From 40542db4005bd787b1601a99e00f8e76fbc74d35 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E5=90=89=E9=91=AB=E5=8D=87?= <xsji@kland.com.cn>
Date: Mon, 31 Aug 2026 17:49:48 +0800
Subject: [PATCH 1/2] feat: add configurable chat display modes

---
 .../components/workspace/chats/chat-box.tsx   |  7 +-
 .../src/components/workspace/input-box.tsx    | 31 ++++---
 .../workspace/messages/message-group.tsx      | 68 +++++++-------
 .../workspace/messages/message-list.tsx       | 47 +++++-----
 .../settings/appearance-settings-page.tsx     | 58 ++++++++----
 frontend-web/src/core/system-settings/api.ts  |  4 +
 frontend-web/src/core/threads/hooks.ts        | 50 +++++++----
 frontend-web/src/pages/IframeChatPage.tsx     | 14 ++-
 .../src/pages/PromptPrefixSettingsPage.tsx    | 27 +++++-
 .../pages/iframe-chat-mode-buttons.test.ts    | 17 ++++
 .../src/pages/iframe-chat-mode-buttons.ts     |  7 +-
 offline-backend-20260512/backend/CLAUDE.md    | 15 +++-
 offline-backend-20260512/backend/README.md    | 21 +++++
 .../app/gateway/routers/system_settings.py    | 31 +++++--
 .../deerflow/agents/lead_agent/prompt.py      | 30 +++++--
 .../deerflow/config/system_settings.py        | 10 ++-
 .../tests/test_es_query_routing_prompt.py     | 17 ++++
 .../backend/tests/test_prompt_prefix.py       | 88 +++++++++++++++++++
 18 files changed, 421 insertions(+), 121 deletions(-)

diff --git a/frontend-web/src/components/workspace/chats/chat-box.tsx b/frontend-web/src/components/workspace/chats/chat-box.tsx
index e2a6c51a..8de0d29a 100644
--- a/frontend-web/src/components/workspace/chats/chat-box.tsx
+++ b/frontend-web/src/components/workspace/chats/chat-box.tsx
@@ -20,6 +20,7 @@ import {
 } from "@/core/artifacts/listing";
 import { getBackendBaseURL } from "@/core/config";
 import { isThreadRagModeLocked, useLocalSettings } from "@/core/settings";
+import { useCitationDisplaySettings } from "@/core/system-settings/hooks";
 import { isSingleRoundRagMessage } from "@/core/threads/use-single-round-rag";
 import { isMultiRoundRagMessage } from "@/core/threads/use-multi-round-rag";
 import { useSkills } from "@/core/skills/hooks";
@@ -101,8 +102,12 @@ const ChatBox: React.FC<{
   const [settings] = useLocalSettings();
   const artifactDirectoryModeEnabled =
     settings.display.artifactDirectoryModeEnabled ?? false;
+  const { data: citationDisplay } = useCitationDisplaySettings();
+  const referenceModeEntryEnabled =
+    citationDisplay?.reference_mode_enabled ?? false;
   const ragModeEnabled =
-    settings.display.ragModeEnabled || isThreadRagModeLocked(threadId);
+    (referenceModeEntryEnabled && settings.display.ragModeEnabled) ||
+    isThreadRagModeLocked(threadId);
   // 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.
diff --git a/frontend-web/src/components/workspace/input-box.tsx b/frontend-web/src/components/workspace/input-box.tsx
index 254a18ca..ac6bd91c 100644
--- a/frontend-web/src/components/workspace/input-box.tsx
+++ b/frontend-web/src/components/workspace/input-box.tsx
@@ -93,14 +93,14 @@ import {
 
 import { useRecommendedQuestions } from "@/core/recommended-questions/hooks";
 import { useUserPreferences } from "@/core/user-preferences";
-import {
-  isThreadRagModeLocked,
-  lockThreadRagMode,
-  useLocalSettings,
-} from "@/core/settings";
-
-
-import { CustomPromptBar } from "./custom-prompt-menu";
+import {
+  isThreadRagModeLocked,
+  lockThreadRagMode,
+  useLocalSettings,
+} from "@/core/settings";
+import { useCitationDisplaySettings } from "@/core/system-settings/hooks";
+
+import { CustomPromptBar } from "./custom-prompt-menu";
 import { useThread } from "./messages/context";
 import { ModeHoverGuide } from "./mode-hover-guide";
 import { Tooltip } from "./tooltip";
@@ -221,9 +221,12 @@ export function InputBox({
   const modelOptions = useMemo(() => {
     return singleRoundRagActive ? extraModels : models;
   }, [extraModels, models, singleRoundRagActive]);
-  const { thread, isMock } = useThread();
-  const { textInput } = usePromptInputController();
-  const promptRootRef = useRef<HTMLDivElement | null>(null);
+  const { thread, isMock } = useThread();
+  const { textInput } = usePromptInputController();
+  const promptRootRef = useRef<HTMLDivElement | null>(null);
+  const { data: citationDisplay } = useCitationDisplaySettings();
+  const referenceModeEntryEnabled =
+    citationDisplay?.reference_mode_enabled ?? false;
 
   const [followups, setFollowups] = useState<string[]>([]);
   const [followupsHidden, setFollowupsHidden] = useState(false);
@@ -830,9 +833,9 @@ export function InputBox({
                 <span className="text-xs font-normal">记忆</span>
               </PromptInputButton>
             </Tooltip>}
-            {!frontendRagActive && !hideContextTools && <Tooltip
-              content={
-                ragModeEnabled
+            {referenceModeEntryEnabled && !frontendRagActive && !hideContextTools && <Tooltip
+              content={
+                ragModeEnabled
                   ? "参考文献模式已开启：检索类结果会按编号引用展示"
                   : "参考文献模式已关闭：点击开启"
               }
diff --git a/frontend-web/src/components/workspace/messages/message-group.tsx b/frontend-web/src/components/workspace/messages/message-group.tsx
index 41a81777..d08cbf97 100644
--- a/frontend-web/src/components/workspace/messages/message-group.tsx
+++ b/frontend-web/src/components/workspace/messages/message-group.tsx
@@ -51,13 +51,12 @@ import {
   resolveSearchQuery,
   type SearchResultItem,
 } from "@/core/messages/search-results";
-import {
-  extractReasoningContentFromMessage,
-  findToolCallResult,
-} from "@/core/messages/utils";
-import { useRehypeSplitWordsIntoSpans } from "@/core/rehype";
-import { useLocalSettings } from "@/core/settings";
-import { useSkills } from "@/core/skills/hooks";
+import {
+  extractReasoningContentFromMessage,
+  findToolCallResult,
+} from "@/core/messages/utils";
+import { useRehypeSplitWordsIntoSpans } from "@/core/rehype";
+import { useSkills } from "@/core/skills/hooks";
 import {
   applyInlineCitations,
   buildSkillDisplayMap,
@@ -81,17 +80,19 @@ import { SourceCard } from "../skill-display-sources";
 import { MarkdownContent } from "./markdown-content";
 import { SingleRoundRagCitationDialog } from "./message-list-item";
 
