mesh-lab/test/integration/whole-mesh-full.test.ts

/**
 * The FULL mesh: both server sets on ONE substrate, converging together — the final stage of the
 * whole-mesh rehearsal (novox/hq). Combines whole-mesh-novox.test.ts and whole-mesh-ace.test.ts.
 *
 *   anchor — substrate ONLY (store, broker, control).
 *   novox  — the 18-module novox set (whole-mesh-novox): providers, web apps, route-proxy, mailu,
 *            firewall, fail2ban. fail2ban is now HOSTABLE: the dry-run fixes (mesh-control/catalog
 *            main) changed its declared capability from the never-detected "intrusion-prevention" to
 *            "firewall", the detector every node with nft already advertises.
 *   ace    — the 24-module ace set (whole-mesh-ace): the media/home stack; its /services/media
 *            library is pre-created so the ADR-0051 `accesses` resolve.
 *
 * An overlay is placed across all three so cross-node `at` resolves. Each service node is
 * self-contained (its own postgres/redis), so nothing crosses a node boundary except enrolment and
 * the shared broker/store on anchor. The four modules both nodes run (postgres, redis, mssql,
 * portainer) are ADDED once and assigned to each node; each gets its own per-node broker account.
 *
 * THE DRY-RUN FIXES THIS RUN PROVES (mesh-control + mesh-catalog main):
 *   - fail2ban is HOSTABLE (capability "firewall"): it is assigned, not refused. Before, it declared
 *     the never-detected "intrusion-prevention" capability, so no node could host it and its
 *     un-hostable assignment refused the whole node's push. Hostability is the gate. Its service
 *     reaching active is a host concern this offline lab cannot meet — the VM ships nftables (so the
 *     firewall detector is advertised) but not fail2ban, and the isolated segment has no route to the
 *     package mirror, so pacman cannot fetch it. That is a documented lab gap, reported not gated.
 *   - the 7 tool-runtime credential modules (ace: plex, bazarr, ombi, home-assistant, nzbget,
 *     qbittorrent; novox: umami) now read their app credential from an operator-provided own-secret.
 *     This bed delivers a FAKE value for each through the real operator path (`secret accept`)
 *     BEFORE the push, and gates on the sidecar getting PAST its old "no credential" crash (it reads
 *     the delivered value). A fake value will not authenticate against the real app — the sidecar may
 *     still fail at app-auth, which is expected and does NOT gate; only the crash being GONE gates.
 *
 * It otherwise tolerates the SAME known gaps the per-server beds proved and escalated (the credential
 * sidecars' app-auth failures, photos/mailu, and firewall's oneshot nftables.service); it gates green
 * on each node's CORE converging whole and on no NON-GAP resource failing to apply — i.e. the two
 * node-plans converge together on one substrate.
 *
 *   MESH_LAB_HOST_BINARY=.../mesh-host   MESH_LAB_BUNDLE=.../examples/substrate-first-node.lock
 */

import { test, before, after } from "node:test";
import assert from "node:assert/strict";
import { existsSync, readFileSync } from "node:fs";
import { dirname, resolve } from "node:path";
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 } from "./harness.ts";

const capability = await labIsUsable();
const binary = hostBinaryPath();
const bundle = process.env["MESH_LAB_BUNDLE"] ?? "";
const modulesEnv = process.env["MESH_LAB_MODULES"] ?? "";

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 = "whole-mesh-full";

const catalogDir = process.env["MESH_LAB_CATALOG"]
  ?? (modulesEnv ? resolve(dirname(dirname(dirname(modulesEnv))), "mesh-catalog", "modules") : "")
  ?? resolve(process.cwd(), "..", "mesh-catalog", "modules");

const MEDIA_DIRS = [
  "/services/media/series", "/services/media/anime", "/services/media/movies",
  "/services/media/music", "/services/media/audiobooks", "/services/media/downloads",
  "/services/media/books",
];

type Mod = { name: string; containers: string[]; node?: boolean; runOnce?: string[] };

