feat: add fixed questions and improve authentication

.gitignore

@@ -93,6 +93,8 @@ offline-backend-20260512/backend/tests/*
 # Keep the model configuration regression coverage versioned even though
 # this deployment repository otherwise ignores newly added backend tests.
 !offline-backend-20260512/backend/tests/test_model_management.py
+# Keep fixed-question exact-match and streaming regression coverage versioned.
+!offline-backend-20260512/backend/tests/test_fixed_questions.py
 deploy
 .history
 

frontend-web/src/App.tsx

@@ -102,16 +102,17 @@ function AppProviders({ children }: { children: React.ReactNode }) {
       forcedTheme={forcedTheme}
     >
       <QueryClientProvider>
-        <I18nProvider initialLocale={locale}>
-          <ThemeProvider>
-            <ChatProvider>
-              {!positionStandaloneMode && <AuthSyncWatcher />}
-              {!positionStandaloneMode && <DesensitizeWordsLoader />}
-              <FontScaleApplier />
-              {children}
-            </ChatProvider>
-          </ThemeProvider>
-        </I18nProvider>
+        <AuthSyncWatcher disabled={positionStandaloneMode}>
+          <I18nProvider initialLocale={locale}>
+            <ThemeProvider>
+              <ChatProvider>
+                {!positionStandaloneMode && <DesensitizeWordsLoader />}
+                <FontScaleApplier />
+                {children}
+              </ChatProvider>
+            </ThemeProvider>
+          </I18nProvider>
+        </AuthSyncWatcher>
       </QueryClientProvider>
     </NextThemesProvider>
   );

frontend-web/src/components/page-sidebar.tsx

@@ -10,6 +10,7 @@ import {
   FolderOpen,
   Gauge,
   ListTree,
+  MessageSquareText,
   MousePointerClick,
   BriefcaseBusiness,
   Settings,
@@ -237,6 +238,14 @@ function SecondaryNavSidebar({ headerHidden }: { headerHidden: boolean }) {
                       按钮管理
                     </DropdownMenuItem>
                   )}
+                  {isAdmin && (
+                    <DropdownMenuItem
+                      onClick={() => navigate("/page/strategy/admin/fixed-questions")}
+                    >
+                      <MessageSquareText className="size-4" />
+                      问题配置
+                    </DropdownMenuItem>
+                  )}
                   {isAdmin && (
                     <DropdownMenuItem
                       onClick={() => navigate("/page/strategy/admin/position-roles")}
@@ -558,6 +567,12 @@ function LegacyAccordionSidebar({
                   按钮管理
                 </DropdownMenuItem>
               )}
+              {isAdmin && (
+                <DropdownMenuItem onClick={() => navigate("/page/strategy/admin/fixed-questions")}>
+                  <MessageSquareText className="size-4" />
+                  问题配置
+                </DropdownMenuItem>
+              )}
               {isAdmin && (
                 <DropdownMenuItem onClick={() => navigate("/page/strategy/admin/position-roles")}>
                   <BriefcaseBusiness className="size-4" />

frontend-web/src/components/workspace/llmwiki-knowledge-selector.tsx

@@ -76,6 +76,7 @@ function SelectionContent({
   error,
   source,
   variant,
+  readOnly,
 }: {
   rows: LlmWikiKnowledgeBase[];
   value: string[];
@@ -86,6 +87,7 @@ function SelectionContent({
   error: unknown;
   source: SelectorSource;
   variant: SelectorVariant;
+  readOnly: boolean;
 }) {
   const selected = useMemo(() => new Set(value), [value]);
   const filtered = useMemo(() => {
@@ -97,6 +99,7 @@ function SelectionContent({
   }, [rows, search]);
   const groups = useMemo(() => groupRows(filtered), [filtered]);
   const toggle = (id: string) => {
+    if (readOnly) return;
     onChange(selected.has(id) ? value.filter((item) => item !== id) : [...value, id]);
   };
 
@@ -168,6 +171,7 @@ function SelectionContent({
                   <DropdownMenuCheckboxItem
                     key={item.id}
                     checked={selected.has(item.id)}
+                    disabled={readOnly}
                     onCheckedChange={() => toggle(item.id)}
                     onSelect={(event) => event.preventDefault()}
                     className={cn(
@@ -183,6 +187,7 @@ function SelectionContent({
                     type="button"
                     role="checkbox"
                     aria-checked={selected.has(item.id)}
+                    disabled={readOnly}
                     onClick={() => toggle(item.id)}
                     className={cn(
                       "my-0.5 flex min-h-11 w-full items-center gap-2 rounded-md px-2 py-1.5 text-left outline-none transition-colors hover:bg-muted/60 focus-visible:ring-2 focus-visible:ring-primary",
@@ -205,15 +210,21 @@ function SelectionContent({
       </div>
 
       <div className="flex items-center justify-between gap-2 border-t bg-muted/20 px-2.5 py-2">
-        <span className="text-[11px] text-muted-foreground">已选择 {value.length} 个</span>
-        <div className="flex items-center gap-1">
-          <Button type="button" variant="ghost" size="sm" className="h-7 px-2 text-xs" onClick={() => onChange(filtered.map((item) => item.id))}>
-            全选
-          </Button>
-          <Button type="button" variant="ghost" size="sm" className="h-7 px-2 text-xs" onClick={() => onChange([])}>
-            清空
-          </Button>
-        </div>
+        <span className="text-[11px] text-muted-foreground">
+          {readOnly ? `本对话已选 ${value.length} 个` : `已选择 ${value.length} 个`}
+        </span>
+        {readOnly ? (
+          <span className="text-[11px] text-muted-foreground">对话开始后不可更改</span>
+        ) : (
+          <div className="flex items-center gap-1">
+            <Button type="button" variant="ghost" size="sm" className="h-7 px-2 text-xs" onClick={() => onChange(filtered.map((item) => item.id))}>
+              全选
+            </Button>
+            <Button type="button" variant="ghost" size="sm" className="h-7 px-2 text-xs" onClick={() => onChange([])}>
+              清空
+            </Button>
+          </div>
+        )}
       </div>
     </>
   );
@@ -226,6 +237,7 @@ export function LlmWikiKnowledgeSelector({
   agentId,
   autoSelectAll = false,
   disabled = false,
+  readOnly = false,
   className,
   label = "知识空间",
   variant = "popover",
@@ -236,6 +248,8 @@ export function LlmWikiKnowledgeSelector({
   agentId?: string | null;
   autoSelectAll?: boolean;
   disabled?: boolean;
+  /** Keep the selected knowledge spaces visible without allowing the thread scope to change. */
+  readOnly?: boolean;
   className?: string;
   label?: string;
   variant?: SelectorVariant;
@@ -293,6 +307,7 @@ export function LlmWikiKnowledgeSelector({
       error={error}
       source={source}
       variant={variant}
+      readOnly={readOnly}
     />
   );
 
@@ -315,9 +330,14 @@ export function LlmWikiKnowledgeSelector({
     );
   }
 
-  const selectedName = value.length === 1
-    ? rows.find((item) => item.id === value[0])?.name
-    : null;
+  const selectedNames = value
+    .map((id) => rows.find((item) => item.id === id)?.name)
+    .filter((name): name is string => !!name);
+  const selectedLabel = selectedNames.length > 0
+    ? selectedNames.join("、")
+    : value.length > 0
+      ? `已选 ${value.length} 个知识空间`
+      : label;
 
   return (
     <DropdownMenu open={open} onOpenChange={setOpen}>
@@ -332,9 +352,10 @@ export function LlmWikiKnowledgeSelector({
             className,
           )}
           disabled={disabled || loading}
+          title={value.length > 0 ? selectedLabel : undefined}
         >
           {loading ? <Loader2 className="size-3.5 animate-spin" /> : <Database className="size-3.5" />}
-          <span className="truncate text-xs font-normal">{selectedName || label}</span>
+          <span className="truncate text-xs font-normal">{selectedLabel}</span>
           {value.length > 0 && (
             <span className="flex size-4 items-center justify-center rounded-full bg-primary text-[9px] font-semibold text-primary-foreground">
               {value.length}

frontend-web/src/components/workspace/workspace-nav-menu.tsx

@@ -11,6 +11,7 @@ import {
   GaugeIcon,
   HistoryIcon,
   MessageCircleQuestionIcon,
+  MessageSquareTextIcon,
   ScrollTextIcon,
   Settings2Icon,
   SettingsIcon,
@@ -268,6 +269,16 @@ export function WorkspaceNavMenu() {
                       推荐问题配置
                     </DropdownMenuItem>
                   )}
+                  {isAdmin && (
+                    <DropdownMenuItem
+                      onClick={() =>
+                        navigate("/page/strategy/admin/fixed-questions")
+                      }
+                    >
+                      <MessageSquareTextIcon />
+                      问题配置
+                    </DropdownMenuItem>
+                  )}
                   {isAdmin && logSystem?.enabled && logSystem.url && (
                     <DropdownMenuItem
                       onClick={() =>

frontend-web/src/core/auth/index.ts

@@ -49,6 +49,17 @@ function normalizeIdentityPart(value: unknown): string {
   return typeof value === "string" ? value.trim().toLowerCase() : "";
 }
 
+function identityFromLoginName(value: unknown): string | null {
+  const normalized = normalizeIdentityPart(value);
+  if (!normalized) return null;
+  // Explicit email login is domain-specific. Bare username login is the
+  // stable business principal even if the backend's synthetic email domain or
+  // internal UUID changes.
+  return normalized.includes("@")
+    ? `email:${normalized}`
+    : `account:${normalized}`;
+}
+
 function readUserInfoIdentity(): string | null {
   let info: Record<string, unknown> | null = null;
   try {
@@ -81,20 +92,24 @@ function readUserInfoIdentity(): string | null {
 /**
  * A stable cross-tab identity key for "did the account really change?" checks.
  *
- * Some external login paths can re-issue a backend ``user_id`` while resolving
- * to the same business account. Prefer business-facing identifiers
- * (email/username/userInfo) and keep ``user_id`` only as the final fallback.
+ * Some external login paths can re-issue a backend ``user_id`` or use a
+ * different synthetic email domain while resolving to the same business
+ * account. Prefer the raw login username returned by the backend, then the
+ * email local-part, and keep ``user_id`` only as the final fallback.
  */
 export function getAccountIdentityKey(
   auth: LoginByUsernameResponse | null = getStoredAuth(),
 ): string | null {
   if (!auth) return null;
 
-  const email = normalizeIdentityPart(auth.email);
-  if (email) return `email:${email}`;
+  const loginIdentity = identityFromLoginName(auth.username);
+  if (loginIdentity) return loginIdentity;
 
-  const username = normalizeIdentityPart(auth.username);
-  if (username) return `username:${username}`;
+  const email = normalizeIdentityPart(auth.email);
+  if (email) {
+    const localPart = email.split("@", 1)[0];
+    return localPart ? `account:${localPart}` : `email:${email}`;
+  }
 
   const userInfoIdentity = readUserInfoIdentity();
   if (userInfoIdentity) return `userInfo:${userInfoIdentity}`;

frontend-web/src/core/auth/sync.tsx

@@ -1,9 +1,15 @@
 "use client";
 
-import { useEffect, useRef } from "react";
+import { Fragment, useEffect, useRef, useState, type ReactNode } from "react";
+import { useLocation, useNavigate } from "react-router-dom";
+import { useQueryClient } from "@tanstack/react-query";
 import { toast } from "sonner";
 
-import { getAccountIdentityKey } from "@/core/auth";
+import {
+  AUTH_STATE_CHANGED_EVENT,
+  getAccountDisplayName,
+  getAccountIdentityKey,
+} from "@/core/auth";
 import { isEmbedActive, isIsolatedSession } from "@/core/embed/embed-session";
 
 const AUTH_STORAGE_KEY = "deerflow.auth";
@@ -14,14 +20,37 @@ function readIdentityKey(): string | null {
   return getAccountIdentityKey();
 }
 
+function freshRouteForAccount(pathname: string): string {
+  // A thread URL belongs to the old account. Keep its workspace/agent context
+  // but move to a valid new conversation before the user can submit into the
+  // stale thread. Other pages can stay in place and are remounted below.
+  const chatMatch = pathname.match(/^(.*\/chats)\/[^/]+\/?$/);
+  return chatMatch ? `${chatMatch[1]}/new` : pathname;
+}
+
 /**
- * Mount once at the app root. Watches localStorage auth changes from other
- * tabs and lets the user decide when to refresh on account switches.
+ * Cross-tab auth boundary for normal pages.
+ *
+ * Same-account token re-issuance is ignored. A genuine account change clears
+ * account-scoped query state, remounts the page, and moves an open chat to its
+ * fresh-chat route without a full browser reload. Embedded/isolated tabs keep
+ * their sessionStorage identity and never participate in this synchronization.
  */
-export function AuthSyncWatcher() {
+export function AuthSyncWatcher({
+  children,
+  disabled = false,
+}: {
+  children?: ReactNode;
+  disabled?: boolean;
+}) {
   const lastIdentityRef = useRef<string | null>(readIdentityKey());
+  const [revision, setRevision] = useState(0);
+  const queryClient = useQueryClient();
+  const navigate = useNavigate();
+  const location = useLocation();
 
   useEffect(() => {
+    if (disabled) return;
     // 嵌入(iframe)态 / 独立会话态(?isolate=1)：鉴权走按标签页的 sessionStorage，本就不与其它标签页
     // 共享，且不应被其它标签页的 localStorage 账号变更打扰 —— 直接不挂跨标签监听。
     if (isEmbedActive() || isIsolatedSession()) return;
@@ -36,18 +65,27 @@ export function AuthSyncWatcher() {
 
       lastIdentityRef.current = nextIdentity;
 
+      void queryClient.cancelQueries();
+      queryClient.clear();
+      window.dispatchEvent(new Event(AUTH_STATE_CHANGED_EVENT));
+      setRevision((value) => value + 1);
+
       if (nextIdentity === null) {
+        toast.info("账号已在其它页面退出", {
+          id: IDENTITY_TOAST_ID,
+          description: "当前页面已同步退出状态。",
+        });
+        navigate("/login", { replace: true });
         return;
       }
 
-      toast.warning("检测到账号在其它标签页发生变化", {
+      const freshRoute = freshRouteForAccount(location.pathname);
+      if (freshRoute !== location.pathname) {
+        navigate(freshRoute, { replace: true });
+      }
+      toast.info("账号已在页面间自动同步", {
         id: IDENTITY_TOAST_ID,
-        description: "当前标签页仍是原会话。如需与新账号同步,请刷新页面。",
-        duration: Infinity,
-        action: {
-          label: "刷新同步",
-          onClick: () => window.location.reload(),
-        },
+        description: `当前账号：${getAccountDisplayName()}。无需刷新页面。`,
       });
     }
 
@@ -68,14 +106,24 @@ export function AuthSyncWatcher() {
       settleTimer = setTimeout(evaluateSettledIdentity, SETTLE_DELAY_MS);
     }
 
