feat(grader): add task-aware grading with new metrics and composite scoring

fix(inference): refine scaling and rerouting rules and action behavior

reward finalisation

fix(inference): add debugging and error handling for env.step action calls

refactor(simulator): add feedback on action effects and enforce capacity discipline

better task 3

Task 3 fixes

fixes

feat(client): add new node and reward related metrics to observations

reward tuning

model changes

feat: implement Kubernetes executor for automated cluster scaling and infrastructure management

upgraded to 10 nodes

feat(curriculum): add progressive training curriculum management

model name fix

fixed env vars

updated inference.py

inference

inference updated and syntax validation

ui and inference changes

deployed to HF

modified tasks for compatibility and added the inference.py script