v4.4.0

changelog.md

@@ -1,5 +1,39 @@
 # Changelog
 
+## 2026-03-03 - 4.4.0 - feat(remoteingress)
+add heartbeat PING/PONG and liveness timeouts; implement fast-reconnect/backoff reset and JS crash-recovery auto-restart
+
+- protocol: add FRAME_PING and FRAME_PONG and unit tests for ping/pong frames
+- edge (Rust): reset backoff after successful connection, respond to PING with PONG, track liveness via deadline and reconnect on timeout, use Duration/Instant helpers
+- hub (Rust): send periodic PING to edges, handle PONGs, enforce liveness timeout and disconnect inactive edges, use tokio interval and time utilities
+- ts: RemoteIngressEdge and RemoteIngressHub: add crash-recovery auto-restart with exponential backoff and max attempts, save/restore config and allowed edges, register/remove exit handlers, ensure stop() marks stopping and cleans up listeners
+- minor API/typing: introduce TAllowedEdge alias and persist allowed edges for restart recovery
+
+## 2026-02-26 - 4.3.0 - feat(hub)
+add optional TLS certificate/key support to hub start config and bridge
+
+- TypeScript: add tls.certPem and tls.keyPem to IHubConfig and include tlsCertPem/tlsKeyPem in startHub bridge command when both are provided
+- TypeScript: extend startHub params with tlsCertPem and tlsKeyPem and conditionally send them
+- Rust: change HubConfig serde attributes for tls_cert_pem and tls_key_pem from skip to default so absent PEM fields deserialize as None
+- Enables optional provisioning of TLS certificate and key to the hub when provided from the JS side
+
+## 2026-02-26 - 4.2.0 - feat(core)
+expose edge peer address in hub events and migrate writers to channel-based, non-blocking framing with stream limits and timeouts
+
+- Add peerAddr to ConnectedEdgeStatus and HubEvent::EdgeConnected and surface it to the TS frontend event (management:edgeConnected).
+- Replace Arc<Mutex<WriteHalf>> writers with dedicated mpsc channel writer tasks in both hub and edge crates to serialize writes off the main tasks.
+- Use non-blocking try_send for data frames to avoid head-of-line blocking and drop frames with warnings when channels are full.
+- Introduce MAX_STREAMS_PER_EDGE semaphore to limit concurrent streams per edge and reject excess opens with a CLOSE_BACK frame.
+- Add a 10s timeout when connecting to SmartProxy to avoid hanging connections.
+- Ensure writer tasks are aborted on shutdown/cleanup and propagate cancellation tokens appropriately.
+
+## 2026-02-26 - 4.1.0 - feat(remoteingress-bin)
+use mimalloc as the global allocator to reduce memory overhead and improve allocation performance
+
+- added mimalloc = "0.1" dependency to rust/crates/remoteingress-bin/Cargo.toml
+- registered mimalloc as the #[global_allocator] in rust/crates/remoteingress-bin/src/main.rs
+- updated Cargo.lock with libmimalloc-sys and mimalloc package entries
+
 ## 2026-02-26 - 4.0.1 - fix(hub)
 cancel per-stream tokens on stream close and avoid duplicate StreamClosed events; bump @types/node devDependency to ^25.3.0
 

package.json

@@ -1,6 +1,6 @@
 {
   "name": "@serve.zone/remoteingress",
-  "version": "4.0.1",
+  "version": "4.4.0",
   "private": false,
   "description": "Edge ingress tunnel for DcRouter - accepts incoming TCP connections at network edge and tunnels them to DcRouter SmartProxy preserving client IP via PROXY protocol v1.",
   "main": "dist_ts/index.js",

rust/Cargo.lock

@@ -327,6 +327,16 @@ version = "0.2.182"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "6800badb6cb2082ffd7b6a67e6125bb39f18782f793520caee8cb8846be06112"
 
+[[package]]
+name = "libmimalloc-sys"
+version = "0.1.44"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "667f4fec20f29dfc6bc7357c582d91796c169ad7e2fce709468aefeb2c099870"
+dependencies = [
+ "cc",
+ "libc",
+]
+
 [[package]]
 name = "lock_api"
 version = "0.4.14"
@@ -348,6 +358,15 @@ version = "2.8.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f8ca58f447f06ed17d5fc4043ce1b10dd205e060fb3ce5b979b8ed8e59ff3f79"
 
+[[package]]
+name = "mimalloc"
+version = "0.1.48"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e1ee66a4b64c74f4ef288bcbb9192ad9c3feaad75193129ac8509af543894fd8"
+dependencies = [
+ "libmimalloc-sys",
+]
+
 [[package]]
 name = "mio"
 version = "1.1.1"
@@ -519,6 +538,7 @@ dependencies = [
  "clap",
  "env_logger",
  "log",
+ "mimalloc",
  "remoteingress-core",
  "remoteingress-protocol",
  "rustls",

rust/crates/remoteingress-bin/Cargo.toml

@@ -17,3 +17,4 @@ serde_json = "1"
 log = "0.4"
 env_logger = "0.11"
 rustls = { version = "0.23", default-features = false, features = ["ring"] }
+mimalloc = "0.1"

