feat: add configurable client tools and photo input

backend/tests/test_pipeline_knowledge.py

@@ -92,6 +92,44 @@ class UserTurnRoutingProcessorTest(unittest.IsolatedAsyncioTestCase):
         self.assertEqual(brain.turns, ["我叫李白"])
         self.assertEqual(forwarded, [(frame, FrameDirection.DOWNSTREAM)])
 
+    async def test_routes_multimodal_user_message_by_its_text_part(self):
+        class FakeBrain:
+            def __init__(self):
+                self.turns = []
+
+            async def on_user_turn_end(self, content):
+                self.turns.append(content)
+                return False
+
+        brain = FakeBrain()
+        processor = UserTurnRoutingProcessor(brain)
+        processor.push_frame = lambda *_args, **_kwargs: _async_none()
+        context = LLMContext(
+            messages=[
+                {
+                    "role": "user",
+                    "content": [
+                        {"type": "text", "text": "看看这张照片"},
+                        {
+                            "type": "image_url",
+                            "image_url": {"url": "data:image/jpeg;base64,AA=="},
+                        },
+                    ],
+                }
+            ]
+        )
+
+        await processor.process_frame(
+            LLMContextFrame(context),
+            FrameDirection.DOWNSTREAM,
+        )
+
+        self.assertEqual(brain.turns, ["看看这张照片"])
+
+
+async def _async_none():
+    return None
+
 
 if __name__ == "__main__":
     unittest.main()