot: it now tries the first Postgres connection up to three times before exiting, so a database that is reachable a few seconds late no longer fails the boot
Original changelog網關負載警示強化,額度檢查省時省力
Added `enduser.sub`, the IdP subject, to the telemetry Claude Desktop and Cowork send through a Claude apps gateway
Added a Claude apps gateway warning when a replica has more requests open than the 256 it sends upstream at once, and a startup log line showing that limit
Fixed an unhandled promise rejection in the Claude apps gateway when Postgres drops a connection during a spend check
Improved the Claude apps gateway's spend-limit check under load: it now takes one database round trip instead of four, so fewer checks time out on a busy gateway
Improved Claude apps gateway sign-in rate limit errors: `/login` now explains the refusal, and the gateway log says which limit was hit and which setting to change
Original changelog對話記錄智慧修復,目標與掛鉤工作階段不中斷
Fixed sessions getting stuck endlessly retrying "unexpected tool_use_id" 400 errors: corrupted transcripts now self-heal where possible, and otherwise a clear error (with a `/rewind` hint) ends the loop
Fixed hook-driven sessions (such as an active `/goal`) ending with "Prompt is too long" instead of compacting when the context overflowed again after a reactive compaction
Fixed an active `/goal` being lost when resuming (`--continue` / `--resume`) a session that had compacted
Fixed the transcript renumbering ordered lists in your own messages (typing "3. 2. 1." displayed "3. 4. 5."); numbers and "N)" markers now show as typed
Fixed Stop prompt hooks re-sending their whole prompt on every block in a conversation; repeat blocks now name the condition with a 500-character label
Original changelog子代理參數完整保留,對話紀錄與進度精確呈現
Fixed `claude agents` losing `--model`, `--effort`, `--permission-mode`, `--allow-dangerously-skip-permissions` and `--agent` after an auto-update relaunch
Fixed subagents with `model: "opus"` on Bedrock, Vertex or Foundry leaving the session's model when its id has no recognizable model family (unless `ANTHROPIC_DEFAULT_OPUS_MODEL` is set)
Fixed a message a subagent sends to the main session disappearing from the Claude Desktop transcript after a relaunch
Fixed a sub-agent's progress summary being replaced by a runaway multi-paragraph reply
Original changelog背景任務接續更流暢,通知彙整省下模型輪次
Fixed a resumed background agent keeping half of an interrupted tool batch when one of its calls was approved with a message
Fixed a local `claude -p --resume` started with `CLAUDE_CODE_RESUME_INTERRUPTED_TURN` not reporting background tasks the previous process left unfinished
Fixed background agent notifications claiming the agent had no live background work when it was still waiting on its own background task and would resume
Fixed headless and SDK sessions making a separate model call for every background task that finished; completions already queued are now answered by one call
Improved Monitor tool notifications: a script's final output and its exit now arrive as one notification instead of two, saving a model turn
Original changelog外掛管理效能升級,設定載入不再頻繁重讀
Fixed a plugin or marketplace directory with no git repository of its own taking its version from an enclosing git repository, such as a git-managed `~/.claude`
Fixed `installed_plugins.json` being rewritten on nearly every start-up when plugin policy comes from remote managed settings, which made Claude Desktop reload every open session's plugins
Fixed the Bash tool re-sourcing the shell profile (a multi-second stall on the next command) after every plugin reload; it now does so only when the plugins' `bin/` directories changed
Fixed plugins with a top-level `$schema` in `hooks/hooks.json` showing an "unknown key" notice
Fixed a plugin loaded from a `.zip` being served from a stale extraction after several overlapping reloads
Changed plugin and marketplace clones to leave Git LFS files as pointers instead of downloading them; `git lfs pull` in the checkout fetches them
Original changelog成果工件讀寫更順暢,團隊協作與發布防覆蓋
Fixed the Artifact tool asking you to approve an update to an artifact that it then refused because the session had not read the latest version
Fixed Cowork and claude.ai cloud sessions with network access on treating reads of a teammate's artifact as if network access were off
Improved Artifact tool errors: when you are not signed in to claude.ai the terminal now says so on the first attempt, and Claude is told to stop retrying a rejected call sooner
Improved artifact publishing: a publish built on an older version is stopped before it is sent, with the newer page to merge