rust/crates/remoteingress-bin/src/main.rs

@@ -1,3 +1,6 @@
+#[global_allocator]
+static GLOBAL: mimalloc::MiMalloc = mimalloc::MiMalloc;
+
 use clap::Parser;
 use serde::{Deserialize, Serialize};
 use std::sync::Arc;
@@ -164,10 +167,10 @@ async fn handle_request(
                 tokio::spawn(async move {
                     while let Some(event) = event_rx.recv().await {
                         match &event {
-                            HubEvent::EdgeConnected { edge_id } => {
+                            HubEvent::EdgeConnected { edge_id, peer_addr } => {
                                 send_event(
                                     "edgeConnected",
-                                    serde_json::json!({ "edgeId": edge_id }),
+                                    serde_json::json!({ "edgeId": edge_id, "peerAddr": peer_addr }),
                                 );
                             }
                             HubEvent::EdgeDisconnected { edge_id } => {

rust/crates/remoteingress-core/src/edge.rs

@@ -1,10 +1,12 @@
 use std::collections::HashMap;
 use std::sync::atomic::{AtomicU32, Ordering};
 use std::sync::Arc;
+use std::time::Duration;
 use tokio::io::{AsyncBufReadExt, AsyncReadExt, AsyncWriteExt, BufReader};
 use tokio::net::{TcpListener, TcpStream};
 use tokio::sync::{mpsc, Mutex, RwLock};
 use tokio::task::JoinHandle;
+use tokio::time::{Instant, sleep_until};
 use tokio_rustls::TlsConnector;
 use tokio_util::sync::CancellationToken;
 use serde::{Deserialize, Serialize};
@@ -202,6 +204,13 @@ async fn edge_main_loop(
         // Cancel connection token to kill all orphaned tasks from this cycle
         connection_token.cancel();
 
+        // Reset backoff after a successful connection for fast reconnect
+        let was_connected = *connected.read().await;
+        if was_connected {
+            backoff_ms = 1000;
+            log::info!("Was connected; resetting backoff to {}ms for fast reconnect", backoff_ms);
+        }
+
         *connected.write().await = false;
         let _ = event_tx.try_send(EdgeEvent::TunnelDisconnected);
         active_streams.store(0, Ordering::Relaxed);
@@ -214,7 +223,7 @@ async fn edge_main_loop(
             EdgeLoopResult::Reconnect => {
                 log::info!("Reconnecting in {}ms...", backoff_ms);
                 tokio::select! {
-                    _ = tokio::time::sleep(std::time::Duration::from_millis(backoff_ms)) => {}
+                    _ = tokio::time::sleep(Duration::from_millis(backoff_ms)) => {}
                     _ = cancel_token.cancelled() => break,
                     _ = shutdown_rx.recv() => break,
                 }
@@ -336,7 +345,7 @@ async fn connect_to_hub_and_run(
                 _ = stun_token.cancelled() => break,
             }
             tokio::select! {
-                _ = tokio::time::sleep(std::time::Duration::from_secs(stun_interval)) => {}
+                _ = tokio::time::sleep(Duration::from_secs(stun_interval)) => {}
                 _ = stun_token.cancelled() => break,
             }
         }
@@ -346,15 +355,33 @@ async fn connect_to_hub_and_run(
     let client_writers: Arc<Mutex<HashMap<u32, mpsc::Sender<Vec<u8>>>>> =
         Arc::new(Mutex::new(HashMap::new()));
 
-    // Shared tunnel writer
-    let tunnel_writer = Arc::new(Mutex::new(write_half));
+    // A5: Channel-based tunnel writer replaces Arc<Mutex<WriteHalf>>
+    let (tunnel_writer_tx, mut tunnel_writer_rx) = mpsc::channel::<Vec<u8>>(4096);
+    let tw_token = connection_token.clone();
+    let tunnel_writer_handle = tokio::spawn(async move {
+        loop {
+            tokio::select! {
+                data = tunnel_writer_rx.recv() => {
+                    match data {
+                        Some(frame_data) => {
+                            if write_half.write_all(&frame_data).await.is_err() {
+                                break;
+                            }
+                        }
+                        None => break,
+                    }
+                }
+                _ = tw_token.cancelled() => break,
+            }
+        }
+    });
 
     // Start TCP listeners for initial ports (hot-reloadable)
     let mut port_listeners: HashMap<u16, JoinHandle<()>> = HashMap::new();
     apply_port_config(
         &handshake.listen_ports,
         &mut port_listeners,
-        &tunnel_writer,
+        &tunnel_writer_tx,
         &client_writers,
         active_streams,
         next_stream_id,
@@ -362,6 +389,11 @@ async fn connect_to_hub_and_run(
         connection_token,
     );
 
