feat(suggest_agent): stop frontend from fetching when suggestions disabled (#3599)

* feat(suggest_agent): stop frontend from fetching when suggestions disabled

* wait for suggestions config to load before fetching

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>

backend/CLAUDE.md

@@ -272,7 +272,7 @@ CORS is same-origin by default when requests enter through nginx on port 2026. S
 | **Uploads** (`/api/threads/{id}/uploads`) | `POST /` - upload files (auto-converts PDF/PPT/Excel/Word); `GET /list` - list; `DELETE /{filename}` - delete |
 | **Threads** (`/api/threads/{id}`) | `DELETE /` - remove DeerFlow-managed local thread data after LangGraph thread deletion; unexpected failures are logged server-side and return a generic 500 detail |
 | **Artifacts** (`/api/threads/{id}/artifacts`) | `GET /{path}` - serve artifacts; active content types (`text/html`, `application/xhtml+xml`, `image/svg+xml`) are always forced as download attachments to reduce XSS risk; `?download=true` still forces download for other file types |
-| **Suggestions** (`/api/threads/{id}/suggestions`) | `POST /` - generate follow-up questions; rich list/block model content is normalized and inline reasoning (`<think>...</think>`, including unclosed/truncated blocks from reasoning models like MiniMax-M3) is stripped before JSON parsing |
+| **Suggestions** (`/api/suggestions`) | `GET /config` - returns global suggestions config boolean; `POST /threads/{id}/suggestions` - generate follow-up questions; rich list/block model content is normalized and inline reasoning (`<think>...</think>`, including unclosed/truncated blocks from reasoning models like MiniMax-M3) is stripped before JSON parsing |
 | **Thread Runs** (`/api/threads/{id}/runs`) | `POST /` - create background run; `POST /stream` - create + SSE stream; `POST /wait` - create + block; `GET /` - list runs; `GET /{rid}` - run details; `POST /{rid}/cancel` - cancel; `GET /{rid}/join` - join SSE; `GET /{rid}/messages` - paginated messages `{data, has_more}`; `GET /{rid}/events` - full event stream; `GET /../messages` - thread messages with feedback; `GET /../token-usage` - aggregate tokens |
 | **Feedback** (`/api/threads/{id}/runs/{rid}/feedback`) | `PUT /` - upsert feedback; `DELETE /` - delete user feedback; `POST /` - create feedback; `GET /` - list feedback; `GET /stats` - aggregate stats; `DELETE /{fid}` - delete specific |
 | **Runs** (`/api/runs`) | `POST /stream` - stateless run + SSE; `POST /wait` - stateless run + block; `GET /{rid}/messages` - paginated messages by run_id `{data, has_more}` (cursor: `after_seq`/`before_seq`); `GET /{rid}/feedback` - list feedback by run_id |

backend/app/gateway/routers/suggestions.py

@@ -31,6 +31,10 @@ class SuggestionsResponse(BaseModel):
     suggestions: list[str] = Field(default_factory=list, description="Suggested follow-up questions")
 
 
+class SuggestionsConfigResponse(BaseModel):
+    enabled: bool = Field(..., description="Whether follow-up suggestions are enabled globally")
+
+
 # Matches a complete <think>...</think> block (case-insensitive, spans newlines).
 _THINK_BLOCK_RE = re.compile(r"<think\b[^>]*>.*?</think\s*>", re.IGNORECASE | re.DOTALL)
 # Matches a dangling, unclosed <think> (model truncated at max_tokens mid-thought).
@@ -122,6 +126,18 @@ def _format_conversation(messages: list[SuggestionMessage]) -> str:
     return "\n".join(parts).strip()
 
 
+@router.get(
+    "/suggestions/config",
+    response_model=SuggestionsConfigResponse,
+    summary="Get Suggestions Configuration",
+    description="Returns the global configuration for follow-up suggestions.",
+)
+async def get_suggestions_config(
+    config: AppConfig = Depends(get_config),
+) -> SuggestionsConfigResponse:
+    return SuggestionsConfigResponse(enabled=config.suggestions.enabled)
+
+
 @router.post(
     "/threads/{thread_id}/suggestions",
     response_model=SuggestionsResponse,

backend/tests/test_suggestions_router.py

@@ -192,3 +192,17 @@ def test_generate_suggestions_returns_empty_when_disabled(monkeypatch):
 
     assert result.suggestions == []
     fake_model.ainvoke.assert_not_called()
+
+
+def test_get_suggestions_config():
+    """Ensure the GET /config endpoint correctly returns the boolean state."""
+
+    # Test when enabled
+    mock_config_true = SimpleNamespace(suggestions=SimpleNamespace(enabled=True))
+    result_true = asyncio.run(suggestions.get_suggestions_config(config=mock_config_true))
+    assert result_true.enabled is True
+
+    # Test when disabled
+    mock_config_false = SimpleNamespace(suggestions=SimpleNamespace(enabled=False))
+    result_false = asyncio.run(suggestions.get_suggestions_config(config=mock_config_false))
+    assert result_false.enabled is False

