feat(lnd): channel-peer watchdog — a dropped peer link heals itself

LND normally reconnects channel peers after a restart, but not reliably:
after long or repeated downtime (an app update, a node reboot,
reconciler churn) the peer link can stay down for hours while BOTH
endpoints keep the channel flagged disabled in the routing graph. The
node looks perfectly healthy, the wallet shows balance, and every
payment in either direction fails "no route to the recipient" —
observed live on framework-pt (2026-09-01): its only channel sat
disabled on both policy sides for ~17 hours after the LND 0.21.2
update, while shorty had 583k spendable and the user was told, by a
mis-mapped modal, that they had 'no payment channel'.

The channel graph is desired state — every open channel should have a
live peer connection. A daemon-side watchdog now enforces it:

- every 2 minutes, list channels + peers over LND REST
- for each channel whose remote peer is not connected, look the peer's
  advertised addresses up in the public graph and dial one
- per-peer retries throttled to 10 minutes so an unreachable peer is
  not hammered; 'already connected' counts as done; a peer with no
  advertised address is logged once per pass (cannot be dialed)
- no-ops quietly on nodes without LND (missing macaroon) and while a
  wallet is locked (503 body has no channels)

Unit tests pin the selection against the live REST shapes
(remote_pubkey in /v1/channels vs pub_key in /v1/peers).

v1.8.10 CHANGELOG + What's New entries staged so the next release run
is clean first time.

core/archipelago/src/container/lnd.rs

@@ -131,6 +131,10 @@ const LND_STATE_DIRS: &[&str] = &[
 /// container, not a Quadlet unit, so it is restarted via `podman`, not systemctl.
 const LND_CONTAINER: &str = "lnd";
 
+/// Canonical on-host admin macaroon — same path the RPC layer reads.
+const LND_ADMIN_MACAROON: &str =
+    "/var/lib/archipelago/lnd/data/chain/bitcoin/mainnet/admin.macaroon";
+
 /// Archipelago data dir (default; not overridden in prod). Holds the
 /// `user-stopped.json` that gates health-monitor auto-restart.
 const ARCHY_DATA_DIR: &str = "/var/lib/archipelago";
@@ -872,6 +876,188 @@ fn cert_sha256_thumbprint(pem: &str) -> Result<String> {
     Ok(hex::encode_upper(Sha256::digest(&der)))
 }
 
