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

/**
 * The mesh assigns redis — a *provider* — and its runtime runs the provisioner AND the tools as one
 * process under one account the mesh delivered (novox/hq ADR 0052).
 *
 * assigned-plex proves an assigned module that serves tools. This proves the provider half: redis's
 * runtime binds its scoped account, serves redis's tools against the real server (redis_ping →
 * PONG), and — the thing 0052 fixes — runs its provisioner in that same broker-bound process, so a
 * grant is provisioned and its lifecycle event is emitted onto the mesh. Before 0052 the provisioner
 * ran in a container with no broker and its emit could not fire at all.
 *
 * A caveat this test makes explicit: runProvisioner needs a seal key ($MESH_SEAL_KEY) and the mesh
 * has no way yet to deliver one to a provider's runtime (04-ISSUES). The manifest here sets a
 * lab-local key so the mechanism can be proven; the delivery is a separate, open design question.
 *
 * 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-module-runtime.sh redis builds mesh-runtime-redis:development into the local
 *   daemon, which scenarios/redis-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 } 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 = "redis-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}`);
}

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("the mesh assigns redis, and its runtime serves tools and provisions grants over the account the mesh delivered", {
  skip, timeout: 900_000,
}, async () => {
  // A redis manifest with both halves it needs on this node: the redis server, and one broker-bound
  // runtime that serves redis's tools AND runs its provisioner. Both reach the server over the host
  // (127.0.0.1:6379) with the same admin password the mesh generated. MESH_SEAL_KEY is lab-local —
  // the mesh cannot yet deliver one to a provider's runtime (see the file header / 04-ISSUES).
  const manifest = JSON.stringify({
    module: "redis",
    version: "1",
    emits: ["module.redis.cache.provisioned", "module.redis.cache.deprovisioned"],
    // redis's events entrypoint subscribes to its own lifecycle events (an audit-trail log), so it
    // consumes them too — declared, or the foundation never makes the queue the runtime binds and it
    // crashes on start with a 404 (novox/hq ADR 0046: a consume is declared).
    consumes: ["module.redis.cache.provisioned", "module.redis.cache.deprovisioned"],
    "own-secrets": { default: "/var/lib/redis-module/default.secret", broker: "/var/lib/mesh/redis/broker" },
    resources: [
      { id: "mesh-state", type: "directory", path: "/var/lib/mesh/redis", mode: "0700" },
      { id: "state", type: "directory", path: "/var/lib/redis-module", mode: "0700" },
      { id: "grants-dir", type: "directory", path: "/var/lib/redis-module/grants", mode: "0700" },
      { id: "data", type: "directory", path: "/services/redis/data", mode: "0700", owner: "999:999" },
      {
        id: "server-conf", type: "file", path: "/var/lib/redis-module/redis.conf", mode: "0644",
        content: "requirepass ${secret:default}\nappendonly no\ndir /data\n",
      },
      {
        id: "server", type: "container", name: "redis", image: pinned("redis"), network: "host",
        volumes: [
          "/services/redis/data:/data",
          "/var/lib/redis-module/redis.conf:/etc/redis/redis.conf:ro",
        ],
        args: ["/etc/redis/redis.conf"],
      },
      {
        id: "runtime", type: "container", name: "mesh-redis", image: pinned("mesh-runtime-redis"),
        network: "host",
        volumes: [
          "/var/lib/mesh/redis/broker:/run/secrets/broker:ro",
          "/var/lib/redis-module/grants:/var/lib/redis-module/grants",
          "/var/lib/redis-module/default.secret:/run/secrets/default:ro",
        ],
        env: {
          MESH_BROKER_FILE: "/run/secrets/broker",
          GRANTS: "/var/lib/redis-module/grants",
          MESH_PROVISION_REDIS: "127.0.0.1:6379",
          MESH_PROVISION_PASSWORD_FILE: "/run/secrets/default",
          MESH_SEAL_KEY: "lab-only-seal-key",
        },
      },
    ],
  });
  await must(`printf %s ${quote(manifest)} > /tmp/redis.json && docker cp /tmp/redis.json mesh-controller:/redis.json`);
  await mesh("module add /redis.json");