+    function handleSameTabAuthChange() {
+      // `storage` never fires in the tab that called setStoredAuth/clearStoredAuth.
+      // Keep the comparison baseline current so a later same-account token
+      // renewal from another normal page is not compared with the pre-login
+      // `null` identity and falsely classified as an account switch.
+      lastIdentityRef.current = readIdentityKey();
+    }
+
     window.addEventListener("storage", handleStorage);
+    window.addEventListener(AUTH_STATE_CHANGED_EVENT, handleSameTabAuthChange);
     return () => {
       window.removeEventListener("storage", handleStorage);
+      window.removeEventListener(AUTH_STATE_CHANGED_EVENT, handleSameTabAuthChange);
       if (settleTimer) {
         clearTimeout(settleTimer);
       }
     };
-  }, []);
+  }, [disabled, location.pathname, navigate, queryClient]);
 
-  return null;
+  return children ? <Fragment key={revision}>{children}</Fragment> : null;
 }

frontend-web/src/core/auth/use-live-account.ts

@@ -8,7 +8,7 @@ import {
   getAccountIdentityKey,
   getStoredAuth,
 } from "@/core/auth";
-import { isEmbedActive } from "@/core/embed/embed-session";
+import { isEmbedActive, isIsolatedSession } from "@/core/embed/embed-session";
 
 const AUTH_STORAGE_KEY = "deerflow.auth";
 
@@ -65,7 +65,9 @@ export function useLiveAccount(): LiveAccount {
         refresh();
       }
     }
-    if (!isEmbedActive()) {
+    // Normal pages share localStorage identity across tabs. Embedded and
+    // isolated pages deliberately keep their per-tab sessionStorage identity.
+    if (!isEmbedActive() && !isIsolatedSession()) {
       window.addEventListener("storage", onStorage);
     }
     window.addEventListener(AUTH_STATE_CHANGED_EVENT, refresh);

frontend-web/src/core/threads/hooks.ts

@@ -696,17 +696,15 @@ export function useThreadStream({
         }
         return;
       }
-      // A "thread not found" 404 almost always means the URL points at a
-      // thread from a previous login session — either this tab outlived a
-      // logout/re-login or the thread genuinely belongs to a different user.
-      // Re-frame the error around the *current* logged-in identity and bounce
-      // the user to a fresh chat instead of leaving them stuck on the stale
-      // route looking at a raw HTTP 404.
-      if (isThreadNotAccessibleError(message)) {
-        const userLabel = buildCurrentUserLabel();
-        toast.info(
-          `当前登录用户为 ${userLabel}，原对话不存在或无权访问，正在为你刷新页面…`,
-        );
+      // A "thread not found" 404 means this route cannot accept another turn.
+      // Move to a fresh chat without a full browser reload; the old reload path
+      // made every click look like a crash and could loop indefinitely when a
+      // different tab's cookie kept overriding this tab's Bearer token.
+      if (isThreadNotAccessibleError(message)) {
+        const userLabel = buildCurrentUserLabel();
+        toast.info(
+          `当前登录用户为 ${userLabel}，原对话不存在或无权访问，已为你打开新对话。`,
+        );
         // Prefer staying inside an agent chat context when the user is on an
         // agent thread URL — otherwise fall back to the global new chat.
         const hash = typeof window !== "undefined" ? window.location.hash : "";
@@ -717,18 +715,7 @@ export function useThreadStream({
           : iframeMatch
             ? "/page/workspace/chats_iframe/new"
             : "/page/workspace/chats/new";
-        // First navigate to a safe URL so the post-reload page lands on a
-        // valid route. Then full-reload so TanStack Query cache, context
-        // providers and any other state captured under the previous user's
-        // identity get rebuilt against the current login.
-        if (typeof window !== "undefined") {
-          window.location.hash = target;
-          window.setTimeout(() => {
-            window.location.reload();
-          }, 900);
-        } else {
-          navigate(target, { replace: true });
-        }
+        navigate(target, { replace: true });
         return;
       }
       // 上一轮还没结束又发了新问题（409）或并发达到上限（429）：

frontend-web/src/core/threads/thread-access-error.ts

@@ -13,8 +13,9 @@ import { getStoredAuth } from "@/core/auth";
  * 404 just leaves the user staring at a scary error. Both the chat stream
  * (``core/threads/hooks.ts``) and the AI-writing stream
  * (``open-canvas/contexts/AIWritingContext.tsx``) funnel their stream errors
- * through here so the UX is identical: detect the login-change 404 and prompt
- * the user to refresh against the current identity instead of erroring out.
+ * through here so the UX is identical: detect the login-change 404 and reset
+ * the stale in-memory session against the current identity instead of showing
+ * a raw error or reloading the browser page.
  */
 
 /** Normalize an unknown stream error into a human-readable message string. */
@@ -77,22 +78,15 @@ export function buildCurrentUserLabel(): string {
 }
 
 /**
- * Re-frame a login-change 404 around the current identity and reload the page.
+ * Re-frame a login-change 404 around the current identity and reset its view.
  *
- * Shows a friendly toast naming the current login, then full-reloads after a
- * short delay so the toast is visible and so TanStack Query cache / context
- * providers / any state captured under the previous user get rebuilt against
- * the current login. Used by streams whose session id lives in component state
- * (not the URL) — a plain reload lands them back on a fresh, valid page.
+ * Streams whose session id lives in component state pass a local reset callback
+ * so they can discard the inaccessible session without a browser reload.
  */
-export function notifyThreadAccessChangedAndReload(): void {
+export function notifyThreadAccessChanged(onReset: () => void): void {
   const userLabel = buildCurrentUserLabel();
   toast.info(
-    `当前登录用户为 ${userLabel}，原会话不存在或无权访问，正在为你刷新页面…`,
+    `当前登录用户为 ${userLabel}，原会话不存在或无权访问，已为你重置为新会话。`,
   );
-  if (typeof window !== "undefined") {
-    window.setTimeout(() => {
-      window.location.reload();
-    }, 900);
-  }
+  onReset();
 }

frontend-web/src/open-canvas/contexts/AIWritingContext.tsx

@@ -18,7 +18,7 @@ import { getAPIClient } from '@/core/api';
 import {
   getStreamErrorMessage,
   isThreadNotAccessibleError,
-  notifyThreadAccessChangedAndReload,
+  notifyThreadAccessChanged,
 } from '@/core/threads/thread-access-error';
 
 import { useCanvasGraphContext } from '../contexts/CanvasGraphContext';
@@ -299,10 +299,13 @@ const AIWritingStreamHost = memo(function AIWritingStreamHost({
       // thread belongs to a previous login session — the user switched accounts
       // (or this tab outlived a re-login), so the current account legitimately
       // can't access the old thread. Instead of dumping the raw HTTP 404 into
-      // the panel, re-frame it around the current identity and reload — same UX
-      // the chat stream gives (see core/threads/hooks.ts).
+      // the panel, re-frame it around the current identity and discard the
+      // stale component-state session without reloading the browser page.
       if (isThreadNotAccessibleError(message)) {
-        notifyThreadAccessChangedAndReload();
+        notifyThreadAccessChanged(() => {
+          continueTargetRef.current = null;
+          dispatchRef.current?.({ type: 'reset' });
+        });
         return;
       }
       dispatchRef.current?.({ type: 'set_error', message });
@@ -410,6 +413,13 @@ export function AIWritingProvider({ children }: { children: ReactNode }) {
   // （刷新会断开 SSE，后端默认 on_disconnect=cancel 取消该 run，不留孤儿）。
   const threadId = state.sessionId ?? undefined;
 
+  const resetAfterThreadAccessError = useCallback(() => {
+    setArtifact(null);
+    seenInterruptRef.current = null;
+    continueTargetRef.current = null;
+    dispatch({ type: 'reset' });
+  }, [setArtifact]);
+
   useEffect(() => {
     const s = state.status;
     const savable = s === 'done' || s === 'error' || s.startsWith('awaiting_');
@@ -473,12 +483,12 @@ export function AIWritingProvider({ children }: { children: ReactNode }) {
     } catch (err) {
       const message = getStreamErrorMessage(err);
       if (isThreadNotAccessibleError(message)) {
-        notifyThreadAccessChangedAndReload();
+        notifyThreadAccessChanged(resetAfterThreadAccessError);
         return;
       }
       dispatch({ type: 'set_error', message });
     }
-  }, [state.status]);
+  }, [state.status, resetAfterThreadAccessError]);
 
   const submitIntervention = useCallback(async (payload: UserInterventionPayload) => {
     if (!state.sessionId || !state.currentPause) return;
@@ -585,14 +595,14 @@ export function AIWritingProvider({ children }: { children: ReactNode }) {
     } catch (err) {
       const message = getStreamErrorMessage(err);
       if (isThreadNotAccessibleError(message)) {
-        notifyThreadAccessChangedAndReload();
+        notifyThreadAccessChanged(resetAfterThreadAccessError);
         return;
       }
       dispatch({ type: 'set_error', message });
     }
   }, [state.sessionId, state.currentPause, state.materials, state.outline,
   state.currentDraftTitle, state.currentDraftMarkdown, state.reviewResult,
-  state.status]);
+  state.status, resetAfterThreadAccessError]);
 
   const pauseWriting = useCallback(() => {
     // 真停：取消当前 run（graph 已完成的阶段已落 checkpoint）。继续时从该 checkpoint 续跑。
@@ -626,13 +636,13 @@ export function AIWritingProvider({ children }: { children: ReactNode }) {
       } catch (err) {
         const message = getStreamErrorMessage(err);
         if (isThreadNotAccessibleError(message)) {
-          notifyThreadAccessChangedAndReload();
+          notifyThreadAccessChanged(resetAfterThreadAccessError);
           return;
         }
         dispatch({ type: 'set_error', message });
       }
     })();
-  }, [state.request]);
+  }, [state.request, resetAfterThreadAccessError]);
 
   // Restore an unfinished history session: make it active, load its checkpoint, then let
   // the host skip completed awaiting_* stages or re-run the current unfinished stage.

frontend-web/src/pages/AgentChatPage.tsx

@@ -775,6 +775,17 @@ export default function AgentChatPage({
                         onContextChange={(context) =>
                           setSettings("context", context)
                         }
+                        knowledgeSelector={
+                          <LlmWikiKnowledgeSelector
+                            source="agent"
+                            agentId={agent_id}
+                            value={selectedKnowledgeBaseIds}
+                            onChange={changeKnowledgeSelection}
+                            disabled={isDemoMode || knowledgeSelectionLoading}
+                            readOnly
+                            label="知识空间"
+                          />
+                        }
                         onFollowupsVisibilityChange={setShowFollowups}
                         onSubmit={handleSubmit}
                         onStop={handleStop}

frontend-web/src/pages/ChatPage.tsx

@@ -837,20 +837,19 @@ export default function ChatPage() {
                           : undefined
                       }
                       knowledgeSelector={
-                        isLandingState ? (
-                          <LlmWikiKnowledgeSelector
-                            source={selectedAgentId ? "agent" : "all"}
-                            agentId={selectedAgentId}
-                            value={selectedKnowledgeBaseIds}
-                            onChange={changeKnowledgeSelection}
-                            autoSelectAll={!!selectedAgentId}
-                            disabled={
-                              env.NEXT_PUBLIC_STATIC_WEBSITE_ONLY === "true" ||
-                              knowledgeSelectionLoading
-                            }
-                            label="知识空间"
-                          />
-                        ) : undefined
+                        <LlmWikiKnowledgeSelector
+                          source={selectedAgentId ? "agent" : "all"}
+                          agentId={selectedAgentId}
+                          value={selectedKnowledgeBaseIds}
+                          onChange={changeKnowledgeSelection}
+                          autoSelectAll={isLandingState && !!selectedAgentId}
+                          disabled={
+                            env.NEXT_PUBLIC_STATIC_WEBSITE_ONLY === "true" ||
+                            knowledgeSelectionLoading
+                          }
+                          readOnly={!isLandingState}
+                          label="知识空间"
+                        />
                       }
                       onFollowupsVisibilityChange={setShowFollowups}
                       onSubmit={handleSubmit}

