Update version to 0.1.22 and fix system metric status calculation

- Fix /tmp usage status to use proper thresholds instead of hardcoded Ok status
- Fix wear level status to use configurable thresholds instead of hardcoded values
- Add dedicated tmp_status field to SystemWidget for proper /tmp status display
- Remove host-level hourglass icon during service operations
- Implement immediate service status updates after start/stop/restart commands
- Remove active users display and collection from NixOS section
- Fix immediate host status aggregation transmission to dashboard

Cargo.lock

@@ -270,7 +270,7 @@ checksum = "a1d728cc89cf3aee9ff92b05e62b19ee65a02b5702cff7d5a377e32c6ae29d8d"
 
 [[package]]
 name = "cm-dashboard"
-version = "0.1.18"
+version = "0.1.21"
 dependencies = [
  "anyhow",
  "chrono",
@@ -291,7 +291,7 @@ dependencies = [
 
 [[package]]
 name = "cm-dashboard-agent"
-version = "0.1.18"
+version = "0.1.21"
 dependencies = [
  "anyhow",
  "async-trait",
@@ -314,7 +314,7 @@ dependencies = [
 
 [[package]]
 name = "cm-dashboard-shared"
-version = "0.1.18"
+version = "0.1.21"
 dependencies = [
  "chrono",
  "serde",

agent/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "cm-dashboard-agent"
-version = "0.1.18"
+version = "0.1.22"
 edition = "2021"
 
 [dependencies]

agent/src/agent.rs

@@ -71,11 +71,11 @@ impl Agent {
             info!("Initial metric collection completed - all data cached and ready");
         }
 
-        // Separate intervals for collection and transmission
+        // Separate intervals for collection, transmission, and email notifications
         let mut collection_interval =
             interval(Duration::from_secs(self.config.collection_interval_seconds));
         let mut transmission_interval = interval(Duration::from_secs(self.config.zmq.transmission_interval_seconds));
-        let mut notification_interval = interval(Duration::from_secs(self.config.status_aggregation.notification_interval_seconds));
+        let mut notification_interval = interval(Duration::from_secs(self.config.notifications.aggregation_interval_seconds));
 
         loop {
             tokio::select! {
@@ -86,13 +86,13 @@ impl Agent {
                     }
                 }
                 _ = transmission_interval.tick() => {
-                    // Send all metrics via ZMQ every 1 second
+                    // Send all metrics via ZMQ (dashboard updates only)
                     if let Err(e) = self.broadcast_all_metrics().await {
                         error!("Failed to broadcast metrics: {}", e);
                     }
                 }
                 _ = notification_interval.tick() => {
-                    // Process batched notifications
+                    // Process batched email notifications (separate from dashboard updates)
                     if let Err(e) = self.host_status_manager.process_pending_notifications(&mut self.notification_manager).await {
                         error!("Failed to process pending notifications: {}", e);
                     }
@@ -127,8 +127,8 @@ impl Agent {
 
         info!("Force collected and cached {} metrics", metrics.len());
 
-        // Process metrics through status manager
+        // Process metrics through status manager (collect status data at startup)
-        self.process_metrics(&metrics).await;
+        let _status_changed = self.process_metrics(&metrics).await;
 
         Ok(())
     }
@@ -146,17 +146,24 @@ impl Agent {
 
         debug!("Collected and cached {} metrics", metrics.len());
 
-        // Process metrics through status manager
+        // Process metrics through status manager and trigger immediate transmission if status changed
-        self.process_metrics(&metrics).await;
+        let status_changed = self.process_metrics(&metrics).await;
+        
+        if status_changed {
+            info!("Status change detected - triggering immediate metric transmission");
+            if let Err(e) = self.broadcast_all_metrics().await {
+                error!("Failed to broadcast metrics after status change: {}", e);
+            }
+        }
 
         Ok(())
     }
 
     async fn broadcast_all_metrics(&mut self) -> Result<()> {
-        debug!("Broadcasting all metrics via ZMQ");
+        debug!("Broadcasting cached metrics via ZMQ");
 
-        // Get all current metrics from collectors
+        // Get cached metrics (no fresh collection)
-        let mut metrics = self.metric_manager.collect_all_metrics().await?;
+        let mut metrics = self.metric_manager.get_cached_metrics();
 
