feat: add support for more ml models

[AzulGarza]

this pr adds support for more ml models

[Copilot]

Pull request overview

Adds additional mlforecast-backed “Auto*” forecasters and expands probabilistic (quantile) forecasting support across the ML and NeuralForecast model wrappers.

Changes:

• Added 7 new AutoMLForecast model wrappers (LinearRegression, XGBoost, Ridge, Lasso, ElasticNet, RandomForest, CatBoost) and refactored shared training/prediction into run_automlforecast_model.
• Enabled quantiles support for AutoNHITS and AutoTFT using NeuralForecast’s MQLoss, plus standardized forecast output conversion via QuantileConverter.
• Updated public exports, tests, dependencies, and changelogs to cover the new models and quantile behavior.

Reviewed changes

Copilot reviewed 8 out of 9 changed files in this pull request and generated 2 comments.

Show a summary per file

File	Description
timecopilot/models/neural.py	Adds quantile forecasting support for AutoNHITS/AutoTFT via MQLoss and output conversion.
timecopilot/models/ml.py	Introduces multiple new ML wrappers and shared run_automlforecast_model helper with quantile output support.
timecopilot/models/__init__.py	Exposes new ML forecasters via imports and __all__.
tests/models/test_models.py	Expands tests to include new models and adjusts quantile/level expectations.
tests/models/conftest.py	Registers new ML models in the test model matrix.
pyproject.toml	Adds catboost and xgboost dependencies required by the new model wrappers.
docs/changelogs/v0.0.26.md	Documents quantile support for AutoLGBM/AutoNHITS/AutoTFT.
docs/changelogs/v0.0.25.md	Documents newly added ML models.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.