refactor: replace heuristic log generation with Go-based environment simulation and update API schema

feat: implement Go-based GridMind-RL simulation core and update inference interface (graph)

feat: define GridMind-RL environment data models and task structures

feat: implement multi-component dense reward function and environmental logic for GridMind-RL

Add Task 4 instruction following, Curriculum Manager for self-improvement, and world modeling simulation

fix: problems with parameters

feat: implement core environment simulation logic and update baseline scores

feat: add baseline scores JSON, inference script, and update Dockerfile for improved project structure

Enhance dashboard: Live Simulation, 72h episodes, and step reward tracking curve

Initial commit