mesh-lab/test/integration/runtime-restart-on-config.test.ts

/**
 * A running tool runtime picks up a settings change — novox/hq 04-ISSUES/009, and its fix.
 *
 * A runtime reads its settings-merged config file once, at start. Change the settings on an
 * already-running runtime and, without this, the container keeps the value it read: its spec did
 * not move (a mounted file's content is not part of it) so the host left it alone, and every check
 * passed while the mesh did the old thing. The fix gives a container `restart-on`, the same field a
 * service has: the runtime names its config resource, and the host recreates the container when that
 * resource changed this pass.
 *
 * This assigns a settings-configured runtime (the fixture wears no catalogue name; its image is grafana's tool runtime), then changes the token and pushes again, and asserts
 * the container was replaced (a new container id) and the config on disk carries the new value.
 * It builds the host from source (no --no-build), because the behaviour under test is the host's.
 *
 *   MESH_LAB_HOST_BINARY=.../mesh-host   MESH_LAB_BUNDLE=.../examples/foundation-first-node.lock
 *   scripts/build-module-runtime.sh grafana builds mesh-runtime-grafana:development, which
 *   scenarios/grafana-node.yml stocks.
 */

import { test, before, after } from "node:test";
import assert from "node:assert/strict";
import { existsSync, readFileSync } from "node:fs";
import { loadScenario } from "../../src/declaration/parse.ts";
import { raise } from "../../src/lifecycle/raise.ts";
import { destroy, exec } from "../../src/lifecycle/operate.ts";
import { hostBinaryPath, HOST_PATH } from "../../src/lifecycle/place.ts";
import { labIsUsable, destroyAll, foundationBundle, onTheMachine } from "./harness.ts";
import type { HeldImage } from "../../src/pinning.ts";

const capability = await labIsUsable();
const binary = hostBinaryPath();
const bundle = process.env["MESH_LAB_BUNDLE"] ?? "";

const skip = !capability.usable
  ? `lab not usable: ${capability.why}`
  : !binary || !existsSync(binary)
    ? "MESH_LAB_HOST_BINARY is not set to a built mesh-host"
    : !bundle || !existsSync(bundle)
      ? "MESH_LAB_BUNDLE is not set to a foundation bundle (mesh-host examples/)"
      : false;

const SCENARIO = "grafana-node";
const MACHINE = "anchor";

let instanceId = "";
let held: HeldImage[] = [];

function quote(s: string): string {
  return `'${s.replaceAll("'", `'\\''`)}'`;
}

async function on(command: string, timeoutMs?: number): Promise<{ out: string; ok: boolean }> {
  const { stdout } = await exec(instanceId, MACHINE, [
    "sh", "-c", `exec 2>&1\n${command}\necho "__exit=$?"`,
  ], timeoutMs);
  const marker = stdout.lastIndexOf("__exit=");
  if (marker < 0) return { out: stdout, ok: false };
  return { out: stdout.slice(0, marker), ok: stdout.slice(marker + 7).trim() === "0" };
}

async function must(command: string, timeoutMs?: number): Promise<string> {
  const { out, ok } = await on(command, timeoutMs);
  if (!ok) throw new Error(`${MACHINE}: ${command}\n${out}`);
  return out;
}

async function mesh(command: string, timeoutMs?: number): Promise<string> {
  return must(`docker exec mesh-controller /mesh-controller ${command}`, timeoutMs);
}

/** What a manifest's image reference becomes on the machine — ours by ID, everything else as written. */
function pinned(reference: string): string {
  return onTheMachine(reference, held);
}

function bundleFor(images: HeldImage[]): string {
  return foundationBundle(bundle, images);
}

function tokenFrom(said: string): string {
  const found = said.split("\n").map((l) => l.trim()).find((l) => l.length > 100 && !l.includes(" "));
  assert.ok(found, `no token in:\n${said}`);
  return found;
}

async function settled(withinMs = 480_000): Promise<void> {
  const until = Date.now() + withinMs;
  let last = "";
  while (Date.now() < until) {
    const asked = await on(`docker exec mesh-controller /mesh-controller status --json`);
    if (asked.ok) {
      try {
        const state = JSON.parse(asked.out) as {
          wrong: { node: string; outcome: string }[];
          waiting: { node: string }[];
          reported: { node: string; outcome: string; current: boolean }[];
        };
        const bad = state.wrong.find((w) => w.node === MACHINE);
        if (bad) throw new Error(`${MACHINE} did not apply what it was sent: ${bad.outcome}\n${asked.out}`);
        const word = state.reported.find((r) => r.node === MACHINE);
        if (!state.waiting.some((w) => w.node === MACHINE) && word?.outcome === "applied" && word.current) return;
        last = asked.out;
      } catch (err) {
        if (err instanceof Error && err.message.includes("did not apply")) throw err;
        last = asked.out;
      }
    }
    await new Promise((r) => setTimeout(r, 5000));
  }
  throw new Error(`${MACHINE} never caught up within ${Math.round(withinMs / 1000)}s. Last:\n${last}`);
}

