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/api.py

@@ -246,6 +246,7 @@ def api_generate_smart():
         "file_path": "public/产品手册.pdf",
         "collection": "public_kb",
         "difficulty": 3,           // 可选，默认 3
+        "max_total": 20,           // 可选，AI出题总数上限。不传则不限制
         "options": {}              // 可选
     }
 
@@ -267,6 +268,16 @@ def api_generate_smart():
         if diff_error:
             return error_response("INVALID_PARAMS", BAD_REQUEST, diff_error, http_status=400)
 
+        # 可选：AI出题总数上限（不传则不限制）
+        max_total = data.get('max_total')
+        if max_total is not None:
+            try:
+                max_total = int(max_total)
+                if max_total <= 0:
+                    return error_response("INVALID_PARAMS", BAD_REQUEST, "max_total 必须为正整数", http_status=400)
+            except (ValueError, TypeError):
+                return error_response("INVALID_PARAMS", BAD_REQUEST, "max_total 必须为整数", http_status=400)
+
         # 校验排除题干列表（可选）
         exclude_stems = data.get('exclude_stems')
         stems_error = validate_exclude_stems(exclude_stems)
@@ -298,11 +309,11 @@ def api_generate_smart():
             f"AI智能出题: {os.path.basename(file_path)}"
         )
 
-        def _do_smart_generate(task, fp, coll, diff, opts, req_id, excl):
+        def _do_smart_generate(task, fp, coll, diff, opts, req_id, excl, max_t):
             """后台执行 AI 智能出题"""
             registry.update_progress(task.id, stage='AI分析', message='正在分析文档内容...')
             from exam_pkg.manager import analyze_file_for_exam
-            ai_analysis = analyze_file_for_exam(file_path=fp, collection=coll)
+            ai_analysis = analyze_file_for_exam(file_path=fp, collection=coll, max_total=max_t)
 
             q_types = ai_analysis.get('question_types', {})
             if not q_types or sum(q_types.values()) == 0:
@@ -325,7 +336,8 @@ def api_generate_smart():
             task.id, _do_smart_generate,
             file_path, collection,
             data.get('difficulty', 3), data.get('options', {}),
-            data.get('request_id'), data.get('exclude_stems')
+            data.get('request_id'), data.get('exclude_stems'),
+            max_total
         )
 
         return success_response(