Implement WakeOnLAN functionality and offline status handling

- Add WakeOnLAN support for offline hosts using 'w' key
- Configure MAC addresses for all infrastructure hosts
- Implement Status::Offline for disconnected hosts
- Exclude offline hosts from status aggregation to prevent false alerts
- Update versions to 0.1.55

CLAUDE.md

@@ -20,12 +20,28 @@ A high-performance Rust-based TUI dashboard for monitoring CMTEC infrastructure.
 - Persistent storage survives agent restarts
 - Automatic flag clearing when services are restarted via dashboard
 
+### Custom Service Logs
+- Configure service-specific log file paths per host in dashboard config
+- Press `L` on any service to view custom log files via `tail -f`
+- Configuration format in dashboard config:
+```toml
+[service_logs]
+hostname1 = [
+  { service_name = "nginx", log_file_path = "/var/log/nginx/access.log" },
+  { service_name = "app", log_file_path = "/var/log/myapp/app.log" }
+]
+hostname2 = [
+  { service_name = "database", log_file_path = "/var/log/postgres/postgres.log" }
+]
+```
+
 ### Service Management
 - **Direct Control**: Arrow keys (↑↓) or vim keys (j/k) navigate services
 - **Service Actions**: 
   - `s` - Start service (sends UserStart command)
   - `S` - Stop service (sends UserStop command)
   - `J` - Show service logs (journalctl in tmux popup)
+  - `L` - Show custom log files (tail -f custom paths in tmux popup)
   - `R` - Rebuild current host
 - **Visual Status**: Green ● (active), Yellow ◐ (inactive), Red ◯ (failed)
 - **Transitional Icons**: Blue arrows during operations
@@ -34,6 +50,7 @@ A high-performance Rust-based TUI dashboard for monitoring CMTEC infrastructure.
 - **Tab**: Switch between hosts
 - **↑↓ or j/k**: Select services
 - **J**: Show service logs (journalctl)
+- **L**: Show custom log files
 - **q**: Quit dashboard
 
 ## Core Architecture Principles

Cargo.lock

@@ -270,7 +270,7 @@ checksum = "a1d728cc89cf3aee9ff92b05e62b19ee65a02b5702cff7d5a377e32c6ae29d8d"
 
 [[package]]
 name = "cm-dashboard"
-version = "0.1.45"
+version = "0.1.55"
 dependencies = [
  "anyhow",
  "chrono",
@@ -286,12 +286,13 @@ dependencies = [
  "toml",
  "tracing",
  "tracing-subscriber",
+ "wake-on-lan",
  "zmq",
 ]
 
 [[package]]
 name = "cm-dashboard-agent"
-version = "0.1.45"
+version = "0.1.55"
 dependencies = [
  "anyhow",
  "async-trait",
@@ -314,7 +315,7 @@ dependencies = [
 
 [[package]]
 name = "cm-dashboard-shared"
-version = "0.1.45"
+version = "0.1.55"
 dependencies = [
  "chrono",
  "serde",
@@ -2064,6 +2065,12 @@ version = "0.9.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "0b928f33d975fc6ad9f86c8f283853ad26bdd5b10b7f1542aa2fa15e2289105a"
 
+[[package]]
+name = "wake-on-lan"
+version = "0.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1ccf60b60ad7e5b1b37372c5134cbcab4db0706c231d212e0c643a077462bc8f"
+
 [[package]]
 name = "walkdir"
 version = "2.5.0"

agent/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "cm-dashboard-agent"
-version = "0.1.46"
+version = "0.1.55"
 edition = "2021"
 
 [dependencies]

agent/src/agent.rs

@@ -180,6 +180,9 @@ impl Agent {
         let version_metric = self.get_agent_version_metric();
         metrics.push(version_metric);
 
+        // Check for user-stopped services that are now active and clear their flags
+        self.clear_user_stopped_flags_for_active_services(&metrics);
+
         if metrics.is_empty() {
             debug!("No metrics to broadcast");
             return Ok(());
@@ -315,16 +318,8 @@ impl Agent {
                 debug!("stdout: {}", String::from_utf8_lossy(&output.stdout));
             }
             
