Claude Code 2.1.277：專案指示新增 AGENTS.md 支援，無專屬設定時自動代入

繁體中文

新功能

專案指示新增 AGENTS.md 支援，無專屬設定時自動代入

當你接手遵循通用標準的專案時，只要根目錄中沒有 CLAUDE.md，Claude Code 現在會自動讀取 AGENTS.md 作為指引。

你可以在 /config 的「Project instructions」項目下自訂要讀取的指示檔案。這項功能目前尚未套用至 Bedrock、Vertex 或 Foundry 平台。

新功能

應用網關轉發代理強化，支援自訂標頭並改由代理解析主機名稱

針對僅透過正向代理連線的企業應用網關，現在可設定 CLAUDE_GATEWAY_PROXY_IS_EGRESS_BOUNDARY=1，讓所有對外請求直接交由代理伺服器解析主機名稱，不再於本機自行解析。上游配置新增選填的 headers: 對應表，可向模型供應商前端的自建代理傳送靜態標頭。設定代理時，遙測（telemetry，收集軟體運作數據以利分析的機制）轉發器不再忽略 NO_PROXY 名單中的主機或網域。本機回送連線錯誤訊息現在會明確提示設定 CLAUDE_GATEWAY_ALLOW_LOOPBACK。

新功能

背景任務即時提示更新，工作階段不再因語言伺服器中斷

檢視執行進度時，若背景任務在此期間處理完畢，/tasks 等面板會即時出現提示行，告知有等待檢視的最新進展。以 claude --bg 啟動的背景工作階段，不再因為外掛的語言伺服器（LSP，在背景分析程式碼語法的輔助工具）結束或關閉標準輸入而異常退出。舊版的 TaskOutput 工具已正式移除，Claude 改用 Read 工具讀取背景任務輸出檔，taskOutputMaxChars 設定與 TASK_MAX_OUTPUT_LENGTH 環境變數不再生效。

新功能

無頭工作階段錯誤即時退出，啟動加速且精準累計費用

透過自動化腳本或 SDK 呼叫時，在無頭模式（headless，沒有終端機視覺介面的執行模式）下的工作階段若遭遇內部錯誤，不再無限期卡住，現在會清楚回報錯誤並以狀態代碼 1 退出。接續執行先前的工作階段時，花費用量與權杖計量不再從零起算，無頭工作階段會在結束時妥善儲存總計數據。SDK 與無頭模式的首輪對話不再等待逐層搜尋目錄下的 CLAUDE.md，加快了啟動速度。在 SDK 或 IDE 之外單獨執行的 claude -p 移除了背景生成標題的 Haiku 請求。

問題修復

子代理結果清晰標註縮排，協同快取與訊息排序修復

多個代理同時協同分工時，子代理的執行結果現在會加上專屬標題與縮排後傳回主工作階段，避免回傳內容被誤認為主對話的指令。接續執行的子代理與隊友不再重新渲染已載入的 MCP（Model Context Protocol，讓 AI 連接外部工具的協定）定義。這項改進妥善保護了快取（暫存提示詞以加快反應）機制。對話中途抵達的代理訊息會精準顯示在抵達位置，而非排在指令列下方。在 claude agents 指令中快速輸入不再產生亂碼。代理面板中按下 Enter 鍵能正常選取。雲端工作流程中的腳本提示詞現在明確標註來源。

新功能

外掛安裝防損毀，市集版本精確記錄並支援更新提示

管理擴充套件時，執行 claude plugin install 重新安裝正在被某個工作階段或其他程式使用的外掛版本，若版本未變更會保留原樣，不再損毀已安裝的副本；若市集有新版本，指令會主動提示並建議改用 claude plugin update。官方市集安裝的外掛現在會在 installed_plugins.json 中正確記錄 Git 提交雜湊，更新固定版本的套件時也會同步刷新紀錄。企業市集規則中若存在格式錯誤的項目，系統不再默默關閉整套市集控管策略。外掛重載預覽不再於結束前持續佔用解壓暫存檔，也不會覆寫備援下載快取（暫存安裝檔的空間）。

新功能

外掛面板顯示淨化，特殊名稱不再造成技能管理閃退

開啟外掛分頁瀏覽已安裝清單時，更新失敗等錯誤訊息現在會自動清除終端機控制字元，確保文字清晰可讀。當技能或舊指令命名為 constructor 或 toString 等特殊屬性名稱時，/plugin 與 /skills 介面不再發生閃退。多選安裝全數失敗時會明確顯示失敗通知，不再無聲關閉面板。移除已解除安裝的外掛後，介面不會再殘留「載入失敗」的無效列。獨立列出的 MCP（Model Context Protocol，讓 AI 連接外部工具的協定）伺服器現在會清楚標示所屬的外掛名稱。

