Clean C-state display to show only CX format

- Strip suffixes like "_ACPI" from C-state names
- Display changes from "C3_ACPI:51%" to "C3:51%"
- Cleaner, more concise presentation

Bump version to v0.1.211

Co-Authored-By: Claude <noreply@anthropic.com>

.gitea/workflows/release.yml

@@ -113,13 +113,13 @@ jobs:
           NIX_HASH="sha256-$(python3 -c "import base64, binascii; print(base64.b64encode(binascii.unhexlify('$NEW_HASH')).decode())")"
           
           # Update the NixOS configuration
-          sed -i "s|version = \"v[^\"]*\"|version = \"$VERSION\"|" hosts/services/cm-dashboard.nix
-          sed -i "s|sha256 = \"sha256-[^\"]*\"|sha256 = \"$NIX_HASH\"|" hosts/services/cm-dashboard.nix
+          sed -i "s|version = \"v[^\"]*\"|version = \"$VERSION\"|" services/cm-dashboard.nix
+          sed -i "s|sha256 = \"sha256-[^\"]*\"|sha256 = \"$NIX_HASH\"|" services/cm-dashboard.nix
 
           # Commit and push changes
           git config user.name "Gitea Actions"
           git config user.email "actions@gitea.cmtec.se"
-          git add hosts/services/cm-dashboard.nix
+          git add services/cm-dashboard.nix
           git commit -m "Auto-update cm-dashboard to $VERSION
 
           - Update version to $VERSION with automated release

CLAUDE.md

@@ -7,6 +7,7 @@ A high-performance Rust-based TUI dashboard for monitoring CMTEC infrastructure.
 ## Current Features
 
 ### Core Functionality
+
 - **Real-time Monitoring**: CPU, RAM, Storage, and Service status
 - **Service Management**: Start/stop services with user-stopped tracking
 - **Multi-host Support**: Monitor multiple servers from single dashboard
@@ -14,6 +15,7 @@ A high-performance Rust-based TUI dashboard for monitoring CMTEC infrastructure.
 - **Backup Monitoring**: Borgbackup status and scheduling
 
 ### User-Stopped Service Tracking
+
 - Services stopped via dashboard are marked as "user-stopped"
 - User-stopped services report Status::OK instead of Warning
 - Prevents false alerts during intentional maintenance
@@ -21,9 +23,11 @@ A high-performance Rust-based TUI dashboard for monitoring CMTEC infrastructure.
 - 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 = [
@@ -36,6 +40,7 @@ hostname2 = [
 ```
 
 ### Service Management
+
 - **Direct Control**: Arrow keys (↑↓) or vim keys (j/k) navigate services
 - **Service Actions**:
   - `s` - Start service (sends UserStart command)
@@ -47,6 +52,7 @@ hostname2 = [
 - **Transitional Icons**: Blue arrows during operations
 
 ### Navigation
+
 - **Tab**: Switch between hosts
 - **↑↓ or j/k**: Select services
 - **s**: Start selected service (UserStart)
@@ -60,14 +66,17 @@ hostname2 = [
 ## Core Architecture Principles
 
 ### Structured Data Architecture (✅ IMPLEMENTED v0.1.131)
+
 Complete migration from string-based metrics to structured JSON data. Eliminates all string parsing bugs and provides type-safe data access.
 
 **Previous (String Metrics):**
+
 - ❌ Agent sent individual metrics with string names like `disk_nvme0n1_temperature`
 - ❌ Dashboard parsed metric names with underscore counting and string splitting
 - ❌ Complex and error-prone metric filtering and extraction logic
 
 **Current (Structured Data):**
+
 ```json
 {
   "hostname": "cmbox",
@@ -75,7 +84,7 @@ Complete migration from string-based metrics to structured JSON data. Eliminates
   "timestamp": 1763926877,
   "system": {
     "cpu": {
-      "load_1min": 3.50,
+      "load_1min": 3.5,
       "load_5min": 3.57,
       "load_15min": 3.58,
       "frequency_mhz": 1500,
@@ -88,7 +97,12 @@ Complete migration from string-based metrics to structured JSON data. Eliminates
       "swap_total_gb": 10.7,
       "swap_used_gb": 0.99,
       "tmpfs": [
-        {"mount": "/tmp", "usage_percent": 15.0, "used_gb": 0.3, "total_gb": 2.0}
+        {
+          "mount": "/tmp",
+          "usage_percent": 15.0,
+          "used_gb": 0.3,
+          "total_gb": 2.0
+        }
       ]
     },
     "storage": {
@@ -99,7 +113,12 @@ Complete migration from string-based metrics to structured JSON data. Eliminates
           "temperature_celsius": 29.0,
           "wear_percent": 1.0,
           "filesystems": [
-            {"mount": "/", "usage_percent": 24.0, "used_gb": 224.9, "total_gb": 928.2}
+            {
+              "mount": "/",
+              "usage_percent": 24.0,
+              "used_gb": 224.9,
+              "total_gb": 928.2
+            }
           ]
         }
       ],
@@ -112,18 +131,14 @@ Complete migration from string-based metrics to structured JSON data. Eliminates
           "usage_percent": 63.0,
           "used_gb": 2355.2,
           "total_gb": 3686.4,
-          "data_drives": [
-            {"name": "sdb", "temperature_celsius": 24.0}
-          ],
-          "parity_drives": [
-            {"name": "sdc", "temperature_celsius": 24.0}
-          ]
+          "data_drives": [{ "name": "sdb", "temperature_celsius": 24.0 }],
+          "parity_drives": [{ "name": "sdc", "temperature_celsius": 24.0 }]
         }
       ]
     }
   },
   "services": [
-    {"name": "sshd", "status": "active", "memory_mb": 4.5, "disk_gb": 0.0}
+    { "name": "sshd", "status": "active", "memory_mb": 4.5, "disk_gb": 0.0 }
   ],
   "backup": {
     "status": "completed",
@@ -134,19 +149,21 @@ Complete migration from string-based metrics to structured JSON data. Eliminates
   }
 }
 ```
+
 - ✅ Agent sends structured JSON over ZMQ (no legacy support)
 - ✅ Type-safe data access: `data.system.storage.drives[0].temperature_celsius`
 - ✅ Complete metric coverage: CPU, memory, storage, services, backup
 - ✅ Backward compatibility via bridge conversion to existing UI widgets
 - ✅ All string parsing bugs eliminated
 
-
 ### Maintenance Mode
+
 - Agent checks for `/tmp/cm-maintenance` file before sending notifications
 - File presence suppresses all email notifications while continuing monitoring
 - Dashboard continues to show real status, only notifications are blocked
 
 Usage:
+
 ```bash
 # Enable maintenance mode
 touch /tmp/cm-maintenance
@@ -163,16 +180,19 @@ rm /tmp/cm-maintenance
 ## Development and Deployment Architecture
 
 ### Development Path
+
 - **Location:** `~/projects/cm-dashboard`
 - **Purpose:** Development workflow only - for committing new code
 - **Access:** Only for developers to commit changes
 
 ### Deployment Path
+
 - **Location:** `/var/lib/cm-dashboard/nixos-config`
 - **Purpose:** Production deployment only - agent clones/pulls from git
 - **Workflow:** git pull → `/var/lib/cm-dashboard/nixos-config` → nixos-rebuild
 
