Add bm25 prefilter stage; unify candidates cache; validate reasoning quality

Add CPU threading, T1-only LLM polish, experiment script

Enrich the granite-embedded candidate text with familiar skills + pillar strengths

Add reasoning LLM, perf tweaks, and UI timing

Add JD parsing, central config, checkpoints & LLM

Ship data in image + orjson loader; fix HF file-not-found

update