問題修復

檔案與搜尋工具全面除錯，精確回報系統資源與比對錯誤

當系統耗盡行程、記憶體或檔案控制代碼導致搜尋無法啟動時，Grep 與 Glob 工具現在會明確報錯，不再誤報為找不到項目。使用 Write 工具寫入既有資料夾路徑時，會明確回報錯誤，不再誤判為權限被拒絕。Edit 工具在處理包含反斜線或非 ASCII 字元的超大文字時，比對失敗會正確顯示找不到字串，不再拋出正規表達式（用符號比對文字的語法）過大的錯誤。Edit 工具也修復了將反斜線後接 uXXXX 文字誤當作 \uXXXX 跳脫處理的問題，可能導致非 ASCII 字元的編輯意外覆蓋跳脫反斜線序列。路徑中的轉義序列會作為文字處理。Windows 環境下工作目錄長度約 120 個字元以上時讀取 PDF 頁面失敗的問題也已修復。

新功能

成果工件發布支援限流重試，專屬工具精確讀取連結

以前 Claude 發布內容撞上頻率限制，會被告知別再重試，但其實東西還沒發出去。發布成果工件（Artifact，AI 產生的獨立檔案或程式碼成果）若觸發頻率限制，系統會清楚告知 Claude 本次尚未發布成功並提示重試時間，不再要求它直接放棄。當對話中包含 claude.ai 工件連結且 Artifact 工具可用時，Claude 會優先使用專屬的工件工具讀取內容，而非使用泛用的 WebFetch 網頁擷取工具。工件工具的權限確認提示語句現在更為簡短，清楚列出頁面與工件的標題或檔名，並將相關連結統一整理在說明文字後方。

新功能

Bash 沙盒複合指令全面受檢，刪除操作主動提示安全防護

開著沙盒（把指令關在隔離區裡跑的防護）時，有些指令其實不該整條溜出去。啟用沙盒時，在沙盒外執行的 Bash 指令中 $TMPDIR 變數不再被展開為空字串。在 sandbox.excludedCommands 豁免設定中，複合指令必須所有子指令都符合規則才能豁免於沙盒，防止部分符合就整條跳出防護。當指令涉及高風險的 rm 刪除操作時，確認提示會具體點出違規指令並建議加上 ${VAR:?} 安全防護變數，讓無頭模式（headless，沒有終端機視覺介面的背景運作模式）也能順利復原。雲端環境上的沙盒提示詞採用官方標準用語，明確規範任務權限邊界。

問題修復

工作階段接續完整保留快取，附件與平行副本技能正常載入

用 --resume 接回舊對話，以前可能當機，或之後每次請求都失敗。接續執行先前的工作階段時，對話歷史若包含純文字助理訊息或空白文字區塊，不再導致請求失敗或崩潰。在 /clear、--continue 或 --resume 接續對話時，若啟動掛鉤（hook，特定事件發生時被觸發的小程式）印出輸出，系統不再遺失首條訊息片段。這項修正避免了快取（暫存提示詞的機制）完全失效。對話附件在重啟後不會被重新渲染，完整保留了思考過程與快取狀態。使用 --worktree 開啟平行副本工作階段時，即使 .claude/skills 未被版控追蹤，也能順利載入主專案技能。歷史紀錄中包含不完整掛鉤摘要的崩潰問題也已修復。

問題修復

設定檔格式異常安全容錯，啟動與外掛管理不再卡死

~/.claude.json 裡只要有一個值格式不對，以前就可能讓 Claude Code 一開就卡住或當掉。使用者在啟動時即便 customApiKeyResponses 或 theme 主題設定值損毀，互動介面也不會卡死或拋出錯誤。開啟 /mcp 工具管理或 /plugin manage 外掛面板時，若 claudeAiMcpEverConnected 欄位格式異常，不會再引發型別錯誤崩潰。遠端控制工作階段的紀錄簿在遇到格式不正確的佔位紀錄時也能正常運作。

問題修復

多版本並行登入不衝突，更新檢查容錯並自動清理快取

莫名被登出、更新時卡住或誤報，這組修的都是登入與更新時會撞到的問題。當本機同時執行新舊版本時，不再發生帳號無預警被登出的問題。代理伺服器回傳無效版本號時，更新檢查不再每 30 分鐘報錯；有設定最低或最高版本時，claude update 不再卡住；格式錯誤的 minimumVersion 現在會被忽略。透過 winget 或 apk 安裝時，若查詢版本失敗不再誤報為最新版本。自動更新失敗後會主動清理 ~/.cache/claude/staging，不再殘留龐大的快取（暫存檔案的空間）。撤銷登入時會提示執行 /login，在主控台登入若伺服器拒絕建立 API 金鑰，也會顯示伺服器錯誤訊息。

新功能

提示詞字元自動過濾清洗，運算中輸入訊息不遺漏

Claude 還在忙時你就先打好下一句，這個習慣現在不會再吃虧。當你在 Claude 仍在運算處理時預先鍵入訊息，這些訊息現在會被妥善排程處理，不再被模型遺漏忽視。輸入提示詞時，系統會主動過濾並清除不可見的 Unicode 格式與標籤字元，並在送出前展示清理後的文字供你確認。從歷史紀錄調出或自外部編輯器載入包含終端機顏色代碼的提示詞時，不再觸發無法復原的介面錯誤崩潰。