 ### Git Flow
+
 ```
 Development: ~/projects/cm-dashboard → git commit → git push
 Deployment:  git pull → /var/lib/cm-dashboard/nixos-config → rebuild
@@ -183,6 +203,7 @@ Deployment:  git pull → /var/lib/cm-dashboard/nixos-config → rebuild
 CM Dashboard uses automated binary releases instead of source builds.
 
 ### Creating New Releases
+
 ```bash
 cd ~/projects/cm-dashboard
 git tag v0.1.X
@@ -190,11 +211,13 @@ git push origin v0.1.X
 ```
 
 This automatically:
+
 - Builds static binaries with `RUSTFLAGS="-C target-feature=+crt-static"`
 - Creates GitHub-style release with tarball
 - Uploads binaries via Gitea API
 
 ### NixOS Configuration Updates
+
 Edit `~/projects/nixosbox/hosts/services/cm-dashboard.nix`:
 
 ```nix
@@ -206,6 +229,7 @@ src = pkgs.fetchurl {
 ```
 
 ### Get Release Hash
+
 ```bash
 cd ~/projects/nixosbox
 nix-build --no-out-link -E 'with import <nixpkgs> {}; fetchurl {
@@ -217,6 +241,7 @@ nix-build --no-out-link -E 'with import <nixpkgs> {}; fetchurl {
 ### Building
 
 **Testing & Building:**
+
 - **Workspace builds**: `nix-shell -p openssl pkg-config --run "cargo build --workspace"`
 - **Clean compilation**: Remove `target/` between major changes
 
@@ -229,6 +254,7 @@ The dashboard uses automatic storage discovery to eliminate manual configuration
 ### Discovery Process
 
 **At Agent Startup:**
+
 1. Parse `/proc/mounts` to identify all mounted filesystems
 2. Detect MergerFS pools by analyzing `fuse.mergerfs` mount sources
 3. Identify member disks and potential parity relationships via heuristics
@@ -236,6 +262,7 @@ The dashboard uses automatic storage discovery to eliminate manual configuration
 5. Generate pool-aware metrics with hierarchical relationships
 
 **Continuous Monitoring:**
+
 - Use stored discovery data for efficient metric collection
 - Monitor individual drives for SMART data, temperature, wear
 - Calculate pool-level health based on member drive status
@@ -244,11 +271,13 @@ The dashboard uses automatic storage discovery to eliminate manual configuration
 ### Supported Storage Types
 
 **Single Disks:**
+
 - ext4, xfs, btrfs mounted directly
 - Individual drive monitoring with SMART data
 - Traditional single-disk display for root, boot, etc.
 
 **MergerFS Pools:**
+
 - Auto-detect from `/proc/mounts` fuse.mergerfs entries
 - Parse source paths to identify member disks (e.g., "/mnt/disk1:/mnt/disk2")
 - Heuristic parity disk detection (sequential device names, "parity" in path)
@@ -256,6 +285,7 @@ The dashboard uses automatic storage discovery to eliminate manual configuration
 - Hierarchical tree display with data/parity disk grouping
 
 **Future Extensions Ready:**
+
 - RAID arrays via `/proc/mdstat` parsing
 - ZFS pools via `zpool status` integration
 - LVM logical volumes via `lvs` discovery
@@ -274,76 +304,35 @@ exclude_fs_types = ["tmpfs", "devtmpfs", "sysfs", "proc"]
 ### Display Format
 
 ```
+Network:
+● eno1:
+  ├─ ip: 192.168.30.105
+  └─ tailscale0: 100.125.108.16
+● eno2:
+  └─ ip: 192.168.32.105
+CPU:
+● Load: 0.23 0.21 0.13
+  └─ Freq: 1048 MHz
+RAM:
+● Usage: 25% 5.8GB/23.3GB
+  ├─ ● /tmp: 2% 0.5GB/2GB
+  └─ ● /var/tmp: 0% 0GB/1.0GB
 Storage:
-● /srv/media (mergerfs (2+1)):
-  ├─ Pool Status: ● Healthy (3 drives)
-  ├─ Total: ● 63% 2355.2GB/3686.4GB
-  ├─ Data Disks:
-  │  ├─ ● sdb T: 24°C
-  │  └─ ● sdd T: 27°C
-  └─ Parity: ● sdc T: 24°C
-● /:
-  ├─ ● nvme0n1 W: 13%
-  └─ ● 7% 14.5GB/218.5GB
+● 844B9A25 T: 25C W: 4%
+  ├─ ● /: 55% 250.5GB/456.4GB
+  └─ ● /boot: 26% 0.3GB/1.0GB
+● mergerfs /srv/media:
+  ├─ ● 63% 2355.2GB/3686.4GB
+  ├─ ● Data_1: WDZQ8H8D T: 28°C
+  ├─ ● Data_2: GGA04461 T: 28°C
+  └─ ● Parity: WDZS8RY0 T: 29°C
+Backup:
+● WD-WCC7K1234567 T: 32°C W: 12%
+  ├─ Last: 2h ago (12.3GB)
+  ├─ Next: in 22h
+  └─ ● Usage: 45% 678GB/1.5TB
 ```
 
-### Implementation Benefits
-
-- **Zero Configuration**: No manual pool definitions required
-- **Always Accurate**: Reflects actual system state automatically
-- **Scales Automatically**: Handles any number of pools without config changes
-- **Backwards Compatible**: Single disks continue working unchanged
-- **Future Ready**: Easy extension for additional storage technologies
-
-### Current Status (v0.1.100)
-
-**✅ Completed:**
-- Auto-discovery system implemented and deployed
-- `/proc/mounts` parsing with smart heuristics for parity detection
-- Storage topology stored at agent startup for efficient monitoring
-- Universal zero-configuration for all hosts (cmbox, steambox, simonbox, srv01, srv02, srv03)
-- Enhanced pool health calculation (healthy/degraded/critical)
-- Hierarchical tree visualization with data/parity disk separation
-
-**🔄 In Progress - Complete Disk Collector Rewrite:**
-
-The current disk collector has grown complex with mixed legacy/auto-discovery approaches. Planning complete rewrite with clean, simple workflow supporting both physical drives and mergerfs pools.
-
-**New Clean Architecture:**
-
-**Discovery Workflow:**
-1. **`lsblk`** to detect all mount points and backing devices
-2. **`df`** to get filesystem usage for each mount point
-3. **Group by physical drive** (nvme0n1, sda, etc.)
-4. **Parse `/proc/mounts`** for mergerfs pools
-5. **Generate unified metrics** for both storage types
-
-**Physical Drive Display:**
-```
-● nvme0n1:
-  ├─ ● Drive: T: 35°C W: 1%
-  ├─ ● Total: 23% 218.0GB/928.2GB
-  ├─ ● /boot: 11% 0.1GB/1.0GB
-  └─ ● /: 23% 214.9GB/928.2GB
-```
-
-**MergerFS Pool Display:**
-```
-● /srv/media (mergerfs):
-  ├─ ● Pool: 63% 2355.2GB/3686.4GB
-  ├─ Data Disks:
-  │  ├─ ● sdb T: 24°C
-  │  └─ ● sdd T: 27°C  
-  └─ ● sdc T: 24°C (parity)
-```
-
-**Implementation Benefits:**
-- **Pure auto-discovery**: No configuration needed
-- **Clean code paths**: Single workflow for all storage types
-- **Consistent display**: Status icons on every line, no redundant text
-- **Simple pipeline**: lsblk → df → group → metrics
-- **Support for both**: Physical drives and mergerfs pools
-
 ## Important Communication Guidelines
 
