test: cover SIGUSR1 restart timeout in run loop

CHANGELOG.md

@@ -34,6 +34,7 @@ Docs: https://docs.openclaw.ai
 - Android/Nodes: harden `app.update` by requiring HTTPS and gateway-host URL matching plus SHA-256 verification, stream URL camera downloads to disk with size guards to avoid memory spikes, and stop signing release builds with debug keys. (#13541) Thanks @smartprogrammer93.
 - Auto-reply/Threading: auto-inject implicit reply threading so `replyToMode` works without requiring model-emitted `[[reply_to_current]]`, while preserving `replyToMode: "off"` behavior for implicit Slack replies and keeping block-streaming chunk coalescing stable under `replyToMode: "first"`. (#14976) Thanks @Diaspar4u.
 - Sandbox: pass configured `sandbox.docker.env` variables to sandbox containers at `docker create` time. (#15138) Thanks @stevebot-alive.
+- Gateway/Restart: clear stale command-queue and heartbeat wake runtime state after SIGUSR1 in-process restarts to prevent zombie gateway behavior where queued work stops draining. (#15195) Thanks @joeykrug.
 - Onboarding/CLI: restore terminal state without resuming paused `stdin`, so onboarding exits cleanly after choosing Web UI and the installer returns instead of appearing stuck.
 - Auth/OpenAI Codex: share OAuth login handling across onboarding and `models auth login --provider openai-codex`, keep onboarding alive when OAuth fails, and surface a direct OAuth help note instead of terminating the wizard. (#15406, follow-up to #14552) Thanks @zhiluo20.
 - Onboarding/Providers: add vLLM as an onboarding provider with model discovery, auth profile wiring, and non-interactive auth-choice validation. (#12577) Thanks @gejifeng.

src/cli/gateway-cli/run-loop.test.ts

@@ -0,0 +1,120 @@
+import { describe, expect, it, vi } from "vitest";
+
+const acquireGatewayLock = vi.fn(async () => ({
+  release: vi.fn(async () => {}),
+}));
+const consumeGatewaySigusr1RestartAuthorization = vi.fn(() => true);
+const isGatewaySigusr1RestartExternallyAllowed = vi.fn(() => false);
+const getActiveTaskCount = vi.fn(() => 0);
+const waitForActiveTasks = vi.fn(async () => ({ drained: true }));
+const resetAllLanes = vi.fn();
+const gatewayLog = {
+  info: vi.fn(),
+  warn: vi.fn(),
+  error: vi.fn(),
+};
+
+vi.mock("../../infra/gateway-lock.js", () => ({
+  acquireGatewayLock: () => acquireGatewayLock(),
+}));
+
+vi.mock("../../infra/restart.js", () => ({
+  consumeGatewaySigusr1RestartAuthorization: () => consumeGatewaySigusr1RestartAuthorization(),
+  isGatewaySigusr1RestartExternallyAllowed: () => isGatewaySigusr1RestartExternallyAllowed(),
+}));
+
+vi.mock("../../process/command-queue.js", () => ({
+  getActiveTaskCount: () => getActiveTaskCount(),
+  waitForActiveTasks: (timeoutMs: number) => waitForActiveTasks(timeoutMs),
+  resetAllLanes: () => resetAllLanes(),
+}));
+
+vi.mock("../../logging/subsystem.js", () => ({
+  createSubsystemLogger: () => gatewayLog,
+}));
+
+function removeNewSignalListeners(
+  signal: NodeJS.Signals,
+  existing: Set<(...args: unknown[]) => void>,
+) {
+  for (const listener of process.listeners(signal)) {
+    const fn = listener as (...args: unknown[]) => void;
+    if (!existing.has(fn)) {
+      process.removeListener(signal, fn);
+    }
+  }
+}
+
+describe("runGatewayLoop", () => {
+  it("restarts after SIGUSR1 even when drain times out, and resets lanes for the new iteration", async () => {
+    vi.clearAllMocks();
+    getActiveTaskCount.mockReturnValueOnce(2).mockReturnValueOnce(0);
+    waitForActiveTasks.mockResolvedValueOnce({ drained: false });
+
+    const closeFirst = vi.fn(async () => {});
+    const closeSecond = vi.fn(async () => {});
+    const start = vi
+      .fn<
+        () => Promise<{
+          close: (opts: { reason: string; restartExpectedMs: number | null }) => Promise<void>;
+        }>
+      >()
+      .mockResolvedValueOnce({ close: closeFirst })
+      .mockResolvedValueOnce({ close: closeSecond })
+      .mockRejectedValueOnce(new Error("stop-loop"));
+
+    const beforeSigterm = new Set(
+      process.listeners("SIGTERM") as Array<(...args: unknown[]) => void>,
+    );
+    const beforeSigint = new Set(
+      process.listeners("SIGINT") as Array<(...args: unknown[]) => void>,
+    );
+    const beforeSigusr1 = new Set(
+      process.listeners("SIGUSR1") as Array<(...args: unknown[]) => void>,
+    );
+
+    const loopPromise = import("./run-loop.js").then(({ runGatewayLoop }) =>
+      runGatewayLoop({
+        start,
+        runtime: {
+          exit: vi.fn(),
+        } as { exit: (code: number) => never },
+      }),
+    );
+
+    try {
+      await vi.waitFor(() => {
+        expect(start).toHaveBeenCalledTimes(1);
+      });
+
+      process.emit("SIGUSR1");
+
+      await vi.waitFor(() => {
+        expect(start).toHaveBeenCalledTimes(2);
+      });
+
+      expect(waitForActiveTasks).toHaveBeenCalledWith(30_000);
+      expect(gatewayLog.warn).toHaveBeenCalledWith(
+        "drain timeout reached; proceeding with restart",
+      );
+      expect(closeFirst).toHaveBeenCalledWith({
+        reason: "gateway restarting",
+        restartExpectedMs: 1500,
+      });
+      expect(resetAllLanes).toHaveBeenCalledTimes(1);
+
+      process.emit("SIGUSR1");
+
+      await expect(loopPromise).rejects.toThrow("stop-loop");
+      expect(closeSecond).toHaveBeenCalledWith({
+        reason: "gateway restarting",
+        restartExpectedMs: 1500,
+      });
+      expect(resetAllLanes).toHaveBeenCalledTimes(2);
+    } finally {
+      removeNewSignalListeners("SIGTERM", beforeSigterm);
+      removeNewSignalListeners("SIGINT", beforeSigint);
+      removeNewSignalListeners("SIGUSR1", beforeSigusr1);
+    }
+  });
+});