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/pipecat/processors.py

@@ -50,9 +50,14 @@ class UserInput:
     input_id: str
     text: str
     has_camera_frame: bool
+    image_asset_token: str | None
     run_immediately: bool
     interrupt: bool
 
+    @property
+    def has_image(self) -> bool:
+        return self.has_camera_frame or bool(self.image_asset_token)
+
     @property
     def prompt_text(self) -> str:
         if self.text:
@@ -61,10 +66,9 @@ class UserInput:
 
     @property
     def transcript_text(self) -> str:
-        # Images are represented as structured media records. A synthetic
-        # sentence would be shown as chat text and persisted as if the user had
-        # said it, while adding no visual information for the model.
-        return self.text
+        # Image turns are persisted as one structured media message, including
+        # any optional text caption. Do not create a duplicate transcript row.
+        return "" if self.has_image else self.text
 
 
 class UserInputError(ValueError):
@@ -155,6 +159,7 @@ def parse_user_input(message) -> UserInput | None:
 
     text = ""
     has_camera_frame = False
+    image_asset_token: str | None = None
     for part in parts:
         if not isinstance(part, dict):
             raise UserInputError("user-input part 格式不正确", input_id=input_id)
@@ -166,23 +171,30 @@ def parse_user_input(message) -> UserInput | None:
             if not text:
                 raise UserInputError("input_text 不能为空", input_id=input_id)
         elif part_type == "input_image":
-            if has_camera_frame:
+            if has_camera_frame or image_asset_token:
                 raise UserInputError("P0 只支持一张图片", input_id=input_id)
             source = part.get("source")
-            if (
-                not isinstance(source, dict)
-                or source.get("type") != "camera_frame"
-                or source.get("frame") != "current"
-            ):
+            if not isinstance(source, dict):
+                raise UserInputError("input_image source 格式不正确", input_id=input_id)
+            if source.get("type") == "camera_frame" and source.get("frame") == "current":
+                has_camera_frame = True
+            elif source.get("type") == "uploaded_asset":
+                token = str(source.get("asset_token") or "").strip()
+                if not token or len(token) > 4096:
+                    raise UserInputError(
+                        "上传图片缺少有效的 asset_token",
+                        input_id=input_id,
+                    )
+                image_asset_token = token
+            else:
                 raise UserInputError(
-                    "P0 只支持当前摄像头画面",
+                    "仅支持当前摄像头画面或已上传图片",
                     input_id=input_id,
                 )
-            has_camera_frame = True
         else:
             raise UserInputError(f"不支持的输入类型: {part_type}", input_id=input_id)
 
-    if not text and not has_camera_frame:
+    if not text and not (has_camera_frame or image_asset_token):
         raise UserInputError("user-input 没有有效内容", input_id=input_id)
 
     options = message.get("options")
@@ -193,6 +205,7 @@ def parse_user_input(message) -> UserInput | None:
         input_id=input_id,
         text=text,
         has_camera_frame=has_camera_frame,
+        image_asset_token=image_asset_token,
         run_immediately=run_immediately,
         interrupt=interrupt,
     )
@@ -565,7 +578,7 @@ class RealtimeUserInputProcessor(FrameProcessor):
                 "当前工作流节点暂不接收用户输入",
             )
             return
-        if user_input.has_camera_frame:
+        if user_input.has_image:
             await self._emit_error(
                 user_input.input_id,
                 "Realtime 模式暂不支持图片输入",