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

  // The server and the runtime the mesh started are both running.
  const running = await must(`docker ps --format '{{.Names}}'`);
  assert.match(running, /\bredis\b/, `redis's server is not running:\n${(await on(`tail -30 /var/log/mesh-host.log`)).out}`);
  assert.match(running, /mesh-redis/, `redis's runtime is not running:\n${(await on(`docker logs mesh-redis 2>&1 | tail -20`)).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/redis/broker`);
  assert.match(credential, /"url":"amqps:\/\/anchor-redis:/, `not the scoped account:\n${credential}`);
  assert.doesNotMatch(credential, /guest:guest/, "redis'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 serve queue is on the broker.
  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\.redis\.redis_ping/.test(served)) break;
    await new Promise((r) => setTimeout(r, 3000));
  }
  assert.match(served, /serve\.redis\.redis_ping/,
    `redis's runtime never bound its serve queue:\n${(await on(`docker logs mesh-redis 2>&1 | tail -30`)).out}\n---\n${served}`);

  // A caller invokes redis.redis_ping over the mesh: the tool runs in the assigned runtime, reaches
  // the real redis, and answers PONG. A positive round-trip against a real backend.
  const pinged = await must(
    `docker run --rm --network host -e MESH_BROKER_URL=amqp://guest:guest@127.0.0.1:5672/ ` +
      `${pinned("mesh-runtime-redis")} invoke redis redis_ping`,
    120_000,
  );
  const pingLine = pinged.split("\n").map((l) => l.trim()).filter(Boolean).pop() ?? "";
  const ping = JSON.parse(pingLine) as { ok: unknown };
  assert.ok(String(ping.ok).toUpperCase().includes("PONG") || ping.ok === true,
    `redis_ping did not answer PONG through the mesh:\n${pinged}`);

  // The provider path: a grant appears (as the control plane would write it), and the provisioner —
  // running inside the same broker-bound runtime — creates the ACL user and emits the lifecycle
  // event. The sealed credential the harness writes only after adapter.create() returns is the
  // proof create() ran to completion; and because emit() awaits the broker's publish confirm
  // (ADR 0047), a completed create() means the provisioned event was accepted onto the mesh.
  const grant = JSON.stringify({ resource: "redis-cache", consumer: "app-one", node: MACHINE, values: {} });
  await must(`printf %s ${quote(grant)} > /var/lib/redis-module/grants/app-one.grant.json`);

  let credentialWritten = false;
  const untilProvisioned = Date.now() + 60_000;
  while (Date.now() < untilProvisioned) {
    const ls = await on(`ls /var/lib/redis-module/grants/`);
    if (ls.ok && /app-one\.redis-cache\.credential/.test(ls.out)) { credentialWritten = true; break; }
    await new Promise((r) => setTimeout(r, 3000));
  }
  assert.ok(credentialWritten,
    `the provisioner never provisioned the grant (no emit under a bound broker?):\n` +
      `${(await on(`docker logs mesh-redis 2>&1 | tail -30`)).out}`);

  // No emit failed: the provisioner's announce() logs "emit ... failed" only when the broker refused
  // the publish. Its absence, with the credential written, is the provisioner emitting on the mesh.
  const runtimeLog = (await on(`docker logs mesh-redis 2>&1`)).out;
  assert.doesNotMatch(runtimeLog, /emit .*failed/,
    `the provisioner's emit was refused — the account cannot publish its lifecycle event:\n${runtimeLog}`);

  // And the ACL user the provisioner created is really on the redis server — the provisioning did
  // its own half, not only the mesh bookkeeping. Asked through the same served tool surface.
  const acl = await must(
    `docker run --rm --network host -e MESH_BROKER_URL=amqp://guest:guest@127.0.0.1:5672/ ` +
      `${pinned("mesh-runtime-redis")} invoke redis redis_command '{"command":"ACL LIST"}'`,
    120_000,
  );
  assert.match(acl, /app-one/, `the provisioner did not create the consumer's ACL user on redis:\n${acl}`);

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