Improve before method in MessageChatMemoryAdvisor

Below is the implementation code of the method before.

	public ChatClientRequest before(ChatClientRequest chatClientRequest, AdvisorChain advisorChain) {
		String conversationId = getConversationId(chatClientRequest.context(), this.defaultConversationId);

		// 1. Retrieve the chat memory for the current conversation.
		List<Message> memoryMessages = this.chatMemory.get(conversationId);

		// 2. Advise the request messages list.
		List<Message> processedMessages = new ArrayList<>(memoryMessages);
		processedMessages.addAll(chatClientRequest.prompt().getInstructions());

		// 3. Create a new request with the advised messages.
		ChatClientRequest processedChatClientRequest = chatClientRequest.mutate()
			.prompt(chatClientRequest.prompt().mutate().messages(processedMessages).build())
			.build();

		// 4. Add the new user message to the conversation memory.
		UserMessage userMessage = processedChatClientRequest.prompt().getUserMessage();
		this.chatMemory.add(conversationId, userMessage);

		return processedChatClientRequest;
	}

In this method, it will invoke chatMemoryRepository.findByConversationId(conversationId) twice, there are
List<Message> memoryMessages = this.chatMemory.get(conversationId);
this.chatMemory.add(conversationId, userMessage);

Maybe there are some ways to improve it, like add a method in ChatMemory defined like
add(String conversationId, Message message, List<Message> memoryMessages )
So we can use invoke it with userMessage, memoryMessages args.

Start with MessageChatMemoryAdvisor.before and the ChatMemory calls shown in the issue, then trace how chatMemoryRepository.findByConversationId is reached by get and add. Define completion as avoiding the duplicate lookup while preserving the processed request and conversation-memory behavior; inspect existing ChatMemory tests before changing the API.