Antigravity 1.1.16

若你用的終端機不支援 OSC 8 超連結，例如 Terminal.app，畫面不會再把控制碼原樣印成文字。這類終端機原本無法解讀控制碼，會把它照字面顯示；現在程式先偵測支援情況，避免送出這些控制碼。偵測也延伸到指令輸出與提醒訊息，兩處以前仍不管終端機是否支援就送出超連結。

現在三處都會先辨識是否能處理 OSC 8。

終端機不支援 Kitty 鍵盤協定（讓終端機辨識鍵盤輸入方式）時，提示列不會再每隔幾秒多出一個 =。原本 renderer（負責畫面顯示的程式部分）會定期重新啟用該協定，但終端機沒有把控制訊號當作協定內容解讀，反而把它印成文字。

現在不支援時，重新啟用協定不會留下等號。

你打開名稱含空格的產物時，清單列、內嵌預覽與詳細標題現在會寫同一個檔名。以前它可能顯示 quarterly%20plan.md，把空格寫成百分比跳脫字元，讀起來像另一個檔案。

名稱中的空格會正常顯示。因此從清單點進預覽或詳細頁，不必猜眼前的名稱是不是同一份產物。

在提示列輸入較長文字、內容換到下一行後，游標現在會留在正確位置。先前編輯器算錯換行後的座標，游標看起來可能指著一處，實際插入文字卻落在另一處。

這在反覆修改長句時尤其容易察覺，也不再誤導你。你在長提示中移動、補字或刪字時，眼睛看到的位置便能對上正在編輯的位置。

MCP 伺服器回傳 PDF、音訊或其他非圖片二進位內容時，read_resource 不會再悄悄把它們丟掉。現在每個 blob 都會先卸到磁碟，只有小型文字與圖片資源會直接嵌進回應。

因此大型 PDF、音訊與其他二進位資源能被使用，而非在讀取途中消失。

使用 Workforce Identity Federation 登入時，不會再因為更新 token（授權令牌，證明登入仍有效的憑據）走錯端點而被登出。問題原本出在更新程序跑到標準登入端點，而不是聯邦登入端點，導致登入狀態大約每小時反覆失效。

你用這種聯邦身分登入後，更新授權令牌會留在正確的登入流程中。

查看 /skills 時，隨 CLI 一起提供的 skills 現在會正確被認成內建項目。以前它們被誤報為非內建，導致 --output-format json 的 builtin 旗標不正確，/skills 面板分組也跟著放錯。

若你用 JSON 輸出供其他工具讀取，或直接在面板瀏覽，兩種呈現會對上。

對話進行到一半想岔問一件小事時，/btw 不再因為你正在使用自訂或 SDK 定義的 agent（代理，代替你執行特定任務的 AI 設定）而報 planner 設定錯誤。側問可在任何正在執行的 agent 下運作。若側問本身失敗，畫面也不會一律猜成 model returned an empty response；有自己的錯誤時，會顯示那個錯誤。

背景任務做完後，狀態列、active-items 清單與 /tasks 面板不會再繼續把它當成進行中。過去任務明明結束，三個位置的資訊卻沒有同步移除，容易讓人以為還要等待。

你查看狀態列、active-items 或 /tasks 時，看到的會是仍在背景執行的任務。

如果 settings.json 因格式錯誤而無法解析，CLI 現在拒絕儲存，卻不會把它覆蓋成預設設定。以前只要之後有任何內容被儲存，所有原有設定都可能被默默還原；現在拒絕儲存時，檔案會維持逐位元組相同，狀態列也會點名是哪個檔案。

原有內容不會被抹掉。

你把子代理的 model 留成 inherit 時，即使父代理本身沒有模型，子代理現在仍能開始工作。舊行為會在啟動時失敗，因為它沒有可繼承的模型。現在會改用預設的快速層級。

因此 inherit 的意思仍優先沿用父代理；父代理沒有模型時，才落到預設快速層級。

If your terminal lacks OSC 8 hyperlinks, such as Terminal.app, control sequences no longer print as literal text. Such terminals originally could not interpret control sequences and displayed them literally; the program now checks support first to avoid sending them. Detection now also covers command output and alert bodies, which had still emitted hyperlinks regardless of support.

All three places now check whether OSC 8 can be handled first.

On a terminal without the Kitty keyboard protocol—the way a terminal interprets keyboard input—the prompt no longer gains a = every couple of seconds. The renderer, the part that draws the display, periodically re-armed the protocol, but the terminal printed that control signal as text instead of interpreting it.

Re-arming no longer leaves equals signs on unsupported terminals.

When an artifact name contains a space, its list row, inline preview, and detail header now spell it the same way. It could previously appear as quarterly%20plan.md, replacing the space with a percent-escape and making it look like another file.

Moving from list to preview or detail no longer makes you wonder whether it is the same artifact.

After long text wraps in the prompt editor, the cursor now stays in the right place. The editor had miscalculated positions after a wrap, so the cursor could point at one spot while inserted text landed elsewhere.

When you move, add, or delete text in a long prompt, the visible position matches the edit position.

When an MCP server returns a PDF, audio file, or other non-image binary content, read_resource no longer silently drops it. Every blob is now offloaded to disk, while only small text and image resources are inlined in the response.

Large PDFs, audio, and other binary resources remain usable instead of disappearing during reading.

With Workforce Identity Federation sign-in, refreshing a token—the credential that keeps a login valid—no longer sends you out through the wrong endpoint. The refresh had gone to the standard sign-in endpoint instead of the federated one, repeatedly invalidating the session roughly every hour.

Token refresh remains in the correct federated sign-in flow.

In /skills, skills shipped with the CLI are now correctly identified as built in. They had been reported as not built in, making the builtin flag in --output-format json wrong and placing them in the wrong /skills panel group.

JSON output for other tools and the panel view now agree.

When a small side question occurs to you mid-conversation, /btw no longer fails with a planner configuration error because you are using a custom or SDK-defined agent—an AI setup that performs a particular task for you. Side questions work with whichever agent is running. If one fails, the card no longer blindly says model returned an empty response; when there is its own error, that error is shown.

After a background task finishes, the status line, active-items list, and /tasks panel no longer keep calling it active. A task could already be done while all three views failed to remove it, making you think you still had to wait.

These views show tasks that are still running in the background.

If settings.json cannot be parsed because its format is broken, the CLI now refuses to save without overwriting it with default settings. Previously, saving anything later could silently revert every existing setting. On a refused save, the file remains byte-for-byte identical and the status line names it.

When a subagent leaves model as inherit, it now starts even if its parent has no model of its own. The old behavior failed because there was nothing to inherit. It now falls back to the default fast tier.

inherit still prefers the parent model, falling back only when that model is absent.