examples(foundational): use system_instruction in all examples

examples/foundational/12b-describe-image-aws.py

@@ -63,16 +63,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         # Here we can't because AWS Bedrock doesn't support it for Claude 3.7,
         # which we need for image input.
         params=AWSBedrockLLMService.InputParams(temperature=0.8),
+        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way. You are also able to describe images.",
     )
 
-    messages = [
-        {
-            "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way. You are also able to describe images.",
-        },
-    ]
-
-    context = LLMContext(messages)
+    context = LLMContext()
     user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
         user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
@@ -121,7 +115,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             size=image.size,
             text=question,
         )
-        messages.append(message)
+        context.add_message(message)
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")