/** The novox node's 17-module set (fail2ban dropped). CORE gates; the rest are documented gaps. */
const NOVOX: Mod[] = [
  { name: "postgres", containers: ["postgres", "mesh-postgres"] },
  { name: "redis", containers: ["redis", "mesh-redis"] },
  { name: "minio", containers: ["minio", "mesh-minio"] },
  { name: "mongodb", containers: ["mongo", "mesh-mongodb"] },
  { name: "mssql", containers: ["mssql", "mesh-mssql"] },
  { name: "keycloak", containers: ["keycloak", "mesh-keycloak"] },
  { name: "gitea", containers: ["gitea", "mesh-gitea"] },
  { name: "nextcloud", containers: ["nextcloud", "mesh-nextcloud"] },
  { name: "umami", containers: ["umami", "mesh-umami"] },
  { name: "photos", containers: ["photos", "mesh-photos"] },
  { name: "invoicing", containers: ["invoicing-app", "invoicing-api"] },
  { name: "portainer", containers: ["portainer", "mesh-portainer"] },
  { name: "verdaccio", containers: ["verdaccio", "mesh-verdaccio"] },
  { name: "registry", containers: ["mesh-registry"] },
  { name: "route-proxy", containers: ["route-proxy"] },
  {
    name: "mailu",
    containers: [
      "mailu-resolver", "mailu-redis", "mailu-admindb", "mailu-admin", "mailu-imap",
      "mailu-smtp", "mailu-antispam", "mailu-webmail", "mailu-front", "mesh-mailu",
    ],
  },
  { name: "firewall", containers: [], node: true },
  { name: "fail2ban", containers: [], node: true },
];
const CORE_NOVOX = new Set([
  "postgres", "redis", "minio", "mongodb", "mssql",
  "keycloak", "gitea", "nextcloud", "invoicing",
  "portainer", "verdaccio", "registry", "route-proxy",
]);
const GAPS_NOVOX = new Set(["umami", "photos", "mailu", "firewall", "fail2ban"]);

/** The ace node's 24-module set. */
const ACE: Mod[] = [
  { name: "postgres", containers: ["postgres", "mesh-postgres"] },
  { name: "redis", containers: ["redis", "mesh-redis"] },
  { name: "mssql", containers: ["mssql", "mesh-mssql"] },
  { name: "sonarr", containers: ["sonarr", "mesh-sonarr"] },
  { name: "radarr", containers: ["radarr", "mesh-radarr"] },
  { name: "lidarr", containers: ["lidarr", "mesh-lidarr"] },
  { name: "plex", containers: ["plex", "mesh-plex"] },
  { name: "bazarr", containers: ["bazarr", "mesh-bazarr"] },
  { name: "nzbget", containers: ["nzbget", "mesh-nzbget"] },
  { name: "qbittorrent", containers: ["qbittorrent", "mesh-qbittorrent"] },
  { name: "jackett", containers: ["jackett", "mesh-jackett"] },
  { name: "ombi", containers: ["ombi", "mesh-ombi"] },
  { name: "tautulli", containers: ["tautulli", "mesh-tautulli"] },
  { name: "bookshelf", containers: ["bookshelf", "mesh-bookshelf"] },
  { name: "home-assistant", containers: ["home-assistant", "mesh-home-assistant"] },
  { name: "mosquitto", containers: ["mosquitto", "mesh-mosquitto"], runOnce: ["mosquitto-bootstrap"] },
  { name: "influxdb", containers: ["influxdb", "mesh-influxdb"] },
  { name: "grafana", containers: ["grafana", "mesh-grafana"] },
  { name: "baserow", containers: ["baserow", "mesh-baserow"] },
  { name: "letta", containers: ["letta", "mesh-letta"] },
  { name: "nodered", containers: ["nodered", "mesh-nodered"] },
  { name: "searxng", containers: ["valkey", "searxng", "mesh-searxng"] },
  { name: "unifi", containers: ["unifi-controller", "mesh-unifi"] },
  { name: "portainer", containers: ["portainer", "mesh-portainer"] },
];
const CORE_ACE = new Set([
  "postgres", "redis", "mssql",
  "sonarr", "radarr", "lidarr", "jackett", "tautulli", "bookshelf",
  "mosquitto", "influxdb", "grafana", "baserow", "nodered", "searxng", "unifi", "portainer",
]);
const GAPS_ACE = new Set(["plex", "bazarr", "nzbget", "qbittorrent", "ombi", "home-assistant", "letta"]);

const PLAN: { node: string; mods: Mod[]; core: Set<string>; gaps: Set<string> }[] = [
  { node: "novox", mods: NOVOX, core: CORE_NOVOX, gaps: GAPS_NOVOX },
  { node: "ace", mods: ACE, core: CORE_ACE, gaps: GAPS_ACE },
];

