fix(lnd): retry channel opens during LND startup + calm non-red notice

LND's RPC answers before its p2p server finishes loading, so connect/open
during that window failed red with the raw "server is still in the
process of starting". Now: quiet ~30s retry first; if still starting, a
calm amber "still finishing its startup" notice instead of an error.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
archipelago
2026-07-22 17:31:47 -04:00
co-authored by Claude Fable 5
parent 97464779d4
commit 088b3e255a
2 changed files with 69 additions and 13 deletions
+49 -11
View File
@@ -5,6 +5,21 @@ use tracing::info;
use super::LND_REST_BASE_URL;
/// LND rejects RPCs with "server is still in the process of starting" for a
/// short window after wallet unlock (p2p/graph subsystems still loading).
/// Transient by design — match it so callers retry and, if it persists,
/// surface a calm notice instead of a scary failure. The exact phrase below
/// is what the frontend keys its softer (non-red) styling on.
fn lnd_still_starting(msg: &str) -> bool {
let m = msg.to_ascii_lowercase();
m.contains("in the process of starting") || m.contains("server is still starting")
}
/// User-facing text for the still-starting state. Deliberately calm: this is
/// a "wait a moment", not an error.
const LND_STARTING_MSG: &str = "Your Lightning node is still finishing its startup — this \
usually takes a minute or two after the node comes online. Please try again shortly.";
#[derive(Debug, Serialize)]
struct ChannelInfo {
chan_id: String,
@@ -251,25 +266,45 @@ impl RpcHandler {
"perm": false,
"timeout": "30"
});
let connect_resp = client
.post(format!("{LND_REST_BASE_URL}/v1/peers"))
.header("Grpc-Metadata-macaroon", &macaroon_hex)
.json(&connect_body)
.timeout(std::time::Duration::from_secs(35))
.send()
.await
.context("Failed to connect to peer")?;
// Right after wallet unlock, LND's RPC answers while its p2p
// server is still spinning up, and every connect attempt gets
// "server is still in the process of starting". That's a
// transient state, not a failure — it clears in seconds — so
// retry quietly for ~30s before surfacing a calm, non-scary
// notice (the frontend styles LND_STARTING_MSG as info, not red).
let mut attempt = 0u32;
loop {
let connect_resp = client
.post(format!("{LND_REST_BASE_URL}/v1/peers"))
.header("Grpc-Metadata-macaroon", &macaroon_hex)
.json(&connect_body)
.timeout(std::time::Duration::from_secs(35))
.send()
.await
.context("Failed to connect to peer")?;
if !connect_resp.status().is_success() {
if connect_resp.status().is_success() {
break;
}
let body: serde_json::Value = connect_resp.json().await.unwrap_or_default();
let msg = body
.get("message")
.and_then(|v| v.as_str())
.unwrap_or("Unknown error");
// LND returns an error if we already have this peer — that is fine
if !msg.contains("already connected") {
return Err(anyhow::anyhow!("Failed to connect to peer: {}", msg));
if msg.contains("already connected") {
break;
}
if lnd_still_starting(msg) && attempt < 5 {
attempt += 1;
info!(attempt, "LND still starting — retrying peer connect in 6s");
tokio::time::sleep(std::time::Duration::from_secs(6)).await;
continue;
}
if lnd_still_starting(msg) {
return Err(anyhow::anyhow!("{LND_STARTING_MSG}"));
}
return Err(anyhow::anyhow!("Failed to connect to peer: {}", msg));
}
}
@@ -305,6 +340,9 @@ impl RpcHandler {
.get("message")
.and_then(|v| v.as_str())
.unwrap_or("Unknown error");
if lnd_still_starting(msg) {
return Err(anyhow::anyhow!("{LND_STARTING_MSG}"));
}
return Err(anyhow::anyhow!("Failed to open channel: {}", msg));
}