+// ── Channel-peer watchdog ──────────────────────────────────────────────────
+
+/// Every open channel's remote peer that is NOT currently connected.
+/// Pure over LND's REST JSON so the selection can be unit-tested.
+///
+/// `/v1/peers` uses `pub_key`; `/v1/channels` uses `remote_pubkey` — the
+/// asymmetry is LND's, not ours.
+fn select_reconnect_targets(
+    channels: &serde_json::Value,
+    peers: &serde_json::Value,
+) -> Vec<String> {
+    let connected: std::collections::HashSet<&str> = peers
+        .get("peers")
+        .and_then(|p| p.as_array())
+        .map(|arr| {
+            arr.iter()
+                .filter_map(|p| p.get("pub_key").and_then(|v| v.as_str()))
+                .collect()
+        })
+        .unwrap_or_default();
+    let mut targets: Vec<String> = channels
+        .get("channels")
+        .and_then(|c| c.as_array())
+        .map(|arr| {
+            arr.iter()
+                .filter_map(|c| c.get("remote_pubkey").and_then(|v| v.as_str()))
+                .filter(|pk| !connected.contains(pk))
+                .map(str::to_string)
+                .collect()
+        })
+        .unwrap_or_default();
+    targets.sort();
+    targets.dedup();
+    targets
+}
+
+/// Reconnect peers of open channels that LND has not re-established on its
+/// own. Returns the number of peers reconnected this pass.
+///
+/// LND normally reconnects channel peers after a restart — but not reliably:
+/// when the restart outages are long or repeated (an app update, a node
+/// reboot, reconciler churn), the peer link can stay down for hours while
+/// BOTH endpoints keep flagging the channel `disabled` in the routing
+/// graph. The node itself looks perfectly healthy and every payment in
+/// either direction fails "no route to the recipient" — observed live on
+/// framework-pt (2026-09-01): its only channel sat disabled on both policy
+/// sides for ~17h after the LND 0.21.2 update, while the wallet showed
+/// plenty of outbound. The channel graph is desired state; this keeps it.
+///
+/// Quietly returns Ok(0) when LND is not installed or its wallet is locked —
+/// that is every node without LND, on every pass.
+///
+/// `last_attempt` throttles retries per peer (`min_retry`) so an unreachable
+/// peer is not hammered every pass; the caller owns the map so the pass
+/// itself stays stateless and testable.
+pub(crate) async fn reconnect_disconnected_channel_peers(
+    last_attempt: &mut std::collections::HashMap<String, std::time::Instant>,
+    min_retry: std::time::Duration,
+) -> Result<usize> {
+    let Ok(macaroon) = read_file_as_root(LND_ADMIN_MACAROON).await else {
+        return Ok(0); // LND not installed (or not initialized yet)
+    };
+    let macaroon_hex = hex::encode(macaroon);
+    let client = reqwest::Client::builder()
+        .no_proxy()
+        .timeout(std::time::Duration::from_secs(8))
+        .danger_accept_invalid_certs(true)
+        .build()
+        .context("building LND REST client for the channel-peer watchdog")?;
+
+    let channels: serde_json::Value = client
+        .get(format!("{LND_REST_BASE_URL}/v1/channels"))
+        .header("Grpc-Metadata-macaroon", &macaroon_hex)
+        .send()
+        .await
+        .context("LND REST: listing channels for the peer watchdog")?
+        .json()
+        .await
+        .context("parsing LND channel list")?;
+    // A locked wallet answers 503 with an error body — it parses as JSON
+    // with no "channels" key, which selects nothing. That is a quiet pass.
+    let peers: serde_json::Value = client
+        .get(format!("{LND_REST_BASE_URL}/v1/peers"))
+        .header("Grpc-Metadata-macaroon", &macaroon_hex)
+        .send()
+        .await
+        .context("LND REST: listing peers for the peer watchdog")?
+        .json()
+        .await
+        .context("parsing LND peer list")?;
+
+    let mut reconnected = 0usize;
+    for pubkey in select_reconnect_targets(&channels, &peers) {
+        if last_attempt
+            .get(&pubkey)
+            .is_some_and(|t| t.elapsed() < min_retry)
+        {
+            continue;
+        }
+        last_attempt.insert(pubkey.clone(), std::time::Instant::now());
+
+        // Where does the peer live? Its advertised addresses in the public
+        // graph. A peer with none (fully private) cannot be dialed from here
+        // — LND itself may still find it; we only log the gap once per pass.
+        // Unknown to the public graph (or the graph query failed) — nothing
+        // to dial on.
+        let Ok(node) = client
+            .get(format!("{LND_REST_BASE_URL}/v1/graph/node/{pubkey}"))
+            .header("Grpc-Metadata-macaroon", &macaroon_hex)
+            .send()
+            .await
+            .and_then(|r| r.error_for_status())
+        else {
+            continue;
+        };
+        let Ok(node) = node.json::<serde_json::Value>().await else {
+            continue;
+        };
+        let addresses: Vec<String> = node
+            .get("node")
+            .and_then(|n| n.get("addresses"))
+            .and_then(|a| a.as_array())
+            .map(|arr| {
+                arr.iter()
+                    .filter_map(|a| a.get("addr").and_then(|v| v.as_str()))
+                    .map(str::to_string)
+                    .collect()
+            })
+            .unwrap_or_default();
+        if addresses.is_empty() {
+            tracing::warn!(
+                peer = %pubkey,
+                "LND channel peer is disconnected and advertises no address — cannot dial it; payments through this channel stay unroutable"
+            );
+            continue;
+        }
+
+        for addr in addresses {
+            let Some((host, port)) = addr.rsplit_once(':') else {
+                continue;
+            };
+            let Ok(port) = port.parse::<u32>() else {
+                continue;
+            };
+            let body = serde_json::json!({
+                "perm": false,
+                "timeout": "15s",
+                "addr": { "pubkey": pubkey, "host": host, "port": port },
+            });
+            match client
+                .post(format!("{LND_REST_BASE_URL}/v1/peers"))
+                .header("Grpc-Metadata-macaroon", &macaroon_hex)
+                .json(&body)
+                .send()
+                .await
+            {
+                Ok(resp) if resp.status().is_success() => {
+                    reconnected += 1;
+                    tracing::info!(
+                        peer = %pubkey,
+                        addr = %addr,
+                        "reconnected a disconnected channel peer (channel was unroutable)"
+                    );
+                    break;
+                }
+                Ok(resp) => {
+                    let msg = resp.text().await.unwrap_or_default();
+                    // Already connected between our list call and now — success.
+                    if msg.contains("already connected") {
+                        break;
+                    }
+                    tracing::debug!(peer = %pubkey, addr = %addr, %msg, "channel-peer connect attempt failed");
+                }
+                Err(e) => {
+                    tracing::debug!(peer = %pubkey, addr = %addr, error = %e, "channel-peer connect attempt failed");
+                }
+            }
+        }
+    }
+    Ok(reconnected)
+}
+
 #[cfg(test)]
 mod tests {
     use super::*;
@@ -985,4 +1171,35 @@ mod tests {
         let cands = unlock_password_candidates().await;
         assert!(cands.iter().any(|p| p == LEGACY_WALLET_PASSWORD));
     }
+
+    #[test]
+    fn reconnect_targets_pick_disconnected_channel_peers_only() {
+        // Shape captured from a live node: /v1/channels uses remote_pubkey,
+        // /v1/peers uses pub_key, and an offline channel's peer is simply
+        // absent from the peer list — that absence is the whole signal.
+        let channels = serde_json::json!({
+            "channels": [
+                { "remote_pubkey": "AAA", "active": true },
+                { "remote_pubkey": "BBB", "active": false },
+                { "remote_pubkey": "AAA" }
+            ]
+        });
+        let peers = serde_json::json!({ "peers": [ { "pub_key": "AAA" } ] });
+
+        let targets = select_reconnect_targets(&channels, &peers);
+        assert_eq!(targets, vec!["BBB".to_string()]);
+    }
+
+    #[test]
+    fn reconnect_targets_empty_without_channels_or_peers() {
+        // No LND wallet (503 error body), locked wallet, or an empty node:
+        // selects nothing, quietly.
+        let error_body = serde_json::json!({ "message": "locked" });
+        assert!(select_reconnect_targets(&error_body, &serde_json::json!({})).is_empty());
+        assert!(select_reconnect_targets(
+            &serde_json::json!({ "channels": [] }),
+            &serde_json::json!({ "peers": [] })
+        )
+        .is_empty());
+    }
 }