/**
 * Host-port remaps (per module — host ports are per-VM, so novox's and ace's never clash). Union of
 * both per-server beds' remaps.
 */
const REMAP: Record<string, Record<string, string>> = {
  nextcloud: { "80": "8090:80" },
  umami: { "3000": "3090:3000" },
  invoicing: { "80": "8091:80", "9000": "9091:9000" },
  qbittorrent: { "8080": "8090:8080" },
  searxng: { "8080": "8092:8080" },
  nzbget: { "6789": "6790:6789" },
};

/**
 * The 7 tool-runtime credential modules (novox/hq dry-run fix). Each now reads its app credential
 * from an operator-provided own-secret (`name`, an own-secret path in its module.json), mounted into
 * the sidecar at MESH_*_FILE. This bed delivers a FAKE value for each via the real operator path
 * (`secret accept <node> <module> <name> --from <file>`) BEFORE the push, and asserts the sidecar
 * gets PAST `crash` — the exact message its client threw when nothing was mounted. A fake value does
 * not authenticate against the real app, so the sidecar may still fail later at app-auth (expected,
 * not gated); only the "no credential" crash being GONE proves the wiring and gates.
 */
const CREDENTIALS: { node: string; module: string; name: string; crash: string }[] = [
  { node: "ace", module: "plex", name: "token", crash: "no Plex token" },
  { node: "ace", module: "bazarr", name: "api-key", crash: "no Bazarr API key" },
  { node: "ace", module: "ombi", name: "api-key", crash: "no Ombi API key" },
  { node: "ace", module: "home-assistant", name: "token", crash: "no Home Assistant token" },
  { node: "ace", module: "nzbget", name: "password", crash: "NZBGet not configured" },
  { node: "ace", module: "qbittorrent", name: "password", crash: "qBittorrent not configured" },
  { node: "novox", module: "umami", name: "admin", crash: "admin password is not set" },
];

let instanceId = "";
let stocked: string[] = [];

function quote(s: string): string {
  return `'${s.replaceAll("'", `'\\''`)}'`;
}

async function on(machine: string, 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(machine: string, command: string, timeoutMs?: number): Promise<string> {
  const { out, ok } = await on(machine, command, timeoutMs);
  if (!ok) throw new Error(`${machine}: ${command}\n${out}`);
  return out;
}

async function mesh(command: string, timeoutMs?: number): Promise<string> {
  return must("anchor", `docker exec mesh-control /mesh-control ${command}`, timeoutMs);
}

function repositoryFor(reference: string): string {
  const withoutDigest = reference.split("@")[0] ?? reference;
  const lastColon = withoutDigest.lastIndexOf(":");
  const lastSlash = withoutDigest.lastIndexOf("/");
  return lastColon > lastSlash ? withoutDigest.slice(0, lastColon) : withoutDigest;
}

function pinned(repository: string): string {
  const found = stocked.find((r) => r.slice(r.indexOf("/") + 1, r.indexOf("@")) === repository);
  assert.ok(found, `the scenario stocks no ${repository}; it serves\n  ${stocked.join("\n  ")}`);
  return found;
}

function bundleFor(images: string[]): string {
  let text = readFileSync(bundle, "utf8");
  for (const ref of images) {
    const repository = ref.slice(ref.indexOf("/") + 1, ref.indexOf("@"));
    const escaped = repository.replaceAll("/", "\\/").replaceAll(".", "\\.");
    text = text.replaceAll(new RegExp(`[A-Za-z0-9_.:-]+\\/${escaped}@sha256:[0-9a-f]+`, "g"), ref);
  }
  return text;
}

function loadManifest(name: string): { manifest: string; broker: boolean } {
  const path = resolve(catalogDir, name, "module.json");
  const m = JSON.parse(readFileSync(path, "utf8")) as {
    resources?: { type: string; image?: string; ports?: string[] }[];
  };
  const remap = REMAP[name] ?? {};
  for (const r of m.resources ?? []) {
    if (r.type !== "container") continue;
    if (typeof r.image === "string") r.image = pinned(repositoryFor(r.image));
    if (Array.isArray(r.ports)) r.ports = r.ports.map((p) => remap[p] ?? p);
  }
  const manifest = JSON.stringify(m);
  return { manifest, broker: manifest.includes("MESH_BROKER_FILE") };
}

