- Adjusted `max_tokens` in `config.yaml` for LLM models to optimize performance, setting `gpt-4o-mini` to 2048 and `gpt-4o` to 5120.
- Enhanced `assemble.py` to include a new `_weather_fields` function for improved metric handling, ensuring consistent data formatting across weather forecasts.
- Updated SQL queries in `weather.py` to incorporate additional wind speed metrics, enhancing the data model for weather analysis.
- Expanded query synthesis documentation in `_default.md` to include conditions for wind speed variations, improving advisory generation logic.
- Added unit tests in `test_assemble.py` to validate wind speed handling in weather forecasts and ensure robustness of the advisory generation process.
- Moved the assignment of `phenology_phase` in assemble.py to ensure it is included only for valid days.
- Updated the docstring in disease.py to clarify the rounding behavior of decimal values, enhancing the understanding of the formatting logic.
- Removed unnecessary checks in the decimal formatting function to streamline the code.
