feat: final smoke-test fixes + spectacular README + UI bugfixes

chore: fix all ruff lint errors (174 -> 0), clean up unused imports/vars, fix line lengths

Fix cross-encoder loading, add offline mode, improve simple query detection

fix: resolve critical bugs - evaluation import cycle, bias detector, slider weights, and 7 more high-severity issues

Overhaul: Plackett-Luce ranking, PII anonymization, live fairness dashboard + LLM-free fallback agents

feat(extraction): add FieldExtractor pipeline, ProfileStore with lazy loading, and skill matching

feat(perf): switch to Ollama qwen2.5:7b, pre-load ML models at startup

feat(ui): wire search pipeline, add scoring sliders, fix infinite replan loop

feat: Phase 10 API layer — FastAPI with search/profiles/ingest/health endpoints

chore: create directory structure with __init__.py files and placeholder scripts