feat: wire frontend to real API, ship plots, multi-stage Docker build

feat: HF Space replay backend — trace store, /api endpoints, Docker, Cell 9

feat: 5 training plots (reward±std, KL/loss, completion stats) + Drive backup in Cell 8

fix: plots gitignore, trainer_state fallback for reward curve, Cell 8 --trainer-state arg

Phase 7/8: full README, video script, make_plots.py, Cell 8 implementation