Introduce telemetry for observability

This introduces the foundational telemetry infrastructure to improve
the observability of LDK Server.

It adds a new `/metrics` endpoint exposed on the REST service address,
which serves Prometheus-compatible metrics. This endpoint is public and
does not require HMAC authentication, allowing for easy integration with
monitoring systems.

- Added `prometheus` dependency and a `Metrics` utility struct.
- Introduced a basic `ldk_health_score` gauge (0-100) that
reflects the node's operational status based on connection to peer,
sync state, and running status.

This is the first step in a larger effort to provide comprehensive telemetry.
Future updates will expand this to include metrics for channels, balances,
payments, and other critical node activities.

Author: Anyitechs

Cargo.lock

@@ -26,3 +26,4 @@ pub const LIST_FORWARDED_PAYMENTS_PATH: &str = "ListForwardedPayments";
 pub const UPDATE_CHANNEL_CONFIG_PATH: &str = "UpdateChannelConfig";
 pub const GET_PAYMENT_DETAILS_PATH: &str = "GetPaymentDetails";
 pub const CONNECT_PEER_PATH: &str = "ConnectPeer";
+pub const GET_METRICS_PATH: &str = "metrics";

ldk-server-protos/src/endpoints.rs

@@ -23,6 +23,8 @@ toml = { version = "0.8.9", default-features = false, features = ["parse"] }
 chrono = { version = "0.4", default-features = false, features = ["clock"] }
 log = "0.4.28"
 base64 = { version = "0.21", default-features = false, features = ["std"] }
+lazy_static = "1.5.0"
+prometheus = "0.14.0"
 
 # Required for RabittMQ based EventPublisher. Only enabled for `events-rabbitmq` feature.
 lapin = { version = "2.4.0", features = ["rustls"], default-features = false, optional = true }

ldk-server/Cargo.toml

@@ -131,3 +131,15 @@ impl From<NodeError> for LdkServerError {
 		LdkServerError::new(error_code, message)
 	}
 }
+
+impl From<prometheus::Error> for LdkServerError {
+	fn from(e: prometheus::Error) -> Self {
+		LdkServerError::new(LdkServerErrorCode::InternalServerError, e.to_string())
+	}
+}
+
+impl From<std::string::FromUtf8Error> for LdkServerError {
+	fn from(e: std::string::FromUtf8Error) -> Self {
+		LdkServerError::new(LdkServerErrorCode::InternalServerError, e.to_string())
+	}
+}

ldk-server/src/api/error.rs

@@ -0,0 +1,18 @@
+// This file is Copyright its original authors, visible in version control
+// history.
+//
+// This file is licensed under the Apache License, Version 2.0 <LICENSE-APACHE
+// or http://www.apache.org/licenses/LICENSE-2.0> or the MIT license
+// <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your option.
+// You may not use this file except in accordance with one or both of these
+// licenses.
+
+use crate::api::error::LdkServerError;
+use crate::util::metrics::METRICS;
+
+pub(crate) fn handle_metrics_request() -> Result<String, LdkServerError> {
+	match METRICS.gather_metrics() {
+		Ok(metrics) => Ok(metrics),
+		Err(e) => Err(e),
+	}
+}

ldk-server/src/api/metrics.rs

@@ -26,6 +26,7 @@ pub(crate) mod get_payment_details;
 pub(crate) mod list_channels;
 pub(crate) mod list_forwarded_payments;
 pub(crate) mod list_payments;
+pub(crate) mod metrics;
 pub(crate) mod onchain_receive;
 pub(crate) mod onchain_send;
 pub(crate) mod open_channel;

ldk-server/src/api/mod.rs

@@ -50,6 +50,7 @@ use crate::io::persist::{
 use crate::service::NodeService;
 use crate::util::config::{load_config, ChainSource};
 use crate::util::logger::ServerLogger;
+use crate::util::metrics::{BUILD_METRICS_INTERVAL, METRICS};
 use crate::util::proto_adapter::{forwarded_payment_to_proto, payment_to_proto};
 use crate::util::tls::get_or_generate_tls_config;
 