問題修復

終端機渲染效能穩定提升，全螢幕文字選取複製即時回饋

慢電腦上剛啟動就當掉、少數情況下畫面停住不動，這兩件事不會再發生。在電腦高負載時啟動工作階段，介面不再因為首次顯示旋轉載入圖示而崩潰退出。內部渲染錯誤後螢幕可能停止刷新的問題已排除，確保畫面在整個工作階段期間持續即時更新。在全螢幕的 /resume 工作階段選擇器與其他覆蓋輸入區的面板中，透過滑鼠拖曳選取文字後，已能正常顯示已複製的提示通知。啟動時商標下方的過長通知提示行，改為以隱藏 N 則通知的簡明文字呈現。

新功能

審查指令指引更智慧，模型清單常駐並精確回報拒絕原因

執行程式碼審查指令 /ultrareview 時，若無待審變更，介面會說明情境並提供審查最新提交紀錄的指令，對新套件庫的首個提交也會完整審查；非互動環境中若無基礎分支或共同歷史則會明確拒絕。在 Anthropic API 模式下，/model 清單一律會顯示 Fable 模型，僅在組織停用時反灰。在 Cowork 雲端工作階段中，WebFetch 網頁擷取與 WebSearch 搜尋工具在請求被拒時會明確告知 Claude 具體原因，例如額度用盡或管理員策略限制。Windows 上回覆後因記憶體不足導致工具呼叫未執行的問題也已修復。

新功能

[VSCode] 面板選單支援快速登出，背景任務與用量統計全面納管

在 VS Code 裡用 Claude Code 的人，這版多了登出、停止背景任務、複製回應等幾項新操作。面板選單中新增了「Sign out」登出選項，並支援在指令列鍵入 /logout 快速登出。代理地圖中現在納入了背景終端機與執行中的背景任務，每項任務均配備停止按鈕，並可透過 /tasks 指令直接開啟檢視。AI 回覆訊息旁新增了複製按鈕，亦可鍵入 /copy 複製完整回覆。閒置的工作階段被自動封存時會彈出單次提示，封存分組中也新增了全部解除封存按鈕。在不適用方案上限的環境中，帳戶用量對話框與工作階段管理器現在會顯示花費與 token（AI 處理與計費的文字單位）使用量。

問題修復

[VSCode] 設定與功能選單直覺開啟，思考程度與快速模式持久保存

在 VS Code 裡設好的偏好，以前重開後可能就不見了。點選「General config」選單項目現在會直接開啟設定頁面，鍵入 /mcp、/hooks（掛鉤，特定事件發生時被觸發的小程式）、/memory、/rewind 等指令也能直接叫出對應的設定對話框。透過思考程度滑桿設定的數值，現在會跨工作階段持續保存，不再遺失先前以 /effort 儲存的等級。以不同大小寫別名（例如「Sonnet」）儲存模型時，模式選擇器不再遺漏自動模式選項。執行 /fast 指令切換的快速模式已能正確儲存為預設值，重新啟動後依然生效。

新功能

[網頁版] 雲端環境分層管理，支援組織共用與嚴謹網路限制

在 Team 或 Enterprise 方案裡共用雲端環境，最怕分不清哪個是自己的、哪個大家都在用。在 Team 與 Enterprise 企業方案中，雲端環境選擇器現在劃分為個人與組織兩個專屬區塊，管理員可直接將個人建立的環境共享給整個組織。組織共用環境在 Code 分頁中預設以唯讀摘要呈現，防止非管理員誤觸修改，編輯功能統一移至管理員設定的雲端環境專區。設定為自訂網路存取但未填寫任何網域的雲端環境，不再無聲還原為受信任模式，儲存時會主動要求至少填入一個網域。管理員設定中的標籤已重新命名為「Cloud sessions」（雲端工作階段），並移除了下方多餘的唯讀行動裝置列。

問題修復

[Claude Tag] 排程跨頻道讀取修復，憑證設定表單與連線日誌升級

在 Slack 裡用 Claude Tag 的團隊，這組修正集中在排程和存取憑證兩塊。在 Slack Enterprise Grid 全組織安裝環境的頻道中建立的例行排程，執行時已能正常讀取同工作區內的其他公開頻道。存取套件中的憑證（用於登入與授權的證明檔案）預設項目上的連結，現在會直接導向各服務供應商專屬的憑證設定指南，而非通用的 API 文件。Pylon 憑證預設項目支援管理員手動指向其歐洲伺服器主機。Google Cloud 憑證表單在上傳金鑰被拒時會具體說明原因，網站與 scopes 會維持鎖定，並在替換被拒時保留貼上的金鑰。管理員設定中的網路事件日誌已修復使用 AWS 簽章、用戶端憑證或自訂憑證授權單位連線時遺漏回應狀態的問題。

English

FEATURE

Added AGENTS.md Support for Project Instructions, Automatically Loaded When No Custom File Exists

When working on projects following common standards, Claude Code now automatically reads AGENTS.md as guidance whenever there is no CLAUDE.md in the root directory.

You can customize the instruction file to read under "Project instructions" in /config. This feature is not yet available on Bedrock, Vertex, or Foundry.