-export function MessageGroup({
-  className,
-  messages,
-  isLoading = false,
-  displaySources = [],
-}: {
-  className?: string;
-  messages: Message[];
-  isLoading?: boolean;
-  displaySources?: RuntimeDisplaySource[];
-}) {
+export function MessageGroup({
+  className,
+  messages,
+  isLoading = false,
+  displaySources = [],
+  ragModeEnabled = false,
+}: {
+  className?: string;
+  messages: Message[];
+  isLoading?: boolean;
+  displaySources?: RuntimeDisplaySource[];
+  ragModeEnabled?: boolean;
+}) {
   const { t } = useI18n();
   const [showAbove, setShowAbove] = useState(
     env.NEXT_PUBLIC_STATIC_WEBSITE_ONLY === "true",
@@ -99,13 +100,12 @@ export function MessageGroup({
   const [showLastThinking, setShowLastThinking] = useState(
     env.NEXT_PUBLIC_STATIC_WEBSITE_ONLY === "true",
   );
-  const steps = useMemo(() => convertToSteps(messages), [messages]);
-  const [settings] = useLocalSettings();
-  const { skills } = useSkills();
-  const skillDisplayMap = useMemo(
-    () => (settings.display.ragModeEnabled ? buildSkillDisplayMap(skills) : new Map()),
-    [settings.display.ragModeEnabled, skills],
-  );
+  const steps = useMemo(() => convertToSteps(messages), [messages]);
+  const { skills } = useSkills();
+  const skillDisplayMap = useMemo(
+    () => (ragModeEnabled ? buildSkillDisplayMap(skills) : new Map()),
+    [ragModeEnabled, skills],
+  );
   const lastToolCallStep = useMemo(() => {
     const filteredSteps = steps.filter((step) => step.type === "toolCall");
     return filteredSteps[filteredSteps.length - 1];
@@ -197,11 +197,11 @@ export function MessageGroup({
                 <ToolCall
                   key={step.id}
                   {...step}
-                  isLoading={isLoading}
-                  skillDisplayMap={skillDisplayMap}
-                  ragModeEnabled={settings.display.ragModeEnabled}
-                />
-              ),
+                  isLoading={isLoading}
+                  skillDisplayMap={skillDisplayMap}
+                  ragModeEnabled={ragModeEnabled}
+                />
+              ),
             )}
           {lastToolCallStep && (
             <FlipDisplay uniqueKey={lastToolCallStep.id ?? ""}>
@@ -209,10 +209,10 @@ export function MessageGroup({
                 key={lastToolCallStep.id}
                 {...lastToolCallStep}
                 isLast={true}
-                isLoading={isLoading}
-                skillDisplayMap={skillDisplayMap}
-                ragModeEnabled={settings.display.ragModeEnabled}
-              />
+                isLoading={isLoading}
+                skillDisplayMap={skillDisplayMap}
+                ragModeEnabled={ragModeEnabled}
+              />
             </FlipDisplay>
           )}
         </ChainOfThoughtContent>
diff --git a/frontend-web/src/components/workspace/messages/message-list.tsx b/frontend-web/src/components/workspace/messages/message-list.tsx
index 097a0baf..15d83aff 100644
--- a/frontend-web/src/components/workspace/messages/message-list.tsx
+++ b/frontend-web/src/components/workspace/messages/message-list.tsx
@@ -28,11 +28,12 @@ import {
   hasToolCalls,
   isHiddenFromUIMessage,
 } from "@/core/messages/utils";
-import { useRehypeSplitWordsIntoSpans } from "@/core/rehype";
-import { isThreadRagModeLocked, useLocalSettings } from "@/core/settings";
-import { useSkills } from "@/core/skills/hooks";
-import {
-  buildSkillDisplayMap,
+import { useRehypeSplitWordsIntoSpans } from "@/core/rehype";
+import { isThreadRagModeLocked, useLocalSettings } from "@/core/settings";
+import { useSkills } from "@/core/skills/hooks";
+import { useCitationDisplaySettings } from "@/core/system-settings/hooks";
+import {
+  buildSkillDisplayMap,
   collectRuntimeDisplaySources,
   type RuntimeDisplaySource,
 } from "@/core/skill-display/runtime";
@@ -299,10 +300,14 @@ export function MessageList({
     }
     return map;
   }, [messages]);
-
-  const [settings] = useLocalSettings();
-  const ragModeEnabled =
-    settings.display.ragModeEnabled || isThreadRagModeLocked(threadId);
+
+  const [settings] = useLocalSettings();
+  const { data: citationDisplay } = useCitationDisplaySettings();
+  const referenceModeEntryEnabled =
+    citationDisplay?.reference_mode_enabled ?? false;
+  const ragModeEnabled =
+    (referenceModeEntryEnabled && settings.display.ragModeEnabled) ||
+    isThreadRagModeLocked(threadId);
   const hasSingleRoundRag = useMemo(
     () =>
       messages.some(
@@ -778,12 +783,13 @@ export function MessageList({
             )) {
               if (hasReasoning(message)) {
                 results.push(
-                  <MessageGroup
-                    key={"thinking-group-" + message.id}
-                    messages={[message]}
-                    isLoading={thread.isLoading}
-                    displaySources={resolveDisplaySources(message)}
-                  />,
+                  <MessageGroup
+                    key={"thinking-group-" + message.id}
+                    messages={[message]}
+                    isLoading={thread.isLoading}
+                    displaySources={resolveDisplaySources(message)}
+                    ragModeEnabled={ragModeEnabled}
+                  />,
                 );
               }
               results.push(
@@ -831,11 +837,12 @@ export function MessageList({
             .find((message) => message.type === "ai");
           return (
             <div key={"group-" + group.id} className="w-full">
-              <MessageGroup
-                messages={group.messages}
-                isLoading={thread.isLoading}
-                displaySources={resolveDisplaySources(processingAi)}
-              />
+              <MessageGroup
+                messages={group.messages}
+                isLoading={thread.isLoading}
+                displaySources={resolveDisplaySources(processingAi)}
+                ragModeEnabled={ragModeEnabled}
+              />
               <MessageTokenUsageList
                 enabled={tokenUsageEnabled}
                 isLoading={thread.isLoading}
diff --git a/frontend-web/src/components/workspace/settings/appearance-settings-page.tsx b/frontend-web/src/components/workspace/settings/appearance-settings-page.tsx
index 75778f2b..804a4772 100644
--- a/frontend-web/src/components/workspace/settings/appearance-settings-page.tsx
+++ b/frontend-web/src/components/workspace/settings/appearance-settings-page.tsx
@@ -205,6 +205,8 @@ export function AppearanceSettingsPage({ onClose }: { onClose?: () => void }) {
   const [effectiveLayoutMode, setLayoutMode] = useLayoutMode();
   const cleanupWords =
     citationDisplay?.cleanup_words ?? settings.display.citationCleanupWords ?? [];
+  const referenceModeEntryEnabled =
+    citationDisplay?.reference_mode_enabled ?? false;
 
   useEffect(() => {
     setShortcutDraft(
@@ -845,23 +847,45 @@ export function AppearanceSettingsPage({ onClose }: { onClose?: () => void }) {
             aria-label="回答速度指示器"
           />
         </div>
-        <div className="flex items-start justify-between gap-4 rounded-lg border p-4">
-          <div>
-            <div className="text-sm font-medium">RAG 引用模式</div>
-            <p className="text-muted-foreground mt-1 max-w-md text-xs leading-relaxed">
-              开启后，已配置展示适配的技能结果会在问答中渲染为编号引用或列表，并支持点击跳转。
-            </p>
-          </div>
-          <Switch
-            checked={settings.display.ragModeEnabled}
-            onCheckedChange={(checked) =>
-              setSettings("display", { ragModeEnabled: checked })
-            }
-            aria-label="RAG 引用模式"
-          />
-        </div>
-        {isAdmin && (
-          <div className="rounded-lg border p-4">
+        {isAdmin && (
+          <div className="flex items-start justify-between gap-4 rounded-lg border p-4">
+            <div>
+              <div className="text-sm font-medium">参考文献模式入口</div>
+              <p className="text-muted-foreground mt-1 max-w-md text-xs leading-relaxed">
+                管理员配置。开启后，普通问答和 iframe 问答输入区会显示「参考文献」按钮；默认关闭。
+              </p>
+            </div>
+            <Switch
+              checked={referenceModeEntryEnabled}
+              disabled={updateCitationDisplay.isPending}
+              onCheckedChange={(checked) =>
+                updateCitationDisplay.mutate({
+                  reference_mode_enabled: checked,
+                })
+              }
+              aria-label="参考文献模式入口"
+            />
+          </div>
+        )}
+        {referenceModeEntryEnabled && (
+          <div className="flex items-start justify-between gap-4 rounded-lg border p-4">
+            <div>
+              <div className="text-sm font-medium">RAG 引用模式</div>
+              <p className="text-muted-foreground mt-1 max-w-md text-xs leading-relaxed">
+                开启后，已配置展示适配的技能结果会在问答中渲染为编号引用或列表，并支持点击跳转。
+              </p>
+            </div>
+            <Switch
+              checked={settings.display.ragModeEnabled}
+              onCheckedChange={(checked) =>
+                setSettings("display", { ragModeEnabled: checked })
+              }
+              aria-label="RAG 引用模式"
+            />
+          </div>
+        )}
+        {isAdmin && (
+          <div className="rounded-lg border p-4">
             <div className="mb-3">
               <div className="text-sm font-medium">参考文献去除词</div>
               <p className="text-muted-foreground mt-1 max-w-2xl text-xs leading-relaxed">
diff --git a/frontend-web/src/core/system-settings/api.ts b/frontend-web/src/core/system-settings/api.ts
index bf59e850..24a212b0 100644
--- a/frontend-web/src/core/system-settings/api.ts
+++ b/frontend-web/src/core/system-settings/api.ts
@@ -6,6 +6,7 @@ export interface PromptPrefixSettings {
   enabled: boolean;
   switch_label: string;
   prompt_prefix: string;
+  ordinary_qa_markdown_format_enabled: boolean;
 }
 
 export interface PluginDomainAgentMappingDto {
@@ -37,6 +38,7 @@ export interface PromptPrefixUpdate {
   enabled?: boolean;
   switch_label?: string;
   prompt_prefix?: string;
+  ordinary_qa_markdown_format_enabled?: boolean;
 }
 
 function fromPluginManagementDto(data: {
@@ -173,10 +175,12 @@ export interface PrivateSquareUpdate {
 }
 
 export interface CitationDisplaySettings {
+  reference_mode_enabled: boolean;
   cleanup_words: string[];
 }
 
 export interface CitationDisplayUpdate {
+  reference_mode_enabled?: boolean;
   cleanup_words?: string[];
 }
 
diff --git a/frontend-web/src/core/threads/hooks.ts b/frontend-web/src/core/threads/hooks.ts
index 5f760442..8bd832e4 100644
--- a/frontend-web/src/core/threads/hooks.ts
+++ b/frontend-web/src/core/threads/hooks.ts
@@ -16,9 +16,14 @@ import { rememberAskTime } from "../chat-timestamps";
 import { getBackendBaseURL, getLangGraphBaseURL } from "../config";
 import { useI18n } from "../i18n/hooks";
 import { OptType, writeYLog } from "../log/y-log";
-import type { FileInMessage } from "../messages/utils";
-import type { LocalSettings } from "../settings";
-import { isThreadRagModeLocked, lockThreadRagMode, useLocalSettings } from "../settings";
+import type { FileInMessage } from "../messages/utils";
+import type { LocalSettings } from "../settings";
+import {
+  isThreadRagModeLocked,
+  lockThreadRagMode,
+  useLocalSettings,
+} from "../settings";
+import { useCitationDisplaySettings } from "../system-settings/hooks";
 import { useUpdateSubtask } from "../tasks/context";
 import type { UploadedFileInfo } from "../uploads";
 import { promptInputFilePartToFile, uploadFiles } from "../uploads";
@@ -588,8 +593,11 @@ export function useThreadStream({
   onToolStart,
   onToolEnd,
 }: ThreadStreamOptions) {
-  const { t } = useI18n();
-  const [localSettings] = useLocalSettings();
+  const { t } = useI18n();
+  const [localSettings] = useLocalSettings();
+  const { data: citationDisplay } = useCitationDisplaySettings();
+  const referenceModeEntryEnabled =
+    citationDisplay?.reference_mode_enabled ?? false;
   // Track the thread ID that is currently streaming to handle thread changes during streaming
   const [onStreamThreadId, setOnStreamThreadId] = useState(() => threadId);
   // Ref to track current thread ID across async callbacks without causing re-renders,
@@ -1540,15 +1548,15 @@ export function useThreadStream({
           ...context,
           ...extraContext,
         };
-        const selectedLlmWikiIds = Array.isArray(
-          mergedContext.llmwiki_knowledge_base_ids,
-        )
-          ? mergedContext.llmwiki_knowledge_base_ids
-          : [];
-        const ragModeEnabled =
-          localSettings.display.ragModeEnabled ||
-          isThreadRagModeLocked(threadId) ||
-          selectedLlmWikiIds.length > 0;
+        const selectedLlmWikiIds = Array.isArray(
+          mergedContext.llmwiki_knowledge_base_ids,
+        )
+          ? mergedContext.llmwiki_knowledge_base_ids
+          : [];
+        const ragModeEnabled =
+          (referenceModeEntryEnabled && localSettings.display.ragModeEnabled) ||
+          isThreadRagModeLocked(threadId) ||
+          selectedLlmWikiIds.length > 0;
         if (ragModeEnabled) {
           lockThreadRagMode(threadId);
         }
@@ -1666,8 +1674,18 @@ export function useThreadStream({
         sendInFlightRef.current = false;
       }
     },
-    [thread, _handleOnStart, t.uploads.uploadingFiles, context, localSettings.display.ragModeEnabled, queryClient, runOptions, confirmOrRejoin],
-  );
+    [
+      thread,
+      _handleOnStart,
+      t.uploads.uploadingFiles,
+      context,
+      referenceModeEntryEnabled,
+      localSettings.display.ragModeEnabled,
+      queryClient,
+      runOptions,
+      confirmOrRejoin,
+    ],
+  );
 
   const handleThreadStop = useCallback(async () => {
     const tid = threadIdRef.current;
diff --git a/frontend-web/src/pages/IframeChatPage.tsx b/frontend-web/src/pages/IframeChatPage.tsx
index cc6a010c..11851cfd 100644
--- a/frontend-web/src/pages/IframeChatPage.tsx
+++ b/frontend-web/src/pages/IframeChatPage.tsx
@@ -39,8 +39,14 @@ import {
   useLocalSettings,
   useThreadSettings,
 } from "@/core/settings";
-import { usePluginManagementSettings } from "@/core/system-settings/hooks";
-import { stopActiveThreadBeforeClarificationReply, useThreadStream } from "@/core/threads/hooks";
+import {
+  useCitationDisplaySettings,
+  usePluginManagementSettings,
+} from "@/core/system-settings/hooks";
+import {
+  stopActiveThreadBeforeClarificationReply,
+  useThreadStream,
+} from "@/core/threads/hooks";
 import { textOfMessage } from "@/core/threads/utils";
 import { env } from "@/env";
 import { cn } from "@/lib/utils";
@@ -383,6 +389,9 @@ export default function IframeChatPage() {
   }, [forceDefaultAssistant, pendingIframeSubmit, selectedAgentId]);
 
   const ragModeLocked = isThreadRagModeLocked(threadId);
+  const { data: citationDisplay } = useCitationDisplaySettings();
+  const referenceModeEntryEnabled =
+    citationDisplay?.reference_mode_enabled ?? false;
   const ragModeEnabled =
     localSettings.display.ragModeEnabled || ragModeLocked;
   const contextCompressionEnabled =
@@ -529,6 +538,7 @@ export default function IframeChatPage() {
     memoryInjectionEnabled: Boolean(
       settings.context.memory_injection_enabled ?? true,
     ),
+    referenceModeEntryEnabled,
     ragModeEnabled,
     ragModeLocked,
     contextCompressionEnabled,
diff --git a/frontend-web/src/pages/PromptPrefixSettingsPage.tsx b/frontend-web/src/pages/PromptPrefixSettingsPage.tsx
index 65e722c9..55c4af60 100644
--- a/frontend-web/src/pages/PromptPrefixSettingsPage.tsx
+++ b/frontend-web/src/pages/PromptPrefixSettingsPage.tsx
@@ -46,6 +46,8 @@ export default function PromptPrefixSettingsPage({
   const [enabled, setEnabled] = useState(false);
   const [switchLabel, setSwitchLabel] = useState("");
   const [promptPrefix, setPromptPrefix] = useState("");
+  const [ordinaryQaMarkdownFormatEnabled, setOrdinaryQaMarkdownFormatEnabled] =
+    useState(false);
   // Only seed the draft from server data once. Re-syncing every time react-query
   // refetches (window focus, route remount, etc.) would silently overwrite the
   // user's in-progress edits — and made the toggle look unresponsive: a click
@@ -57,6 +59,9 @@ export default function PromptPrefixSettingsPage({
     setEnabled(data.enabled);
     setSwitchLabel(data.switch_label);
     setPromptPrefix(data.prompt_prefix);
+    setOrdinaryQaMarkdownFormatEnabled(
+      data.ordinary_qa_markdown_format_enabled === true,
+    );
     initializedRef.current = true;
   }, [data]);
 
@@ -79,6 +84,8 @@ export default function PromptPrefixSettingsPage({
         enabled,
         switch_label: switchLabel,
         prompt_prefix: promptPrefix,
+        ordinary_qa_markdown_format_enabled:
+          ordinaryQaMarkdownFormatEnabled,
       });
       toast.success("已保存",darkToastOpts.success);
     } catch (e) {
@@ -95,10 +102,9 @@ export default function PromptPrefixSettingsPage({
       }
     >
       <div>
-        <h1 className={embedded ? "text-base font-semibold" : "text-xl font-semibold"}>问答前缀配置</h1>
+        <h1 className={embedded ? "text-base font-semibold" : "text-xl font-semibold"}>问答提示词配置</h1>
         <p className="text-muted-foreground mt-1 text-sm">
-          管理员可在此配置问答页输入框中的「前缀开关」。开启后，用户在新会话中第一次提问时，
-          会将下方配置的前缀文本和原问题拼接后再发送给模型。
+          管理员可在此配置问答前缀和普通问答的固定 Markdown 格式提示词。
         </p>
       </div>
 
@@ -147,6 +153,21 @@ export default function PromptPrefixSettingsPage({
             />
           </div>
 
+          <div className="flex items-start justify-between gap-4 rounded-lg border p-4">
+            <div>
+              <div className="text-sm font-medium">固定格式提示词</div>
+              <p className="text-muted-foreground mt-1 max-w-md text-xs leading-relaxed">
+                开启后，普通问答的长篇内容会按“# 主标题、## 一、标题、###
+                (一) 标题、#### 1. 标题”的固定 Markdown 格式生成。默认关闭。
+              </p>
+            </div>
+            <Switch
+              checked={ordinaryQaMarkdownFormatEnabled}
+              onCheckedChange={setOrdinaryQaMarkdownFormatEnabled}
+              aria-label="固定格式提示词"
+            />
+          </div>
+
           <div className="flex justify-end">
             <Button onClick={handleSave} disabled={update.isPending}>
               {update.isPending && (
diff --git a/frontend-web/src/pages/iframe-chat-mode-buttons.test.ts b/frontend-web/src/pages/iframe-chat-mode-buttons.test.ts
index 6e33a752..e9144784 100644
--- a/frontend-web/src/pages/iframe-chat-mode-buttons.test.ts
+++ b/frontend-web/src/pages/iframe-chat-mode-buttons.test.ts
@@ -9,6 +9,7 @@ test("includes the context compression toggle in the iframe chat toolbar", () =>
     agentSelected: false,
     writingModeEnabled: false,
     memoryInjectionEnabled: true,
+    referenceModeEntryEnabled: true,
     ragModeEnabled: false,
     ragModeLocked: false,
     contextCompressionEnabled: false,
@@ -28,11 +29,27 @@ test("includes the context compression toggle in the iframe chat toolbar", () =>
   );
 });
 
+test("hides the references toggle when reference mode is disabled globally", () => {
+  const buttons = buildIframeModeButtons({
+    agentSelected: false,
+    writingModeEnabled: false,
+    memoryInjectionEnabled: true,
+    referenceModeEntryEnabled: false,
+    ragModeEnabled: true,
+    ragModeLocked: false,
+    contextCompressionEnabled: false,
+    proModeEnabled: false,
+  });
+
+  assert.equal(buttons.some((button) => button.key === "references"), false);
+});
+
 test("returns only concrete toolbar button configs", () => {
   const buttons = buildIframeModeButtons({
     agentSelected: true,
     writingModeEnabled: false,
     memoryInjectionEnabled: true,
+    referenceModeEntryEnabled: true,
     ragModeEnabled: false,
     ragModeLocked: false,
     contextCompressionEnabled: false,
diff --git a/frontend-web/src/pages/iframe-chat-mode-buttons.ts b/frontend-web/src/pages/iframe-chat-mode-buttons.ts
index 47f3edd4..506fde9f 100644
--- a/frontend-web/src/pages/iframe-chat-mode-buttons.ts
+++ b/frontend-web/src/pages/iframe-chat-mode-buttons.ts
@@ -15,6 +15,7 @@ type BuildIframeModeButtonsInput = {
   agentSelected: boolean;
   writingModeEnabled: boolean;
   memoryInjectionEnabled: boolean;
+  referenceModeEntryEnabled: boolean;
   ragModeEnabled: boolean;
   ragModeLocked: boolean;
   contextCompressionEnabled: boolean;
@@ -25,12 +26,13 @@ export function buildIframeModeButtons({
   agentSelected,
   writingModeEnabled,
   memoryInjectionEnabled,
+  referenceModeEntryEnabled,
   ragModeEnabled,
   ragModeLocked,
   contextCompressionEnabled,
   proModeEnabled,
 }: BuildIframeModeButtonsInput): IframeModeButtonState[] {
-  return [
+  const buttons: IframeModeButtonState[] = [
     {
       key: "writing",
       label: "写作",
@@ -63,4 +65,7 @@ export function buildIframeModeButtons({
       active: agentSelected,
     },
   ];
+  return referenceModeEntryEnabled
+    ? buttons
+    : buttons.filter((button) => button.key !== "references");
 }
diff --git a/offline-backend-20260512/backend/CLAUDE.md b/offline-backend-20260512/backend/CLAUDE.md
index 488331e5..de8b34c5 100644
--- a/offline-backend-20260512/backend/CLAUDE.md
+++ b/offline-backend-20260512/backend/CLAUDE.md
@@ -324,7 +324,7 @@ FastAPI application on port 8001 with health checks at `GET|HEAD /health`, `/api
 | **Threads** (`/api/threads/{id}`) | `DELETE /` - remove DeerFlow-managed local thread data after LangGraph thread deletion; unexpected failures are logged server-side and return a generic 500 detail |
 | **Threads search** (`POST /threads/search`, LangGraph-compat) | Conversation listing. **System threads are excluded by default**: rows whose `metadata.system` is truthy (scheduler runs, roundtable workers) never crowd the user's list; a caller whose `metadata` filter explicitly references `thread_type`/`system` (e.g. studio notebooks) opts out of the exclusion. New `query` field = case-insensitive title (`display_name`) substring search, used by the chats page's server-side pagination. `POST /threads/count` takes the same request body (limit/offset ignored) and returns `{total}` under identical filtering/exclusion semantics ? powers the chats page's ??/??? display without fetching rows (`ThreadMetaStore.count`). `ThreadMetaStore.search` gained `exclude_system`/`query` params; JSON-blob filters batch-scan until the requested `limit`/`offset` window is full (so pagination over a heavily-filtered set never under-fills), with a `thread_id` tie-breaker on the `updated_at DESC` ordering for stable OFFSET paging. Tests: `tests/test_thread_meta_search.py` |
 | **Artifacts** (`/api/threads/{id}/artifacts`) | `GET /{path}` - serve artifacts; active content types (`text/html`, `application/xhtml+xml`, `image/svg+xml`) are always forced as download attachments to reduce XSS risk; `?download=true` still forces download for other file types |
-| **Word export** (`POST /api/writing/export/docx`) | Shared Markdown → DOCX generator used by conversation, artifact, scheduled-task, Deep Research, and AI-writing download surfaces. `app/gateway/word_export.py` builds OOXML with no Python conversion dependency: A4 portrait, 3.7/3.5/2.8/2.6 cm margins, real multilevel heading numbering (`一、` / `(一)` / `1.`), two-character first-line indent on heading levels 1–3, formal body/table styles, page numbers beginning at 1 with odd pages left-aligned and even pages right-aligned, and embedded `app/gateway/assets/fonts/方正小标宋简体.ttf`. Before numbering it removes complete manual heading prefixes (including `2.1` / `2.1.1`) and drops Markdown horizontal rules from Word output. The default ordinary-Q&A Lead Agent prompt emits the matching Markdown heading forms and avoids unordered bullet lists; writing setup, writing mode, notebook, scheduled runs, and SOUL-driven custom agents keep their independent prompts. The font loader validates its internal family, SHA-256, and OpenType embedding permission (`OS/2.fsType`) before export. Tests: `tests/test_word_export.py`, `tests/test_es_query_routing_prompt.py`. |
+| **Word export** (`POST /api/writing/export/docx`) | Shared Markdown → DOCX generator used by conversation, artifact, scheduled-task, Deep Research, and AI-writing download surfaces. `app/gateway/word_export.py` builds OOXML with no Python conversion dependency: A4 portrait, 3.7/3.5/2.8/2.6 cm margins, real multilevel heading numbering (`一、` / `(一)` / `1.`), two-character first-line indent on heading levels 1–3, formal body/table styles, page numbers beginning at 1 with odd pages left-aligned and even pages right-aligned, and embedded `app/gateway/assets/fonts/方正小标宋简体.ttf`. Before numbering it removes complete manual heading prefixes (including `2.1` / `2.1.1`) and drops Markdown horizontal rules from Word output. The ordinary-Q&A Lead Agent can emit the matching Markdown heading forms and avoid unordered bullet lists when the admin enables `prompt_prefix.ordinary_qa_markdown_format_enabled` in `system_settings.json`; the switch defaults off, while writing setup, writing mode, notebook, scheduled runs, and SOUL-driven custom agents keep their independent prompts. The font loader validates its internal family, SHA-256, and OpenType embedding permission (`OS/2.fsType`) before export. Tests: `tests/test_word_export.py`, `tests/test_es_query_routing_prompt.py`. |
 | **Deep Research** (`/api/deep-research`) | Durable, user-owned research sessions/jobs with replayable SSE events and hidden-thread artifacts. `basic`/`quick` use the compact runner; `detailed` creates bounded subtopics, searches/writes sections concurrently, and assembles a report; `deep` recursively searches follow-up questions under a deterministic breadth/depth query budget. `multi_agent` is a LangGraph 1.x editor/researcher/writer/reviewer graph: its initial plan emits `awaiting_input`, the recorder stores the interrupt and releases the lease, and `POST /jobs/{id}/resume` rebuilds the graph from the persisted approved/revised plan. A bounded `custom_outline` is frozen into the session; headings/list entries deterministically supply the detailed and multi-agent plan, and the shared writer receives it only as a guarded content constraint. Completed reports support owner-scoped follow-up (`GET /sessions/{id}/messages`, `POST /sessions/{id}/chat`): context is only the current report, selected sources and recent messages; source-id citations are persisted, while `allow_new_research=true` is explicitly rejected. Owners may change that evidence set only after the job stops via `PATCH /sessions/{id}/sources/{source_id}`; this applies to future follow-ups rather than rewriting a completed report. Optional report illustrations are gated by `config.yaml -> deep_research.image_generation`: the Harness `OpenAICompatibleImageProvider` requires base64 output, the shared runner step writes only bounded `research-image-01..04.(png|jpg|webp)` artifacts and Markdown uses private `deep-research://` links. `GET /sessions/{id}/artifacts/{name}` checks session ownership before serving an image; an unavailable provider yields a warning but never fails the text report. Runners live in `packages/harness/deerflow/agents/deep_research/runners/`, may never import `app.*`, and use only the `AdapterBundle`. |
 | **Gateway auth** | Owner-scoped Deep Research routes await the platform's asynchronous `get_current_user` resolver before they read or write persistence, ensuring each session and job operation receives a concrete user ID. Deep Research artifacts are always resolved from a whitelisted filename via `/mnt/user-data/outputs/<name>` before mapping to a host path, preserving the sandbox guard on native Windows and Linux hosts. |
 | **Suggestions** (`/api/threads/{id}/suggestions`) | `POST /` - generate follow-up questions; rich list/block model content is normalized before JSON parsing |
@@ -477,6 +477,19 @@ Admin-configurable, **access-control-free** categories that published agents/ski
 
 Each agent/skill carries a single `square_id` column (`AgentRow` / `SkillRow`, `String(64)` NOT NULL default `''`, migration `20260611_01`, idempotent SQL in `column_additions_mysql.sql`). One column = at most one square, so an item can never be "published twice". `''` = unassigned ? resolved to the default square at read/filter time. Writes normalize via `normalize_square_id`: agents on create/update (`square_id` field), skills on publish (`PUT /api/skills/custom/{name}/published` accepts optional `square_id`). Listing filters: `GET /api/agents?square=` and `GET /api/skills?square=` keep only that square's items; the **default** square additionally sweeps in legacy `''` rows (`square_is_default`). Tests: `tests/test_publish_squares.py`. Frontend: `core/system-settings` (`usePublishSquares`/`useUpdatePublishSquares`), admin `PublishSquaresSettingsPage` (embedded in the appearance/settings hub), square picker in the agent edit dialog + per-skill card, and a ??-tab square sub-filter in both galleries.
 
+### Reference-mode Entry Switch
+
+The 参考文献/RAG citation-mode composer entry is system-controlled through
+`system_settings.json` → `citation_display.reference_mode_enabled` (default
+`false`). `GET /api/system-settings/citation-display` remains readable so the
+frontend can hide or show the entry consistently; `PUT` is admin-only and
+partially updates `reference_mode_enabled` and/or `cleanup_words`. The normal
+workspace input box, iframe chat toolbar, send context, right reference panel,
+and appearance settings all use this flag, while already locked citation
+threads and knowledge-base selections still render their references. Tests:
+`tests/test_prompt_prefix.py` and
+`frontend-web/src/pages/iframe-chat-mode-buttons.test.ts`.
+
 ### Agent Module Tag Config (zzJC / zzXD 按类型聚合)
 
 Backs the zzJC / zzXD agent-chat left sidebar (「按类型聚合智能体 + 聊天记录」). An admin picks which agent **tags** belong to a module; the module's left sidebar then shows only agents under those tags (empty/unconfigured = show all visible agents). Stored in `system_settings.json` → `agent_modules` (`AgentModuleSettings`: `modules: {module_key → [tag_id, ...]}`); pure helpers `get_module_tag_ids` / `set_module_tag_ids` (de-dupe + strip). Endpoints (in `app/gateway/routers/system_settings.py`): `GET /api/system-settings/agent-modules/{key}` (readable by any user — the sidebar needs it to filter), `PUT /api/system-settings/agent-modules/{key}` (admin only, full replacement of the tag-id list). Module keys are frontend-defined (`AGENT_MODULES` in `components/workspace/agents/agent-module-sidebar.tsx`, keyed by the module's landing agent id: `6bf`→`zzjc`, `10d69…`→`zzxd`). Tests: `tests/test_agent_modules.py`. Frontend: `core/system-settings` (`useAgentModuleConfig`/`useUpdateAgentModuleConfig`), admin `AgentModuleSettingsDialog` (gear button in the agent-chat header).
diff --git a/offline-backend-20260512/backend/README.md b/offline-backend-20260512/backend/README.md
index c23e9ad1..efef9706 100644
--- a/offline-backend-20260512/backend/README.md
+++ b/offline-backend-20260512/backend/README.md
@@ -664,6 +664,27 @@ login and theme query parameters, each shortcut may include ordered keyless
 it as an encoded path segment (including inside a `#/…` hash route); password
 remains an ordinary login query parameter with the key `password`.
 
