Fix the aggregation of tokens in metrics taking into account function calls #1800
Description
This was done for Amazon Bedrock Converse but needs to be done for the other all the other models.
- AnthropicChatModel : Fix Anthropic chat model functioncalling token usage #1918
- AzureOpenAiChatModel : Fix Azure OpenAI chat model function calling token usage #1916
- BedrockProxyChatModel : Using BedrockProxyChatModel with tools, chatResponse.metadata.usage is returning ONLY the last model invocation usage #1743
- OpenAiChatModel : Fix OpenAI ChatResponse usage calculation when toolcalling is used #1872
- MiniMaxChatModel : TBD: MiniMaxChatModel toolcalling cumulative token usage #1980
- MistralAiChatModel : Fix Mistral AI Chat model function call usage calculation #1905
- MoonshotChatModel : Fix Moonshot Chat model toolcalling token usage #1927
- OllamaChatModel : feat(ollama): Add streaming support for function calls and improve Ollama #1848
- VertexAiGeminiChatModel: TBD Google Vertex AI toolcalling token usage #1963 & Vertex AI toolcalling cumulative token usage #1992
- ZhiPuAiChatModel TBD: ZhiPuAiChatModel toolcalling cumulative token usage #1979