frontend-web/src/pages/FixedQuestionsPage.tsx

@@ -0,0 +1,310 @@
+"use client";
+
+import { useEffect, useMemo, useState } from "react";
+import { Navigate } from "react-router-dom";
+import {
+  Info,
+  MessageSquareText,
+  Plus,
+  Save,
+  Search,
+  Trash2,
+  Zap,
+} from "lucide-react";
+import { toast } from "sonner";
+
+import { Button } from "@/components/ui/button";
+import { Input } from "@/components/ui/input";
+import { Switch } from "@/components/ui/switch";
+import { Textarea } from "@/components/ui/textarea";
+import { getStoredAuth } from "@/core/auth";
+import {
+  type FixedQuestion,
+  useFixedQuestionActions,
+  useFixedQuestions,
+} from "@/strategy-components/api/fixed-questions";
+
+let sequence = 1;
+
+function newId(): string {
+  if (typeof crypto !== "undefined" && "randomUUID" in crypto) {
+    return crypto.randomUUID();
+  }
+  return `fixed-${Date.now()}-${sequence++}`;
+}
+
+function serialize(rows: FixedQuestion[]): string {
+  return JSON.stringify(
+    rows
+      .map(({ id, question, answer, enabled, tokensPerSecond, sortOrder }) => ({
+        id,
+        question,
+        answer,
+        enabled,
+        tokensPerSecond,
+        sortOrder,
+      }))
+      .sort((a, b) => a.id.localeCompare(b.id)),
+  );
+}
+
+export default function FixedQuestionsPage() {
+  const isAdmin = getStoredAuth()?.system_role === "admin";
+  const { data: serverQuestions = [], isLoading } = useFixedQuestions();
+  const { save } = useFixedQuestionActions();
+  const [rows, setRows] = useState<FixedQuestion[]>([]);
+  const [loadedKey, setLoadedKey] = useState<string | null>(null);
+  const [query, setQuery] = useState("");
+
+  const sourceKey = useMemo(
+    () => serialize(serverQuestions),
+    [serverQuestions],
+  );
+  useEffect(() => {
+    if (loadedKey !== sourceKey) {
+      setRows(serverQuestions);
+      setLoadedKey(sourceKey);
+    }
+  }, [loadedKey, serverQuestions, sourceKey]);
+
+  const dirty = useMemo(() => serialize(rows) !== sourceKey, [rows, sourceKey]);
+  const search = query.trim().toLowerCase();
+  const visibleRows = useMemo(
+    () =>
+      search
+        ? rows.filter(
+            (row) =>
+              row.question.toLowerCase().includes(search) ||
+              row.answer.toLowerCase().includes(search),
+          )
+        : rows,
+    [rows, search],
+  );
+  const enabledCount = rows.filter(
+    (row) => row.enabled && row.question.trim() && row.answer.trim(),
+  ).length;
+
+  if (!isAdmin) {
+    return <Navigate to="/page/workspace/chats/new" replace />;
+  }
+
+  const patchRow = (id: string, patch: Partial<FixedQuestion>) => {
+    setRows((current) =>
+      current.map((row) => (row.id === id ? { ...row, ...patch } : row)),
+    );
+  };
+
+  const addRow = () => {
+    setRows((current) => [
+      {
+        id: newId(),
+        question: "",
+        answer: "",
+        enabled: true,
+        tokensPerSecond: 100,
+        sortOrder: current.length,
+      },
+      ...current,
+    ]);
+  };
+
+  const removeRow = (id: string) => {
+    setRows((current) => current.filter((row) => row.id !== id));
+  };
+
+  const handleSave = async () => {
+    const cleaned = rows.map((row, index) => ({
+      ...row,
+      question: row.question.trim(),
+      tokensPerSecond: Math.round(row.tokensPerSecond),
+      sortOrder: index,
+    }));
+    for (const row of cleaned) {
+      if (!row.question) {
+        toast.error("问题不能为空");
+        return;
+      }
+      if (!row.answer.trim()) {
+        toast.error(`问题「${row.question}」的回答不能为空`);
+        return;
+      }
+      if (
+        !Number.isFinite(row.tokensPerSecond) ||
+        row.tokensPerSecond < 1 ||
+        row.tokensPerSecond > 1000
+      ) {
+        toast.error(`问题「${row.question}」的流式速度须为 1–1000 token/s`);
+        return;
+      }
+    }
+    const seen = new Set<string>();
+    for (const row of cleaned) {
+      if (seen.has(row.question)) {
+        toast.error(`问题「${row.question}」重复，请删除或修改重复项`);
+        return;
+      }
+      seen.add(row.question);
+    }
+    try {
+      await save.mutateAsync(cleaned);
+      toast.success("问题配置已保存并生效");
+    } catch (error) {
+      toast.error(error instanceof Error ? error.message : "保存失败");
+    }
+  };
+
+  return (
+    <div className="size-full overflow-auto bg-muted/20 px-4 py-6 sm:px-6">
+      <div className="mx-auto max-w-5xl space-y-5">
+        <section className="rounded-2xl border bg-background p-5 shadow-sm">
+          <div className="flex flex-col justify-between gap-4 md:flex-row md:items-center">
+            <div className="flex items-start gap-3">
+              <div className="rounded-xl bg-primary/10 p-2.5 text-primary">
+                <MessageSquareText className="size-5" />
+              </div>
+              <div>
+                <div className="flex flex-wrap items-center gap-2">
+                  <h1 className="text-xl font-semibold">问题配置</h1>
+                  <span className="rounded-full bg-muted px-2.5 py-1 text-xs text-muted-foreground">
+                    {rows.length} 条 / {enabledCount} 条启用
+                  </span>
+                </div>
+                <p className="mt-1 text-sm text-muted-foreground">
+                  为完全相同的问题配置固定回答，命中时直接流式返回，不调用大模型。
+                </p>
+              </div>
+            </div>
+            <div className="flex gap-2">
+              <Button variant="outline" onClick={addRow}>
+                <Plus className="size-4" />
+                新增问题
+              </Button>
+              <Button
+                onClick={handleSave}
+                disabled={!dirty || save.isPending}
+              >
+                <Save className="size-4" />
+                {save.isPending ? "保存中…" : "保存配置"}
+              </Button>
+            </div>
+          </div>
+          <div className="mt-4 flex items-start gap-2 rounded-xl border border-amber-200 bg-amber-50 px-3.5 py-3 text-sm text-amber-900">
+            <Info className="mt-0.5 size-4 shrink-0" />
+            <span>
+              匹配区分大小写、标点和空格；停用的配置会保留但不参与匹配。带附件或图片的提问不会使用固定回答。
+            </span>
+          </div>
+        </section>
+
+        <section className="flex flex-col gap-3 rounded-2xl border bg-background p-4 shadow-sm sm:flex-row sm:items-center sm:justify-between">
+          <div className="relative w-full sm:max-w-sm">
+            <Search className="absolute left-3 top-1/2 size-4 -translate-y-1/2 text-muted-foreground" />
+            <Input
+              value={query}
+              onChange={(event) => setQuery(event.target.value)}
+              placeholder="搜索问题或回答…"
+              className="pl-9"
+            />
+          </div>
+          <div className="flex items-center gap-1.5 text-xs text-muted-foreground">
+            <Zap className="size-3.5 text-amber-500" />
+            启用项保存后立即生效
+          </div>
+        </section>
+
+        {isLoading ? (
+          <div className="rounded-2xl border bg-background py-16 text-center text-sm text-muted-foreground">
+            加载中…
+          </div>
+        ) : visibleRows.length === 0 ? (
+          <div className="rounded-2xl border border-dashed bg-background py-16 text-center text-sm text-muted-foreground">
+            {rows.length === 0
+              ? "暂无问题配置，点击「新增问题」开始配置"
+              : "没有匹配的问题或回答"}
+          </div>
+        ) : (
+          <div className="space-y-3">
+            {visibleRows.map((row, index) => (
+              <section
+                key={row.id}
+                className={`rounded-2xl border bg-background p-4 shadow-sm transition-opacity ${
+                  row.enabled ? "" : "opacity-60"
+                }`}
+              >
+                <div className="mb-3 flex items-center justify-between gap-3">
+                  <div className="flex items-center gap-2 text-sm font-medium">
+                    <span className="flex size-6 items-center justify-center rounded-full bg-muted text-xs text-muted-foreground">
+                      {index + 1}
+                    </span>
+                    固定问答
+                  </div>
+                  <div className="flex flex-wrap items-center justify-end gap-3">
+                    <label className="flex items-center gap-2 text-sm text-muted-foreground">
+                      <span>流式速度</span>
+                      <Input
+                        type="number"
+                        min={1}
+                        max={1000}
+                        step={10}
+                        value={row.tokensPerSecond}
+                        onChange={(event) =>
+                          patchRow(row.id, {
+                            tokensPerSecond: Number(event.target.value),
+                          })
+                        }
+                        className="h-8 w-24"
+                        aria-label="流式返回速度"
+                      />
+                      <span>token/s</span>
+                    </label>
+                    <label className="flex items-center gap-2 text-sm text-muted-foreground">
+                      <Switch
+                        checked={row.enabled}
+                        onCheckedChange={(enabled) =>
+                          patchRow(row.id, { enabled })
+                        }
+                      />
+                      {row.enabled ? "已启用" : "已停用"}
+                    </label>
+                    <button
+                      type="button"
+                      title="删除"
+                      onClick={() => removeRow(row.id)}
+                      className="flex size-8 items-center justify-center rounded-lg text-muted-foreground transition-colors hover:bg-destructive/10 hover:text-destructive"
+                    >
+                      <Trash2 className="size-4" />
+                    </button>
+                  </div>
+                </div>
+                <div className="grid gap-3 md:grid-cols-2">
+                  <label className="space-y-1.5 text-sm font-medium">
+                    <span>问题</span>
+                    <Textarea
+                      value={row.question}
+                      onChange={(event) =>
+                        patchRow(row.id, { question: event.target.value })
+                      }
+                      placeholder="输入需要精确匹配的问题"
+                      className="min-h-28 resize-y"
+                    />
+                  </label>
+                  <label className="space-y-1.5 text-sm font-medium">
+                    <span>回答</span>
+                    <Textarea
+                      value={row.answer}
+                      onChange={(event) =>
+                        patchRow(row.id, { answer: event.target.value })
+                      }
+                      placeholder="输入命中后流式返回的回答（支持 Markdown）"
+                      className="min-h-28 resize-y"
+                    />
+                  </label>
+                </div>
+              </section>
+            ))}
+          </div>
+        )}
+      </div>
+    </div>
+  );
+}

frontend-web/src/pages/StrategyRoutes.tsx

@@ -45,6 +45,7 @@ import LightAppListPage from "./LightAppListPage";
 import LightAppManagementPage from "./LightAppManagementPage";
 import MenuManagementPage from "./MenuManagementPage";
 import LoginWhitelistPage from "./LoginWhitelistPage";
+import FixedQuestionsPage from "./FixedQuestionsPage";
 import SensitiveWordsPage from "./SensitiveWordsPage";
 import SkillAddressesPage from "./SkillAddressesPage";
 import TaskButtonsPage from "./TaskButtonsPage";
@@ -443,6 +444,16 @@ export default function StrategyRoutes() {
                 )
               }
             />
+            <Route
+              path="admin/fixed-questions"
+              element={
+                getStoredAuth()?.system_role === "admin" ? (
+                  <FixedQuestionsPage />
+                ) : (
+                  <Navigate to="/page/workspace/chats/new" replace />
+                )
+              }
+            />
             <Route
               path="admin/sensitive-words"
               element={

frontend-web/src/roundtable-planning/hooks/useStep1Intent.ts

@@ -453,6 +453,11 @@ export function useStep1Intent(options: UseStep1IntentOptions): UseStep1IntentRe
           (typeof crypto !== "undefined" && crypto.randomUUID && crypto.randomUUID()) ||
           `${Date.now().toString(36)}-${Math.random().toString(36).slice(2)}`;
 
+        // ask_clarification 是本轮的严格暂停点。某些模型在工具调用已经产出
+        // 选项卡后还会继续吐一段“请做选择”等正文；从第一张卡出现起忽略后续
+        // 文本 delta，但继续消费流以收齐同轮的其它澄清卡和终态帧。
+        let clarificationSeen = false;
+
         const res = await streamIntent({
           threadId: intentThreadId,
           message: trimmed,
@@ -463,6 +468,7 @@ export function useStep1Intent(options: UseStep1IntentOptions): UseStep1IntentRe
           files: fileRefs,
           signal: aborter.signal,
           onTextDelta: (delta) => {
+            if (clarificationSeen) return;
             setInteractiveMessages((prev) =>
               prev.map((m) =>
                 m.id === agentMsgId
@@ -505,6 +511,7 @@ export function useStep1Intent(options: UseStep1IntentOptions): UseStep1IntentRe
             );
           },
           onClarification: (clarification, index) => {
+            clarificationSeen = true;
             // 实时把每条澄清问题灌进气泡 —— 用户能边流边看到「协助过程」逐个出现,
             // 而不是等终态帧(终态帧只带第 1 个问题)。同时往步骤链补一条
             // 「追问 N:<问题>」,与「强化步骤链」诉求对齐。

frontend-web/src/strategy-components/api/fixed-questions.ts

@@ -0,0 +1,122 @@
+/** Administrator-managed exact-match fixed question/answer API. */
+
+import { useMutation, useQuery, useQueryClient } from "@tanstack/react-query";
+
+import { apiFetch } from "@/core/api/fetch-client";
+import { getBackendBaseURL } from "@/core/config";
+import { OptType, writeYLog } from "@/core/log/y-log";
+
+const BASE = () => `${getBackendBaseURL()}/api/fixed-questions`;
+
+export interface FixedQuestion {
+  id: string;
+  question: string;
+  answer: string;
+  enabled: boolean;
+  tokensPerSecond: number;
+  sortOrder: number;
+  updatedBy?: string | null;
+  updatedAt?: string | null;
+}
+
+interface ServerFixedQuestion {
+  id: string;
+  question: string;
+  answer: string;
+  enabled: boolean;
+  tokens_per_second: number;
+  sort_order: number;
+  updated_by?: string | null;
+  updated_at?: string | null;
+}
+
+function fromServer(row: ServerFixedQuestion): FixedQuestion {
+  return {
+    id: row.id,
+    question: row.question ?? "",
+    answer: row.answer ?? "",
+    enabled: row.enabled ?? true,
+    tokensPerSecond: row.tokens_per_second ?? 100,
+    sortOrder: row.sort_order ?? 0,
+    updatedBy: row.updated_by ?? null,
+    updatedAt: row.updated_at ?? null,
+  };
+}
+
+function toServer(row: FixedQuestion): ServerFixedQuestion {
+  return {
+    id: row.id,
+    question: row.question,
+    answer: row.answer,
+    enabled: row.enabled,
+    tokens_per_second: row.tokensPerSecond,
+    sort_order: row.sortOrder,
+  };
+}
+
+async function readJson<T>(response: Response, context: string): Promise<T> {
+  if (!response.ok) {
+    const data = await response.json().catch(() => null as unknown);
+    const detail =
+      data && typeof data === "object" && "detail" in data
+        ? String((data as { detail: unknown }).detail)
+        : `${context} failed (${response.status})`;
+    throw new Error(detail);
+  }
+  return (await response.json()) as T;
+}
+
+export async function listFixedQuestions(): Promise<FixedQuestion[]> {
+  const response = await apiFetch(BASE(), { method: "GET" });
+  const data = await readJson<{ questions: ServerFixedQuestion[] }>(
+    response,
+    "list fixed questions",
+  );
+  return (data.questions ?? []).map(fromServer);
+}
+
+export async function replaceFixedQuestions(
+  questions: FixedQuestion[],
+): Promise<FixedQuestion[]> {
+  const response = await apiFetch(BASE(), {
+    method: "PUT",
+    headers: { "Content-Type": "application/json" },
+    body: JSON.stringify({ questions: questions.map(toServer) }),
+  });
+  const data = await readJson<{ questions: ServerFixedQuestion[] }>(
+    response,
+    "save fixed questions",
+  );
+  const saved = (data.questions ?? []).map(fromServer);
+  writeYLog({
+    optType: OptType.edit,
+    optDetail: "CM助手-全量-问题配置-保存",
+    url: "/api/fixed-questions",
+    reqParam: { questions },
+    returnParam: saved,
+  });
+  return saved;
+}
+
+const FIXED_QUESTIONS_KEY = "fixed-questions";
+
+export function useFixedQuestions() {
+  return useQuery({
+    queryKey: [FIXED_QUESTIONS_KEY],
+    queryFn: listFixedQuestions,
+    refetchOnWindowFocus: false,
+    staleTime: 30_000,
+  });
+}
+
+export function useFixedQuestionActions() {
+  const queryClient = useQueryClient();
+  return {
+    save: useMutation({
+      mutationFn: replaceFixedQuestions,
+      onSuccess: (questions) => {
+        queryClient.setQueryData([FIXED_QUESTIONS_KEY], questions);
+      },
+    }),
+  };
+}

