mesh-lab/test/integration/assigned-schedule-tick.test.ts

/**
 * The mesh assigns schedtest — the thinnest possible carrier of the scheduled-container primitive
 * (novox/hq ADR 0053) — and its scheduled container fires on its cadence WITHOUT the install having
 * run it or gated convergence.
 *
 * schedtest declares one `container` marked `schedule: "* * * * *"` — a bare alpine that appends a
 * timestamp line to /data/runs.log (a mounted data directory) each time the host fires it. It is the
 * recurring twin of the run-once bed (catalogue-mqtt), with the gating rule deliberately reversed.
 * The three claims this bed proves, straight from ADR 0053's "How each claim is checked":
 *
 *   - **Installing it does not run it, and the node is current WITHOUT a run.** Right after the push
 *     converges (settled → the node reports applied+current), the run log is captured as a baseline;
 *     the schedule is state that is present, not a step that gated. Cron "* * * * *" fires at the top
 *     of the next minute, so the baseline is normally empty/absent — but a fire could race the minute
 *     boundary, so the baseline is a line-count, not an assertion of strict zero.
 *   - **It fires on its cadence.** Polled for ~150s, the run log gains at least one line beyond the
 *     baseline — the host's Scheduler fired the container off the clock.
 *   - **It recurs.** Polled ~150s more, the run log gains a SECOND line — it fired again on the next
 *     minute, proving recurrence rather than a one-shot.
 *
 * schedtest neither serves tools nor consumes a provision nor emits/consumes events, and carries no
 * runtime of its own, so it is NOT issued a broker account: `module add` → `assign` → ONE `push` is
 * the whole sequence, with no `module issue` (a serve/consume-less module needs none — `assign`'s own
 * plan resolves without any own-secret). The tick image is a bare alpine served by the scenario's
 * registry by digest; the host pulls and runs it on the cadence.
 *
 *   MESH_LAB_HOST_BINARY=.../mesh-host (feat/apply-schedule — the scheduler that fires the step)
 *   MESH_LAB_BUNDLE=.../examples/substrate-first-node.lock
 *   MESH_LAB_MODULES=.../mesh-control/examples/modules (feat/schedule-container — the parser that
 *   carries `schedule` through). scenarios/schedule-tick.yml stocks alpine:latest (which must be in
 *   the local daemon) and serves it by digest; there is no runtime image — schedtest is a bare tick.
 */

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 = "schedule-tick";
const MACHINE = "anchor";

let instanceId = "";
/** The mesh's own images, as the machines hold them. */
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-control /mesh-control ${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 substrate bundle: ours by the ID the machine holds, everything else upstream. */
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;
}

/**
 * How many lines the tick has written so far — tolerant of the run log not existing yet.
 *
 * The scheduled container appends one line per fire with `date >> /data/runs.log`, and the data
 * directory is mounted from /var/lib/schedtest on the machine, so counting newlines there counts
 * fires. `wc -l` on an absent file is an error, so a missing file reads as 0 rather than throwing —
 * which is exactly the pre-first-fire state.
 */
async function tickLines(): Promise<number> {
  const { out } = await on(`wc -l < /var/lib/schedtest/runs.log 2>/dev/null || echo 0`);
  const n = Number.parseInt(out.trim(), 10);
  return Number.isFinite(n) ? n : 0;
}

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-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;

  // Raise the substrate — store, broker, control — from the bundle.
  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}`);
  }

  // The node joins its own mesh, so it is a node the mesh can assign to, and start the host so it
  // applies what it is pushed AND fires scheduled steps off its clock (the daemon holds one
  // Scheduler for the life of the process — novox/hq ADR 0053).
  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 assigns schedtest: installing the schedule does not run it, and the container fires on its cadence, again and again", {
  skip, timeout: 1_500_000,
}, async () => {
  // A single scheduled container: a bare alpine that appends a timestamp to /data/runs.log each time
  // the host fires it, mounted from /var/lib/schedtest on the machine. `schedule: "* * * * *"` makes
  // it the recurring twin of a run-once step — installed as present state, fired by the clock, never
  // by the apply (ADR 0053). No own-secrets, no broker account: it serves and consumes nothing. The
  // image is pinned to what this scenario serves by digest.
  const manifest = JSON.stringify({
    module: "schedtest",
    version: "1",
    resources: [
      { id: "mesh-state", type: "directory", path: "/var/lib/mesh/schedtest", mode: "0700" },
      { id: "data", type: "directory", path: "/var/lib/schedtest", mode: "0700" },
      {
        id: "tick", type: "container", name: "schedtest-tick",
        image: pinned("alpine"), network: "none",
        schedule: "* * * * *",
        volumes: ["/var/lib/schedtest:/data"],
        args: ["sh", "-c", "date -u +%FT%TZ >> /data/runs.log"],
      },
    ],
  });

  await must(`printf %s ${quote(manifest)} > /tmp/schedtest.json && docker cp /tmp/schedtest.json mesh-control:/schedtest.json`);
  await mesh("module add /schedtest.json");
  // No `module issue`: schedtest serves/consumes nothing and carries no runtime, so it needs no
  // broker account. `assign` resolves its plan (no own-secret to fill) and ONE push converges it.
  await mesh(`assign ${MACHINE} schedtest`);
  await mesh(`push ${MACHINE}`);
  await settled();

  // --- non-gating: the node is current with the schedule installed, WITHOUT a run having gated -----
  // settled() only returns once the node reports applied+current, so reaching here already proves the
  // schedule converged as present state rather than gating on a run (the inversion of run-once). The
  // status is re-read to make that an explicit assertion, and the run log is captured as a baseline:
  // cron "* * * * *" fires at the top of the next minute, so it is normally empty/absent now, but a
  // fire could race the minute boundary — so the baseline is a line-count, not a strict zero.
  const status = JSON.parse(await mesh(`status --json`)) as {
    reported: { node: string; outcome: string; current: boolean }[];
  };
  const word = status.reported.find((r) => r.node === MACHINE);
  assert.ok(word?.outcome === "applied" && word.current,
    `installing the schedule should leave ${MACHINE} current without a run gating it:\n${JSON.stringify(status)}`);
  const baseline = await tickLines();
  console.log(`schedule-tick: baseline run-log lines right after convergence = ${baseline}`);

  // --- fires on cadence: the host's Scheduler runs the container off the clock -----------------------
  // Poll up to ~150s (the tick fires at the top of the next minute; the daemon evaluates its
  // schedules on a minute ticker), asserting the run log gains at least one line beyond the baseline.
  let fired = baseline;
  const untilFired = Date.now() + 150_000;
  while (Date.now() < untilFired) {
    fired = await tickLines();
    if (fired > baseline) break;
    await new Promise((r) => setTimeout(r, 5000));
  }
  assert.ok(fired > baseline,
    `the scheduled container never fired: run-log lines stayed at the baseline ${baseline} for ~150s ` +
      `after convergence.\n---host log---\n${(await on(`tail -60 /var/log/mesh-host.log`)).out}`);

  // --- recurs: it fires AGAIN on the next minute — recurrence, not a one-shot ------------------------
  // Continue polling up to ~150s more for a SECOND line beyond the baseline. One fire could be a
  // run-once by another name; a second fire on the following minute is the proof of cadence.
  let again = fired;
  const untilAgain = Date.now() + 150_000;
  while (Date.now() < untilAgain) {
    again = await tickLines();
    if (again > fired) break;
    await new Promise((r) => setTimeout(r, 5000));
  }
  assert.ok(again > fired,
    `the scheduled container fired once (${fired} lines) but did not recur within ~150s — a schedule ` +
      `must fire again on its next occurrence, not run once.\n` +
      `---host log---\n${(await on(`tail -60 /var/log/mesh-host.log`)).out}`);
  assert.ok(again - baseline >= 2,
    `expected at least two fires beyond the baseline ${baseline}, saw ${again} total lines`);
});