 Keep responses concise and focused. Avoid extensive implementation summaries unless requested.
@@ -351,17 +340,20 @@ Keep responses concise and focused. Avoid extensive implementation summaries unl
 ## Commit Message Guidelines
 
 **NEVER mention:**
+
 - Claude or any AI assistant names
 - Automation or AI-generated content
 - Any reference to automated code generation
 
 **ALWAYS:**
+
 - Focus purely on technical changes and their purpose
 - Use standard software development commit message format
 - Describe what was changed and why, not how it was created
 - Write from the perspective of a human developer
 
 **Examples:**
+
 - ❌ "Generated with Claude Code"
 - ❌ "AI-assisted implementation"
 - ❌ "Automated refactoring"
@@ -369,50 +361,6 @@ Keep responses concise and focused. Avoid extensive implementation summaries unl
 - ✅ "Restructure storage widget with improved layout"
 - ✅ "Update CPU thresholds to production values"
 
-## Completed Architecture Migration (v0.1.131)
-
-### ✅ Phase 1: Structured Data Types (Shared Crate) - COMPLETED
-- ✅ Created AgentData struct matching JSON structure
-- ✅ Added complete type hierarchy: CPU, memory, storage, services, backup
-- ✅ Implemented serde serialization/deserialization
-- ✅ Updated ZMQ protocol for structured data transmission
-
-### ✅ Phase 2: Agent Refactor - COMPLETED  
-- ✅ Agent converts all metrics to structured AgentData
-- ✅ Comprehensive metric parsing: storage (drives, temp, wear), services, backup
-- ✅ Structured JSON transmission over ZMQ (no legacy support)
-- ✅ Type-safe data flow throughout agent pipeline
-
-### ✅ Phase 3: Dashboard Refactor - COMPLETED
-- ✅ Dashboard receives structured data and bridges to existing UI
-- ✅ Bridge conversion maintains compatibility with current widgets
-- ✅ All metric types converted: storage, services, backup, CPU, memory
-- ✅ Foundation ready for direct structured data widget migration
-
-### 🚀 Next Phase: Direct Widget Migration
-- Replace metric bridge with direct structured data access in widgets
-- Eliminate temporary conversion layer
-- Full end-to-end type safety from agent to UI
-
-## Key Achievements (v0.1.131)
-
-**✅ NVMe Temperature Issue SOLVED**
-- Temperature data now flows as typed field: `agent_data.system.storage.drives[0].temperature_celsius: f32`
-- Eliminates string parsing bugs: no more `"disk_nvme0n1_temperature"` extraction failures
-- Type-safe access prevents all similar parsing issues across the system
-
-**✅ Complete Structured Data Implementation**  
-- Agent: Collects metrics → structured JSON → ZMQ transmission
-- Dashboard: Receives JSON → bridge conversion → existing UI widgets  
-- Full metric coverage: CPU, memory, storage (drives, pools), services, backup
-- Zero legacy support - clean architecture with no compatibility cruft
-
-**✅ Foundation for Future Enhancements**
-- Type-safe data structures enable easy feature additions
-- Self-documenting JSON schema shows all available metrics
-- Direct field access eliminates entire class of parsing bugs
-- Ready for next phase: direct widget migration for ultimate performance
-
 ## Implementation Rules
 
 1. **Agent Status Authority**: Agent calculates status for each metric using thresholds
@@ -420,6 +368,7 @@ Keep responses concise and focused. Avoid extensive implementation summaries unl
 3. **Status Aggregation**: Dashboard aggregates individual metric statuses for widget status
 
 **NEVER:**
+
 - Copy/paste ANY code from legacy implementations
 - Calculate status in dashboard widgets
 - Hardcode metric names in widgets (use const arrays)
@@ -427,6 +376,7 @@ Keep responses concise and focused. Avoid extensive implementation summaries unl
 - Create documentation files unless explicitly requested
 
 **ALWAYS:**
+
 - Prefer editing existing files to creating new ones
 - Follow existing code conventions and patterns
 - Use existing libraries and utilities

Cargo.lock

@@ -279,7 +279,7 @@ checksum = "a1d728cc89cf3aee9ff92b05e62b19ee65a02b5702cff7d5a377e32c6ae29d8d"
 
 [[package]]
 name = "cm-dashboard"
-version = "0.1.137"
+version = "0.1.210"
 dependencies = [
  "anyhow",
  "chrono",
@@ -301,7 +301,7 @@ dependencies = [
 
 [[package]]
 name = "cm-dashboard-agent"
-version = "0.1.137"
+version = "0.1.210"
 dependencies = [
  "anyhow",
  "async-trait",
@@ -324,7 +324,7 @@ dependencies = [
 
 [[package]]
 name = "cm-dashboard-shared"
-version = "0.1.137"
+version = "0.1.210"
 dependencies = [
  "chrono",
  "serde",

agent/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "cm-dashboard-agent"
-version = "0.1.138"
+version = "0.1.211"
 edition = "2021"
 
 [dependencies]

agent/src/agent.rs

@@ -4,22 +4,37 @@ use std::time::Duration;
 use tokio::time::interval;
 use tracing::{debug, error, info};
 
-use crate::communication::{AgentCommand, ZmqHandler};
+use crate::communication::ZmqHandler;
 use crate::config::AgentConfig;
-use crate::metrics::MetricCollectionManager;
+use crate::collectors::{
+    Collector,
+    backup::BackupCollector,
+    cpu::CpuCollector,
+    disk::DiskCollector,
+    memory::MemoryCollector,
+    network::NetworkCollector,
+    nixos::NixOSCollector,
+    systemd::SystemdCollector,
+};
 use crate::notifications::NotificationManager;
-use crate::service_tracker::UserStoppedServiceTracker;
-use crate::status::HostStatusManager;
-use cm_dashboard_shared::{AgentData, Metric, MetricValue, Status, TmpfsData, DriveData, FilesystemData, ServiceData};
+use cm_dashboard_shared::AgentData;
 
 pub struct Agent {
     hostname: String,
     config: AgentConfig,
     zmq_handler: ZmqHandler,
-    metric_manager: MetricCollectionManager,
+    collectors: Vec<Box<dyn Collector>>,
     notification_manager: NotificationManager,
-    host_status_manager: HostStatusManager,
-    service_tracker: UserStoppedServiceTracker,
+    previous_status: Option<SystemStatus>,
+}
+
+/// Track system component status for change detection
+#[derive(Debug, Clone)]
+struct SystemStatus {
+    cpu_load_status: cm_dashboard_shared::Status,
+    cpu_temperature_status: cm_dashboard_shared::Status,
+    memory_usage_status: cm_dashboard_shared::Status,
+    // Add more as needed
 }
 
 impl Agent {
@@ -40,75 +55,84 @@ impl Agent {
             config.zmq.publisher_port
         );
 