+### Citation display settings
+
+Reference-mode entry points are controlled by `citation_display` in
+`.deer-flow/system_settings.json`. `reference_mode_enabled` defaults to `false`;
+when disabled, the frontend hides the "参考文献" composer button in both the
+normal workspace and iframe chat, and hides the per-user RAG citation toggle
+from appearance settings. `GET /api/system-settings/citation-display` is
+readable by logged-in users so the UI can decide whether to expose the entry;
+`PUT /api/system-settings/citation-display` is admin-only and supports partial
+updates for both `reference_mode_enabled` and `cleanup_words`.
+
+### Ordinary Q&A Markdown format switch
+
+Administrators can opt into the formal long-answer Markdown prompt from the
+admin "问答提示词配置" panel. The value is persisted as
+`prompt_prefix.ordinary_qa_markdown_format_enabled` in
+`.deer-flow/system_settings.json` and defaults to `false`. When enabled, only
+ordinary Q&A receives the `# 主标题` / `## 一、标题` / `### (一) 标题` /
+`#### 1. 标题` rules; writing mode, notebook mode and scheduled runs remain
+unaffected. The change takes effect when the next prompt is built.
+
 ---
 
 ## Technology Stack
diff --git a/offline-backend-20260512/backend/app/gateway/routers/system_settings.py b/offline-backend-20260512/backend/app/gateway/routers/system_settings.py
index 7d5d72a5..011cb5b7 100644
--- a/offline-backend-20260512/backend/app/gateway/routers/system_settings.py
+++ b/offline-backend-20260512/backend/app/gateway/routers/system_settings.py
@@ -42,12 +42,17 @@ class PromptPrefixResponse(BaseModel):
     enabled: bool = Field(..., description="Whether the toggle is exposed to users")
     switch_label: str = Field(..., description="Toggle label shown in the chat input")
     prompt_prefix: str = Field(..., description="Prefix text prepended to the first user message")
+    ordinary_qa_markdown_format_enabled: bool = Field(
+        default=False,
+        description="Whether formal Markdown heading rules are injected into ordinary Q&A system prompts",
+    )
 
 
 class PromptPrefixUpdateRequest(BaseModel):
     enabled: bool | None = None
     switch_label: str | None = None
     prompt_prefix: str | None = None
+    ordinary_qa_markdown_format_enabled: bool | None = None
 
 
 class PluginDomainAgentMappingItem(BaseModel):
@@ -82,10 +87,12 @@ class PrivateSquareUpdateRequest(BaseModel):
 
 
 class CitationDisplayResponse(BaseModel):
+    reference_mode_enabled: bool = Field(default=False, description="Whether reference-mode entry points are exposed to users")
     cleanup_words: list[str] = Field(default_factory=list, description="Global citation cleanup words")
 
 
 class CitationDisplayUpdateRequest(BaseModel):
+    reference_mode_enabled: bool | None = None
     cleanup_words: list[str] | None = None
 
 
@@ -110,6 +117,7 @@ def _to_response(settings: PromptPrefixSettings) -> PromptPrefixResponse:
         enabled=settings.enabled,
         switch_label=settings.switch_label,
         prompt_prefix=settings.prompt_prefix,
+        ordinary_qa_markdown_format_enabled=settings.ordinary_qa_markdown_format_enabled,
     )
 
 
@@ -410,9 +418,12 @@ async def update_leaderboard_settings(
 
 @router.get("/citation-display", response_model=CitationDisplayResponse)
 async def get_citation_display() -> CitationDisplayResponse:
-    """Return global citation display cleanup settings."""
+    """Return global citation display settings."""
     settings = load_system_settings().citation_display
-    return CitationDisplayResponse(cleanup_words=settings.cleanup_words)
+    return CitationDisplayResponse(
+        reference_mode_enabled=settings.reference_mode_enabled,
+        cleanup_words=settings.cleanup_words,
+    )
 
 
 @router.put("/citation-display", response_model=CitationDisplayResponse)
@@ -420,14 +431,22 @@ async def update_citation_display(
     body: CitationDisplayUpdateRequest,
     request: Request,
 ) -> CitationDisplayResponse:
-    """Update global citation display cleanup settings. Admin only."""
+    """Update global citation display settings. Admin only."""
     await _require_admin(request)
 
     current = load_system_settings()
-    words = [str(item).strip() for item in (body.cleanup_words or []) if str(item).strip()]
-    updated = current.citation_display.model_copy(update={"cleanup_words": words})
+    fields = body.model_dump(exclude_unset=True)
+    update: dict[str, object] = {}
+    if "reference_mode_enabled" in fields and fields["reference_mode_enabled"] is not None:
+        update["reference_mode_enabled"] = bool(fields["reference_mode_enabled"])
+    if "cleanup_words" in fields and fields["cleanup_words"] is not None:
+        update["cleanup_words"] = [str(item).strip() for item in fields["cleanup_words"] if str(item).strip()]
+    updated = current.citation_display.model_copy(update=update)
     saved = save_system_settings(current.model_copy(update={"citation_display": updated}))
-    return CitationDisplayResponse(cleanup_words=saved.citation_display.cleanup_words)
+    return CitationDisplayResponse(
+        reference_mode_enabled=saved.citation_display.reference_mode_enabled,
+        cleanup_words=saved.citation_display.cleanup_words,
+    )
 
 
 @router.get("/private-square", response_model=PrivateSquareStatusResponse)
diff --git a/offline-backend-20260512/backend/packages/harness/deerflow/agents/lead_agent/prompt.py b/offline-backend-20260512/backend/packages/harness/deerflow/agents/lead_agent/prompt.py
index cb556124..62fb2549 100644
--- a/offline-backend-20260512/backend/packages/harness/deerflow/agents/lead_agent/prompt.py
+++ b/offline-backend-20260512/backend/packages/harness/deerflow/agents/lead_agent/prompt.py
@@ -7,10 +7,11 @@ import threading
 from datetime import datetime
 from functools import lru_cache
 from typing import TYPE_CHECKING
-from zoneinfo import ZoneInfo
-
-from deerflow.config.agents_config import load_agent_soul
-from deerflow.skills.storage import get_or_new_skill_storage
+from zoneinfo import ZoneInfo
+
+from deerflow.config.agents_config import load_agent_soul
+from deerflow.config.system_settings import load_system_settings
+from deerflow.skills.storage import get_or_new_skill_storage
 from deerflow.skills.types import Skill, SkillCategory
 from deerflow.subagents import get_available_subagent_names
 
@@ -498,6 +499,21 @@ _ORDINARY_QA_MARKDOWN_FORMAT_SECTION = """
 """
 
