feat: wire trained GGUF model (customer-support-grpo-v5) into inference

feat: HF Jobs training pipeline + revert AUTO_TRAIN from Space

fix: stream training logs to stdout for HF Spaces Logs tab visibility

fix: use /tmp for logs and checkpoints — /app is read-only on HF Spaces

feat: AUTO_TRAIN=1 launches training pipeline on Space startup

feat: one-shot training script + frontend on HF Spaces port 7860

fix: rate limit bypass for admin key + JSON 429 + LLM judge killswitch

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

fix(security): close all 7 audit findings from V2/V3 security audit

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

feat: Progressive 4-stage curriculum (v2.1.0)

feat: Round 2 — Hierarchical multi-agent environment (v2.0)

chore: remove global auth for testing

fix: Phase 17 final production lock (auth, PII redact, structlog)

feat: complete hackathon hardening and nightmare mode integration

fix: resolve all openenv validate failures for Phase 1 submission

fix: production hardening — rate limiting, session cap, body limit, logging, deep copy, e2e tests

fix: address 6 audit report issues — input validation, CORS, session TTL, health check, log safety, history truncation

feat: complete CustomerSupportEnv RL environment for OpenEnv hackathon