Set up a Python LLM dev environment

Set up a reproducible local Python environment to develop the Mistral-based agent. Demonstrate how you would: install a specific Python version with pyenv; create and activate a virtual environment; manage dependencies with a lockfile; configure environment variables for secrets without committing them; structure the project for quick local execution and testing; and verify the setup by running a short script that prints the model name from a test Mistral API call.