feat: seed-variant pool + chain gate enforcement

fix: align step_reward with grade_episode, pin deps, update docs, clean inference

feat: 10-task jitter variants + progressive disclosure gating

fix: thread-safe sessions, meaningful jitter, remove investigation_hints giveaway

feat: enforce investigation discipline + fix easy-task grading + add investigation_hints

feat: Iteration_3 — openenv validate PASS, wire compat, PayOpsReward, OPENAI_API_KEY- Fix completed, Docker verification alone pending- Padma

feat: Iteration_2 — trajectory reward shaping, episode jitter, flag identification

chore: pre-iteration-1 snapshot — 75/75 e2e passing, baseline bug fixed

Initial Commit