+    // Heartbeat: liveness timeout detects silent hub failures
+    let liveness_timeout_dur = Duration::from_secs(45);
+    let mut last_activity = Instant::now();
+    let mut liveness_deadline = Box::pin(sleep_until(last_activity + liveness_timeout_dur));
+
     // Read frames from hub
     let mut frame_reader = FrameReader::new(buf_reader);
     let result = loop {
@@ -369,11 +401,18 @@ async fn connect_to_hub_and_run(
             frame_result = frame_reader.next_frame() => {
                 match frame_result {
                     Ok(Some(frame)) => {
+                        // Reset liveness on any received frame
+                        last_activity = Instant::now();
+                        liveness_deadline.as_mut().reset(last_activity + liveness_timeout_dur);
+
                         match frame.frame_type {
                             FRAME_DATA_BACK => {
+                                // A1: Non-blocking send to prevent head-of-line blocking
                                 let writers = client_writers.lock().await;
                                 if let Some(tx) = writers.get(&frame.stream_id) {
-                                    let _ = tx.send(frame.payload).await;
+                                    if tx.try_send(frame.payload).is_err() {
+                                        log::warn!("Stream {} back-channel full, dropping frame", frame.stream_id);
+                                    }
                                 }
                             }
                             FRAME_CLOSE_BACK => {
@@ -390,7 +429,7 @@ async fn connect_to_hub_and_run(
                                     apply_port_config(
                                         &update.listen_ports,
                                         &mut port_listeners,
-                                        &tunnel_writer,
+                                        &tunnel_writer_tx,
                                         &client_writers,
                                         active_streams,
                                         next_stream_id,
@@ -399,6 +438,14 @@ async fn connect_to_hub_and_run(
                                     );
                                 }
                             }
+                            FRAME_PING => {
+                                let pong_frame = encode_frame(0, FRAME_PONG, &[]);
+                                if tunnel_writer_tx.try_send(pong_frame).is_err() {
+                                    log::warn!("Failed to send PONG, writer channel full/closed");
+                                    break EdgeLoopResult::Reconnect;
+                                }
+                                log::trace!("Received PING from hub, sent PONG");
+                            }
                             _ => {
                                 log::warn!("Unexpected frame type {} from hub", frame.frame_type);
                             }
@@ -414,6 +461,11 @@ async fn connect_to_hub_and_run(
                     }
                 }
             }
+            _ = &mut liveness_deadline => {
+                log::warn!("Hub liveness timeout (no frames for {}s), reconnecting",
+                    liveness_timeout_dur.as_secs());
+                break EdgeLoopResult::Reconnect;
+            }
             _ = connection_token.cancelled() => {
                 log::info!("Connection cancelled");
                 break EdgeLoopResult::Shutdown;
@@ -427,6 +479,7 @@ async fn connect_to_hub_and_run(
     // Cancel connection token to propagate to all child tasks BEFORE aborting
     connection_token.cancel();
     stun_handle.abort();
+    tunnel_writer_handle.abort();
     for (_, h) in port_listeners.drain() {
         h.abort();
     }
@@ -438,7 +491,7 @@ async fn connect_to_hub_and_run(
 fn apply_port_config(
     new_ports: &[u16],
     port_listeners: &mut HashMap<u16, JoinHandle<()>>,
-    tunnel_writer: &Arc<Mutex<tokio::io::WriteHalf<tokio_rustls::client::TlsStream<TcpStream>>>>,
+    tunnel_writer_tx: &mpsc::Sender<Vec<u8>>,
     client_writers: &Arc<Mutex<HashMap<u32, mpsc::Sender<Vec<u8>>>>>,
     active_streams: &Arc<AtomicU32>,
     next_stream_id: &Arc<AtomicU32>,
@@ -458,7 +511,7 @@ fn apply_port_config(
 
     // Add new ports
     for &port in new_set.difference(&old_set) {
-        let tunnel_writer = tunnel_writer.clone();
+        let tunnel_writer_tx = tunnel_writer_tx.clone();
         let client_writers = client_writers.clone();
         let active_streams = active_streams.clone();
         let next_stream_id = next_stream_id.clone();
@@ -481,7 +534,7 @@ fn apply_port_config(
                         match accept_result {
                             Ok((client_stream, client_addr)) => {
                                 let stream_id = next_stream_id.fetch_add(1, Ordering::Relaxed);
-                                let tunnel_writer = tunnel_writer.clone();
+                                let tunnel_writer_tx = tunnel_writer_tx.clone();
                                 let client_writers = client_writers.clone();
                                 let active_streams = active_streams.clone();
                                 let edge_id = edge_id.clone();
@@ -496,7 +549,7 @@ fn apply_port_config(
                                         stream_id,
                                         port,
                                         &edge_id,
-                                        tunnel_writer,
+                                        tunnel_writer_tx,
                                         client_writers,
                                         client_token,
                                     )
@@ -526,7 +579,7 @@ async fn handle_client_connection(
     stream_id: u32,
     dest_port: u16,
     edge_id: &str,
-    tunnel_writer: Arc<Mutex<tokio::io::WriteHalf<tokio_rustls::client::TlsStream<TcpStream>>>>,
+    tunnel_writer_tx: mpsc::Sender<Vec<u8>>,
     client_writers: Arc<Mutex<HashMap<u32, mpsc::Sender<Vec<u8>>>>>,
     client_token: CancellationToken,
 ) {
@@ -536,14 +589,11 @@ async fn handle_client_connection(
     // Determine edge IP (use 0.0.0.0 as placeholder — hub doesn't use it for routing)
     let edge_ip = "0.0.0.0";
 
-    // Send OPEN frame with PROXY v1 header
+    // Send OPEN frame with PROXY v1 header via writer channel
     let proxy_header = build_proxy_v1_header(&client_ip, edge_ip, client_port, dest_port);
     let open_frame = encode_frame(stream_id, FRAME_OPEN, proxy_header.as_bytes());
-    {
-        let mut w = tunnel_writer.lock().await;
-        if w.write_all(&open_frame).await.is_err() {
-            return;
-        }
+    if tunnel_writer_tx.send(open_frame).await.is_err() {
+        return;
     }
 
     // Set up channel for data coming back from hub
@@ -576,7 +626,7 @@ async fn handle_client_connection(
         let _ = client_write.shutdown().await;
     });
 
