fix: bug

crawler/realtime_conflict_service.py

@@ -297,8 +297,43 @@ def _rss_to_gdelt_fallback() -> None:
 LAST_FETCH = {"items": 0, "inserted": 0, "error": None}
 
 
+def _refresh_panel_data() -> int:
+    """从近期事件重新提取并合并战损/据点等面板实时数据，不依赖本轮是否有新 RSS。返回合并条数。"""
+    if not os.path.exists(DB_PATH):
+        return 0
+    try:
+        from db_merge import merge
+        use_dashscope = bool(os.environ.get("DASHSCOPE_API_KEY", "").strip())
+        if use_dashscope:
+            from extractor_dashscope import extract_from_news
+        elif os.environ.get("CLEANER_AI_DISABLED", "0") == "1":
+            from extractor_rules import extract_from_news
+        else:
+            from extractor_ai import extract_from_news
+        conn = sqlite3.connect(DB_PATH, timeout=10)
+        rows = conn.execute(
+            "SELECT id, timestamp, category, summary FROM situation_update ORDER BY timestamp DESC LIMIT 50"
+        ).fetchall()
+        conn.close()
+        merged = 0
+        for r in rows:
+            uid, ts, cat, summary = r
+            text = ((cat or "") + " " + (summary or "")).strip()
+            if len(text) < 20:
+                continue
+            try:
+                extracted = extract_from_news(text, timestamp=ts)
+                if extracted and merge(extracted, db_path=DB_PATH):
+                    merged += 1
+            except Exception:
+                pass
+        return merged
+    except Exception:
+        return 0
+
+
 def fetch_news() -> None:
-    """执行完整写库流水线；GDELT 禁用时用 RSS 回填 gdelt_events，再通知 Node。"""
+    """执行完整写库流水线；产出看板实时数据（战损、据点、冲突事件）+ 事件脉络。GDELT 禁用时用 RSS 回填 gdelt_events。"""
     try:
         from pipeline import run_full_pipeline
         LAST_FETCH["error"] = None
@@ -314,7 +349,7 @@ def fetch_news() -> None:
             _rss_to_gdelt_fallback()
         _notify_node()
         ts = datetime.now().strftime("%H:%M:%S")
-        print(f"[{ts}] RSS 抓取 {n_fetched} 条，去重后新增 {n_news} 条资讯，写入事件脉络 {n_panel} 条")
+        print(f"[{ts}] 抓取 {n_fetched} 条，去重新增 {n_news} 条，写脉络 {n_panel} 条 → 面板实时数据（战损/据点）已由本批提取更新")
         if n_fetched == 0:
             print(f"[{ts}] （0 条：检查网络、RSS 源或 KEYWORDS 过滤）")
     except Exception as e:
@@ -322,6 +357,10 @@ def fetch_news() -> None:
         print(f"[{datetime.now().strftime('%H:%M:%S')}] 新闻抓取失败: {e}")
 
 
+# 每 N 轮做一次「从近期事件回填面板实时数据」，保证战损/据点等与最新内容一致
+BACKFILL_CYCLES = int(os.environ.get("BACKFILL_CYCLES", "2"))
+_cycle_count = 0
+
 # ==========================
 # 定时任务（asyncio 后台任务，避免 APScheduler executor 关闭竞态）
 # ==========================
@@ -329,11 +368,20 @@ _bg_task: Optional[asyncio.Task] = None
 
 
 async def _periodic_fetch() -> None:
+    global _cycle_count
     loop = asyncio.get_event_loop()
     while True:
         try:
             await loop.run_in_executor(None, fetch_news)
             await loop.run_in_executor(None, fetch_gdelt_events)
+            _cycle_count += 1
+            if _cycle_count >= BACKFILL_CYCLES:
+                _cycle_count = 0
+                merged = _refresh_panel_data()
+                if merged > 0:
+                    _notify_node()
+                    ts = datetime.now().strftime("%H:%M:%S")
+                    print(f"[{ts}] 面板实时数据回填：从近期事件合并 {merged} 条（战损/据点）")
         except asyncio.CancelledError:
             break
         except Exception as e: