diff --git a/memhub/apps/core/src/one_memory/api.py b/memhub/apps/core/src/one_memory/api.py
index 6195537..6eca464 100644
--- a/memhub/apps/core/src/one_memory/api.py
+++ b/memhub/apps/core/src/one_memory/api.py
@@ -1450,6 +1450,7 @@ def create_app(
             app.state.memory_graph_backfill = MemoryGraphBackfill(
                 coordinator=app.state.sdk_write_coordinator,
                 state=app.state.evolve_state_store,
+                lifecycle_open=lambda: _embedding_writes_open(app),
             )
             # C2 owns the single production budget (handle 5s + reserve 250ms,
             # total 5.25s, lease 10s, renew 1s, claim 250ms). The composition
@@ -1848,6 +1849,16 @@ def create_app(
                         name="one-memory-durable-write-drain",
                     )
 
+                async def resume_graph_backfill() -> None:
+                    saved = app.state.evolve_state_store.graph_build()
+                    if saved.state != "running":
+                        return
+                    if _memory_mode(app) != "ultra":
+                        app.state.evolve_state_store.set_graph_build(GraphBuildState())
+                        return
+                    users = await asyncio.to_thread(_known_user_ids, app)
+                    app.state.memory_graph_backfill.recover(users)
+
                 async def start_evolve_schedule() -> None:
                     # Idle outside ultra: each tick asks the mode first.
                     app.state.evolve_scheduler.start()
@@ -1936,6 +1947,7 @@ def create_app(
                     # served from the live space throughout.
                     if sdk:
                         await step("embedding_spaces", resume_embedding_spaces)
+                        await step("graph_backfill", resume_graph_backfill)
                     await step("write_drain", start_write_drain)
                     if sdk:
                         await step("evolve_schedule", start_evolve_schedule)
diff --git a/memhub/apps/core/src/one_memory/memory_evolution.py b/memhub/apps/core/src/one_memory/memory_evolution.py
index 1488ac6..abfd9cc 100644
--- a/memhub/apps/core/src/one_memory/memory_evolution.py
+++ b/memhub/apps/core/src/one_memory/memory_evolution.py
@@ -545,10 +545,12 @@ class MemoryGraphBackfill:
         *,
         coordinator: EvolveCoordinator,
         state: EvolveStateStore,
+        lifecycle_open: Callable[[], bool] = lambda: True,
         now: Callable[[], datetime] = lambda: datetime.now(UTC),
     ) -> None:
         self.coordinator = coordinator
         self.state = state
+        self.lifecycle_open = lifecycle_open
         self._now = now
         self._task: asyncio.Task[None] | None = None
 
@@ -569,6 +571,35 @@ class MemoryGraphBackfill:
         self._task = asyncio.create_task(self._run(users), name="one-memory-graph-backfill")
         return state
 
+    def recover(self, user_ids: Iterable[str]) -> GraphBuildState:
+        """Resume an interrupted backfill without repeating completed users."""
+        if self.running:
+            return self.state.graph_build()
+        saved = self.state.graph_build()
+        if saved.state != "running":
+            return saved
+        users = tuple(dict.fromkeys((*saved.users.keys(), *user_ids)))
+        pending = tuple(
+            user_id
+            for user_id in users
+            if saved.users.get(user_id, GraphBuildUser()).state != "succeeded"
+        )
+        resumed = saved.model_copy(deep=True)
+        for user_id in pending:
+            resumed.users[user_id] = GraphBuildUser()
+        if not pending:
+            resumed.state = "succeeded"
+            resumed.finished_at = self._now()
+            self.state.set_graph_build(resumed)
+            return resumed
+        resumed.state = "running"
+        resumed.finished_at = None
+        self.state.set_graph_build(resumed)
+        self._task = asyncio.create_task(
+            self._run(pending), name="one-memory-graph-backfill-recovery"
+        )
+        return resumed
+
     async def wait(self) -> None:
         if self._task is not None:
             await asyncio.shield(self._task)
@@ -576,6 +607,8 @@ class MemoryGraphBackfill:
     async def _run(self, users: tuple[str, ...]) -> None:
         state = self.state.graph_build()
         for user_id in users:
+            while not self.lifecycle_open():
+                await asyncio.sleep(0.2)
             state.users[user_id] = GraphBuildUser(state="running")
             await asyncio.to_thread(self.state.set_graph_build, state.model_copy(deep=True))
             try:
diff --git a/memhub/apps/core/tests/test_memory_mode_and_evolve.py b/memhub/apps/core/tests/test_memory_mode_and_evolve.py
index b8f3255..fced7df 100644
--- a/memhub/apps/core/tests/test_memory_mode_and_evolve.py
+++ b/memhub/apps/core/tests/test_memory_mode_and_evolve.py
@@ -41,6 +41,8 @@ from one_memory.memory_evolution import (
     EvolveScheduler,
     EvolveService,
     EvolveStateStore,
+    GraphBuildState,
+    GraphBuildUser,
     MemoryGraphBackfill,
     evolve_due,
 )
@@ -692,6 +694,63 @@ def test_the_graph_backfill_runs_once_per_user(tmp_path, monkeypatch) -> None:
     }
 
