UI Overhaul, W&B Tracking, Automated Compliance Scripts, and Documentation Update for Hackathon Submission

fix: stabilize deployment, action safety, and benchmark reproducibility

Restore critical training fixes after PR merge

Finalize OpenEnv submission (multi-mode server, strict scoring, uv lock)

Fix GRPO JSON parsing and add chat format support

Add Colab training notebook and wire real inference logic into Streamlit

Initial commit for EcoGrid-OpenEnv hackathon