-            // Clear user-stopped flag AFTER successful start command
+            // Note: User-stopped flag will be cleared by systemd collector 
-            if matches!(action, ServiceAction::UserStart) {
+            // when service actually reaches 'active' state, not here
-                info!("Clearing user-stopped flag for service '{}' after successful start", service_name);
-                if let Err(e) = self.service_tracker.clear_user_stopped(service_name) {
-                    error!("Failed to clear user-stopped flag: {}", e);
-                } else {
-                    // Sync to global tracker
-                    UserStoppedServiceTracker::update_global(&self.service_tracker);
-                }
-            }
         } else {
             let stderr = String::from_utf8_lossy(&output.stderr);
             error!("Service {} {} failed: {}", service_name, action_str, stderr);
@@ -344,4 +339,33 @@ impl Agent {
         Ok(())
     }
 
+    /// Check metrics for user-stopped services that are now active and clear their flags
+    fn clear_user_stopped_flags_for_active_services(&mut self, metrics: &[Metric]) {
+        for metric in metrics {
+            // Look for service status metrics that are active
+            if metric.name.starts_with("service_") && metric.name.ends_with("_status") {
+                if let MetricValue::String(status) = &metric.value {
+                    if status == "active" {
+                        // Extract service name from metric name (service_nginx_status -> nginx)
+                        let service_name = metric.name
+                            .strip_prefix("service_")
+                            .and_then(|s| s.strip_suffix("_status"))
+                            .unwrap_or("");
+                        
+                        if !service_name.is_empty() && UserStoppedServiceTracker::is_service_user_stopped(service_name) {
+                            info!("Service '{}' is now active - clearing user-stopped flag", service_name);
+                            if let Err(e) = self.service_tracker.clear_user_stopped(service_name) {
+                                error!("Failed to clear user-stopped flag for '{}': {}", service_name, e);
+                            } else {
+                                // Sync to global tracker
+                                UserStoppedServiceTracker::update_global(&self.service_tracker);
+                                debug!("Cleared user-stopped flag for service '{}'", service_name);
+                            }
+                        }
+                    }
+                }
+            }
+        }
+    }
+
 }

agent/src/collectors/backup.rs

@@ -140,6 +140,7 @@ impl Collector for BackupCollector {
                 Status::Warning => "warning".to_string(),
                 Status::Critical => "critical".to_string(),
                 Status::Unknown => "unknown".to_string(),
+                Status::Offline => "offline".to_string(),
             }),
             status: overall_status,
             timestamp,
@@ -202,6 +203,7 @@ impl Collector for BackupCollector {
                     Status::Warning => "warning".to_string(),
                     Status::Critical => "critical".to_string(),
                     Status::Unknown => "unknown".to_string(),
+                    Status::Offline => "offline".to_string(),
                 }),
                 status: service_status,
                 timestamp,

agent/src/collectors/systemd.rs

@@ -357,7 +357,15 @@ impl SystemdCollector {
     /// Calculate service status, taking user-stopped services into account
     fn calculate_service_status(&self, service_name: &str, active_status: &str) -> Status {
         match active_status.to_lowercase().as_str() {
-            "active" => Status::Ok,
+            "active" => {
+                // If service is now active and was marked as user-stopped, clear the flag
+                if UserStoppedServiceTracker::is_service_user_stopped(service_name) {
+                    debug!("Service '{}' is now active - clearing user-stopped flag", service_name);
+                    // Note: We can't directly clear here because this is a read-only context
+                    // The agent will need to handle this differently
+                }
+                Status::Ok
+            },
             "inactive" | "dead" => {
                 // Check if this service was stopped by user action
                 if UserStoppedServiceTracker::is_service_user_stopped(service_name) {
@@ -368,7 +376,15 @@ impl SystemdCollector {
                 }
             },
             "failed" | "error" => Status::Critical,
-            "activating" | "deactivating" | "reloading" | "start" | "stop" | "restart" => Status::Pending,
+            "activating" | "deactivating" | "reloading" | "start" | "stop" | "restart" => {
+                // For user-stopped services that are transitioning, keep them as OK during transition
+                if UserStoppedServiceTracker::is_service_user_stopped(service_name) {
+                    debug!("Service '{}' is transitioning but was user-stopped - treating as OK", service_name);
+                    Status::Ok
+                } else {
+                    Status::Pending
+                }
+            },
             _ => Status::Unknown,
         }
     }

