main
Message drafts (#3044)
Add "servers" attribute to openapi spec of demo plug-ins (#3294)
Revert "Cleanup `handle_worker()` in preparation for #2815 (Stop generation early) (#3573)" (#3644)
Custom instructions feature (#3597)
Inference: Associate chats with user IDs (#1826)
Initial inference documentation pass (#3330)
Add rate limits to assistant chat messages (#3514)
Added max size to work queue and an error response if full when enqueuing (#2279)
Add hide all chats endpoint (#3423)