When the LLM Refuses: A Fallback Chain That Salvages Most Refusals

Every production LLM app eats false-positive refusals. A user asks something perfectly fine, the safety filter trips, the model emits two sentences of "I can't help with that," and your UI shows a wall. Do that a few times and the user leaves.

We've measured this on — Telegram-native AI companion bot where a single refusal mid-conversation kills the experience. Canonical version: — the four adjustable harm categories, threshold semantics, what BLOCK_NONE does and doesn't.