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/33-gemini-rag.py

@@ -199,8 +199,8 @@ Your response will be turned into speech so use only simple words and punctuatio
     llm = GoogleLLMService(
         settings=GoogleLLMSettings(
             model=VOICE_MODEL,
+            system_instruction=system_prompt,
         ),
-        system_instruction=system_prompt,
         api_key=os.getenv("GOOGLE_API_KEY"),
     )
     llm.register_function("query_knowledge_base", query_knowledge_base)