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_input_assets.py

@@ -0,0 +1,58 @@
+from __future__ import annotations
+
+import unittest
+from io import BytesIO
+from unittest.mock import patch
+
+from PIL import Image
+
+from services.input_assets import consume_input_image, store_input_image
+
+
+def png_bytes(size: tuple[int, int] = (32, 24)) -> bytes:
+    output = BytesIO()
+    Image.new("RGBA", size, (20, 80, 160, 180)).save(output, format="PNG")
+    return output.getvalue()
+
+
+class InputAssetTests(unittest.TestCase):
+    def test_store_normalizes_and_consume_removes_temporary_object(self):
+        with (
+            patch("services.input_assets.put_object") as put_object,
+            patch("services.input_assets.get_object") as get_object,
+            patch("services.input_assets.delete_object") as delete_object,
+        ):
+            stored = store_input_image(png_bytes())
+
+            key, normalized, mime_type = put_object.call_args.args
+            self.assertTrue(key.startswith("conversation-inputs/"))
+            self.assertEqual(mime_type, "image/jpeg")
+            self.assertTrue(normalized.startswith(b"\xff\xd8"))
+            self.assertEqual((stored.width, stored.height), (32, 24))
+            self.assertEqual(stored.size_bytes, len(normalized))
+
+            get_object.return_value = normalized
+            consumed = consume_input_image(stored.token)
+
+        self.assertEqual(consumed, normalized)
+        get_object.assert_called_once_with(key)
+        delete_object.assert_called_once_with(key)
+
+    def test_tampered_token_is_rejected_before_storage_read(self):
+        with patch("services.input_assets.put_object"):
+            stored = store_input_image(png_bytes())
+        tampered = f"{stored.token}x"
+
+        with patch("services.input_assets.get_object") as get_object:
+            with self.assertRaisesRegex(ValueError, "签名无效"):
+                consume_input_image(tampered)
+
+        get_object.assert_not_called()
+
+    def test_non_image_is_rejected(self):
+        with self.assertRaisesRegex(ValueError, "可识别的图片"):
+            store_input_image(b"not an image")
+
+
+if __name__ == "__main__":
+    unittest.main()