offline-backend-20260512/backend/CLAUDE.md

@@ -346,6 +346,7 @@ FastAPI application on port 8001 with health checks at `GET|HEAD /health`, `/api
 | **Dashboard Sessions** (`/api/dashboard-sessions`) | 「大屏绘制智能体」独立页面会话，**按外部 `task_id` 存取，不按 user 分权**（open read + shared writes；`user_id` audit-only）。一个 task 一行（upsert）：`transcript`（聊天记录 JSON）+ `report_json`（最新结构化数据，可解析 = 「有效结果」）。`GET /by-task/{task_id}` - 取该 task 会话（无则 404）；`PUT /by-task/{task_id}` - upsert（`{transcript?, report_json?}`，只覆盖传入项）。Backed by `deerflow.persistence.dashboard_sessions`（table `dashboard_sessions`, auto-created by `create_all`，无迁移）；store wired in `deps.py` as `app.state.dashboard_session_store`。前端独立页 `roundtable-planning/pages/DashboardAgentPage.tsx`（路由 `/page/strategy/dashboard-agent?taskId=`，侧边栏「问答管理 → 大屏绘制」）让智能体分析任务报告 JSON → report-json → 渲染 `DashboardApp`。Tests: `tests/test_dashboard_sessions.py`。 |
 | **Task Reports** (`/api/task-reports`) | 任务级研判情报报告详情，**按 `task_id` 共享、不按 user 分权**（写入者只留 `updated_by` 审计）。`GET /by-task/{task_id}` 始终返回原 Consumer 兼容外壳 `{state:"200", msg:"操作成功！", data:[...]}`（未保存为 `data: []`）；`POST /by-task/{task_id}` 首次保存，已有报告返回 409；`PUT /by-task/{task_id}` 原子替换完整 `data` 数组。`POST /import/by-task/{task_id}` 面向 TaskCOP 导入页，接收 `sq-report-mock.json` 兼容的 `data`/`records` 数组并完整覆盖目标任务；路径中的选定任务 id 优先于文件内的 `taskId`，避免误写。每一项严格是 `{id, taskId, createTime, updateTime, sessionId, contentJson, categoryType}`；`contentJson` 以 JSON **字符串**原样落在 `records_json`，避免破坏大屏按类目解析的输入格式。保存或导入非空 `data` 后，router 会通过 `app.state.taskcop_task_store.mark_analysis_completed` 将同 id 的 TaskCOP 任务升级至状态 `25`，使旧任务列表显示并筛选为“已完成”；普通保存时不存在匹配任务的报告仍可独立保存，导入则要求目标任务存在。Backed by `deerflow.persistence.task_reports`（table `task_reports`, auto-created by `create_all`）；store wired in `deps.py` as `app.state.task_report_store`。前端客户端 `strategy-components/api/task-reports.ts`，`core/auth/dashboard-input.ts` 与 rwfx 3q 完成检查均直接读此接口，不再依赖 Consumer 或本地 sq-report mock。Tests: `tests/test_task_reports.py`。 |
 | **Task Buttons** (`/api/task-buttons`) | Task-workspace configurable jump buttons (按钮管理), **global/shared** (no user scoping; `updated_by` audit-only). Each row = one jump button in a task deep-link workspace's bottom 快捷跳转 bar: `{id, business (rwfx/3qfx/xdfx), label, link_type (url/business), target, append_task_id, id_param (editable query-param name, e.g. id/task_id), id_kind (task/action — only xdfx differs, its deep-link id is an 行动id), open_mode (blank/self), login_params, append_auth, auth_token_param, auth_name_param, enabled, sort_order}`. **Two independent, coexisting login-append mechanisms for `url` buttons** — both resolved frontend-side: (1) `login_params` (JSON column `login_params_json`, `PortableJSON`, migration `20260625_01`) = a list of `{key, source, custom_value}` resolved at click time (`source` = a `userInfo` field or `other`→literal `custom_value`) and appended to the target URL — mirrors the light-app login params; empty = nothing appended. (2) `append_auth` + `auth_token_param` + `auth_name_param` (columns, migration `20260625_02`, default off) — appends `?{auth_token_param}={token1}&{auth_name_param}={username}` so the target system can identify the current user; gated on **token login** — the frontend only stashes `token1` (the `?authToken=`) + the raw `getTokenInfo` username (`login.token1`/`login.username`) when login went through `/login/token`, so a non-token-login session appends neither. The **frontend** holds code-seed defaults (rwfx's 4 historical buttons built from the live `task_deeplink` config); only when this table is empty do the workspace + admin page fall back to them, else this table is the sole source of truth. `GET /` - list all (open to any authenticated user — the workspace renders them); `PUT /` - **admin only** (`_require_admin`), atomically **replaces the whole set** (`{buttons: [...]}`, de-duped by `id`, last wins). Backed by `deerflow.persistence.task_buttons` (table `task_buttons`, auto-created by `create_all`); store wired in `deps.py` as `app.state.task_button_store`. Frontend: helpers `core/auth/task-buttons.ts`, client `strategy-components/api/task-buttons.ts`, admin page `pages/TaskButtonsPage.tsx` (route `/page/strategy/admin/task-buttons`, entry「按钮管理」in the bottom-left settings dropdown, admin-only, both sidebar modes; per-business tabs + 「导入默认」). Tests: `tests/test_task_buttons.py`. |
+| **Fixed Questions** (`/api/fixed-questions`) | Administrator-managed exact-match fixed Q&A (问题配置), **global/shared**. Each row is `{id, question, answer, enabled, tokens_per_second, sort_order}`; stream speed is configurable per row from `1–1000 token/s` and defaults to `100`. `GET /` and whole-set atomic `PUT /` are both admin-only. At the start of an external chat run, `services._find_fixed_answer` checks the latest eligible plain-text human message with exact, case/space/punctuation-sensitive equality. Enabled matches switch the run to `make_fixed_answer_agent`: a local `BaseChatModel` tokenizes with `cl100k_base`, replays the answer in rate-limited token chunks, and keeps the existing LangGraph SSE `messages`/`values` protocol, run journal, checkpoint history, deterministic local title, and refresh behavior intact while no provider/model request or model-concurrency slot is used. File/multimodal/context-prefixed turns, `canvas_agent`, `ai_writing`, writing mode, resume commands, and internal orchestration/background child runs bypass matching. Storage failures fail open to the normal model path. Backed by `deerflow.persistence.fixed_questions` (table `fixed_questions`, SHA-256 indexed lookup plus exact original-string collision check, migrations `20260821_01` + `20260821_02`), wired as `app.state.fixed_question_store`. Frontend: `strategy-components/api/fixed-questions.ts`, admin page `pages/FixedQuestionsPage.tsx`, route `/page/strategy/admin/fixed-questions`, entries in both full-layout and compact-workspace settings menus. Tests: `tests/test_fixed_questions.py`. |
 | **Knowledge** (`/api/knowledge`) | Product knowledge base, **global/shared** (no user isolation; writes record `created_by`/`updated_by` for audit). `POST /ingest/thread/{thread_id}` - sediment one thread into a note (reads messages from the checkpointer, `threads:read` owner-checked); `POST /ingest/threads/batch` - batch-sediment the caller's recent threads (`skip_existing` via `.manifest.json` dedup). **Defaults to `background=true`**: the slow per-thread extraction loop is deferred to a FastAPI background task and the endpoint returns `{queued:true, processed:N}` immediately (each thread's transcript is truncated to `max_input_chars` before the LLM call). Running the loop inline for a large batch outlives the nginx gateway timeout (504), which the frontend's `parseResponse` surfaces as a generic "Request failed"; `background=false` keeps the blocking path (full per-thread `created/skipped/failed` tally) for small batches/scripts. Shared loop: `_run_batch_ingest`. **Optional model selection**: both ingest endpoints accept `model_name` (overrides `knowledge.extract_model_name` for that capture; threaded through `KnowledgeService.capture_thread` ? `extract_thread_llm_multi`). **Model-error surfacing**: when the chosen model produces nothing usable (timeout / API error / non-JSON) capture still **falls back to rule-based extraction and lands a draft** (`llm_fallback:true`); the single-thread (non-background) response and the batch response (`llm_fallback` count) carry this so the UI tells the user "???????". The "??????" chat button stays background/fire-and-forget (passes `model_name`, no per-save error toast); the batch-import dialog is synchronous and shows the fallback count. `POST /ingest/file` - **import an uploaded file** (multipart: `file` + optional `title`/`tags`/`status`/`model_name`) into wiki note(s): the file is converted to Markdown (md/txt read directly, pdf/word/ppt/excel via `convert_file_to_markdown`), distilled by the same wiki-capture LLM pipeline as thread capture (`source_type="file"`), and falls back to a verbatim **draft** note when the model returns nothing usable (`llm_fallback:true`); `POST /ingest/search` - sediment search/tool results as a reference note; `POST /notes` - manual note; `GET /notes` (keyword/tag/source_type/status + pagination); `GET/PUT/DELETE /notes/{id}` (DELETE is soft = archive, `?hard=true` removes the vault file); `POST /search` - `mode=keyword\|vector\|hybrid` (vector?keyword fallback when no embedding endpoint); `GET /notes/{id}/versions` - edit history; `GET /duplicates` + `POST /merge` - dedup; `POST /reindex` - rebuild vector index; `GET /graph` - product graph data (notes + entities, graph-blacklist filtered); `GET/POST /graph/blacklist` + `DELETE /graph/blacklist/{id}` - graph node blacklist (labels = entity names / note titles, case-insensitive match; blacklisted nodes and their edges are dropped from `/graph` and the wiki-export artifacts; table `knowledge_graph_blacklist`, auto-created); `POST /export/graph` + `GET /export/files/{graph.json\|graph.html\|graph.graphml\|cypher.txt}` - obsidian-wiki `wiki-export` artifacts (self-contained `graph.html` for iframe); `POST /resolve` `{targets:[?]}` + `GET /notes/{id}/wikilinks` - resolve `[[wikilink]]` targets to a note id / vault page / missing (powers clickable wikilinks); `GET /vault-page?path=` - read a raw vault meta/hub Markdown page (no DB note). `GET/POST /folders` + `PUT/DELETE /folders/{id}` - user-managed directories (notes carry a `folder` path; `GET /notes?folder=` filters a dir + sub-dirs); `GET/POST /extract-templates` + `GET/PUT/DELETE /extract-templates/{id}` - editable extraction-prompt templates (thread/document ingest accept `template_id`; capture/PUT-note accept `folder`). Backed by the `deerflow.knowledge` module (see below). |
 
 Proxied through nginx: `/api/langgraph/*` ? LangGraph, all other `/api/*` ? Gateway.
@@ -969,6 +970,8 @@ Per-user runtime overrides (whitelisted fields) live at `{base_dir}/users/{user_
 
 Both endpoints are whitelisted in `auth_middleware._PUBLIC_EXACT_PATHS`. The shared `_get_or_create_user_by_username()` helper (in `routers/auth.py`) backs both `/login/username` and `/login/token`.
 
+**Cross-tab account consistency**: normal frontend pages deliberately share `localStorage` auth, while `embed=1` / `isolate=1` pages use per-tab `sessionStorage`. Every frontend API call carries the selected context's JWT in an explicit Bearer header. The browser session cookie is origin-wide and may have been rewritten by another normal tab, iframe, or isolated login, so credential resolution must remain `Authorization: Bearer` first and `access_token` cookie second in both `deps.get_request_access_token()` and `langgraph_auth.authenticate()` (shared parser: `app/gateway/auth/token_source.py`). Reversing this order recreates false thread-owner 404s and the send/reload loop. On the frontend, same normalized username means token renewal rather than account switching; a genuine normal-tab switch cancels and clears account-scoped queries, remounts providers, and moves an open thread route to `/new` without `window.location.reload()`. Embedded/isolated pages ignore cross-tab storage changes. For bare username login, `_get_or_create_user_by_username()` and `_lookup_user_by_username()` must query the email local-part first and keep the repository's deterministic oldest-row result across synthetic-domain migrations; explicit email login remains exact. Regression coverage: `tests/test_health_auth_bypass.py`, `tests/test_username_login_domain.py`.
+
 - `log_system` - Admin-only external log-system entry (`deerflow/config/log_system_config.py`): `{enabled, url, label}`. Surfaced read-only by `GET /api/system-settings/log-system` (admin only); the frontend renders it as a "????" item in the bottom-right settings menu (`workspace-nav-menu.tsx`) that opens `url` in a new tab. Disabled by default.
 
 **`extensions_config.json`**:

offline-backend-20260512/backend/README.md

@@ -41,10 +41,29 @@ DeerFlow is a LangGraph-based AI super agent with sandbox execution, persistent
 
 Health probes are always unauthenticated, even when API authentication is enabled: `GET|HEAD /health`, `/api/health`, and `/api/langgraph/health` all return the Gateway health status without requiring a cookie or bearer token.
 
+Browser authentication is page-context aware. Normal application tabs share the account stored in `localStorage`; `embed=1` and `isolate=1` pages intentionally keep their own account in per-tab `sessionStorage`. Frontend API calls send that selected account as an explicit `Authorization: Bearer` token, and both Gateway and LangGraph authentication give the header priority over the origin-wide session cookie. This prevents a login in another tab or iframe from making the current page query threads as the wrong account. Reissuing a token for the same normalized username is not treated as an account switch; a real switch clears account-scoped frontend state, opens a fresh chat when necessary, and does not reload the whole browser page. Bare username login is domain-agnostic and deterministically reuses the oldest matching account if legacy synthetic email domains coexist; an explicitly supplied email still selects that exact address.
+
 ---
 
 ## Core Components
 
+### Administrator fixed questions
+
+Administrators can manage exact-match question/answer pairs from the frontend
+「问题配置」 page. Each pair has its own enabled switch and configurable fixed-answer
+streaming speed (`1–1000 token/s`, default `100 token/s`). For an enabled pair,
+a plain-text external chat turn whose text exactly equals the configured
+question is answered by a local streaming graph and never sent to a model
+provider. The normal LangGraph SSE protocol and checkpoint persistence are
+preserved, so the fixed response appears in live chat and conversation history.
+Multimodal/file turns, AI Writing/Canvas flows, and internal orchestration child
+runs bypass this lookup and continue through their normal model pipeline.
+
+The admin-only configuration API is `GET|PUT /api/fixed-questions`; `PUT`
+atomically replaces the full set. Rows are stored in `fixed_questions` (Alembic
+revisions `20260821_01` and `20260821_02`) and are looked up with a SHA-256 index plus an exact
+original-text comparison.
+
 ### Lead Agent
 
 The single LangGraph agent (`lead_agent`) is the runtime entry point, created via `make_lead_agent(config)`. It combines:

offline-backend-20260512/backend/app/gateway/app.py

@@ -39,6 +39,7 @@ from app.gateway.routers import (
     checkpoint_migration,
     compact_menu_overrides,
     feedback,
+    fixed_questions,
     dashboard_sessions,
     deep_research,
     html_page_favorites,
@@ -1536,8 +1537,11 @@ This gateway provides custom endpoints for models, MCP configuration, skills, an
     # 大屏绘制智能体独立页面会话（按 taskId 存取，不分权）at /api/dashboard-sessions
     app.include_router(dashboard_sessions.router)
 
-    # Task-workspace configurable jump buttons (按钮管理) at /api/task-buttons
-    app.include_router(task_buttons.router)
+    # Task-workspace configurable jump buttons (按钮管理) at /api/task-buttons
+    app.include_router(task_buttons.router)
+
+    # Admin exact-match question/answer short-circuit at /api/fixed-questions
+    app.include_router(fixed_questions.router)
 