-        // Initialize metric collection manager with cache config
-        let metric_manager = MetricCollectionManager::new(&config.collectors, &config).await?;
-        info!("Metric collection manager initialized");
+        // Initialize collectors
+        let mut collectors: Vec<Box<dyn Collector>> = Vec::new();
+        
+        // Add enabled collectors
+        if config.collectors.cpu.enabled {
+            collectors.push(Box::new(CpuCollector::new(config.collectors.cpu.clone())));
+        }
+        
+        if config.collectors.memory.enabled {
+            collectors.push(Box::new(MemoryCollector::new(config.collectors.memory.clone())));
+        }
+        
+        if config.collectors.disk.enabled {
+            collectors.push(Box::new(DiskCollector::new(config.collectors.disk.clone())));
+        }
+        
+        if config.collectors.systemd.enabled {
+            collectors.push(Box::new(SystemdCollector::new(config.collectors.systemd.clone())));
+        }
+        
+        if config.collectors.backup.enabled {
+            collectors.push(Box::new(BackupCollector::new()));
+        }
+
+        if config.collectors.network.enabled {
+            collectors.push(Box::new(NetworkCollector::new(config.collectors.network.clone())));
+        }
+
+        if config.collectors.nixos.enabled {
+            collectors.push(Box::new(NixOSCollector::new(config.collectors.nixos.clone())));
+        }
+
+        info!("Initialized {} collectors", collectors.len());
 
         // Initialize notification manager
         let notification_manager = NotificationManager::new(&config.notifications, &hostname)?;
         info!("Notification manager initialized");
 
-        // Initialize host status manager
-        let host_status_manager = HostStatusManager::new(config.status_aggregation.clone());
-        info!("Host status manager initialized");
-
-        // Initialize user-stopped service tracker
-        let service_tracker = UserStoppedServiceTracker::init_global()?;
-        info!("User-stopped service tracker initialized");
-
         Ok(Self {
             hostname,
             config,
             zmq_handler,
-            metric_manager,
+            collectors,
             notification_manager,
-            host_status_manager,
-            service_tracker,
+            previous_status: None,
         })
     }
 
+    /// Main agent loop with structured data collection
     pub async fn run(&mut self, mut shutdown_rx: tokio::sync::oneshot::Receiver<()>) -> Result<()> {
-        info!("Starting agent main loop with separated collection and transmission");
+        info!("Starting agent main loop");
 
-        // CRITICAL: Collect ALL data immediately at startup before entering the loop
-        info!("Performing initial FORCE collection of all metrics at startup");
-        if let Err(e) = self.collect_all_metrics_force().await {
-            error!("Failed to collect initial metrics: {}", e);
-        } else {
-            info!("Initial metric collection completed - all data cached and ready");
+        // Initial collection
+        if let Err(e) = self.collect_and_broadcast().await {
+            error!("Initial metric collection failed: {}", e);
         }
 
-        // 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.notifications.aggregation_interval_seconds));
+        // Set up intervals
+        let mut transmission_interval = interval(Duration::from_secs(
+            self.config.zmq.transmission_interval_seconds,
+        ));
+        let mut notification_interval = interval(Duration::from_secs(30)); // Check notifications every 30s
+
+        // Skip initial ticks to avoid immediate execution
+        transmission_interval.tick().await;
+        notification_interval.tick().await;
 
         loop {
             tokio::select! {
-                _ = collection_interval.tick() => {
-                    // Only collect and cache metrics, no ZMQ transmission
-                    if let Err(e) = self.collect_metrics_only().await {
-                        error!("Failed to collect metrics: {}", e);
-                    }
-                }
                 _ = transmission_interval.tick() => {
-                    // Send all metrics via ZMQ (dashboard updates only)
-                    if let Err(e) = self.broadcast_all_metrics().await {
-                        error!("Failed to broadcast metrics: {}", e);
+                    if let Err(e) = self.collect_and_broadcast().await {
+                        error!("Failed to collect and broadcast metrics: {}", e);
                     }
                 }
                 _ = notification_interval.tick() => {
-                    // 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);
-                    }
-                }
-                // Handle incoming commands (check periodically)
-                _ = tokio::time::sleep(Duration::from_millis(100)) => {
-                    if let Err(e) = self.handle_commands().await {
-                        error!("Error handling commands: {}", e);
-                    }
+                    // Process any pending notifications
+                    // NOTE: With structured data, we might need to implement status tracking differently
+                    // For now, we skip this until status evaluation is migrated
                 }
                 _ = &mut shutdown_rx => {
                     info!("Shutdown signal received, stopping agent loop");
@@ -121,511 +145,112 @@ impl Agent {
         Ok(())
     }
 
-    async fn collect_all_metrics_force(&mut self) -> Result<()> {
-        info!("Starting FORCE metric collection for startup");
+    /// Collect structured data from all collectors and broadcast via ZMQ
+    async fn collect_and_broadcast(&mut self) -> Result<()> {
+        debug!("Starting structured data collection");
 
-        // Force collect all metrics from all collectors immediately
-        let metrics = self.metric_manager.collect_all_metrics_force().await?;
+        // Initialize empty AgentData
+        let mut agent_data = AgentData::new(self.hostname.clone(), env!("CARGO_PKG_VERSION").to_string());
 
-        if metrics.is_empty() {
-            error!("No metrics collected during force collection!");
-            return Ok(());
-        }
-
-        info!("Force collected and cached {} metrics", metrics.len());
-
-        // Process metrics through status manager (collect status data at startup)
-        let _status_changed = self.process_metrics(&metrics).await;
-
-        Ok(())
-    }
-
-    async fn collect_metrics_only(&mut self) -> Result<()> {
-        debug!("Starting metric collection cycle (cache only)");
-
-        // Collect all metrics from all collectors and cache them
-        let metrics = self.metric_manager.collect_all_metrics().await?;
-
-        if metrics.is_empty() {
-            debug!("No metrics collected this cycle");
-            return Ok(());
-        }
-
-        debug!("Collected and cached {} metrics", metrics.len());
-
-        // Process metrics through status manager and trigger immediate transmission if status changed
-        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);
+        // Collect data from all collectors
+        for collector in &self.collectors {
+            if let Err(e) = collector.collect_structured(&mut agent_data).await {
+                error!("Collector failed: {}", e);
+                // Continue with other collectors even if one fails
             }
         }
 
-        Ok(())
+        // Check for status changes and send notifications
+        if let Err(e) = self.check_status_changes_and_notify(&agent_data).await {
+            error!("Failed to check status changes: {}", e);
         }
 
