Add comprehensive logging to quiz grading and feedback

Fix grading agent: Use chat template + proper generation config

Restore ContentAgent (Agent 3) with RAG integration

Add merge_and_unload() and comprehensive model logging

Fix model generation with stable sampling and speed optimizations

Fix LoRA adapter loading and add comprehensive logging

Add TeachingAgent and integrate with Orchestrator (TDD)

Linting

Merge remote-tracking branch 'origin' into agent-3-and-eval

Linting

Clean up adapters

Add adapters

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

Agent 1 + eval

Create agent 3 - cleaning up

Create agent 3