ai agent is not calling tool some time , if connected with memory , need to disconnect and run the chat then only aging it work as normal , i already clearly mentioned use tool always befor send output , but its just take previs chat and give replay to us
Please can you share your workflow in a code block or your system prompt so we can have a look.
PS: You can also clear the memory using the following node while testing to make sure you use a clean memory, but for production use you need to enhance the prompt maybe to be more explicit
The Agent (LLM) ends its actions by simulating a tool call in the following format:
Calling My_Tool with input: {“query”:“my query”,“tool”:“my_tool”,“id”:“call_453138186985815f”}
This is especially common when forcing the Agent to call tools sequentially. It will call the first one correctly, but the second one will fail with the aforementioned error.
I think a similar problem was also observed in the following issue.