final mvp created

feat(phase10): ABScriptEnv, ContrastiveReward, A/B rollout fn, 25 tests PASS, gate PASS

Phase 8 implemented

Phase 7 implemented

Phase 6 implemented

Phase 5 implemented

feat(phase4): critic escalation engine, difficulty tracker, env wiring, gate PASS

phase2 implemented

feat(phase1): OpenEnv scaffold + R1/R2 rewards — PHASE 1 GATE PASS

feat(phase0): add Groq backend, set as default (llama-3.3-70b-versatile)

feat(phase0): switch default model to Qwen2.5-1.5B-Instruct

refactor(phase0): replace Anthropic SDK with LLMBackend abstraction (default Qwen)

feat(phase0): add run_critic_gate CLI with rich output and fixture saving

feat(phase0): scaffold directories and requirements