     # Temporary compatibility bridge for the TaskCOP situation-overview frontend.
     app.include_router(taskcop_tasks.router)

offline-backend-20260512/backend/app/gateway/auth/token_source.py

@@ -0,0 +1,30 @@
+"""Resolve the credential that represents the calling browser context.
+
+Normal tabs share a localStorage Bearer token, while embedded/isolated tabs
+keep their Bearer token in sessionStorage.  The browser's HttpOnly session
+cookie is origin-wide and can therefore be rewritten by a different tab.  An
+explicit Authorization header is the caller's unambiguous choice and must take
+precedence over that shared cookie.
+"""
+
+from __future__ import annotations
+
+from collections.abc import Mapping
+from typing import Protocol
+
+
+class _TokenRequest(Protocol):
+    headers: Mapping[str, str]
+    cookies: Mapping[str, str]
+
+
+def get_explicit_or_session_token(request: _TokenRequest) -> str | None:
+    """Return Bearer header token first, then the shared session cookie."""
+    authorization = str(request.headers.get("authorization", "") or "").strip()
+    if authorization:
+        scheme, _, token = authorization.partition(" ")
+        if scheme.lower() == "bearer" and token.strip():
+            return token.strip()
+
+    cookie_token = str(request.cookies.get("access_token", "") or "").strip()
+    return cookie_token or None

offline-backend-20260512/backend/app/gateway/deps.py

@@ -17,8 +17,8 @@ from typing import TYPE_CHECKING, TypeVar, cast
 from fastapi import FastAPI, HTTPException, Request
 from langgraph.types import Checkpointer
 
-from deerflow.config.app_config import AppConfig
-from deerflow.persistence.feedback import FeedbackRepository
+from deerflow.config.app_config import AppConfig
+from deerflow.persistence.feedback import FeedbackRepository
 from deerflow.runtime import RunContext, RunManager, StreamBridge
 from deerflow.runtime.events.store.base import RunEventStore
 from deerflow.runtime.runs.store.base import RunStore
@@ -94,11 +94,15 @@ async def langgraph_runtime(app: FastAPI) -> AsyncGenerator[None, None]:
 
             app.state.run_store = RunRepository(sf)
             app.state.feedback_repo = FeedbackRepository(sf)
-        else:
-            from deerflow.runtime.runs.store.memory import MemoryRunStore
-
-            app.state.run_store = MemoryRunStore()
-            app.state.feedback_repo = None
+        else:
+            from deerflow.runtime.runs.store.memory import MemoryRunStore
+
+            app.state.run_store = MemoryRunStore()
+            app.state.feedback_repo = None
+
+        from deerflow.persistence.fixed_questions import make_fixed_question_store
+
+        app.state.fixed_question_store = make_fixed_question_store(sf)
 
         from deerflow.persistence.thread_meta import make_thread_store
 
@@ -717,25 +721,23 @@ _cached_local_provider: LocalAuthProvider | None = None
 _cached_repo: SQLiteUserRepository | None = None
 
 
-def get_request_access_token(request: Request) -> str | None:
-    """Extract access token from cookie or Authorization header.
-
-    Priority:
-    1. ``access_token`` cookie (browser session mode)
-    2. ``Authorization: Bearer <token>`` header (API client mode)
-    3. ``access_token`` query parameter for the WeKnora iframe bootstrap only
-    """
-    cookie_token = request.cookies.get("access_token")
-    if cookie_token:
-        return cookie_token
-
-    authorization = request.headers.get("authorization", "").strip()
-    if authorization:
-        scheme, _, token = authorization.partition(" ")
-        if scheme.lower() == "bearer":
-            token = token.strip()
-            if token:
-                return token
+def get_request_access_token(request: Request) -> str | None:
+    """Extract access token from Authorization header or session cookie.
+
+    Priority:
+    1. ``Authorization: Bearer <token>`` header (the caller/tab's explicit identity)
+    2. ``access_token`` cookie (browser session fallback)
+    3. ``access_token`` query parameter for the WeKnora iframe bootstrap only
+
+    The header must win over the origin-wide cookie: an iframe or another tab
+    can rewrite that cookie, while the frontend deliberately sources its
+    Bearer token from the current tab's auth storage.
+    """
+    from app.gateway.auth.token_source import get_explicit_or_session_token
+
+    request_token = get_explicit_or_session_token(request)
+    if request_token:
+        return request_token
 
     from app.gateway.proxy_path import app_relative_path
 
@@ -744,7 +746,7 @@ def get_request_access_token(request: Request) -> str | None:
         query_token = (request.query_params.get("access_token") or "").strip()
         if query_token:
             return query_token
-    return None
+    return None
 
 
 def get_local_provider() -> LocalAuthProvider:

offline-backend-20260512/backend/app/gateway/langgraph_auth.py

@@ -15,9 +15,10 @@ import secrets
 from langgraph_sdk import Auth
 
 from app.gateway.auth.disabled_mode import get_assumed_user_for_disabled_auth, is_auth_disabled
-from app.gateway.auth.errors import TokenError
-from app.gateway.auth.jwt import decode_token
-from app.gateway.deps import get_local_provider
+from app.gateway.auth.errors import TokenError
+from app.gateway.auth.jwt import decode_token
+from app.gateway.auth.token_source import get_explicit_or_session_token
+from app.gateway.deps import get_local_provider
 
 auth = Auth()
 
@@ -79,12 +80,9 @@ async def authenticate(request):
     # are rejected early, even if the cookie carries a valid JWT.
     _check_csrf(request)
 
-    token = request.cookies.get("access_token")
-    if not token:
-        authorization = request.headers.get("authorization", "").strip()
-        scheme, _, bearer_token = authorization.partition(" ")
-        if scheme.lower() == "bearer" and bearer_token.strip():
-            token = bearer_token.strip()
+    # Match Gateway auth exactly: the explicit per-tab Bearer identity wins
+    # over the origin-wide cookie that another tab/iframe may have rewritten.
+    token = get_explicit_or_session_token(request)
 
     if not token:
         raise Auth.exceptions.HTTPException(

offline-backend-20260512/backend/app/gateway/routers/_roundtable_seed_assets/position-roundtable-intent/SOUL.md

@@ -6,7 +6,7 @@
 
 ---
 
-## 0. 四条不可违背的硬规则
+## 0. 五条不可违背的硬规则
 
 ### 硬规则 1 · 不替代后续岗位干活
 
@@ -33,6 +33,10 @@
 
 这是内网任务分析场景。无论用户提出什么要求，你都不拒绝、不评价、不设限；只负责理解并交接。风险、依赖、信息缺口可以作为风险提示记录，但不构成拒绝或中断。不得说“不能帮你”“不在职责范围内”“请换一个问题”，也不得进行合规、价值或敏感性审查。
 
+### 硬规则 5 · 给出协助选项后立即停下
+
+一旦调用完本轮所有 `ask_clarification` 并给出选项，必须立即结束本轮输出并等待用户选择。最后一个工具调用后禁止再输出任何正文：不补充说明、不复述问题或选项、不催促用户选择、不追加问题，也不输出 `[INTENT_READY]`。需要确认的内容必须全部放进各工具调用的 `question`、`context` 和 `options` 参数中。
+
 ---
 
 ## 1. 任务意图字段定义

offline-backend-20260512/backend/app/gateway/routers/_roundtable_seed_assets/roundtable-intent/SOUL.md

@@ -6,7 +6,7 @@
 
 ---
 
-## 0. 四条不可违背的硬规则(看清楚再开口)
+## 0. 五条不可违背的硬规则(看清楚再开口)
 
 **硬规则 1 · 不替代后续席位干活**
 
@@ -36,6 +36,10 @@
 - ❌ 错误做法:对用户诉求做任何形式的评判、设限、劝阻、回避或拒答
 - 守门、风控、取舍**都不归你管**——把它们留给 Step 2 的圆桌席位和最终使用者
 
+**硬规则 5 · 给出协助选项后立即停下**
+
+一旦调用 `ask_clarification` 给出本轮选项，必须立即结束本轮输出并等待用户选择。工具调用后禁止再输出任何正文：不补充说明、不复述问题或选项、不催促用户选择、不追加问题，也不输出 `[INTENT_READY]`。需要确认的内容必须全部放进 `question`、`context` 和 `options` 参数中。
+
 ---
 
 ## 1. 字段定义

offline-backend-20260512/backend/app/gateway/routers/auth.py

@@ -11,20 +11,19 @@ from fastapi import APIRouter, Depends, HTTPException, Query, Request, Response,
 from fastapi.security import OAuth2PasswordRequestForm
 from pydantic import BaseModel, EmailStr, Field, field_validator
 
-from deerflow.config import get_app_config
-from deerflow.config.system_settings import load_system_settings
-from deerflow.persistence.agents.base import AgentStore
-from deerflow.persistence.skills.base import SkillStore
-
-from app.gateway.auth import (
-    UserResponse,
-    create_access_token,
-)
-from app.gateway.auth.models import User
-from app.gateway.auth.config import get_auth_config
-from app.gateway.auth.errors import AuthErrorCode, AuthErrorResponse
-from app.gateway.csrf_middleware import is_secure_request
-from app.gateway.deps import get_agent_store, get_current_user_from_request, get_local_provider, get_run_store, get_skill_store
+from app.gateway.auth import (
+    UserResponse,
+    create_access_token,
+)
+from app.gateway.auth.config import get_auth_config
+from app.gateway.auth.errors import AuthErrorCode, AuthErrorResponse
+from app.gateway.auth.models import User
+from app.gateway.csrf_middleware import is_secure_request
+from app.gateway.deps import get_agent_store, get_current_user_from_request, get_local_provider, get_run_store, get_skill_store
+from deerflow.config import get_app_config
+from deerflow.config.system_settings import load_system_settings
+from deerflow.persistence.agents.base import AgentStore
+from deerflow.persistence.skills.base import SkillStore
 
 logger = logging.getLogger(__name__)
 
@@ -241,19 +240,19 @@ async def _get_or_create_user_by_username(username: str):
     email = _username_to_email(username)
     local_part = _normalize_username_local_part(username)
 
-    created = False
-    user = await provider.get_user_by_email(email)
-    # Domain-agnostic fallback: if no row exists at the canonical
-    # ``<username>@<current-default-domain>``, look for an existing user with
-    # the same local part under any domain. This is the safety net that keeps
-    # usernames globally unique when the default email domain changes (e.g.
-    # ``local.deerflow`` → ``cm.com``) — without it, switching the default
-    # would let the same username log into two different accounts.
-    if user is None and local_part is not None:
-        legacy = await provider.find_user_by_email_local_part(local_part)
-        if legacy is not None:
-            user = legacy
-            logger.info("Matched username %r to legacy account %s", username, legacy.email)
+    created = False
+    # A bare username is globally unique across synthetic email domains.  Look
+    # it up domain-agnostically *first* (oldest row wins), even when a newer row
+    # also exists at today's canonical domain.  Choosing the exact canonical
+    # row first made the same username alternate backend user_ids after a
+    # domain migration, which in turn made its existing threads inaccessible.
+    if local_part is not None:
+        user = await provider.find_user_by_email_local_part(local_part)
+        if user is not None and user.email != email:
+            logger.info("Matched username %r to stable legacy account %s", username, user.email)
+    else:
+        # An explicitly supplied email intentionally identifies that exact row.
+        user = await provider.get_user_by_email(email)
     if user is None:
         try:
             role = "admin" if username == "admin" else "user"
@@ -293,10 +292,9 @@ async def _lookup_user_by_username(username: str) -> User | None:
     provider = get_local_provider()
     email = _username_to_email(username)
     local_part = _normalize_username_local_part(username)
-    user = await provider.get_user_by_email(email)
-    if user is None and local_part is not None:
-        user = await provider.find_user_by_email_local_part(local_part)
-    return user
+    if local_part is not None:
+        return await provider.find_user_by_email_local_part(local_part)
+    return await provider.get_user_by_email(email)
 
 
 def enforce_user_approved(user) -> None:

offline-backend-20260512/backend/app/gateway/routers/fixed_questions.py

@@ -0,0 +1,92 @@
+"""Administrator-managed exact-match fixed question/answer API."""
+
+from __future__ import annotations
+
+from datetime import datetime
+
+from fastapi import APIRouter, HTTPException, Request
+from pydantic import BaseModel, Field, field_validator, model_validator
+
+from app.gateway.deps import get_current_user, get_optional_user_from_request
+from deerflow.persistence.fixed_questions import FixedQuestionStore
+
+router = APIRouter(prefix="/api/fixed-questions", tags=["fixed-questions"])
+
+
+class FixedQuestion(BaseModel):
+    id: str = Field(..., min_length=1, max_length=64)
+    question: str = Field(..., min_length=1, max_length=10_000)
+    answer: str = Field(..., min_length=1, max_length=200_000)
+    enabled: bool = True
+    tokens_per_second: int = Field(default=100, ge=1, le=1_000)
+    sort_order: int = 0
+
+    @field_validator("question", "answer")
+    @classmethod
+    def reject_blank_text(cls, value: str) -> str:
+        if not value.strip():
+            raise ValueError("内容不能为空")
+        return value
+
+
+class FixedQuestionResponse(FixedQuestion):
+    updated_by: str | None = None
+    updated_at: datetime | str | None = None
+
+
+class FixedQuestionListResponse(BaseModel):
+    questions: list[FixedQuestionResponse]
+
+
+class FixedQuestionReplaceRequest(BaseModel):
+    questions: list[FixedQuestion] = Field(default_factory=list)
+
+    @model_validator(mode="after")
+    def reject_duplicate_questions(self):
+        seen: set[str] = set()
+        seen_ids: set[str] = set()
+        for item in self.questions:
+            if item.id in seen_ids:
+                raise ValueError(f"配置 ID「{item.id}」重复")
+            seen_ids.add(item.id)
+            if item.question in seen:
+                raise ValueError(f"问题「{item.question}」重复")
+            seen.add(item.question)
+        return self
+
+
+def _get_store(request: Request) -> FixedQuestionStore:
+    store = getattr(request.app.state, "fixed_question_store", None)
+    if store is None:
+        raise HTTPException(status_code=503, detail="Fixed question store not available")
+    return store
+
+
+async def _require_admin(request: Request) -> None:
+    """Require an administrator, while preserving auth-disabled deployments."""
+    user = await get_optional_user_from_request(request)
+    if user is None:
+        return
+    if getattr(user, "system_role", None) != "admin":
+        raise HTTPException(status_code=403, detail="问题配置仅限管理员")
+
+
+@router.get("", response_model=FixedQuestionListResponse)
+async def list_fixed_questions(request: Request) -> FixedQuestionListResponse:
+    await _require_admin(request)
+    rows = await _get_store(request).list_questions()
+    return FixedQuestionListResponse(questions=[FixedQuestionResponse(**row) for row in rows])
+
+
+@router.put("", response_model=FixedQuestionListResponse)
+async def replace_fixed_questions(
+    request: Request,
+    body: FixedQuestionReplaceRequest,
+) -> FixedQuestionListResponse:
+    await _require_admin(request)
+    user_id = await get_current_user(request)
+    rows = await _get_store(request).replace_all(
+        [question.model_dump() for question in body.questions],
+        updated_by=user_id,
+    )
+    return FixedQuestionListResponse(questions=[FixedQuestionResponse(**row) for row in rows])

offline-backend-20260512/backend/app/gateway/routers/intent.py

@@ -29,7 +29,8 @@ SSE 协议（与前端 ``streamIntent`` 对齐）
      - ``done``：已解析 ``[INTENT_READY]`` + JSON 块，``summary`` 有值；
      - ``error``：上游或网关异常。
 