agent/src/status/mod.rs

@@ -272,11 +272,13 @@ impl HostStatusManager {
     /// Check if a status change is significant enough for notification
     fn is_significant_change(&self, old_status: Status, new_status: Status) -> bool {
         match (old_status, new_status) {
-            // Always notify on problems
+            // Don't notify on transitions from Unknown (startup/restart scenario)
+            (Status::Unknown, _) => false,
+            // Always notify on problems (but not from Unknown)
             (_, Status::Warning) | (_, Status::Critical) => true,
             // Only notify on recovery if it's from a problem state to OK and all services are OK
             (Status::Warning | Status::Critical, Status::Ok) => self.current_host_status == Status::Ok,
-            // Don't notify on startup or other transitions
+            // Don't notify on other transitions
             _ => false,
         }
     }
@@ -374,8 +376,8 @@ impl HostStatusManager {
             details.push('\n');
         }
 
-        // Show recoveries
+        // Show recoveries only if host status is now OK (all services recovered)
-        if !recovery_changes.is_empty() {
+        if !recovery_changes.is_empty() && aggregated.host_status_final == Status::Ok {
             details.push_str(&format!("✅ RECOVERIES ({}):\n", recovery_changes.len()));
             for change in recovery_changes {
                 details.push_str(&format!("  {}\n", change));

dashboard/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "cm-dashboard"
-version = "0.1.46"
+version = "0.1.55"
 edition = "2021"
 
 [dependencies]
@@ -19,3 +19,4 @@ ratatui = { workspace = true }
 crossterm = { workspace = true }
 toml = { workspace = true }
 gethostname = { workspace = true }
+wake-on-lan = "0.2"

dashboard/src/app.rs

@@ -67,8 +67,8 @@ impl Dashboard {
             }
         };
 
-        // Connect to predefined hosts from configuration
+        // Connect to configured hosts from configuration
-        let hosts = config.hosts.predefined_hosts.clone();
+        let hosts: Vec<String> = config.hosts.keys().cloned().collect();
 
         // Try to connect to hosts but don't fail if none are available
         match zmq_consumer.connect_to_predefined_hosts(&hosts).await {

dashboard/src/config/mod.rs

@@ -6,9 +6,10 @@ use std::path::Path;
 #[derive(Debug, Clone, Serialize, Deserialize)]
 pub struct DashboardConfig {
     pub zmq: ZmqConfig,
-    pub hosts: HostsConfig,
+    pub hosts: std::collections::HashMap<String, HostDetails>,
     pub system: SystemConfig,
     pub ssh: SshConfig,
+    pub service_logs: std::collections::HashMap<String, Vec<ServiceLogConfig>>,
 }
 
 /// ZMQ consumer configuration
@@ -17,10 +18,10 @@ pub struct ZmqConfig {
     pub subscriber_ports: Vec<u16>,
 }
 
-/// Hosts configuration
+/// Individual host configuration details
 #[derive(Debug, Clone, Serialize, Deserialize)]
-pub struct HostsConfig {
+pub struct HostDetails {
-    pub predefined_hosts: Vec<String>,
+    pub mac_address: Option<String>,
 }
 
 /// System configuration
@@ -39,6 +40,13 @@ pub struct SshConfig {
     pub rebuild_alias: String,
 }
 
+/// Service log file configuration per host
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct ServiceLogConfig {
+    pub service_name: String,
+    pub log_file_path: String,
+}
+
 impl DashboardConfig {
     pub fn load_from_file<P: AsRef<Path>>(path: P) -> Result<Self> {
         let path = path.as_ref();
@@ -60,8 +68,3 @@ impl Default for ZmqConfig {
     }
 }
 
