From 83844a528365e657cd5f4d2cda51d72ced9900da Mon Sep 17 00:00:00 2001
From: DanConwayDev <DanConwayDev@protonmail.com>
Date: Thu, 11 Dec 2025 12:36:51 +0000
Subject: fix: wire up relay disconnection detection for metrics

- Add periodic health check in RelayConnection::run_event_loop that polls
  nostr-sdk's relay.is_connected() every second to detect dead connections
- When event channel closes without explicit Closed/Shutdown, send
  DisconnectNotification to SyncManager (fixes case where TCP drops silently)
- Enable test_relay_connected_status test which validates the
  ngit_sync_relay_connected metric correctly reflects connection state

The issue was that when a remote relay stops abruptly, nostr-sdk's
notification receiver blocks indefinitely waiting for data. TCP disconnect
detection without keepalive can take minutes. The health check polls
nostr-sdk's internal relay status which detects disconnection promptly.
---
 src/sync/mod.rs | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

(limited to 'src/sync/mod.rs')

diff --git a/src/sync/mod.rs b/src/sync/mod.rs
index c62b478..15c89e3 100644
--- a/src/sync/mod.rs
+++ b/src/sync/mod.rs
@@ -1251,6 +1251,9 @@ impl SyncManager {
         let metrics_clone = self.metrics.clone(); // Clone metrics for the spawned task
         let is_bootstrap_clone = is_bootstrap; // Clone is_bootstrap for the spawned task
         tokio::spawn(async move {
+            // Track whether we've already sent a disconnect notification
+            let mut disconnect_sent = false;
+            
             while let Some(relay_event) = event_rx.recv().await {
                 match relay_event {
                     RelayEvent::Event(event) => {
@@ -1297,6 +1300,7 @@ impl SyncManager {
                                 relay_url: relay_url_clone.clone(),
                             })
                             .await;
+                        disconnect_sent = true;
                         break;
                     }
                     RelayEvent::Shutdown => {
@@ -1307,10 +1311,25 @@ impl SyncManager {
                                 relay_url: relay_url_clone.clone(),
                             })
                             .await;
+                        disconnect_sent = true;
                         break;
                     }
                 }
             }
+            
+            // If the event channel closed without a Closed/Shutdown event
+            // (e.g., connection dropped unexpectedly), still notify SyncManager
+            if !disconnect_sent {
+                tracing::info!(
+                    relay = %relay_url_clone,
+                    "Event channel closed, notifying SyncManager of disconnect"
+                );
+                let _ = disconnect_tx
+                    .send(DisconnectNotification {
+                        relay_url: relay_url_clone.clone(),
+                    })
+                    .await;
+            }
         });
 
         tracing::info!(
-- 
cgit v1.2.3