Implement heartbeat-based host connectivity detection

- Add agent_heartbeat metric to agent transmission for reliable host detection
- Update dashboard to track heartbeat timestamps per host instead of general metrics
- Add configurable heartbeat_timeout_seconds to dashboard ZMQ config (default 10s)
- Remove unused timeout_ms from agent config and revert to non-blocking command reception
- Remove unused heartbeat_interval_ms from agent configuration
- Host disconnect detection now uses dedicated heartbeat metrics for improved reliability
- Bump version to 0.1.57

dashboard/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "cm-dashboard"
-version = "0.1.56"
+version = "0.1.57"
 edition = "2021"
 
 [dependencies]

dashboard/src/app.rs

@@ -22,7 +22,7 @@ pub struct Dashboard {
     terminal: Option<Terminal<CrosstermBackend<io::Stdout>>>,
     headless: bool,
     initial_commands_sent: std::collections::HashSet<String>,
-    _config: DashboardConfig,
+    config: DashboardConfig,
 }
 
 impl Dashboard {
@@ -133,7 +133,7 @@ impl Dashboard {
             terminal,
             headless,
             initial_commands_sent: std::collections::HashSet::new(),
-            _config: config,
+            config,
         })
     }
 
@@ -247,7 +247,7 @@ impl Dashboard {
                     if let Some(ref mut tui_app) = self.tui_app {
                         let connected_hosts = self
                             .metric_store
-                            .get_connected_hosts(Duration::from_secs(30));
+                            .get_connected_hosts(Duration::from_secs(self.config.zmq.heartbeat_timeout_seconds));
                         
                         
                         tui_app.update_hosts(connected_hosts);

dashboard/src/communication/mod.rs

@@ -141,9 +141,9 @@ impl ZmqConsumer {
         }
     }
 
-    /// Receive metrics from any connected agent (non-blocking)
+    /// Receive metrics from any connected agent (with timeout)
     pub async fn receive_metrics(&mut self) -> Result<Option<MetricMessage>> {
-        match self.subscriber.recv_bytes(zmq::DONTWAIT) {
+        match self.subscriber.recv_bytes(0) {
             Ok(data) => {
                 debug!("Received {} bytes from ZMQ", data.len());
 

dashboard/src/config/mod.rs

@@ -16,6 +16,13 @@ pub struct DashboardConfig {
 #[derive(Debug, Clone, Serialize, Deserialize)]
 pub struct ZmqConfig {
     pub subscriber_ports: Vec<u16>,
+    /// Heartbeat timeout in seconds - hosts considered offline if no heartbeat received within this time
+    #[serde(default = "default_heartbeat_timeout_seconds")]
+    pub heartbeat_timeout_seconds: u64,
+}
+
+fn default_heartbeat_timeout_seconds() -> u64 {
+    10 // Default to 10 seconds - allows for multiple missed heartbeats
 }
 
 /// Individual host configuration details

dashboard/src/metrics/store.rs

@@ -11,8 +11,8 @@ pub struct MetricStore {
     current_metrics: HashMap<String, HashMap<String, Metric>>,
     /// Historical metrics for trending
     historical_metrics: HashMap<String, Vec<MetricDataPoint>>,
-    /// Last update timestamp per host
-    last_update: HashMap<String, Instant>,
+    /// Last heartbeat timestamp per host
+    last_heartbeat: HashMap<String, Instant>,
     /// Configuration
     max_metrics_per_host: usize,
     history_retention: Duration,
@@ -23,7 +23,7 @@ impl MetricStore {
         Self {
             current_metrics: HashMap::new(),
             historical_metrics: HashMap::new(),
-            last_update: HashMap::new(),
+            last_heartbeat: HashMap::new(),
             max_metrics_per_host,
             history_retention: Duration::from_secs(history_retention_hours * 3600),
         }
@@ -56,10 +56,13 @@ impl MetricStore {
 
             // Add to history
             host_history.push(MetricDataPoint { received_at: now });
-        }
 
-        // Update last update timestamp
-        self.last_update.insert(hostname.to_string(), now);
+            // Track heartbeat metrics for connectivity detection
+            if metric_name == "agent_heartbeat" {
+                self.last_heartbeat.insert(hostname.to_string(), now);
+                debug!("Updated heartbeat for host {}", hostname);
+            }
+        }
 
         // Get metrics count before cleanup
         let metrics_count = host_metrics.len();
@@ -88,16 +91,18 @@ impl MetricStore {
         }
     }
 
-    /// Get connected hosts (hosts with recent updates)
+    /// Get connected hosts (hosts with recent heartbeats)
     pub fn get_connected_hosts(&self, timeout: Duration) -> Vec<String> {
         let now = Instant::now();
 
-        self.last_update
+        self.last_heartbeat
             .iter()
-            .filter_map(|(hostname, &last_update)| {
-                if now.duration_since(last_update) <= timeout {
+            .filter_map(|(hostname, &last_heartbeat)| {
+                if now.duration_since(last_heartbeat) <= timeout {
                     Some(hostname.clone())
                 } else {
+                    debug!("Host {} considered offline - last heartbeat was {:?} ago", 
+                           hostname, now.duration_since(last_heartbeat));
                     None
                 }
             })