fix(exam_pkg): 判断题返回bool + 填空题扁平数组归一化

grader.py:
- 判断题批阅结果 student_answer/correct_answer 统一返回 true/false (bool)
  兼容 "对"/"错"/"true"/"false"/True/False/1/0 等所有输入格式
- 填空题新增 _normalize_fill_blank_answer 兜底归一化
  修复 LLM 生成扁平数组 ["ans1","ans2"] 导致 1空多选项误判满分的bug
- feedback 文本统一用小写 true/false

generator.py:
- validate_questions_schema 出题时修正扁平数组为二维格式
  从源头防止填空题答案格式错误

exam_pkg/generator.py

@@ -169,6 +169,14 @@ def validate_questions_schema(questions: List[Dict]) -> List[Dict]:
             if not content.get('data', {}).get('options'):
                 continue
 
+        # 填空题答案格式归一化：扁平数组 → 二维数组
+        if q_type == 'fill_blank':
+            ans = content.get('answer')
+            if isinstance(ans, list) and ans and all(isinstance(item, str) for item in ans):
+                # 扁平数组 ["答案1", "答案2"] → [["答案1"], ["答案2"]]
+                content['answer'] = [[item] for item in ans]
+                logger.warning(f"填空题答案格式修正: 扁平数组 → 二维数组 ({len(ans)} 空)")
+
         validated.append(q)
 
     return validated

exam_pkg/grader.py

@@ -88,11 +88,33 @@ grading_semaphore = threading.Semaphore(MAX_CONCURRENT_GRADING)
 
 # ==================== 本地批阅函数 ====================
 
+def _normalize_true_false(value) -> bool:
+    """
+    将判断题的各种表示形式统一转为 bool。
+
+    支持: "对"/"错", "正确"/"错误", "true"/"false", "yes"/"no",
+          True/False, 1/0, "T"/"F", "1"/"0"
+    """
+    if isinstance(value, bool):
+        return value
+    if isinstance(value, (int, float)):
+        return bool(value)
+    if isinstance(value, str):
+        v = value.strip().lower()
+        if v in ('对', '正确', 'true', 'yes', 't', '1'):
+            return True
+        if v in ('错', '错误', 'false', 'no', 'f', '0'):
+            return False
+    # 无法识别时返回 None，让比较逻辑走原始字符串匹配
+    return None
+
+
 def grade_objective(answer: Dict) -> Dict:
     """
     批阅客观题（选择/判断）
 
     🔥 本地直接判断，无 LLM 调用
+    判断题返回的 student_answer / correct_answer 统一为 bool (true/false)
     """
     q_type = answer['question_type']
     question_content = answer.get('content', {})
@@ -100,17 +122,39 @@ def grade_objective(answer: Dict) -> Dict:
     student_answer = answer.get('student_answer')
     max_score = answer.get('max_score', 2.0)
 
-    # 判断正确性
+    # 判断题：归一化为 bool 比较 + bool 输出
-    if q_type == 'single_choice':
+    if q_type == 'true_false':
+        norm_correct = _normalize_true_false(correct_answer)
+        norm_student = _normalize_true_false(student_answer)
+        if norm_correct is not None and norm_student is not None:
+            correct = norm_correct == norm_student
+            correct_answer = norm_correct
+            student_answer = norm_student
+        else:
+            # 兜底：无法归一化时用原始字符串比较
+            correct = student_answer == correct_answer
+            # 仍尝试转为 bool 输出，转不了则保留原值
+            if norm_correct is not None:
+                correct_answer = norm_correct
+            if norm_student is not None:
+                student_answer = norm_student
+    elif q_type == 'single_choice':
         correct = student_answer == correct_answer
     elif q_type == 'multiple_choice':
         # 多选题：答案顺序无关
         correct = set(student_answer) == set(correct_answer) if isinstance(student_answer, list) else False
-    elif q_type == 'true_false':
-        correct = student_answer == correct_answer
     else:
         correct = False
 
+    # 构造 feedback：判断题用 true/false，其他题型用原值
+    if not correct:
+        if q_type == 'true_false' and isinstance(correct_answer, bool):
+            feedback = f"正确答案: {'true' if correct_answer else 'false'}"
+        else:
+            feedback = f"正确答案: {correct_answer}"
+    else:
+        feedback = "正确！"
+
     return {
         "question_id": answer.get('question_id'),
         "score": max_score if correct else 0,
@@ -120,11 +164,49 @@ def grade_objective(answer: Dict) -> Dict:
             "correct": correct,
             "student_answer": student_answer,
             "correct_answer": correct_answer,
-            "feedback": f"正确答案: {correct_answer}" if not correct else "正确！"
+            "feedback": feedback
         }
     }
 
 
+def _normalize_fill_blank_answer(correct_answers: list, blank_count: int = 0) -> list:
+    """
+    归一化填空题答案为二维数组 [["答案1", "同义词"], ["答案2"], ...]
+
+    修复 LLM 生成扁平数组 ["答案1", "答案2"] 的格式错误：
+    - 扁平数组会被误认为"1个空、多个可选答案"，导致匹配一个就给满分
+    - 归一化后每个元素独立为空，各自占分
+
+    Args:
+        correct_answers: 原始答案（可能是 1D 或 2D）
+        blank_count: 题目声明的空数（来自 content.data.blank_count），用于辅助判断
+    """
+    if not correct_answers:
+        return correct_answers
+
+    # 已经是标准二维格式：每个元素都是 list
+    if all(isinstance(item, list) for item in correct_answers):
+        return correct_answers
+
+    # 扁平数组：元素全是字符串 → 每个字符串是独立的空
+    if all(isinstance(item, str) for item in correct_answers):
+        expected_blanks = blank_count if blank_count > 0 else len(correct_answers)
+        logger.warning(
+            f"填空题答案格式修正: 扁平数组 {correct_answers!r} → 二维数组 "
+            f"(检测到 {len(correct_answers)} 个元素, blank_count={blank_count})"
+        )
+        return [[item] for item in correct_answers]
+
+    # 混合类型（不太可能发生），尝试兜底
+    result = []
+    for item in correct_answers:
+        if isinstance(item, list):
+            result.append(item)
+        else:
+            result.append([item])
+    return result
+
+
 def grade_fill_blank(answer: Dict) -> Dict:
     """
     批阅填空题 - 支持同义词匹配
@@ -137,6 +219,10 @@ def grade_fill_blank(answer: Dict) -> Dict:
     student_answers = answer.get('student_answer', [])
     max_score = answer.get('max_score', 4.0)
 
+    # 归一化答案格式（修复 LLM 生成的扁平数组问题）
+    blank_count = question_content.get('data', {}).get('blank_count', 0)
+    correct_answers = _normalize_fill_blank_answer(correct_answers, blank_count)
+
     if not correct_answers or not student_answers:
         return {
             "question_id": answer.get('question_id'),