mesh-lab/test/integration/route-forwarding.test.ts

/**
 * The mesh assigns the route-proxy provider and a hello-web consumer, and a request to the
 * consumer's name — sent to the proxy — is forwarded to the workload and returns the workload's own
 * answer. Then the consumer is unassigned and the same request stops working. This is the
 * route-forwarding half of exposure, mesh-driven end to end (novox/hq ADR 0007, 08-connectivity
 * §3), with nothing hand-written.
 *
 * **A route is a grant.** hello-web `requires: route` and contributes `{name, port}`; route-proxy
 * `provides: route`, and the *mesh* writes it the contributions file (`receives.route`) — the test
 * places nothing. The proxy reads that file as $ROUTES and forwards by the `Host` header to
 * `http://<at>:<port>`, where `at` is where the mesh says the consumer is (empty here — co-located —
 * so 127.0.0.1, the published backend port). The two claims this bed proves, straight from
 * 08-connectivity §3's "Checked in the lab":
 *
 *   - a request to the consumer's name reaches the workload across the proxy and returns its answer;
 *   - unassigning the module withdraws the route and the same request stops working — the proxy
 *     replaces its table rather than merging, so a name whose module left is no longer served.
 *
 * route-proxy carries no broker account, no own-secrets and no provisioner: it neither mints a
 * credential nor emits an event, it only reads the file the mesh writes. So `module add` → `assign`
 * → ONE `push` is the whole sequence for each of the two modules, with no `module issue` (as
 * schedule-tick and the run-once bed established for a module that needs no scoped account).
 *
 * This bed proves ROUTE-FORWARDING over plain HTTP. The public-ACME/TLS half — ordering a
 * publicly-trusted certificate and answering an HTTP-01 challenge at the name — is proven separately
 * by certificates.test.ts, which drives the same proxy binary against a real ACME server (Pebble).
 *
 *   MESH_LAB_HOST_BINARY=.../mesh-host   MESH_LAB_BUNDLE=.../examples/foundation-first-node.lock
 *   scripts/build-route-proxy-image.sh builds mesh-route-proxy:development into the local daemon;
 *   scenarios/route-forwarding.yml stocks it and alpine:latest, and serves both by digest.
 */

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 = "route-forwarding";
const MACHINE = "anchor";
const NAME = "hello.example";
const PAGE = "hello from hello-web, routed by the mesh";

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;
}

/** 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 = 600_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}`);
}

/** A request to the proxy carrying the consumer's public name. The proxy binds :80 on the machine's
 *  own network (network: host), so it is reached at 127.0.0.1 from inside the machine. */
async function throughProxy(host: string): Promise<{ out: string; ok: boolean }> {
  return on(`curl -s --max-time 5 -H ${quote(`Host: ${host}`)} http://127.0.0.1/`);
}

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 the host runs 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 routes a public name through the proxy to the consumer, and withdraws it on unassign", {
  skip, timeout: 1_500_000,
}, async () => {
  // The PROVIDER: route-proxy in the plain-HTTP shape — provides `route`, is given every consumer as
  // the file at receives.route, forwards by Host. No TLS here (that is certificates.test.ts); the
  // image is pinned to what this scenario serves by digest.
  const proxyManifest = JSON.stringify({
    module: "route-proxy",
    version: "1",
    capabilities: ["container-runtime"],
    provides: [{ name: "route", scope: "mesh" }],
    serves: { route: {} },
    receives: { route: "/var/lib/route-proxy/routes/mesh.json" },
    listens: [{ port: 80, protocol: "tcp", from: "anywhere", why: "public HTTP; the route-forwarding front door" }],
    resources: [
      { id: "state", type: "directory", path: "/var/lib/route-proxy", mode: "0700" },
      { id: "routes-dir", type: "directory", path: "/var/lib/route-proxy/routes", mode: "0700" },
      {
        id: "server", type: "container", name: "route-proxy",
        image: pinned("mesh-route-proxy"), network: "host",
        volumes: ["/var/lib/route-proxy/routes:/routes:ro"],
        env: { ROUTES: "/routes/mesh.json", LISTEN: ":80" },
      },
    ],
  });

