Improve notification behavior during startup and recovery

Fix notification issues for better operational experience:

Startup Notification Suppression:
- Suppress notifications for transitions from Status::Unknown during agent/server startup
- Prevents notification spam when services transition from Unknown to Warning/Critical on restart
- Only real status changes (not initial discovery) trigger notifications
- Maintains alerting for actual service state changes after startup

Recovery Notification Refinement:
- Recovery notifications only sent when ALL services reach OK status
- Individual service recoveries suppressed if other services still have problems
- Ensures recovery notifications indicate complete system health restoration
- Prevents premature celebration when partial recoveries occur

Result: Clean startup experience without false alerts and meaningful recovery
notifications that truly indicate full system health restoration.

Bump version to v0.1.48

Cargo.lock

@@ -270,7 +270,7 @@ checksum = "a1d728cc89cf3aee9ff92b05e62b19ee65a02b5702cff7d5a377e32c6ae29d8d"
 
 [[package]]
 name = "cm-dashboard"
-version = "0.1.45"
+version = "0.1.47"
 dependencies = [
  "anyhow",
  "chrono",
@@ -291,7 +291,7 @@ dependencies = [
 
 [[package]]
 name = "cm-dashboard-agent"
-version = "0.1.45"
+version = "0.1.47"
 dependencies = [
  "anyhow",
  "async-trait",
@@ -314,7 +314,7 @@ dependencies = [
 
 [[package]]
 name = "cm-dashboard-shared"
-version = "0.1.45"
+version = "0.1.47"
 dependencies = [
  "chrono",
  "serde",

agent/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "cm-dashboard-agent"
-version = "0.1.46"
+version = "0.1.48"
 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
-            if matches!(action, ServiceAction::UserStart) {
-                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);
-                }
-            }
+            // Note: User-stopped flag will be cleared by systemd collector 
+            // when service actually reaches 'active' state, not here
         } 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/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
-        if !recovery_changes.is_empty() {
+        // Show recoveries only if host status is now OK (all services recovered)
+        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 = "0.1.48"
 edition = "2021"
 
 [dependencies]

dashboard/src/ui/mod.rs

@@ -302,7 +302,7 @@ ssh -tt {}@{} 'bash -ic {}'",
                             .arg("-h") 
                             .arg("80%")
                             .arg("-t")
-                            .arg(format!("Logs: {}.service", service_name))
+                            .arg(format!("Logs: {}", service_name))
                             .arg(&journalctl_command)
                             .spawn()
                             .ok(); // Ignore errors, tmux will handle them

shared/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "cm-dashboard-shared"
-version = "0.1.46"
+version = "0.1.48"
 edition = "2021"
 
 [dependencies]