Fix: role-type skill detection, OpenRouter base_url support, Dockerfile for HF Spaces with 500-profile sample indexes

feat: align candidate relevance ranking & implement robust Turbo Mode fallback

Fix remote candidate search returning 0 results by mapping preferred_work_mode

refactor: extract shared query parser module, clean up imports

feat: full 100k index pipeline - switch from samples to full offset index

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

perf(core): reuse open file handle in ProfileStore for fast candidate fetches

fix(core): add default values to MatchScores and slider_weights to SearchRequest

fix(core): wrap OpenAI api_key in SecretStr

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

Refine skill matching and add original query pipeline

Multi-dimensional scoring upgrade: behavioral signals, career trajectory, skill proficiency, honeypot detection

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

fix: resolve 20 high/medium bugs across search, agents, core, and extraction modules

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

fix(search): cross-encoder sigmoid normalization, hybrid search cache, exact location filters

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

chore: commit remaining changes from previous sessions (PRD, plans, tests)

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

fix(core): three architecture fixes — translation API, constants, vector scoring

feat(ingestion): add Phase 3 ingestion pipeline

feat(core): add Phase 1 core infrastructure

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