Merge pull request 'Serve mode waits for its broker instead of crash-looping (issue 058)' (#10) from fix/the-runtime-waits-for-its-broker into main

src/main.ts

@@ -66,13 +66,37 @@ async function connectBroker(): Promise<Broker> {
   return connectAmqp(url);
 }
 
+/**
+ * Connect for serve mode, retrying while the broker is merely not reachable yet. At startup that
+ * is the NORMAL case, not a failure: a container comes up in seconds and the overlay tunnel a
+ * moment later (novox/hq issue 058). Exiting instead delegated the retry to the container
+ * runtime, which read as a crash-loop to every restart-counting health check and every person
+ * watching. Retried indefinitely, aloud: the dependency appears or somebody reads why not.
+ *
+ * Only reachability retries. A pinned-certificate mismatch is a refusal, not a wait — an
+ * impostor does not become the broker by being asked again — and configuration errors already
+ * exit inside connectBroker before anything is thrown here.
+ */
+async function connectBrokerPatiently(): Promise<Broker> {
+  for (let delay = 2_000; ; delay = Math.min(delay * 2, 30_000)) {
+    try {
+      return await connectBroker();
+    } catch (err) {
+      const why = err instanceof Error ? err.message : String(err);
+      if (why.includes("does not match the pinned")) throw err;
+      console.error(`mesh-tools: the broker is not reachable yet (${why}); retrying in ${delay / 1000}s`);
+      await new Promise((r) => setTimeout(r, delay));
+    }
+  }
+}
+
 async function serve(): Promise<void> {
   const moduleEntrypoints = (process.env.MESH_TOOL_MODULES ?? "")
     .split(",")
     .map((s) => s.trim())
     .filter(Boolean);
 
-  const broker = await connectBroker();
+  const broker = await connectBrokerPatiently();
   const stop = await runTools({ broker, moduleEntrypoints });
 
   const shutdown = async (): Promise<void> => {