November 5, 2024

Bit of a small one today, but we wanted to fix the latency issues introduced last week!

Custom prompting

When sending codex data to the AI, the entries are
now sorted alphabetically
(for those that split up their codex entries: this should help quite a bit!)
Added new "names" format to codex functions, which skips all descriptions (useful for dictation prompts), for example :
codex.all("names")
or
codex.getAllByType("character", "names")
Added new "system as user" toggle for models that don't support system messages (for o1 and some infermatic models)
Added an option to disable streaming for models that don't support those kinds of responses (o1 for example)

Other changes

Fixed floating panels (codex, snippet, chat) appearing in front of (alert) modals
Fixed highlighting markers in timeline not showing their actual height
Fixed collapsed sections still showing highlighting markers in timeline
Some other bugfixes and improvements