         // Add the host status summary metric from status manager
         let host_status_metric = self.host_status_manager.get_host_status_metric();
@@ -171,7 +178,7 @@ impl Agent {
             return Ok(());
         }
 
-        debug!("Broadcasting {} metrics (including host status summary)", metrics.len());
+        debug!("Broadcasting {} cached metrics (including host status summary)", metrics.len());
 
         // Create and send message with all current data
         let message = MetricMessage::new(self.hostname.clone(), metrics);
@@ -181,11 +188,15 @@ impl Agent {
         Ok(())
     }
 
-    async fn process_metrics(&mut self, metrics: &[Metric]) {
+    async fn process_metrics(&mut self, metrics: &[Metric]) -> bool {
+        let mut status_changed = false;
         for metric in metrics {
-            self.host_status_manager.process_metric(metric, &mut self.notification_manager).await;
+            if self.host_status_manager.process_metric(metric, &mut self.notification_manager).await {
+                status_changed = true;
             }
         }
+        status_changed
+    }
 
     /// Create agent version metric for cross-host version comparison
     fn get_agent_version_metric(&self) -> Metric {
@@ -259,7 +270,7 @@ impl Agent {
     }
 
     /// Handle systemd service control commands
-    async fn handle_service_control(&self, service_name: &str, action: &ServiceAction) -> Result<()> {
+    async fn handle_service_control(&mut self, service_name: &str, action: &ServiceAction) -> Result<()> {
         let action_str = match action {
             ServiceAction::Start => "start",
             ServiceAction::Stop => "stop", 
@@ -289,9 +300,12 @@ impl Agent {
 
         // Force refresh metrics after service control to update service status
         if matches!(action, ServiceAction::Start | ServiceAction::Stop | ServiceAction::Restart) {
-            info!("Triggering metric refresh after service control");
+            info!("Triggering immediate metric refresh after service control");
-            // Note: We can't call self.collect_metrics_only() here due to borrowing issues
+            if let Err(e) = self.collect_metrics_only().await {
-            // The next metric collection cycle will pick up the changes
+                error!("Failed to refresh metrics after service control: {}", e);
+            } else {
+                info!("Service status refreshed immediately after {} {}", action_str, service_name);
+            }
         }
 
         Ok(())

agent/src/collectors/disk.rs

@@ -556,8 +556,8 @@ impl Collector for DiskCollector {
 
                 // Drive wear level (for SSDs)
                 if let Some(wear) = drive.wear_level {
-                    let wear_status = if wear >= 90.0 { Status::Critical }
+                    let wear_status = if wear >= self.config.wear_critical_percent { Status::Critical }
-                                     else if wear >= 80.0 { Status::Warning }
+                                     else if wear >= self.config.wear_warning_percent { Status::Warning }
                                      else { Status::Ok };
                     
                     metrics.push(Metric {

agent/src/collectors/memory.rs

@@ -187,7 +187,7 @@ impl MemoryCollector {
         }
 
         // Monitor tmpfs (/tmp) usage
-        if let Ok(tmpfs_metrics) = self.get_tmpfs_metrics() {
+        if let Ok(tmpfs_metrics) = self.get_tmpfs_metrics(status_tracker) {
             metrics.extend(tmpfs_metrics);
         }
 
@@ -195,7 +195,7 @@ impl MemoryCollector {
     }
 
     /// Get tmpfs (/tmp) usage metrics  
-    fn get_tmpfs_metrics(&self) -> Result<Vec<Metric>, CollectorError> {
+    fn get_tmpfs_metrics(&self, status_tracker: &mut StatusTracker) -> Result<Vec<Metric>, CollectorError> {
         use std::process::Command;
         
         let output = Command::new("df")
@@ -249,12 +249,15 @@ impl MemoryCollector {
         let mut metrics = Vec::new();
         let timestamp = chrono::Utc::now().timestamp() as u64;
 
+        // Calculate status using same thresholds as main memory
+        let tmp_status = self.calculate_usage_status("memory_tmp_usage_percent", usage_percent, status_tracker);
+        
         metrics.push(Metric {
             name: "memory_tmp_usage_percent".to_string(),
             value: MetricValue::Float(usage_percent),
             unit: Some("%".to_string()),
             description: Some("tmpfs /tmp usage percentage".to_string()),
-            status: Status::Ok,
+            status: tmp_status,
             timestamp,
         });
 

agent/src/collectors/nixos.rs

@@ -10,7 +10,6 @@ use crate::config::NixOSConfig;
 /// 
 /// Collects NixOS-specific system information including:
 /// - NixOS version and build information
-/// - Currently active/logged in users
 pub struct NixOSCollector {
 }
 
