v3.5.0

Rewrite textgen to use responses api and actually work this time (i hope).

If you use llama.cpp like I do, you need to inject 0 into usage.output_tokens_details.reasoning_tokens or else async-openai will complain it isn't to spec (cuz why would i make an issue)

Full Changelog: v3.4.11...v3.5.0

v3.4.11

I've lost the will to update this every goddamn time I update a few dependencies.

Full Changelog: v3.4.10...v3.4.11

v3.4.10

update shit

Full Changelog: v3.4.9...v3.4.10

v3.4.9

update dependencies

Full Changelog: v3.4.8...v3.4.9

v3.4.8

update shit

Full Changelog: v3.4.7...v3.4.8

v3.4.7

update dependencies and rust

Full Changelog: v3.4.6...v3.4.7

v3.4.6

update poise and shit

Full Changelog: v3.4.5...v3.4.6

v3.4.5

update dependencies

Full Changelog: v3.4.4...v3.4.5

v3.4.4

make system stats globally accessable

Full Changelog: v3.4.3...v3.4.4

v3.4.3

finally fix web_scrape

Full Changelog: v3.4.2...v3.4.3