mesh-lab/test/integration/assigned-grafana.test.ts

/**
 * The mesh assigns grafana's tool runtime, configured entirely by the assignment's settings — the
 * ADR 0051 + 0052 case: config is the assignment's, delivered as a settings-merged file the runtime
 * reads, not a credential baked into the manifest.
 *
 * plex/sonarr prove a runtime that self-detects its key from the app's own config. This proves the
 * other half: the operator states grafana's URL and an API token as settings for this node, the
 * control plane merges them into the module's mergeable config file, and the runtime reads that file
 * at start, registers grafana's tools, and serves them under its scoped account. There is no live
 * Grafana — that the serve queue is bound is the proof the settings reached the runtime and its
 * tools loaded from them.
 *
 *   MESH_LAB_HOST_BINARY=.../mesh-host   MESH_LAB_BUNDLE=.../examples/substrate-first-node.lock
 *   scripts/build-module-runtime.sh grafana builds mesh-runtime-grafana:development into the local
 *   daemon, which scenarios/grafana-node.yml stocks — so no MESH_LAB_RUNTIME here; the host pulls it.
 */

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, substrateBundle, 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 substrate 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-control /mesh-control ${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 substrateBundle(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-control /mesh-control 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}`);
}

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/substrate.lock <<'MESHBUNDLE'\n${bundleFor(raised.images)}\nMESHBUNDLE`);
  await must(`${HOST_PATH} apply /tmp/substrate.lock`, 600_000);
  const up = await must(`docker ps --format '{{.Names}}'`);
  for (const c of ["mesh-store", "mesh-broker", "mesh-control"]) {
    assert.match(up, new RegExp(c), `the substrate 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("the mesh assigns grafana's runtime, configured by settings, and it serves its tools", {
  skip, timeout: 900_000,
}, async () => {
  // A grafana manifest with no credential in it: its runtime, and a mergeable config file the
  // settings will fill. This is the whole point of ADR 0051 — the manifest carries defaults and
  // structure, the assignment carries the URL and token.
  const manifest = JSON.stringify({
    module: "grafana",
    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: "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",
        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/grafana.json && docker cp /tmp/grafana.json mesh-control:/grafana.json`);
  await mesh("module add /grafana.json");

  // The operator states grafana's URL and API token as settings for this node — the config the
  // runtime will read. Nothing about them is in the manifest.
  const settings = JSON.stringify({ url: "http://127.0.0.1:3000", token: "lab-grafana-token" });
  await must(`printf %s ${quote(settings)} > /tmp/grafana-settings.json && docker cp /tmp/grafana-settings.json mesh-control:/grafana-settings.json`);
  await mesh(`settings set grafana /grafana-settings.json --node ${MACHINE}`);

  const issued = await mesh(`module issue grafana --node ${MACHINE}`);
  assert.match(issued, /scoped to what it emits and consumes/, issued);
  await mesh(`assign ${MACHINE} grafana`);
  await mesh(`push ${MACHINE}`);
  await settled();

  const running = await must(`docker ps --format '{{.Names}}'`);
  assert.match(running, /mesh-grafana/,
    `grafana's runtime was assigned and is not running:\n${(await on(`tail -30 /var/log/mesh-host.log`)).out}`);

  // The settings reached the node: the rendered config file carries what was set, not the manifest's
  // empty default.
  const config = await must(`cat /var/lib/mesh/grafana/config.json`);
  assert.match(config, /lab-grafana-token/, `the settings did not merge into the config file:\n${config}`);

  const credential = await must(`cat /var/lib/mesh/grafana/broker`);
  assert.match(credential, /"url":"amqps:\/\/anchor-grafana:/, `not the scoped account:\n${credential}`);
  assert.doesNotMatch(credential, /guest:guest/, "grafana's runtime holds the broker's own account");

  // The runtime read that config, built its client from the settings-provided token, registered its
  // tools, and bound their serve queues — the queue on the broker is the proof the settings-config
  // path reached serving, with no credential in the manifest and no live Grafana.
  let served = "";
  const untilServing = Date.now() + 60_000;
  while (Date.now() < untilServing) {
    served = await must(`docker exec mesh-broker lavinmqctl list_queues name 2>&1 || true`);
    if (/serve\.grafana\.grafana_status/.test(served)) break;
    await new Promise((r) => setTimeout(r, 3000));
  }
  assert.match(served, /serve\.grafana\.grafana_status/,
    `grafana's runtime never bound its serve queue (settings not read?):\n` +
      `${(await on(`docker logs mesh-grafana 2>&1 | tail -20`)).out}\n---\n${served}`);

  const users = await must(`docker exec mesh-broker lavinmqctl list_users 2>&1`);
  assert.match(users, /anchor-grafana/, `the scoped account is not on the broker:\n${users}`);
});