Claude Code 2.1.248

長工作階段裡請 Claude 處理複雜工作，最怕它途中重新整理工具說明，連延伸思考的脈絡也跟著掉了。

先前這種提示詞快取（把已處理內容暫存起來直接用）失效大約每小時發生一次。帳號進入用量超額後再用 --resume 接續時，ScheduleWakeup 的定義也固定了，第一輪不會因此整份重算。

背景工作隔著關機再回來，最需要的是看清它真正停在哪。

新建工作階段也不再誤開較舊的對話，或吞掉你剛打的提示。若一個已停止的工作階段早已在另一個終端機接續，再從 claude agents 打開不會啟動第二個行程；該列會直接說它已在某個終端機開啟。

打開 claude agents 時，該問的工作區信任提示不會因設定了 CI 環境變數（程式啟動時讀取的設定值）就被跳過。PR 狀態快取（把查過的合併請求結果暫存起來）混入損壞資料時，啟動也不再崩潰。

背景工作階段卡住不動時，原因若是 PermissionRequest 或 PreToolUse 掛鉤（特定事件發生時觸發的小程式）印出無效答案，claude agents 現在會直接列出掛鉤名稱與 schema error。schema error 是回覆結構不符規格。掛鉤 stdout（程式的一般文字輸出）若印出看似物件的 {…}，卻不是合法 JSON，也不再被當成普通文字略過，而會回報掛鉤錯誤與解析訊息。

工作樹（Git 讓同一專案平行開多份副本的功能）分支若已併入你簽出的預設分支，例如本機 main，即使還沒 push，claude agents 與 claude rm 也不會再以「有提交尚未推送」拒絕刪除。反過來，仍在執行的背景工作階段會持有工作樹的鎖。清理程序與 git worktree remove 會略過它，不會讓工作中的代理突然失去簽出內容。

另一個 Claude Code 行程正在更新 token（用來證明登入狀態的授權令牌），剛好你的工作階段 token 又過期時，過去會直接把你送回登入畫面。

修正後，這次請求會以可重試的錯誤失敗。它沒有說請求會自動成功，也沒有改變登入方式；差別是短暫的更新鎖衝突不再被誤當成你需要重新登入。

有些機器已設定 ANTHROPIC_API_KEY，或使用 API 金鑰輔助程式，因此無法採用 /login 建議的 Console 登入。以前流程還沒顯示登入網址，就先以 OAuth 錯誤中止。現在 /login 會改走 API 金鑰登入，讓既有憑證來源能接手。這是登入方式的備援，不是上一張 token 更新鎖的重試機制。

連上 Claude apps 閘道時，若流程需要受管設定的安全核准對話框，/login 不會再卡住。另一種情況是 apiKeyHelper 成為唯一憑證來源；過去即使開啟閘道模型探索，探索也完全不執行，現在已能運作。原文點名的環境變數是：

CLAUDE_CODE_ENABLE_GATEWAY_MODEL_DISCOVERY

這個環境變數（程式啟動時讀取的外部設定）只控制原文所說的模型探索。

MCP（讓 AI 連接外部工具的協定）項目現在會按真實範圍顯示。專案 .mcp.json 中宣告 claude.ai connector type 的項目，不再列在受信任的「claude.ai」標題下，而會出現在真正範圍。型別宣告不會改變它的歸類。

MCP（讓 AI 連接外部工具的協定）server 的 headersHelper 若提供 Authorization header，遇到 401 時，現在會照文件重跑 helper 並重試呼叫，不再落入 OAuth discovery。

你在 Claude Desktop 或 Cowork 開的工作階段，只要應用程式裡還留著，它的逐字稿就不會再因為例行清理而在 30 天後被刪掉。如果你的組織有自己的保留規則，仍照組織的走。想給這個「不刪」設一個期限，就到 ~/.claude/settings.json 加一行，數字換成你要保留的天數（範例是 30）：

