In chat mode, add a "generate more" button when reaching the max token limit

[TheLapinMalin]

Is your feature request related to a problem? Please describe.
In chat mode, the model sometimes outputs the max number of tokens (512/512) but hasn't finished answering yet.

Setting num predict chat to -1 doesn't work with the model I'm using, and increasing the limit to 1024-2048 tokens just pushes the issue little bit further.

Describe the solution you'd like
It would be there a way to complete/extend the answer with additional tokens. (another batch of 512 for instance)

Describe alternatives you've considered
n/a

Additional context
n/a

[nviraj]

First and foremost, thanks for the excellent extension! I started using it today, and I already love it.

To add to this request, I noticed that when I request to continue for long code, it creates a new code block with messed-up indentation.

For this feature, I propose taking inspiration from textgen webui's instruct mode. In that mode, pressing the 'continue' button appends to the existing code block or message, rather than starting a new one.