 
+def test_an_interrupted_graph_backfill_resumes_only_unfinished_users(tmp_path, monkeypatch) -> None:
+    sdk = _EvolveSdk()
+    state = EvolveStateStore(tmp_path)
+    state.set_graph_build(
+        GraphBuildState(
+            state="running",
+            started_at=_at(1, 3),
+            users={
+                "local": GraphBuildUser(state="succeeded", memories_scanned=4, nodes=4),
+                "wife": GraphBuildUser(state="running"),
+            },
+        )
+    )
+    backfill = MemoryGraphBackfill(coordinator=_Coordinator(sdk, monkeypatch), state=state)
+
+    async def scenario():
+        resumed = backfill.recover(["local", "wife"])
+        assert resumed.state == "running"
+        assert resumed.users["local"].state == "succeeded"
+        assert resumed.users["wife"].state == "pending"
+        await backfill.wait()
+
+    asyncio.run(scenario())
+    assert sdk.graph_builds == ["wife"]
+    assert state.graph_build().state == "succeeded"
+
+
+def test_graph_backfill_waits_for_embedding_maintenance_to_finish(tmp_path, monkeypatch) -> None:
+    sdk = _EvolveSdk()
+    state = EvolveStateStore(tmp_path)
+    gate = [False]
+    checked = asyncio.Event()
+
+    def lifecycle_open() -> bool:
+        checked.set()
+        return gate[0]
+
+    backfill = MemoryGraphBackfill(
+        coordinator=_Coordinator(sdk, monkeypatch),
+        state=state,
+        lifecycle_open=lifecycle_open,
+    )
+
+    async def scenario():
+        backfill.start(["local"])
+        await checked.wait()
+        assert sdk.graph_builds == []
+        assert state.graph_build().state == "running"
+        assert state.graph_build().users["local"].state == "pending"
+        gate[0] = True
+        await backfill.wait()
+
+    asyncio.run(scenario())
+    assert sdk.graph_builds == ["local"]
+    assert state.graph_build().state == "succeeded"
+
+
 # --- the HTTP surface -----------------------------------------------------------
 
 
diff --git a/memhub/apps/web/src/App.setup.test.tsx b/memhub/apps/web/src/App.setup.test.tsx
index 716f1c1..f013891 100644
--- a/memhub/apps/web/src/App.setup.test.tsx
+++ b/memhub/apps/web/src/App.setup.test.tsx
@@ -37,6 +37,36 @@ const { getOnboarding, sources, modelProps, mutations } = vi.hoisted(() => ({
 vi.mock("./api", () => ({
   getOnboarding,
   getModelProfiles: vi.fn().mockResolvedValue([]),
+  getMemoryMode: vi.fn().mockResolvedValue({
+    mode: "pro",
+    configured_mode: "pro",
+    explicitly_configured: false,
+    forced_by_env: false,
+    modes: ["lite", "pro", "ultra"],
+    graph_build: {
+      state: "idle",
+      started_at: null,
+      finished_at: null,
+      users: {},
+    },
+  }),
+  getEvolveSchedule: vi.fn().mockResolvedValue({
+    enabled: true,
+    time: "03:00",
+  }),
+  getEvolveOverview: vi.fn().mockResolvedValue({
+    mode: "pro",
+    schedule: { enabled: true, time: "03:00" },
+    users: {},
+    running: [],
+  }),
+  getMemoryProcessing: vi.fn().mockResolvedValue({
+    embedding_switch: null,
+  }),
+  setMemoryMode: vi.fn(),
+  setEvolveSchedule: vi.fn(),
+  startEvolve: vi.fn(),
+  apiErrorCode: vi.fn().mockReturnValue(null),
   getSources: vi.fn().mockResolvedValue(sources),
   getCurrentEmbeddingSwitch: vi
     .fn()
diff --git a/memhub/apps/web/src/MemoryModeSettings.test.tsx b/memhub/apps/web/src/MemoryModeSettings.test.tsx
index 2151b7c..55dbb8a 100644
--- a/memhub/apps/web/src/MemoryModeSettings.test.tsx
+++ b/memhub/apps/web/src/MemoryModeSettings.test.tsx
@@ -80,6 +80,43 @@ it("confirms the data effects before switching to lite", async () => {
   await waitFor(() => expect(setMemoryMode).toHaveBeenCalledWith("lite"));
 });
 
+it("traps modal focus, closes on Escape and restores the mode-card focus", async () => {
+  prepare("pro");
+  const user = userEvent.setup();
+  render(<MemoryModeSettings hasActiveModel onConfigureModel={vi.fn()} />);
+  const lite = await screen.findByRole("button", {
+    name: /基础记忆（lite）/,
+  });
+  await user.click(lite);
+
+  const cancel = screen.getByRole("button", { name: "取消" });
+  await waitFor(() => expect(document.activeElement).toBe(cancel));
+  await user.keyboard("{Shift>}{Tab}{/Shift}");
+  expect(document.activeElement).toBe(
+    screen.getByRole("button", { name: "切换模式" }),
+  );
+  await user.keyboard("{Escape}");
+
+  expect(screen.queryByRole("dialog")).toBeNull();
+  expect(document.activeElement).toBe(lite);
+});
+
+it("keeps focus inside the modal while the mode change is pending", async () => {
+  prepare("pro");
+  vi.mocked(setMemoryMode).mockReturnValue(new Promise(() => {}));
+  const user = userEvent.setup();
+  render(<MemoryModeSettings hasActiveModel onConfigureModel={vi.fn()} />);
+  await user.click(
+    await screen.findByRole("button", { name: /基础记忆（lite）/ }),
+  );
+  await user.click(screen.getByRole("button", { name: "切换模式" }));
+
+  const modal = screen.getByRole("dialog");
+  await waitFor(() => expect(document.activeElement).toBe(modal));
+  await user.keyboard("{Tab}");
+  expect(document.activeElement).toBe(modal);
+});
+
 it("routes to model setup instead of switching pro without a model", async () => {
   prepare("lite");
   const configure = vi.fn();
@@ -178,3 +215,22 @@ it("does not let an older refresh undo a saved schedule change", async () => {
     expect(toggle.getAttribute("aria-checked")).toBe("false"),
   );
 });
+
+it("keeps the mode usable when an evolve status read fails", async () => {
+  prepare("pro");
+  vi.mocked(getEvolveSchedule).mockRejectedValueOnce(new Error("offline"));
+  render(<MemoryModeSettings hasActiveModel onConfigureModel={vi.fn()} />);
+
+  expect(
+    (
+      await screen.findByRole("button", { name: /智能记忆（pro）/ })
+    ).getAttribute("aria-pressed"),
+  ).toBe("true");
+  expect(
+    (
+      screen.getByRole("button", {
+        name: /基础记忆（lite）/,
+      }) as HTMLButtonElement
+    ).disabled,
+  ).toBe(false);
+});
diff --git a/memhub/apps/web/src/MemoryModeSettings.tsx b/memhub/apps/web/src/MemoryModeSettings.tsx
index 7f575ae..b18a2fc 100644
--- a/memhub/apps/web/src/MemoryModeSettings.tsx
+++ b/memhub/apps/web/src/MemoryModeSettings.tsx
@@ -67,10 +67,12 @@ function plannedEffects(
 