 
+def _ordinary_qa_markdown_format_enabled() -> bool:
+    """Return the admin-controlled formal Markdown prompt switch.
+
+    Reading the small runtime settings document for each prompt build makes an
+    administrator's change effective for the next run without a process-level
+    cache or restart. Any missing/invalid setting safely falls back to off.
+    """
+
+    try:
+        return bool(load_system_settings().prompt_prefix.ordinary_qa_markdown_format_enabled)
+    except Exception:
+        logger.debug("Failed to read the ordinary Q&A Markdown format switch; using disabled", exc_info=True)
+        return False
+
+
 SYSTEM_PROMPT_TEMPLATE = """
 <role>
 You are {agent_name}, an internal super agent.
@@ -1545,7 +1561,11 @@ When a search, knowledge, skill, or MCP tool returns a result list:
     )
     ordinary_qa_format_section = (
         _ORDINARY_QA_MARKDOWN_FORMAT_SECTION
-        if not is_bootstrap and not writing_mode and not is_notebook_mode and not is_scheduled_run
+        if _ordinary_qa_markdown_format_enabled()
+        and not is_bootstrap
+        and not writing_mode
+        and not is_notebook_mode
+        and not is_scheduled_run
         else ""
     )
 
diff --git a/offline-backend-20260512/backend/packages/harness/deerflow/config/system_settings.py b/offline-backend-20260512/backend/packages/harness/deerflow/config/system_settings.py
index 5cb8e139..cbfa0257 100644
--- a/offline-backend-20260512/backend/packages/harness/deerflow/config/system_settings.py
+++ b/offline-backend-20260512/backend/packages/harness/deerflow/config/system_settings.py
@@ -153,6 +153,10 @@ class PromptPrefixSettings(BaseModel):
     enabled: bool = Field(default=False, description="Whether the prefix toggle is offered to users at all")
     switch_label: str = Field(default="加入立场前缀", description="Toggle label shown in the chat input")
     prompt_prefix: str = Field(default="", description="Text prepended to the first user message when enabled")
+    ordinary_qa_markdown_format_enabled: bool = Field(
+        default=False,
+        description="Whether the formal Markdown heading rules are injected into ordinary Q&A system prompts.",
+    )
     model_config = ConfigDict(extra="ignore")
 
 
@@ -255,8 +259,12 @@ class AppearanceSettings(BaseModel):
 
 
 class CitationDisplaySettings(BaseModel):
-    """System-wide cleanup rules for citation cards and detail dialogs."""
+    """System-wide controls for citation mode entry and display cleanup."""
 
+    reference_mode_enabled: bool = Field(
+        default=False,
+        description="Whether the reference-mode entry points are exposed to users.",
+    )
     cleanup_words: list[str] = Field(
         default_factory=list,
         description="Words or phrases used to remove noisy advertisement/disclaimer lines from citation display.",
diff --git a/offline-backend-20260512/backend/tests/test_es_query_routing_prompt.py b/offline-backend-20260512/backend/tests/test_es_query_routing_prompt.py
index e11728ae..18c3b18e 100644
--- a/offline-backend-20260512/backend/tests/test_es_query_routing_prompt.py
+++ b/offline-backend-20260512/backend/tests/test_es_query_routing_prompt.py
@@ -112,6 +112,7 @@ def test_es_query_routing_registration_log_explains_custom_agent_exclusion(caplo
 
 def test_formal_markdown_rules_are_scoped_to_ordinary_qa(monkeypatch) -> None:
     config = _app_config(enabled=False)
+    monkeypatch.setattr(prompt_module, "_ordinary_qa_markdown_format_enabled", lambda: True)
     monkeypatch.setattr(prompt_module, "_get_memory_context", lambda *args, **kwargs: "")
     monkeypatch.setattr(prompt_module, "get_agent_soul", lambda *args, **kwargs: "")
     monkeypatch.setattr(prompt_module, "get_skills_prompt_section", lambda *args, **kwargs: "")
@@ -134,3 +135,19 @@ def test_formal_markdown_rules_are_scoped_to_ordinary_qa(monkeypatch) -> None:
     assert '<ordinary_qa_markdown_format>' not in writing_prompt
     assert '<ordinary_qa_markdown_format>' not in notebook_prompt
     assert '<ordinary_qa_markdown_format>' not in scheduled_prompt
+
+
+def test_formal_markdown_rules_are_disabled_when_switch_is_off(monkeypatch) -> None:
+    config = _app_config(enabled=False)
+    monkeypatch.setattr(prompt_module, "_ordinary_qa_markdown_format_enabled", lambda: False)
+    monkeypatch.setattr(prompt_module, "_get_memory_context", lambda *args, **kwargs: "")
+    monkeypatch.setattr(prompt_module, "get_agent_soul", lambda *args, **kwargs: "")
+    monkeypatch.setattr(prompt_module, "get_skills_prompt_section", lambda *args, **kwargs: "")
+    monkeypatch.setattr(prompt_module, "get_deferred_tools_prompt_section", lambda *args, **kwargs: "")
+    monkeypatch.setattr(prompt_module, "_build_acp_section", lambda *args, **kwargs: "")
+    monkeypatch.setattr(prompt_module, "_build_custom_mounts_section", lambda *args, **kwargs: "")
+    monkeypatch.setattr(prompt_module, "_current_time_context", lambda: "")
+
+    ordinary_prompt = prompt_module.apply_prompt_template(app_config=config)
+
+    assert '<ordinary_qa_markdown_format>' not in ordinary_prompt
diff --git a/offline-backend-20260512/backend/tests/test_prompt_prefix.py b/offline-backend-20260512/backend/tests/test_prompt_prefix.py
index ce790e52..e87898ed 100644
--- a/offline-backend-20260512/backend/tests/test_prompt_prefix.py
+++ b/offline-backend-20260512/backend/tests/test_prompt_prefix.py
@@ -9,7 +9,9 @@ from types import SimpleNamespace
 import pytest
 from langchain_core.messages import AIMessage, HumanMessage
 
+from app.gateway.routers import system_settings as ss_router
 from app.gateway.services import _prepend_prompt_prefix, _prompt_prefix_opted_in
+from deerflow.agents.lead_agent import prompt as prompt_module
 from deerflow.config import system_settings as ss
 
 
@@ -28,6 +30,9 @@ def test_load_returns_defaults_when_missing(tmp_runtime_home: Path) -> None:
     settings = ss.load_system_settings()
     assert settings.prompt_prefix.enabled is False
     assert settings.prompt_prefix.prompt_prefix == ""
+    assert settings.prompt_prefix.ordinary_qa_markdown_format_enabled is False
+    assert settings.citation_display.reference_mode_enabled is False
+    assert settings.citation_display.cleanup_words == []
 
