fix(gateway): deduplicate Weixin messages by content fingerprint

gateway/platforms/weixin.py

@@ -1308,6 +1308,15 @@ async def _process_message(self, message: Dict[str, Any]) -> None:
         if message_id and self._dedup.is_duplicate(message_id):
             return
 
+        # Secondary content-fingerprint dedup for text messages
+        item_list = message.get("item_list") or []
+        text = _extract_text(item_list)
+        if text:
+            content_key = f"content:{sender_id}:{hashlib.md5(text.encode()).hexdigest()}"
+            if self._dedup.is_duplicate(content_key):
+                logger.debug("[%s] Content-dedup: skipping duplicate message from %s", self.name, sender_id)
+                return
+
         chat_type, effective_chat_id = _guess_chat_type(message, self._account_id)
         if chat_type == "group":
             if self._group_policy == "disabled":
@@ -1322,8 +1331,6 @@ async def _process_message(self, message: Dict[str, Any]) -> None:
             self._token_store.set(self._account_id, sender_id, context_token)
         asyncio.create_task(self._maybe_fetch_typing_ticket(sender_id, context_token or None))
 
-        item_list = message.get("item_list") or []
-        text = _extract_text(item_list)
         media_paths: List[str] = []
         media_types: List[str] = []
 

tests/gateway/test_weixin.py

@@ -5,7 +5,7 @@
 import json
 import os
 from pathlib import Path
-from unittest.mock import AsyncMock, patch
+from unittest.mock import AsyncMock, Mock, patch
 
 from gateway.config import PlatformConfig
 from gateway.config import GatewayConfig, HomeChannel, Platform, _apply_env_overrides
@@ -758,3 +758,43 @@ def test_send_file_sets_voice_metadata_for_silk_payload(
         assert voice_item["encode_type"] == 6
         assert voice_item["sample_rate"] == 24000
         assert voice_item["bits_per_sample"] == 16
+
+
+class TestWeixinContentDedup:
+    """Regression tests for Issue #16182 — upstream API sends duplicate content
+    with different message_ids, bypassing message_id deduplication.
+    """
+
+    def test_duplicate_content_with_different_message_ids_is_dropped(self):
+        adapter = _make_adapter()
+        adapter._poll_session = object()
+        adapter.handle_message = AsyncMock()
+
+        base_msg = {
+            "from_user_id": "wxid_user1",
+            "item_list": [{"type": 1, "text_item": {"text": "hello world"}}],
+        }
+
+        asyncio.run(adapter._process_message({**base_msg, "message_id": "msg-1"}))
+        asyncio.run(adapter._process_message({**base_msg, "message_id": "msg-2"}))
+
+        assert adapter.handle_message.await_count == 1
+        event = adapter.handle_message.await_args[0][0]
+        assert event.text == "hello world"
+
+    def test_content_dedup_not_called_for_messages_without_text(self):
+        adapter = _make_adapter()
+        adapter._poll_session = object()
+        adapter.handle_message = AsyncMock()
+        adapter._dedup.is_duplicate = Mock(return_value=False)
+
+        empty_msg = {
+            "from_user_id": "wxid_user1",
+            "message_id": "msg-1",
+            "item_list": [],
+        }
+        asyncio.run(adapter._process_message(empty_msg))
+
+        assert adapter.handle_message.await_count == 0
+        # is_duplicate should only be called for message_id, never for content
+        assert all("content:" not in str(call) for call in adapter._dedup.is_duplicate.call_args_list)