fix: clamp all scores strictly to (0, 1) — no 0.0 or 1.0

fix: clamp all task scores to strict (0,1) range — never exactly 0.0 or 1.0

Fix critical crash bug + audit fixes

Fix all 4 remaining issues for hackathon

Fix 4 critical grader bugs

Improve grader quality + research framing

CodeReviewEnv v1.0 — OpenEnv-compliant submission