Increase training scale: more steps, episodes, and SFT epochs

Cap prompt generation at 512 tokens and add version print

Add SFT warm start before GRPO and DB connectivity init check

Add local model inference backend for Layer 2

Increase max completion length from 512 to 2048

Add Supabase upload for training results (Storage + DB)

Add raw training summary output and adjust training scale

Improve reward function to break refuse-everything local minimum and scale training

Update output paths to use persistent volume at /workspace/output

Clean up dead code, unused imports, and move hardcoded values to config.yaml

Reduce episodes_per_candidate from 5 to 3

Reduce GRPO training params to minimum: 2 candidates, 5 steps, 5 episodes

Centralize all training params in config.yaml (single source of truth)