Add voice_message_prompt tool to API and UI components. Update DuplexPipeline, Assistants, and DebugDrawer to support new tool functionality, including parameter validation and speech synthesis integration. Ensure existing tools are preserved during seeding process in the database.

engine/core/duplex_pipeline.py

@@ -146,12 +146,24 @@ class DuplexPipeline:
                 "required": [],
             },
         },
+        "voice_message_prompt": {
+            "name": "voice_message_prompt",
+            "description": "Speak a message prompt on client side",
+            "parameters": {
+                "type": "object",
+                "properties": {
+                    "msg": {"type": "string", "description": "Message text to speak"},
+                },
+                "required": ["msg"],
+            },
+        },
     }
     _DEFAULT_CLIENT_EXECUTORS = frozenset({
         "turn_on_camera",
         "turn_off_camera",
         "increase_volume",
         "decrease_volume",
+        "voice_message_prompt",
     })
 
     def __init__(