-    // Task: client -> hub
+    // Task: client -> hub (via writer channel)
     let mut buf = vec![0u8; 32768];
     loop {
         tokio::select! {
@@ -585,8 +635,9 @@ async fn handle_client_connection(
                     Ok(0) => break,
                     Ok(n) => {
                         let data_frame = encode_frame(stream_id, FRAME_DATA, &buf[..n]);
-                        let mut w = tunnel_writer.lock().await;
-                        if w.write_all(&data_frame).await.is_err() {
+                        // A5: Use try_send to avoid blocking if writer channel is full
+                        if tunnel_writer_tx.try_send(data_frame).is_err() {
+                            log::warn!("Stream {} tunnel writer full, closing", stream_id);
                             break;
                         }
                     }
@@ -600,8 +651,7 @@ async fn handle_client_connection(
     // Send CLOSE frame (only if not cancelled)
     if !client_token.is_cancelled() {
         let close_frame = encode_frame(stream_id, FRAME_CLOSE, &[]);
-        let mut w = tunnel_writer.lock().await;
-        let _ = w.write_all(&close_frame).await;
+        let _ = tunnel_writer_tx.try_send(close_frame);
     }
 
     // Cleanup

rust/crates/remoteingress-core/src/hub.rs

@@ -1,8 +1,10 @@
 use std::collections::HashMap;
 use std::sync::Arc;
+use std::time::Duration;
 use tokio::io::{AsyncBufReadExt, AsyncReadExt, AsyncWriteExt, BufReader};
 use tokio::net::{TcpListener, TcpStream};
-use tokio::sync::{mpsc, Mutex, RwLock};
+use tokio::sync::{mpsc, Mutex, RwLock, Semaphore};
+use tokio::time::{interval, sleep_until, Instant};
 use tokio_rustls::TlsAcceptor;
 use tokio_util::sync::CancellationToken;
 use serde::{Deserialize, Serialize};
@@ -15,9 +17,9 @@ use remoteingress_protocol::*;
 pub struct HubConfig {
     pub tunnel_port: u16,
     pub target_host: Option<String>,
-    #[serde(skip)]
+    #[serde(default)]
     pub tls_cert_pem: Option<String>,
-    #[serde(skip)]
+    #[serde(default)]
     pub tls_key_pem: Option<String>,
 }
 
@@ -65,6 +67,7 @@ pub struct ConnectedEdgeStatus {
     pub edge_id: String,
     pub connected_at: u64,
     pub active_streams: usize,
+    pub peer_addr: String,
 }
 
 /// Events emitted by the hub.
@@ -73,7 +76,7 @@ pub struct ConnectedEdgeStatus {
 #[serde(tag = "type")]
 pub enum HubEvent {
     #[serde(rename_all = "camelCase")]
-    EdgeConnected { edge_id: String },
+    EdgeConnected { edge_id: String, peer_addr: String },
     #[serde(rename_all = "camelCase")]
     EdgeDisconnected { edge_id: String },
     #[serde(rename_all = "camelCase")]
@@ -105,6 +108,7 @@ pub struct TunnelHub {
 
 struct ConnectedEdgeInfo {
     connected_at: u64,
+    peer_addr: String,
     active_streams: Arc<Mutex<HashMap<u32, (mpsc::Sender<Vec<u8>>, CancellationToken)>>>,
     config_tx: mpsc::Sender<EdgeConfigUpdate>,
     #[allow(dead_code)] // kept alive for Drop — cancels child tokens when edge is removed
@@ -176,6 +180,7 @@ impl TunnelHub {
                 edge_id: id.clone(),
                 connected_at: info.connected_at,
                 active_streams: streams.len(),
+                peer_addr: info.peer_addr.clone(),
             });
         }
 
@@ -218,9 +223,10 @@ impl TunnelHub {
                                 let event_tx = event_tx.clone();
                                 let target = target_host.clone();
                                 let edge_token = hub_token.child_token();
+                                let peer_addr = addr.ip().to_string();
                                 tokio::spawn(async move {
                                     if let Err(e) = handle_edge_connection(
-                                        stream, acceptor, allowed, connected, event_tx, target, edge_token,
+                                        stream, acceptor, allowed, connected, event_tx, target, edge_token, peer_addr,
                                     ).await {
                                         log::error!("Edge connection error: {}", e);
                                     }
@@ -264,6 +270,9 @@ impl Drop for TunnelHub {
     }
 }
 
+/// Maximum concurrent streams per edge connection.
+const MAX_STREAMS_PER_EDGE: usize = 1024;
+
 /// Handle a single edge connection: authenticate, then enter frame loop.
 async fn handle_edge_connection(
     stream: TcpStream,
@@ -273,6 +282,7 @@ async fn handle_edge_connection(
     event_tx: mpsc::Sender<HubEvent>,
     target_host: String,
     edge_token: CancellationToken,
+    peer_addr: String,
 ) -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
     let tls_stream = acceptor.accept(stream).await?;
     let (read_half, mut write_half) = tokio::io::split(tls_stream);
@@ -307,9 +317,10 @@ async fn handle_edge_connection(
         }
     };
 
-    log::info!("Edge {} authenticated", edge_id);
+    log::info!("Edge {} authenticated from {}", edge_id, peer_addr);
     let _ = event_tx.try_send(HubEvent::EdgeConnected {
         edge_id: edge_id.clone(),
+        peer_addr: peer_addr.clone(),
     });
 
     // Send handshake response with initial config before frame protocol begins
@@ -338,6 +349,7 @@ async fn handle_edge_connection(
             edge_id.clone(),
             ConnectedEdgeInfo {
                 connected_at: now,
+                peer_addr,
                 active_streams: streams.clone(),
                 config_tx,
                 cancel_token: edge_token.clone(),
@@ -345,11 +357,30 @@ async fn handle_edge_connection(
         );
     }
 
