Enforce strict (0.001, 0.999) bounds on ALL rewards and scores

Fix terminal reward to be grader score only (strict 0-1 range)

Fix score bounds to (0.001, 0.999) and use HF Router defaults

Tighten score bounds to (0.000001, 0.999999) for strict validation

Fix grader scores to be strictly within (0, 1) range

Version 3

fix: monorepo