mesh-lab/test/integration/postgres-grant-end-to-end.test.ts

/**
 * The whole grant for a database, mesh-driven — novox/hq ADR 0052/0053, the postgres case.
 *
 * The redis bed proves the provider/consumer contract for a cache. This proves it for a database, on
 * a provider whose code shells out to `psql` (so the runtime image carries it): postgres is assigned,
 * a consumer that requires postgres-database is assigned, and the mesh mints one password, seals a
 * copy to each end, and writes each its file. postgres's provisioner — reading only the mesh's
 * contributions — creates a role and a database under the login the mesh derived, with the password
 * the mesh minted. The proof is the consumer connecting to its database with the credential the mesh
 * delivered it. Nothing is placed by the test.
 *
 *   MESH_LAB_HOST_BINARY=.../mesh-host   MESH_LAB_BUNDLE=.../examples/foundation-first-node.lock
 *   scripts/build-module-runtime.sh postgres builds mesh-runtime-postgres:development (with psql),
 *   which scenarios/postgres-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, 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 = "postgres-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 grants a consumer a postgres database, and the credential it delivers connects", {
  skip, timeout: 900_000,
}, async () => {
  // The PROVIDER: postgres in its committed shape — server and a broker-bound runtime (carrying psql)
  // on the private postgres network, the runtime running the provisioner.
  const postgresManifest = JSON.stringify({
    module: "postgres",
    version: "1",
    provides: [{ name: "postgres-database", scope: "mesh" }],
    serves: { "postgres-database": {} },
    emits: ["module.postgres.database.provisioned", "module.postgres.database.deprovisioned"],
    consumes: ["module.postgres.database.provisioned", "module.postgres.database.deprovisioned"],
    receives: { "postgres-database": "/var/lib/postgres/grants/mesh.json" },
    grants: { "postgres-database": "/var/lib/postgres/grants" },
    "own-secrets": { superuser: "/var/lib/postgres/superuser.secret", broker: "/var/lib/mesh/postgres/broker" },
    resources: [
      { id: "mesh-state", type: "directory", path: "/var/lib/mesh/postgres", mode: "0700" },
      { id: "state", type: "directory", path: "/var/lib/postgres", mode: "0700" },
      { id: "grants", type: "directory", path: "/var/lib/postgres/grants", mode: "0700" },
      { id: "superuser-env", type: "file", path: "/var/lib/postgres/superuser.env", mode: "0600", content: "POSTGRES_PASSWORD=${secret:superuser}\n" },
      { id: "data", type: "directory", path: "/services/postgres/db-data", mode: "0700" },
      { id: "net", type: "network", name: "postgres" },
      {
        // No published port here: the foundation's own store already holds host :5432 on this
        // single-node bed, and the consumer reaches postgres over the private network by name. The
        // committed manifest publishes it for cross-node consumers, which is a different node.
        id: "server", type: "container", name: "postgres", image: pinned("postgres"), network: "postgres",
        env: { POSTGRES_USER: "postgres", POSTGRES_DB: "postgres" },
        "env-file": ["/var/lib/postgres/superuser.env"],
        volumes: ["/services/postgres/db-data:/var/lib/postgresql/data"],
      },
      {
        id: "runtime", type: "container", name: "mesh-postgres", image: pinned("mesh-runtime-postgres"),
        network: "postgres",
        volumes: [
          "/var/lib/mesh/postgres/broker:/run/secrets/broker:ro",
          "/var/lib/postgres/grants:/var/lib/postgres/grants:ro",
          "/var/lib/postgres/superuser.secret:/run/secrets/superuser:ro",
        ],
        env: {
          MESH_BROKER_FILE: "/run/secrets/broker",
          MESH_RECEIVES: "/var/lib/postgres/grants/mesh.json",
          MESH_PROVISION_POSTGRES: "postgres://postgres@postgres:5432/postgres?sslmode=disable",
          MESH_PROVISION_PASSWORD_FILE: "/run/secrets/superuser",
        },
      },
    ],
  });

  // The CONSUMER: a module that requires postgres-database and contributes a name so it asks.
  const consumerManifest = JSON.stringify({
    module: "dbuser",
    version: "1",
    requires: ["postgres-database"],
    contributes: { "postgres-database": { name: "dbuser" } },
    binds: { "postgres-database": "/var/lib/dbuser/db.json" },
    secrets: { "postgres-database": "/var/lib/dbuser/db.secret" },
    resources: [{ id: "state", type: "directory", path: "/var/lib/dbuser", mode: "0700" }],
  });

  await must(`printf %s ${quote(postgresManifest)} > /tmp/postgres.json && docker cp /tmp/postgres.json mesh-controller:/postgres.json`);
  await mesh("module add /postgres.json");
  await mesh(`module issue postgres --node ${MACHINE}`);
  await mesh(`assign ${MACHINE} postgres`);

  await must(`printf %s ${quote(consumerManifest)} > /tmp/dbuser.json && docker cp /tmp/dbuser.json mesh-controller:/dbuser.json`);
  await mesh("module add /dbuser.json");
  await mesh(`assign ${MACHINE} dbuser`);

  await mesh(`push ${MACHINE}`);
  await settled();

  // The mesh delivered the consumer its bound file and its unsealed password.
  let boundRaw = "";
  const untilBound = Date.now() + 60_000;
  while (Date.now() < untilBound) {
    const got = await on(`cat /var/lib/dbuser/db.json 2>/dev/null`);
    if (got.ok && /"as"/.test(got.out)) { boundRaw = got.out; break; }
    await new Promise((r) => setTimeout(r, 3000));
  }
  assert.match(boundRaw, /"as"/, `the consumer was never told about its database:\n${boundRaw}`);
  const bound = JSON.parse(boundRaw) as { as: string; provision: string };
  assert.equal(bound.provision, "postgres-database");
  const as = bound.as;
  const password = (await must(`cat /var/lib/dbuser/db.secret`)).trim();
  assert.ok(as && password, `the consumer's login or password was empty (as=${as})`);

  // THE PROOF: connect to postgres as the consumer, with the login and password the mesh delivered
  // it, to the database postgres's provisioner created — a real password-checked TCP connection (the
  // runtime carries psql). A `1` back means the role, the database, and the password all line up
  // across the two ends. A provisioner that set a different password answers "authentication failed".
  const conn = `postgresql://${as}:${encodeURIComponent(password)}@postgres:5432/${as}?sslmode=disable`;
  let out = { out: "", ok: false };
  const untilConn = Date.now() + 90_000;
  while (Date.now() < untilConn) {
    out = await on(`docker exec mesh-postgres psql ${quote(conn)} -tAc 'select 1' 2>&1`);
    if (out.ok && /^1$/m.test(out.out)) break;
    if (/authentication failed/i.test(out.out)) break; // fast-fail: the credential is wrong
    await new Promise((r) => setTimeout(r, 3000));
  }
  assert.doesNotMatch(out.out, /authentication failed/i,
    `the consumer could not authenticate with the mesh's password — the two ends do not agree:\n${out.out}`);
  assert.match(out.out, /^1$/m,
    `the consumer could not connect to its granted database as ${as}:\n${out.out}\n---\n${(await on(`docker logs mesh-postgres 2>&1 | tail -30`)).out}`);
});