feat(exam_pkg): 优化出题系统稳定性与推理模型适配

- core/llm_utils: MiMo模型自动注入thinking=disabled参数，全局生效
- config: 新增LLM_DISABLE_THINKING配置项（默认true）
- generator: 推理模型自适应max_tokens（1.5x）、429限流重试+指数退避、v2管线补题机制
- generator: analyze_document_for_exam新增max_total参数控制AI出题上限
- generator: validate_questions_schema兼容type和question_type字段
- grader: 主观题max_tokens从1000提升至2000、fuzzy_match增加编辑距离容错
- manager: results变量初始化防NameError、透传max_total参数
- api: /exam/generate-smart支持max_total请求参数

exam_pkg/grader.py

@@ -37,6 +37,21 @@ except ImportError:
     MODEL = None
     LLM_AVAILABLE = False
 
+# 推理模型识别（与 generator.py 共享同一套关键词）
+_REASONING_MODEL_KEYWORDS = ('mimo', 'qwq', 'deepseek-r1', 'deepseek-reasoner', 'o1', 'o3')
+
+def _is_reasoning_model(model_name: str) -> bool:
+    if not model_name:
+        return False
+    name_lower = model_name.lower()
+    return any(kw in name_lower for kw in _REASONING_MODEL_KEYWORDS)
+
+def _get_effective_max_tokens(base_max: int, model_name: str) -> int:
+    """推理模型需要 1.5x token 预算给思考链"""
+    if _is_reasoning_model(model_name):
+        return max(base_max, int(base_max * 1.5))
+    return base_max
+
 
 # ==================== 装饰器 ====================
 
@@ -169,19 +184,56 @@ def grade_fill_blank(answer: Dict) -> Dict:
 
 def fuzzy_match(student_answer: str, correct_answer: str) -> bool:
     """
-    模糊匹配（支持同义词）
+    模糊匹配（支持同义词和小编辑距离容错）
 
-    当前实现：精确匹配（忽略前后空格、大小写）
-    TODO: 可以扩展为语义相似度匹配
+    策略：
+    1. 精确匹配（去空格、转小写、统一标点）
+    2. 编辑距离容错（≥4字答案允许≤2字符差异）
     """
     if not student_answer or not correct_answer:
         return False
 
-    # 标准化：去空格、转小写
-    s = student_answer.strip().lower()
-    c = correct_answer.strip().lower()
+    # 标准化：去空格、转小写、统一标点
+    def _normalize(text: str) -> str:
+        t = text.strip().lower()
+        # 统一常见中文标点变体
+        t = t.replace('（', '(').replace('）', ')').replace('，', ',')
+        t = t.replace('；', ';').replace('：', ':').replace('"', '"').replace('"', '"')
+        return t
 
-    return s == c
+    s = _normalize(student_answer)
+    c = _normalize(correct_answer)
+
+    if s == c:
+        return True
+
+    # 编辑距离容错：答案≥4字时允许≤2字符差异
+    if len(s) >= 4 and len(c) >= 4:
+        dist = _edit_distance(s, c)
+        if dist <= 2:
+            return True
+
+    return False
+
+
+def _edit_distance(s1: str, s2: str) -> int:
+    """计算两个字符串的编辑距离（Levenshtein）"""
+    if len(s1) < len(s2):
+        return _edit_distance(s2, s1)
+    if len(s2) == 0:
+        return len(s1)
+
+    prev_row = list(range(len(s2) + 1))
+    for i, c1 in enumerate(s1):
+        curr_row = [i + 1]
+        for j, c2 in enumerate(s2):
+            # 插入、删除、替换
+            insertions = prev_row[j + 1] + 1
+            deletions = curr_row[j] + 1
+            substitutions = prev_row[j] + (c1 != c2)
+            curr_row.append(min(insertions, deletions, substitutions))
+        prev_row = curr_row
+    return prev_row[-1]
 
 
 # ==================== AnswerGrader 类 ====================
@@ -237,7 +289,21 @@ class AnswerGrader:
 
         # 🔥 P1 改进：并发调用 LLM 批阅主观题
         if llm_questions:
-            self._grade_subjective_concurrently(llm_questions, results_map)
+            try:
+                self._grade_subjective_concurrently(llm_questions, results_map)
+            except Exception as e:
+                logger.error(f"主观题并发批阅整体异常: {e}")
+                # 兜底：为所有未完成的主观题设置失败状态
+                for ans in llm_questions:
+                    qid = ans.get('question_id')
+                    if qid not in results_map:
+                        results_map[qid] = {
+                            "question_id": qid,
+                            "score": 0,
+                            "max_score": ans.get('max_score', 10),
+                            "grading_status": "failed",
+                            "details": {"error": f"批阅系统异常: {str(e)}"}
+                        }
 
         # 🔥 P1 改进：按原始顺序重组结果
         results = [results_map.get(ans.get('question_id')) for ans in answers]
@@ -369,7 +435,7 @@ class AnswerGrader:
             prompt=prompt,
             model=self.model,
             temperature=0.3,
-            max_tokens=1000,
+            max_tokens=_get_effective_max_tokens(2000, self.model),
             messages=messages
         )
         if result is None: