feat(autocomplete): threshold=0.05 + max 3 suggestions

fix(autocomplete): replace beam search with sampling for diverse GPT-2 predictions

fix(autocomplete): GPT-2 now generates complete words, not BPE subword tokens

fix(autocomplete): true context awareness - GPT-2 now adds own candidates + cache key uses 5 words

feat(NLP-4): AutoComplete integration — hybrid bigram + GPT-2