Update lesson 1 to have only 1 grammar topic

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

Merge remote-tracking branch 'origin/main' into orchestration-implementation

Restore ContentAgent (Agent 3) with RAG integration

Add simplified lesson 1 v2

Add teaching agent v2 training data and SageMaker fine-tuning notebook

Rag clean up + missing specs

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

old script deletions

Fix HuggingFace Spaces README metadata

Clean up docs

Fix Agent 3 RAG schema mismatch - remove 'correct' field

Complete Agent 3 evaluation infrastructure and identify RAG schema issue

Remove old content agent implementation

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

Agent 2 implementation + baseline eval and small improvements

Agent 1 + eval

Create combined training data + fine tuning logic

Create training data sets

Evaluate RAG retrieval and update

Improve on RAG content to have right size

Baseline eval report + small changes

Fix inconsistencies

Fix inconsistencies

Create RAG DB content for lesson 1 and reusable exercises

Fix baseline feedback template usage and linting

Clean up docs and reorganize: Flatten structure, remove outdated files

Reorganize for v2: Archive v1, add v2 docs and eval test cases

Fix linting errors

Initial project setup: directory structure, dependencies, README