Antigravity 1.2.10

當你交辦複雜任務給助理時，既不想被整頁的工具呼叫與思考細節洗版，又希望能看清執行了哪些指令與最終產出。在 /config 設定選單中，現在新增了介於 high 與 low 之間的 medium 詳細程度（Verbosity，控制終端機輸出多寡的設定）選項。切換到這個模式後，助理會把一連串相關的工具呼叫與思考過程，整合成像是 Explored N files 這樣的簡短摘要。所有實際跑過的指令與產生的文字回覆，依然會完整顯示在畫面上。Verbosity 設定本身以及底下的每個選項，現在都附上了說明文字，清楚標示各選項會顯示與隱藏哪些內容。

在終端機裡開啟圖表或數學公式時，畫面載入與按鍵操作現在更俐落。在支援 Kitty 圖片協定的終端機中，成品檢視器（artifact viewer，瀏覽產出圖表與文件的介面）會在背景預先渲染產物，打開瞬間就能看見 Mermaid 圖表與 LaTeX 算式。圖片改以較小尺寸一次上傳，使用 Ctrl+= 與 Ctrl+- 縮放不再閃爍。檢視器頁尾將置頂與置底提示整併為 g/G top/bottom，m 鍵會清楚標示切換模式（包含 diagram、LaTeX、ASCII 或 raw），並修復箭頭符號過早折行的問題。在 tmux 或 GNU screen 內若圖片無法傳入，系統會自動備援降級為 ASCII 純文字圖表避免留白，有設定穿透者仍可用 CLI_GRAPHICS=kitty 強制開啟圖片模式。

讓助理在終端機裡自動執行各項指令時，安全防護與按鍵操作現在更符合直覺。終端機沙盒（sandbox，在隔離環境中執行指令以確保安全的機制）現在經過改善，助理要求跳出沙盒確認的頻率明顯降低。助理現在清楚知道沙盒內的指令可以直接讀寫自己的 artifact 與 scratch 資料夾，而且就算前面某個指令曾需要跳出沙盒，接下來的指令依然會優先在沙盒內嘗試。執行結束且回傳非零退出碼的指令，其步驟標題已從原先的 Errored 正式改為 Failed。當終端機跳出建議下拉選單時，按下 Esc 鍵現在會先關閉選單，按第二下 Esc 才會中斷助理執行，避免選字時不小心誤按中斷。

當你在專案中自訂技能、規則或外掛目錄時，現在設定檔的載入行為變得更精確可預測。在 skills.json、rules.json、agents.json 與 plugins.json 這類自訂設定檔（customization，用於擴充助理能力與行為的設定）中，填入目錄路徑時現在只會載入直接位於該目錄下的第一層項目，行為與預設的 .agents/skills/ 資料夾一致，不再自動遞迴載入所有子目錄中的內容。如果你想要引入深層子目錄裡的特定巢狀項目，必須在設定項目中透過 include_only 明確列出路徑，例如：

{"path": "shared_skills", "include_only": ["category/my-skill"]}

When delegating complex tasks to an agent, you might want to avoid being flooded with pages of tool calls and thought details while still clearly tracking executed commands and final responses. The /config settings menu now introduces a medium verbosity option between high and low. In this mode, the agent groups a series of related tool calls and thought processes into concise summaries like Explored N files. All executed commands and resulting text responses remain fully visible on the screen. The Verbosity setting and each individual option beneath it now include descriptive text clearly outlining what is shown or hidden.

Viewing diagrams or math formulas in the terminal is now smoother across loading and key interactions. On terminals supporting the Kitty graphics protocol, the artifact viewer pre-renders artifacts in the background so Mermaid diagrams and LaTeX formulas appear instantly upon opening. Images are uploaded once at a smaller size, eliminating flickering when zooming with Ctrl+= and Ctrl+-. The viewer footer combines the separate top and bottom hints into g/G top/bottom, labels the m key with the active switch target (including diagram, LaTeX, ASCII, or raw), and fixes hints containing arrow symbols wrapping too early. Inside tmux or GNU screen where images cannot reach the terminal, the system automatically falls back to ASCII text diagrams to prevent blank gaps, while setups with passthrough can still force image mode using CLI_GRAPHICS=kitty.

Running commands automatically with an agent in the terminal is now safer and more intuitive. With improvements to the terminal sandbox, the agent requests to bypass the sandbox significantly less often. The agent now recognizes that sandboxed commands can directly read and write its own artifact and scratch directories, and it continues to prioritize the sandbox for subsequent commands even after an earlier command required a bypass. For commands that finish execution with a non-zero exit code, the step title is formally updated from Errored to Failed. When the suggestions dropdown is open in the terminal, pressing Esc now closes the dropdown first, requiring a second Esc press to interrupt the agent and preventing accidental cancellation during autocomplete.

Loading behavior for customization files is now more precise and predictable when defining skills, rules, or plugins directories in a project. In customization files such as skills.json, rules.json, agents.json, and plugins.json, directory entries now load only first-level items located directly inside that directory—matching the behavior of the default .agents/skills/ directory—rather than recursively scanning every subdirectory. To include a specific nested item within a deeper subdirectory, you must explicitly specify its path via include_only, for example:

{"path": "shared_skills", "include_only": ["category/my-skill"]}