fix: improve maintenance and synchronize live conversations

backend/app/knowledge/crawl4ai_fallback.py

@@ -262,7 +262,6 @@ class Crawl4AIFallback:
                 # Always use a separate thread for running Crawl4AI to avoid conflicts
                 logger.debug("Event loop running, creating new loop in separate thread")
                 
-                import concurrent.futures
                 import threading
                 
                 result = [None, None, None]

backend/app/knowledge/enhanced_pdf_kb.py

@@ -14,9 +14,8 @@ See the License for the specific language governing permissions and
 limitations under the License.
 """
 
-from typing import Any, Dict, Iterator, List, Optional
+from typing import Any, Dict, Optional
 from agno.knowledge.pdf import PDFKnowledgeBase
-from agno.document import Document
 from app.core.logger import get_logger
 
 logger = get_logger(__name__)

backend/app/knowledge/enhanced_website_kb.py

@@ -14,7 +14,7 @@ See the License for the specific language governing permissions and
 limitations under the License.
 """
 
-from typing import Any, Dict, Iterator, List, Optional, Union
+from typing import Any, Dict, Iterator, List, Optional
 import time
 from datetime import datetime
 from concurrent.futures import ThreadPoolExecutor, as_completed

backend/app/knowledge/enhanced_website_reader.py

@@ -14,7 +14,6 @@ See the License for the specific language governing permissions and
 limitations under the License.
 """
 
-import random
 import re
 import socket
 import threading
@@ -22,13 +21,12 @@ import time
 from copy import deepcopy
 from datetime import datetime
 from dataclasses import dataclass, field
-from typing import Dict, List, Set, Tuple, Optional, Callable
+from typing import Dict, List, Tuple, Optional, Callable
 from urllib.parse import urljoin, urlparse, urldefrag, urlunparse
 from app.knowledge.crawler_identity import CRAWLER_USER_AGENT
 from app.knowledge.url_safety import BlockedHostError
 from app.knowledge.deadline import Deadline
 from app.knowledge.page_fetch import NotAPage, fetch_page_text
-import concurrent.futures
 from concurrent.futures import ThreadPoolExecutor, as_completed
 
 from bs4 import BeautifulSoup, Tag
@@ -47,7 +45,7 @@ from app.knowledge.crawl_scope import (
     url_scheme,
 )
 from app.knowledge.domains import registrable_domain
-from app.knowledge.failure_advice import FAILURE_ADVICE, FailureCause
+from app.knowledge.failure_advice import FAILURE_ADVICE as FAILURE_ADVICE, FailureCause
 from app.knowledge.main_content import select_main_node
 
 # Initialize logger for this module
@@ -1330,4 +1328,4 @@ class EnhancedWebsiteReader(WebsiteReader):
         duration = end_time - start_time
         logger.info(f"[{datetime.now().strftime('%Y-%m-%d %H:%M:%S')}] Completed reading from {url} - Created {len(documents)} documents (Total time: {duration:.2f}s)")
         
-        return documents 
+        return documents

backend/app/knowledge/knowledge_base.py

@@ -14,8 +14,8 @@ See the License for the specific language governing permissions and
 limitations under the License.
 """
 
-from agno.knowledge.pdf import PDFKnowledgeBase, PDFImageReader, PDFReader
-from agno.vectordb.pgvector import PgVector, SearchType
+from agno.knowledge.pdf import PDFImageReader, PDFReader
+from agno.vectordb.pgvector import SearchType
 from app.knowledge.optimized_pgvector import OptimizedPgVector
 from app.core.config import settings
 from app.core.logger import get_logger
@@ -31,7 +31,6 @@ from app.knowledge.pdf_limits import PdfRefused, check_page_count
 from app.models.knowledge import Knowledge, SourceType
 from app.models.knowledge_to_agent import KnowledgeToAgent
 from app.models.knowledge_queue import ProcessingStage, QueueStatus
-from app.repositories.ai_config import AIConfigRepository
 from app.database import SessionLocal
 from app.repositories.knowledge_to_agent import KnowledgeToAgentRepository
 from app.repositories.knowledge import KnowledgeRepository
@@ -47,7 +46,7 @@ from app.knowledge.embedder import get_embedder
 
 # Try to import enterprise modules
 try:
-    from app.enterprise.repositories.subscription import SubscriptionRepository
+    from app.enterprise.repositories.subscription import SubscriptionRepository  # noqa: F401 - class presence selects enterprise knowledge behavior
     HAS_ENTERPRISE = True
 except ImportError:
     HAS_ENTERPRISE = False
@@ -81,11 +80,6 @@ class KnowledgeManager:
         self.org_id = org_id
         self.agent_id = agent_id
 
-        # Get API key from AI config using context manager
-        with SessionLocal() as db:
-            ai_config_repo = AIConfigRepository(db)
-            ai_config = ai_config_repo.get_active_config(org_id)
-        
         # Default to SentenceTransformer embedder if no AI config is found
         embedder = None
         table_name = f"d_{org_id}"

backend/app/knowledge/optimized_pgvector.py

@@ -20,7 +20,7 @@ from hashlib import md5
 from agno.document import Document
 from agno.embedder import Embedder
 from agno.reranker.base import Reranker
-from agno.utils.log import log_debug, log_info, logger
+from agno.utils.log import logger
 from agno.vectordb.pgvector.pgvector import PgVector
 from agno.vectordb.distance import Distance
 from agno.vectordb.pgvector.index import HNSW, Ivfflat