4991164591bdd9de2bfe072a7bd4e248a6fa1aec
Replace static OFFENSIVE_USERNAME_KEYWORDS substring matching with a lightweight LLM call that evaluates whether a global username violates server rules (gambling, scam, NSFW, SARA, etc). Fail-open design: if the LLM call fails/times out, the nickname reset still completes.
Description
Bete Discord moderation watcher
27 MiB
Languages
TypeScript
96.5%
CSS
1.2%
Nix
0.8%
Shell
0.7%
PLpgSQL
0.5%
Other
0.3%