Add PersistencePredictor baseline model

[GiGiKoneti]

Describe your changes

• Add PersistencePredictor, a baseline StepPredictor model that returns the previous state unchanged at each autoregressive step.
• Register PersistencePredictor as persistence in the MODELS registry inside neural_lam/models/__init__.py.
• Add validation logic in neural_lam/train_model.py to prevent training the persistence model, raising a ValueError if training is attempted.
• Add comprehensive unit tests covering the forward pass, kwargs absorption, forecaster unrolling, predicts_std behavior, and training error prevention.

No changes to any existing prediction pathways.

None.

Issue Link

closes #676

Type of change

• 🐛 Bug fix (non-breaking change that fixes an issue)
• ✨ New feature (non-breaking change that adds functionality)
• 💥 Breaking change (fix or feature that would cause existing functionality to not work as expected)
• 📖 Documentation (Addition or improvements to documentation)

Checklist before requesting a review

• My branch is up-to-date with the target branch - if not update your fork with the changes from the target branch (use pull with --rebase option if possible).
• I have performed a self-review of my code
• For any new/modified functions/classes I have added docstrings that clearly describe its purpose, expected inputs and returned values
• I have placed in-line comments to clarify the intent of any hard-to-understand passages of my code
• I have updated the README to cover introduced code changes
• I have added tests that prove my fix is effective or that my feature works
• I have given the PR a name that clearly describes the change, written in imperative form (context).
• I have requested a reviewer and an assignee (assignee is responsible for merging). This applies only if you have write access to the repo, otherwise feel free to tag a maintainer to add a reviewer and assignee.

Checklist for reviewers

Each PR comes with its own improvements and flaws. The reviewer should check the following:

• the code is readable
• the code is well tested
• the code is documented (including return types and parameters)
• the code is easy to maintain

Author checklist after completed review

• I have added a line to the CHANGELOG describing this change, in a section
  reflecting type of change (add section where missing):
  • added: when you have added new functionality
  • changed: when default behaviour of the code has been changed
  • fixes: when your contribution fixes a bug
  • maintenance: when your contribution is relates to repo maintenance, e.g. CI/CD or documentation

Checklist for assignee

• PR is up to date with the base branch
• the tests pass
• (if the PR is not just maintenance/bugfix) the PR is assigned to the next milestone. If it is not, propose it for a future milestone.
• author has added an entry to the changelog (and designated the change as added, changed, fixed or maintenance)
• Once the PR is ready to be merged, squash commits and merge the PR.

[sadamov]

Thanks @GiGiKoneti, this is clean and well-scoped. I ran it locally: the 5 tests pass, pre-commit is clean, and --eval test --model persistence runs end-to-end with the loss growing by lead time...

A few small asks inline, none of them block the logic.

• the training guard in train_model.py compares against the literal "persistence". Fine for a single baseline, though a trainable = False class attribute would be more robust if more analytical baselines arrive later.
• --output_std is silently ignored with persistence (documented, harmless). A logger.warning would make the no-op explicit.
• README is still unchecked in the PR checklist. A one-liner noting --model persistence needs --eval val/test would help discoverability.

[GiGiKoneti]

@sadamov

• Replaced the hardcoded training guard with a trainable class attribute on StepPredictor.
• Fixed the cascading test_eval_without_load_warning failure caused by the new MODELS dictionary lookup in train_model.py.
• Addressed all inline suggestions for the changelog, test assertions, std warning, and README.

[joeloskarsson]

Looking very good, I added some ideas above that could be small improvements :)

[joeloskarsson]

Nice! LGTM

[sadamov]

Clean and correct, already approved. A few small polish asks inline, none block the logic.

[GiGiKoneti]

Done!

• Removed the vestigial patches from test_eval_without_load_warning in tests/test_train_model_warnings.py as suggested.
• Added the missing predictor.trainable is False assertion to test_persistence_predictor_returns_prev_state in tests/test_persistence.py to exercise the dynamic trainable property.