profanity-checker

Cloudflare Worker that asks Jev `Noul` for literal profanity in text or usernames and a second `Noul` for phonetic or look-alike disguise (`a55h0le`, `mike_hunt`); the threshold, `max()` policy, JSON response, and OpenAPI schema live in Worker code and the endpoint is callable from other Workers via service bindings.

SCORE 呼び出しの形

この質問型の一般的な骨格であって、このプロジェクトの実際のコードではない。

from typesafe import TypeSafe

ts = TypeSafe()
result = ts.evaluate(
    state=candidate,
    questions={
        "relevance": {
            "type": "score",
            "levels": ["low", "medium", "high"],
            "instructions": "How relevant is this to the query?",
        }
    },
)
if result["relevance"] >= 0.7:
    keep(candidate)