{"desktopSessionCleanupPeriodDays": 30}

跑完 claude logs 回到原本的終端機後，滑鼠操作或貼上方式不該還像停留在日誌介面。這次修正會在離開時關掉三種先前殘留的模式：mouse tracking、bracketed paste，以及 alternate screen。它們分別影響滑鼠事件、貼上內容的邊界標記與終端機使用的替代畫面。修正只保證 claude logs 不再把這些模式留著，沒有改你的其他終端機設定。

終端機裡幾個看似小問題，都指向同一件事：文字應照原字顯示，欄位也該站在正確位置。

/model 與快速模式切換通知中的模型名稱改用程式碼樣式，因此 [1m] 這類字尾會按字面顯示，不再變連結。信任對話框的儲存庫權限規則很長時，不再因從 emoji 中間截斷而出現亂碼。開機警告也不再比其餘逐字稿右移一欄。

你按下 ctrl+c，接著立刻按 shift+tab 切換權限模式時，畫面會同時需要顯示退出提醒與權限狀態。以前「Press Ctrl-C again to exit」提示會蓋住權限模式指示器，讓人無法確認剛才是否切換成功。現在兩者不再互相遮擋；修正的是這個緊接按鍵的顯示順序，沒有改 ctrl+c 或 shift+tab 本身的功能。

用 /ultrareview 或從本機播種雲端工作階段時，未提交修改可能藏在編輯器自動留下的暫存、臨時或備份副本。現在 prod.env 類檔案、*.tfvars，以及憑證檔的這些副本都不會上傳，例如 key.pem.tmp、id_rsa.swo；修改會留在你的機器上。這項修正鎖定的是這些敏感檔案及其副本，不代表所有未提交檔案一律不上傳。

Remote Control 工作階段在 CLI 靜默重連後，連線裝置偶爾會停在舊畫面：該出現的權限提示沒來，最新訊息也看不到。

這個偶發同步問題已修正，裝置會重新看到權限提示與最新訊息。修正針對 CLI 靜默重連後的顯示缺漏，原文沒有宣稱所有 Remote Control 連線問題都因此解決。

包裝程式有時會在 claude remote-control 子命令前插入選項，使用者也可能先放全域旗標。過去只要前方多了這些內容，子命令自己的 --spawn、--name 等旗標就可能被拒絕。現在解析順序已修正，前面的全域旗標或包裝程式注入選項，不會妨礙 remote-control 讀取自己的旗標。

雲端工作階段啟動時，容器裡的工作階段憑證可能還處於讀不到的短暫過渡期。以前偶爾會因此直接啟動失敗；現在流程會處理這段先後差，避免把「憑證尚未可讀」當成最終失敗。原文只說修正啟動時的偶發問題，沒有公布等待多久、重試幾次，也沒有表示無效憑證會被接受。

VSCode 聊天分頁若對應的工作階段從未存檔，本來沒有舊對話可載入，卻會一直卡在「No conversation found」。現在遇到這個條件，分頁會直接建立新對話，讓你可以開始輸入。修正只針對「從未存檔」的工作階段，不是把遺失的歷史內容找回來；畫面也不會再停在一個無法前進的錯誤狀態。

A long, complex Claude session could lose its extended-thinking context when tool definitions were rendered again after an OAuth token refresh.

The roughly hourly prompt-cache miss is fixed. ScheduleWakeup also keeps the same definition on the first --resume turn after an account enters usage overage, avoiding a full cache miss.

After a machine wakes, you need to know where background work really stopped.

A new session no longer opens an older conversation or drops the prompt you typed. Opening a stopped session already resumed in another terminal does not start a second process; its claude agents row says it is open in a terminal.

When claude agents opens, setting the CI environment variable no longer skips the workspace trust prompt. A malformed entry in the PR-status cache also no longer crashes launch.

A background session no longer waits silently when a PermissionRequest or PreToolUse hook prints an invalid answer. Its claude agents row names the hook and schema error. If hook stdout prints a {…} object that is not valid JSON, it is no longer accepted as plain text; Claude Code reports a hook error with the parse message.