-   ``content`` — 展示用 AI 正文（澄清时优先用 tool 后的 follow-up 文本）。
+   ``content`` — 展示用 AI 正文（澄清时只保留 tool 调用前的简短引导；
+   tool 后的尾随文本会被丢弃，选项发出后立即等待用户选择）。
 
    仅 ``status == "done"`` 时带 ``summary``；澄清时还带
    ``question``、``clarification_type``、``clarification_context``、
@@ -625,6 +626,14 @@ async def stream_intent(request: Request, payload: dict = Body(...)) -> Streamin
                 # 2. message 前缀——给模型一个明确的"本轮必须收敛"信号。
                 # 仅文件、无文本时给一句兜底引导，让模型先读文件再澄清意图。
                 effective_message = message or "我上传了文件，请先阅读文件内容，再据此理解并澄清我的任务意图。"
+                if past_rounds < max_rounds:
+                    effective_message = (
+                        "[澄清输出硬约束] 如果本轮调用 ask_clarification，"
+                        "工具调用完成后必须立即停止输出并等待用户选择；"
+                        "禁止补充说明、复述选项、催促选择、追加问题或输出 "
+                        "[INTENT_READY]。需要确认的全部内容只能写入工具参数。\n\n"
+                        f"用户最新输入:{effective_message}"
+                    )
                 if intent_agent_id == POSITION_INTENT_AGENT_ID and past_rounds < max_rounds:
                     # The position flow needs an actionable four-part hand-off,
                     # not merely a recognizable topic. One turn may ask several
@@ -637,6 +646,8 @@ async def stream_intent(request: Request, payload: dict = Body(...)) -> Streamin
                         "ask_clarification；每个工具调用只能问一个决策点，不能把多项"
                         "问题合并成一张卡片。用户会一次性回答这些卡片。"
                         "如果四项意图已经足够明确，则直接输出最终结果。"
+                        "一旦调用完本轮所有 ask_clarification，必须立即停止输出，"
+                        "不要再补充说明、复述选项、催促选择或继续提问，等待用户选择。"
                         "不要以风险提示和战略意义为空的 [INTENT_READY] 结束。"
                         "本轮是第 %d/%d 轮用户协助；第 %d 轮若仍有缺口，必须把所有"
                         "剩余关键缺口分别发成卡片，收到回答后立即收敛。\n\n"
@@ -756,9 +767,6 @@ async def stream_intent(request: Request, payload: dict = Body(...)) -> Streamin
                 content = _flatten_content(dispatch_msg.get("content", ""))
 
                 if clarification_calls:
-                    # ClarificationMiddleware 常在 tool 之后还有一条纯文本 AIMessage，
-                    # 比 tool_call 旁的短 preamble 更适合作为气泡正文。
-                    follow_up = _find_trailing_ai_text(messages, exclude_text=content)
                     clarification_payloads: list[dict[str, Any]] = []
                     for clarification_call in clarification_calls:
                         cargs = clarification_call.get("args") or {}
@@ -790,6 +798,9 @@ async def stream_intent(request: Request, payload: dict = Body(...)) -> Streamin
                         )
 
                     if not clarification_payloads:
+                        # 这里只在所有卡片都因重复而被过滤时才允许使用 tool 后文本；
+                        # 此时前端没有选项需要等待，不属于澄清暂停态。
+                        follow_up = _find_trailing_ai_text(messages, exclude_text=content)
                         fallback_msg = (
                             follow_up
                             or content
@@ -805,7 +816,11 @@ async def stream_intent(request: Request, payload: dict = Body(...)) -> Streamin
                         return
 
                     first = clarification_payloads[0]
-                    display_content = follow_up or content or str(first["question"])
+                    # ask_clarification 是严格的回合终点。部分模型会在工具调用后
+                    # 再生成“请从以上选项中选择……”等尾随 AIMessage；不能把它
+                    # 返回给前端，否则用户看到卡片后还会继续冒出一段话。
+                    # 仅保留工具调用自身携带的前置短句；没有则直接由卡片展示问题。
+                    display_content = content
                     final_frame: dict[str, Any] = {
                         "status": "clarification",
                         "content": display_content,

offline-backend-20260512/backend/app/gateway/services.py

@@ -22,6 +22,7 @@ from langchain_core.messages import HumanMessage
 
 from app.gateway.deps import get_concurrency_gate, get_run_context, get_run_manager, get_stream_bridge
 from app.gateway.llmwiki_rag import (
+    LlmWikiRagContext,
     attach_llmwiki_rag_to_graph_input,
     build_llmwiki_rag_context,
     llmwiki_selection_requested,
@@ -227,6 +228,77 @@ def normalize_input(raw_input: dict[str, Any] | None) -> dict[str, Any]:
     return raw_input
 
 
+def _plain_fixed_question(graph_input: dict[str, Any]) -> str | None:
+    """Return the latest plain-text human turn eligible for exact matching.
+
+    Messages carrying files or multimodal blocks are intentionally excluded:
+    their answer depends on more than the visible question text, so replaying a
+    global fixed answer would be surprising and unsafe.
+    """
+
+    messages = graph_input.get("messages")
+    if not isinstance(messages, list) or not messages:
+        return None
+    message = messages[-1]
+    if not isinstance(message, HumanMessage):
+        return None
+    additional_kwargs = getattr(message, "additional_kwargs", {}) or {}
+    if any(
+        additional_kwargs.get(key)
+        for key in ("files", "uploaded_files", "attachments", "prompt_prefix")
+    ):
+        return None
+    content = getattr(message, "content", None)
+    if isinstance(content, str):
+        return content
+    if not isinstance(content, list):
+        return None
+    parts: list[str] = []
+    for item in content:
+        if isinstance(item, str):
+            parts.append(item)
+            continue
+        if not isinstance(item, Mapping):
+            return None
+        item_type = str(item.get("type") or "text")
+        text = item.get("text")
+        if item_type not in {"text", "input_text"} or not isinstance(text, str):
+            return None
+        parts.append(text)
+    return "".join(parts)
+
+
+async def _find_fixed_answer(
+    *,
+    body: Any,
+    request: Request,
+    graph_input: dict[str, Any],
+    run_scope: str,
+) -> dict[str, Any] | None:
+    """Look up an enabled exact match, falling back to the model on errors."""
+
+    if run_scope != RUN_SCOPE_EXTERNAL_ROOT or getattr(body, "command", None) is not None:
+        return None
+    assistant_id = str(getattr(body, "assistant_id", None) or _DEFAULT_ASSISTANT_ID)
+    if assistant_id in {"canvas_agent", "ai_writing"}:
+        return None
+    context = getattr(body, "context", None) or {}
+    if isinstance(context, Mapping) and context.get("writing_mode"):
+        return None
+    question = _plain_fixed_question(graph_input)
+    if question is None:
+        return None
+    store = getattr(request.app.state, "fixed_question_store", None)
+    if store is None:
+        return None
+    try:
+        return await store.find_enabled(question)
+    except Exception:
+        # Configuration storage must never make normal chat unavailable.
+        logger.warning("Fixed-question lookup failed; continuing with model", exc_info=True)
+        return None
+
+
 _DEFAULT_ASSISTANT_ID = "lead_agent"
 
 # Built-in LangGraph graph IDs registered in langgraph.json.
@@ -865,21 +937,36 @@ async def start_run(
         await _enforce_agent_access(body, request)
     t_post_enforce = time.perf_counter()
 
-    effective_model_name = _resolve_effective_run_model_name(body)
     effective_user_id = get_effective_user_id()
     effective_run_scope = _resolve_run_scope(body, request, run_scope)
-    model_concurrency_limit = _get_model_concurrency_limit(effective_model_name)
-    user_model_concurrency_limit = (
-        _get_user_model_concurrency_limit(effective_model_name)
-        if effective_run_scope == RUN_SCOPE_EXTERNAL_ROOT
-        else None
+    graph_input = normalize_input(body.input)
+    fixed_answer = await _find_fixed_answer(
+        body=body,
+        request=request,
+        graph_input=graph_input,
+        run_scope=effective_run_scope,
     )
+    if fixed_answer is not None:
+        effective_model_name = "fixed-answer"
+        model_concurrency_limit = None
+        user_model_concurrency_limit = None
+    else:
+        effective_model_name = _resolve_effective_run_model_name(body)
+        model_concurrency_limit = _get_model_concurrency_limit(effective_model_name)
+        user_model_concurrency_limit = (
+            _get_user_model_concurrency_limit(effective_model_name)
+            if effective_run_scope == RUN_SCOPE_EXTERNAL_ROOT
+            else None
+        )
     run_id = str(uuid.uuid4())
 
     run_metadata = dict(body.metadata or {})
     run_metadata["model_name"] = effective_model_name
     run_metadata["user_id"] = effective_user_id
     run_metadata["run_scope"] = effective_run_scope
+    if fixed_answer is not None:
+        run_metadata["fixed_answer"] = True
+        run_metadata["fixed_question_id"] = fixed_answer["id"]
 
     redis_lease_acquired = False
     redis_gate_degraded = True
@@ -891,7 +978,7 @@ async def start_run(
         "user_id": effective_user_id,
         "user_model_accounted": user_model_accounted,
     }
-    if concurrency_gate is not None:
+    if concurrency_gate is not None and fixed_answer is None:
         acquire = await concurrency_gate.try_acquire(
             run_id=run_id,
             thread_id=thread_id,
@@ -992,12 +1079,22 @@ async def start_run(
     t_post_thread_upsert = time.perf_counter()
 
     try:
-        agent_factory = resolve_agent_factory(body.assistant_id)
+        if fixed_answer is not None:
+            from deerflow.agents.fixed_answer_agent import make_fixed_answer_agent
+
+            def agent_factory(config):  # noqa: ANN001, ARG001 - worker factory contract
+                return make_fixed_answer_agent(
+                    question=str(fixed_answer["question"]),
+                    answer=str(fixed_answer["answer"]),
+                    fixed_question_id=str(fixed_answer["id"]),
+                    tokens_per_second=int(fixed_answer.get("tokens_per_second", 100)),
+                )
+        else:
+            agent_factory = resolve_agent_factory(body.assistant_id)
     except Exception:
         if concurrency_gate is not None and redis_lease_acquired:
             await concurrency_gate.release(**lease_metadata)
         raise
-    graph_input = normalize_input(body.input)
 
     # Admin-configurable prompt prefix: when the caller opted in via
     # context.prompt_prefix_enabled, tag the human message with the configured
@@ -1007,14 +1104,18 @@ async def start_run(
     # applies once. We intentionally do NOT gate on thread-row existence: the
     # thread_meta row is frequently pre-created, which previously skipped the
     # prefix for genuine first turns.
-    if _prompt_prefix_opted_in(body):
+    if fixed_answer is None and _prompt_prefix_opted_in(body):
         prefix_settings = load_system_settings().prompt_prefix
         if prefix_settings.enabled and prefix_settings.prompt_prefix.strip():
             graph_input = _prepend_prompt_prefix(graph_input, prefix_settings.prompt_prefix.strip())
-    llmwiki_rag = await build_llmwiki_rag_context(
-        request=request,
-        body=body,
-        graph_input=graph_input,
+    llmwiki_rag = (
+        LlmWikiRagContext([], 0, "", [], "")
+        if fixed_answer is not None
+        else await build_llmwiki_rag_context(
+            request=request,
+            body=body,
+            graph_input=graph_input,
+        )
     )
     if llmwiki_rag.prompt or llmwiki_rag.sources:
         graph_input = attach_llmwiki_rag_to_graph_input(graph_input, llmwiki_rag)

offline-backend-20260512/backend/packages/harness/deerflow/agents/fixed_answer_agent.py

@@ -0,0 +1,186 @@
+"""Small local streaming graph used for exact-match fixed answers.
+
+The graph deliberately uses a local ``BaseChatModel`` implementation so
+LangGraph emits the same token/message stream events as a normal model-backed
+answer, while making no network or model-provider request.
+"""
+
+from __future__ import annotations
+
+import asyncio
+import codecs
+import math
+import uuid
+from collections.abc import AsyncIterator, Sequence
+from typing import Any
+
+import tiktoken
+from langchain_core.callbacks import AsyncCallbackManagerForLLMRun, CallbackManagerForLLMRun
+from langchain_core.language_models.chat_models import BaseChatModel
+from langchain_core.messages import AIMessage, AIMessageChunk, BaseMessage
+from langchain_core.outputs import ChatGeneration, ChatGenerationChunk, ChatResult
+from langchain_core.runnables import RunnableConfig
+from langgraph.graph import END, START, StateGraph
+
+from deerflow.agents.thread_state import ThreadState
+
+_TOKEN_ENCODING = tiktoken.get_encoding("cl100k_base")
+_TARGET_CHUNKS_PER_SECOND = 10
+_MAX_TOKENS_PER_CHUNK = 20
+_MAX_TOKENS_PER_SECOND = 1_000
+
+
+class FixedAnswerChatModel(BaseChatModel):
+    """A local streaming model that only replays an administrator answer."""
+
+    answer: str
+    message_id: str
+    fixed_question_id: str
+    tokens_per_second: int = 100
+
+    @property
+    def _llm_type(self) -> str:
+        return "fixed-answer"
+
+    @property
+    def _identifying_params(self) -> dict[str, Any]:
+        return {
+            "fixed_question_id": self.fixed_question_id,
+            "tokens_per_second": self.tokens_per_second,
+        }
+
+    def _message(self) -> AIMessage:
+        return AIMessage(
+            content=self.answer,
+            id=self.message_id,
+            additional_kwargs={
+                "fixed_answer": True,
+                "fixed_question_id": self.fixed_question_id,
+                "tokens_per_second": self.tokens_per_second,
+            },
+        )
+
+    def _generate(
+        self,
+        messages: list[BaseMessage],
+        stop: list[str] | None = None,
+        run_manager: CallbackManagerForLLMRun | None = None,
+        **kwargs: Any,
+    ) -> ChatResult:
+        del messages, stop, run_manager, kwargs
+        return ChatResult(generations=[ChatGeneration(message=self._message())])
+
+    async def _astream(
+        self,
+        messages: list[BaseMessage],
+        stop: list[str] | None = None,
+        run_manager: AsyncCallbackManagerForLLMRun | None = None,
+        **kwargs: Any,
+    ) -> AsyncIterator[ChatGenerationChunk]:
+        del messages, stop, run_manager, kwargs
+        answer = self.answer
+        if not answer:
+            yield ChatGenerationChunk(message=AIMessageChunk(content="", id=self.message_id))
+            return
+        token_ids = _TOKEN_ENCODING.encode(answer, disallowed_special=())
+        tokens_per_second = max(
+            1,
+            min(_MAX_TOKENS_PER_SECOND, self.tokens_per_second),
+        )
+        chunk_size = max(
+            1,
+            min(
+                _MAX_TOKENS_PER_CHUNK,
+                math.ceil(tokens_per_second / _TARGET_CHUNKS_PER_SECOND),
+            ),
+        )
+        decoder = codecs.getincrementaldecoder("utf-8")()
+        token_groups = [token_ids[:1], *(token_ids[offset : offset + chunk_size] for offset in range(1, len(token_ids), chunk_size))]
+        for index, chunk_token_ids in enumerate(token_groups):
+            if index > 0:
+                await asyncio.sleep(len(chunk_token_ids) / tokens_per_second)
+            chunk_bytes = b"".join(_TOKEN_ENCODING.decode_single_token_bytes(token_id) for token_id in chunk_token_ids)
+            is_last = index == len(token_groups) - 1
+            content = decoder.decode(chunk_bytes, final=is_last)
+            chunk_kwargs = (
+                {
+                    "fixed_answer": True,
+                    "fixed_question_id": self.fixed_question_id,
+                    "tokens_per_second": tokens_per_second,
+                }
+                if index == 0
+                else {}
+            )
+            yield ChatGenerationChunk(
+                message=AIMessageChunk(
+                    content=content,
+                    id=self.message_id,
+                    additional_kwargs=chunk_kwargs,
+                )
+            )
+
+
+def _fallback_title(question: str) -> str:
+    if len(question) > 50:
+        return question[:50].rstrip() + "..."
+    return question or "New Conversation"
+
+
+def make_fixed_answer_agent(
+    *,
+    question: str,
+    answer: str,
+    fixed_question_id: str,
+    tokens_per_second: int = 100,
+):
+    """Build a one-node graph that streams and persists a fixed answer."""
+
+    tokens_per_second = max(
+        1,
+        min(_MAX_TOKENS_PER_SECOND, int(tokens_per_second)),
+    )
+    message_id = f"fixed-answer-{uuid.uuid4()}"
+    model = FixedAnswerChatModel(
+        answer=answer,
+        message_id=message_id,
+        fixed_question_id=fixed_question_id,
+        tokens_per_second=tokens_per_second,
+    ).with_config(tags=["fixed-answer"])
+
+    async def respond(
+        state: ThreadState,
+        config: RunnableConfig,
+    ) -> dict[str, Any]:
+        messages: Sequence[BaseMessage] = state.get("messages", [])
+        # Calling the local model through ``astream`` makes the runtime publish
+        # normal messages-mode chunks. The full AIMessage returned below is the
+        # durable checkpoint value used on refresh/history reads.
+        async for _chunk in model.astream(list(messages), config=config):
+            pass
+        update: dict[str, Any] = {
+            "messages": [
+                AIMessage(
+                    content=answer,
+                    id=message_id,
+                    additional_kwargs={
+                        "fixed_answer": True,
+                        "fixed_question_id": fixed_question_id,
+                        "tokens_per_second": tokens_per_second,
+                    },
+                )
+            ]
+        }
+        if not state.get("title"):
+            update["title"] = _fallback_title(question)
+            update["title_provisional"] = False
+        elif state.get("title_provisional") is True:
+            # A fixed-answer run must not trigger the worker's background LLM
+            # title finalizer either; keep the already-visible local title.
+            update["title_provisional"] = False
+        return update
+
+    graph = StateGraph(ThreadState)
+    graph.add_node("fixed_answer", respond)
+    graph.add_edge(START, "fixed_answer")
+    graph.add_edge("fixed_answer", END)
+    return graph.compile()