@@ -19,31 +18,6 @@ impl NixOSCollector {
         Self {}
     }
 
-    /// Get NixOS build information
-    fn get_nixos_build_info(&self) -> Result<String, Box<dyn std::error::Error>> {
-        // Get nixos-version output directly
-        let output = Command::new("nixos-version").output()?;
-        
-        if !output.status.success() {
-            return Err("nixos-version command failed".into());
-        }
-
-        let version_line = String::from_utf8_lossy(&output.stdout);
-        let version = version_line.trim();
-        
-        if version.is_empty() {
-            return Err("Empty nixos-version output".into());
-        }
-        
-        // Remove codename part (e.g., "(Warbler)")
-        let clean_version = if let Some(pos) = version.find(" (") {
-            version[..pos].to_string()
-        } else {
-            version.to_string()
-        };
-        
-        Ok(clean_version)
-    }
 
     /// Get agent hash from binary path
     fn get_agent_hash(&self) -> Result<String, Box<dyn std::error::Error>> {
@@ -90,27 +64,6 @@ impl NixOSCollector {
         Err("Could not extract hash from nix store path".into())
     }
 
-    /// Get currently active users
-    fn get_active_users(&self) -> Result<Vec<String>, Box<dyn std::error::Error>> {
-        let output = Command::new("who").output()?;
-        
-        if !output.status.success() {
-            return Err("who command failed".into());
-        }
-
-        let who_output = String::from_utf8_lossy(&output.stdout);
-        let mut users = std::collections::HashSet::new();
-
-        for line in who_output.lines() {
-            if let Some(username) = line.split_whitespace().next() {
-                if !username.is_empty() {
-                    users.insert(username.to_string());
-                }
-            }
-        }
-
-        Ok(users.into_iter().collect())
-    }
 }
 
 #[async_trait]
@@ -146,31 +99,6 @@ impl Collector for NixOSCollector {
             }
         }
 
-        // Collect active users
-        match self.get_active_users() {
-            Ok(users) => {
-                let users_str = users.join(", ");
-                metrics.push(Metric {
-                    name: "system_active_users".to_string(),
-                    value: MetricValue::String(users_str),
-                    unit: None,
-                    description: Some("Currently active users".to_string()),
-                    status: Status::Ok,
-                    timestamp,
-                });
-            }
-            Err(e) => {
-                debug!("Failed to get active users: {}", e);
-                metrics.push(Metric {
-                    name: "system_active_users".to_string(),
-                    value: MetricValue::String("unknown".to_string()),
-                    unit: None,
-                    description: Some("Active users (failed to detect)".to_string()),
-                    status: Status::Unknown,
-                    timestamp,
-                });
-            }
-        }
 
         // Collect config hash
         match self.get_config_hash() {

agent/src/config/mod.rs

@@ -143,6 +143,8 @@ pub struct NotificationConfig {
     pub from_email: String,
     pub to_email: String,
     pub rate_limit_minutes: u64,
+    /// Email notification batching interval in seconds (default: 60)
+    pub aggregation_interval_seconds: u64,
 }
 
 

agent/src/metrics/mod.rs

@@ -21,6 +21,7 @@ struct TimedCollector {
 pub struct MetricCollectionManager {
     collectors: Vec<TimedCollector>,
     status_tracker: StatusTracker,
+    cached_metrics: Vec<Metric>,
 }
 
 impl MetricCollectionManager {
@@ -177,6 +178,7 @@ impl MetricCollectionManager {
         Ok(Self {
             collectors,
             status_tracker: StatusTracker::new(),
+            cached_metrics: Vec::new(),
         })
     }
 
@@ -198,6 +200,9 @@ impl MetricCollectionManager {
                 }
             }
         }
+        
+        // Cache the collected metrics
+        self.cached_metrics = all_metrics.clone();
         Ok(all_metrics)
     }
 
@@ -231,6 +236,18 @@ impl MetricCollectionManager {
                 }
             }
         }
+        
+        // Update cache with newly collected metrics
+        if !all_metrics.is_empty() {
+            // Merge new metrics with cached metrics (replace by name)
+            for new_metric in &all_metrics {
+                // Remove any existing metric with the same name
+                self.cached_metrics.retain(|cached| cached.name != new_metric.name);
+                // Add the new metric
+                self.cached_metrics.push(new_metric.clone());
+            }
+        }
+        
         Ok(all_metrics)
     }
 
