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/54c-context-summarization-dedicated-llm.py

@@ -40,7 +40,7 @@ from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSetting
 from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.google.llm import GoogleLLMService, GoogleLLMSettings
 from pipecat.services.llm_service import FunctionCallParams
-from pipecat.services.openai.llm import OpenAILLMService
+from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -108,7 +108,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
                     """
 
     # Primary LLM for conversation (could be any provider)
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), system_instruction=system_prompt)
+    llm = OpenAILLMService(
+        api_key=os.getenv("OPENAI_API_KEY"),
+        settings=OpenAILLMSettings(
+            system_instruction=system_prompt,
+        ),
+    )
 
     # Dedicated cheap/fast LLM for summarization only
     summarization_llm = GoogleLLMService(