 export function MemoryModeSettings({
   hasActiveModel,
+  modelStateKnown = true,
   onConfigureModel,
   onModeChange,
 }: {
   hasActiveModel: boolean;
+  modelStateKnown?: boolean;
   onConfigureModel(): void;
   onModeChange?(mode: MemoryPipelineMode): void;
 }) {
@@ -86,29 +88,76 @@ export function MemoryModeSettings({
   const [error, setError] = useState("");
   const [run, setRun] = useState<EvolveRunReceipt | null>(null);
   const refreshVersion = useRef(0);
+  const dialog = useRef<HTMLElement>(null);
+  const dialogOpener = useRef<HTMLElement | null>(null);
+  const busyRef = useRef(false);
+  busyRef.current = busy;
+
+  useEffect(() => {
+    if (!pendingMode || !dialog.current) return;
+    const panel = dialog.current;
+    const controls = () =>
+      Array.from(panel.querySelectorAll<HTMLElement>("button:not(:disabled)"));
+    controls()[0]?.focus();
+    const handleKey = (event: KeyboardEvent) => {
+      if (event.key === "Escape" && !busyRef.current) {
+        event.preventDefault();
+        setPendingMode(null);
+        return;
+      }
+      if (event.key !== "Tab") return;
+      const items = controls();
+      const first = items[0];
+      const last = items.at(-1);
+      if (!first || !last) {
+        event.preventDefault();
+        panel.focus();
+        return;
+      }
+      if (event.shiftKey && document.activeElement === first) {
+        event.preventDefault();
+        last.focus();
+      } else if (!event.shiftKey && document.activeElement === last) {
+        event.preventDefault();
+        first.focus();
+      }
+    };
+    panel.addEventListener("keydown", handleKey);
+    return () => {
+      panel.removeEventListener("keydown", handleKey);
+      if (dialogOpener.current?.isConnected) dialogOpener.current.focus();
+    };
+  }, [pendingMode]);
+
+  useEffect(() => {
+    if (pendingMode && busy) dialog.current?.focus();
+  }, [busy, pendingMode]);
 
   const refresh = useCallback(async () => {
     const version = ++refreshVersion.current;
-    try {
-      const [nextMode, nextSchedule, nextOverview, processing] =
-        await Promise.all([
-          getMemoryMode(),
-          getEvolveSchedule(),
-          getEvolveOverview(),
-          getMemoryProcessing(),
-        ]);
-      if (version !== refreshVersion.current) return;
-      setState(nextMode);
-      onModeChange?.(nextMode.mode);
-      setScheduleState(nextSchedule);
-      setOverview(nextOverview);
-      setMaintenance(Boolean(processing.embedding_switch));
-      setRun(nextOverview.running[0] ?? null);
+    const [modeResult, scheduleResult, overviewResult, processingResult] =
+      await Promise.allSettled([
+        getMemoryMode(),
+        getEvolveSchedule(),
+        getEvolveOverview(),
+        getMemoryProcessing(),
+      ]);
+    if (version !== refreshVersion.current) return;
+    if (modeResult.status === "fulfilled") {
+      setState(modeResult.value);
+      onModeChange?.(modeResult.value.mode);
       setError("");
-    } catch {
-      if (version !== refreshVersion.current) return;
+    } else {
       setError("记忆模式状态暂时无法读取，请重试。");
     }
+    if (scheduleResult.status === "fulfilled")
+      setScheduleState(scheduleResult.value);
+    if (overviewResult.status === "fulfilled") {
+      setOverview(overviewResult.value);
+      setRun(overviewResult.value.running[0] ?? null);
+    }
+    if (processingResult.status === "fulfilled")
+      setMaintenance(Boolean(processingResult.value.embedding_switch));
   }, [onModeChange]);
 
   useEffect(() => {
@@ -138,6 +187,10 @@ export function MemoryModeSettings({
       return;
     }
     setError("");
+    dialogOpener.current =
+      document.activeElement instanceof HTMLElement
+        ? document.activeElement
+        : null;
     setPendingMode(mode);
   }
 
@@ -226,7 +279,12 @@ export function MemoryModeSettings({
             type="button"
             className="r6-mode-option"
             aria-pressed={state?.mode === mode}
-            disabled={!state || busy || lifecycleBusy}
+            disabled={
+              !state ||
+              busy ||
+              lifecycleBusy ||
+              (mode !== "lite" && !modelStateKnown)
+            }
             onClick={() => choose(mode)}
           >
             <strong>{text(MODE_COPY[mode].title)}</strong>
@@ -320,10 +378,12 @@ export function MemoryModeSettings({
       {pendingMode ? (
         <div className="r6-settings-dialog-layer" role="presentation">
           <section
+            ref={dialog}
             className="r6-settings-dialog"
             role="dialog"
             aria-modal="true"
             aria-labelledby="memory-mode-confirm-title"
+            tabIndex={-1}
           >
             <h2 id="memory-mode-confirm-title">
               {text("切换到 {mode}？").replace("{mode}", pendingMode)}
diff --git a/memhub/apps/web/src/MemorySpace.r6.test.tsx b/memhub/apps/web/src/MemorySpace.r6.test.tsx
index 75b4228..15004e7 100644
--- a/memhub/apps/web/src/MemorySpace.r6.test.tsx
+++ b/memhub/apps/web/src/MemorySpace.r6.test.tsx
@@ -255,6 +255,52 @@ it("shows raw conversations instead of advanced memory in lite", async () => {
   expect(screen.getByText(/当前使用基础记忆/)).toBeTruthy();
 });
 
