test/integration/fresh-mesh.test.ts

@@ -162,6 +162,29 @@ async function mesh(command: string, timeoutMs?: number): Promise<string> {
   return must(CONTROL, `docker exec mesh-control /mesh-control ${command}`, timeoutMs);
 }
 
+/**
+ * Wait for one container, BY NAME, to be running.
+ *
+ * **Named exactly, because substring matching passed a step that had failed.** Waiting for "a
+ * container whose name contains lavinmq" was satisfied by the broker — `lavinmq`, up and healthy —
+ * while the thing actually under test, the module's own runtime `mesh-lavinmq`, was crash-looping
+ * beside it. The step went green and the fault was found by reading `docker ps` by hand.
+ */
+async function waitForContainer(node: string, container: string, seconds = 200): Promise<string> {
+  const deadline = Date.now() + seconds * 1_000;
+  let last = "";
+  while (Date.now() < deadline) {
+    const ps = (await on(node, `docker ps -a --format '{{.Names}}\t{{.Status}}'`)).out;
+    last = ps;
+    const line = ps.split("\n").find((l) => l.split("\t")[0]?.trim() === container);
+    if (line && /^Up /.test(line.split("\t")[1]?.trim() ?? "")) return ps;
+    await new Promise((r) => setTimeout(r, 5_000));
+  }
+  const logs = (await on(node, `docker logs --tail 15 ${container} 2>&1`)).out;
+  throw new Error(
+    `${container} is not running on ${node}.\n\ncontainers:\n${last}\n\nwhat it said:\n${logs}`);
+}
+
 /**
  * Register a module from a manifest on this workstation.
  *
@@ -346,15 +369,15 @@ before(async () => {
       1_500_000);
     assert.doesNotMatch(built, /failed/i, built);
     await mesh(`assign ${CONTROL} ${PROVIDER.module}`);
+    // **Its account on the mesh's own broker, and not swallowed.** A module's runtime is a tool
+    // host: it connects to the mesh broker before it does anything, and what it reads is a sealed
+    // credential document. Without an account the mesh still fills the secret this module declares
+    // it owns — with a generated value — so the container starts, fails to parse a password as a
+    // credential, and crash-loops on a JSON syntax error that says nothing about the missing
+    // account. Issuing it is not optional and neither is hearing that it failed.
+    await mesh(`module issue ${PROVIDER.module} --node ${CONTROL}`);
     await mesh(`push ${CONTROL}`, 600_000);
-    for (let i = 0; i < 60; i++) {
-      const ps = (await on(CONTROL, `docker ps --format '{{.Names}}\t{{.Status}}'`)).out;
-      const line = ps.split("\n").find((l) => l.includes(PROVIDER.module));
-      if (line && /Up /.test(line)) return ps;
-      await new Promise((r) => setTimeout(r, 5_000));
-    }
-    throw new Error(`${PROVIDER.module} never came up on ${CONTROL}:\n` +
-      (await on(CONTROL, `docker ps -a --format '{{.Names}}\t{{.Status}}'`)).out);
+    return waitForContainer(CONTROL, "mesh-lavinmq");
   });
 
   // ---- 5. THE ANCHOR RUNS IT ------------------------------------------------------------------
@@ -362,18 +385,10 @@ before(async () => {
   // The machine that built it. This is the case every earlier proof covered, and it is here as the
   // control for step 6: if this fails, step 6's failure says nothing about fetching.
   await step("the anchor runs the module the mesh built", NEEDS, async () => {
-    await mesh(`module issue ${MODULE.module} --node ${CONTROL}`).catch(() => {});
+    await mesh(`module issue ${MODULE.module} --node ${CONTROL}`);
     await mesh(`assign ${CONTROL} ${MODULE.module}`);
     await mesh(`push ${CONTROL}`, 600_000);
-    for (let i = 0; i < 40; i++) {
-      const ps = (await on(CONTROL, `docker ps --format '{{.Names}}\t{{.Status}}'`)).out;
-      if (/amqp-ping/.test(ps) && /Up /.test(ps.split("\n").find((l) => l.includes("amqp-ping")) ?? "")) {
-        return ps;
-      }
-      await new Promise((r) => setTimeout(r, 5_000));
-    }
-    throw new Error(`amqp-ping never came up on ${CONTROL}:\n` +
-      (await on(CONTROL, `docker ps -a --format '{{.Names}}\t{{.Status}}'`)).out);
+    return waitForContainer(CONTROL, MODULE.module);
   });
 
   // ---- 6. AND A MACHINE THAT DID NOT BUILD IT -------------------------------------------------
@@ -387,20 +402,15 @@ before(async () => {
   // evidence of what does work.
   await step(`a joined machine runs the module the mesh built`,
     "the anchor runs the module the mesh built", async () => {
-    await mesh(`module issue ${MODULE.module} --node ${SECOND}`).catch(() => {});
+    await mesh(`module issue ${MODULE.module} --node ${SECOND}`);
     await mesh(`assign ${SECOND} ${MODULE.module}`);
     await mesh(`push ${SECOND}`, 600_000);
-    for (let i = 0; i < 40; i++) {
-      const ps = (await on(SECOND, `docker ps --format '{{.Names}}\t{{.Status}}'`)).out;
-      const line = ps.split("\n").find((l) => l.includes("amqp-ping"));
-      if (line && /Up /.test(line)) return ps;
-      await new Promise((r) => setTimeout(r, 5_000));
+    try {
+      return await waitForContainer(SECOND, MODULE.module);
+    } catch (err) {
+      const log = (await on(SECOND, `tail -40 /var/log/mesh-host.log`)).out;
+      throw new Error(`${(err as Error).message}\n\nwhat the host said:\n${log}`);
     }
-    const state = (await on(SECOND, `docker ps -a --format '{{.Names}}\t{{.Status}}'`)).out;
-    const log = (await on(SECOND, `tail -40 /var/log/mesh-host.log`)).out;
-    throw new Error(
-      `amqp-ping never came up on ${SECOND} — the machine that did NOT build it.\n\n` +
-      `containers:\n${state}\n\nwhat the host said:\n${log}`);
   });
 
   console.log(`\n================ WHAT THIS MESH DID FOR ITSELF ================`);