Hoernchen

I have been watching and "secretly" using your branch since tuesday, and can confirm that the current repo appears to have fixed the issue and calls just keep working, thanks...

Support would be really nice to have because now there is the offical llama 3.2 in 1b and 3b which should be suitable for 8/70b 3.1, at least according to...

I can't even get it to work reliably with the current firefox... but: I can get it to work with curl-impersonate 100% of the time. Works after patching mainline, too....

Some users have so many posts that the server returns 429 and it breaks trying to generate the posts, and then it fails if you try to pull the db...

The way downloads break is by stalling with no traffic for some time, and then the connection breaks/times out, so it's different. The code does notice that: `DEBUG | party.posts:download:199...

Still facing the same issue as of 1.100.2, it breaks the vcpkg getting started docs provided by Microsoft when using vscode.. incredibly frustrating experience so far.