[grid] from AI vision in chat

[sam (Sam Saffron)]

I started looking at this, the fix in AI is actually quite easy, trouble is we will need a fix in chat as well @zogstrip / @j.jaffeux

Specifically, once we remove [grid] stuff gets weird ™.

For a block like this supplied to chat:

![Create an image in a humorous illustration style, featuring a cartoon monkey with exaggerated features. The monkey is wearing a vibrant-colored Hawaiian shirt and sunglasses. The spendthrift character has a wide grin and is holding a banana as if it's a microphone. The illustration features bright, playful colors similar to those found in children's books. Set against a background depicting a tropical beach with palm trees and a blazing sunset.](upload://6mq3rDixX44cdKzsXb2efl0GfwG.jpeg) ![Generate an image of a photo-realistic humorous monkey dressed in a business suit, seated at an office desk looking serious. The desk is strewn with banana peels, and the monkey is holding a banana as if it were a telephone to its ear. The office environment should depict a sense of chaos, with papers fluttering around, creating an amusing contrast.](upload://yLUEHwfiDZFeNeNgJmyi7YzD88q.jpeg)

Chat renders:

This is a bit of a problem on a few counts.

1. So much text
2. It is only grabbing the title of the first image in the markdown which is confusing
3. When you click the link it does not use lightbox, which is not fun

We can avoid the bugs by prepending text and getting something like:

But this does feel quite hacky.

…

Fixing by removing the grid will leave stuff worse off

---

Also worse considering, we need to make sure there are proper upload refs for this case so we are not stuck with orphan images.