-impl Default for HostsConfig {
-    fn default() -> Self {
-        panic!("Dashboard configuration must be loaded from file - no hardcoded defaults allowed")
-    }
-}

dashboard/src/ui/mod.rs

@@ -9,6 +9,7 @@ use ratatui::{
 use std::collections::HashMap;
 use std::time::Instant;
 use tracing::info;
+use wake_on_lan::MagicPacket;
 
 pub mod theme;
 pub mod widgets;
@@ -93,15 +94,25 @@ pub struct TuiApp {
 
 impl TuiApp {
     pub fn new(config: DashboardConfig) -> Self {
-        Self {
+        let mut app = Self {
             host_widgets: HashMap::new(),
             current_host: None,
-            available_hosts: Vec::new(),
+            available_hosts: config.hosts.keys().cloned().collect(),
             host_index: 0,
             should_quit: false,
             user_navigated_away: false,
             config,
+        };
+        
+        // Sort predefined hosts
+        app.available_hosts.sort();
+        
+        // Initialize with first host if available
+        if !app.available_hosts.is_empty() {
+            app.current_host = Some(app.available_hosts[0].clone());
         }
+        
+        app
     }
 
     /// Get or create host widgets for the given hostname
@@ -186,21 +197,28 @@ impl TuiApp {
     }
 
     /// Update available hosts with localhost prioritization
-    pub fn update_hosts(&mut self, hosts: Vec<String>) {
+    pub fn update_hosts(&mut self, discovered_hosts: Vec<String>) {
-        // Sort hosts alphabetically
+        // Start with configured hosts (always visible)
-        let mut sorted_hosts = hosts.clone();
+        let mut all_hosts: Vec<String> = self.config.hosts.keys().cloned().collect();
+        
+        // Add any discovered hosts that aren't already configured
+        for host in discovered_hosts {
+            if !all_hosts.contains(&host) {
+                all_hosts.push(host);
+            }
+        }
         
         // Keep hosts that have pending transitions even if they're offline
         for (hostname, host_widgets) in &self.host_widgets {
             if !host_widgets.pending_service_transitions.is_empty() {
-                if !sorted_hosts.contains(hostname) {
+                if !all_hosts.contains(hostname) {
-                    sorted_hosts.push(hostname.clone());
+                    all_hosts.push(hostname.clone());
                 }
             }
         }
         
-        sorted_hosts.sort();
+        all_hosts.sort();
-        self.available_hosts = sorted_hosts;
+        self.available_hosts = all_hosts;
         
         // Get the current hostname (localhost) for auto-selection
         let localhost = gethostname::gethostname().to_string_lossy().to_string();
@@ -244,14 +262,9 @@ impl TuiApp {
                 KeyCode::Char('r') => {
                     // System rebuild command - works on any panel for current host
                     if let Some(hostname) = self.current_host.clone() {
-                        // Create command that shows CM Dashboard logo and then rebuilds
+                        // Create command that shows logo, rebuilds, and waits for user input
                         let logo_and_rebuild = format!(
-                            r"cat << 'EOF'
+                            "bash -c 'cat << \"EOF\"\nNixOS System Rebuild\nTarget: {}\n\nEOF\nssh -tt {}@{} \"bash -ic {}\"\necho\necho \"========================================\"\necho \"Rebuild completed. Press any key to close...\"\necho \"========================================\"\nread -n 1 -s\nexit'",
-NixOS System Rebuild
-Target: {}
-
-EOF
-ssh -tt {}@{} 'bash -ic {}'",
                             hostname,
                             self.config.ssh.rebuild_user,
                             hostname,
@@ -259,11 +272,10 @@ ssh -tt {}@{} 'bash -ic {}'",
                         );
                         
                         std::process::Command::new("tmux")
-                            .arg("display-popup")
+                            .arg("split-window")
-                            .arg("-w")
+                            .arg("-v")
-                            .arg("80%")
+                            .arg("-p")
-                            .arg("-h") 
+                            .arg("30")
-                            .arg("80%")
                             .arg(&logo_and_rebuild)
                             .spawn()
                             .ok(); // Ignore errors, tmux will handle them
@@ -286,28 +298,50 @@ ssh -tt {}@{} 'bash -ic {}'",
                     }
                 }
                 KeyCode::Char('J') => {
-                    // Show service logs via journalctl in tmux popup
+                    // Show service logs via journalctl in tmux split window
                     if let (Some(service_name), Some(hostname)) = (self.get_selected_service(), self.current_host.clone()) {
                         let journalctl_command = format!(
-                            "ssh -tt {}@{} 'journalctl -u {}.service -f --no-pager -n 50'",
+                            "bash -c \"ssh -tt {}@{} 'sudo journalctl -u {}.service -f --no-pager -n 50'; exit\"",
                             self.config.ssh.rebuild_user,
                             hostname,
                             service_name
                         );
                         
