fix(doctor): treat gateway memory probe timeout as inconclusive (#72618)

CHANGELOG.md

@@ -29,6 +29,7 @@ Docs: https://docs.openclaw.ai
 - Exec/node: skip approval-plan preparation for full-trust `host=node` runs so interpreter and script commands no longer fail with `SYSTEM_RUN_DENIED: approval cannot safely bind` when effective policy is `security=full` and `ask=off`. Fixes #48457 and duplicate #69251. Thanks @ajtran303, @jaserNo1, @Blakeshannon, @lesliefag, and @AvIsBeastMC.
 - Exec/node: synthesize a local approval plan when a paired node advertises `system.run` without `system.run.prepare`, unblocking approval-required `host=node` exec on current macOS companion nodes while preserving remote prepare for node hosts that support it. Fixes #37591 and duplicate #66839; carries forward #69725. Thanks @soloclz.
 - Memory/QMD: prefer QMD's `--mask` collection pattern flag so root memory indexing stays scoped to `MEMORY.md` instead of widening to every markdown file in the workspace. Thanks @codex.
+- Memory/doctor: treat the specific `gateway timeout after ...` gateway memory probe result as inconclusive instead of reporting embeddings not ready, while preserving warnings for explicit failures. Fixes #44426; carries forward #46576 with the Greptile review feedback applied. Thanks Cengiz (@ghost).
 - Gateway/memory: defer QMD startup for implicit non-default agents and scope memory runtime loading to the selected memory slot so Gateway boot and first memory recall avoid broad plugin runtime fanout. Thanks @vincentkoc.
 - Gateway/startup: keep core request handlers, setup wizard, and channel runtime helpers off the boot path until the first matching request, wizard run, or channel start, reducing no-plugin Gateway ready RSS and avoidable startup imports. Thanks @vincentkoc.
 - CLI/Gateway: use a parse-only config snapshot for plain `gateway status` reads and reuse same-path service config context so status no longer spends tens of seconds in full config validation before printing. Thanks @vincentkoc.

src/commands/doctor-gateway-health.test.ts

@@ -0,0 +1,57 @@
+import { beforeEach, describe, expect, it, vi } from "vitest";
+import type { OpenClawConfig } from "../config/config.js";
+
+const callGateway = vi.hoisted(() => vi.fn());
+
+vi.mock("../gateway/call.js", () => ({
+  buildGatewayConnectionDetails: vi.fn(() => ({
+    message: "Gateway target: ws://127.0.0.1:18789",
+  })),
+  callGateway,
+}));
+
+vi.mock("./health.js", () => ({
+  healthCommand: vi.fn(),
+}));
+
+import { probeGatewayMemoryStatus } from "./doctor-gateway-health.js";
+
+describe("probeGatewayMemoryStatus", () => {
+  const cfg = {} as OpenClawConfig;
+
+  beforeEach(() => {
+    callGateway.mockReset();
+  });
+
+  it("treats outer gateway timeouts as inconclusive", async () => {
+    callGateway.mockRejectedValue(
+      new Error("gateway timeout after 8000ms\nGateway target: ws://127.0.0.1:18789"),
+    );
+
+    await expect(probeGatewayMemoryStatus({ cfg })).resolves.toEqual({
+      checked: false,
+      ready: false,
+      error: expect.stringContaining("gateway memory probe timed out"),
+    });
+  });
+
+  it("keeps gateway request timeouts as explicit failures", async () => {
+    callGateway.mockRejectedValue(new Error("gateway request timeout for doctor.memory.status"));
+
+    await expect(probeGatewayMemoryStatus({ cfg })).resolves.toEqual({
+      checked: true,
+      ready: false,
+      error: "gateway memory probe unavailable: gateway request timeout for doctor.memory.status",
+    });
+  });
+
+  it("keeps non-timeout gateway errors as explicit failures", async () => {
+    callGateway.mockRejectedValue(new Error("gateway closed (1006): no close reason"));
+
+    await expect(probeGatewayMemoryStatus({ cfg })).resolves.toEqual({
+      checked: true,
+      ready: false,
+      error: "gateway memory probe unavailable: gateway closed (1006): no close reason",
+    });
+  });
+});

src/commands/doctor-gateway-health.ts

@@ -14,6 +14,10 @@ export type GatewayMemoryProbe = {
   error?: string;
 };
 
+function isGatewayCallTimeout(message: string): boolean {
+  return /^gateway timeout after \d+ms(?:\n|$)/.test(message);
+}
+
 export async function checkGatewayHealth(params: {
   runtime: RuntimeEnv;
   cfg: OpenClawConfig;
@@ -84,6 +88,13 @@ export async function probeGatewayMemoryStatus(params: {
     };
   } catch (err) {
     const message = formatErrorMessage(err);
+    if (isGatewayCallTimeout(message)) {
+      return {
+        checked: false,
+        ready: false,
+        error: `gateway memory probe timed out: ${message}`,
+      };
+    }
     return {
       checked: true,
       ready: false,

src/commands/doctor-memory-search.test.ts

@@ -228,6 +228,24 @@ describe("noteMemorySearchHealth", () => {
     expect(note).not.toHaveBeenCalled();
   });
 
+  it("does not treat an inconclusive gateway timeout as local embeddings not ready", async () => {
+    resolveMemorySearchConfig.mockReturnValue({
+      provider: "local",
+      local: {},
+      remote: {},
+    });
+
+    await noteMemorySearchHealth(cfg, {
+      gatewayMemoryProbe: {
+        checked: false,
+        ready: false,
+        error: "gateway memory probe timed out: gateway timeout after 8000ms",
+      },
+    });
+
+    expect(note).not.toHaveBeenCalled();
+  });
+
   it("does not warn when local provider has an explicit hf: modelPath", async () => {
     resolveMemorySearchConfig.mockReturnValue({
       provider: "local",