diff --git a/core/websocket_client.py b/core/websocket_client.py
index 396d144..a6e4d2e 100755
--- a/core/websocket_client.py
+++ b/core/websocket_client.py
@@ -468,7 +468,12 @@ class QingjianAPIClient:
         """判断文本是否指代之前的图片（图一/图二/这张/那张/上面那张等）"""
         if not msg:
             return False
-        refs = ("图一", "图二", "第一张", "第二张", "这张", "那张", "上面那张", "下面那张", "刚才那张", "上一张", "下一张")
+        refs = (
+            "图一", "图二", "第一张", "第二张",
+            "这张", "那张", "这图", "那个图",
+            "这个", "这个呢",
+            "上面那张", "下面那张", "刚才那张", "上一张", "下一张",
+        )
         return any(r in msg for r in refs)
 
     def _extract_image_urls(self, msg: str) -> list:
@@ -612,7 +617,9 @@ class QingjianAPIClient:
                     old.cancel()
                 async def _delay_flush(capture_key, capture_data):
                     await asyncio.sleep(self._DEBOUNCE_SECONDS + 4)
-                    await self._flush_pending_images(capture_key, capture_data)
+                    # 与同客户 agent_reply 串行，避免“延迟报价”和“当前追问”并发打架
+                    async with self._get_customer_lock(capture_key):
+                        await self._flush_pending_images(capture_key, capture_data)
                 task = asyncio.create_task(_delay_flush(key, data))
                 self._pending_image_tasks[key] = task
                 return
diff --git a/image/image_analyzer.py b/image/image_analyzer.py
index 33e3198..5ded00f 100755
--- a/image/image_analyzer.py
+++ b/image/image_analyzer.py
@@ -241,6 +241,7 @@ class ImageAnalyzer:
 
     DENSE_TEXT_SUBJECT_KEYWORDS = (
         "宣传栏", "公告栏", "展板", "海报墙", "通知栏", "知识栏", "制度牌", "公示栏", "墙报", "密密麻麻",
+        "宣传海报", "知识海报", "科普海报", "防灾减灾", "宣传板", "宣传页",
         "表格", "检索表", "配伍表", "药物配伍", "课程表", "流程表", "说明表", "数据表",
         "word wall", "poster wall", "bulletin board",
     )
@@ -571,6 +572,10 @@ class ImageAnalyzer:
             kw in scene_text
             for kw in self.DENSE_TEXT_SUBJECT_KEYWORDS
         )
+        dense_text_hint = any(
+            kw in scene_text
+            for kw in ("密集文字", "大量文字", "小字", "多板块", "细字")
+        )
 
         # 校验比例合法性
         valid_ratios = {"1:1", "9:16", "16:9", "3:4", "4:3", "3:2", "2:3", "5:4", "4:5"}
@@ -640,7 +645,8 @@ class ImageAnalyzer:
 
         # 硬规则1：文字很多（>100）且密密麻麻不接单
         text_gt_100 = text_amount in ["大量 (51-200 字)", "极多 (200 字以上)"]
-        if text_gt_100 or dense_text_scene:
+        dense_text_hard_reject = text_gt_100 or dense_text_scene or (has_text == "yes" and dense_text_hint)
+        if dense_text_hard_reject:
             feasibility = "no"
             risk = "high"
             note = "文字内容过于密集（如宣传栏/公告栏），暂不接单处理"