持久化表情中文语义资产\n\n- 新增 t_emoji_assets 表及迁移脚本，持久化保存表情发送参数、中文语义与预览图路径\n- 在消息归档与媒体补偿流程中自动回填表情资产，实现收到表情即落语义、补图后回填预览\n- 后台表情库与自动回复优先读取持久化表情资产，仅在空表场景下小范围回补历史数据

plugins/ai_auto_response/core/emoji_reply.py

@@ -6,8 +6,6 @@ from typing import Any, Dict, List, Optional
 from db.emoji_asset_db import EmojiAssetDB
 from utils.wechat.emoji_semantic_parser import (
     dedupe_emoji_semantic_candidates,
-    extract_emoji_meta,
-    extract_emoji_semantic_info,
     normalize_emoji_match_text,
     safe_text,
 )
@@ -88,38 +86,29 @@ class EmojiReplySelector:
         if self._cache_assets and now < self._cache_expires_at:
             return self._cache_assets
 
-        rows = self.asset_db.get_recent_emoji_assets(limit=self.asset_limit)
-        assets: Dict[str, Dict[str, Any]] = {}
-        for row in rows:
-            attachment_url = safe_text(row.get("attachment_url"))
-            md5, total_length = extract_emoji_meta(attachment_url)
-            if not md5 or total_length <= 0:
-                continue
-
-            semantic_info = extract_emoji_semantic_info(attachment_url)
+        assets = self.asset_db.list_emoji_assets(limit=self.asset_limit, require_preview=False)
+        if not assets:
+            # 只有持久化资产表还是空时，才回补一小批最近历史；
+            # 正常情况下，归档和媒体补偿流程会自动维护这张表，自动回复不该在每次加载时去扫原始消息。
+            self.asset_db.sync_recent_emoji_assets(limit=min(self.asset_limit, 120))
+            assets = self.asset_db.list_emoji_assets(limit=self.asset_limit, require_preview=False)
+        normalized_assets: List[Dict[str, Any]] = []
+        for asset in assets:
             semantic_aliases = [
                 alias
-                for alias in (semantic_info.get("semantic_aliases") or [])
+                for alias in (asset.get("semantic_aliases") or [])
                 if len(alias) <= self.max_alias_chars
             ]
             if not semantic_aliases:
                 continue
-
-            target = assets.setdefault(md5, {
-                "md5": md5,
-                "total_length": total_length,
-                "semantic_text": "",
-                "semantic_aliases": [],
+            normalized_assets.append({
+                "md5": asset.get("md5", ""),
+                "total_length": int(asset.get("total_length") or 0),
+                "semantic_text": asset.get("semantic_text", ""),
+                "semantic_aliases": dedupe_emoji_semantic_candidates(semantic_aliases),
             })
-            if not target.get("total_length") and total_length > 0:
-                target["total_length"] = total_length
-            if not target.get("semantic_text") and semantic_info.get("semantic_text"):
-                target["semantic_text"] = semantic_info.get("semantic_text")
-            target["semantic_aliases"] = dedupe_emoji_semantic_candidates(
-                list(target.get("semantic_aliases") or []) + semantic_aliases
-            )
 
-        self._cache_assets = [asset for asset in assets.values() if asset.get("semantic_aliases")]
+        self._cache_assets = [asset for asset in normalized_assets if asset.get("semantic_aliases")]
         self._cache_expires_at = now + self.cache_ttl_sec
         return self._cache_assets