-    // Shared writer for sending frames back to edge
-    let write_half = Arc::new(Mutex::new(write_half));
+    // A5: Channel-based writer replaces Arc<Mutex<WriteHalf>>
+    // All frame writes go through this channel → dedicated writer task serializes them
+    let (frame_writer_tx, mut frame_writer_rx) = mpsc::channel::<Vec<u8>>(4096);
+    let writer_token = edge_token.clone();
+    let writer_handle = tokio::spawn(async move {
+        loop {
+            tokio::select! {
+                data = frame_writer_rx.recv() => {
+                    match data {
+                        Some(frame_data) => {
+                            if write_half.write_all(&frame_data).await.is_err() {
+                                break;
+                            }
+                        }
+                        None => break,
+                    }
+                }
+                _ = writer_token.cancelled() => break,
+            }
+        }
+    });
 
     // Spawn task to forward config updates as FRAME_CONFIG frames
-    let config_writer = write_half.clone();
+    let config_writer_tx = frame_writer_tx.clone();
     let config_edge_id = edge_id.clone();
     let config_token = edge_token.clone();
     let config_handle = tokio::spawn(async move {
@@ -360,8 +391,7 @@ async fn handle_edge_connection(
                         Some(update) => {
                             if let Ok(payload) = serde_json::to_vec(&update) {
                                 let frame = encode_frame(0, FRAME_CONFIG, &payload);
-                                let mut w = config_writer.lock().await;
-                                if w.write_all(&frame).await.is_err() {
+                                if config_writer_tx.send(frame).await.is_err() {
                                     log::error!("Failed to send config update to edge {}", config_edge_id);
                                     break;
                                 }
@@ -376,6 +406,17 @@ async fn handle_edge_connection(
         }
     });
 
+    // A4: Semaphore to limit concurrent streams per edge
+    let stream_semaphore = Arc::new(Semaphore::new(MAX_STREAMS_PER_EDGE));
+
+    // Heartbeat: periodic PING and liveness timeout
+    let ping_interval_dur = Duration::from_secs(15);
+    let liveness_timeout_dur = Duration::from_secs(45);
+    let mut ping_ticker = interval(ping_interval_dur);
+    ping_ticker.tick().await; // consume the immediate first tick
+    let mut last_activity = Instant::now();
+    let mut liveness_deadline = Box::pin(sleep_until(last_activity + liveness_timeout_dur));
+
     // Frame reading loop
     let mut frame_reader = FrameReader::new(buf_reader);
 
@@ -384,8 +425,24 @@ async fn handle_edge_connection(
             frame_result = frame_reader.next_frame() => {
                 match frame_result {
                     Ok(Some(frame)) => {
+                        // Reset liveness on any received frame
+                        last_activity = Instant::now();
+                        liveness_deadline.as_mut().reset(last_activity + liveness_timeout_dur);
+
                         match frame.frame_type {
                             FRAME_OPEN => {
+                                // A4: Check stream limit before processing
+                                let permit = match stream_semaphore.clone().try_acquire_owned() {
+                                    Ok(p) => p,
+                                    Err(_) => {
+                                        log::warn!("Edge {} exceeded max streams ({}), rejecting stream {}",
+                                            edge_id, MAX_STREAMS_PER_EDGE, frame.stream_id);
+                                        let close_frame = encode_frame(frame.stream_id, FRAME_CLOSE_BACK, &[]);
+                                        let _ = frame_writer_tx.try_send(close_frame);
+                                        continue;
+                                    }
+                                };
+
                                 // Payload is PROXY v1 header line
                                 let proxy_header = String::from_utf8_lossy(&frame.payload).to_string();
 
@@ -396,7 +453,7 @@ async fn handle_edge_connection(
                                 let edge_id_clone = edge_id.clone();
                                 let event_tx_clone = event_tx.clone();
                                 let streams_clone = streams.clone();
-                                let writer_clone = write_half.clone();
+                                let writer_tx = frame_writer_tx.clone();
                                 let target = target_host.clone();
                                 let stream_token = edge_token.child_token();
 
@@ -414,9 +471,19 @@ async fn handle_edge_connection(
 
                                 // Spawn task: connect to SmartProxy, send PROXY header, pipe data
                                 tokio::spawn(async move {
+                                    let _permit = permit; // hold semaphore permit until stream completes
+
                                     let result = async {
-                                        let mut upstream =
-                                            TcpStream::connect((target.as_str(), dest_port)).await?;
+                                        // A2: Connect to SmartProxy with timeout
+                                        let mut upstream = tokio::time::timeout(
+                                            Duration::from_secs(10),
+                                            TcpStream::connect((target.as_str(), dest_port)),
+                                        )
+                                        .await
+                                        .map_err(|_| -> Box<dyn std::error::Error + Send + Sync> {
+                                            format!("connect to SmartProxy {}:{} timed out (10s)", target, dest_port).into()
+                                        })??;
+
                                         upstream.write_all(proxy_header.as_bytes()).await?;
 
                                         let (mut up_read, mut up_write) =
@@ -443,7 +510,7 @@ async fn handle_edge_connection(
                                             let _ = up_write.shutdown().await;
                                         });
 