+it("does not request advanced memories before the pipeline mode is known", async () => {
+  setup();
+  let resolveProcessing!: (value: unknown) => void;
+  reads.processing.mockReturnValueOnce(
+    new Promise((resolve) => {
+      resolveProcessing = resolve;
+    }),
+  );
+  render(<MemorySpace simplified />);
+
+  await act(async () => Promise.resolve());
+  expect(reads.sdkLibrary).not.toHaveBeenCalled();
+  expect(reads.sdkGraph).not.toHaveBeenCalled();
+
+  await act(async () => {
+    resolveProcessing({
+      running: 0,
+      pending: 0,
+      blocked_stages: [],
+      completed: 0,
+      pipeline: {
+        mode: "lite",
+        configured_mode: "lite",
+        forced_by_env: false,
+        evolve: {
+          mode: "lite",
+          schedule: { enabled: true, time: "03:00" },
+          users: {},
+          running: [],
+        },
+        last_evolve_at: null,
+        graph_build: {
+          state: "idle",
+          started_at: null,
+          finished_at: null,
+          users: {},
+        },
+        features: {},
+      },
+    });
+  });
+  await screen.findByText(/当前使用基础记忆/);
+  expect(reads.sdkLibrary).not.toHaveBeenCalled();
+  expect(reads.sdkGraph).not.toHaveBeenCalled();
+});
+
 it("keeps an added memory visible while it waits for model processing", async () => {
   setup();
   render(<MemorySpace simplified onConfigureModel={vi.fn()} />);
diff --git a/memhub/apps/web/src/MemorySpace.tsx b/memhub/apps/web/src/MemorySpace.tsx
index 974b13f..2754cbe 100644
--- a/memhub/apps/web/src/MemorySpace.tsx
+++ b/memhub/apps/web/src/MemorySpace.tsx
@@ -214,7 +214,21 @@ export function MemorySpace({
   // The page the list shows, for the namespace of a memory being opened.
   const sdkPageRef = useRef<MemoryLibraryPage | null>(null);
   sdkPageRef.current = sdkLibrary.page;
-  const sdkMapVisible = simplified && active && displayedMode === "map";
+  const [processing, setProcessing] = useState<MemoryProcessingSummary | null>(
+    null,
+  );
+  const [processingFailed, setProcessingFailed] = useState(false);
+  const [processingResolved, setProcessingResolved] = useState(false);
+  const pipelineMode =
+    processing?.pipeline?.mode ??
+    (processingResolved && !processingFailed ? "pro" : null);
+  const lite = pipelineMode === "lite";
+  const sdkMapVisible =
+    simplified &&
+    active &&
+    displayedMode === "map" &&
+    pipelineMode !== null &&
+    !lite;
   useEffect(() => {
     if (!sdkMapVisible) return;
     // A write bumps the revision; reading it here re-runs the read at once
@@ -337,15 +351,6 @@ export function MemorySpace({
   }
   const [busy, setBusy] = useState(false);
   const [error, setError] = useState<string | null>(null);
-  const [processing, setProcessing] = useState<MemoryProcessingSummary | null>(
-    null,
-  );
-  const [processingFailed, setProcessingFailed] = useState(false);
-  const [processingResolved, setProcessingResolved] = useState(false);
-  const pipelineMode =
-    processing?.pipeline?.mode ??
-    (processingResolved && !processingFailed ? "pro" : null);
-  const lite = pipelineMode === "lite";
   const [pendingAdd, setPendingAdd] = useState<PendingMemoryAdd | null>(null);
   const [checkingSetup, setCheckingSetup] = useState(false);
   // biome-ignore lint/correctness/useExhaustiveDependencies: Source authority changes invalidate an in-flight setup snapshot.
@@ -1176,10 +1181,12 @@ export function MemorySpace({
         className="memory-library-layout"
         hidden={displayedMode !== "library"}
       >
-        <SdkMemoryLibrary
-          active={active}
-          focusedMemoryId={sdkFocusedMemoryId}
-        />
+        {!simplified || (pipelineMode !== null && !lite) ? (
+          <SdkMemoryLibrary
+            active={active}
+            focusedMemoryId={sdkFocusedMemoryId}
+          />
+        ) : null}
       </div>
     </section>
   );
diff --git a/memhub/apps/web/src/OnboardingModelController.test.tsx b/memhub/apps/web/src/OnboardingModelController.test.tsx
new file mode 100644
index 0000000..1b2e3a2
--- /dev/null
+++ b/memhub/apps/web/src/OnboardingModelController.test.tsx
@@ -0,0 +1,83 @@
+// @vitest-environment jsdom
+
+import { cleanup, render, screen, waitFor } from "@testing-library/react";
+import userEvent from "@testing-library/user-event";
+import { afterEach, expect, it, vi } from "vitest";
+import { OnboardingModelController } from "./OnboardingModelController";
+
+const { models } = vi.hoisted(() => ({
+  models: {
+    profiles: [
+      {
+        profile_id: "active-profile",
+        revision: 3,
+        name: "Current model",
+        provider_kind: "openai_compatible",
+        model: "model-1",
+        base_url: "https://models.example/v1",
+        disable_thinking: true,
+        embedding_provider_kind: "local_onnx",
+        embedding_model: "bge-small-zh-v1.5",
+        embedding_base_url: null,
+        timeout_seconds: 90,
+        max_concurrency: 4,
+        context_window: null,
+        has_api_key: true,
+        is_active: true,
+      },
+    ],
+    pendingProbe: false,
+    probeStorageFailed: false,
+    pendingCreation: false,
+    creationStorageFailed: false,
+    error: null,
+    create: vi.fn(),
+    update: vi.fn(),
+    probeProfile: vi.fn(),
+    activate: vi.fn(),
+  },
+}));
+
+vi.mock("./use-model-profiles", () => ({
+  useModelProfiles: () => models,
+}));
+vi.mock("./OnboardingModelStep", () => ({
+  OnboardingModelStep: (props: {
+    probe?: { message: string } | null;
+    enableActionLabel?: string;
+    onSaveAndEnable(): Promise<void>;
+  }) => (
+    <section>
+      <p>{props.probe?.message}</p>
+      <button type="button" onClick={() => void props.onSaveAndEnable()}>
+        {props.enableActionLabel}
+      </button>
+    </section>
+  ),
+}));
+
+afterEach(() => {
+  cleanup();
+  vi.clearAllMocks();
+});
+
+it("resumes onboarding with an already active model after a restart", async () => {
+  const enabled = vi.fn();
+  render(
+    <OnboardingModelController
+      sourceNames={[]}
+      onBack={vi.fn()}
+      onEnabled={enabled}
+    />,
+  );
+
+  expect(
+    await screen.findByText("当前模型已经启用，可以继续完成首次设置。"),
+  ).toBeTruthy();
+  await userEvent.click(
+    screen.getByRole("button", { name: "继续使用当前模型" }),
+  );
+
+  await waitFor(() => expect(enabled).toHaveBeenCalledOnce());
+  expect(models.activate).not.toHaveBeenCalled();
+});
diff --git a/memhub/apps/web/src/OnboardingModelController.tsx b/memhub/apps/web/src/OnboardingModelController.tsx
index b125dcf..b8e548b 100644
--- a/memhub/apps/web/src/OnboardingModelController.tsx
+++ b/memhub/apps/web/src/OnboardingModelController.tsx
@@ -89,6 +89,37 @@ export function OnboardingModelController({
     null,
   );
   const flight = useRef(false);
+  const draftTouched = useRef(false);
+
+  useEffect(() => {
+    const active = (models.profiles ?? []).find((profile) => profile.is_active);
+    if (!active || saved || draftTouched.current) return;
+    setSaved(active);
+    setDraft((current) => ({
+      ...current,
+      name: active.name,
+      provider_kind: active.provider_kind,
+      model: active.model,
+      base_url: active.base_url ?? "",
+      disable_thinking: active.disable_thinking,
+      embedding_mode:
+        active.embedding_provider_kind === "local_onnx" ? "local" : "custom",
+      embedding_provider_kind:
+        active.embedding_provider_kind === "ollama"
+          ? "ollama"
+          : "openai_compatible",
+      embedding_model: active.embedding_model ?? "",
+      embedding_base_url: active.embedding_base_url ?? "",
+      timeout_seconds: String(active.timeout_seconds),
+      max_concurrency: String(active.max_concurrency),
+      context_window:
+        active.context_window === null ? "" : String(active.context_window),
+    }));
+    setProbe({
+      state: "passed",
+      message: "当前模型已经启用，可以继续完成首次设置。",
+    });
+  }, [models.profiles, saved]);
 
