Split train and tool simulator modules; mastery curriculum and grader workflow nudge.

feat: default GRPO/eval to Qwen/Qwen3-1.7B + LoRA; disable Qwen3 thinking in chat template

fix: T4-safe 4bit compute, eval/audit resilience, async inference, plot_rewards CSV/table

Update notebooks and proof artifact tooling

Fix rollout logprobs and vLLM generation

Harden notebook vLLM compatibility checks

Docs: align with Hugging Face Hub + TRL official guides

Fix Colab TRL+vLLM: pin vllm<0.19, add tomli deps, guard train

Fix notebook package refresh and training runtime

Harden training parser and validation workflow

Improve DriftShield training prompts and logging

Diagnostic: track parse_ok_ratio per episode, dump health every 5 episodes

Fix flat-reward training: stronger SYSTEM_PROMPT with few-shot, longer completions, MAX_TURNS=16, schema sanity probe

Rename files to DriftShield: notebooks, server module, kernel folder

Rebrand: drop 'Support Ops' user-facing text; add DriftShield* aliases; tighten README

DriftShield Phase C: README pivot + driftshield_easy as default curriculum

fix: patch Qwen GRPO trainer setup for current TRL

feat: GRPO training stack (Qwen3 + Unsloth opt-in, curriculum, eval, audit)