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

/**
 * The mesh assigns the audit logger, and it consumes over an account the mesh delivered.
 *
 * events.test.ts proves the events path with the audit logger started by hand. This proves the
 * whole of novox/hq ADR 0048: the module is assigned through the control plane, the mesh issues it
 * a broker account scoped to what it consumes, seals it to the machine, and the host runs it as a
 * container that connects over amqps with that account — never the broker's own. The trail filling
 * is the proof the delivered, scoped credential authenticated and the subscription bound.
 *
 * It needs the host binary, the foundation bundle, and the runtime image the scenario loads:
 *
 *   MESH_LAB_HOST_BINARY=.../mesh-host
 *   MESH_LAB_BUNDLE=.../examples/foundation-first-node.lock
 *   scripts/build-runtime-image.sh builds mesh-runtime-audit:development into the local daemon,
 *   which scenarios/audit-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, foundationBundle, onTheMachine, catalogueModule, catalogueIsPresent } 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/)"
      : catalogueIsPresent();

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

let instanceId = "";
/** The mesh's own images, as the machines hold them. */
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;
}

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

/** The reference a manifest should carry, once this scenario has been raised. */
/** 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);
}

/** The foundation bundle: ours by the ID the machine holds, everything else upstream. */
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}`);
}

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;

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

  // 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 the audit logger, and it consumes over the account the mesh delivered", {
  skip, timeout: 900_000,
}, async () => {
  // The catalogue's manifest (novox/hq 04-ISSUES/073). Its runtime artifact is the image this
  // scenario stocks under the module's slug, `mesh-runtime-audit` — built by scripts/build-runtime-image.sh
  // before build-module-runtime.sh generalised it, and named as it was.
  const manifest = catalogueModule("audit-logger", held, { artifacts: { runtime: "mesh-runtime-audit" } });
  await must(`printf %s ${quote(manifest)} > /tmp/audit.json && docker cp /tmp/audit.json mesh-controller:/audit.json`);
  await mesh("module add /audit.json");

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

  // The container the mesh started is running.
  const running = await must(`docker ps --format '{{.Names}}'`);
  assert.match(running, /mesh-audit-logger/,
    `the audit logger 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/audit-logger/broker`);
  assert.match(credential, /"url":"amqps:\/\/anchor-audit-logger:/, `not the scoped account:\n${credential}`);
  assert.doesNotMatch(credential, /guest:guest/, "the audit logger holds the broker's own account");
  assert.match(credential, /"fingerprint":"(sha256:)?[0-9a-f]{64}"/, "no fingerprint to pin the broker");

  // An event, emitted by a probe over the bootstrap account (the audit logger's own may not emit).
  await must(
    `docker run --rm --network host -e MESH_BROKER_URL=amqp://guest:guest@127.0.0.1:5672/ ` +
      `-e MESH_MODULE=probe -e MESH_NODE=${MACHINE} ${pinned("mesh-runtime-audit")} ` +
      `emit module.probe.site.created '{"domain":"my-app"}'`,
  );

  // It reaches the trail the assigned container writes — proof its delivered account authenticated.
  let line: Record<string, unknown> | undefined;
  const until = Date.now() + 60_000;
  while (Date.now() < until) {
    const raw = await must(`cat /var/lib/audit-logger/trail/audit.log 2>/dev/null || true`);
    line = raw.split("\n").map((l) => l.trim()).filter(Boolean).map((l) => JSON.parse(l) as Record<string, unknown>)
      .find((e) => e.type === "module.probe.site.created");
    if (line) break;
    await new Promise((r) => setTimeout(r, 3000));
  }
  assert.ok(line, `the event never reached the trail:\n${(await on(`docker logs mesh-audit-logger 2>&1 | tail -20`)).out}`);
  assert.equal(line.source, "probe");
  assert.deepEqual(line.body, { domain: "my-app" });

  // And the account the mesh made for it is a real one on the broker — the trail above already
  // proved it authenticated and read its queue. That it reaches no further than its own queue is
  // the scope CreateModuleAccount applies, checked as patterns in mesh-controller's own tests.
  const users = await must(`docker exec mesh-broker lavinmqctl list_users 2>&1`);
  assert.match(users, /anchor-audit-logger/, `the scoped account is not on the broker:\n${users}`);
});