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;
}

interface NodeState {
  reached: boolean;
  applied: boolean;
  current: boolean;
  waiting: boolean;
  wrong?: { outcome: string; refused?: string | undefined; failed?: { id: string; error: string }[] | undefined } | undefined;
  raw: string;
}

async function nodeState(node: string): Promise<NodeState> {
  const asked = await on("anchor", `docker exec mesh-control /mesh-control status --json`);
  if (!asked.ok) return { reached: false, applied: false, current: false, waiting: false, raw: asked.out };
  let state: {
    wrong: { node: string; outcome: string; refused?: string; failed?: { id: string; error: string }[] }[];
    waiting: { node: string }[];
    reported: { node: string; outcome: string; current: boolean }[];
  };
  try {
    state = JSON.parse(asked.out);
  } catch {
    return { reached: false, applied: false, current: false, waiting: false, raw: asked.out };
  }
  const word = state.reported.find((r) => r.node === node);
  const bad = state.wrong.find((w) => w.node === node);
  return {
    reached: true,
    applied: word?.outcome === "applied",
    current: !!word?.current,
    waiting: state.waiting.some((w) => w.node === node),
    wrong: bad ? { outcome: bad.outcome, refused: bad.refused, failed: bad.failed } : undefined,
    raw: asked.out,
  };
}

async function psMapOf(node: string): Promise<Map<string, string>> {
  const out = (await on(node, `docker ps -a --format '{{.Names}}\t{{.Status}}'`)).out;
  const map = new Map<string, string>();
  for (const line of out.split("\n")) {
    const [n, ...rest] = line.split("\t");
    if (n) map.set(n.trim(), rest.join("\t").trim());
  }
  return map;
}

before(async () => {
  if (skip) return;
  assert.ok(existsSync(catalogDir), `mesh-catalog modules not found at ${catalogDir}`);

  const raised = await raise(loadScenario(`scenarios/${SCENARIO}.yml`), {
    onProgress: (m) => console.log(`raise: ${m}`),
  });
  instanceId = raised.instanceId;
  stocked = raised.images;

  await must("anchor", `cat > /tmp/substrate.lock <<'MESHBUNDLE'\n${bundleFor(raised.images)}\nMESHBUNDLE`);
  await must("anchor", `${HOST_PATH} apply /tmp/substrate.lock`, 900_000);
  const up = await must("anchor", `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}`);
  }

  for (const machine of ["anchor", "novox", "ace"]) {
    await mesh(`node add ${machine}`);
    const token = tokenFrom(await mesh(`token issue --node ${machine}`));
    const said = await must(machine, `${HOST_PATH} enrol --token ${quote(token)}`);
    assert.match(said, new RegExp(`enrolled as ${machine}`), said);
    await must(machine, `nohup ${HOST_PATH} run > /var/log/mesh-host.log 2>&1 & sleep 3`);
  }

  // The operator provides ace's media library (ADR 0051 accesses confirm the paths, create nothing).
  await must("ace", `mkdir -p ${MEDIA_DIRS.join(" ")}`);
}, { timeout: 3_000_000 });

after(async () => {
  if (instanceId) await destroy(instanceId);
  await destroyAll(`${SCENARIO}-`);
}, { timeout: 900_000 });

test("both server sets converge together on one substrate", { skip, timeout: 3_600_000 }, async () => {
  // Overlay across all three, so every node's private address exists and cross-node `at` resolves.
  await mesh("overlay place anchor --hub --endpoint 192.0.2.10:51820 --site lab");
  await mesh("overlay place novox --site lab");
  await mesh("overlay place ace --site lab");
  await mesh("assign anchor networking");
  await mesh("assign novox networking");
  await mesh("assign ace networking");