   useEffect(() => {
     const finished = embeddingSwitch.current?.last_finished;
@@ -113,6 +144,7 @@ export function OnboardingModelController({
 
   function edit(patch: Partial<OnboardingModelDraft>) {
     if (flight.current) return;
+    draftTouched.current = true;
     if (patch.provider_id && patch.provider_id !== draft.provider_id) {
       const preset = PROVIDER_PRESETS.find(
         (item) => item.id === patch.provider_id,
@@ -259,6 +291,10 @@ export function OnboardingModelController({
 
   async function enable() {
     if (flight.current || probe?.state !== "passed" || !saved) return;
+    if (saved.is_active) {
+      onEnabled?.();
+      return;
+    }
     flight.current = true;
     setPhase("enabling");
     setError(null);
@@ -313,6 +349,7 @@ export function OnboardingModelController({
         phase={phase}
         capability={{ saveAndEnable: true }}
         canSaveAndEnable={probe?.state === "passed" && !!saved}
+        enableActionLabel={saved?.is_active ? "继续使用当前模型" : undefined}
         canTest={!models.pendingProbe && !models.probeStorageFailed}
         canSaveDraft={!models.pendingCreation && !models.creationStorageFailed}
         inputsLocked={flight.current}
diff --git a/memhub/apps/web/src/R6Settings.tsx b/memhub/apps/web/src/R6Settings.tsx
index 3b360e0..78edffa 100644
--- a/memhub/apps/web/src/R6Settings.tsx
+++ b/memhub/apps/web/src/R6Settings.tsx
@@ -307,6 +307,7 @@ export function R6Settings({
           >
             <MemoryModeSettings
               hasActiveModel={currentModel !== null}
+              modelStateKnown={profiles !== null && !modelError}
               onConfigureModel={() => openConfiguration("generation")}
               onModeChange={setMemoryModeState}
             />
diff --git a/memhub/apps/web/src/SdkRawHistory.test.tsx b/memhub/apps/web/src/SdkRawHistory.test.tsx
index 9f69177..84604b5 100644
--- a/memhub/apps/web/src/SdkRawHistory.test.tsx
+++ b/memhub/apps/web/src/SdkRawHistory.test.tsx
@@ -1,5 +1,11 @@
 // @vitest-environment jsdom
-import { cleanup, render, screen } from "@testing-library/react";
+import {
+  act,
+  cleanup,
+  fireEvent,
+  render,
+  screen,
+} from "@testing-library/react";
 import userEvent from "@testing-library/user-event";
 import { afterEach, expect, it, vi } from "vitest";
 
