Fix Tab key 1-second delay by reverting ZMQ to non-blocking mode

- Change receive_metrics() from blocking to DONTWAIT to prevent main loop freezing
- Eliminate 1-second ZMQ socket timeout that was blocking UI after Tab key press
- Main loop now continues immediately after immediate render instead of waiting
- Maintain heartbeat-based host detection while fixing visual responsiveness
- Fix blocking operation introduced when implementing heartbeat timeout mechanism
- Tab navigation now truly immediate without any network operation delays
- Bump version to 0.1.61

Cargo.lock

@@ -270,7 +270,7 @@ checksum = "a1d728cc89cf3aee9ff92b05e62b19ee65a02b5702cff7d5a377e32c6ae29d8d"
 
 [[package]]
 name = "cm-dashboard"
-version = "0.1.55"
+version = "0.1.60"
 dependencies = [
  "anyhow",
  "chrono",
@@ -292,7 +292,7 @@ dependencies = [
 
 [[package]]
 name = "cm-dashboard-agent"
-version = "0.1.55"
+version = "0.1.60"
 dependencies = [
  "anyhow",
  "async-trait",
@@ -315,7 +315,7 @@ dependencies = [
 
 [[package]]
 name = "cm-dashboard-shared"
-version = "0.1.55"
+version = "0.1.60"
 dependencies = [
  "chrono",
  "serde",

agent/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "cm-dashboard-agent"
-version = "0.1.56"
+version = "0.1.61"
 edition = "2021"
 
 [dependencies]

agent/src/agent.rs

@@ -180,6 +180,10 @@ impl Agent {
         let version_metric = self.get_agent_version_metric();
         metrics.push(version_metric);
 
+        // Add heartbeat metric for host connectivity detection
+        let heartbeat_metric = self.get_heartbeat_metric();
+        metrics.push(heartbeat_metric);
+
         // Check for user-stopped services that are now active and clear their flags
         self.clear_user_stopped_flags_for_active_services(&metrics);
 
@@ -232,6 +236,21 @@ impl Agent {
         format!("v{}", env!("CARGO_PKG_VERSION"))
     }
 
+    /// Create heartbeat metric for host connectivity detection
+    fn get_heartbeat_metric(&self) -> Metric {
+        use std::time::{SystemTime, UNIX_EPOCH};
+        
+        let timestamp = SystemTime::now()
+            .duration_since(UNIX_EPOCH)
+            .unwrap()
+            .as_secs();
+        
+        Metric::new(
+            "agent_heartbeat".to_string(),
+            MetricValue::Integer(timestamp as i64),
+            Status::Ok,
+        )
+    }
 
     async fn handle_commands(&mut self) -> Result<()> {
         // Try to receive commands (non-blocking)

agent/src/communication/mod.rs

@@ -66,8 +66,6 @@ impl ZmqHandler {
     }
 
 
-    /// Send heartbeat (placeholder for future use)
-
     /// Try to receive a command (non-blocking)
     pub fn try_receive_command(&self) -> Result<Option<AgentCommand>> {
         match self.command_receiver.recv_bytes(zmq::DONTWAIT) {

agent/src/config/mod.rs

@@ -28,8 +28,6 @@ pub struct ZmqConfig {
     pub publisher_port: u16,
     pub command_port: u16,
     pub bind_address: String,
-    pub timeout_ms: u64,
-    pub heartbeat_interval_ms: u64,
     pub transmission_interval_seconds: u64,
 }
 

agent/src/config/validation.rs

@@ -19,10 +19,6 @@ pub fn validate_config(config: &AgentConfig) -> Result<()> {
         bail!("ZMQ bind address cannot be empty");
     }
 
-    if config.zmq.timeout_ms == 0 {
-        bail!("ZMQ timeout cannot be 0");
-    }
-
     // Validate collection interval
     if config.collection_interval_seconds == 0 {
         bail!("Collection interval cannot be 0");

dashboard/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "cm-dashboard"
-version = "0.1.56"
+version = "0.1.61"
 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,
         })
     }
 
@@ -191,6 +191,17 @@ impl Dashboard {
                         break;
                     }
                 }
+
+                // Render UI immediately after handling input for responsive feedback
+                if let Some(ref mut terminal) = self.terminal {
+                    if let Some(ref mut tui_app) = self.tui_app {
+                        if let Err(e) = terminal.draw(|frame| {
+                            tui_app.render(frame, &self.metric_store);
+                        }) {
+                            error!("Error rendering TUI after input: {}", e);
+                        }
+                    }
+                }
             }
 
             // Check for new metrics
@@ -247,7 +258,7 @@ 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/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
                 }
             })

dashboard/src/ui/mod.rs

@@ -90,10 +90,13 @@ pub struct TuiApp {
     user_navigated_away: bool,
     /// Dashboard configuration
     config: DashboardConfig,
+    /// Cached localhost hostname to avoid repeated system calls
+    localhost: String,
 }
 
 impl TuiApp {
     pub fn new(config: DashboardConfig) -> Self {
+        let localhost = gethostname::gethostname().to_string_lossy().to_string();
         let mut app = Self {
             host_widgets: HashMap::new(),
             current_host: None,
@@ -102,6 +105,7 @@ impl TuiApp {
             should_quit: false,
             user_navigated_away: false,
             config,
+            localhost,
         };
         
