fix: harden image handling and update docs

core/adapters/qianniu_adapter.py

@@ -2,7 +2,7 @@ import re
 import logging
 import json
 from pathlib import Path
-from typing import List, Tuple
+from typing import List, Tuple, Any
 from core.adapters.base import BaseAdapter
 from core.schema import StandardMessage, StandardResponse
 
@@ -78,6 +78,10 @@ class QianniuAdapter(BaseAdapter):
         acc_id = str(raw.get("acc_id") or raw.get("shop_id") or "")
         from_id = str(raw.get("from_id") or raw.get("cy_id") or "")
         msg_text = str(raw.get("msg") or raw.get("content") or "")
+        raw_msg_type = self._safe_int(raw.get("msg_type"), 0)
+        image_urls = self._extract_inbound_image_urls(raw, msg_text)
+        if raw_msg_type == 1 and not msg_text.strip():
+            msg_text = "【系统：已收到图片消息】"
         
         # 判断方向：如果 from_id 包含了店铺名或 acc_id，通常说明是商家自己在说话
         # 或者逆向接口通常有一个特定的标识，这里我们做一个通用的逻辑判断
@@ -96,7 +100,8 @@ class QianniuAdapter(BaseAdapter):
             user_id=user_id,
             user_name=str(raw.get("from_name", "")),
             content=msg_text,
-            image_urls=self._extract_urls(msg_text),
+            msg_type=raw_msg_type,
+            image_urls=image_urls,
             acc_id=acc_id,
             acc_type=str(raw.get("acc_type") or "AliWorkbench"),
             raw_data=raw
@@ -135,3 +140,52 @@ class QianniuAdapter(BaseAdapter):
         image_exts = (".jpg", ".jpeg", ".png", ".gif", ".webp", ".bmp")
         candidates = re.findall(r'https?://[^\s#]+', text)
         return [u for u in candidates if any(ext in u.lower() for ext in image_exts)]
+
+    @staticmethod
+    def _safe_int(value: Any, default: int = 0) -> int:
+        try:
+            return int(value)
+        except Exception:
+            return default
+
+    def _extract_inbound_image_urls(self, raw: dict, msg_text: str) -> List[str]:
+        urls = []
+        seen = set()
+
+        def add_url(url: str):
+            if not url:
+                return
+            s = str(url).strip()
+            if not s or s in seen:
+                return
+            if self._extract_urls(s):
+                seen.add(s)
+                urls.append(s)
+
+        for url in self._extract_urls(msg_text):
+            add_url(url)
+
+        for url in self._find_image_urls_in_obj(raw):
+            add_url(url)
+
+        return urls
+
+    def _find_image_urls_in_obj(self, obj: Any) -> List[str]:
+        found: List[str] = []
+
+        def walk(val: Any):
+            if val is None:
+                return
+            if isinstance(val, str):
+                found.extend(self._extract_urls(val))
+                return
+            if isinstance(val, dict):
+                for item in val.values():
+                    walk(item)
+                return
+            if isinstance(val, (list, tuple, set)):
+                for item in val:
+                    walk(item)
+
+        walk(obj)
+        return found