FEATURE

Enhanced Forward Proxy Support for App Gateways, Adding Custom Headers and Proxy-Side Hostname Resolution

For enterprise Claude apps gateways whose only egress is a forward proxy, setting CLAUDE_GATEWAY_PROXY_IS_EGRESS_BOUNDARY=1 now hands the proxy the hostname for every outbound request instead of resolving it locally. An optional headers: map has been added to upstream configurations to send static headers to a custom proxy running in front of a provider. When a proxy is configured, the telemetry relay no longer ignores collector hosts or domains listed in NO_PROXY. Loopback connection error messages now clearly suggest setting CLAUDE_GATEWAY_ALLOW_LOOPBACK.

FEATURE

Real-Time Background Task Update Notices, Preventing Session Crashes from Language Server Exits

When checking task progress, panels such as /tasks now display a line notifying you that an update is waiting if a background task finishes while the panel is open. Background sessions started with claude --bg no longer unexpectedly exit when a plugin's LSP server exits or closes its stdin. The deprecated TaskOutput tool has been officially removed; Claude now reads background task output files using the Read tool, and the taskOutputMaxChars setting along with the TASK_MAX_OUTPUT_LENGTH environment variable no longer have any effect.

FEATURE

Immediate Error Exits for Headless Sessions, Accelerating Startup and Accurately Accumulating Costs

When invoked via automated scripts or the SDK, sessions in headless mode no longer hang indefinitely after encountering an internal error; they now clearly report the error and exit with status code 1. Resuming earlier sessions no longer resets cost and token usage totals to zero, as headless sessions properly save their cumulative totals at exit. The first turn in SDK and headless modes no longer waits on per-directory lookups for CLAUDE.md, speeding up startup. Standalone claude -p runs outside an SDK or IDE have removed the background Haiku auto-title request.

BUGFIX

Subagent Results Clearly Indented Under Headers, Fixing Collaborative Caching and Message Ordering

When collaborating across multiple agents, subagent results are now returned to the main agent under a dedicated header with indented formatting, preventing output from being mistaken for the session's own instructions. Resumed subagents and teammates no longer re-render loaded MCP definitions, preserving the prompt caching mechanism. Agent messages arriving mid-turn now appear precisely where they arrived rather than below the command execution row. Fast typing or pasting in claude agents dispatch input no longer produces scrambled text. Pressing Enter on a selected agent panel row now functions properly. Script-computed prompts in cloud workflows are now clearly framed with their source.

FEATURE

Plugin Installation Corruption Prevention, Accurately Recording Marketplace Versions with Update Prompts

When managing extensions, running claude plugin install to reinstall a plugin version currently in use by a session or another program leaves unchanged copies alone instead of corrupting the installed copy; if a newer version exists in the marketplace, the command now proactively notifies you and suggests claude plugin update. Plugins installed from the official marketplace now correctly record their Git commit hash in installed_plugins.json, and updating a pinned-commit plugin updates this record accordingly. A malformed entry in enterprise marketplace rules no longer silently disables the entire marketplace policy. Plugin reload previews no longer keep unpacked archive files until exit, nor do they overwrite the fallback download cache.

FEATURE

Cleaned Plugin Panel Display, Preventing Skill Management Crashes from Reserved Object Property Names

When browsing installed plugins on the Installed tab, error messages such as failed plugin updates now strip terminal control characters, ensuring clean, readable text. The /plugin and /skills interfaces no longer crash when a skill or legacy command is named after built-in Object properties like constructor or toString. When every install in a multi-select operation fails, the panel now shows an explicit failure notice instead of closing silently. Removing uninstalled plugins no longer leaves orphaned "failed to load" rows in the interface. MCP servers listed separately from their plugins now clearly indicate which plugin they belong to.

BUGFIX

Comprehensive Fixes for File and Search Tools, Accurately Reporting System Resource and Match Errors

When searches cannot start because the system is out of processes, memory, or file handles, the Grep and Glob tools now return explicit errors instead of incorrectly reporting no matches. Writing to an existing directory path with the Write tool now reports a clear error instead of treating it as declined permission. When matching fails on very large edits containing non-ASCII text or backslashes, the Edit tool now properly reports that the string was not found instead of throwing a regular expression too large error. The Edit tool also fixed an issue where an escaped backslash followed by uXXXX text was mistakenly treated as a \uXXXX escape sequence, which could cause edits of non-ASCII characters to accidentally overwrite escaped backslashes. Escaped control characters in paths are now handled as literal text. Reading PDF pages on Windows when working folder paths are long (about 120 characters or more) has also been resolved.

FEATURE

Rate-Limited Artifact Publishes Support Retries, Dedicated Tool Accurately Reads Artifact Links

Previously, when Claude hit a rate limit while publishing, it was told to stop retrying even though nothing had been published. If publishing an artifact hits rate limits, Claude is now clearly informed that nothing was published along with guidance on when to retry, rather than being told to give up completely. When conversations include claude.ai artifact links and the Artifact tool is available, Claude prioritizes reading content with the dedicated Artifact tool instead of using the generic WebFetch tool. Permission prompts for the Artifact tool are now more concise, listing pages and artifacts by title or file name while grouping relevant links after the explanatory text.

