AgentHub/server/__tests__/self-restart.test.js

/**
 * @file self-restart.test.js
 * @description After an update, a server our service unit runs is restarted
 * by the unit, never by a detached replacement: v2.7.2 on the S3 system unit
 * left the replacement holding the port while `Restart=always` started the
 * unit every 3 s, each start exiting "already running". Without a unit, the
 * detached helper's replacement server logs to `data/agenthub-server.log`.
 * @author Nguyễn Ngọc Trí Vĩ <vinnt@smartgift.vn>
 */

const { describe, it } = require("node:test");
const assert = require("node:assert/strict");
const fs = require("node:fs");
const os = require("node:os");
const path = require("node:path");
const { execFileSync } = require("node:child_process");
const { scheduleRestart, owningUnit } = require("../lib/self-restart");

function deps(unit, restartAnswer = "restarted") {
  const calls = { restart: [], kill: 0, spawn: 0 };
  return {
    calls,
    unit,
    svc: () => ({
      restartUserService: (name) => {
        calls.restart.push(name);
        return restartAnswer;
      },
    }),
    kill: () => calls.kill++,
    spawnHelper: (_exe, args) => {
      calls.spawn++;
      calls.helperArgs = args;
      return { unref() {} };
    },
  };
}

describe("self-restart", () => {
  it("tells which unit owns this process, from its cgroup or launchd label", () => {
    const linux = (text) => owningUnit({ platform: "linux", cgroup: () => text });
    assert.equal(linux("0::/system.slice/agenthub.service\n"), "systemd");
    assert.equal(
      linux("0::/user.slice/user-1001.slice/user@1001.service/app.slice/agenthub.service\n"),
      "systemd"
    );
    assert.equal(linux("0::/user.slice/user-1001.slice/session-3.scope\n"), null);
    assert.equal(linux("0::/system.slice/agenthub.service.d/x\n"), null);
    assert.equal(
      owningUnit({
        platform: "linux",
        cgroup: () => {
          throw new Error("no /proc");
        },
      }),
      null
    );
    assert.equal(
      owningUnit({ platform: "darwin", env: { XPC_SERVICE_NAME: "io.smartgift.agenthub" } }),
      "launchd"
    );
    assert.equal(owningUnit({ platform: "darwin", env: {} }), null);
  });

  it("asks systemd to restart its unit and starts no replacement", () => {
    const d = deps("systemd");
    assert.equal(scheduleRestart("/r", d), "service");
    assert.deepEqual(d.calls.restart, ["agenthub"]);
    assert.equal(d.calls.spawn, 0);
    assert.equal(d.calls.kill, 0, "systemd's restart job stops this process");
  });

  it("exits for Restart=always when systemd cannot be asked — still no replacement", () => {
    const d = deps("systemd", "failed");
    assert.equal(scheduleRestart("/r", d), "exit");
    assert.equal(d.calls.kill, 1);
    assert.equal(d.calls.spawn, 0);
  });

  it("exits under launchd, whose KeepAlive starts the new code", () => {
    const d = deps("launchd");
    assert.equal(scheduleRestart("/r", d), "exit");
    assert.equal(d.calls.kill, 1);
    assert.equal(d.calls.spawn, 0);
    assert.deepEqual(d.calls.restart, []);
  });

  it("hands over to the detached helper when no unit owns the server", () => {
    const d = deps(null);
    assert.equal(scheduleRestart("/r", d), "helper");
    assert.equal(d.calls.spawn, 1);
    assert.equal(d.calls.kill, 1);
    // The new server logs where `agenthub start` does — never into nothing.
    assert.equal(d.calls.helperArgs.at(-1), path.join("/r", "data", "agenthub-server.log"));
  });

  it("restart-helper appends the new server's stdout and stderr to the log", async () => {
    const dir = fs.mkdtempSync(path.join(os.tmpdir(), "restart-helper-"));
    const entry = path.join(dir, "entry.js");
    const log = path.join(dir, "data", "agenthub-server.log");
    fs.writeFileSync(entry, 'console.log("up"); throw new Error("boom");\n');
    const helper = path.join(__dirname, "..", "..", "scripts", "restart-helper.js");
    // pid 0x7fffffff is never alive, so the helper restarts at once.
    execFileSync(process.execPath, [helper, "2147483647", entry, log]);
    const deadline = Date.now() + 5000;
    let text = "";
    while (Date.now() < deadline && !/boom/.test(text)) {
      await new Promise((r) => setTimeout(r, 50));
      text = fs.existsSync(log) ? fs.readFileSync(log, "utf8") : "";
    }
    fs.rmSync(dir, { recursive: true, force: true });
    assert.match(text, /restart-helper: old server 2147483647 gone/);
    assert.match(text, /^up$/m);
    assert.match(text, /Error: boom/);
  });
});