openai o1, o3-mini chat response does not format code blocks

Before submitting your bug report

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

Relevant environment info

- OS:Windows 10
- Continue version: 0.9.268 pre release
- IDE version: VSCode 1.97.1
- Model: 03-mini
- config.json:
  
...
{
      "title": "GPTo3 mini",
      "provider": "openai",
      "model": "o3-mini",
      
      "contextLength": 10090,
      "apiKey": "itsmineyoucanthaveit!",
      "completionOptions": {
        "maxTokens": 6096
      }
    }

Description

To reproduce

See screenshot. o1 acts the same as well. Raw response:

Here's a simple JavaScript function that outputs (returns) a random number between 0 (inclusive) and 1 (exclusive):

----------------------------------------------------
function getRandomNumber() {
  return Math.random();
}

console.log(getRandomNumber());
----------------------------------------------------

Explanation:
• Math.random() is a built-in JavaScript function that returns a random floating-point number in the range 0 (inclusive) to 1 (exclusive).
• getRandomNumber() simply wraps Math.random() and returns its value.
• The console.log call prints the random number to the console.

If you need a random number within a specific range, say between a minimum value (min) and a maximum value (max), you can modify the function like this:

----------------------------------------------------
function getRandomInRange(min, max) {
  return Math.random() * (max - min) + min;
}

console.log(getRandomInRange(1, 10));  // Outputs a random number between 1 and 10
----------------------------------------------------

Feel free to adjust the code according to your needs!

Log output