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/services/vision.py

@@ -49,6 +49,21 @@ def image_data_uri(frame: UserImageRawFrame) -> str:
     return f"data:image/jpeg;base64,{encoded}"
 
 
+def image_frame_from_jpeg(data: bytes) -> UserImageRawFrame:
+    """Decode one normalized uploaded JPEG into Pipecat's raw image frame."""
+
+    try:
+        image = Image.open(BytesIO(data)).convert("RGB")
+        image.load()
+    except (OSError, ValueError) as exc:
+        raise ValueError("上传图片无法解码") from exc
+    return UserImageRawFrame(
+        image=image.tobytes(),
+        size=image.size,
+        format="RGB",
+    )
+
+
 async def analyze_image_with_vision_model(
     cfg: AssistantConfig,
     frame: UserImageRawFrame,