model routing: cost/latency ranking with ranked fallback list (#849)

This commit is contained in:
Adil Hafeez 2026-03-30 13:46:52 -07:00 committed by GitHub
parent 3a531ce22a
commit e5751d6b13
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
23 changed files with 1524 additions and 317 deletions

View file

@ -150,6 +150,10 @@ fn get_quota(limit: Limit) -> Quota {
TimeUnit::Second => Quota::per_second(tokens),
TimeUnit::Minute => Quota::per_minute(tokens),
TimeUnit::Hour => Quota::per_hour(tokens),
TimeUnit::Day => {
let per_hour = limit.tokens.saturating_div(24).max(1);
Quota::per_hour(NonZero::new(per_hour).expect("per_hour must be positive"))
}
}
}