refactor: Update task configurations and grading logic for improved scoring and consistency

refactor: Reward clamping in graders

refactor: Task3 reward model changed, agent adjusted for new model

refactor: Improved grading logic for task 2

refactor: grader trivial bug,

refactor: Update ActionType to include costs and modified grader for task 1

refactor: Rename submit_function to submit and removes asserts from eval.py

refactor: Update grading logic and submission handling across tasks for improved accuracy and consistency

fix: Handle optional request body in reset endpoint and set default task ID

fix: Update API responses to return JSON format and remove deprecated file references

fix: update file path for landing page in root endpoint

html file path and api corrected

fix: Update file paths and ensure model loading in PropertyRetriever

feat: Add landing page and API documentation

fix import paths in app.py to reflect correct module structure

Structure Changed, files reviewed