Move supabase to core dependencies

Add Supabase upload for training results (Storage + DB)

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

Add training report & logging system with reward charts and conversation comparisons

Fix setuptools: explicitly list packages for flat layout discovery

Fix build backend: use setuptools.build_meta instead of invalid _legacy path

Wire up real LLM integration via HF Inference API

Fix critical gaps: prompt-sensitive agent, adversarial customers, executable GRPO, OpenEnv wrapper

Implement self-improving AI oversight system with nested RL environments