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

core/llm_utils.py

@@ -11,6 +11,24 @@ from typing import List, Optional, Union, Iterator, Callable
 
 logger = logging.getLogger(__name__)
 
+# MiMo 推理模型关键词（用于识别需要 thinking 参数的模型）
+_MIMO_MODEL_KEYWORDS = ('mimo',)
+
+def _is_mimo_model(model_name: str) -> bool:
+    """判断是否为小米 MiMo 模型（支持 thinking 参数）"""
+    if not model_name:
+        return False
+    return any(kw in model_name.lower() for kw in _MIMO_MODEL_KEYWORDS)
+
+def _inject_mimo_thinking(kwargs: dict, model: str, disable_thinking: bool = True) -> dict:
+    """为 MiMo 模型注入 thinking 参数。返回更新后的 kwargs。"""
+    if not _is_mimo_model(model):
+        return kwargs
+    extra = dict(kwargs.get('extra_body') or {})
+    extra['thinking'] = {'type': 'disabled' if disable_thinking else 'enabled'}
+    kwargs['extra_body'] = extra
+    return kwargs
+
 
 def call_llm(
     client,
@@ -57,6 +75,13 @@ def call_llm(
     if messages is None:
         messages = [{"role": "user", "content": prompt}]
 
+    # MiMo 模型自动注入 thinking 参数
+    try:
+        from config import LLM_DISABLE_THINKING
+    except ImportError:
+        LLM_DISABLE_THINKING = True
+    kwargs = _inject_mimo_thinking(kwargs, model, disable_thinking=LLM_DISABLE_THINKING)
+
     try:
         response = client.chat.completions.create(
             model=model,
@@ -145,6 +170,13 @@ def call_llm_stream(
     if messages is None:
         messages = [{"role": "user", "content": prompt}]
 
+    # MiMo 模型自动注入 thinking 参数
+    try:
+        from config import LLM_DISABLE_THINKING
+    except ImportError:
+        LLM_DISABLE_THINKING = True
+    kwargs = _inject_mimo_thinking(kwargs, model, disable_thinking=LLM_DISABLE_THINKING)
+
     try:
         stream = client.chat.completions.create(
             model=model,