Fix #4: use resolution_hint in reply scoring — category hits 0.03, hint hits 0.05, cap 0.25 (intentional specificity incentive)

Fix #2: cap _reply_quality at 0.25, add case-insensitive punctuation-stripped matching (weights now sum to exactly 1.0)

feat: fix scoring formula, improve system prompt, boost reply quality grader - Task1 1.0, Task2 0.60, Task3 0.41, Overall 0.67

Initial commit