core/archipelago/src/server.rs

@@ -841,6 +841,37 @@ impl Server {
             });
         }
 
+        // LND channel-peer watchdog — every 2 minutes, reconnect the peers
+        // of open channels that LND has not re-established on its own. LND's
+        // reconnect logic gives up with a long backoff after repeated or
+        // extended downtime (an app update, a reboot, reconciler churn), and
+        // while the peer link is down BOTH endpoints keep the channel flagged
+        // `disabled` in the routing graph — payments fail "no route" in both
+        // directions while the node itself looks perfectly healthy. The
+        // channel graph is desired state; this keeps it (framework-pt,
+        // 2026-09-01: only channel unroutable ~17h after the 0.21.2 update).
+        // No-ops quietly on nodes without LND. Per-peer retries are throttled
+        // to 10 minutes so an unreachable peer is not hammered every pass.
+        {
+            tokio::spawn(async move {
+                let mut interval = tokio::time::interval(Duration::from_secs(120));
+                let mut last_attempt: HashMap<String, Instant> = HashMap::new();
+                loop {
+                    interval.tick().await;
+                    match crate::container::lnd::reconnect_disconnected_channel_peers(
+                        &mut last_attempt,
+                        Duration::from_secs(600),
+                    )
+                    .await
+                    {
+                        Ok(0) => {}
+                        Ok(n) => info!(n, "LND channel-peer watchdog reconnected channel peers"),
+                        Err(e) => debug!("LND channel-peer watchdog (non-fatal): {}", e),
+                    }
+                }
+            });
+        }
+
         // FIPS seed-anchor apply loop — every 5 minutes we re-push the
         // configured seed anchors into the running fips daemon via
         // `fipsctl connect`. This keeps the mesh bootstrap resilient: