mesh-lab/test/integration/provider-uses-mesh-credential.test.ts

/**
 * A provider creates the resource with the credential the mesh minted — novox/hq ADR 0053.
 *
 * The old provisioner generated its own password, sealed it with a key nothing delivered, and
 * handed it back. This proves the corrected contract: redis's provisioner reads the mesh's
 * contributions file and, for each consumer, the password the mesh minted and the host unsealed, and
 * creates the ACL user under the login the mesh derived, with that exact password. No $MESH_SEAL_KEY
 * is set anywhere. The proof is authentication: a client logging in as that consumer with the mesh's
 * password gets PONG — where a provisioner that invented its own password would answer WRONGPASS.
 *
 * A hand-written contributions file and secret stand in for the control plane here (a full grant
 * from a second module is a heavier bed); their SHAPE is exactly what mesh-control writes — a
 * `receives` doc with `as`/`secret`, and the secret file the host leaves after unsealing.
 *
 *   MESH_LAB_HOST_BINARY=.../mesh-host   MESH_LAB_BUNDLE=.../examples/substrate-first-node.lock
 *   scripts/build-module-runtime.sh redis builds mesh-runtime-redis:development, which
 *   scenarios/redis-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, 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 = "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-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("redis creates a consumer's login with the password the mesh minted, sealing nothing", {
  skip, timeout: 900_000,
}, async () => {
  // redis as a provider: the server, and a broker-bound runtime that serves its tools AND runs its
  // provisioner. The provisioner is pointed at the contributions file the mesh would write
  // (MESH_RECEIVES). There is NO MESH_SEAL_KEY — the whole point of ADR 0053 is that a provider
  // needs none.
  const manifest = JSON.stringify({
    module: "redis",
    version: "1",
    emits: ["module.redis.cache.provisioned", "module.redis.cache.deprovisioned"],
    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",
          MESH_RECEIVES: "/var/lib/redis-module/grants/redis-cache.json",
          MESH_PROVISION_REDIS: "127.0.0.1:6379",
          MESH_PROVISION_PASSWORD_FILE: "/run/secrets/default",
        },
      },
    ],
  });
  await must(`printf %s ${quote(manifest)} > /tmp/redis.json && docker cp /tmp/redis.json mesh-control:/redis.json`);
  await mesh("module add /redis.json");
  await mesh(`module issue redis --node ${MACHINE}`);
  await mesh(`assign ${MACHINE} redis`);
  await mesh(`push ${MACHINE}`);
  await settled();

  const running = await must(`docker ps --format '{{.Names}}'`);
  assert.match(running, /mesh-redis/, `redis's runtime is not running:\n${(await on(`docker logs mesh-redis 2>&1 | tail -20`)).out}`);

  // What the mesh delivers to the provider: a contributions file naming the consumer's login and
  // where its password is, and the password itself as the file the host leaves after unsealing.
  const password = "mesh-minted-9f3c2a";
  await must(`printf %s ${quote(password)} > /var/lib/redis-module/grants/app.secret`);
  const contributions = JSON.stringify({
    contributions: 1,
    requirement: "redis-cache",
    generated: "by the mesh — do not edit",
    given: [
      { from: "app", node: "app-node", at: "192.0.2.20:6379", as: "app-one", secret: "/var/lib/redis-module/grants/app.secret", values: {} },
    ],
  });
  await must(`printf %s ${quote(contributions)} > /var/lib/redis-module/grants/redis-cache.json`);

  // Within a reconcile tick the provisioner creates the ACL user. It exists on the server.
  let acl = "";
  const until = Date.now() + 60_000;
  while (Date.now() < until) {
    acl = (await on(`docker exec redis redis-cli -a ${quote(await must(`cat /var/lib/redis-module/default.secret`))} --no-auth-warning ACL LIST 2>/dev/null`)).out;
    if (/app-one/.test(acl)) break;
    await new Promise((r) => setTimeout(r, 3000));
  }
  assert.match(acl, /app-one/, `the provisioner never created the consumer's login:\n${(await on(`docker logs mesh-redis 2>&1 | tail -30`)).out}\n---\n${acl}`);

  // The proof: authenticate as that consumer with the password the MESH minted. PONG means the
  // provisioner created the login with exactly that password. A provisioner that invented its own
  // (the old behaviour) would answer WRONGPASS here.
  const authed = await on(`docker exec redis redis-cli --user app-one --pass ${quote(password)} --no-auth-warning PING 2>&1`);
  assert.doesNotMatch(authed.out, /WRONGPASS/,
    `the consumer could not authenticate with the mesh's password — the provider used a different one:\n${authed.out}`);
  assert.match(authed.out, /PONG/, `expected PONG authenticating as the consumer:\n${authed.out}`);

  // And it needed no seal key: the runtime came up and provisioned with MESH_SEAL_KEY set nowhere.
  const env = await must(`docker inspect mesh-redis --format '{{json .Config.Env}}'`);
  assert.doesNotMatch(env, /MESH_SEAL_KEY/, `a seal key was set after all — ADR 0053 is not what ran:\n${env}`);

  // The provisioner emitted its lifecycle event under the bound account, and no emit was refused.
  const log = (await on(`docker logs mesh-redis 2>&1`)).out;
  assert.doesNotMatch(log, /emit .*failed/, `the provisioned event was refused:\n${log}`);
});