                         std::process::Command::new("tmux")
-                            .arg("display-popup")
+                            .arg("split-window")
-                            .arg("-w")
+                            .arg("-v")
-                            .arg("80%")
+                            .arg("-p")
-                            .arg("-h") 
+                            .arg("30")
-                            .arg("80%")
-                            .arg("-t")
-                            .arg(format!("Logs: {}.service", service_name))
                             .arg(&journalctl_command)
                             .spawn()
                             .ok(); // Ignore errors, tmux will handle them
                     }
                 }
+                KeyCode::Char('L') => {
+                    // Show custom service log file in tmux split window
+                    if let (Some(service_name), Some(hostname)) = (self.get_selected_service(), self.current_host.clone()) {
+                        // Check if this service has a custom log file configured
+                        if let Some(host_logs) = self.config.service_logs.get(&hostname) {
+                            if let Some(log_config) = host_logs.iter().find(|config| config.service_name == service_name) {
+                                let tail_command = format!(
+                                    "bash -c \"ssh -tt {}@{} 'sudo tail -n 50 -f {}'; exit\"",
+                                    self.config.ssh.rebuild_user,
+                                    hostname,
+                                    log_config.log_file_path
+                                );
+                                
+                                std::process::Command::new("tmux")
+                                    .arg("split-window")
+                                    .arg("-v")
+                                    .arg("-p")
+                                    .arg("30")
+                                    .arg(&tail_command)
+                                    .spawn()
+                                    .ok(); // Ignore errors, tmux will handle them
+                            }
+                        }
+                    }
+                }
                 KeyCode::Char('b') => {
                     // Trigger backup
                     if let Some(hostname) = self.current_host.clone() {
@@ -315,6 +349,33 @@ ssh -tt {}@{} 'bash -ic {}'",
                         return Ok(Some(UiCommand::TriggerBackup { hostname }));
                     }
                 }
+                KeyCode::Char('w') => {
+                    // Wake on LAN for offline hosts
+                    if let Some(hostname) = self.current_host.clone() {
+                        // Check if host has MAC address configured
+                        if let Some(host_details) = self.config.hosts.get(&hostname) {
+                            if let Some(mac_address) = &host_details.mac_address {
+                                // Parse MAC address and send WoL packet
+                                let mac_bytes = Self::parse_mac_address(mac_address);
+                                match mac_bytes {
+                                    Ok(mac) => {
+                                        match MagicPacket::new(&mac).send() {
+                                            Ok(_) => {
+                                                info!("WakeOnLAN packet sent successfully to {} ({})", hostname, mac_address);
+                                            }
+                                            Err(e) => {
+                                                tracing::error!("Failed to send WakeOnLAN packet to {}: {}", hostname, e);
+                                            }
+                                        }
+                                    }
+                                    Err(_) => {
+                                        tracing::error!("Invalid MAC address format for {}: {}", hostname, mac_address);
+                                    }
+                                }
+                            }
+                        }
+                    }
+                }
                 KeyCode::Tab => {
                     // Tab cycles to next host
                     self.navigate_host(1);
@@ -576,11 +637,14 @@ ssh -tt {}@{} 'bash -ic {}'",
             return;
         }
 
-        // Calculate worst-case status across all hosts
+        // Calculate worst-case status across all hosts (excluding offline)
         let mut worst_status = Status::Ok;
         for host in &self.available_hosts {
             let host_status = self.calculate_host_status(host, metric_store);
-            worst_status = Status::aggregate(&[worst_status, host_status]);
+            // Don't include offline hosts in status aggregation
+            if host_status != Status::Offline {
+                worst_status = Status::aggregate(&[worst_status, host_status]);
+            }
         }
 