  // Add every unique module ONCE (the four shared modules are added once, assigned to each node), then
  // issue a per-node broker account and assign, resiliently.
  const added = new Map<string, boolean>(); // name -> needs broker
  async function ensureAdded(name: string): Promise<boolean> {
    const known = added.get(name);
    if (known !== undefined) return known;
    const { manifest, broker } = loadManifest(name);
    await must("anchor", `printf %s ${quote(manifest)} > /tmp/${name}.json && docker cp /tmp/${name}.json mesh-control:/${name}.json`);
    await mesh(`module add /${name}.json`);
    added.set(name, broker);
    return broker;
  }

  const assigned: Record<string, Set<string>> = { novox: new Set(), ace: new Set() };
  const refused: Record<string, { name: string; why: string }[]> = { novox: [], ace: [] };
  for (const { node, mods } of PLAN) {
    for (const { name } of mods) {
      try {
        const broker = await ensureAdded(name);
        if (broker) await mesh(`module issue ${name} --node ${node}`);
        await mesh(`assign ${node} ${name}`);
        assigned[node]!.add(name);
      } catch (err) {
        const why = (err as Error).message.split("\n").map((l) => l.trim()).filter(Boolean).slice(1, 5).join(" | ");
        refused[node]!.push({ name, why });
        console.log(`NOT ASSIGNED ${node}/${name}: ${why}`);
      }
    }
  }

  // Operator-provided app credentials (novox/hq dry-run fix). BEFORE the push, hand the mesh a FAKE
  // value for each of the 7 credential modules through the real operator path — `secret accept`,
  // which seals the value to the node and records it as `accepted` (the mesh will not invent one).
  // The push then delivers it to the sidecar's own-secret path. The `--from` file is staged into the
  // mesh-control container (one file per distinct secret name). A module the node could not host is
  // skipped (its secret has nowhere to go).
  const credentialDelivered = new Map<string, boolean>();
  for (const name of new Set(CREDENTIALS.map((c) => c.name))) {
    await must("anchor", `printf %s ${quote(`fake-${name}-value`)} > /tmp/fake-${name} && docker cp /tmp/fake-${name} mesh-control:/fake-${name}`);
  }
  for (const c of CREDENTIALS) {
    if (!assigned[c.node]!.has(c.module)) {
      credentialDelivered.set(`${c.node}/${c.module}`, false);
      console.log(`CREDENTIAL SKIPPED ${c.node}/${c.module}: not assigned, nowhere to deliver`);
      continue;
    }
    try {
      await mesh(`secret accept ${c.node} ${c.module} ${c.name} --from /fake-${c.name}`);
      credentialDelivered.set(`${c.node}/${c.module}`, true);
    } catch (err) {
      credentialDelivered.set(`${c.node}/${c.module}`, false);
      console.log(`CREDENTIAL ACCEPT FAILED ${c.node}/${c.module}: ${(err as Error).message.split("\n").slice(0, 3).join(" | ")}`);
    }
  }

  // ONE push per node.
  const pushError: Record<string, string> = { novox: "", ace: "" };
  for (const node of ["novox", "ace"]) {
    try {
      await mesh(`push ${node}`, 240_000);
    } catch (err) {
      pushError[node] = (err as Error).message;
      console.log(`PUSH REJECTED (${node}):\n${pushError[node]}`);
    }
  }

  // Wait for both nodes' CORE containers to come up (they pull concurrently from the one registry).
  const psMaps: Record<string, Map<string, string>> = { novox: new Map(), ace: new Map() };
  for (const { node, mods, core } of PLAN) {
    if (pushError[node]) continue;
    const coreContainers = mods.filter((m) => core.has(m.name) && assigned[node]!.has(m.name)).flatMap((m) => m.containers);
    const until = Date.now() + 2_700_000;
    while (Date.now() < until) {
      psMaps[node] = await psMapOf(node);
      if (coreContainers.every((c) => (psMaps[node]!.get(c) ?? "").startsWith("Up"))) break;
      await new Promise((r) => setTimeout(r, 10000));
    }
  }
  await new Promise((r) => setTimeout(r, 20000)); // let first-boot bounces settle

