Add raw repeat spam check with threshold 6

Batch EN detox inference and safer gibberish early-exit

Refine blacklist matching and strengthen spam heuristics

Add early-exit and Detoxify call counters to moderation logs

Add int8 quantization and batch moderation endpoint

Optimize moderation fast paths for blacklist and Detoxify

Fix verdict logic to include insult hits

Deploy Sentinel API to HF Space