Turn off thinking for Gemini models by default

examples/foundational/07n-interruptible-google.py

@@ -61,7 +61,12 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
         credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
     )
 
-    llm = GoogleLLMService(api_key=os.getenv("GOOGLE_API_KEY"))
+    llm = GoogleLLMService(
+        api_key=os.getenv("GOOGLE_API_KEY"),
+        model="gemini-2.5-flash",
+        # turn on thinking if you want it
+        # params=GoogleLLMService.InputParams(extra={"thinking_config": {"thinking_budget": 4096}}),)
+    )
 
     messages = [
         {

examples/foundational/07s-interruptible-google-audio-in.py

@@ -214,7 +214,12 @@ transport_params = {
 async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_sigint: bool):
     logger.info(f"Starting bot")
 
-    llm = GoogleLLMService(api_key=os.getenv("GOOGLE_API_KEY"), model="gemini-2.0-flash-001")
+    llm = GoogleLLMService(
+        api_key=os.getenv("GOOGLE_API_KEY"),
+        model="gemini-2.5-flash",
+        # turn on thinking if you want it
+        # params=GoogleLLMService.InputParams(extra={"thinking_config": {"thinking_budget": 4096}}),
+    )
 
     tts = GoogleTTSService(
         voice_id="en-US-Chirp3-HD-Charon",