         // Use the worst status color as background
@@ -658,7 +722,7 @@ ssh -tt {}@{} 'bash -ic {}'",
         let metrics = metric_store.get_metrics_for_host(hostname);
 
         if metrics.is_empty() {
-            return Status::Unknown;
+            return Status::Offline;
         }
 
         // First check if we have the aggregated host status summary from the agent
@@ -678,7 +742,8 @@ ssh -tt {}@{} 'bash -ic {}'",
                 Status::Warning => has_warning = true,
                 Status::Pending => has_pending = true,
                 Status::Ok => ok_count += 1,
-                Status::Unknown => {} // Ignore unknown for aggregation
+                Status::Unknown => {}, // Ignore unknown for aggregation
+                Status::Offline => {}, // Ignore offline for aggregation
             }
         }
 
@@ -718,6 +783,8 @@ ssh -tt {}@{} 'bash -ic {}'",
         shortcuts.push("r: Rebuild".to_string());
         shortcuts.push("s/S: Start/Stop".to_string());
         shortcuts.push("J: Logs".to_string());
+        shortcuts.push("L: Custom".to_string());
+        shortcuts.push("w: Wake".to_string());
         
         // Always show quit
         shortcuts.push("q: Quit".to_string());
@@ -756,5 +823,20 @@ ssh -tt {}@{} 'bash -ic {}'",
         }
     }
 
+    /// Parse MAC address string (e.g., "AA:BB:CC:DD:EE:FF") to [u8; 6]
+    fn parse_mac_address(mac_str: &str) -> Result<[u8; 6], &'static str> {
+        let parts: Vec<&str> = mac_str.split(':').collect();
+        if parts.len() != 6 {
+            return Err("MAC address must have 6 parts separated by colons");
+        }
 
+        let mut mac = [0u8; 6];
+        for (i, part) in parts.iter().enumerate() {
+            match u8::from_str_radix(part, 16) {
+                Ok(byte) => mac[i] = byte,
+                Err(_) => return Err("Invalid hexadecimal byte in MAC address"),
+            }
+        }
+        Ok(mac)
+    }
 }

dashboard/src/ui/theme.rs

@@ -147,6 +147,7 @@ impl Theme {
             Status::Warning => Self::warning(),
             Status::Critical => Self::error(),
             Status::Unknown => Self::muted_text(),
+            Status::Offline => Self::muted_text(), // Dark gray for offline
         }
     }
 
@@ -244,8 +245,9 @@ impl StatusIcons {
             Status::Ok => "●",
             Status::Pending => "◉", // Hollow circle for pending
             Status::Warning => "◐",
-            Status::Critical => "◯",
+            Status::Critical => "!",
             Status::Unknown => "?",
+            Status::Offline => "○", // Empty circle for offline
         }
     }
 
@@ -258,6 +260,7 @@ impl StatusIcons {
             Status::Warning => Theme::warning(),    // Yellow
             Status::Critical => Theme::error(),     // Red
             Status::Unknown => Theme::muted_text(), // Gray
+            Status::Offline => Theme::muted_text(), // Dark gray for offline
         };
 
         vec![

dashboard/src/ui/widgets/services.rs

@@ -146,6 +146,7 @@ impl ServicesWidget {
             Status::Warning => Theme::warning(),
             Status::Critical => Theme::error(),
             Status::Unknown => Theme::muted_text(),
+            Status::Offline => Theme::muted_text(),
         };
         
         (icon.to_string(), info.status.clone(), status_color)

shared/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "cm-dashboard-shared"
-version = "0.1.46"
+version = "0.1.55"
 edition = "2021"
 
 [dependencies]

shared/src/metrics.rs

@@ -87,6 +87,7 @@ pub enum Status {
     Warning,
     Critical,
     Unknown,
+    Offline,
 }
 
 impl Status {
@@ -190,6 +191,16 @@ impl HysteresisThresholds {
                     Status::Ok
                 }
             }
+            Status::Offline => {
+                // Host coming back online, use normal thresholds like first measurement
+                if value >= self.critical_high {
+                    Status::Critical
+                } else if value >= self.warning_high {
+                    Status::Warning
+                } else {
+                    Status::Ok
+                }
+            }
         }
     }
 }