Merge pull request #3006 from pipecat-ai/aleix/vision-image-backwards-compatibility

restore vision/image backwards compatibility

CHANGELOG.md

@@ -108,6 +108,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Fixed
 
+- Restore backwards compatibility for vision/image features (broken in 0.0.92)
+  when using non-universal context and assistant aggregators.
+
 - Fixed `DeepgramSTTService._disconnect()` to properly await `is_connected()`
   method call, which is an async coroutine in the Deepgram SDK.
 

src/pipecat/frames/frames.py

@@ -1215,12 +1215,32 @@ class UserImageRequestFrame(SystemFrame):
         text: An optional text associated to the image request.
         append_to_context: Whether the requested image should be appended to the LLM context.
         video_source: Specific video source to capture from.
+        context: [DEPRECATED] Optional context for the image request.
+        function_name: [DEPRECATED] Name of function that generated this request (if any).
+        tool_call_id: [DEPRECATED] Tool call ID if generated by function call.
     """
 
     user_id: str
     text: Optional[str] = None
     append_to_context: Optional[bool] = None
     video_source: Optional[str] = None
+    context: Optional[Any] = None
+    function_name: Optional[str] = None
+    tool_call_id: Optional[str] = None
+
+    def __post_init__(self):
+        super().__post_init__()
+
+        if self.context or self.function_name or self.tool_call_id:
+            import warnings
+
+            with warnings.catch_warnings():
+                warnings.simplefilter("always")
+                warnings.warn(
+                    "`UserImageRequestFrame` fields `context`, `function_name` and `tool_call_id` are deprecated.",
+                    DeprecationWarning,
+                    stacklevel=2,
+                )
 
     def __str__(self):
         return f"{self.name}(user: {self.user_id}, text: {self.text}, append_to_context: {self.append_to_context}, {self.video_source})"
@@ -1299,11 +1319,27 @@ class UserImageRawFrame(InputImageRawFrame):
         user_id: Identifier of the user who provided this image.
         text: An optional text associated to this image.
         append_to_context: Whether the requested image should be appended to the LLM context.
+        request: [DEPRECATED] The original image request frame if this is a response.
     """
 
     user_id: str = ""
     text: Optional[str] = None
     append_to_context: Optional[bool] = None
+    request: Optional[UserImageRequestFrame] = None
+
+    def __post_init__(self):
+        super().__post_init__()
+
+        if self.request:
+            import warnings
+
+            with warnings.catch_warnings():
+                warnings.simplefilter("always")
+                warnings.warn(
+                    "`UserImageRawFrame` field `request` is deprecated.",
+                    DeprecationWarning,
+                    stacklevel=2,
+                )
 
     def __str__(self):
         pts = format_pts(self.pts)

src/pipecat/services/llm_service.py

@@ -509,7 +509,14 @@ class LLMService(AIService):
                 DeprecationWarning,
             )
         await self.push_frame(
-            UserImageRequestFrame(user_id=user_id, text=text_content),
+            UserImageRequestFrame(
+                user_id=user_id,
+                text=text_content,
+                # Deprecated fields below.
+                function_name=function_name,
+                tool_call_id=tool_call_id,
+                context=text_content,
+            ),
             FrameDirection.UPSTREAM,
         )
 

src/pipecat/transports/daily/transport.py

@@ -1844,6 +1844,8 @@ class DailyInputTransport(BaseInputTransport):
                 format=video_frame.color_format,
                 text=request_frame.text if request_frame else None,
                 append_to_context=request_frame.append_to_context if request_frame else None,
+                # Deprecated fields below.
+                request=request_frame,
             )
             frame.transport_source = video_source
             await self.push_video_frame(frame)

src/pipecat/transports/smallwebrtc/transport.py

@@ -672,6 +672,8 @@ class SmallWebRTCInputTransport(BaseInputTransport):
                                 format=video_frame.format,
                                 text=request_text,
                                 append_to_context=add_to_context,
+                                # Deprecated fields below.
+                                request=request_frame,
                             )
                             image_frame.transport_source = video_source
                             # Push the frame to the pipeline