Add CLAUDE.md project documentation

[steveya]

Summary

Added comprehensive project documentation file (CLAUDE.md) that serves as a reference guide for developers working on the volatility-forecast library.

Key Changes

• New file: CLAUDE.md with complete project overview and developer guide
  • Project description and purpose
  • Detailed repository structure with all major modules and their responsibilities
  • Development environment setup instructions (Python 3.11/3.12, conda, pip)
  • Environment variable configuration (.env file)
  • Common commands for testing and running examples
  • CI/CD pipeline documentation (GitHub Actions)
  • Architecture patterns and model hierarchy explanation
  • Feature system design and key feature types
  • Data pipeline and evaluation methodology
  • Coding conventions and best practices
  • Configuration file references
  • Core and optional dependencies

Notable Details

• Documents the scikit-learn compatible API design with BaseVolatilityModel
• Explains the four main forecasting models (ES, STES, XGBoost-STES, VolGRU)
• Clarifies point-in-time (PIT) alignment requirements for the data pipeline
• Provides evaluation methodology including fixed-split training and Diebold-Mariano testing
• Emphasizes compatibility with alphaforge conventions and minimal edit philosophy

https://claude.ai/code/session_013jwWg13tp461tdKsEV5h8u

[steveya]

@claude CI/CD failed. please fix

[steveya]

@copilot CI/CD failed, please fix

[Copilot]

@steveya I've opened a new pull request, #3, to work on those changes. Once the pull request is ready, I'll request review from you.

[Copilot]

Pull request overview

Adds a new top-level CLAUDE.md developer reference guide for the volatility-forecast library, covering repository structure, development setup, CI, architecture, conventions, and dependencies.

Changes:

• Introduces CLAUDE.md with a project overview and repository/module map.
• Documents local dev workflow (Python versions, .env keys, common commands).
• Summarizes core architecture (model hierarchy, features, PIT pipeline, evaluation) and config/dependency pointers.

---

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

[Copilot]

The "Run examples" command implies pip install -e .[dev] is sufficient, but examples/demo_forecast.py imports alphaforge and will fail unless alphaforge is installed separately. Consider noting the additional install prerequisite (and any other optional deps needed by examples) right here to avoid setup confusion.

[steveya]

@copilot CI/CD failed, please fix until pass

[Copilot]

@steveya I've opened a new pull request, #4, to work on those changes. Once the pull request is ready, I'll request review from you.