Since the 0.8.28 update, custom provider chat no longer works (return 400 Error).

[kit1858644]

Before submitting your bug report

• [X] I believe this is a bug. I'll try to join the Continue Discord for questions
• [X] I'm not able to find an open issue that reports the same bug
• [X] I've seen the troubleshooting guide on the Continue Docs

Relevant environment info

- OS: Windows 10
- Continue: v0.8.29
- IDE: VSCode lastest
OpenAI API

Description

Continue Chat post request is not an OpenAI request format, This caused the request to fail:

My settings work correctly in continue 0.8.27 version.

• Edit: I found that when using "model": "gpt-4", it works normally, but when using "model": "gpt-4o", an error occurs.

Continue Post Format:

{
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "Hello"
        }
      ]
    }
  ],
  "model": "gpt-4o",
  "stream": true
}

OpenAI Post Format:

{
  "messages": [
    {
      "role": "system",
      "content": "You are ChatGPT..."
    },
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "stream": true,
  "model": "gpt-4o"
}

This is my config.json:

{
      "model": "gpt-4o",
      "title": "GPT-4o",
      "apiKey": "sk-ABCEDFG",
      "apiBase": "https://api.xxx.com/v1",
      "provider": "openai"
    }

To reproduce

-

Log output

https://api.XXX.com/v1/chat/completions {"error":{"message":"invalid paramters (request id: xxxxxxxxxxxxx)","type":"invalid_request_error","param":"","code":null}}

[sestinj]

@kit1858644 just solved this here: https://github.com/continuedev/continue/commit/cc900ed9d801118aff50aa536985790eeeeb2455

It'll be in the next pre-release soon