async function setToken(token: string): Promise<void> {
  const settings = JSON.stringify({ url: "http://127.0.0.1:3000", token });
  await must(`printf %s ${quote(settings)} > /tmp/s.json && docker cp /tmp/s.json mesh-controller:/s.json`);
  await mesh(`settings set a-runtime /s.json --node ${MACHINE}`);
}

async function containerId(): Promise<string> {
  return (await must(`docker inspect mesh-grafana --format '{{.Id}}'`)).trim();
}

before(async () => {
  if (skip) return;

  const raised = await raise(loadScenario(`scenarios/${SCENARIO}.yml`), {
    onProgress: (m) => console.log(`raise: ${m}`),
  });
  instanceId = raised.instanceId;
  held = raised.images;

  await must(`cat > /tmp/foundation.lock <<'MESHBUNDLE'\n${bundleFor(raised.images)}\nMESHBUNDLE`);
  await must(`${HOST_PATH} apply /tmp/foundation.lock`, 600_000);
  const up = await must(`docker ps --format '{{.Names}}'`);
  for (const c of ["mesh-store", "mesh-broker", "mesh-controller"]) {
    assert.match(up, new RegExp(c), `the foundation did not raise ${c}:\n${up}`);
  }

  await mesh(`node add ${MACHINE}`);
  const token = tokenFrom(await mesh(`token issue --node ${MACHINE}`));
  await must(`${HOST_PATH} enrol --token ${quote(token)}`);
  await must(`nohup ${HOST_PATH} run > /var/log/mesh-host.log 2>&1 & sleep 3`);
}, { timeout: 1_800_000 });

after(async () => {
  if (instanceId) await destroy(instanceId);
  await destroyAll(`${SCENARIO}-`);
}, { timeout: 600_000 });

test("a running runtime is recreated when its settings change, and reads the new value", {
  skip, timeout: 900_000,
}, async () => {
  const manifest = JSON.stringify({
    module: "a-runtime",
    version: "1",
    emits: ["module.grafana.alert.firing"],
    "own-secrets": { broker: "/var/lib/mesh/grafana/broker" },
    resources: [
      { id: "mesh-state", type: "directory", path: "/var/lib/mesh/grafana", mode: "0700" },
      { id: "runtime-config", type: "file", path: "/var/lib/mesh/grafana/config.json", mode: "0600", content: "{}\n", merge: "json" },
      {
        id: "runtime", type: "container", name: "mesh-grafana", image: pinned("mesh-runtime-grafana"),
        network: "host",
        "restart-on": ["runtime-config"],
        volumes: [
          "/var/lib/mesh/grafana/broker:/run/secrets/broker:ro",
          "/var/lib/mesh/grafana/config.json:/run/config/config.json:ro",
        ],
        env: { MESH_BROKER_FILE: "/run/secrets/broker", MESH_GRAFANA_CONFIG_FILE: "/run/config/config.json" },
      },
    ],
  });
  await must(`printf %s ${quote(manifest)} > /tmp/a-runtime.json && docker cp /tmp/a-runtime.json mesh-controller:/a-runtime.json`);
  await mesh("module add /a-runtime.json");

  await setToken("token-alpha");
  await mesh(`module issue a-runtime --node ${MACHINE}`);
  await mesh(`assign ${MACHINE} a-runtime`);
  await mesh(`push ${MACHINE}`);
  await settled();

  const before = await containerId();
  const configBefore = await must(`cat /var/lib/mesh/grafana/config.json`);
  assert.match(configBefore, /token-alpha/, `first settings not rendered:\n${configBefore}`);

  // Change the setting on the already-running runtime, and push. Nothing about the container's
  // spec changes — only the content of the file it mounts.
  await setToken("token-bravo");
  await mesh(`push ${MACHINE}`);
  await settled();

  const configAfter = await must(`cat /var/lib/mesh/grafana/config.json`);
  assert.match(configAfter, /token-bravo/, `the settings change did not re-render the config:\n${configAfter}`);

  const after = await containerId();
  assert.notEqual(after, before,
    `the runtime was NOT recreated on a config change (issue 009 not fixed): id stayed ${before}\n` +
      `host log:\n${(await on(`grep -i grafana /var/log/mesh-host.log | tail -10`)).out}`);

  // And it is running on the new container, so the process re-read the new config.
  const running = await must(`docker ps --format '{{.Names}}'`);
  assert.match(running, /mesh-grafana/, "the recreated runtime is not running");
});