Multi-step GRPO, milestone reward, benchmark, Neo4j export, graph viz

Increase GRPO diversity: G=8, temperature=1.1

Fix narada_grpo.ipynb Cell 6: handle TRL chat-format completions

Fix narada_grpo.ipynb Cell 3: disable Unsloth stats + thinking mode

Fix narada_grpo.ipynb: max_completion_length 300 -> 600

upgrades for openenv validation

Fix notebook cell source encoding (char-split artifact from editor)

Add phenotypes_absent obs field, fix training config, update README framing

rules added for training and evaluation of Narada-CLAUDE, along with a colab notebook for training. Also added a prompt for generating code using Narada-CLAUDE.

Add training notebook, architecture docs, baseline benchmark, and WS fixes