From dd213df0e292677121914572742f519ad4455cdd Mon Sep 17 00:00:00 2001
From: lacerate551 <128470311+lacerate551@users.noreply.github.com>
Date: Mon, 22 Jun 2026 19:06:55 +0800
Subject: [PATCH] =?UTF-8?q?fix(exam=5Fpkg):=20v2=E8=A1=A5=E9=A2=98?=
 =?UTF-8?q?=E5=8E=BB=E9=87=8D=E4=B8=8Efinal=E5=B7=B2=E6=9C=89=E9=A2=98?=
 =?UTF-8?q?=E5=B9=B2=E4=BA=A4=E5=8F=89=E5=8E=BB=E9=87=8D?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

补题阶段仅和exclude_stems去重，未检查final中已有题干，
可能补出重复题目。修复：收集final题干+exclude_stems合并传入
_deduplicate_questions，多题型补题时逐轮累积排除列表。
---
 exam_pkg/generator.py | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/exam_pkg/generator.py b/exam_pkg/generator.py
index 1bfceda..332861f 100644
--- a/exam_pkg/generator.py
+++ b/exam_pkg/generator.py
@@ -1300,12 +1300,21 @@ def generate_questions_structured_v2(
 
     if shortage_types:
         logger.info(f"  [v2] 补题: 缺少题型 {dict(shortage_types)}")
+        # 收集 final 中已有题干，补题时一并排除
+        existing_stems = [q.get('content', {}).get('stem', '') for q in final if q.get('content', {}).get('stem')]
+        combined_exclude = list(exclude_stems or []) + existing_stems
+
         for q_type, shortage in shortage_types.items():
             logger.info(f"    补充 {q_type} {shortage} 道...")
             extra = generator._makeup_questions(chunks, q_type, shortage, difficulty, document_name)
-            # 补题也需去重
-            extra_deduped = _deduplicate_questions(extra, exclude_stems=exclude_stems)
+            # 补题需与已有题目 + 跨调用排除列表一起去重
+            extra_deduped = _deduplicate_questions(extra, exclude_stems=combined_exclude)
             final.extend(extra_deduped[:shortage])
+            # 将新补的题干也加入排除列表，防止后续题型补出重复
+            for q in extra_deduped:
+                stem = q.get('content', {}).get('stem', '')
+                if stem:
+                    combined_exclude.append(stem)
 
         # 补题后重新统计
         type_counts = defaultdict(int)