Carl-Robert Linnupuu

Noice! 👍 It happens because the tests on the Github runner are executed in headless mode. You can replicate this by running `export JAVA_TOOL_OPTIONS='-Djava.awt.headless=true'` before executing the tests. Not sure...

I haven't had a chance to review this PR yet, but I'll try to do it sometime early next week. Also, I'll probably do the next release without these refactorings...

The response seems a bit off. Also, the success callback isn't being triggered once the server is up and running, so it looks like it's booting up forever.

Was able to fix the response by modifying the prompt and adding a stop token.

> Thank you for testing and fixing! Stream was not the problem, `begin_of_text` isn't needed, but `assistant`, `stopTokens` and server hack (?). I followed the template format from their official...

Hey, I'm putting this refactoring on pause for a bit until I have run a compatibility comparison between different IDE builds. Most likely, this won't cause any issues, but I...

Hi Jacob, Thank you for considering CodeGPT! This is something I have been thinking about as well, especially since I use CodeGPT's chat interface for non-technical stuff quite a bit....

Hey! I'm closing this PR since I've implemented this in another branch. I've also added the Rubber Duck persona to the list. If you have any other cool ideas about...

Since the change was recent, we need to update the llama.cpp submodule as well

I'll try running the model locally soon and see if any other changes are necessary