Add session checkpoint: v3 launch decision with full context bead5cb verified rtferraz commited on 16 days ago
apply v3 task-aware thinking controls and delete deprecated notebook 1d514ac rtferraz commited on 16 days ago
Add v3 thinking control patch - task-aware system prompts + think efficiency reward 0f39df7 verified rtferraz commited on 16 days ago
Initial commit: Tucano2-Commerce GRPO v3 training pipeline fa4a874 rtferraz Claude Opus 4.6 commited on 16 days ago
Rename notebooks/grpo_vertex_v3.ipynb to notebooks/DEPRECATED_grpo_vertex_v3.ipynb a62f1dc verified rtferraz commited on 16 days ago
feat: add v3 notebook (.ipynb) — ready for Vertex AI Workbench 6c51e5f verified rtferraz commited on 16 days ago
feat: add GRPO v3 implementation with entropy collapse fixes a6a8b11 verified rtferraz commited on 16 days ago
docs: add ADR-001 next steps with detailed execution plans b47b36b verified rtferraz commited on 17 days ago