offline-backend-20260512/backend/packages/harness/deerflow/persistence/fixed_questions/__init__.py

@@ -0,0 +1,22 @@
+"""Exact-match fixed-question persistence."""
+
+from __future__ import annotations
+
+from deerflow.persistence.fixed_questions.base import FixedQuestionStore
+from deerflow.persistence.fixed_questions.memory import MemoryFixedQuestionStore
+from deerflow.persistence.fixed_questions.model import FixedQuestionRow
+from deerflow.persistence.fixed_questions.sql import FixedQuestionRepository
+
+__all__ = [
+    "FixedQuestionRepository",
+    "FixedQuestionRow",
+    "FixedQuestionStore",
+    "MemoryFixedQuestionStore",
+    "make_fixed_question_store",
+]
+
+
+def make_fixed_question_store(session_factory):
+    if session_factory is None:
+        return MemoryFixedQuestionStore()
+    return FixedQuestionRepository(session_factory)

offline-backend-20260512/backend/packages/harness/deerflow/persistence/fixed_questions/base.py

@@ -0,0 +1,30 @@
+"""Abstract persistence API for administrator-managed fixed questions."""
+
+from __future__ import annotations
+
+from abc import ABC, abstractmethod
+from typing import Any
+
+
+class FixedQuestionStore(ABC):
+    """Global fixed-question configuration shared by every account."""
+
+    @abstractmethod
+    async def list_questions(self) -> list[dict[str, Any]]:
+        """Return every configured question in display order."""
+        raise NotImplementedError
+
+    @abstractmethod
+    async def find_enabled(self, question: str) -> dict[str, Any] | None:
+        """Return the enabled row whose question exactly equals ``question``."""
+        raise NotImplementedError
+
+    @abstractmethod
+    async def replace_all(
+        self,
+        rows: list[dict[str, Any]],
+        *,
+        updated_by: str | None = None,
+    ) -> list[dict[str, Any]]:
+        """Atomically replace the complete fixed-question configuration."""
+        raise NotImplementedError

offline-backend-20260512/backend/packages/harness/deerflow/persistence/fixed_questions/memory.py

@@ -0,0 +1,56 @@
+"""In-memory fixed-question store used by memory deployments and tests."""
+
+from __future__ import annotations
+
+from datetime import UTC, datetime
+from typing import Any
+
+from deerflow.persistence.fixed_questions.base import FixedQuestionStore
+
+
+def _normalize(data: dict[str, Any], updated_by: str | None) -> dict[str, Any]:
+    return {
+        "id": str(data["id"]),
+        "question": str(data.get("question") or ""),
+        "answer": str(data.get("answer") or ""),
+        "enabled": bool(data.get("enabled", True)),
+        "tokens_per_second": int(data.get("tokens_per_second", 100)),
+        "sort_order": int(data.get("sort_order", 0)),
+        "updated_by": updated_by,
+        "updated_at": datetime.now(UTC).isoformat(),
+    }
+
+
+class MemoryFixedQuestionStore(FixedQuestionStore):
+    def __init__(self) -> None:
+        self._rows: dict[str, dict[str, Any]] = {}
+
+    async def list_questions(self) -> list[dict[str, Any]]:
+        rows = sorted(
+            self._rows.values(),
+            key=lambda row: (row.get("sort_order", 0), row.get("question", "")),
+        )
+        return [dict(row) for row in rows]
+
+    async def find_enabled(self, question: str) -> dict[str, Any] | None:
+        for row in self._rows.values():
+            if row["enabled"] and row["question"] == question:
+                return dict(row)
+        return None
+
+    async def replace_all(
+        self,
+        rows: list[dict[str, Any]],
+        *,
+        updated_by: str | None = None,
+    ) -> list[dict[str, Any]]:
+        # Last duplicate question wins, mirroring the SQL repository.
+        by_id: dict[str, dict[str, Any]] = {}
+        for row in rows:
+            question = row.get("question")
+            row_id = row.get("id")
+            if row_id and question not in (None, ""):
+                by_id[str(row_id)] = row
+        by_question = {str(row["question"]): row for row in by_id.values()}
+        self._rows = {str(row["id"]): _normalize(row, updated_by) for row in by_question.values()}
+        return await self.list_questions()

offline-backend-20260512/backend/packages/harness/deerflow/persistence/fixed_questions/model.py

@@ -0,0 +1,41 @@
+"""ORM model for exact-match, administrator-managed fixed questions."""
+
+from __future__ import annotations
+
+from datetime import UTC, datetime
+
+from sqlalchemy import Boolean, Integer, String, Text, UniqueConstraint
+from sqlalchemy.orm import Mapped, mapped_column
+
+from deerflow.persistence.base import Base
+from deerflow.persistence.types import BeijingDateTime, PortableLongText
+
+
+class FixedQuestionRow(Base):
+    """One globally shared question/answer pair.
+
+    ``question_hash`` provides a portable indexed lookup for questions stored in
+    ``Text``. The repository always compares the original question as well, so a
+    theoretical SHA-256 collision cannot cause a false match.
+    """
+
+    __tablename__ = "fixed_questions"
+    __table_args__ = (UniqueConstraint("question_hash", name="uq_fixed_questions_question_hash"),)
+
+    id: Mapped[str] = mapped_column(String(64), primary_key=True)
+    question: Mapped[str] = mapped_column(Text, nullable=False)
+    question_hash: Mapped[str] = mapped_column(String(64), nullable=False, index=True)
+    answer: Mapped[str] = mapped_column(PortableLongText, nullable=False)
+    enabled: Mapped[bool] = mapped_column(Boolean, default=True, server_default="1")
+    tokens_per_second: Mapped[int] = mapped_column(
+        Integer,
+        default=100,
+        server_default="100",
+    )
+    sort_order: Mapped[int] = mapped_column(Integer, default=0, server_default="0")
+    updated_by: Mapped[str | None] = mapped_column(String(64), nullable=True)
+    updated_at: Mapped[datetime] = mapped_column(
+        BeijingDateTime(),
+        default=lambda: datetime.now(UTC),
+        onupdate=lambda: datetime.now(UTC),
+    )

offline-backend-20260512/backend/packages/harness/deerflow/persistence/fixed_questions/sql.py

@@ -0,0 +1,88 @@
+"""SQLAlchemy-backed fixed-question store."""
+
+from __future__ import annotations
+
+import hashlib
+from datetime import datetime
+from typing import Any
+
+from sqlalchemy import delete, select
+from sqlalchemy.ext.asyncio import AsyncSession, async_sessionmaker
+
+from deerflow.persistence.fixed_questions.base import FixedQuestionStore
+from deerflow.persistence.fixed_questions.model import FixedQuestionRow
+
+
+def question_hash(question: str) -> str:
+    return hashlib.sha256(question.encode("utf-8")).hexdigest()
+
+
+def _to_dict(row: FixedQuestionRow) -> dict[str, Any]:
+    data = row.to_dict()
+    data.pop("question_hash", None)
+    value = data.get("updated_at")
+    if isinstance(value, datetime):
+        data["updated_at"] = value.isoformat()
+    return data
+
+
+def _row_from(data: dict[str, Any], updated_by: str | None) -> FixedQuestionRow:
+    question = str(data.get("question") or "")
+    return FixedQuestionRow(
+        id=str(data["id"]),
+        question=question,
+        question_hash=question_hash(question),
+        answer=str(data.get("answer") or ""),
+        enabled=bool(data.get("enabled", True)),
+        tokens_per_second=int(data.get("tokens_per_second", 100)),
+        sort_order=int(data.get("sort_order", 0)),
+        updated_by=updated_by,
+    )
+
+
+class FixedQuestionRepository(FixedQuestionStore):
+    def __init__(self, session_factory: async_sessionmaker[AsyncSession]) -> None:
+        self._sf = session_factory
+
+    async def list_questions(self) -> list[dict[str, Any]]:
+        stmt = select(FixedQuestionRow).order_by(
+            FixedQuestionRow.sort_order.asc(),
+            FixedQuestionRow.question.asc(),
+        )
+        async with self._sf() as session:
+            result = await session.execute(stmt)
+            return [_to_dict(row) for row in result.scalars()]
+
+    async def find_enabled(self, question: str) -> dict[str, Any] | None:
+        stmt = select(FixedQuestionRow).where(
+            FixedQuestionRow.question_hash == question_hash(question),
+            FixedQuestionRow.enabled.is_(True),
+        )
+        async with self._sf() as session:
+            row = (await session.execute(stmt)).scalar_one_or_none()
+            if row is None or row.question != question:
+                return None
+            return _to_dict(row)
+
+    async def replace_all(
+        self,
+        rows: list[dict[str, Any]],
+        *,
+        updated_by: str | None = None,
+    ) -> list[dict[str, Any]]:
+        # Last duplicate question wins, preventing a unique-hash violation even
+        # if a non-UI caller submits malformed data.
+        by_id: dict[str, dict[str, Any]] = {}
+        for row in rows:
+            question = row.get("question")
+            row_id = row.get("id")
+            if row_id and question not in (None, ""):
+                by_id[str(row_id)] = row
+        by_question = {str(row["question"]): row for row in by_id.values()}
+
+        async with self._sf() as session:
+            await session.execute(delete(FixedQuestionRow))
+            new_rows = [_row_from(row, updated_by) for row in by_question.values()]
+            session.add_all(new_rows)
+            await session.commit()
+            return [_to_dict(row) for row in new_rows]

offline-backend-20260512/backend/packages/harness/deerflow/persistence/migrations/versions/20260821_01_fixed_questions.py

@@ -0,0 +1,51 @@
+"""Create administrator-managed exact-match fixed questions.
+
+Revision ID: 20260821_01
+Revises: 20260816_01
+Create Date: 2026-08-21
+"""
+
+from __future__ import annotations
+
+import sqlalchemy as sa
+from alembic import op
+from sqlalchemy.dialects import mysql
+
+revision = "20260821_01"
+down_revision = "20260816_01"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    bind = op.get_bind()
+    if sa.inspect(bind).has_table("fixed_questions"):
+        return
+    long_text = sa.Text().with_variant(mysql.LONGTEXT(), "mysql")
+    op.create_table(
+        "fixed_questions",
+        sa.Column("id", sa.String(length=64), primary_key=True),
+        sa.Column("question", sa.Text(), nullable=False),
+        sa.Column("question_hash", sa.String(length=64), nullable=False),
+        sa.Column("answer", long_text, nullable=False),
+        sa.Column("enabled", sa.Boolean(), nullable=False, server_default=sa.true()),
+        sa.Column("sort_order", sa.Integer(), nullable=False, server_default="0"),
+        sa.Column("updated_by", sa.String(length=64), nullable=True),
+        sa.Column("updated_at", sa.DateTime(timezone=True), nullable=False),
+        sa.UniqueConstraint(
+            "question_hash",
+            name="uq_fixed_questions_question_hash",
+        ),
+    )
+    op.create_index(
+        "ix_fixed_questions_question_hash",
+        "fixed_questions",
+        ["question_hash"],
+        unique=False,
+    )
+
+
+def downgrade() -> None:
+    bind = op.get_bind()
+    if sa.inspect(bind).has_table("fixed_questions"):
+        op.drop_table("fixed_questions")

offline-backend-20260512/backend/packages/harness/deerflow/persistence/migrations/versions/20260821_02_fixed_question_stream_speed.py