@@ -239,4 +256,9 @@ impl MetricCollectionManager {
         self.collect_metrics_timed().await
     }
     
+    /// Get cached metrics without triggering fresh collection
+    pub fn get_cached_metrics(&self) -> Vec<Metric> {
+        self.cached_metrics.clone()
+    }
+
 }

agent/src/status/mod.rs

@@ -9,7 +9,6 @@ use chrono::Utc;
 pub struct HostStatusConfig {
     pub enabled: bool,
     pub aggregation_method: String, // "worst_case"
-    pub notification_interval_seconds: u64,
 }
 
 impl Default for HostStatusConfig {
@@ -17,7 +16,6 @@ impl Default for HostStatusConfig {
         Self {
             enabled: true,
             aggregation_method: "worst_case".to_string(),
-            notification_interval_seconds: 30,
         }
     }
 }
@@ -160,25 +158,62 @@ impl HostStatusManager {
 
 
 
-    /// Process a metric - updates status (notifications handled separately via batching)
+    /// Process a metric - updates status and queues for aggregated notifications if status changed
-    pub async fn process_metric(&mut self, metric: &Metric, _notification_manager: &mut crate::notifications::NotificationManager) {
+    pub async fn process_metric(&mut self, metric: &Metric, _notification_manager: &mut crate::notifications::NotificationManager) -> bool {
-        // Just update status - notifications are handled by process_pending_notifications
+        let old_service_status = self.service_statuses.get(&metric.name).copied();
-        self.update_service_status(metric.name.clone(), metric.status);
+        let old_host_status = self.current_host_status;
+        let new_service_status = metric.status;
+        
+        // Update status (this recalculates host status internally)
+        self.update_service_status(metric.name.clone(), new_service_status);
+        
+        let new_host_status = self.current_host_status;
+        let mut status_changed = false;
+        
+        // Check if service status actually changed (ignore first-time status setting)
+        if let Some(old_service_status) = old_service_status {
+            if old_service_status != new_service_status {
+                debug!("Service status change detected for {}: {:?} -> {:?}", metric.name, old_service_status, new_service_status);
+                
+                // Queue change for aggregated notification (not immediate)
+                self.queue_status_change(&metric.name, old_service_status, new_service_status);
+                
+                status_changed = true;
+            }
+        } else {
+            debug!("Initial status set for {}: {:?}", metric.name, new_service_status);
         }
         
-    /// Process pending notifications - call this at notification intervals
+        // Check if host status changed (this should trigger immediate transmission)
+        if old_host_status != new_host_status {
+            debug!("Host status change detected: {:?} -> {:?}", old_host_status, new_host_status);
+            status_changed = true;
+        }
+        
+        status_changed // Return true if either service or host status changed
+    }
+
+    /// Queue status change for aggregated notification
+    fn queue_status_change(&mut self, metric_name: &str, old_status: Status, new_status: Status) {
+        // Add to pending changes for aggregated notification
+        let entry = self.pending_changes.entry(metric_name.to_string()).or_insert((old_status, old_status, 0));
+        entry.1 = new_status; // Update final status
+        entry.2 += 1; // Increment change count
+        
+        // Set batch start time if this is the first change
+        if self.batch_start_time.is_none() {
+            self.batch_start_time = Some(Instant::now());
+        }
+    }
+
+
+    /// Process pending notifications - legacy method, now rarely used
     pub async fn process_pending_notifications(&mut self, notification_manager: &mut crate::notifications::NotificationManager) -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
         if !self.config.enabled || self.pending_changes.is_empty() {
             return Ok(());
         }
 
-        let batch_start = self.batch_start_time.unwrap_or_else(Instant::now);
+        // Process notifications immediately without interval batching
-        let batch_duration = batch_start.elapsed();
-        
-        // Only process if enough time has passed
-        if batch_duration.as_secs() < self.config.notification_interval_seconds {
-            return Ok(());
-        }
 
         // Create aggregated status changes
         let aggregated = self.create_aggregated_changes();

dashboard/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "cm-dashboard"
-version = "0.1.18"
+version = "0.1.22"
 edition = "2021"
 
