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

/**
 * The mesh assigns plex's tool runtime, and it serves plex's tools over an account the mesh
 * delivered — the whole of novox/hq ADR 0052.
 *
 * assigned-audit proves an assigned *consumer* (ADR 0048). This proves an assigned module that runs
 * its OWN code as its OWN process under its OWN scoped account and *serves tools*: the module is
 * assigned through the control plane, the mesh issues it an account scoped to serve.plex.* (and its
 * events), seals it to the machine, and the host runs it as a container that binds amqps with that
 * account. A caller then invokes plex.plex_reachable over the mesh and gets the tool's own answer —
 * proof the invocation routed to the assigned runtime, ran plex's real code, and replied, all under
 * the scoped account and never the broker's own.
 *
 * It needs the host binary, the substrate bundle, and the runtime image stocked by the scenario:
 *
 *   MESH_LAB_HOST_BINARY=.../mesh-host
 *   MESH_LAB_BUNDLE=.../examples/substrate-first-node.lock
 *   scripts/build-module-runtime.sh plex builds mesh-runtime-plex:development into the local daemon,
 *   which scenarios/plex-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 } from "./harness.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 = "plex-node";
const MACHINE = "anchor";

let instanceId = "";
/** What the scenario's registry serves, by digest. */
let stocked: string[] = [];

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;
}

/** The control plane, a container on the node. */
async function mesh(command: string, timeoutMs?: number): Promise<string> {
  return must(`docker exec mesh-control /mesh-control ${command}`, timeoutMs);
}

/** The pinned reference for one of the scenario's images, by repository. */
function pinned(repository: string): string {
  const found = stocked.find((r) => r.slice(r.indexOf("/") + 1, r.indexOf("@")) === repository);
  assert.ok(found, `the scenario stocks no ${repository}; it serves ${stocked.join(", ")}`);
  return found;
}

/** The substrate bundle, its image references pointed at this scenario's own registry. */
function bundleFor(images: string[]): string {
  let text = readFileSync(bundle, "utf8");
  for (const ref of images) {
    const repository = ref.slice(ref.indexOf("/") + 1, ref.indexOf("@"));
    const escaped = repository.replaceAll("/", "\\/").replaceAll(".", "\\.");
    text = text.replaceAll(new RegExp(`[A-Za-z0-9_.:-]+\\/${escaped}@sha256:[0-9a-f]+`, "g"), ref);
  }
  return text;
}

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;
  stocked = raised.images;

  // Raise the substrate — store, broker, control — from the bundle.
  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}`);
  }

  // The node joins its own mesh, so it is a node the mesh can assign to, and start the host so it
  // applies what it is pushed.
  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 plex's runtime, and it serves plex's tools over the account the mesh delivered", {
  skip, timeout: 900_000,
}, async () => {
  // A minimal plex manifest: its tools/events runtime (no Plex server or media mounts in the lab),
  // its emits and consumes so the account is scoped to those too, and a token in the environment so
  // the tools register without a running Plex to detect one from. The runtime image is the digest
  // this scenario's registry serves.
  const manifest = JSON.stringify({
    module: "plex",
    version: "1",
    emits: [
      "module.plex.playback.started",
      "module.plex.playback.stopped",
      "module.plex.item.added",
    ],
    consumes: ["module.*.download.completed"],
    "own-secrets": { broker: "/var/lib/mesh/plex/broker" },
    resources: [
      { id: "mesh-state", type: "directory", path: "/var/lib/mesh/plex", mode: "0700" },
      {
        id: "runtime", type: "container", name: "mesh-plex", image: pinned("mesh-runtime-plex"),
        network: "host",
        volumes: ["/var/lib/mesh/plex/broker:/run/secrets/broker:ro"],
        env: {
          MESH_BROKER_FILE: "/run/secrets/broker",
          MESH_PLEX_URL: "http://127.0.0.1:32400",
          MESH_PLEX_TOKEN: "lab-token",
        },
      },
    ],
  });
  await must(`printf %s ${quote(manifest)} > /tmp/plex.json && docker cp /tmp/plex.json mesh-control:/plex.json`);
  await mesh("module add /plex.json");

  // The mesh issues plex's scoped account and seals it to this machine, then assigns and pushes it.
  const issued = await mesh(`module issue plex --node ${MACHINE}`);
  assert.match(issued, /scoped to what it emits and consumes/, issued);
  await mesh(`assign ${MACHINE} plex`);
  await mesh(`push ${MACHINE}`);
  await settled();

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

  // The credential on disk is the scoped account over amqps, sealed — not the broker's own.
  const credential = await must(`cat /var/lib/mesh/plex/broker`);
  assert.match(credential, /"url":"amqps:\/\/anchor-plex:/, `not the scoped account:\n${credential}`);
  assert.doesNotMatch(credential, /guest:guest/, "plex's runtime holds the broker's own account");
  assert.match(credential, /"fingerprint":"(sha256:)?[0-9a-f]{64}"/, "no fingerprint to pin the broker");

  // The runtime registered and is serving its tools — the queue it declared is on the broker,
  // named for the scope its account is granted (serve.plex.*).
  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\.plex\.plex_reachable/.test(served)) break;
    await new Promise((r) => setTimeout(r, 3000));
  }
  assert.match(served, /serve\.plex\.plex_reachable/,
    `plex's runtime never bound its serve queue:\n${(await on(`docker logs mesh-plex 2>&1 | tail -20`)).out}\n---\n${served}`);

  // A caller invokes plex.plex_reachable over the mesh, from the bootstrap account (a caller, like
  // mesh-control's command API — plex's own account serves, it does not call). The reply is the
  // tool's own answer: it ran in the assigned runtime and reported the Plex server is unreachable
  // (there is none in the lab). A reply at all — not a timeout — is the proof the invocation routed
  // to the assigned runtime and ran plex's real code under its scoped account.
  const invoked = await must(
    `docker run --rm --network host -e MESH_BROKER_URL=amqp://guest:guest@127.0.0.1:5672/ ` +
      `${pinned("mesh-runtime-plex")} invoke plex plex_reachable`,
    120_000,
  );
  const line = invoked.split("\n").map((l) => l.trim()).filter(Boolean).pop() ?? "";
  const result = JSON.parse(line) as { reachable: boolean; url: string; error?: string };
  assert.equal(result.reachable, false, `expected the lab's Plex to be unreachable:\n${invoked}`);
  assert.match(result.url, /127\.0\.0\.1:32400/, `the tool ran but not against the configured server:\n${invoked}`);

  // And the account the mesh made for it is a real one on the broker, scoped — proven above by the
  // serve queue authenticating and the invocation round-tripping under it.
  const users = await must(`docker exec mesh-broker lavinmqctl list_users 2>&1`);
  assert.match(users, /anchor-plex/, `the scoped account is not on the broker:\n${users}`);
});