@@ -15,6 +21,8 @@ import { SdkRawHistory } from "./SdkRawHistory";
 afterEach(() => {
   cleanup();
   localStorage.clear();
+  vi.clearAllMocks();
+  vi.useRealTimers();
 });
 
 it("localizes controls without translating original conversation fields", async () => {
@@ -114,3 +122,123 @@ it("does not call a zero-result search an empty conversation history", async ()
     screen.queryByText("还没有原始对话。连接来源后，对话会显示在这里。"),
   ).toBeNull();
 });
+
+it("retries the lite history read in place after a load failure", async () => {
+  getSdkRaw.mockRejectedValueOnce(new Error("offline")).mockResolvedValueOnce({
+    items: [
+      {
+        raw_id: "raw-recovered",
+        content: "恢复后的原始对话",
+        session_id: "session-recovered",
+        source: "cursor",
+        memory_at: null,
+      },
+    ],
+    total: 1,
+    offset: 0,
+    limit: 100,
+  });
+  render(<SdkRawHistory />);
+
+  await userEvent.click(await screen.findByRole("button", { name: "重试" }));
+
+  expect(await screen.findByText("恢复后的原始对话")).toBeTruthy();
+  expect(getSdkRaw).toHaveBeenCalledTimes(2);
+});
+
+it("retries the failed raw search instead of reloading history", async () => {
+  getSdkRaw.mockResolvedValue({
+    items: [],
+    total: 0,
+    offset: 0,
+    limit: 100,
+  });
+  searchSdkRaw
+    .mockRejectedValueOnce(new Error("offline"))
+    .mockResolvedValueOnce([
+      {
+        kind: "raw",
+        raw_id: "raw-search-recovered",
+        content: "重试后的搜索结果",
+        source: "cursor",
+        session_id: "session-search",
+        memory_at: null,
+        score: 0.8,
+        truncated: false,
+      },
+    ]);
+  render(<SdkRawHistory />);
+
+  await userEvent.type(screen.getByLabelText("搜索原始对话"), "恢复搜索");
+  await userEvent.click(screen.getByRole("button", { name: "搜索" }));
+  await userEvent.click(await screen.findByRole("button", { name: "重试" }));
+
+  expect(await screen.findByText("重试后的搜索结果")).toBeTruthy();
+  expect(searchSdkRaw).toHaveBeenCalledTimes(2);
+  expect(getSdkRaw).toHaveBeenCalledTimes(1);
+});
+
+it("does not let a history poll clear an independent search failure", async () => {
+  vi.useFakeTimers();
+  getSdkRaw.mockResolvedValue({
+    items: [
+      {
+        raw_id: "raw-old",
+        content: "已有历史",
+        session_id: "session-old",
+        source: "cursor",
+        memory_at: null,
+      },
+    ],
+    total: 1,
+    offset: 0,
+    limit: 100,
+  });
+  searchSdkRaw.mockRejectedValue(new Error("search offline"));
+  render(<SdkRawHistory />);
+  await act(async () => Promise.resolve());
+
+  fireEvent.change(screen.getByLabelText("搜索原始对话"), {
+    target: { value: "失败查询" },
+  });
+  await act(async () => {
+    fireEvent.click(screen.getByRole("button", { name: "搜索" }));
+    await Promise.resolve();
+  });
+  expect(screen.getByRole("alert").textContent).toContain("原始对话搜索失败");
+
+  await act(async () => {
+    await vi.advanceTimersByTimeAsync(12_000);
+  });
+  expect(screen.getByRole("alert").textContent).toContain("原始对话搜索失败");
+});
+
+it("ignores a stale initial-history failure after a newer search succeeds", async () => {
+  let rejectHistory!: (reason: Error) => void;
+  getSdkRaw.mockReturnValueOnce(
+    new Promise((_resolve, reject) => {
+      rejectHistory = reject;
+    }),
+  );
+  searchSdkRaw.mockResolvedValue([
+    {
+      kind: "raw",
+      raw_id: "raw-new-search",
+      content: "较新的搜索结果",
+      source: "cursor",
+      session_id: "session-new",
+      memory_at: null,
+      score: 0.9,
+      truncated: false,
+    },
+  ]);
+  render(<SdkRawHistory />);
+
+  await userEvent.type(screen.getByLabelText("搜索原始对话"), "新查询");
+  await userEvent.click(screen.getByRole("button", { name: "搜索" }));
+  expect(await screen.findByText("较新的搜索结果")).toBeTruthy();
+  await act(async () => rejectHistory(new Error("late history failure")));
+
+  expect(screen.queryByRole("alert")).toBeNull();
+  expect(screen.getByText("较新的搜索结果")).toBeTruthy();
+});
diff --git a/memhub/apps/web/src/SdkRawHistory.tsx b/memhub/apps/web/src/SdkRawHistory.tsx
index 7177d4a..c59af4b 100644
--- a/memhub/apps/web/src/SdkRawHistory.tsx
+++ b/memhub/apps/web/src/SdkRawHistory.tsx
@@ -12,18 +12,32 @@ export function SdkRawHistory({ active = true }: { active?: boolean }) {
   const [results, setResults] = useState<SdkRawContextItem[] | null>(null);
   const [query, setQuery] = useState("");
   const [error, setError] = useState("");
+  const [errorKind, setErrorKind] = useState<"load" | "search" | null>(null);
+  const errorKindRef = useRef<"load" | "search" | null>(null);
+  const searchEpoch = useRef(0);
   const [busy, setBusy] = useState(false);
+  const [revision, setRevision] = useState(0);
 
