新增获取全部知识库的接口，api版本号重归到v1

backend/services/crawler_service.py

@@ -30,6 +30,11 @@ class CrawlerService:
         self._active_workers: Dict[int, set] = {} 
         self._lock = threading.Lock()
 
+    def get_knowledge_base_list(self):
+        """获取知识库列表"""
+        return data_service.get_all_tasks()
+
+
     def _track_start(self, task_id: int, url: str):
         """[Internal] 标记某个URL开始处理"""
         with self._lock:

backend/services/data_service.py

@@ -63,6 +63,38 @@ class DataService:
                 and_(self.db.queue.c.task_id == task_id, self.db.queue.c.url == clean_url)
             ).values(status=status))
 
+    def get_all_tasks(self):
+        """
+        [新增] 获取所有已注册的任务（知识库列表）
+        用于前端展示或工作流的路由选择
+        """
+        with self.db.engine.connect() as conn:
+            # 查询 id, root_url, created_at (如果有的话)
+            # 这里假设 tasks 表里有 id 和 root_url
+            stmt = select(self.db.tasks.c.id, self.db.tasks.c.root_url).order_by(self.db.tasks.c.id)
+            rows = conn.execute(stmt).fetchall()
+            
+            # 返回精简列表
+            return [
+                {"task_id": r[0], "root_url": r[1], "name": self._extract_name(r[1])} 
+                for r in rows
+            ]
+
+    def _extract_name(self, url: str) -> str:
+        """辅助方法：从 URL 提取一个简短的名字作为 Alias"""
+        try:
+            from urllib.parse import urlparse
+            domain = urlparse(url).netloc
+            # 比如 docs.firecrawl.dev -> firecrawl
+            parts = domain.split('.')
+            if len(parts) >= 2:
+                return parts[-2] 
+            return domain
+        except:
+            return url
+
+    # ... (保持 get_task_monitor_data, save_chunks, search 等方法不变) ...
+
     def get_task_monitor_data(self, task_id: int):
         """[数据库层监控] 获取持久化的任务状态"""
         with self.db.engine.connect() as conn: