@skeang
Hello! It sounds like you're encountering an issue with the "Test Endpoint" button not behaving as expected. Typically, the function name should be included in the POST request when testing an endpoint. This could be a bug or a misconfiguration in the testing setup.
Regarding setting up your webhook, it's common to have one endpoint that can handle multiple functions by parsing the incoming data to determine which function to call. However, if you prefer a more straightforward approach or if your use case requires it, you can set up one endpoint per function call.
As for testing how the LLM (Large Language Model) would construct its response given the function call results, you would typically simulate the function call and feed the results to the LLM in a controlled environment. This way, you can see how the LLM processes the input and constructs a response.
If you need further assistance with setting up your webhook or testing the LLM response, please let me know, and I'll be happy to help!