Changed artifact watching in local sessions: a new version published elsewhere no longer starts a turn; Claude learns of it from a later Artifact tool result
Original changelog指令權限把關更嚴密,工作樹隔離與編輯預覽修正
Fixed Bash permission checks for commands that loop over or assign certain special shell variables; these commands now ask for permission
Fixed worktree-isolated sessions accepting Bash commands with certain nested shell expansions; these are now refused
Fixed the Edit permission prompt preview sometimes showing a different location than the approved edit in files with multi-byte characters
Improved safety checks before removing an agent worktree that contains submodule checkouts
Original changelog全螢幕訊息點擊展開,問答預覽與檔案連結修復
Added click-to-expand for collapsed teammate and agent messages in fullscreen mode
Fixed clickable links to local file paths doing nothing in VS Code and other terminals that require a `file://` URI
Fixed AskUserQuestion preview notes being attached to a previously chosen option instead of the highlighted one
Fixed AskUserQuestion preview mode dropping the highlighted option when submitting a note with Enter
Fixed extra empty editor windows opening at startup on Linux under Wayland when running inside the Cursor or VS Code terminal
Original changelog斜線指令提示精準對齊,程式碼審查更輕量
Fixed error hints in Claude Desktop sessions to suggest slash commands like `/usage-credits` instead of CLI flags that cannot be used there
Fixed `/schedule` saving a routine's prompt without its message role when Claude writes the routine in the shape that listing routines returns
Fixed `/status` not showing the `apiKeyHelper` failure that its own error banner told you to check
Fixed `/fast on` in non-interactive sessions reporting on and then turning off under an organization's managed fast mode policy; it now says the organization has disabled it
Changed `/code-review` to use leaner inline review prompts for every model that has no tuned settings of its own, instead of spawning many review subagents
Changed the `/status` GitHub line to read "Cloud sessions", and `/web-setup`, `/ultrareview`, and teleport messages to say "cloud session" instead of "Claude Code on the web"
Original changelog語言伺服器診斷不卡頓,自託管執行器穩定續航
Fixed a per-turn slowdown when a language server publishes project-wide diagnostics for thousands of files
Fixed self-hosted runner sessions failing every turn with a 401 after a few failed token refreshes, until the next scheduled refresh; the runner now keeps retrying, and fetches a new token after a 401
Fixed the first turn of a cloud session sometimes starting without the tools of an SDK-hosted MCP server that was still connecting
Changed self-hosted runners to skip a read-only repository the git host refuses at the access check instead of failing the session start
Original changelog[VSCode] 視窗重載接續執行,自訂選單管理記憶與指示
[VSCode] Added continuation of the step a window reload interrupted, labeled in the chat, with a Claude Code: Continue After Reload setting to turn it off
[VSCode] Added Memory and Instructions entries to the Customize menu: Memory shows the auto-memory toggles, the saved memories and the memory folders, and Instructions edits the CLAUDE.md files
[VSCode] Added a `claudeCode.lockEditorGroups` setting to stop Claude from locking the editor groups it opens in
[VSCode] Fixed a message sent while Claude was running a tool disappearing from the conversation after a window reload
[VSCode] Fixed reopening a closed Claude tab splitting the editor layout when its locked group still holds another Claude tab and a file
[VSCode] Fixed New session opening another locked editor group whenever a file tab shared the group with your Claude tab
Original changelog[VSCode] 設定寫入防衝突,快捷鍵開啟分頁即刻輸入
[VSCode] Fixed a `/btw` side question asked in a new conversation's first seconds occasionally showing another session's side-question history
[VSCode] Fixed a brief freeze when the extension first looks up your global gitignore file
[VSCode] Fixed sign-ins and sign-outs made in a terminal not showing until a reload after `CLAUDE_CONFIG_DIR` changed in the Environment Variables setting
[VSCode] Fixed overlapping settings writes from the extension leaving `~/.claude/settings.json` unparseable or dropping a setting
[VSCode] Fixed Open in New Tab (Ctrl/Cmd+Shift+Esc) sometimes leaving the new tab's message box unfocused, so typing went nowhere until you clicked it
[VSCode] Changed the default global gitignore file to `$XDG_CONFIG_HOME/git/ignore` when `XDG_CONFIG_HOME` is an absolute path
Original changelog[VSCode] 差異比對完整呈現,無障礙與高對比主題修復
[VSCode] Fixed the Manage Plugins enable toggle and MCP servers dialog rows being unreachable from the keyboard