@@ -291,6 +292,16 @@ fn main() {
 			}
 		};
 		let event_node = Arc::clone(&node);
+
+		let metrics_node = Arc::clone(&node);
+		let mut interval = tokio::time::interval(BUILD_METRICS_INTERVAL);
+		runtime.spawn(async move {
+			loop {
+				interval.tick().await;
+				METRICS.update_service_health_score(&metrics_node);
+			}
+		});
+
 		let rest_svc_listener = TcpListener::bind(config_file.rest_service_addr)
 			.await
 			.expect("Failed to bind listening port");

ldk-server/src/main.rs

@@ -21,9 +21,9 @@ use ldk_node::Node;
 use ldk_server_protos::endpoints::{
 	BOLT11_RECEIVE_PATH, BOLT11_SEND_PATH, BOLT12_RECEIVE_PATH, BOLT12_SEND_PATH,
 	CLOSE_CHANNEL_PATH, CONNECT_PEER_PATH, FORCE_CLOSE_CHANNEL_PATH, GET_BALANCES_PATH,
-	GET_NODE_INFO_PATH, GET_PAYMENT_DETAILS_PATH, LIST_CHANNELS_PATH, LIST_FORWARDED_PAYMENTS_PATH,
-	LIST_PAYMENTS_PATH, ONCHAIN_RECEIVE_PATH, ONCHAIN_SEND_PATH, OPEN_CHANNEL_PATH, SPLICE_IN_PATH,
-	SPLICE_OUT_PATH, UPDATE_CHANNEL_CONFIG_PATH,
+	GET_METRICS_PATH, GET_NODE_INFO_PATH, GET_PAYMENT_DETAILS_PATH, LIST_CHANNELS_PATH,
+	LIST_FORWARDED_PAYMENTS_PATH, LIST_PAYMENTS_PATH, ONCHAIN_RECEIVE_PATH, ONCHAIN_SEND_PATH,
+	OPEN_CHANNEL_PATH, SPLICE_IN_PATH, SPLICE_OUT_PATH, UPDATE_CHANNEL_CONFIG_PATH,
 };
 use prost::Message;
 
@@ -41,6 +41,7 @@ use crate::api::get_payment_details::handle_get_payment_details_request;
 use crate::api::list_channels::handle_list_channels_request;
 use crate::api::list_forwarded_payments::handle_list_forwarded_payments_request;
 use crate::api::list_payments::handle_list_payments_request;
+use crate::api::metrics::handle_metrics_request;
 use crate::api::onchain_receive::handle_onchain_receive_request;
 use crate::api::onchain_send::handle_onchain_send_request;
 use crate::api::open_channel::handle_open_channel;
@@ -148,6 +149,25 @@ impl Service<Request<Incoming>> for NodeService {
 	type Future = Pin<Box<dyn Future<Output = Result<Self::Response, Self::Error>> + Send>>;
 
 	fn call(&self, req: Request<Incoming>) -> Self::Future {
+		// Handle metrics endpoint separately to bypass auth and return plain text
+		if req.uri().path().len() > 1 && &req.uri().path()[1..] == GET_METRICS_PATH {
+			return Box::pin(async move {
+				match handle_metrics_request() {
+					Ok(metrics) => Ok(Response::builder()
+						.header("Content-Type", "text/plain")
+						.body(Full::new(Bytes::from(metrics)))
+						.unwrap()),
+					Err(e) => {
+						let (error_response, status_code) = to_error_response(e);
+						Ok(Response::builder()
+							.status(status_code)
+							.body(Full::new(Bytes::from(error_response.encode_to_vec())))
+							.unwrap())
+					},
+				}
+			});
+		}
+
 		// Extract auth params from headers (validation happens after body is read)
 		let auth_params = match extract_auth_params(&req) {
 			Ok(params) => params,