Adding CI test suite

[sridhs21]

This PR adds a lightweight testing framework. It addresses the need to catch basic syntax and logic errors without depending on large, external simulation data.

This is done with two main additions:

• A --smoke-test flag that runs a brief end-to-end training loop. It uses a new SyntheticXPointDataset to generate mock data and makes sure the core training pipeline is functional. This provides a sanity check, confirming that data loading, model forward/backward passes, and the main training loop execute without errors.

• A pytest suite for more targeted checks. This includes unit tests for components like the DiceLoss function and an integration test to verify that model checkpointing (saving and loading) works correctly.

[cwsmith]

@sridhs21 Thank you. Are all the functions defined in test_xpoint_ml.py automatically called by pytest? How do we run the pytest suite?

[sridhs21]

Yes, all functions in test_xpoint_ml.py are automatically called by pytest because they follow the naming convention of starting with test_. To run the pytest suite, pytest reconClassifier/test_xpoint_ml.py or pytest test_xpoint_ml.py will work, depending on the directory you are in.

[cwsmith]

Looks good. Thank you.