-                                        // Forward data from SmartProxy back to edge
+                                        // Forward data from SmartProxy back to edge via writer channel
                                         let mut buf = vec![0u8; 32768];
                                         loop {
                                             tokio::select! {
@@ -453,8 +520,9 @@ async fn handle_edge_connection(
                                                         Ok(n) => {
                                                             let frame =
                                                                 encode_frame(stream_id, FRAME_DATA_BACK, &buf[..n]);
-                                                            let mut w = writer_clone.lock().await;
-                                                            if w.write_all(&frame).await.is_err() {
+                                                            // A5: Use try_send to avoid blocking if writer channel is full
+                                                            if writer_tx.try_send(frame).is_err() {
+                                                                log::warn!("Stream {} writer channel full, closing", stream_id);
                                                                 break;
                                                             }
                                                         }
@@ -468,8 +536,7 @@ async fn handle_edge_connection(
                                         // Send CLOSE_BACK to edge (only if not cancelled)
                                         if !stream_token.is_cancelled() {
                                             let close_frame = encode_frame(stream_id, FRAME_CLOSE_BACK, &[]);
-                                            let mut w = writer_clone.lock().await;
-                                            let _ = w.write_all(&close_frame).await;
+                                            let _ = writer_tx.try_send(close_frame);
                                         }
 
                                         writer_for_edge_data.abort();
@@ -482,8 +549,7 @@ async fn handle_edge_connection(
                                         // Send CLOSE_BACK on error (only if not cancelled)
                                         if !stream_token.is_cancelled() {
                                             let close_frame = encode_frame(stream_id, FRAME_CLOSE_BACK, &[]);
-                                            let mut w = writer_clone.lock().await;
-                                            let _ = w.write_all(&close_frame).await;
+                                            let _ = writer_tx.try_send(close_frame);
                                         }
                                     }
 
@@ -501,9 +567,12 @@ async fn handle_edge_connection(
                                 });
                             }
                             FRAME_DATA => {
+                                // A1: Non-blocking send to prevent head-of-line blocking
                                 let s = streams.lock().await;
                                 if let Some((tx, _)) = s.get(&frame.stream_id) {
-                                    let _ = tx.send(frame.payload).await;
+                                    if tx.try_send(frame.payload).is_err() {
+                                        log::warn!("Stream {} data channel full, dropping frame", frame.stream_id);
+                                    }
                                 }
                             }
                             FRAME_CLOSE => {
@@ -516,6 +585,9 @@ async fn handle_edge_connection(
                                     });
                                 }
                             }
+                            FRAME_PONG => {
+                                log::debug!("Received PONG from edge {}", edge_id);
+                            }
                             _ => {
                                 log::warn!("Unexpected frame type {} from edge", frame.frame_type);
                             }
@@ -531,6 +603,19 @@ async fn handle_edge_connection(
                     }
                 }
             }
+            _ = ping_ticker.tick() => {
+                let ping_frame = encode_frame(0, FRAME_PING, &[]);
+                if frame_writer_tx.try_send(ping_frame).is_err() {
+                    log::warn!("Failed to send PING to edge {}, writer channel full/closed", edge_id);
+                    break;
+                }
+                log::trace!("Sent PING to edge {}", edge_id);
+            }
+            _ = &mut liveness_deadline => {
+                log::warn!("Edge {} liveness timeout (no frames for {}s), disconnecting",
+                    edge_id, liveness_timeout_dur.as_secs());
+                break;
+            }
             _ = edge_token.cancelled() => {
                 log::info!("Edge {} cancelled by hub", edge_id);
                 break;
@@ -541,6 +626,7 @@ async fn handle_edge_connection(
     // Cleanup: cancel edge token to propagate to all child tasks
     edge_token.cancel();
     config_handle.abort();
+    writer_handle.abort();
     {
         let mut edges = connected.lock().await;
         edges.remove(&edge_id);
@@ -757,10 +843,12 @@ mod tests {
     fn test_hub_event_edge_connected_serialize() {
         let event = HubEvent::EdgeConnected {
             edge_id: "edge-1".to_string(),
+            peer_addr: "203.0.113.5".to_string(),
         };
         let json = serde_json::to_value(&event).unwrap();
         assert_eq!(json["type"], "edgeConnected");
         assert_eq!(json["edgeId"], "edge-1");
+        assert_eq!(json["peerAddr"], "203.0.113.5");
     }
 
     #[test]

rust/crates/remoteingress-protocol/src/lib.rs

@@ -7,6 +7,8 @@ pub const FRAME_CLOSE: u8 = 0x03;
 pub const FRAME_DATA_BACK: u8 = 0x04;
 pub const FRAME_CLOSE_BACK: u8 = 0x05;
 pub const FRAME_CONFIG: u8 = 0x06;     // Hub -> Edge: configuration update
+pub const FRAME_PING: u8 = 0x07;       // Hub -> Edge: heartbeat probe
+pub const FRAME_PONG: u8 = 0x08;       // Edge -> Hub: heartbeat response
 
 // Frame header size: 4 (stream_id) + 1 (type) + 4 (length) = 9 bytes
 pub const FRAME_HEADER_SIZE: usize = 9;
@@ -261,6 +263,8 @@ mod tests {
             FRAME_DATA_BACK,
             FRAME_CLOSE_BACK,
             FRAME_CONFIG,
+            FRAME_PING,
+            FRAME_PONG,
         ];
 
         let mut data = Vec::new();
@@ -293,4 +297,19 @@ mod tests {
         assert_eq!(frame.frame_type, FRAME_CLOSE);
         assert!(frame.payload.is_empty());
     }
+
+    #[test]
+    fn test_encode_frame_ping_pong() {
+        // PING: stream_id=0, empty payload (control frame)
+        let ping = encode_frame(0, FRAME_PING, &[]);
+        assert_eq!(ping[4], FRAME_PING);
+        assert_eq!(&ping[0..4], &0u32.to_be_bytes());
+        assert_eq!(ping.len(), FRAME_HEADER_SIZE);
+
+        // PONG: stream_id=0, empty payload (control frame)
+        let pong = encode_frame(0, FRAME_PONG, &[]);
+        assert_eq!(pong[4], FRAME_PONG);
+        assert_eq!(&pong[0..4], &0u32.to_be_bytes());
+        assert_eq!(pong.len(), FRAME_HEADER_SIZE);
+    }
 }