  // The CONSUMER: hello-web requires `route` and contributes the name it wants and the port it
  // listens on. It runs no code of the mesh's — a bare alpine serving a fixed page over a busybox nc
  // loop stands in for a web service. `contributes` is what makes it *ask*: the grant forms from it.
  const webManifest = JSON.stringify({
    module: "hello-web",
    slug: "hello",
    version: "1",
    capabilities: ["container-runtime"],
    requires: ["route"],
    contributes: { route: { name: NAME, port: 8080 } },
    binds: { route: "/var/lib/hello-web/route.json" },
    listens: [{ port: 8080, protocol: "tcp", from: "mesh", why: "the demo page; only the proxy reaches it" }],
    resources: [
      { id: "state", type: "directory", path: "/var/lib/hello-web", mode: "0700" },
      { id: "page", type: "file", path: "/var/lib/hello-web/index.html", mode: "0644", content: `${PAGE}\n` },
      { id: "net", type: "network", name: "hello-web" },
      {
        id: "server", type: "container", name: "hello-web",
        image: pinned("alpine"), network: "hello-web", ports: ["8080:8080"],
        volumes: ["/var/lib/hello-web/index.html:/www/index.html:ro"],
        args: ["sh", "-c",
          "while true; do { printf 'HTTP/1.1 200 OK\\r\\nContent-Type: text/plain\\r\\nConnection: close\\r\\n\\r\\n'; cat /www/index.html; } | nc -l -p 8080; done"],
      },
    ],
  });

  await must(`printf %s ${quote(proxyManifest)} > /tmp/route-proxy.json && docker cp /tmp/route-proxy.json mesh-controller:/route-proxy.json`);
  await mesh("module add /route-proxy.json");
  // No `module issue`: route-proxy has no broker account and no own-secret to mint. `assign` resolves
  // its plan and the provider is matchable by a consumer's route from that alone.
  await mesh(`assign ${MACHINE} route-proxy`);

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

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

  // The mesh matched the two and wrote route-proxy its contributions file — the test wrote nothing.
  const routes = await must(`cat /var/lib/route-proxy/routes/mesh.json`);
  assert.match(routes, new RegExp(NAME.replace(/\./g, "\\.")),
    `the mesh did not write route-proxy the route for ${NAME}:\n${routes}`);
  assert.match(routes, /"port": *8080/, `the route did not carry the consumer's port:\n${routes}`);

  // --- THE PROOF: a request to the name, sent to the proxy, returns the workload's own answer ------
  // The proxy polls its routes file every couple of seconds and the backend takes a moment to bind,
  // so this is retried. It is the exact shape of 08-connectivity §3's lab check.
  let served = { out: "", ok: false };
  const untilServed = Date.now() + 120_000;
  while (Date.now() < untilServed) {
    served = await throughProxy(NAME);
    if (served.ok && served.out.includes(PAGE)) break;
    await new Promise((r) => setTimeout(r, 3000));
  }
  assert.ok(served.out.includes(PAGE),
    `the name ${NAME} was never routed to the workload:\n${served.out}\n` +
      `---routes---\n${routes}\n` +
      `---proxy log---\n${(await on(`docker logs route-proxy 2>&1 | tail -20`)).out}\n` +
      `---host log---\n${(await on(`tail -40 /var/log/mesh-host.log`)).out}`);

  // --- a name the proxy does not serve is refused by name, not with a bare 404 --------------------
  const unknown = await throughProxy("nobody-asked-for-this.example");
  assert.doesNotMatch(unknown.out, new RegExp(PAGE),
    `an unrouted name reached the workload:\n${unknown.out}`);
  assert.match(unknown.out, /no route for/,
    `the proxy did not name what it serves for an unknown host:\n${unknown.out}`);

  // --- WITHDRAWAL: unassigning the consumer removes the route, and the same request stops working --
  // The file the proxy is given is the whole truth about who has a route, so the proxy replaces its
  // table rather than merging — a name whose module left is no longer served (08-connectivity §3).
  await mesh(`unassign ${MACHINE} hello-web`);
  await mesh(`push ${MACHINE}`);
  await settled();

  let gone = { out: "", ok: false };
  const untilGone = Date.now() + 60_000;
  while (Date.now() < untilGone) {
    gone = await throughProxy(NAME);
    if (!gone.out.includes(PAGE)) break;
    await new Promise((r) => setTimeout(r, 3000));
  }
  assert.doesNotMatch(gone.out, new RegExp(PAGE),
    `the route outlived the module that asked for it — withdrawal did not take:\n${gone.out}\n` +
      `---routes---\n${(await on(`cat /var/lib/route-proxy/routes/mesh.json`)).out}`);
  assert.match(gone.out, /no route for/,
    `after withdrawal the proxy did not report ${NAME} as unserved:\n${gone.out}`);
});