[VSCode] Fixed Edit diffs in the chat being cut off at the bottom at some panel widths and for long wrapped lines; diff boxes now fit the rows shown
[VSCode] Fixed session names shifting sideways in the session picker while typing a search query
[VSCode] Fixed the plan review card cutting off its Send feedback button and reason field when a plan has several comments; the comment list now scrolls
[VSCode] Fixed inline code and code blocks in chat replies being unreadable under the High Contrast themes
[VSCode] Improved screen reader navigation of the conversation: each message is announced as "You" or "Claude", with the tool name for tool steps
Original changelog[網頁版] 雲端分支靈活比對,Git 操作與認證更穩定
[Claude Code on the web] Added a "Compare against" branch picker to a cloud session's diff view, so you can diff its changes against any branch instead of only the base branch
[Claude Code on the web] Fixed git operations in cloud sessions failing with "service unavailable" when GitHub's token renewal briefly errors
[Claude Code on the web] Fixed commits in cloud sessions occasionally failing with a signing error for a few minutes after the session's credentials refreshed
[Claude Code on the web] Fixed sessions sometimes flipping back to unread right after you mark them read
Original changelog[網頁版] 例行排程穩定度提升,連線異常支援長效重試
[Claude Code on the web] Fixed editing a routine occasionally making it fire twice or re-enabling a routine that had just been paused
[Claude Code on the web] Fixed the toast after saving a routine whose GitHub trigger couldn't be linked to show the reason, such as a per-repository trigger limit, instead of only "edit to retry"
[Claude Code on the web] Changed routines to skip a run and retry for up to 72 hours when the owner's GitHub connection is missing, instead of switching the routine off at the first failed check
[Claude Code on the web] Changed a routine's on-hold notice: when your subscription is paused it now tells you to turn the routine back on yourself instead of promising an automatic resume
Original changelog[Claude Tag] 頻道訪客權限預先設定,機器人標記即時喚醒
[Claude Tag] Added a Guests setting to the Add channel and Add workspace forms in Claude Tag admin settings, so owners can pick Inherit, Allow, Channel only or Restrict up front
[Claude Tag] Fixed Claude not answering when another Slack app or bot @mentions it; the tag now gets a reply and wakes Claude in a channel it had stopped following after days of inactivity
[Claude Tag] Fixed Claude missing another app's message that tagged @Claude right after a new Slack channel was created; it's now delivered once Claude has joined
[Claude Tag] Fixed Claude folding a follow-up sent minutes after its last Slack message into it as a silent edit; late updates such as blockers now post as a new reply that notifies
[Claude Tag] Fixed Claude refusing to watch an Enterprise Grid channel shared with the whole organization when asked from another workspace in the grid
[Claude Tag] Fixed the Environment picker in Claude Tag admin settings showing a raw environment ID instead of the environment's name for archived or app-created environments
Original changelog[Claude Tag] 單一頻道搜尋修復,即時進度清單排版最佳化
[Claude Tag] Fixed Claude's Slack search failing with an error whenever it searched within a single channel; it now returns that channel's matching messages
[Claude Tag] Fixed a safety-filter stop silently resetting a Slack thread's context when nobody was waiting; Claude now always says so and no longer cancels background work still running
[Claude Tag] Fixed email addresses in Claude's Slack replies rendering with a visible `mailto:` prefix; they now show as the plain, clickable address
[Claude Tag] Improved Claude's live progress checklist in Slack: capped at 2,000 characters, reposted at most every 15 minutes in busy threads, with older "Latest task list" links updated
[Claude Tag] Removed the repeated guest-attribution note Claude appended to a Slack canvas each time it edited one in a channel using the "Channel only" guest setting
Original changelog[Code Review] 審查意見直白易懂,錯誤重試與連結指引完善
[Code Review] Fixed re-reviews occasionally leaving a fixed finding's thread open when the new review also filed a lower-severity note under it
[Code Review] Fixed rare reviews ending with "Code review encountered an error" when GitHub or an internal service failed transiently at launch; they now wait and retry
[Code Review] Improved how Code Review words each posted finding: short plain sentences that say who is affected, where the code goes wrong, and the fix up front
[Code Review] Improved the check-run card and PR comment when a review is skipped because of an organization limit: each cause now links the admin page that fixes it