fix: preserve knowledge base references

frontend-web/src/components/workspace/chats/chat-box.tsx

@@ -86,7 +86,11 @@ const ChatBox: React.FC<{
   threadId,
   disableArtifacts = false,
 }) => {
-  const { isMock, thread } = useThread();
+  const {
+    isMock,
+    thread,
+    knowledgeReferencesEnabled = false,
+  } = useThread();
   const pathname = usePathname();
   const threadIdRef = useRef(threadId);
   const artifactsCountRef = useRef(0);
@@ -107,7 +111,8 @@ const ChatBox: React.FC<{
     citationDisplay?.reference_mode_enabled ?? false;
   const ragModeEnabled =
     (referenceModeEntryEnabled && settings.display.ragModeEnabled) ||
-    isThreadRagModeLocked(threadId);
+    isThreadRagModeLocked(threadId) ||
+    knowledgeReferencesEnabled;
   // Frontend RAG modes write their own hidden source tool messages. They use
   // the existing reference panel, but must not request or write reference
   // batches through DeerFlow's backend APIs.
@@ -121,7 +126,7 @@ const ChatBox: React.FC<{
   );
   const referencesEnabled = ragModeEnabled || hasFrontendRag;
   const shouldFetchBackendReferenceBatches =
-    referencesEnabled && !hasFrontendRag;
+    referencesEnabled && !hasFrontendRag && !!threadId && threadId !== "new";
   const { skills } = useSkills();
 
   const canScanArtifactDirectory =

frontend-web/src/components/workspace/messages/context.ts

@@ -4,11 +4,17 @@ import { createContext, useContext } from "react";
 import type { RuntimeDisplaySource } from "@/core/skill-display/runtime";
 import type { AgentThreadState } from "@/core/threads";
 
-export interface ThreadContextType {
-  thread: BaseStream<AgentThreadState>;
-  isMock?: boolean;
-  /**
-   * When set, the conversation is rendered from a public read-only share.
+export interface ThreadContextType {
+  thread: BaseStream<AgentThreadState>;
+  isMock?: boolean;
+  /**
+   * True when the active conversation has selected LLMWiki knowledge bases.
+   * Knowledge-base Q&A should always expose its source documents, independent
+   * from the admin-controlled manual reference-mode button.
+   */
+  knowledgeReferencesEnabled?: boolean;
+  /**
+   * When set, the conversation is rendered from a public read-only share.
    * Artifact/image URLs then resolve to the unauthenticated
    * `/api/public/shares/{code}/files/...` endpoint instead of the
    * auth-gated thread artifact route.

frontend-web/src/components/workspace/messages/message-list.tsx

@@ -305,9 +305,12 @@ export function MessageList({
   const { data: citationDisplay } = useCitationDisplaySettings();
   const referenceModeEntryEnabled =
     citationDisplay?.reference_mode_enabled ?? false;
+  const knowledgeReferencesEnabled =
+    threadContext?.knowledgeReferencesEnabled === true;
   const ragModeEnabled =
     (referenceModeEntryEnabled && settings.display.ragModeEnabled) ||
-    isThreadRagModeLocked(threadId);
+    isThreadRagModeLocked(threadId) ||
+    knowledgeReferencesEnabled;
   const hasSingleRoundRag = useMemo(
     () =>
       messages.some(