FEATURE

Compound Bash Commands Fully Evaluated Under Sandbox, Dangerous Deletions Prompt Safety Guards

With the sandbox on (the guard that runs commands in an isolated area), some commands were slipping out of it entirely when they should not have. When sandboxing is enabled, $TMPDIR no longer expands to an empty string in Bash commands executed outside the sandbox. Under the sandbox.excludedCommands exemption setting, every part of a compound command must match the rule to be exempt from the sandbox, preventing a partial match from bypassing sandboxing entirely. When a command involves high-risk rm deletions, the permission prompt explicitly names the flagged command and suggests adding a ${VAR:?} guard so headless runs can recover. Sandbox prompt instructions on cloud platforms now adopt first-party wording that clearly defines task permission boundaries.

BUGFIX

Full Cache Preservation on Resumed Sessions, Reliably Loading Attachments and Worktree Skills

Picking an old conversation back up with --resume could previously crash it, or make every request after it fail. Resuming an earlier session whose history contains plain-string assistant messages or empty text blocks alongside other content no longer causes request failures or crashes. When continuing sessions after /clear, --continue, or --resume, startup hook output no longer causes the first message fragment to be missed, preventing full prompt cache misses. Conversation attachments are no longer re-rendered after a resume or relaunch, fully preserving extended thinking and prompt cache status. Opening worktree sessions with --worktree now reliably loads main project skills even when .claude/skills is untracked by version control. A crash when resuming transcripts containing incomplete hook summaries has also been resolved.

BUGFIX

Fault Tolerance for Malformed Configuration Files, Preventing Launch and Plugin Management Freezes

A single malformed value in ~/.claude.json used to be enough to make Claude Code hang or crash on launch. Interactive startup no longer hangs or throws errors for users when customApiKeyResponses or theme values are corrupted. Opening /mcp or the /plugin manage panel with a malformed claudeAiMcpEverConnected field no longer triggers type error crashes. Remote Control session bookkeeping now functions properly even when encountering malformed placeholder records.

BUGFIX

Conflict-Free Multi-Version Logins, Tolerant Update Checks and Automatic Staging Cache Cleanup

Unexpected logouts, stalled or misleading updates: this group fixes problems you can hit while signing in and updating. Running older and newer versions locally no longer causes unexpected account logouts. If a proxy returns an invalid version number, update checks no longer error every 30 minutes; when a minimum or maximum version is set, claude update no longer hangs; a malformed minimumVersion is now ignored. Installations managed via winget or apk no longer falsely report being up to date when version lookups fail. Failed auto-updates now proactively clean up ~/.cache/claude/staging, leaving no large staged downloads behind. Errors following revoked logins now lead with /login, and Console sign-in displays the server's error message when API key creation is refused.

FEATURE

Automatic Sanitization for Invisible Prompt Characters, Ensuring Inputs During Processing Are Not Dropped

If you like to type your next message while Claude is still busy, that habit no longer costs you. Messages typed while Claude is actively working are now properly processed rather than being ignored by the model. When prompts are entered, invisible Unicode formatting and tag characters are automatically stripped, displaying the cleaned prompt for your review before sending. Loading prompts containing terminal color codes from history or an external editor no longer triggers unrecoverable interface crashes.

BUGFIX

Stable Terminal Rendering Enhancements, Real-Time Feedback on Fullscreen Text Copying

Crashing right after launch on slow machines and, in rare cases, a screen that stops updating: neither happens anymore. Launching sessions under heavy system load no longer crashes with unrecoverable interface errors when the initial spinner appears. A rare issue where the screen could stop updating for the rest of the session after an internal rendering error has been eliminated, ensuring continuous live updates. In the fullscreen /resume session picker and other panels covering the prompt area, drag-selecting text with the mouse now reliably displays the copied notice. Startup overflow lines under the logo now concisely show how many notices are hidden.

FEATURE

Smarter Code Review Command Guidance, Persistent Model Listings with Clear Refusal Explanations

When running the code review command /ultrareview with nothing to review, the interface now explains the context and offers a command to review your latest commit, while the first commit in a new repository is reviewed in full; in non-interactive sessions, it explicitly refuses when the repository lacks a base branch or shared history. On the Anthropic API, Fable now always appears in the /model list, appearing greyed out only when disabled by organization settings. In Cowork cloud sessions, WebFetch and WebSearch now clearly inform Claude of the exact reason when requests are refused, such as a used-up fetch budget or admin policy restrictions. An issue on Windows where out-of-memory errors immediately following Claude's reply prevented tool calls from executing has also been resolved.

FEATURE

[VSCode] Panel Menu Supports Quick Logout, Comprehensively Managing Background Tasks and Usage Metrics

If you use Claude Code in VS Code, this release adds new actions such as signing out, stopping background tasks, and copying responses. A "Sign out" row has been added to the panel menu, along with support for typing /logout in the command menu. The agent map now includes background shells and running tasks, each equipped with a Stop button, and can be opened directly with /tasks. A Copy response button is now available beside AI responses, alongside a typed /copy command. A one-time notice appears when inactive sessions are archived automatically, and an "Unarchive all" action has been added to the Archived sessions group. In environments where plan limits do not apply, the Account & usage dialog and session manager now display costs and token usage.

