mesh-lab/test/integration/assigned-ca-trust.test.ts

/**
 * A machine trusts the mesh's own authority because a module put its root there — and stops when
 * the module is taken away (novox/hq ADR 0147, 04-ISSUES/129).
 *
 * What is dialled is the authority itself. step-ca serves its own API with a leaf it issued, so a
 * plain client verifying that handshake — no `-k`, no `--cacert` — is verifying exactly one thing:
 * that this machine's trust store now contains the mesh's root. No proxy, no routed name, no public
 * issuance. A trust bed leaning on those would pass for their reasons, which is the failure this
 * whole sequence keeps producing.
 *
 * The negative half runs twice, before the module is assigned and after it is unassigned. An anchor
 * bed that only checks the success would pass on a machine that already trusted everything, and
 * would say nothing at all about removal — which is the half issue 129 asked for by name.
 *
 *   MESH_LAB_HOST_BINARY=.../mesh-host
 *   MESH_LAB_BUNDLE=.../examples/foundation-first-node-nats.lock
 *   MESH_LAB_CATALOG=.../mesh-catalog/modules
 *   step-ca's image is upstream, pinned by the catalogue, pulled by the machine over its uplink.
 *   ca-trust carries no image: a script, a unit, and the machine's own systemd.
 */

import { test, before, after } from "node:test";
import assert from "node:assert/strict";
import { existsSync } 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, 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 = "trust-anchor";
const MACHINE = "anchor";
/** The authority's own API, which it serves with a certificate it issued itself. */
const AUTHORITY = "https://127.0.0.1:9000/health";
/** Where the module puts the root, and therefore what removal must take away. */
const ANCHOR = "/etc/ca-certificates/trust-source/anchors/mesh-internal-ca.crt";

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);
}

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}`);
}

/** Install a catalogue module's manifest into the control plane, read from the catalogue. */
async function register(module: string): Promise<void> {
  const manifest = catalogueModule(module, held);
  await must(
    `printf %s ${quote(manifest)} > /tmp/${module}.json && ` +
      `docker cp /tmp/${module}.json mesh-controller:/${module}.json`,
  );
  await mesh(`module add /${module}.json`);
}

/**
 * Put the mesh's composed user list where this machine's bus reads it, and make it re-read.
 *
 * **What genesis has to do by hand, and only genesis** (novox/hq 04-ISSUES/146). Every account on
 * the bus reaches it in the declaration of the machine that runs it — which requires that machine
 * to be an enrolled node, and at genesis it is not. So until the bus is a module, the composition
 * is placed by whoever is raising the machine: the control plane says what it composed, and this
 * writes it beside the bus's configuration. Twice, because two accounts come into existence at
 * different moments — the enrolment when the token is issued, and the node's own when it enrols.
 */
async function composeTheBusUsers(): Promise<void> {
  await must(
    `docker exec mesh-controller /mesh-controller broker accounts > /var/lib/mesh-bus-conf/accounts.conf && ` +
      `docker kill -s HUP mesh-broker`,
  );
}

/** Dial the authority the way anything on this machine would: verifying, with nothing handed to it. */
async function verifying(): Promise<{ out: string; ok: boolean }> {
  return on(`curl --silent --show-error --max-time 10 ${AUTHORITY}`);
}

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${foundationBundle(bundle, raised.images)}\nMESHBUNDLE`);
  await must(`${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 control plane is a container, and a container that is restarting answers nothing. Asked
  // until it answers rather than once, so a crash-looping control plane is reported as itself
  // instead of as whatever command happened to be sent first.
  let control = { out: "", ok: false };
  const answering = Date.now() + 120_000;
  while (Date.now() < answering) {
    control = await on(`docker exec mesh-controller /mesh-controller status`);
    if (control.ok) break;
    await new Promise((r) => setTimeout(r, 3000));
  }
  assert.ok(control.ok,
    `the control plane never answered:\n${control.out}\n` +
      `${(await on(`docker logs mesh-controller 2>&1 | tail -40`)).out}`);

