- Integrate Pydantic and Pydantic Settings for config models and validation
- Add `config.yaml` for structured and readable configuration
- Centralize environment variable loading and configuration instance
This commit addresses two issues in `software/source/server/i.py`:
1. Fix the `UnboundLocalError` caused by importing the `os` module at both the top level and within the `configure_interpreter` function.
2. Make the `interpreter.llm.model` configurable via the `MODEL` environment variable or `--model` command line argument. Defaults to gpt-4. This allows users to run O1 locally.
Fixes#116
James C. Palmer