BUGFIX

[VSCode] Intuitive Settings and Feature Menus, Persisting Effort Levels and Fast Mode

Preferences you set in VS Code could previously vanish after a restart. Clicking the "General config" menu item now opens settings directly, and typing commands such as /mcp, /hooks, /memory, and /rewind directly opens their respective dialogs. Effort levels adjusted via the slider now persist across sessions on models that already had a level saved with /effort. The mode picker no longer misses the Auto option when saved model settings use differently-cased aliases like "Sonnet". Toggling fast mode with /fast is now correctly saved as the default, remaining active after restarts.

FEATURE

[Claude Code on the Web] Tiered Cloud Environment Management, Supporting Organization Sharing and Network Safeguards

When a Team or Enterprise plan shares cloud environments, the hard part is telling which ones are yours and which ones everyone uses. On Team and Enterprise plans, the cloud environment picker is now divided into Personal and Organization sections, allowing admins to share personal environments with the entire organization. Organization environments open as read-only summaries by default on the Code tab to prevent unauthorized modifications, while editing is consolidated under Admin settings → Cloud environments. Cloud environments saved with Custom network access and no domains no longer silently revert to Trusted mode, and the dialog now requires at least one domain. The admin setting label has been renamed to "Cloud sessions", removing the redundant read-only Mobile row beneath it.

BUGFIX

[Claude Tag] Fixed Cross-Channel Routine Reads, Upgraded Credential Forms and Network Logs

For teams using Claude Tag in Slack, this group of fixes centers on routines and access credentials. Routines created in a Slack channel on an Enterprise Grid org-wide install can now properly read other public channels in their workspace when running. Links on credential presets in Claude Tag access bundles now open each vendor's dedicated credential-setup page instead of generic API documentation. Admins can now point the Pylon credential preset at Pylon's EU host. Google Cloud credential forms in access bundles now explain why a key file is refused, the website and scopes stay locked, and pasted keys are preserved when a replacement is rejected. The network events log in admin settings fixed missing response statuses for connections using AWS signing, client certificates, or a custom CA.

原始 CHANGELOG

Original changelog專案指示新增 AGENTS.md 支援，無專屬設定時自動代入

Added AGENTS.md support: in a project with no CLAUDE.md, Claude Code reads AGENTS.md instead; change it under "Project instructions" in `/config` (not yet on Bedrock, Vertex or Foundry)

Original changelog應用網關轉發代理強化，支援自訂標頭並改由代理解析主機名稱

Added `CLAUDE_GATEWAY_PROXY_IS_EGRESS_BOUNDARY=1` for Claude apps gateways whose only egress is a forward proxy: every outbound request hands the proxy the hostname instead of resolving it locally
Added an optional `headers:` map on Claude apps gateway upstreams, to send static headers to a proxy you run in front of a provider
Fixed the Claude apps gateway's telemetry relay ignoring a collector hostname or domain listed in `NO_PROXY` when a proxy is set
Improved the Claude apps gateway's loopback error messages to name `CLAUDE_GATEWAY_ALLOW_LOOPBACK`

Original changelog背景任務即時提示更新，工作階段不再因語言伺服器中斷

Added a line saying a background task's update is waiting when it finishes while a panel such as `/tasks` is open
Fixed background sessions (`claude --bg`) exiting when a plugin's LSP server exited or closed its stdin
Removed the deprecated TaskOutput tool; Claude reads a background task's output file with Read instead, and the `taskOutputMaxChars` setting and `TASK_MAX_OUTPUT_LENGTH` no longer have any effect

Original changelog無頭工作階段錯誤即時退出，啟動加速且精準累計費用

Fixed `claude -p` and Agent SDK sessions that could hang with no result after an internal error; they now report the error and exit with code 1
Fixed a headless resume (`claude -p --resume`, the SDK, a VS Code extension window reload) starting the session's cost and usage totals at zero; headless sessions now save their totals at exit
Improved session start-up for SDK and headless (`-p`) use: the first turn no longer waits on the per-directory CLAUDE.md lookup
Removed the background Haiku auto-title request from `claude -p` runs launched outside an SDK or IDE

Original changelog子代理結果清晰標註縮排，協同快取與訊息排序修復

Fixed messages from other agents (such as a subagent's SendMessage) that arrived mid-turn showing up below the "Ran N shell commands" row instead of where they arrived
Fixed typed or pasted text occasionally coming out scrambled in the `claude agents` dispatch input during key repeat or very fast input
Fixed Enter on a selected agent panel row doing nothing when `keybindings.json` rebinds Enter in the Chat context, for example to `chat:queueSubmit`
Fixed resumed subagents and teammates re-rendering the MCP tool definitions they had loaded, which broke prompt caching for that agent
Changed subagent results to reach the main agent under a header marking them as subagent output, with the result indented, so text in a subagent's result cannot pass as the session's own instructions
Changed workflow scripts' computed `agent()` prompts on Bedrock, Vertex and Foundry to reach the subagent framed as script-authored text, so the safety classifier does not read them as the user

