Move system_instruction into LLMSettings

Add `system_instruction` field to `LLMSettings` so it is runtime-updatable via settings.
For Google (GoogleLLMService, GoogleVertexLLMService), deprecate the init-time arg since it was already shipped. For Anthropic, AWS Bedrock, and OpenAI, remove the init-time arg entirely since it was never shipped.

Add system instruction prepend logic to `build_chat_completion_params` overrides in Cerebras, SambaNova, Fireworks, Mistral, and Perplexity, which build params from scratch rather than calling `super()`.

Still need to handle realtime services (OpenAI Realtime, Grok Realtime, Gemini Live).

examples/foundational/14l-function-calling-deepseek.py

@@ -73,8 +73,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         api_key=os.getenv("DEEPSEEK_API_KEY"),
         settings=DeepSeekLLMSettings(
             model="deepseek-chat",
-        ),
-        system_instruction="""You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way.
+            system_instruction="""You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way.
 
 You have one functions available:
 
@@ -85,6 +84,7 @@ Infer whether to use Fahrenheit or Celsius automatically based on the location,
 Start by asking me for my location. Then, use 'get_weather_current' to give me a forecast.
 
     Respond to what the user said in a creative and helpful way.""",
+        ),
     )
     # You can also register a function_name of None to get all functions
     # sent to the same callback with an additional function_name parameter.