-    async fn broadcast_all_metrics(&mut self) -> Result<()> {
-        debug!("Broadcasting cached metrics via ZMQ");
-
-        // Get cached metrics (no fresh collection)
-        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();
-        metrics.push(host_status_metric);
-
-        // Add agent version metric for cross-host version comparison
-        let version_metric = self.get_agent_version_metric();
-        metrics.push(version_metric);
-
-        // Heartbeat removed - dashboard detects connectivity via regular transmission timestamps
-
-        // 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(());
-        }
-
-        debug!("Broadcasting {} cached metrics as structured data", metrics.len());
-
-        // Convert metrics to structured data and send
-        let agent_data = self.metrics_to_structured_data(&metrics)?;
-        self.zmq_handler.publish_agent_data(&agent_data).await?;
-        
-        debug!("Structured data broadcasted successfully");
-        Ok(())
-    }
-
-    /// Convert legacy metrics to structured data format
-    fn metrics_to_structured_data(&self, metrics: &[Metric]) -> Result<AgentData> {
-        let mut agent_data = AgentData::new(self.hostname.clone(), self.get_agent_version());
-
-        // Parse metrics into structured data
-        for metric in metrics {
-            self.parse_metric_into_agent_data(&mut agent_data, metric)?;
-        }
-
-        Ok(agent_data)
-    }
-
-    /// Parse a single metric into the appropriate structured data field
-    fn parse_metric_into_agent_data(&self, agent_data: &mut AgentData, metric: &Metric) -> Result<()> {
-        // CPU metrics
-        if metric.name == "cpu_load_1min" {
-            if let Some(value) = metric.value.as_f32() {
-                agent_data.system.cpu.load_1min = value;
-            }
-        } else if metric.name == "cpu_load_5min" {
-            if let Some(value) = metric.value.as_f32() {
-                agent_data.system.cpu.load_5min = value;
-            }
-        } else if metric.name == "cpu_load_15min" {
-            if let Some(value) = metric.value.as_f32() {
-                agent_data.system.cpu.load_15min = value;
-            }
-        } else if metric.name == "cpu_frequency_mhz" {
-            if let Some(value) = metric.value.as_f32() {
-                agent_data.system.cpu.frequency_mhz = value;
-            }
-        } else if metric.name == "cpu_temperature_celsius" {
-            if let Some(value) = metric.value.as_f32() {
-                agent_data.system.cpu.temperature_celsius = Some(value);
-            }
-        }
-        // Memory metrics  
-        else if metric.name == "memory_usage_percent" {
-            if let Some(value) = metric.value.as_f32() {
-                agent_data.system.memory.usage_percent = value;
-            }
-        } else if metric.name == "memory_total_gb" {
-            if let Some(value) = metric.value.as_f32() {
-                agent_data.system.memory.total_gb = value;
-            }
-        } else if metric.name == "memory_used_gb" {
-            if let Some(value) = metric.value.as_f32() {
-                agent_data.system.memory.used_gb = value;
-            }
-        } else if metric.name == "memory_available_gb" {
-            if let Some(value) = metric.value.as_f32() {
-                agent_data.system.memory.available_gb = value;
-            }
-        } else if metric.name == "memory_swap_total_gb" {
-            if let Some(value) = metric.value.as_f32() {
-                agent_data.system.memory.swap_total_gb = value;
-            }
-        } else if metric.name == "memory_swap_used_gb" {
-            if let Some(value) = metric.value.as_f32() {
-                agent_data.system.memory.swap_used_gb = value;
-            }
-        }
-        // Tmpfs metrics - handle multiple auto-discovered tmpfs mounts
-        else if metric.name.starts_with("memory_tmpfs_") {
-            if let Some((mount_point, metric_type)) = self.parse_tmpfs_metric_name(&metric.name) {
-                if let Some(value) = metric.value.as_f32() {
-                    self.update_tmpfs_data(&mut agent_data.system.memory.tmpfs, &mount_point, &metric_type, value);
-                }
-            }
-        }
-        // Storage metrics
-        else if metric.name.starts_with("disk_") {
-            if metric.name.contains("_temperature") {
-                if let Some(drive_name) = self.extract_drive_name(&metric.name) {
-                    if let Some(temp) = metric.value.as_f32() {
-                        self.ensure_drive_exists(agent_data, &drive_name);
-                        if let Some(drive) = agent_data.system.storage.drives.iter_mut().find(|d| d.name == drive_name) {
-                            drive.temperature_celsius = Some(temp);
-                        }
-                    }
-                }
-            } else if metric.name.contains("_wear_percent") {
-                if let Some(drive_name) = self.extract_drive_name(&metric.name) {
-                    if let Some(wear) = metric.value.as_f32() {
-                        self.ensure_drive_exists(agent_data, &drive_name);
-                        if let Some(drive) = agent_data.system.storage.drives.iter_mut().find(|d| d.name == drive_name) {
-                            drive.wear_percent = Some(wear);
-                        }
-                    }
-                }
-            } else if metric.name.contains("_health") {
-                if let Some(drive_name) = self.extract_drive_name(&metric.name) {
-                    let health = metric.value.as_string();
-                    self.ensure_drive_exists(agent_data, &drive_name);
-                    if let Some(drive) = agent_data.system.storage.drives.iter_mut().find(|d| d.name == drive_name) {
-                        drive.health = health;
-                    }
-                }
-            } else if metric.name.contains("_fs_") {
-                // Filesystem metrics: disk_{pool}_fs_{filesystem}_{metric}
-                if let Some((pool_name, fs_name)) = self.extract_pool_and_filesystem(&metric.name) {
-                    if metric.name.contains("_usage_percent") {
-                        if let Some(usage) = metric.value.as_f32() {
-                            self.ensure_filesystem_exists(agent_data, &pool_name, &fs_name, usage, 0.0, 0.0);
-                        }
-                    } else if metric.name.contains("_used_gb") {
-                        if let Some(used) = metric.value.as_f32() {
-                            self.update_filesystem_field(agent_data, &pool_name, &fs_name, |fs| fs.used_gb = used);
-                        }
-                    } else if metric.name.contains("_total_gb") {
-                        if let Some(total) = metric.value.as_f32() {
-                            self.update_filesystem_field(agent_data, &pool_name, &fs_name, |fs| fs.total_gb = total);
-                        }
-                    }
-                }
-            }
-        }
-        // Service metrics
-        else if metric.name.starts_with("service_") {
-            if let Some(service_name) = self.extract_service_name(&metric.name) {
-                if metric.name.contains("_status") {
-                    let status = metric.value.as_string();
-                    self.ensure_service_exists(agent_data, &service_name, &status);
-                } else if metric.name.contains("_memory_mb") {
-                    if let Some(memory) = metric.value.as_f32() {
-                        self.update_service_field(agent_data, &service_name, |svc| svc.memory_mb = memory);
-                    }
-                } else if metric.name.contains("_disk_gb") {
-                    if let Some(disk) = metric.value.as_f32() {
-                        self.update_service_field(agent_data, &service_name, |svc| svc.disk_gb = disk);
-                    }
-                }
-            }
-        }
-        // Backup metrics
-        else if metric.name.starts_with("backup_") {
-            if metric.name == "backup_status" {
-                agent_data.backup.status = metric.value.as_string();
-            } else if metric.name == "backup_last_run_timestamp" {
-                if let Some(timestamp) = metric.value.as_i64() {
-                    agent_data.backup.last_run = Some(timestamp as u64);
-                }
-            } else if metric.name == "backup_next_scheduled_timestamp" {
-                if let Some(timestamp) = metric.value.as_i64() {
-                    agent_data.backup.next_scheduled = Some(timestamp as u64);
-                }
-            } else if metric.name == "backup_size_gb" {
-                if let Some(size) = metric.value.as_f32() {
-                    agent_data.backup.total_size_gb = Some(size);
-                }
-            } else if metric.name == "backup_repository_health" {
-                agent_data.backup.repository_health = Some(metric.value.as_string());
-            }
-        }
-
-        Ok(())
-    }
-
-    /// Parse tmpfs metric name to extract mount point and metric type
-    /// Example: "memory_tmpfs_tmp_usage_percent" -> ("/tmp", "usage_percent")
-    fn parse_tmpfs_metric_name(&self, metric_name: &str) -> Option<(String, String)> {
-        if !metric_name.starts_with("memory_tmpfs_") {
-            return None;
-        }
-        
-        let remainder = &metric_name[13..]; // Remove "memory_tmpfs_" prefix
-        
-        // Find the last underscore to separate metric type from mount point
-        if let Some(last_underscore) = remainder.rfind('_') {
-            let mount_safe = &remainder[..last_underscore];
-            let metric_type = &remainder[last_underscore + 1..];
-            
-            // Convert safe mount name back to actual mount point
-            let mount_point = if mount_safe.is_empty() {
-                "/"
+        // Broadcast the structured data via ZMQ
+        if let Err(e) = self.zmq_handler.publish_agent_data(&agent_data).await {
+            error!("Failed to broadcast agent data: {}", e);
         } else {
-                &format!("/{}", mount_safe.replace('_', "/"))
+            debug!("Successfully broadcast structured agent data");
+        }
+
+        Ok(())
+    }
+
+    /// Check for status changes and send notifications
+    async fn check_status_changes_and_notify(&mut self, agent_data: &AgentData) -> Result<()> {
+        // Extract current status
+        let current_status = SystemStatus {
+            cpu_load_status: agent_data.system.cpu.load_status.clone(),
+            cpu_temperature_status: agent_data.system.cpu.temperature_status.clone(),
+            memory_usage_status: agent_data.system.memory.usage_status.clone(),
         };
 