Original changelog外掛安裝防損毀，市集版本精確記錄並支援更新提示

Fixed `claude plugin install` sometimes failing and breaking the installed copy when reinstalling a plugin version that a session or another program was using; an unchanged copy is now left alone
Fixed one malformed `strictKnownMarketplaces` or `blockedMarketplaces` entry silently disabling the whole enterprise marketplace policy
Fixed plugins from the official marketplace being recorded without their commit in `installed_plugins.json`, and `installed_plugins.json` keeping the old commit after updating a pinned-commit plugin
Fixed plugin reload previews keeping every previewed copy of a plugin archive unpacked until exit, and overwriting the cached `--plugin-url` archive a reload falls back to when its download fails
Improved `claude plugin install` on an already-installed plugin: it now says when the marketplace offers a newer version and names the `claude plugin update` command

Original changelog外掛面板顯示淨化，特殊名稱不再造成技能管理閃退

Fixed `/plugin` not stripping terminal control characters from messages on the Installed tab, such as the error of a failed plugin update
Fixed `/plugin` → Installed and `/skills` crashing when a skill or legacy command is named like a built-in Object property such as `constructor` or `toString`
Fixed `/plugin` closing with no message when every install in a multi-select failed
Fixed uninstalled plugins reappearing as "failed to load" rows in `/plugin` Installed, and Remove not clearing such a row
Improved `/plugin` Installed: an MCP server listed apart from its plugin now shows which plugin it belongs to

Original changelog檔案與搜尋工具全面除錯，精確回報系統資源與比對錯誤

Fixed Grep and Glob reporting no matches when the search could not start because the system was out of processes, memory or file handles; they now return an error saying so
Fixed the Write tool silently ending the turn as a declined permission when the target path is an existing directory; it now reports a clear error
Fixed the Edit tool treating an escaped backslash followed by `uXXXX` text as a `\uXXXX` escape, which could make an edit of a non-ASCII character rewrite an escaped backslash sequence instead
Fixed the Edit tool reporting "Invalid regular expression: regular expression too large" instead of "String not found in file" when a very large edit containing non-ASCII text did not match the file
Fixed a turn ending early with "Path contains null bytes" when a tool call's file path contained `\u0000` written as an escape sequence; escaped control characters now stay as literal text
Fixed PDF page reads on Windows failing when the working folder's path is long (about 120 characters or more)

Original changelog成果工件發布支援限流重試，專屬工具精確讀取連結

Fixed rate-limited artifact publishes telling Claude to stop retrying; Claude is now told nothing was published and when to send the same publish again
Improved artifact link handling so Claude reads claude.ai artifact links with the Artifact tool instead of WebFetch when that tool is available
Improved the Artifact tool's permission prompts: shorter sentences, pages and artifacts named by title or file name, and links listed after the text

Original changelogBash 沙盒複合指令全面受檢，刪除操作主動提示安全防護

Fixed `$TMPDIR` expanding empty in Bash commands that run outside the sandbox while sandboxing is enabled
Fixed a `sandbox.excludedCommands` glob exempting an entire compound Bash command from the sandbox when only one part matched; every part must now match
Improved the dangerous-rm permission prompt to name the flagged rm command and suggest a `${VAR:?}` guard, so headless runs can recover
Changed the Bash sandbox instructions on Bedrock, Vertex and Foundry to the first-party wording, which frames the sandbox as the boundary of what the task was given

Original changelog工作階段接續完整保留快取，附件與平行副本技能正常載入

Fixed conversations failing every request with "text content blocks must be non-empty" when an earlier assistant turn held an empty text block beside other content, including after `--resume`
Fixed a crash when resuming a session whose saved history holds an assistant message stored as a plain string
Fixed sessions continued after `/clear` (restart, `--continue`, `--resume`) missing part of their first message when a SessionStart hook printed output, causing a full prompt-cache miss
Fixed a crash ("unrecoverable interface error") when resuming a session whose saved transcript contains a stop hook summary without a well-formed hook list
Fixed project skills from the main repository not loading in `--worktree` sessions when `.claude/skills` is untracked
Fixed attachments recorded earlier in a conversation being re-rendered after a resume or relaunch, which dropped extended thinking and missed the prompt cache

Original changelog設定檔格式異常安全容錯，啟動與外掛管理不再卡死

Fixed interactive start-up hanging or showing an error for `ANTHROPIC_API_KEY` users when `~/.claude.json` holds a malformed `customApiKeyResponses` value
Fixed a crash ("Type error") when opening `/mcp` or `/plugin manage` with a malformed `claudeAiMcpEverConnected` value in `~/.claude.json`
Fixed a crash at launch when `~/.claude.json` holds a malformed `theme` value
Fixed Remote Control session bookkeeping failing when `~/.claude.json` holds a malformed placeholder record