 
 def test_save_then_load_roundtrips(tmp_runtime_home: Path) -> None:
@@ -36,6 +41,7 @@ def test_save_then_load_roundtrips(tmp_runtime_home: Path) -> None:
             enabled=True,
             switch_label="加入立场前缀",
             prompt_prefix="你需要站在中方角度",
+            ordinary_qa_markdown_format_enabled=True,
         )
     )
     ss.save_system_settings(settings)
@@ -49,6 +55,88 @@ def test_save_then_load_roundtrips(tmp_runtime_home: Path) -> None:
     assert reloaded.prompt_prefix.enabled is True
     assert reloaded.prompt_prefix.switch_label == "加入立场前缀"
     assert reloaded.prompt_prefix.prompt_prefix == "你需要站在中方角度"
+    assert reloaded.prompt_prefix.ordinary_qa_markdown_format_enabled is True
+
+
+def test_runtime_markdown_format_switch_defaults_off_and_updates_without_restart(
+    tmp_runtime_home: Path,
+) -> None:
+    assert prompt_module._ordinary_qa_markdown_format_enabled() is False
+
+    ss.save_system_settings(
+        ss.SystemSettings(
+            prompt_prefix=ss.PromptPrefixSettings(
+                ordinary_qa_markdown_format_enabled=True,
+            )
+        )
+    )
+
+    assert prompt_module._ordinary_qa_markdown_format_enabled() is True
+
+
+def _patch_admin(monkeypatch: pytest.MonkeyPatch) -> None:
+    admin = SimpleNamespace(
+        id="admin1",
+        system_role="admin",
+        email="admin@example.com",
+    )
+
+    async def _optional(_request):
+        return admin
+
+    monkeypatch.setattr(ss_router, "get_optional_user_from_request", _optional)
+
+
+@pytest.mark.asyncio
+async def test_prompt_settings_update_can_enable_markdown_format_without_changing_prefix(
+    tmp_runtime_home: Path,
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    _patch_admin(monkeypatch)
+    current = ss.SystemSettings(
+        prompt_prefix=ss.PromptPrefixSettings(
+            enabled=True,
+            switch_label="加入立场前缀",
+            prompt_prefix="你需要站在中方角度",
+        )
+    )
+    ss.save_system_settings(current)
+
+    response = await ss_router.update_prompt_prefix(
+        ss_router.PromptPrefixUpdateRequest(ordinary_qa_markdown_format_enabled=True),
+        SimpleNamespace(),
+    )
+
+    assert response.ordinary_qa_markdown_format_enabled is True
+    assert response.enabled is True
+    assert response.switch_label == "加入立场前缀"
+    assert response.prompt_prefix == "你需要站在中方角度"
+
+
+@pytest.mark.asyncio
+async def test_citation_display_update_preserves_unspecified_fields(
+    tmp_runtime_home: Path,
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    _patch_admin(monkeypatch)
+    current = ss.SystemSettings(
+        citation_display=ss.CitationDisplaySettings(
+            cleanup_words=["广告", "免责声明"],
+        )
+    )
+    ss.save_system_settings(current)
+
+    response = await ss_router.update_citation_display(
+        ss_router.CitationDisplayUpdateRequest(reference_mode_enabled=True),
+        SimpleNamespace(),
+    )
+
+    assert response.reference_mode_enabled is True
+    assert response.cleanup_words == ["广告", "免责声明"]
+
+    payload = json.loads((tmp_runtime_home / "system_settings.json").read_text(encoding="utf-8"))
+    assert payload["citation_display"]["reference_mode_enabled"] is True
+    assert payload["citation_display"]["cleanup_words"] == ["广告", "免责声明"]
 
 
 def test_prepend_prefix_tags_first_human_without_touching_content() -> None:

From 8e0d755b5778286c1e4eb77d7fa8e4f5335e4d63 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E5=90=89=E9=91=AB=E5=8D=87?= <xsji@kland.com.cn>
Date: Mon, 31 Aug 2026 18:02:05 +0800
Subject: [PATCH 2/2] fix: preserve knowledge base references

---
 .../src/components/workspace/chats/chat-box.tsx  | 11 ++++++++---
 .../src/components/workspace/messages/context.ts | 16 +++++++++++-----
 .../workspace/messages/message-list.tsx          |  5 ++++-
 frontend-web/src/pages/AgentChatPage.tsx         |  8 +++++++-
 frontend-web/src/pages/ChatPage.tsx              |  9 ++++++++-
 offline-backend-20260512/backend/CLAUDE.md       |  3 ++-
 offline-backend-20260512/backend/README.md       |  4 +++-
 7 files changed, 43 insertions(+), 13 deletions(-)

diff --git a/frontend-web/src/components/workspace/chats/chat-box.tsx b/frontend-web/src/components/workspace/chats/chat-box.tsx
index 8de0d29a..5687a78f 100644
--- a/frontend-web/src/components/workspace/chats/chat-box.tsx
+++ b/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 =
diff --git a/frontend-web/src/components/workspace/messages/context.ts b/frontend-web/src/components/workspace/messages/context.ts
index d22189c7..65f3a626 100644
--- a/frontend-web/src/components/workspace/messages/context.ts
+++ b/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.
diff --git a/frontend-web/src/components/workspace/messages/message-list.tsx b/frontend-web/src/components/workspace/messages/message-list.tsx
index 15d83aff..e5cae494 100644
--- a/frontend-web/src/components/workspace/messages/message-list.tsx
+++ b/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(
diff --git a/frontend-web/src/pages/AgentChatPage.tsx b/frontend-web/src/pages/AgentChatPage.tsx
index 20774b4f..80f9595b 100644
--- a/frontend-web/src/pages/AgentChatPage.tsx
+++ b/frontend-web/src/pages/AgentChatPage.tsx
@@ -779,7 +779,13 @@ export default function AgentChatPage({
       : "ready";
 
   return (
-    <ThreadContext.Provider value={{ thread: displayThread }}>
+    <ThreadContext.Provider
+      value={{
+        thread: displayThread,
+        knowledgeReferencesEnabled:
+          knowledgeSelectionReady && selectedKnowledgeBaseIds.length > 0,
+      }}
+    >
       {/* Root: fixed-height horizontal split. ChatBox (chat + artifact
           preview) lives in the left flex cell; the agent detail panel is a
           separate flex sibling OUTSIDE ChatBox, so the artifact preview
diff --git a/frontend-web/src/pages/ChatPage.tsx b/frontend-web/src/pages/ChatPage.tsx
index c52559cf..2a7a93a7 100644
--- a/frontend-web/src/pages/ChatPage.tsx
+++ b/frontend-web/src/pages/ChatPage.tsx
@@ -688,7 +688,14 @@ export default function ChatPage() {
     !isWujieEnv();
 
   return (
-    <ThreadContext.Provider value={{ thread: displayThread, isMock }}>
+    <ThreadContext.Provider
+      value={{
+        thread: displayThread,
+        isMock,
+        knowledgeReferencesEnabled:
+          knowledgeSelectionReady && selectedKnowledgeBaseIds.length > 0,
+      }}
+    >
       <ChatBox threadId={threadId}>
         <div
           className={cn(
diff --git a/offline-backend-20260512/backend/CLAUDE.md b/offline-backend-20260512/backend/CLAUDE.md
index de8b34c5..93cd1461 100644
--- a/offline-backend-20260512/backend/CLAUDE.md
+++ b/offline-backend-20260512/backend/CLAUDE.md
@@ -486,7 +486,8 @@ frontend can hide or show the entry consistently; `PUT` is admin-only and
 partially updates `reference_mode_enabled` and/or `cleanup_words`. The normal
 workspace input box, iframe chat toolbar, send context, right reference panel,
 and appearance settings all use this flag, while already locked citation
-threads and knowledge-base selections still render their references. Tests:
+threads and selected LLMWiki knowledge bases still render their source
+documents in the reference panel. Tests:
 `tests/test_prompt_prefix.py` and
 `frontend-web/src/pages/iframe-chat-mode-buttons.test.ts`.
 
diff --git a/offline-backend-20260512/backend/README.md b/offline-backend-20260512/backend/README.md
index efef9706..584ce987 100644
--- a/offline-backend-20260512/backend/README.md
+++ b/offline-backend-20260512/backend/README.md
@@ -670,7 +670,9 @@ Reference-mode entry points are controlled by `citation_display` in
 `.deer-flow/system_settings.json`. `reference_mode_enabled` defaults to `false`;
 when disabled, the frontend hides the "参考文献" composer button in both the
 normal workspace and iframe chat, and hides the per-user RAG citation toggle
-from appearance settings. `GET /api/system-settings/citation-display` is
+from appearance settings. Conversations with selected LLMWiki knowledge bases
+still show their source documents in the reference panel even when the manual
+entry is hidden. `GET /api/system-settings/citation-display` is
 readable by logged-in users so the UI can decide whether to expose the entry;
 `PUT /api/system-settings/citation-display` is admin-only and supports partial
 updates for both `reference_mode_enabled` and `cleanup_words`.