frontend/src/components/workspace/input-box.tsx

@@ -62,6 +62,7 @@ import { useI18n } from "@/core/i18n/hooks";
 import { useModels } from "@/core/models/hooks";
 import type { Skill } from "@/core/skills";
 import { useSkills } from "@/core/skills/hooks";
+import { useSuggestionsConfig } from "@/core/suggestions/hooks";
 import type { AgentThreadContext } from "@/core/threads";
 import { textOfMessage } from "@/core/threads/utils";
 import { cn } from "@/lib/utils";
@@ -203,6 +204,7 @@ export function InputBox({
   const textareaRef = useRef<HTMLTextAreaElement | null>(null);
 
   const [followups, setFollowups] = useState<string[]>([]);
+  const { data: suggestionsConfig } = useSuggestionsConfig();
   const [followupsHidden, setFollowupsHidden] = useState(false);
   const [followupsLoading, setFollowupsLoading] = useState(false);
   const [textareaFocused, setTextareaFocused] = useState(false);
@@ -524,6 +526,9 @@ export function InputBox({
     if (!lastAiId || lastAiId === lastGeneratedForAiIdRef.current) {
       return;
     }
+    if (suggestionsConfig === undefined) {
+      return;
+    }
     lastGeneratedForAiIdRef.current = lastAiId;
 
     const recent = messagesRef.current
@@ -540,6 +545,11 @@ export function InputBox({
       return;
     }
 
+    if (!suggestionsConfig?.enabled) {
+      setFollowups([]);
+      return;
+    }
+
     const controller = new AbortController();
     setFollowupsHidden(false);
     setFollowupsLoading(true);
@@ -576,7 +586,14 @@ export function InputBox({
       });
 
     return () => controller.abort();
-  }, [context.model_name, disabled, isMock, status, threadId]);
+  }, [
+    context.model_name,
+    disabled,
+    isMock,
+    status,
+    threadId,
+    suggestionsConfig?.enabled,
+  ]);
 
   return (
     <div

frontend/src/core/suggestions/api.ts

@@ -0,0 +1,20 @@
+import { fetch } from "@/core/api/fetcher";
+import { getBackendBaseURL } from "@/core/config";
+
+export interface SuggestionsConfigResponse {
+  enabled: boolean;
+}
+
+export async function loadSuggestionsConfig(): Promise<SuggestionsConfigResponse> {
+  const response = await fetch(`${getBackendBaseURL()}/api/suggestions/config`);
+  if (!response.ok) {
+    if (response.status === 404) {
+      // Fallback to true if the backend is older
+      return { enabled: true };
+    }
+    throw new Error(
+      `Failed to load suggestions config: ${response.statusText}`,
+    );
+  }
+  return response.json() as Promise<SuggestionsConfigResponse>;
+}

frontend/src/core/suggestions/hooks.ts

@@ -0,0 +1,11 @@
+import { useQuery } from "@tanstack/react-query";
+
+import { loadSuggestionsConfig } from "./api";
+
+export function useSuggestionsConfig() {
+  return useQuery({
+    queryKey: ["suggestionsConfig"],
+    queryFn: loadSuggestionsConfig,
+    staleTime: Infinity,
+  });
+}

frontend/tests/e2e/chat.spec.ts

@@ -310,4 +310,47 @@ test.describe("Chat workspace", () => {
     });
     await expect(promptForm.getByText("report.docx")).toBeHidden();
   });
+
+  test("does not fetch follow-up suggestions when disabled in config", async ({
+    page,
+  }) => {
+    await page.route("**/api/suggestions/config", (route) => {
+      return route.fulfill({
+        status: 200,
+        contentType: "application/json",
+        body: JSON.stringify({ enabled: false }),
+      });
+    });
+
+    let suggestionsFetched = false;
+    await page.route("**/api/threads/*/suggestions", (route) => {
+      suggestionsFetched = true;
+      return route.fulfill({
+        status: 200,
+        contentType: "application/json",
+        body: JSON.stringify({ suggestions: [] }),
+      });
+    });
+
+    let streamCalled = false;
+    await page.route("**/runs/stream", (route) => {
+      streamCalled = true;
+      return handleRunStream(route);
+    });
+
+    await page.goto("/workspace/chats/new");
+
+    const textarea = page.getByPlaceholder(/how can i assist you/i);
+    await expect(textarea).toBeVisible({ timeout: 15_000 });
+
+    await textarea.fill("Hello");
+    await textarea.press("Enter");
+
+    await expect.poll(() => streamCalled, { timeout: 10_000 }).toBeTruthy();
+    await expect(page.getByText("Hello from DeerFlow!")).toBeVisible({
+      timeout: 10_000,
+    });
+    await page.waitForTimeout(1000);
+    expect(suggestionsFetched).toBe(false);
+  });
 });