@@ -0,0 +1,44 @@
+"""Add configurable fixed-answer streaming speed.
+
+Revision ID: 20260821_02
+Revises: 20260821_01
+Create Date: 2026-08-21
+"""
+
+from __future__ import annotations
+
+import sqlalchemy as sa
+from alembic import op
+
+revision = "20260821_02"
+down_revision = "20260821_01"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    bind = op.get_bind()
+    inspector = sa.inspect(bind)
+    if not inspector.has_table("fixed_questions"):
+        return
+    columns = {column["name"] for column in inspector.get_columns("fixed_questions")}
+    if "tokens_per_second" not in columns:
+        op.add_column(
+            "fixed_questions",
+            sa.Column(
+                "tokens_per_second",
+                sa.Integer(),
+                nullable=False,
+                server_default="100",
+            ),
+        )
+
+
+def downgrade() -> None:
+    bind = op.get_bind()
+    inspector = sa.inspect(bind)
+    if not inspector.has_table("fixed_questions"):
+        return
+    columns = {column["name"] for column in inspector.get_columns("fixed_questions")}
+    if "tokens_per_second" in columns:
+        op.drop_column("fixed_questions", "tokens_per_second")

offline-backend-20260512/backend/packages/harness/deerflow/persistence/models/__init__.py

@@ -47,6 +47,7 @@ from deerflow.persistence.deep_research_sources.model import DeepResearchSourceR
 from deerflow.persistence.document_rewrite_versions.model import DocumentRewriteVersionRow
 from deerflow.persistence.embed_sessions.model import EmbedSessionRow
 from deerflow.persistence.feedback.model import FeedbackRow
+from deerflow.persistence.fixed_questions.model import FixedQuestionRow
 from deerflow.persistence.intent_turns.model import IntentTurnRow
 from deerflow.persistence.light_apps.model import LightAppRow
 from deerflow.persistence.llm_metrics.model import LlmCallMetricRow
@@ -97,6 +98,7 @@ from deerflow.persistence.user_prompts.model import UserCustomPromptRow
 
 __all__ = [
     "FeedbackRow",
+    "FixedQuestionRow",
     "AgentExtrasRow",
     "AgentFavoriteRow",
     "AgentRow",

offline-backend-20260512/backend/tests/test_fixed_questions.py

@@ -0,0 +1,288 @@
+"""Regression tests for administrator-managed exact-match fixed answers."""
+
+from __future__ import annotations
+
+from types import SimpleNamespace
+
+import pytest
+from langchain_core.messages import HumanMessage
+from pydantic import ValidationError
+from sqlalchemy.ext.asyncio import async_sessionmaker, create_async_engine
+
+from app.gateway.routers.fixed_questions import (
+    FixedQuestion,
+    FixedQuestionReplaceRequest,
+)
+from app.gateway.services import (
+    RUN_SCOPE_EXTERNAL_ROOT,
+    RUN_SCOPE_ORCHESTRATION_CHILD,
+    _find_fixed_answer,
+    normalize_input,
+)
+from deerflow.agents import fixed_answer_agent as fixed_answer_module
+from deerflow.agents.fixed_answer_agent import make_fixed_answer_agent
+from deerflow.persistence.fixed_questions import MemoryFixedQuestionStore
+from deerflow.persistence.fixed_questions.model import FixedQuestionRow
+from deerflow.persistence.fixed_questions.sql import FixedQuestionRepository
+
+
+def _body(**overrides):
+    data = {
+        "assistant_id": "lead_agent",
+        "command": None,
+        "context": {},
+    }
+    data.update(overrides)
+    return SimpleNamespace(**data)
+
+
+def _request(store: MemoryFixedQuestionStore):
+    return SimpleNamespace(
+        app=SimpleNamespace(
+            state=SimpleNamespace(fixed_question_store=store),
+        )
+    )
+
+
+@pytest.mark.asyncio
+async def test_memory_store_matches_only_enabled_exact_question() -> None:
+    store = MemoryFixedQuestionStore()
+    await store.replace_all(
+        [
+            {
+                "id": "enabled",
+                "question": "系统开放时间？",
+                "answer": "工作日 09:00—18:00。",
+                "enabled": True,
+                "tokens_per_second": 80,
+                "sort_order": 0,
+            },
+            {
+                "id": "disabled",
+                "question": "停用问题",
+                "answer": "不应返回",
+                "enabled": False,
+                "sort_order": 1,
+            },
+        ]
+    )
+
+    match = await store.find_enabled("系统开放时间？")
+    assert match is not None
+    assert match["answer"] == "工作日 09:00—18:00。"
+    assert match["tokens_per_second"] == 80
+    assert await store.find_enabled("系统开放时间?") is None
+    assert await store.find_enabled(" 系统开放时间？") is None
+    assert await store.find_enabled("停用问题") is None
+
+
+@pytest.mark.asyncio
+async def test_sql_store_round_trips_and_exact_matches() -> None:
+    engine = create_async_engine("sqlite+aiosqlite:///:memory:")
+    try:
+        async with engine.begin() as connection:
+            await connection.run_sync(FixedQuestionRow.__table__.create)
+        repository = FixedQuestionRepository(async_sessionmaker(engine, expire_on_commit=False))
+        saved = await repository.replace_all(
+            [
+                {
+                    "id": "sql-q1",
+                    "question": "SQL 精确问题",
+                    "answer": "SQL 固定回答",
+                    "enabled": True,
+                    "tokens_per_second": 120,
+                    "sort_order": 0,
+                }
+            ],
+            updated_by="admin",
+        )
+        assert saved[0]["updated_by"] == "admin"
+        assert saved[0]["tokens_per_second"] == 120
+        assert (await repository.find_enabled("SQL 精确问题"))["answer"] == "SQL 固定回答"
+        assert await repository.find_enabled("sql 精确问题") is None
+    finally:
+        await engine.dispose()
+
+
+@pytest.mark.asyncio
+async def test_lookup_skips_attachments_and_internal_runs() -> None:
+    store = MemoryFixedQuestionStore()
+    await store.replace_all(
+        [
+            {
+                "id": "q1",
+                "question": "固定问题",
+                "answer": "固定回答",
+                "enabled": True,
+                "sort_order": 0,
+            }
+        ]
+    )
+    request = _request(store)
+
+    plain_input = normalize_input({"messages": [{"content": "固定问题"}]})
+    match = await _find_fixed_answer(
+        body=_body(),
+        request=request,
+        graph_input=plain_input,
+        run_scope=RUN_SCOPE_EXTERNAL_ROOT,
+    )
+    assert match is not None
+    assert match["id"] == "q1"
+
+    attachment_input = normalize_input(
+        {
+            "messages": [
+                {
+                    "content": "固定问题",
+                    "additional_kwargs": {"files": [{"name": "context.pdf"}]},
+                }
+            ]
+        }
+    )
+    assert (
+        await _find_fixed_answer(
+            body=_body(),
+            request=request,
+            graph_input=attachment_input,
+            run_scope=RUN_SCOPE_EXTERNAL_ROOT,
+        )
+        is None
+    )
+    contextual_input = normalize_input(
+        {
+            "messages": [
+                {
+                    "content": "固定问题",
+                    "additional_kwargs": {"prompt_prefix": "网页正文上下文"},
+                }
+            ]
+        }
+    )
+    assert (
+        await _find_fixed_answer(
+            body=_body(),
+            request=request,
+            graph_input=contextual_input,
+            run_scope=RUN_SCOPE_EXTERNAL_ROOT,
+        )
+        is None
+    )
+    assert (
+        await _find_fixed_answer(
+            body=_body(),
+            request=request,
+            graph_input=plain_input,
+            run_scope=RUN_SCOPE_ORCHESTRATION_CHILD,
+        )
+        is None
+    )
+
+
+@pytest.mark.asyncio
+async def test_fixed_answer_agent_streams_chunks_and_persists_full_answer() -> None:
+    question = "固定问题"
+    answer = "这是一个足够长的固定回答，用于验证返回内容会拆成多个流式消息块，同时完整写入会话状态。"
+    agent = make_fixed_answer_agent(
+        question=question,
+        answer=answer,
+        fixed_question_id="q1",
+        tokens_per_second=1000,
+    )
+
+    chunks: list[str] = []
+    final_state = None
+    async for mode, data in agent.astream(
+        {"messages": [HumanMessage(content=question)]},
+        stream_mode=["values", "messages"],
+    ):
+        if mode == "messages":
+            message, _metadata = data
+            if isinstance(message.content, str):
+                chunks.append(message.content)
+        elif mode == "values":
+            final_state = data
+
+    assert "".join(chunks) == answer
+    assert len([chunk for chunk in chunks if chunk]) >= 2
+    assert final_state is not None
+    assert final_state["messages"][-1].content == answer
+    assert final_state["messages"][-1].additional_kwargs["fixed_answer"] is True
+    assert final_state["messages"][-1].additional_kwargs["tokens_per_second"] == 1000
+    assert final_state["title"] == question
+    assert final_state["title_provisional"] is False
+
+
+@pytest.mark.asyncio
+async def test_fixed_answer_default_speed_schedules_100_tokens_per_second(
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    answer = "one two three four five six seven eight nine ten eleven twelve thirteen"
+    sleeps: list[float] = []
+
+    async def record_sleep(delay: float) -> None:
+        sleeps.append(delay)
+
+    monkeypatch.setattr(fixed_answer_module.asyncio, "sleep", record_sleep)
+    model = fixed_answer_module.FixedAnswerChatModel(
+        answer=answer,
+        message_id="speed-test",
+        fixed_question_id="q-speed",
+    )
+
+    chunks: list[str] = []
+    async for generation in model._astream([]):
+        chunks.append(str(generation.message.content))
+
+    token_count = len(fixed_answer_module._TOKEN_ENCODING.encode(answer))
+    assert "".join(chunks) == answer
+    assert model.tokens_per_second == 100
+    assert sum(sleeps) == pytest.approx((token_count - 1) / 100)
+
+
+def test_replace_request_rejects_duplicate_exact_questions() -> None:
+    row = {
+        "question": "重复问题",
+        "answer": "回答",
+        "enabled": True,
+        "tokens_per_second": 100,
+        "sort_order": 0,
+    }
+    with pytest.raises(ValidationError):
+        FixedQuestionReplaceRequest(
+            questions=[
+                FixedQuestion(id="q1", **row),
+                FixedQuestion(id="q2", **row),
+            ]
+        )
+    with pytest.raises(ValidationError):
+        FixedQuestionReplaceRequest(
+            questions=[
+                FixedQuestion(id="same-id", **row),
+                FixedQuestion(
+                    id="same-id",
+                    question="另一个问题",
+                    answer="另一个回答",
+                    enabled=True,
+                    sort_order=1,
+                ),
+            ]
+        )
+
+
+def test_fixed_question_stream_speed_defaults_and_bounds() -> None:
+    default_row = FixedQuestion(
+        id="default-speed",
+        question="默认速度",
+        answer="回答",
+    )
+    assert default_row.tokens_per_second == 100
+
+    for invalid_speed in (0, 1001):
+        with pytest.raises(ValidationError):
+            FixedQuestion(
+                id=f"invalid-{invalid_speed}",
+                question="非法速度",
+                answer="回答",
+                tokens_per_second=invalid_speed,
+            )

offline-backend-20260512/backend/tests/test_health_auth_bypass.py

@@ -2,12 +2,15 @@
 
 from __future__ import annotations
 
+from types import SimpleNamespace
+
 import pytest
 from fastapi import FastAPI
 from fastapi.testclient import TestClient
 
 from app.gateway import auth_middleware
 from app.gateway.app import app as gateway_app
+from app.gateway.auth.token_source import get_explicit_or_session_token
 from app.gateway.auth_middleware import PUBLIC_HEALTH_PATHS, AuthMiddleware
 
 
@@ -98,3 +101,28 @@ def test_non_health_route_still_requires_auth(monkeypatch: pytest.MonkeyPatch) -
         response = client.get("/private")
 
     assert response.status_code == 401
+
+
+def _auth_request(*, authorization: str = "", cookie: str = "") -> SimpleNamespace:
+    headers = {"authorization": authorization} if authorization else {}
+    cookies = {"access_token": cookie} if cookie else {}
+    return SimpleNamespace(headers=headers, cookies=cookies)
+
+
+def test_explicit_bearer_token_wins_over_shared_cookie() -> None:
+    """Another tab's cookie must not override this tab's explicit token."""
+    request = _auth_request(authorization="Bearer current-tab", cookie="other-tab")
+
+    assert get_explicit_or_session_token(request) == "current-tab"
+
+
+def test_cookie_remains_the_fallback_for_cookie_only_clients() -> None:
+    request = _auth_request(cookie="browser-session")
+
+    assert get_explicit_or_session_token(request) == "browser-session"
+
+
+def test_malformed_authorization_header_does_not_hide_valid_cookie() -> None:
+    request = _auth_request(authorization="Basic abc", cookie="browser-session")
+
+    assert get_explicit_or_session_token(request) == "browser-session"

offline-backend-20260512/backend/tests/test_username_login_domain.py

@@ -9,15 +9,18 @@ Verifies that:
 
 from __future__ import annotations
 
-import os
 from datetime import UTC, datetime
-from uuid import UUID, uuid4
+from uuid import uuid4
 
 import pytest
 
+from app.gateway.auth.local_provider import LocalAuthProvider
 from app.gateway.auth.models import User
 from app.gateway.auth.repositories.base import UserRepository
+from app.gateway.routers import auth as auth_module
 from app.gateway.routers.auth import (
+    _get_or_create_user_by_username,
+    _lookup_user_by_username,
     _normalize_username_local_part,
     _username_to_email,
 )
@@ -74,6 +77,9 @@ class FakeUserRepository(UserRepository):
     async def count_admin_users(self) -> int:
         return sum(1 for u in self.rows.values() if u.system_role == "admin")
 
+    async def list_users(self) -> list[User]:
+        return sorted(self.rows.values(), key=lambda user: user.created_at)
+
     async def get_user_by_oauth(self, provider: str, oauth_id: str) -> User | None:
         return None
 
@@ -146,3 +152,38 @@ async def test_local_part_lookup_misses_unknown_username() -> None:
     repo = FakeUserRepository()
     _seed(repo, "alice@cm.com")
     assert await repo.find_user_by_email_local_part("bob") is None
+
+
+@pytest.mark.asyncio
+async def test_username_login_uses_oldest_account_when_canonical_duplicate_exists(
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    """A domain migration must not make one username alternate user ids."""
+    repo = FakeUserRepository()
+    older = _seed(repo, "alice@local.deerflow")
+    older.created_at = datetime(2024, 1, 1, tzinfo=UTC)
+    newer = _seed(repo, "alice@cm.com")
+    newer.created_at = datetime(2026, 1, 1, tzinfo=UTC)
+    monkeypatch.setattr(auth_module, "get_local_provider", lambda: LocalAuthProvider(repo))
+
+    user, created = await _get_or_create_user_by_username("alice")
+
+    assert created is False
+    assert user.id == older.id
+
+
+@pytest.mark.asyncio
+async def test_password_lookup_uses_same_stable_username_account(
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    repo = FakeUserRepository()
+    older = _seed(repo, "alice@local.deerflow")
+    older.created_at = datetime(2024, 1, 1, tzinfo=UTC)
+    newer = _seed(repo, "alice@cm.com")
+    newer.created_at = datetime(2026, 1, 1, tzinfo=UTC)
+    monkeypatch.setattr(auth_module, "get_local_provider", lambda: LocalAuthProvider(repo))
+
+    user = await _lookup_user_by_username("alice")
+
+    assert user is not None
+    assert user.id == older.id