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

Restore Groq API defaults in inference.py

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

Fix inference action sanitization and improve mobile responsiveness

fix: monorepo