fix(train): v5 — JSON preprocessor + dual-token for friend's account

fix(train): v3 — repair truncated JSON + earlier evals + fix GGUF path

fix(train): v2 — fix collapse root causes + best-ckpt tracking + GGUF export

feat(round2): DB-grounded multi_domain task with 30-ticket curriculum stage

fix: Qwen3-8B-Instruct support — model name, think token stripping

feat: hackathon improvements — benchmark dashboard, GRPO training pipeline, grader fixes