ts/00_commitinfo_data.ts

@@ -3,6 +3,6 @@
  */
 export const commitinfo = {
   name: '@serve.zone/remoteingress',
-  version: '4.0.1',
+  version: '4.4.0',
   description: 'Edge ingress tunnel for DcRouter - accepts incoming TCP connections at network edge and tunnels them to DcRouter SmartProxy preserving client IP via PROXY protocol v1.'
 }

ts/classes.remoteingressedge.ts

@@ -40,9 +40,16 @@ export interface IEdgeConfig {
   secret: string;
 }
 
+const MAX_RESTART_ATTEMPTS = 10;
+const MAX_RESTART_BACKOFF_MS = 30_000;
+
 export class RemoteIngressEdge extends EventEmitter {
   private bridge: InstanceType<typeof plugins.smartrust.RustBridge<TEdgeCommands>>;
   private started = false;
+  private stopping = false;
+  private savedConfig: IEdgeConfig | null = null;
+  private restartBackoffMs = 1000;
+  private restartAttempts = 0;
   private statusInterval: ReturnType<typeof setInterval> | undefined;
 
   constructor() {
@@ -109,11 +116,17 @@ export class RemoteIngressEdge extends EventEmitter {
       edgeConfig = config;
     }
 
+    this.savedConfig = edgeConfig;
+    this.stopping = false;
+
     const spawned = await this.bridge.spawn();
     if (!spawned) {
       throw new Error('Failed to spawn remoteingress-bin');
     }
 
+    // Register crash recovery handler
+    this.bridge.on('exit', this.handleCrashRecovery);
+
     await this.bridge.sendCommand('startEdge', {
       hubHost: edgeConfig.hubHost,
       hubPort: edgeConfig.hubPort ?? 8443,
@@ -122,6 +135,8 @@ export class RemoteIngressEdge extends EventEmitter {
     });
 
     this.started = true;
+    this.restartAttempts = 0;
+    this.restartBackoffMs = 1000;
 
     // Start periodic status logging
     this.statusInterval = setInterval(async () => {
@@ -142,6 +157,7 @@ export class RemoteIngressEdge extends EventEmitter {
    * Stop the edge and kill the Rust process.
    */
   public async stop(): Promise<void> {
+    this.stopping = true;
     if (this.statusInterval) {
       clearInterval(this.statusInterval);
       this.statusInterval = undefined;
@@ -152,6 +168,7 @@ export class RemoteIngressEdge extends EventEmitter {
       } catch {
         // Process may already be dead
       }
+      this.bridge.removeListener('exit', this.handleCrashRecovery);
       this.bridge.kill();
       this.started = false;
     }
@@ -170,4 +187,55 @@ export class RemoteIngressEdge extends EventEmitter {
   public get running(): boolean {
     return this.bridge.running;
   }
+
+  /**
+   * Handle unexpected Rust binary crash — auto-restart with backoff.
+   */
+  private handleCrashRecovery = async (code: number | null, signal: string | null) => {
+    if (this.stopping || !this.started || !this.savedConfig) {
+      return;
+    }
+
+    console.error(
+      `[RemoteIngressEdge] Rust binary crashed (code=${code}, signal=${signal}), ` +
+      `attempt ${this.restartAttempts + 1}/${MAX_RESTART_ATTEMPTS}`
+    );
+
+    this.started = false;
+
+    if (this.restartAttempts >= MAX_RESTART_ATTEMPTS) {
+      console.error('[RemoteIngressEdge] Max restart attempts reached, giving up');
+      this.emit('crashRecoveryFailed');
+      return;
+    }
+
+    await new Promise(resolve => setTimeout(resolve, this.restartBackoffMs));
+    this.restartBackoffMs = Math.min(this.restartBackoffMs * 2, MAX_RESTART_BACKOFF_MS);
+    this.restartAttempts++;
+
+    try {
+      const spawned = await this.bridge.spawn();
+      if (!spawned) {
+        console.error('[RemoteIngressEdge] Failed to respawn binary');
+        return;
+      }
+
+      this.bridge.on('exit', this.handleCrashRecovery);
+
+      await this.bridge.sendCommand('startEdge', {
+        hubHost: this.savedConfig.hubHost,
+        hubPort: this.savedConfig.hubPort ?? 8443,
+        edgeId: this.savedConfig.edgeId,
+        secret: this.savedConfig.secret,
+      });
+
+      this.started = true;
+      this.restartAttempts = 0;
+      this.restartBackoffMs = 1000;
+      console.log('[RemoteIngressEdge] Successfully recovered from crash');
+      this.emit('crashRecovered');
+    } catch (err) {
+      console.error(`[RemoteIngressEdge] Crash recovery failed: ${err}`);
+    }
+  };
 }

ts/classes.remoteingresshub.ts

@@ -11,6 +11,8 @@ type THubCommands = {
     params: {
       tunnelPort: number;
       targetHost?: string;
+      tlsCertPem?: string;
+      tlsKeyPem?: string;
     };
     result: { started: boolean };
   };
@@ -33,6 +35,7 @@ type THubCommands = {
         edgeId: string;
         connectedAt: number;
         activeStreams: number;
+        peerAddr: string;
       }>;
     };
   };
@@ -41,11 +44,25 @@ type THubCommands = {
 export interface IHubConfig {
   tunnelPort?: number;
   targetHost?: string;
+  tls?: {
+    certPem?: string;
+    keyPem?: string;
+  };
 }
 
