Update to lesson v2: remove old lesson, fix cache parsing

Remove RAG from startup, use pre-built lesson cache

Rag clean up + missing specs

Linting and address feedback: fix model size (3B→7B), JSON capitalization, remove tokens from notebooks

Add noqa comments for E402 in standalone eval scripts

Fix linting: unused loop variable

old script deletions

script clean up

Fix HuggingFace Spaces README metadata

Address comments

Agent 3 set up and improvements

Complete Agent 3 evaluation infrastructure and identify RAG schema issue

Agent 2 implementation + baseline eval and small improvements - clean up

Agent 2 implementation + baseline eval and small improvements

Address feedback

Create combined training data + fine tuning logic

Linting

Address feedback

Create training data sets

Evaluate RAG retrieval and update

Retrieve RAG content

Cleaning up

Create RAG ingestion pipeline

Address feedback

Improve on RAG content to have right size

Improve on RAG content to have right size

Clean up repository: Remove v1 and placeholder directories

Fix linting errors

Setup modern Python tooling and RAG pipeline