-            Some((mount_point.to_string(), metric_type.to_string()))
-        } else {
-            None
-        }
+        // Check for status changes
+        if let Some(previous) = self.previous_status.clone() {
+            self.check_and_notify_status_change(
+                "CPU Load",
+                &previous.cpu_load_status,
+                &current_status.cpu_load_status,
+                format!("CPU load: {:.1}", agent_data.system.cpu.load_1min)
+            ).await?;
+
+            self.check_and_notify_status_change(
+                "CPU Temperature", 
+                &previous.cpu_temperature_status,
+                &current_status.cpu_temperature_status,
+                format!("CPU temperature: {}°C", 
+                    agent_data.system.cpu.temperature_celsius.unwrap_or(0.0) as i32)
+            ).await?;
+
+            self.check_and_notify_status_change(
+                "Memory Usage",
+                &previous.memory_usage_status, 
+                &current_status.memory_usage_status,
+                format!("Memory usage: {:.1}%", agent_data.system.memory.usage_percent)
+            ).await?;
         }
 
-    /// Update tmpfs data in the tmpfs vector
-    fn update_tmpfs_data(&self, tmpfs_vec: &mut Vec<TmpfsData>, mount_point: &str, metric_type: &str, value: f32) {
-        // Find existing tmpfs entry
-        let existing_index = tmpfs_vec.iter()
-            .position(|tmpfs| tmpfs.mount == mount_point);
-
-        let tmpfs_index = if let Some(index) = existing_index {
-            index
-        } else {
-            // Create new entry
-            tmpfs_vec.push(TmpfsData {
-                mount: mount_point.to_string(),
-                usage_percent: 0.0,
-                used_gb: 0.0,
-                total_gb: 0.0,
-            });
-            tmpfs_vec.len() - 1
-        };
-
-        // Update the tmpfs entry
-        if let Some(tmpfs) = tmpfs_vec.get_mut(tmpfs_index) {
-            match metric_type {
-                "usage_percent" => tmpfs.usage_percent = value,
-                "used_gb" => tmpfs.used_gb = value,
-                "total_gb" => tmpfs.total_gb = value,
-                _ => {} // Unknown metric type, ignore
-            }
-        }
-    }
-
-    /// Extract drive name from metric like "disk_nvme0n1_temperature"
-    fn extract_drive_name(&self, metric_name: &str) -> Option<String> {
-        if metric_name.starts_with("disk_") {
-            let suffixes = ["_temperature", "_wear_percent", "_health"];
-            for suffix in suffixes {
-                if let Some(suffix_pos) = metric_name.rfind(suffix) {
-                    return Some(metric_name[5..suffix_pos].to_string()); // Skip "disk_"
-                }
-            }
-        }
-        None
-    }
-
-    /// Extract pool and filesystem from "disk_{pool}_fs_{filesystem}_{metric}"
-    fn extract_pool_and_filesystem(&self, metric_name: &str) -> Option<(String, String)> {
-        if let Some(fs_pos) = metric_name.find("_fs_") {
-            let pool_name = metric_name[5..fs_pos].to_string(); // Skip "disk_"
-            let after_fs = &metric_name[fs_pos + 4..]; // Skip "_fs_"
-            if let Some(metric_pos) = after_fs.find('_') {
-                let fs_name = after_fs[..metric_pos].to_string();
-                return Some((pool_name, fs_name));
-            }
-        }
-        None
-    }
-
-    /// Extract service name from "service_{name}_{metric}"
-    fn extract_service_name(&self, metric_name: &str) -> Option<String> {
-        if metric_name.starts_with("service_") {
-            let suffixes = ["_status", "_memory_mb", "_disk_gb"];
-            for suffix in suffixes {
-                if let Some(suffix_pos) = metric_name.rfind(suffix) {
-                    return Some(metric_name[8..suffix_pos].to_string()); // Skip "service_"
-                }
-            }
-        }
-        None
-    }
-
-    /// Ensure drive exists in agent_data
-    fn ensure_drive_exists(&self, agent_data: &mut AgentData, drive_name: &str) {
-        if !agent_data.system.storage.drives.iter().any(|d| d.name == drive_name) {
-            agent_data.system.storage.drives.push(DriveData {
-                name: drive_name.to_string(),
-                health: "UNKNOWN".to_string(),
-                temperature_celsius: None,
-                wear_percent: None,
-                filesystems: Vec::new(),
-            });
-        }
-    }
-
-    /// Ensure filesystem exists in the correct drive
-    fn ensure_filesystem_exists(&self, agent_data: &mut AgentData, pool_name: &str, fs_name: &str, usage_percent: f32, used_gb: f32, total_gb: f32) {
-        self.ensure_drive_exists(agent_data, pool_name);
-        if let Some(drive) = agent_data.system.storage.drives.iter_mut().find(|d| d.name == pool_name) {
-            if !drive.filesystems.iter().any(|fs| fs.mount == fs_name) {
-                drive.filesystems.push(FilesystemData {
-                    mount: fs_name.to_string(),
-                    usage_percent,
-                    used_gb,
-                    total_gb,
-                });
-            }
-        }
-    }
-
-    /// Update filesystem field
-    fn update_filesystem_field<F>(&self, agent_data: &mut AgentData, pool_name: &str, fs_name: &str, update_fn: F)
-    where F: FnOnce(&mut FilesystemData) {
-        if let Some(drive) = agent_data.system.storage.drives.iter_mut().find(|d| d.name == pool_name) {
-            if let Some(fs) = drive.filesystems.iter_mut().find(|fs| fs.mount == fs_name) {
-                update_fn(fs);
-            }
-        }
-    }
-
-    /// Ensure service exists
-    fn ensure_service_exists(&self, agent_data: &mut AgentData, service_name: &str, status: &str) {
-        if !agent_data.services.iter().any(|s| s.name == service_name) {
-            agent_data.services.push(ServiceData {
-                name: service_name.to_string(),
-                status: status.to_string(),
-                memory_mb: 0.0,
-                disk_gb: 0.0,
-                user_stopped: false, // TODO: Get from service tracker
-            });
-        } else if let Some(service) = agent_data.services.iter_mut().find(|s| s.name == service_name) {
-            service.status = status.to_string();
-        }
-    }
-
-    /// Update service field
-    fn update_service_field<F>(&self, agent_data: &mut AgentData, service_name: &str, update_fn: F)
-    where F: FnOnce(&mut ServiceData) {
-        if let Some(service) = agent_data.services.iter_mut().find(|s| s.name == service_name) {
-            update_fn(service);
-        }
-    }
-
-    async fn process_metrics(&mut self, metrics: &[Metric]) -> bool {
-        let mut status_changed = false;
-        for metric in metrics {
-            // Filter excluded metrics from email notification processing only
-            if self.config.notifications.exclude_email_metrics.contains(&metric.name) {
-                debug!("Excluding metric '{}' from email notification processing", metric.name);
-                continue;
-            }
-            
-            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 {
-        // Get version from executable path (same logic as main.rs get_version)
-        let version = self.get_agent_version();
-        
-        Metric::new(
-            "agent_version".to_string(),
-            MetricValue::String(version),
-            Status::Ok,
-        )
-    }
-
-    /// Get agent version from Cargo package version
-    fn get_agent_version(&self) -> String {
-        // Use the version from Cargo.toml (e.g., "0.1.11")
-        format!("v{}", env!("CARGO_PKG_VERSION"))
-    }
-
-    /// Create heartbeat metric for host connectivity detection
-
-    async fn handle_commands(&mut self) -> Result<()> {
-        // Try to receive commands (non-blocking)
-        match self.zmq_handler.try_receive_command() {
-            Ok(Some(command)) => {
-                info!("Received command: {:?}", command);
-                self.process_command(command).await?;
-            }
-            Ok(None) => {
-                // No command available - this is normal
-            }
-            Err(e) => {
-                error!("Error receiving command: {}", e);
-            }
-        }
+        // Store current status for next comparison
+        self.previous_status = Some(current_status);
         Ok(())
     }
 
