fix(gemini-live-vertex): disable NON_BLOCKING tools

GeminiLiveVertexLLMService overrides _supports_non_blocking_tools to
return False — Vertex AI's Gemini Live endpoint doesn't yet accept the
NON_BLOCKING behavior field on function declarations or the scheduling
field on FunctionResponse, and sending either breaks tool calling.

Effect: function declarations sent to Vertex no longer carry
NON_BLOCKING; FunctionResponses no longer carry scheduling: WHEN_IDLE.
Users registering a function with cancel_on_interruption=False against
Vertex get the same one-time logger.error + push_error the base class
surfaces on Gemini 3.x.

src/pipecat/services/google/gemini_live/vertex/llm.py

@@ -238,6 +238,20 @@ class GeminiLiveVertexLLMService(GeminiLiveLLMService):
             "When using Vertex AI, the recommended approach is to use Google Cloud Storage for file handling. The Gemini File API is not directly supported in this context."
         )
 
+    @property
+    def _supports_non_blocking_tools(self) -> bool:
+        """Vertex AI's Gemini Live endpoint does not yet support NON_BLOCKING tool calls.
+
+        Override the base ``GeminiLiveLLMService`` getter to disable the
+        NON_BLOCKING ``behavior`` field on function declarations and the
+        ``scheduling`` field on FunctionResponse for Vertex sessions —
+        sending either appears to break tool calling against Vertex.
+        Users hitting this on a function registered with
+        ``cancel_on_interruption=False`` will see the same one-time
+        warning the base class surfaces for unsupported models.
+        """
+        return False
+
     @staticmethod
     def _get_credentials(
         credentials: str | None, credentials_path: str | None