  // ================================================================================================
  // Per-node report + gating. GREEN = each node's push accepted, every CORE module converged whole,
  // no NON-GAP resource failed to apply, fail2ban is hostable (assigned, not refused), and every
  // credential sidecar advanced past its "no credential" crash. Tolerated: the credential sidecars'
  // app-auth failures (bogus fake value), photos/mailu, firewall's oneshot nftables.service, and
  // fail2ban's package (the offline lab cannot fetch it — a documented host gap).
  // ================================================================================================
  const users = (await on("anchor", `docker exec mesh-broker lavinmqctl list_users 2>&1`)).out;
  const allProblems: string[] = [];
  const report: string[] = ["================ FULL MESH CONVERGENCE ================"];

  for (const { node, mods, core, gaps } of PLAN) {
    const psMap = psMaps[node] = await psMapOf(node);
    const st = await nodeState(node);
    const running = (name: string): boolean => (psMap.get(name) ?? "").startsWith("Up");
    const ranOnce = (name: string): boolean => !psMap.has(name) || /^(Up|Exited \(0\))/.test(psMap.get(name) ?? "");
    const failedResources = st.wrong?.failed ?? [];

    report.push(`\n---- node ${node}: reached=${st.reached} applied=${st.applied} current=${st.current} waiting=${st.waiting} ----`);
    if (pushError[node]) report.push(`  PUSH REJECTED: ${pushError[node].split("\n").slice(0, 6).join("\n    ")}`);
    if (st.wrong) {
      report.push(`  NODE WRONG: outcome=${st.wrong.outcome}`);
      for (const f of failedResources) report.push(`    failed ${f.id}: ${f.error}`);
    }
    for (const r of refused[node]!) report.push(`  REFUSED ${r.name}: ${r.why}`);

    const coreFailures: string[] = [];
    for (const mod of mods) {
      if (!assigned[node]!.has(mod.name)) continue;
      const states = mod.containers.map((c) => `${c}:${running(c) ? "UP" : (psMap.get(c) ?? "MISSING")}`);
      const ok = mod.containers.every(running) && (mod.runOnce ?? []).every(ranOnce);
      const tag = core.has(mod.name) ? (ok ? "OK  " : "FAIL") : (ok ? "ok  " : "GAP ");
      report.push(`  ${core.has(mod.name) ? "*" : " "} ${mod.name.padEnd(15)} ${tag} ${states.join("  ")}`);
      if (core.has(mod.name) && !ok) coreFailures.push(mod.name);
    }
    const issuedHere = mods.filter((m) => new RegExp(`${node}-${m.name}\\b`).test(users)).length;
    report.push(`  broker accounts: ${issuedHere} present for ${node}`);

    // Gate: push accepted, all CORE up, no NON-GAP resource failed. A failed resource names its
    // owning module inside the error (`applying "firewall.load": …`), not in `id` (which is the outer
    // "apply" key), so the owner is extracted from either — and a failure owned by a KNOWN_GAP module
    // (firewall's oneshot nftables.service) is tolerated.
    const gapOwnerOf = (f: { id: string; error: string }): string => {
      const m = f.error.match(/applying "([^".]+)\./);
      return m?.[1] ?? (f.id.split(".")[0] ?? "");
    };
    if (pushError[node]) allProblems.push(`${node}: push rejected`);
    if (coreFailures.length) allProblems.push(`${node}: CORE not converged: ${coreFailures.join(", ")}`);
    const nonGapFailed = failedResources.filter((f) => !gaps.has(gapOwnerOf(f)));
    if (nonGapFailed.length) allProblems.push(`${node}: non-gap resource failed: ${nonGapFailed.map((f) => `${f.id} (${f.error.slice(0, 60)})`).join(", ")}`);
  }

  // ================================================================================================
  // The dry-run fixes, proved by name.
  // ================================================================================================

