fix: clamp all grader scores to strict (0,1) open interval

Fix: add grader property to PayOpsTask, include grader in grade_episode per_task_rewards, add per-task grader definitions to openenv.yaml

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

feat: investigation required for full credit on hard/critical + replay seed support

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

fix: correct reward constants and test suite issues

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

Initial Commit