Original changelog多版本並行登入不衝突，更新檢查容錯並自動清理快取

Fixed being unexpectedly logged out when an older Claude Code build (for example an IDE extension's bundled CLI) runs on the same machine as the current one
Fixed update checks erroring every 30 minutes, and `claude update` hanging when a minimum or maximum version is set, if a proxy returns an invalid version; a malformed `minimumVersion` is now ignored
Fixed `claude update` on winget- or apk-managed installs reporting "up to date" when the version lookup failed
Fixed failed auto-updates leaving large staged downloads behind in `~/.cache/claude/staging`
Fixed the error after a revoked claude.ai login blaming an expired Anthropic profile; it now leads with `/login`
Fixed Console sign-in showing only "Request failed with status code 400" when the server refuses to create an API key; it now shows the server's message

Original changelog提示詞字元自動過濾清洗，運算中輸入訊息不遺漏

Fixed a crash ("unrecoverable interface error") when the prompt held text containing terminal color codes, for example a prompt recalled from history or text loaded from the external editor
Fixed messages typed while Claude is still working sometimes being ignored by the model
Improved prompt handling: invisible Unicode formatting and tag characters in a prompt are removed and the cleaned prompt is shown for review before it is sent

Original changelog終端機渲染效能穩定提升，全螢幕文字選取複製即時回饋

Fixed sessions on slow or heavily loaded machines sometimes exiting with "Claude Code exited after an unrecoverable interface error" when the first spinner appeared
Fixed a rare case where the screen could stop updating for the rest of the session after an internal rendering error
Fixed the "copied" notice not appearing after drag-selecting text in the fullscreen `/resume` picker and other panels that cover the prompt area
Improved the startup notice overflow line under the logo: it now reads "N more notices hidden" instead of "+N more · /status"

Original changelog審查指令指引更智慧，模型清單常駐並精確回報拒絕原因

Fixed a rare case on Windows where a turn could stop with an error such as "Out of memory" right after Claude replied, so that reply's tool calls never ran
Fixed WebFetch and WebSearch in Cowork cloud sessions not telling Claude why a request was refused, such as a used-up fetch budget or an admin policy
Improved `/ultrareview` when there's nothing to review: messages say which case you're in, offer a command that reviews your latest commit, and a new repository's first commit is reviewed in full
Changed Fable to always appear in `/model` on the Anthropic API; it is greyed out only when your organization's settings disable it
Changed `/ultrareview` in non-interactive sessions to refuse when the repository has no base branch or shared history

Original changelog[VSCode] 面板選單支援快速登出，背景任務與用量統計全面納管

[VSCode] Added a Sign out row to the panel menu, with `/logout` in the typed command menu
[VSCode] Added background shells and other running tasks to the agent map, each with a Stop, and a typed `/tasks` that opens it
[VSCode] Added a Copy response button on responses and a typed `/copy`
[VSCode] Added a one-time notice when inactive sessions are archived automatically, and an "Unarchive all" action on the Archived sessions group
[VSCode] Added the session's cost and token usage to the Account & usage dialog and the session manager where plan limits do not apply (Vertex, Bedrock, Foundry, API key)

Original changelog[VSCode] 設定與功能選單直覺開啟，思考程度與快速模式持久保存

[VSCode] Fixed the "General config" menu row showing `/config` usage text instead of opening settings, and made typed `/mcp`, `/hooks`, `/memory`, `/rewind` and similar commands open their dialogs
[VSCode] Fixed the effort slider's level not persisting into later sessions on a model that already had a level saved with `/effort`
[VSCode] Fixed Auto missing from the mode picker for conversations opened in an already-used panel when the saved model setting is a differently-cased alias such as "Sonnet"
[VSCode] Fixed `/fast` not saving fast mode as the default, so it was lost when the extension relaunched Claude Code

Original changelog[網頁版] 雲端環境分層管理，支援組織共用與嚴謹網路限制

[Claude Code on the web] Added Personal and Organization sections to the environment picker on Team and Enterprise plans, and admins can now share a personal environment with the organization
[Claude Code on the web] Changed organization environments to open as a read-only summary from the Code tab on Team and Enterprise plans, with editing under Admin settings → Cloud environments
[Claude Code on the web] Fixed a cloud environment saved with Custom network access and no domains silently reverting to Trusted; the dialog now asks for at least one domain
[Claude Code on the web] Changed the admin Claude Code setting labeled "Web" to "Cloud sessions" and removed the redundant read-only Mobile row beneath it

Original changelog[Claude Tag] 排程跨頻道讀取修復，憑證設定表單與連線日誌升級

[Claude Tag] Fixed routines created in a Slack channel on an Enterprise Grid org-wide install failing to read other public channels in their workspace when they ran
[Claude Tag] Fixed the "Learn more" links on credential presets in Claude Tag access bundles to open each vendor's credential-setup page instead of a generic API reference
[Claude Tag] Changed the Pylon credential preset in Claude Tag access bundles so admins can point it at Pylon's EU host
[Claude Tag] Fixed Google Cloud credential forms in Claude Tag access bundles: a refused key file now says why, the website and scopes stay locked, and a rejected rotation keeps the pasted key
[Claude Tag] Fixed the network events log in Claude Tag admin settings showing no response status for requests through connections that use AWS signing, client certificates or a custom CA