Why Does Including Custom 'name' Fields in Function-Enabled Completions Cause a 500 Error?

I'm encountering consistent HTTP 500 errors when making a POST request to the V1 completions endpoint with functions enabled. It seems like the inclusion of custom "name" fields in non-function messages might be causing issues. Here’s a summary of the problem and what I’ve tried:

What I try to do

I make a POST call to the V1 completions endpoint with the following POST body:

JSONCopied
{
    "model": "gpt-3.5-turbo-16k-0613",
    "messages": [
        {
            "role": "system",
            "content": "You are an assistant called Maia. You are always open for a pleasant conversation. You love using emojies."
        },
        {
            "role": "user",
            "content": "I could actually use a bit of help understanding this Wikipedia page [LINK REDACTED] specifically I want to know more about public works and such he did. Can you help?",
            "name": "John"
        },
        {
            "role": "assistant",
            "content": "During his reign, Al-Walid I financed impressive public works, including:\n\n🕌 The construction of the Great Mosque of Damascus\n🕌 The construction of the al-Aqsa Mosque in Jerusalem\n🕌 The construction of the Prophet's Mosque in Medina\n\nHe also built way-stations and dug wells along the roads in Syria, installed street lighting in the cities, and invested in land reclamation projects. Additionally, he built numerous palaces, fortresses, and other buildings throughout the Umayyad Empire.",
            "name": "Maia"
        },
        {
            "role": "user",
            "content": "Ah thank you!",
            "name": "John"
        }
    ],
    "functions": [
        {
            "name": "QueryWebPage",
            "description": "Queries the giving web page for the requested information.",
            "parameters": {
                "type": "object",
                "properties": {
                    "url": {
                        "type": "string"
                    },
                    "question": {
                        "type": "string",
                        "description": "A human readable sentence describing what information you would like to retrieve from the web page."
                    }
                },
                "required": [
                    "url",
                    "question"
                ]
            }
        },
        {
            "name": "DoWebSearch",
            "description": "Performs a web search and returns a list of URLs fitting the search query.",
            "parameters": {
                "type": "object",
                "properties": {
                    "query": {
                        "type": "string",
                        "description": "The search query."
                    }
                },
                "required": [
                    "query"
                ]
            }
        }
    ],
    "temperature": 0.5
}

What happens

I receive a 500 internal server error with the message: “The server had an error processing your request. Sorry about that! You can retry your request, or contact us through our help center at help.openai.com if you keep seeing this error.”

What I would expect

The request to succeed and return a valid completion response.

Observations

1. Removing the last message (which includes the custom "name" field) prevents the error.
2. Removing the functions property also prevents the error.

It appears that including custom "name" fields with functions leads to the error. Any suggestions on how to adjust my request to avoid this problem?