  // fail2ban is now HOSTABLE (capability "firewall"): what the dry-run fix buys is that a node can
  // host it at all. Before, it declared the never-detected "intrusion-prevention" capability, so NO
  // node could host it AND its un-hostable assignment refused the whole node's push. So the GATE is
  // hostability: it must be ASSIGNED and NOT refused.
  //
  // Its systemd service reaching active is a SEPARATE, host-level concern this offline lab cannot
  // satisfy: the VM base image ships `nftables` (so firewall's package resolves and the `firewall`
  // detector is advertised — which is exactly why fail2ban is now hostable) but NOT `fail2ban`, and
  // the lab segment (RFC 5737 192.0.2.0/24) has no route to the package mirror, so pacman times out
  // fetching fail2ban and its deps. That is a documented LAB gap (fail2ban ∈ GAPS_NOVOX, so its
  // failed `fail2ban.package` resource is tolerated like firewall's oneshot nftables.service) — it is
  // reported, not gated. On an online node the package installs and the service runs.
  {
    const refusedF2B = refused["novox"]!.find((r) => r.name === "fail2ban");
    const assignedF2B = assigned["novox"]!.has("fail2ban");
    const active = (await on("novox", `systemctl is-active fail2ban 2>&1`)).out.trim();
    const pkg = (await on("novox", `pacman -Q fail2ban 2>&1`)).out.trim();
    report.push(`\n---- fail2ban (novox): HOSTABLE assigned=${assignedF2B} refused=${refusedF2B ? "YES" : "no"} | service=${active} package="${pkg}" ----`);
    if (refusedF2B) {
      allProblems.push(`fail2ban still not hostable on novox: ${refusedF2B.why}`);
    } else if (!assignedF2B) {
      allProblems.push(`fail2ban was not assigned to novox`);
    }
    if (active !== "active") {
      report.push(`  service not active — offline lab could not install the package (documented gap, not gated); detail:`);
      report.push(`  ${(await on("novox", `systemctl status fail2ban --no-pager 2>&1 | head -8`)).out}`);
    }
  }

  // The 7 credential sidecars: each got its fake own-secret, so each must have advanced PAST the old
  // "no credential" crash (it read the delivered value). It may still fail at app-auth against the
  // real app with a bogus value — that is expected and does NOT gate; only the crash being gone does.
  report.push(`\n---- credential sidecars: past the "no credential" crash? (fake secret delivered) ----`);
  for (const c of CREDENTIALS) {
    const container = `mesh-${c.module}`;
    const psMap = psMaps[c.node]!;
    const status = (psMap.get(container) ?? "MISSING").split(" ")[0] ?? "MISSING";
    const delivered = credentialDelivered.get(`${c.node}/${c.module}`) ?? false;
    const logs = (await on(c.node, `docker logs ${container} 2>&1 | tail -60`)).out;
    const stillCrashes = logs.includes(c.crash);
    const appAuth = logs.split("\n").reverse().find((l) => /fail|reject|error|401|403|refused/i.test(l) && !l.includes(c.crash))?.trim().slice(0, 90) ?? "";
    report.push(`  ${c.node}/${c.module.padEnd(15)} secret=${delivered ? "delivered" : "SKIPPED"} sidecar=${status.padEnd(10)} crash("${c.crash}")=${stillCrashes ? "STILL PRESENT" : "gone"}${appAuth ? `  last:"${appAuth}"` : ""}`);
    if (delivered && stillCrashes) {
      allProblems.push(`${c.node}/${c.module}: credential wiring did not take — sidecar still crashes "${c.crash}"`);
    }
    if (!delivered && assigned[c.node]!.has(c.module)) {
      allProblems.push(`${c.node}/${c.module}: fake credential was not delivered (secret accept failed)`);
    }
  }

  const summary = report.join("\n");
  console.log(summary);

  // Cross-node identity proof: each node's own scoped broker accounts exist and are distinct — the
  // two node-plans share one broker without colliding (both run a `postgres`, `redis`, `mssql`).
  for (const acct of ["novox-postgres", "ace-postgres", "novox-redis", "ace-redis"]) {
    if (!new RegExp(acct).test(users)) allProblems.push(`missing broker account ${acct}`);
  }

  // Diagnostics for any CORE failure (the gaps are expected; a CORE failure is what we must see).
  for (const { node, mods, core } of PLAN) {
    const psMap = psMaps[node]!;
    for (const mod of mods) {
      if (!core.has(mod.name) || !assigned[node]!.has(mod.name)) continue;
      for (const c of mod.containers) {
        if (psMap.has(c) && !(psMap.get(c) ?? "").startsWith("Up")) {
          console.log(`\n---- ${node} logs: ${c} (${psMap.get(c)}) ----\n${(await on(node, `docker logs ${c} 2>&1 | tail -25`)).out}`);
        }
      }
    }
  }

  assert.deepEqual(allProblems, [], `the full mesh did not converge together:\n  ${allProblems.join("\n  ")}\n\n${summary}`);
});