         // Sort predefined hosts
@@ -131,31 +135,31 @@ impl TuiApp {
             // Only update widgets if we have metrics for this host
             let all_metrics = metric_store.get_metrics_for_host(&hostname);
             if !all_metrics.is_empty() {
-                // Get metrics first while hostname is borrowed
-                let cpu_metrics: Vec<&Metric> = all_metrics
-                    .iter()
-                    .filter(|m| {
-                        m.name.starts_with("cpu_")
-                            || m.name.contains("c_state_")
-                            || m.name.starts_with("process_top_")
-                    })
-                    .copied()
-                    .collect();
-                let memory_metrics: Vec<&Metric> = all_metrics
-                    .iter()
-                    .filter(|m| m.name.starts_with("memory_") || m.name.starts_with("disk_tmp_"))
-                    .copied()
-                    .collect();
-                let service_metrics: Vec<&Metric> = all_metrics
-                    .iter()
-                    .filter(|m| m.name.starts_with("service_"))
-                    .copied()
-                    .collect();
-                let all_backup_metrics: Vec<&Metric> = all_metrics
-                    .iter()
-                    .filter(|m| m.name.starts_with("backup_"))
-                    .copied()
-                    .collect();
+                // Single pass metric categorization for better performance
+                let mut cpu_metrics = Vec::new();
+                let mut memory_metrics = Vec::new();
+                let mut service_metrics = Vec::new();
+                let mut backup_metrics = Vec::new();
+                let mut nixos_metrics = Vec::new();
+                let mut disk_metrics = Vec::new();
+                
+                for metric in all_metrics {
+                    if metric.name.starts_with("cpu_") 
+                        || metric.name.contains("c_state_") 
+                        || metric.name.starts_with("process_top_") {
+                        cpu_metrics.push(metric);
+                    } else if metric.name.starts_with("memory_") || metric.name.starts_with("disk_tmp_") {
+                        memory_metrics.push(metric);
+                    } else if metric.name.starts_with("service_") {
+                        service_metrics.push(metric);
+                    } else if metric.name.starts_with("backup_") {
+                        backup_metrics.push(metric);
+                    } else if metric.name == "system_nixos_build" || metric.name == "system_active_users" || metric.name == "agent_version" {
+                        nixos_metrics.push(metric);
+                    } else if metric.name.starts_with("disk_") {
+                        disk_metrics.push(metric);
+                    }
+                }
 
                 // Clear completed transitions first
                 self.clear_completed_transitions(&hostname, &service_metrics);
@@ -166,21 +170,7 @@ impl TuiApp {
                 // Collect all system metrics (CPU, memory, NixOS, disk/storage)
                 let mut system_metrics = cpu_metrics;
                 system_metrics.extend(memory_metrics);
-                
-                // Add NixOS metrics - using exact matching for build display fix
-                let nixos_metrics: Vec<&Metric> = all_metrics
-                    .iter()
-                    .filter(|m| m.name == "system_nixos_build" || m.name == "system_active_users" || m.name == "agent_version")
-                    .copied()
-                    .collect();
                 system_metrics.extend(nixos_metrics);
-                
-                // Add disk/storage metrics
-                let disk_metrics: Vec<&Metric> = all_metrics
-                    .iter()
-                    .filter(|m| m.name.starts_with("disk_"))
-                    .copied()
-                    .collect();
                 system_metrics.extend(disk_metrics);
 
                 host_widgets.system_widget.update_from_metrics(&system_metrics);
@@ -189,7 +179,7 @@ impl TuiApp {
                     .update_from_metrics(&service_metrics);
                 host_widgets
                     .backup_widget
-                    .update_from_metrics(&all_backup_metrics);
+                    .update_from_metrics(&backup_metrics);
 
                 host_widgets.last_update = Some(Instant::now());
             }
@@ -221,13 +211,12 @@ impl TuiApp {
         self.available_hosts = all_hosts;
         
         // Get the current hostname (localhost) for auto-selection
-        let localhost = gethostname::gethostname().to_string_lossy().to_string();
         if !self.available_hosts.is_empty() {
-            if self.available_hosts.contains(&localhost) && !self.user_navigated_away {
+            if self.available_hosts.contains(&self.localhost) && !self.user_navigated_away {
                 // Localhost is available and user hasn't navigated away - switch to it
-                self.current_host = Some(localhost.clone());
+                self.current_host = Some(self.localhost.clone());
                 // Find the actual index of localhost in the sorted list
-                self.host_index = self.available_hosts.iter().position(|h| h == &localhost).unwrap_or(0);
+                self.host_index = self.available_hosts.iter().position(|h| h == &self.localhost).unwrap_or(0);
             } else if self.current_host.is_none() {
                 // No current host - select first available (which is localhost if available)
                 self.current_host = Some(self.available_hosts[0].clone());
@@ -424,9 +413,8 @@ impl TuiApp {
         self.current_host = Some(self.available_hosts[self.host_index].clone());
         
         // Check if user navigated away from localhost
-        let localhost = gethostname::gethostname().to_string_lossy().to_string();
         if let Some(ref current) = self.current_host {
-            if current != &localhost {
+            if current != &self.localhost {
                 self.user_navigated_away = true;
             } else {
                 self.user_navigated_away = false; // User navigated back to localhost

shared/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "cm-dashboard-shared"
-version = "0.1.56"
+version = "0.1.61"
 edition = "2021"
 
 [dependencies]