  await mesh(`node add ${MACHINE}`);
  const token = tokenFrom(await mesh(`token issue --node ${MACHINE}`));
  // The account that token is the password of exists in the mesh's records now; this is what puts
  // it on the bus, because nothing else can until this machine is a node.
  await composeTheBusUsers();
  await must(`${HOST_PATH} enrol --token ${quote(token)}`);
  // And again for the credential enrolment just minted, which the machine's own link connects with.
  await composeTheBusUsers();
  await must(`nohup ${HOST_PATH} run > /var/log/mesh-host.log 2>&1 & sleep 3`);
}, { timeout: 1_800_000 });

after(async () => {
  if (process.env["MESH_LAB_KEEP"]) {
    console.log(`MESH_LAB_KEEP set — leaving ${instanceId} standing`);
    return;
  }
  if (instanceId) await destroy(instanceId);
  await destroyAll(`${SCENARIO}-`);
}, { timeout: 600_000 });

test("the mesh's authority is verified on a machine holding ca-trust, and not on one that is not", {
  skip, timeout: 1_800_000,
}, async () => {
  // The private network first. The authority certifies itself for the address it holds there
  // (`${machine:at}`), which a machine with no overlay has not got — so this is what the bed needs
  // it for, and nothing else.
  await mesh(`overlay place ${MACHINE} --hub --endpoint 192.0.2.10:51820 --site lab`);
  // The control plane ships this one — its resources are computed per node, so there is no
  // manifest to register.
  await mesh(`assign ${MACHINE} networking`);
  await mesh(`push ${MACHINE}`);
  await settled();

  // The authority next, on its own. Nothing about trust yet.
  await register("step-ca");
  // No `module issue`: that delivers a bus account, and the authority declares none — its own
  // secret is the password it initialises itself with, which the mesh mints at assignment.
  await mesh(`assign ${MACHINE} step-ca`);
  await mesh(`push ${MACHINE}`);
  await settled();

  // It is up and answering — asked the way nothing else in this bed is allowed to ask, with
  // verification off, because at this point in the bed no machine could verify it.
  let answering = false;
  const until = Date.now() + 180_000;
  while (Date.now() < until && !answering) {
    answering = (await on(`curl --silent --insecure --max-time 5 ${AUTHORITY}`)).ok;
    if (!answering) await new Promise((r) => setTimeout(r, 3000));
  }
  assert.ok(answering, `the authority never answered:\n${(await on(`docker logs step-ca 2>&1 | tail -30`)).out}`);

  // **The negative half, before anything is assigned.** If this passes, the bed is measuring
  // something already in the machine's trust store and everything below it is worthless.
  const before = await verifying();
  assert.equal(before.ok, false, `the authority verified before anything anchored its root:\n${before.out}`);
  assert.match(before.out, /certificate|issuer/i, `it failed for some other reason:\n${before.out}`);

  // Now the module.
  await register("ca-trust");
  await mesh(`assign ${MACHINE} ca-trust`);
  await mesh(`push ${MACHINE}`);
  await settled();

  const unit = await on(`systemctl is-active mesh-ca-trust.service`);
  assert.ok(unit.ok, `the unit is ${unit.out.trim()}:\n${(await on(`journalctl -u mesh-ca-trust --no-pager | tail -30`)).out}`);
  await must(`test -s ${ANCHOR}`);
  const anchors = await must(`trust list | grep -A2 -i 'Mesh Internal CA' || trust list`);
  assert.match(anchors, /Mesh Internal CA/, `the mesh's authority is not among the machine's anchors:\n${anchors}`);

  // **The whole claim, in one command.** No -k, no --cacert: the machine's own trust store, and a
  // certificate the mesh's authority issued.
  const after = await verifying();
  assert.ok(after.ok, `the authority still does not verify with the module assigned:\n${after.out}`);

  // **And removal is the same unit's business.** Unassigned, the host stops it; stopping it takes
  // the anchor away and refreshes the bundles, so the machine stops trusting the mesh.
  await mesh(`unassign ${MACHINE} ca-trust`);
  await mesh(`push ${MACHINE}`);
  await settled();

  const gone = await on(`test -e ${ANCHOR}`);
  assert.equal(gone.ok, false, "the anchor is still on the machine after the module was unassigned");
  const afterwards = await verifying();
  assert.equal(afterwards.ok, false, `the machine still verifies the mesh's authority with nothing anchoring it:\n${afterwards.out}`);
  assert.match(afterwards.out, /certificate|issuer/i, `it failed for some other reason:\n${afterwards.out}`);
});