+type TAllowedEdge = { id: string; secret: string; listenPorts?: number[]; stunIntervalSecs?: number };
+
+const MAX_RESTART_ATTEMPTS = 10;
+const MAX_RESTART_BACKOFF_MS = 30_000;
+
 export class RemoteIngressHub extends EventEmitter {
   private bridge: InstanceType<typeof plugins.smartrust.RustBridge<THubCommands>>;
   private started = false;
+  private stopping = false;
+  private savedConfig: IHubConfig | null = null;
+  private savedEdges: TAllowedEdge[] = [];
+  private restartBackoffMs = 1000;
+  private restartAttempts = 0;
 
   constructor() {
     super();
@@ -73,7 +90,7 @@ export class RemoteIngressHub extends EventEmitter {
     });
 
     // Forward events from Rust binary
-    this.bridge.on('management:edgeConnected', (data: { edgeId: string }) => {
+    this.bridge.on('management:edgeConnected', (data: { edgeId: string; peerAddr: string }) => {
       this.emit('edgeConnected', data);
     });
     this.bridge.on('management:edgeDisconnected', (data: { edgeId: string }) => {
@@ -91,29 +108,42 @@ export class RemoteIngressHub extends EventEmitter {
    * Start the hub — spawns the Rust binary and starts the tunnel server.
    */
   public async start(config: IHubConfig = {}): Promise<void> {
+    this.savedConfig = config;
+    this.stopping = false;
+
     const spawned = await this.bridge.spawn();
     if (!spawned) {
       throw new Error('Failed to spawn remoteingress-bin');
     }
 
+    // Register crash recovery handler
+    this.bridge.on('exit', this.handleCrashRecovery);
+
     await this.bridge.sendCommand('startHub', {
       tunnelPort: config.tunnelPort ?? 8443,
       targetHost: config.targetHost ?? '127.0.0.1',
+      ...(config.tls?.certPem && config.tls?.keyPem
+        ? { tlsCertPem: config.tls.certPem, tlsKeyPem: config.tls.keyPem }
+        : {}),
     });
 
     this.started = true;
+    this.restartAttempts = 0;
+    this.restartBackoffMs = 1000;
   }
 
   /**
    * Stop the hub and kill the Rust process.
    */
   public async stop(): Promise<void> {
+    this.stopping = true;
     if (this.started) {
       try {
         await this.bridge.sendCommand('stopHub', {} as Record<string, never>);
       } catch {
         // Process may already be dead
       }
+      this.bridge.removeListener('exit', this.handleCrashRecovery);
       this.bridge.kill();
       this.started = false;
     }
@@ -122,7 +152,8 @@ export class RemoteIngressHub extends EventEmitter {
   /**
    * Update the list of allowed edges that can connect to this hub.
    */
-  public async updateAllowedEdges(edges: Array<{ id: string; secret: string; listenPorts?: number[]; stunIntervalSecs?: number }>): Promise<void> {
+  public async updateAllowedEdges(edges: TAllowedEdge[]): Promise<void> {
+    this.savedEdges = edges;
     await this.bridge.sendCommand('updateAllowedEdges', { edges });
   }
 
@@ -139,4 +170,62 @@ export class RemoteIngressHub extends EventEmitter {
   public get running(): boolean {
     return this.bridge.running;
   }
+
+  /**
+   * Handle unexpected Rust binary crash — auto-restart with backoff.
+   */
+  private handleCrashRecovery = async (code: number | null, signal: string | null) => {
+    if (this.stopping || !this.started || !this.savedConfig) {
+      return;
+    }
+
+    console.error(
+      `[RemoteIngressHub] Rust binary crashed (code=${code}, signal=${signal}), ` +
+      `attempt ${this.restartAttempts + 1}/${MAX_RESTART_ATTEMPTS}`
+    );
+
+    this.started = false;
+
+    if (this.restartAttempts >= MAX_RESTART_ATTEMPTS) {
+      console.error('[RemoteIngressHub] Max restart attempts reached, giving up');
+      this.emit('crashRecoveryFailed');
+      return;
+    }
+
+    await new Promise(resolve => setTimeout(resolve, this.restartBackoffMs));
+    this.restartBackoffMs = Math.min(this.restartBackoffMs * 2, MAX_RESTART_BACKOFF_MS);
+    this.restartAttempts++;
+
+    try {
+      const spawned = await this.bridge.spawn();
+      if (!spawned) {
+        console.error('[RemoteIngressHub] Failed to respawn binary');
+        return;
+      }
+
+      this.bridge.on('exit', this.handleCrashRecovery);
+
+      const config = this.savedConfig;
+      await this.bridge.sendCommand('startHub', {
+        tunnelPort: config.tunnelPort ?? 8443,
+        targetHost: config.targetHost ?? '127.0.0.1',
+        ...(config.tls?.certPem && config.tls?.keyPem
+          ? { tlsCertPem: config.tls.certPem, tlsKeyPem: config.tls.keyPem }
+          : {}),
+      });
+
+      // Restore allowed edges
+      if (this.savedEdges.length > 0) {
+        await this.bridge.sendCommand('updateAllowedEdges', { edges: this.savedEdges });
+      }
+
+      this.started = true;
+      this.restartAttempts = 0;
+      this.restartBackoffMs = 1000;
+      console.log('[RemoteIngressHub] Successfully recovered from crash');
+      this.emit('crashRecovered');
+    } catch (err) {
+      console.error(`[RemoteIngressHub] Crash recovery failed: ${err}`);
+    }
+  };
 }