+  // biome-ignore lint/correctness/useExhaustiveDependencies: revision is the explicit retry trigger.
   useEffect(() => {
     if (!active) return;
     let current = true;
+    const startedBeforeSearch = searchEpoch.current;
     const consume = (value: unknown) => {
       if (!current) return;
       setRecent((value as Awaited<ReturnType<typeof getSdkRaw>>).items);
-      setError("");
+      if (errorKindRef.current !== "search") {
+        errorKindRef.current = null;
+        setError("");
+        setErrorKind(null);
+      }
     };
     void getSdkRaw({ limit: 100 }).then(consume, () => {
-      if (current) setError(translation.current("sdk.raw.loadFailed"));
+      if (current && startedBeforeSearch === searchEpoch.current) {
+        setError(translation.current("sdk.raw.loadFailed"));
+        errorKindRef.current = "load";
+        setErrorKind("load");
+      }
     });
     const stop = subscribePoll({
       key: "sdk-raw-history",
@@ -35,20 +49,30 @@ export function SdkRawHistory({ active = true }: { active?: boolean }) {
       current = false;
       stop();
     };
-  }, [active]);
+  }, [active, revision]);
+
+  async function runSearch(value: string) {
+    searchEpoch.current += 1;
+    setBusy(true);
+    setResults(null);
+    setError("");
+    errorKindRef.current = null;
+    setErrorKind(null);
+    try {
+      setResults(await searchSdkRaw(value));
+    } catch {
+      setError(t("sdk.raw.searchFailed"));
+      errorKindRef.current = "search";
+      setErrorKind("search");
+    } finally {
+      setBusy(false);
+    }
+  }
 
   async function submit(event: FormEvent) {
     event.preventDefault();
     if (!query.trim()) return;
-    setBusy(true);
-    setError("");
-    try {
-      setResults(await searchSdkRaw(query.trim()));
-    } catch {
-      setError(t("sdk.raw.searchFailed"));
-    } finally {
-      setBusy(false);
-    }
+    await runSearch(query.trim());
   }
 