-    async fn process_command(&mut self, command: AgentCommand) -> Result<()> {
-        match command {
-            AgentCommand::CollectNow => {
-                info!("Processing CollectNow command");
-                if let Err(e) = self.collect_metrics_only().await {
-                    error!("Failed to collect metrics on command: {}", e);
-                }
-            }
-            AgentCommand::SetInterval { seconds } => {
-                info!("Processing SetInterval command: {} seconds", seconds);
-                // Note: This would require modifying the interval, which is complex
-                // For now, just log the request
-                info!("Interval change requested but not implemented yet");
-            }
-            AgentCommand::ToggleCollector { name, enabled } => {
-                info!(
-                    "Processing ToggleCollector command: {} -> {}",
-                    name, enabled
+    /// Check individual status change and send notification if degraded
+    async fn check_and_notify_status_change(
+        &mut self,
+        component: &str,
+        previous: &cm_dashboard_shared::Status,
+        current: &cm_dashboard_shared::Status,
+        details: String
+    ) -> Result<()> {
+        use cm_dashboard_shared::Status;
+
+        // Only notify on status degradation (OK → Warning/Critical, Warning → Critical)
+        let should_notify = match (previous, current) {
+            (Status::Ok, Status::Warning) => true,
+            (Status::Ok, Status::Critical) => true,
+            (Status::Warning, Status::Critical) => true,
+            _ => false,
+        };
+
+        if should_notify {
+            let subject = format!("{} {} Alert", self.hostname, component);
+            let body = format!(
+                "Alert: {} status changed from {:?} to {:?}\n\nDetails: {}\n\nTime: {}",
+                component,
+                previous,
+                current, 
+                details,
+                chrono::Utc::now().format("%Y-%m-%d %H:%M:%S UTC")
             );
-                // Note: This would require dynamic collector management
-                info!("Collector toggle requested but not implemented yet");
-            }
-            AgentCommand::Ping => {
-                info!("Processing Ping command - agent is alive");
-                // Could send a response back via ZMQ if needed
+
+            info!("Sending notification: {} - {:?} → {:?}", component, previous, current);
+            
+            if let Err(e) = self.notification_manager.send_direct_email(&subject, &body).await {
+                error!("Failed to send notification for {}: {}", component, e);
             }
         }
+
         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

@@ -1,448 +1,120 @@
 use async_trait::async_trait;
-use chrono::Utc;
-use cm_dashboard_shared::{Metric, MetricValue, Status, StatusTracker};
+use cm_dashboard_shared::{AgentData, BackupData, BackupDiskData};
 use serde::{Deserialize, Serialize};
 use std::collections::HashMap;
-use tokio::fs;
+use std::fs;
+use std::path::Path;
+use tracing::debug;
 
 use super::{Collector, CollectorError};
-use tracing::error;
 
-/// Backup collector that reads TOML status files for borgbackup metrics
-#[derive(Debug, Clone)]
+/// Backup collector that reads backup status from TOML files with structured data output
 pub struct BackupCollector {
-    pub backup_status_file: String,
-    pub max_age_hours: u64,
+    /// Path to backup status file
+    status_file_path: String,
 }
 
 impl BackupCollector {
-    pub fn new(backup_status_file: Option<String>, max_age_hours: u64) -> Self {
+    pub fn new() -> Self {
         Self {
-            backup_status_file: backup_status_file
-                .unwrap_or_else(|| "/var/lib/backup/backup-status.toml".to_string()),
-            max_age_hours,
+            status_file_path: "/var/lib/backup/backup-status.toml".to_string(),
         }
     }
 
+    /// Read backup status from TOML file
     async fn read_backup_status(&self) -> Result<Option<BackupStatusToml>, CollectorError> {
-        // Check if we're in maintenance mode
-        if std::fs::metadata("/tmp/cm-maintenance").is_ok() {
-            // Return special maintenance mode status
-            let maintenance_status = BackupStatusToml {
-                backup_name: "maintenance".to_string(),
-                start_time: chrono::Utc::now().format("%Y-%m-%d %H:%M:%S UTC").to_string(),
-                current_time: chrono::Utc::now().format("%Y-%m-%d %H:%M:%S UTC").to_string(),
-                duration_seconds: 0,
-                status: "pending".to_string(),
-                last_updated: chrono::Utc::now().format("%Y-%m-%d %H:%M:%S UTC").to_string(),
-                disk_space: None,
-                disk_product_name: None,
-                disk_serial_number: None,
-                disk_wear_percent: None,
-                services: HashMap::new(),
-            };
-            return Ok(Some(maintenance_status));
+        if !Path::new(&self.status_file_path).exists() {
+            debug!("Backup status file not found: {}", self.status_file_path);
+            return Ok(None);
         }
 
-        // Check if backup status file exists
-        if !std::path::Path::new(&self.backup_status_file).exists() {
-            return Ok(None); // File doesn't exist, but this is not an error
-        }
-
-        let content = fs::read_to_string(&self.backup_status_file)
-            .await
+        let content = fs::read_to_string(&self.status_file_path)
             .map_err(|e| CollectorError::SystemRead {
-                path: self.backup_status_file.clone(),
+                path: self.status_file_path.clone(),
                 error: e.to_string(),
             })?;
 
-        let backup_status = toml::from_str(&content).map_err(|e| CollectorError::Parse {
-            value: "backup status TOML".to_string(),
-            error: e.to_string(),
+        let status: BackupStatusToml = toml::from_str(&content)
+            .map_err(|e| CollectorError::Parse {
+                value: content.clone(),
+                error: format!("Failed to parse backup status TOML: {}", e),
             })?;
 
