Rewrite notebook to follow Unsloth GRPO pattern (trl==0.22.2)

Fix missing mergekit dependency in Colab install cell

Merge remote changes and fix parse_model_action for GET payloads

Add GRPO training notebook and dense reward redesign for Round 2

Fix score formula: proportional to MAX_TASK_REWARD, clamped to (0.001, 0.999)

Fix inference.py: correct stdout format and default ENV_URL to HF Space

Add uv.lock

Move Dockerfile to root for HF Spaces

Initial submission: Bug Hunter Env

initial commit