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>

backend/tests/test_conversation_history.py

@@ -139,6 +139,8 @@ class ConversationRecorderTest(unittest.IsolatedAsyncioTestCase):
                 input_id="input_photo",
                 timestamp="2026-08-05T10:00:00+08:00",
                 mime_type="image/jpeg",
+                content="帮我看看",
+                source="uploaded_asset",
             )
 
         self.assertTrue(session.committed)
@@ -146,7 +148,9 @@ class ConversationRecorderTest(unittest.IsolatedAsyncioTestCase):
         message, artifact = session.added
         self.assertEqual(message.content_type, "image")
         self.assertEqual(message.role, "user")
+        self.assertEqual(message.content, "帮我看看")
         self.assertEqual(message.extra["input_id"], "input_photo")
+        self.assertEqual(message.extra["source"], "uploaded_asset")
         self.assertEqual(artifact.message_id, message.id)
         self.assertEqual(artifact.kind, "image")
         self.assertEqual(artifact.size_bytes, len(b"jpeg-data"))