feat: support uploaded images in debug voice preview

Allow paste/drag temporary image assets so vision turns work without a live camera frame.

Co-authored-by: Cursor <cursoragent@cursor.com>

frontend/src/hooks/use-voice-preview.ts

@@ -61,7 +61,9 @@ export type UserInputPart =
   | { type: "input_text"; text: string }
   | {
       type: "input_image";
-      source: { type: "camera_frame"; frame: "current" };
+      source:
+        | { type: "camera_frame"; frame: "current" }
+        | { type: "uploaded_asset"; asset_token: string };
     };
 export type UserInputResult = {
   inputId: string;
@@ -880,7 +882,12 @@ export function useVoicePreview(
   );
 
   const appendUserImage = useCallback(
-    (inputId: string, imageUrl: string, timestamp: string) => {
+    (
+      inputId: string,
+      imageUrl: string,
+      timestamp: string,
+      content = "",
+    ) => {
       messageSeqRef.current += 1;
       const sequence = messageSeqRef.current;
       setMessages((previous) =>
@@ -889,7 +896,7 @@ export function useVoicePreview(
           {
             id: `user-image-${inputId}`,
             role: "user",
-            content: "",
+            content: content.trim(),
             timestamp,
             sequence,
             attachments: [
@@ -897,7 +904,7 @@ export function useVoicePreview(
                 id: `image-${inputId}`,
                 type: "image",
                 url: imageUrl,
-                alt: "用户拍摄的照片",
+                alt: "用户提交的图片",
               },
             ],
           },