If a worktree branch is already merged into the checked-out default branch, such as local main, claude agents and claude rm no longer refuse deletion merely because that merge has not been pushed. Meanwhile, a running background session holds its worktree lock. Cleanup and git worktree remove leave it alone instead of taking away its checkout.

If another Claude Code process holds the token-refresh lock just as the current session token expires, you are no longer sent to the login screen.

The request fails with a retryable error. It is still a failed request, not a promise of automatic success; the temporary lock conflict is simply no longer mistaken for a lost login.

Some machines cannot use the recommended Console sign-in because ANTHROPIC_API_KEY or an API-key helper is set. /login used to stop with an OAuth error before even showing the sign-in URL. It now falls back to API-key sign-in and uses the credential path already available. This is a login-method fallback, separate from retrying token-refresh contention.

/login no longer hangs when connecting to a Claude apps gateway requires the managed-settings security-approval dialog. Gateway model discovery also runs when apiKeyHelper is the only credential source. The environment variable named in the changelog is:

CLAUDE_CODE_ENABLE_GATEWAY_MODEL_DISCOVERY

MCP entries now appear under their real scope. A project .mcp.json entry declaring the claude.ai connector type no longer appears under the trusted “claude.ai” heading. That type declaration does not change its classification.

When an MCP server’s headersHelper supplies the Authorization header and gets a 401, Claude Code now reruns the helper and retries the call as documented instead of entering OAuth discovery.

A session you opened in Claude Desktop or Cowork keeps its transcript as long as the app still holds it; routine cleanup no longer deletes it after 30 days. An organization retention rule, if you have one, still wins. To put a limit on that keep-alive, add one line to ~/.claude/settings.json and change the number to the days you want (30 is the example):

{"desktopSessionCleanupPeriodDays": 30}

After claude logs exits, its terminal should no longer behave as if the log viewer were still open. Claude Code now switches off mouse tracking, bracketed paste, and the alternate screen in the terminal where the command ran. The fix concerns modes enabled by claude logs; it does not claim to replace other terminal preferences.

Several terminal glitches had one theme: text should remain literal and columns should align.

Model names in /model and fast-mode notices render as code, so a suffix such as [1m] stays literal instead of becoming a link. Long repository-permission rules no longer show a garbled character when truncated inside an emoji. Startup warnings also align with the rest of the transcript instead of shifting one column right.

Pressing shift+tab immediately after ctrl+c used to leave the permission-mode indicator hidden behind “Press Ctrl-C again to exit.” The indicator now remains visible, so you can see the selected mode while the exit hint is present. The fix changes this display overlap, not what ctrl+c or shift+tab does.

/ultrareview and locally seeded cloud sessions no longer upload uncommitted edits hidden in swap, temporary, or backup copies of sensitive files. This covers prod.env-style files, *.tfvars, and credential-file copies such as key.pem.tmp and id_rsa.swo; they stay on your machine. The statement is specific to these files, not every uncommitted edit.

After the CLI silently reconnected a Remote Control session, a connected device could remain on stale state: no permission prompt and no latest messages.

That occasional catch-up failure is fixed. The scope is the missing prompt and messages after silent CLI reconnection, not every possible Remote Control connection problem.

A wrapper may inject an option before the claude remote-control subcommand, and users may place a global flag there too. That prefix used to make remote-control reject its own flags, including --spawn and --name. The parser now accepts those flags despite the preceding options.

A cloud session could occasionally fail at startup because its container's session credentials were not readable yet. Startup now handles that transition instead of treating “not readable yet” as a final failure. The changelog gives no wait duration or retry count, and does not say invalid credentials are accepted.

A VS Code chat tab could become stuck on “No conversation found” when its session had never been saved, meaning there was no old conversation to load. It now starts a new conversation so you can type. This does not recover missing history; it handles the specific never-saved state.