Som/Timegpt Model Summary

[smdp2000ofc]

Adding summarize_model_timegpt to agent_summarize_models

Notes for Reviewer:
summarize_model_timegpt : Added logs for model args, engine params, api config and model variant if long horizon model is used. Below is the example summary table for an agent run

[Copilot]

Pull request overview

This PR adds comprehensive model summarization support for the TimeGPT forecasting model and excludes it from the feature selection process.

• Implements summarize_model_timegpt() function to extract and report TimeGPT model configuration, including API endpoint type, external regressors, and model variant
• Removes TimeGPT from the feature selection list since it's an API-based model that doesn't use traditional features
• Minor whitespace cleanup in the model summarization file

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 1 comment.

File	Description
R/train_models.R	Excludes TimeGPT from the multivariate models feature selection list to prevent issues with feature-based model workflows
R/agent_summarize_models.R	Adds TimeGPT to the model summarization dispatcher and implements the full summarize_model_timegpt() function with API configuration details, external regressor tracking, and long-horizon model variant detection

---

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

[mitokic]

looks good! Just keep in mind that eventually we will need to add some sort of feature importance to timegpt so the agent can explain which xregs were impactful or not.