swarm-queue-based lifecycle notices, replacing push_todo(MANAGER_AGENT)

hive-c0re/src/swarm_queue.rs

@@ -0,0 +1,72 @@
+//! One swarm-queue connection, shared by every consumer in this process.
+//!
+//! [`swarm_status`](crate::swarm_status) and
+//! [`swarm_notices`](crate::swarm_notices) both need the swarm queue, and
+//! both authenticate as the *same* identity (`hive-<name>`, minted for
+//! this hive — see `swarm-authelia.nix`). Two independent `connect()`
+//! calls would be two token mints and two live connections for one
+//! identity, not two different credentials — the same shape that turned
+//! `swarm-controller`'s own connect into the shared `swarm-queue-client`
+//! crate in the first place, one layer up. This module is that same move
+//! made again, this time between two consumers *inside* one process.
+//!
+//! Connects lazily on first use rather than at boot — nothing here
+//! blocks `hive-c0re` starting up on hosts with no queue configured,
+//! which is the ordinary case.
+
+use tokio::sync::OnceCell;
+
+/// Env var prefix for this daemon's swarm-queue credentials — see
+/// [`swarm_queue_client::QueueConfig::from_env`]. All four or none.
+const ENV_PREFIX: &str = "HIVE_C0RE";
+
+static CLIENT: OnceCell<Option<async_nats::Client>> = OnceCell::const_new();
+
+/// The shared swarm-queue client, connecting on first call and memoized
+/// for the rest of the process's life.
+///
+/// `None` covers both "no queue configured" (the ordinary case, logged
+/// once at `info`) and "config present but connecting failed" (bannered
+/// once via [`crate::warnings::set_boot_warning`] the first time this is
+/// called) — either way, a caller with `None` should just skip whatever
+/// it was about to publish. No caller needs to distinguish the two: both
+/// mean "this hive is not offering anything to the swarm right now."
+pub async fn client() -> Option<async_nats::Client> {
+    CLIENT.get_or_init(connect_once).await.clone()
+}
+
+async fn connect_once() -> Option<async_nats::Client> {
+    let cfg = match swarm_queue_client::QueueConfig::from_env(ENV_PREFIX) {
+        Ok(Some(cfg)) => cfg,
+        Ok(None) => {
+            tracing::info!("no swarm queue configured; this hive offers nothing upward");
+            return None;
+        }
+        Err(e) => {
+            // A one-shot startup step with no later retry to clear it —
+            // exactly what `set_boot_warning` is for. `chain`, not
+            // `{:#}`: this is `swarm_queue_client::Error`, whose
+            // `Display` ignores the alternate flag (see `chain`'s own
+            // doc comment), so `{:#}` would drop which env vars are
+            // actually missing.
+            crate::warnings::set_boot_warning(
+                "swarm_queue_config",
+                "warn",
+                format!("swarm queue is off: {}", swarm_queue_client::chain(&e)),
+            );
+            return None;
+        }
+    };
+
+    match swarm_queue_client::connect(cfg).await {
+        Ok(client) => Some(client),
+        Err(e) => {
+            crate::warnings::set_boot_warning(
+                "swarm_queue_config",
+                "warn",
+                format!("swarm queue is off: {}", swarm_queue_client::chain(&e)),
+            );
+            None
+        }
+    }
+}