----

feat: implement dataset loader, environment, and GRPO training pipeline for undertrial bail prediction

modified

Fix 8 compliance gaps: repeat-action dedup+cache, min-steps hard block, criminal history tool (12th action), efficiency removed from training formula, circular import cleaned, yaml formula synced

Add 4 missing actions: read_submissions, assess_flight_risk, check_case_factors, apply_proportionality (fixes 4.3d/e/g/h/i)

Fix all audit gaps: custody neutral, parity-first bias, skip penalty 0.40, statutory process reward, /observation endpoint, reset() timeout, drift determinism

Fix 5 audit gaps: conditional bail, action history, efficiency reward, train/val split, env API routing

first commit