fix: async document processing in background threads, improve chat UX

- Fix knowledge_base_service calling async process_document synchronously
  in background threads — use asyncio.new_event_loop().run_until_complete()
  instead of bare call that returned unawaited coroutine
- Same fix for _update_document and reindex_document
- Replace ModeSelector with auto-detect: RAG mode when knowledge bases selected
- Convert regenerateMessage to streaming (was synchronous API call)
- Show "知识库检索模式" indicator above input when KB selected
- Remove loadSessions side-effect from streaming onComplete
- Fix chat page loading state to avoid flash
- Improve forum page spacing and sizing

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

web/src/app/(main)/chat/page.tsx

@@ -14,9 +14,10 @@ import { PanelLeftClose, PanelLeftOpen } from "lucide-react";
 export default function ChatPage() {
   const router = useRouter();
   const { isAuthenticated, user, isLoading: authLoading } = useAuthStore();
-  const { loadSessions, isLoading: chatLoading } = useChatStore();
+  const { loadSessions, sessions } = useChatStore();
   const [isInitialized, setIsInitialized] = useState(false);
   const [sidebarOpen, setSidebarOpen] = useState(true);
+  const [initialLoading, setInitialLoading] = useState(true);
 
   useEffect(() => {
     if (!authLoading && !isAuthenticated) {
@@ -25,12 +26,12 @@ export default function ChatPage() {
     }
 
     if (isAuthenticated && !isInitialized) {
-      loadSessions();
+      loadSessions().then(() => setInitialLoading(false));
       setIsInitialized(true);
     }
   }, [isAuthenticated, authLoading, isInitialized, router, loadSessions]);
 
-  if (authLoading || chatLoading) {
+  if (authLoading || initialLoading) {
     return (
       <div className="min-h-screen flex items-center justify-center">
         <LoadingSpinner size="lg" />