mesh-lab/test/integration/local-model-bed.test.ts

/**
 * The mesh proves model-access answered by a NODE, end to end (novox/hq ADR 0055). Where the Anthropic
 * and OpenAI beds answer model-access with a licence (a vendor), this answers it with the mesh's OWN
 * model: an Ollama server on the node `provides: ["model-access"]` at node scope and serves its
 * endpoint, and a consumer requiring model-access is handed that endpoint — base URL + model — with no
 * licence and no key.
 *
 *   the ollama provider is assigned (provides model-access at node scope, serves { port, model }) ->
 *   the local-model consumer requires model-access and is answered by the local node (the resolver
 *   prefers a local model over a licence) -> the mesh fills the consumer's bound facts with ollama's
 *   at/port/model -> the consumer's templated openai.env carries OPENAI_BASE_URL=http://<at>:<port>/v1.
 *
 * The property proven: the consumer is delivered a reachable local endpoint through the same
 * model-access provision it would use for a vendor — no adapter, no credential, no licence. The bed
 * asserts the templated URL and that a request to it reaches the running server (ollama answers
 * /v1/models even with no model pulled — the wiring is what is proven, not a model's output).
 *
 *   MESH_LAB_HOST_BINARY=.../mesh-host   MESH_LAB_BUNDLE=.../examples/foundation-first-node.lock
 *   No module runtime image is built — both modules are pure declaration.
 */

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, 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 = "local-model-bed";
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);
}

async function meshTry(command: string): Promise<{ out: string; ok: boolean }> {
  return on(`docker exec mesh-controller /mesh-controller ${command}`);
}

/** 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 = 600_000): Promise<void> {
  const until = Date.now() + withinMs;
  let last = "";
  while (Date.now() < until) {
    const asked = await meshTry(`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}`);
}

async function addAssign(name: string, manifest: string): Promise<void> {
  await must(`printf %s ${quote(manifest)} > /tmp/${name}.json && docker cp /tmp/${name}.json mesh-controller:/${name}.json`);
  await mesh(`module add /${name}.json`);
  await mesh(`module issue ${name} --node ${MACHINE}`);
  await mesh(`assign ${MACHINE} ${name}`);
}

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("a node hosting a model answers model-access, and the consumer is handed its endpoint", {
  skip, timeout: 1_500_000,
}, async () => {
  // Both manifests are the catalogue's own (novox/hq 04-ISSUES/073). The provider: ollama runs the
  // model server and `provides: ["model-access"]` at node scope, serving its port and model. It mints
  // nothing — provides/serves are declaration the mesh reads, so there is no runtime container, only
  // the server. The consumer requires model-access and is answered by the local node: no secret (the
  // local server is keyless), only the bound endpoint facts, templated into an openai.env the mesh writes.
  const ollamaManifest = catalogueModule("ollama", held);
  const consumerManifest = catalogueModule("local-model-consumer", held);

  await addAssign("ollama", ollamaManifest);
  await addAssign("local-model-consumer", consumerManifest);
  await mesh(`push ${MACHINE}`);
  await settled();

  // The ollama server is running, and the consumer's endpoint file was written from its served facts.
  const up = await must(`docker ps --format '{{.Names}}'`);
  assert.match(up, /(^|\n)ollama(\n|$)/, `the ollama server is not running:\n${up}`);

  // Wait for the templated endpoint file, then read the base URL the mesh filled in.
  let env = "";
  for (let i = 0; i < 20; i++) {
    const got = await on(`cat /var/lib/local-model-consumer/config/openai.env`);
    if (got.ok && got.out.includes("OPENAI_BASE_URL=http")) { env = got.out; break; }
    await new Promise((r) => setTimeout(r, 3000));
  }
  assert.match(env, /OPENAI_BASE_URL=http:\/\/[^\s:]+:\d+\/v1/, `the base URL was not templated from the served endpoint:\n${env}`);
  assert.match(env, /OPENAI_MODEL=llama3\.2/, `the served model fact did not reach the consumer:\n${env}`);

  const baseUrl = (env.match(/OPENAI_BASE_URL=(\S+)/) ?? [])[1] ?? "";
  assert.ok(baseUrl, `no OPENAI_BASE_URL in:\n${env}`);

  // The endpoint the consumer was handed is reachable — a request to the local model server's
  // OpenAI-compatible API succeeds (ollama answers /v1/models even with no model pulled). This is the
  // wiring proven: the mesh routed the consumer to the model the mesh runs itself.
  let reached = "";
  for (let i = 0; i < 20; i++) {
    const got = await on(`curl -sS -m 5 ${quote(`${baseUrl}/models`)}`);
    if (got.ok && (got.out.includes("\"data\"") || got.out.includes("\"object\""))) { reached = got.out; break; }
    await new Promise((r) => setTimeout(r, 3000));
  }
  assert.ok(reached, `the consumer's endpoint ${baseUrl}/models was never reachable`);
});