Spring-ai Fix the aggregation of tokens in metrics taking into account function calls

This was done for Amazon Bedrock Converse but needs to be done for the other all the other models. - [x] AnthropicChatModel : https://github.com/spring-projects/spring-ai/pull/1918 - [x] AzureOpenAiChatModel : https://github.com/spring-projects/spring-ai/pull/1916 - [x] BedrockProxyChatModel : https://github.com/spring-projects/spring-ai/issues/1743 - [x] OpenAiChatModel : https://github.com/spring-projects/spring-ai/pull/1872 - [x] MiniMaxChatModel : TBD: https://github.com/spring-projects/spring-ai/issues/1980 - [x] MistralAiChatModel : https://github.com/spring-projects/spring-ai/pull/1905 - [x] MoonshotChatModel : https://github.com/spring-projects/spring-ai/pull/1927 - [x] OllamaChatModel : https://github.com/spring-projects/spring-ai/pull/1848 - [x] VertexAiGeminiChatModel: TBD https://github.com/spring-projects/spring-ai/pull/1963 & https://github.com/spring-projects/spring-ai/issues/1992 - [x] ZhiPuAiChatModel TBD: https://github.com/spring-projects/spring-ai/issues/1979

Comment From: ilayaperumalg

Marking this as complete and moving the TBD PR/issues into the upcoming release.