 [dependencies]

dashboard/src/main.rs

@@ -14,7 +14,7 @@ use app::Dashboard;
 
 /// Get hardcoded version
 fn get_version() -> &'static str {
-    "v0.1.18"
+    "v0.1.22"
 }
 
 /// Check if running inside tmux session

dashboard/src/ui/mod.rs

@@ -724,24 +724,9 @@ impl TuiApp {
                 spans.push(Span::styled(" ", Typography::title()));
             }
 
-            // Check if this host has a command status that affects the icon
+            // Always show normal status icon based on metrics (no command status at host level)
-            let (status_icon, status_color) = if let Some(host_widgets) = self.host_widgets.get(host) {
-                match &host_widgets.command_status {
-                    Some(CommandStatus::InProgress { .. }) => {
-                        // Show working indicator for in-progress commands
-                        ("⏳", Theme::highlight())
-                    }
-                    _ => {
-                        // Normal status icon based on metrics
             let host_status = self.calculate_host_status(host, metric_store);
-                        (StatusIcons::get_icon(host_status), Theme::status_color(host_status))
+            let (status_icon, status_color) = (StatusIcons::get_icon(host_status), Theme::status_color(host_status));
-                    }
-                }
-            } else {
-                // No host widgets yet, use normal status
-                let host_status = self.calculate_host_status(host, metric_store);
-                (StatusIcons::get_icon(host_status), Theme::status_color(host_status))
-            };
 
             // Add status icon
             spans.push(Span::styled(

dashboard/src/ui/widgets/system.rs

@@ -15,7 +15,6 @@ pub struct SystemWidget {
     // NixOS information
     nixos_build: Option<String>,
     config_hash: Option<String>,
-    active_users: Option<String>,
     agent_hash: Option<String>,
     
     // CPU metrics
@@ -33,6 +32,7 @@ pub struct SystemWidget {
     tmp_used_gb: Option<f32>,
     tmp_total_gb: Option<f32>,
     memory_status: Status,
+    tmp_status: Status,
     
     // Storage metrics (collected from disk metrics)
     storage_pools: Vec<StoragePool>,
@@ -66,7 +66,6 @@ impl SystemWidget {
         Self {
             nixos_build: None,
             config_hash: None,
-            active_users: None,
             agent_hash: None,
             cpu_load_1min: None,
             cpu_load_5min: None,
@@ -80,6 +79,7 @@ impl SystemWidget {
             tmp_used_gb: None,
             tmp_total_gb: None,
             memory_status: Status::Unknown,
+            tmp_status: Status::Unknown,
             storage_pools: Vec::new(),
             has_data: false,
         }
@@ -334,11 +334,6 @@ impl Widget for SystemWidget {
                         self.config_hash = Some(hash.clone());
                     }
                 }
-                "system_active_users" => {
-                    if let MetricValue::String(users) = &metric.value {
-                        self.active_users = Some(users.clone());
-                    }
-                }
                 "agent_version" => {
                     if let MetricValue::String(version) = &metric.value {
                         self.agent_hash = Some(version.clone());
@@ -390,6 +385,7 @@ impl Widget for SystemWidget {
                 "memory_tmp_usage_percent" => {
                     if let MetricValue::Float(usage) = metric.value {
                         self.tmp_usage_percent = Some(usage);
+                        self.tmp_status = metric.status.clone();
                     }
                 }
                 "memory_tmp_used_gb" => {
@@ -432,10 +428,6 @@ impl SystemWidget {
             Span::styled(format!("Agent: {}", agent_version_text), Typography::secondary())
         ]));
         
-        let users_text = self.active_users.as_deref().unwrap_or("unknown");
-        lines.push(Line::from(vec![
-            Span::styled(format!("Active users: {}", users_text), Typography::secondary())
-        ]));
 
         // CPU section
         lines.push(Line::from(vec![
@@ -472,7 +464,7 @@ impl SystemWidget {
             Span::styled("  └─ ", Typography::tree()),
         ];
         tmp_spans.extend(StatusIcons::create_status_spans(
-            self.memory_status.clone(),
+            self.tmp_status.clone(),
             &format!("/tmp: {}", tmp_text)
         ));
         lines.push(Line::from(tmp_spans));

shared/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "cm-dashboard-shared"
-version = "0.1.18"
+version = "0.1.22"
 edition = "2021"
 
 [dependencies]