Improve notification email format with detailed service groupings

agent/src/status/mod.rs

@@ -251,10 +251,32 @@ impl HostStatusManager {
             details: Some(self.format_aggregated_details(aggregated)),
         };
 
+        // Create a descriptive summary based on change types
+        let mut summary_parts = Vec::new();
+        let critical_count = aggregated.service_summaries.iter().filter(|s| s.final_status == Status::Critical).count();
+        let warning_count = aggregated.service_summaries.iter().filter(|s| s.final_status == Status::Warning).count();
+        let recovery_count = aggregated.service_summaries.iter().filter(|s| 
+            matches!((s.initial_status, s.final_status), (Status::Warning | Status::Critical, Status::Ok))
+        ).count();
+        let startup_count = aggregated.service_summaries.iter().filter(|s| 
+            matches!((s.initial_status, s.final_status), (Status::Unknown, Status::Ok | Status::Pending))
+        ).count();
+
+        if critical_count > 0 { summary_parts.push(format!("{} critical", critical_count)); }
+        if warning_count > 0 { summary_parts.push(format!("{} warning", warning_count)); }
+        if recovery_count > 0 { summary_parts.push(format!("{} recovered", recovery_count)); }
+        if startup_count > 0 { summary_parts.push(format!("{} started", startup_count)); }
+
+        let summary_text = if summary_parts.is_empty() {
+            format!("{} service changes", aggregated.service_summaries.len())
+        } else {
+            summary_parts.join(", ")
+        };
+
         // Create a dummy metric for the notification
         let summary_metric = Metric {
             name: "host_status_summary".to_string(),
-            value: cm_dashboard_shared::MetricValue::String(format!("{} services changed", aggregated.service_summaries.len())),
+            value: cm_dashboard_shared::MetricValue::String(summary_text),
             status: aggregated.host_status_final,
             timestamp: Utc::now().timestamp() as u64,
             description: Some("Aggregated status summary".to_string()),
@@ -282,32 +304,72 @@ impl HostStatusManager {
             ));
         }
 
-        details.push_str("Service Changes:\n");
+        // Group services by change type
+        let mut critical_changes = Vec::new();
+        let mut warning_changes = Vec::new();
+        let mut recovery_changes = Vec::new();
+        let mut startup_changes = Vec::new();
+        let mut other_changes = Vec::new();
+
         for summary in &aggregated.service_summaries {
-            if summary.significant_change {
-                let status_indicator = if summary.final_status == Status::Ok && 
-                    (summary.initial_status == Status::Warning || summary.initial_status == Status::Critical) {
-                    "✅"
-                } else if summary.final_status == Status::Warning {
-                    "🟡"
-                } else if summary.final_status == Status::Critical {
-                    "🔴"
-                } else {
-                    "ℹ️"
-                };
+            let change_info = format!(
+                "{}: {:?} → {:?}{}",
+                summary.service_name,
+                summary.initial_status,
+                summary.final_status,
+                if summary.change_count > 1 { format!(" ({} changes)", summary.change_count) } else { String::new() }
+            );
 
-                details.push_str(&format!(
-                    "  {} {}: {:?} → {:?}",
-                    status_indicator,
-                    summary.service_name,
-                    summary.initial_status,
-                    summary.final_status
-                ));
+            match (summary.initial_status, summary.final_status) {
+                (_, Status::Critical) => critical_changes.push(change_info),
+                (_, Status::Warning) => warning_changes.push(change_info),
+                (Status::Warning | Status::Critical, Status::Ok) => recovery_changes.push(change_info),
+                (Status::Unknown, Status::Ok | Status::Pending) => startup_changes.push(change_info),
+                _ => other_changes.push(change_info),
+            }
+        }
 
-                if summary.change_count > 1 {
-                    details.push_str(&format!(" ({} changes)", summary.change_count));
-                }
-                details.push('\n');
+        // Show critical problems first
+        if !critical_changes.is_empty() {
+            details.push_str(&format!("🔴 CRITICAL ISSUES ({}):\n", critical_changes.len()));
+            for change in critical_changes {
+                details.push_str(&format!("  {}\n", change));
+            }
+            details.push('\n');
+        }
+
+        // Show warnings
+        if !warning_changes.is_empty() {
+            details.push_str(&format!("🟡 WARNINGS ({}):\n", warning_changes.len()));
+            for change in warning_changes {
+                details.push_str(&format!("  {}\n", change));
+            }
+            details.push('\n');
+        }
+
+        // Show recoveries
+        if !recovery_changes.is_empty() {
+            details.push_str(&format!("✅ RECOVERIES ({}):\n", recovery_changes.len()));
+            for change in recovery_changes {
+                details.push_str(&format!("  {}\n", change));
+            }
+            details.push('\n');
+        }
+
+        // Show startups (usually not important but good to know)
+        if !startup_changes.is_empty() {
+            details.push_str(&format!("🟢 SERVICE STARTUPS ({}):\n", startup_changes.len()));
+            for change in startup_changes {
+                details.push_str(&format!("  {}\n", change));
+            }
+            details.push('\n');
+        }
+
+        // Show other changes
+        if !other_changes.is_empty() {
+            details.push_str(&format!("ℹ️ OTHER CHANGES ({}):\n", other_changes.len()));
+            for change in other_changes {
+                details.push_str(&format!("  {}\n", change));
             }
         }