   const items = results ?? recent.map(asContextItem);
@@ -66,7 +90,27 @@ export function SdkRawHistory({ active = true }: { active?: boolean }) {
           {busy ? t("sdk.raw.searching") : t("sdk.raw.search")}
         </button>
       </form>
-      {error ? <p role="alert">{error}</p> : null}
+      {error ? (
+        <p role="alert">
+          {error}{" "}
+          <button
+            type="button"
+            disabled={busy}
+            onClick={() => {
+              if (errorKind === "search" && query.trim()) {
+                void runSearch(query.trim());
+              } else {
+                setError("");
+                errorKindRef.current = null;
+                setErrorKind(null);
+                setRevision((value) => value + 1);
+              }
+            }}
+          >
+            {t("connectionFallback.retry")}
+          </button>
+        </p>
+      ) : null}
       <p aria-live="polite">
         {results === null
           ? t("sdk.raw.recent")
diff --git a/memhub/docs/contracts/memory-mode-evolve-v1.md b/memhub/docs/contracts/memory-mode-evolve-v1.md
index f13c63e..c393592 100644
--- a/memhub/docs/contracts/memory-mode-evolve-v1.md
+++ b/memhub/docs/contracts/memory-mode-evolve-v1.md
@@ -72,6 +72,8 @@ and they are the owner's:
     (`build_memory_graph(user_id, limit=10000, clear_first=False)`);
   - this runs in the background, one user at a time, never beside that
     user's write;
+  - after a crash or App update, startup resumes users that did not finish
+    and does not repeat users already recorded as succeeded;
   - progress is reported in `graph_build`.
 - Vector collection names never depend on the mode. The mode is a separate
   client parameter, not part of the embedding-space identity.
diff --git a/memhub/packages/i18n/src/gui-i18n-mode.ts b/memhub/packages/i18n/src/gui-i18n-mode.ts
index bda3492..bcdf9e0 100644
--- a/memhub/packages/i18n/src/gui-i18n-mode.ts
+++ b/memhub/packages/i18n/src/gui-i18n-mode.ts
@@ -6,6 +6,9 @@ const modeChineseMessages = {
   返回导入: "返回导入",
   继续: "继续",
   "正在保存…": "正在保存…",
+  "当前模型已经启用，可以继续完成首次设置。":
+    "当前模型已经启用，可以继续完成首次设置。",
+  继续使用当前模型: "继续使用当前模型",
   "你希望 MemHub 如何形成记忆？": "你希望 MemHub 如何形成记忆？",
   "需要明确选择一种方式；之后仍可在设置中更改。":
     "需要明确选择一种方式；之后仍可在设置中更改。",
@@ -85,6 +88,9 @@ export const modeEnglishMessages: ModeMessages = {
   返回导入: "Back to import",
   继续: "Continue",
   "正在保存…": "Saving…",
+  "当前模型已经启用，可以继续完成首次设置。":
+    "The current model is already enabled. Continue to finish setup.",
+  继续使用当前模型: "Continue with current model",
   "你希望 MemHub 如何形成记忆？": "How should MemHub create memories?",
   "需要明确选择一种方式；之后仍可在设置中更改。":
     "Choose one option. You can change it later in Settings.",
@@ -166,6 +172,9 @@ export const modeSpanishMessages: ModeMessages = {
   返回导入: "Volver a la importación",
   继续: "Continuar",
   "正在保存…": "Guardando…",
+  "当前模型已经启用，可以继续完成首次设置。":
+    "El modelo actual ya está activo. Continúa para terminar la configuración.",
+  继续使用当前模型: "Continuar con el modelo actual",
   "你希望 MemHub 如何形成记忆？": "¿Cómo quieres que MemHub cree memorias?",
   "需要明确选择一种方式；之后仍可在设置中更改。":
     "Elige una opción. Podrás cambiarla después en Configuración.",
@@ -247,6 +256,9 @@ export const modeTraditionalChineseMessages: ModeMessages = {
   返回导入: "返回匯入",
   继续: "繼續",
   "正在保存…": "儲存中…",
+  "当前模型已经启用，可以继续完成首次设置。":
+    "目前模型已啟用，可以繼續完成首次設定。",
+  继续使用当前模型: "繼續使用目前模型",
   "你希望 MemHub 如何形成记忆？": "你希望 MemHub 如何形成記憶？",
   "需要明确选择一种方式；之后仍可在设置中更改。":
     "請選擇一種方式；之後仍可在設定中更改。",
@@ -322,6 +334,9 @@ export const modeJapaneseMessages: ModeMessages = {
   返回导入: "インポートに戻る",
   继续: "続ける",
   "正在保存…": "保存中…",
+  "当前模型已经启用，可以继续完成首次设置。":
+    "現在のモデルはすでに有効です。このまま初期設定を完了できます。",
+  继续使用当前模型: "現在のモデルで続ける",
   "你希望 MemHub 如何形成记忆？": "MemHub でどのように記憶を作成しますか？",
   "需要明确选择一种方式；之后仍可在设置中更改。":
     "いずれかを選択してください。後から設定で変更できます。",
@@ -403,6 +418,9 @@ export const modeGermanMessages: ModeMessages = {
   返回导入: "Zurück zum Import",
   继续: "Weiter",
   "正在保存…": "Wird gespeichert…",
+  "当前模型已经启用，可以继续完成首次设置。":
+    "Das aktuelle Modell ist bereits aktiviert. Fahre fort, um die Einrichtung abzuschließen.",
+  继续使用当前模型: "Mit aktuellem Modell fortfahren",
   "你希望 MemHub 如何形成记忆？": "Wie soll MemHub Erinnerungen erstellen?",
   "需要明确选择一种方式；之后仍可在设置中更改。":
     "Wählen Sie eine Option. Sie können sie später in den Einstellungen ändern.",
@@ -485,6 +503,9 @@ export const modePortugueseMessages: ModeMessages = {
   返回导入: "Voltar à importação",
   继续: "Continuar",
   "正在保存…": "A guardar…",
+  "当前模型已经启用，可以继续完成首次设置。":
+    "O modelo atual já está ativo. Continua para concluir a configuração.",
+  继续使用当前模型: "Continuar com o modelo atual",
   "你希望 MemHub 如何形成记忆？": "Como deve o MemHub criar memórias?",
   "需要明确选择一种方式；之后仍可在设置中更改。":
     "Escolha uma opção. Pode alterá-la mais tarde nas Definições.",
@@ -567,6 +588,9 @@ export const modeFrenchMessages: ModeMessages = {
   返回导入: "Retour à l’importation",
   继续: "Continuer",
   "正在保存…": "Enregistrement…",
+  "当前模型已经启用，可以继续完成首次设置。":
+    "Le modèle actuel est déjà activé. Continuez pour terminer la configuration.",
+  继续使用当前模型: "Continuer avec le modèle actuel",
   "你希望 MemHub 如何形成记忆？": "Comment MemHub doit-il créer des mémoires ?",
   "需要明确选择一种方式；之后仍可在设置中更改。":
     "Choisissez une option. Vous pourrez la modifier plus tard dans les réglages.",
@@ -648,6 +672,9 @@ export const modeKoreanMessages: ModeMessages = {
   返回导入: "가져오기로 돌아가기",
   继续: "계속",
   "正在保存…": "저장 중…",
+  "当前模型已经启用，可以继续完成首次设置。":
+    "현재 모델이 이미 활성화되어 있습니다. 계속해서 초기 설정을 완료하세요.",
+  继续使用当前模型: "현재 모델로 계속",
   "你希望 MemHub 如何形成记忆？": "MemHub가 메모리를 어떻게 만들까요?",
   "需要明确选择一种方式；之后仍可在设置中更改。":
     "한 가지 방식을 선택하세요. 나중에 설정에서 변경할 수 있습니다.",
@@ -729,6 +756,9 @@ export const modeRussianMessages: ModeMessages = {
   返回导入: "Назад к импорту",
   继续: "Продолжить",
   "正在保存…": "Сохранение…",
+  "当前模型已经启用，可以继续完成首次设置。":
+    "Текущая модель уже включена. Продолжите, чтобы завершить настройку.",
+  继续使用当前模型: "Продолжить с текущей моделью",
   "你希望 MemHub 如何形成记忆？": "Как MemHub должен создавать воспоминания?",
   "需要明确选择一种方式；之后仍可在设置中更改。":
     "Выберите один вариант. Его можно изменить позже в настройках.",
@@ -811,6 +841,9 @@ export const modeIndonesianMessages: ModeMessages = {
   返回导入: "Kembali ke impor",
   继续: "Lanjutkan",
   "正在保存…": "Menyimpan…",
+  "当前模型已经启用，可以继续完成首次设置。":
+    "Model saat ini sudah aktif. Lanjutkan untuk menyelesaikan penyiapan.",
+  继续使用当前模型: "Lanjutkan dengan model saat ini",
   "你希望 MemHub 如何形成记忆？": "Bagaimana MemHub membuat memori?",
   "需要明确选择一种方式；之后仍可在设置中更改。":
     "Pilih satu opsi. Anda dapat mengubahnya nanti di Pengaturan.",