-        Ok(Some(backup_status))
+        Ok(Some(status))
     }
 
-    fn calculate_backup_status(&self, backup_status: &BackupStatusToml) -> Status {
-        // Parse the start time to check age - handle both RFC3339 and local timestamp formats
-        let start_time = match chrono::DateTime::parse_from_rfc3339(&backup_status.start_time) {
-            Ok(dt) => dt.with_timezone(&Utc),
-            Err(_) => {
-                // Try parsing as naive datetime and assume UTC
-                match chrono::NaiveDateTime::parse_from_str(
-                    &backup_status.start_time,
-                    "%Y-%m-%dT%H:%M:%S%.f",
-                ) {
-                    Ok(naive_dt) => naive_dt.and_utc(),
-                    Err(_) => {
-                        error!(
-                            "Failed to parse backup timestamp: {}",
-                            backup_status.start_time
-                        );
-                        return Status::Unknown;
-                    }
-                }
-            }
+    /// Convert BackupStatusToml to BackupData and populate AgentData
+    async fn populate_backup_data(&self, agent_data: &mut AgentData) -> Result<(), CollectorError> {
+        if let Some(backup_status) = self.read_backup_status().await? {
+            // Use raw start_time string from TOML
+
+            // Extract disk information
+            let repository_disk = if let Some(disk_space) = &backup_status.disk_space {
+                Some(BackupDiskData {
+                    serial: backup_status.disk_serial_number.clone().unwrap_or_else(|| "Unknown".to_string()),
+                    usage_percent: disk_space.usage_percent as f32,
+                    used_gb: disk_space.used_gb as f32,
+                    total_gb: disk_space.total_gb as f32,
+                    wear_percent: backup_status.disk_wear_percent,
+                    temperature_celsius: None, // Not available in current TOML
+                })
+            } else if let Some(serial) = &backup_status.disk_serial_number {
+                // Fallback: create minimal disk info if we have serial but no disk_space
+                Some(BackupDiskData {
+                    serial: serial.clone(),
+                    usage_percent: 0.0,
+                    used_gb: 0.0,
+                    total_gb: 0.0,
+                    wear_percent: backup_status.disk_wear_percent,
+                    temperature_celsius: None,
+                })
+            } else {
+                None
             };
 
-        let hours_since_backup = Utc::now().signed_duration_since(start_time).num_hours();
+            // Calculate total repository size from services
+            let total_size_gb = backup_status.services
+                .values()
+                .map(|service| service.repo_size_bytes as f32 / (1024.0 * 1024.0 * 1024.0))
+                .sum::<f32>();
 
-        // Check overall backup status
-        match backup_status.status.as_str() {
-            "success" => {
-                if hours_since_backup > self.max_age_hours as i64 {
-                    Status::Warning // Backup too old
+            let backup_data = BackupData {
+                status: backup_status.status,
+                total_size_gb: Some(total_size_gb),
+                repository_health: Some("ok".to_string()), // Derive from status if needed
+                repository_disk,
+                last_backup_size_gb: None, // Not available in current TOML format
+                start_time_raw: Some(backup_status.start_time),
+            };
+
+            agent_data.backup = backup_data;
         } else {
-                    Status::Ok
-                }
-            }
-            "failed" => Status::Critical,
-            "warning" => Status::Warning, // Backup completed with warnings
-            "running" => Status::Ok, // Currently running is OK
-            "pending" => Status::Pending, // Maintenance mode or backup starting
-            _ => Status::Unknown,
-        }
+            // No backup status available - set default values
+            agent_data.backup = BackupData {
+                status: "unavailable".to_string(),
+                total_size_gb: None,
+                repository_health: None,
+                repository_disk: None,
+                last_backup_size_gb: None,
+                start_time_raw: None,
+            };
         }
 
-    fn calculate_service_status(&self, service: &ServiceStatus) -> Status {
-        match service.status.as_str() {
-            "completed" => {
-                if service.exit_code == 0 {
-                    Status::Ok
-                } else {
-                    Status::Critical
-                }
-            }
-            "failed" => Status::Critical,
-            "disabled" => Status::Warning, // Service intentionally disabled
-            "running" => Status::Ok,
-            _ => Status::Unknown,
-        }
-    }
-
-    fn bytes_to_gb(bytes: u64) -> f32 {
-        bytes as f32 / (1024.0 * 1024.0 * 1024.0)
+        Ok(())
     }
 }
 
 #[async_trait]
 impl Collector for BackupCollector {
-
-    async fn collect(&self, _status_tracker: &mut StatusTracker) -> Result<Vec<Metric>, CollectorError> {
-        let backup_status_option = self.read_backup_status().await?;
-        let mut metrics = Vec::new();
-        let timestamp = chrono::Utc::now().timestamp() as u64;
-
-        // If no backup status file exists, return minimal metrics indicating no backup system
-        let backup_status = match backup_status_option {
-            Some(status) => status,
-            None => {
-                // No backup system configured - return minimal "unknown" metrics
-                metrics.push(Metric {
-                    name: "backup_overall_status".to_string(),
-                    value: MetricValue::String("no_backup_system".to_string()),
-                    status: Status::Unknown,
-                    timestamp,
-                    description: Some("No backup system configured (no status file found)".to_string()),
-                    unit: None,
-                });
-                return Ok(metrics);
-            }
-        };
-
-        // Overall backup status
-        let overall_status = self.calculate_backup_status(&backup_status);
-        metrics.push(Metric {
-            name: "backup_overall_status".to_string(),
-            value: MetricValue::String(match overall_status {
-                Status::Ok => "ok".to_string(),
-                Status::Inactive => "inactive".to_string(),
-                Status::Pending => "pending".to_string(),
-                Status::Warning => "warning".to_string(),
-                Status::Critical => "critical".to_string(),
-                Status::Unknown => "unknown".to_string(),
-                Status::Offline => "offline".to_string(),
-            }),
-            status: overall_status,
-            timestamp,
-            description: Some(format!(
-                "Backup: {} at {}",
-                backup_status.status, backup_status.start_time
-            )),
-            unit: None,
-        });
-
-        // Backup duration
-        metrics.push(Metric {
-            name: "backup_duration_seconds".to_string(),
-            value: MetricValue::Integer(backup_status.duration_seconds),
-            status: Status::Ok,
-            timestamp,
-            description: Some("Duration of last backup run".to_string()),
-            unit: Some("seconds".to_string()),
-        });
-
-        // Last backup timestamp - use last_updated (when backup finished) instead of start_time
-        let last_updated_dt_result =
-            chrono::DateTime::parse_from_rfc3339(&backup_status.last_updated)
-                .map(|dt| dt.with_timezone(&Utc))
-                .or_else(|_| {
-                    // Try parsing as naive datetime and assume UTC
-                    chrono::NaiveDateTime::parse_from_str(
-                        &backup_status.last_updated,
-                        "%Y-%m-%dT%H:%M:%S%.f",
-                    )
-                    .map(|naive_dt| naive_dt.and_utc())
-                });
-
-        if let Ok(last_updated_dt) = last_updated_dt_result {
-            metrics.push(Metric {
-                name: "backup_last_run_timestamp".to_string(),
-                value: MetricValue::Integer(last_updated_dt.timestamp()),
-                status: Status::Ok,
-                timestamp,
-                description: Some("Timestamp of last backup completion".to_string()),
-                unit: Some("unix_timestamp".to_string()),
-            });
-        } else {
-            error!(
-                "Failed to parse backup timestamp for last_run_timestamp: {}",
-                backup_status.last_updated
-            );
-        }
-
-        // Individual service metrics
-        for (service_name, service) in &backup_status.services {
-            let service_status = self.calculate_service_status(service);
-
-            // Service status
-            metrics.push(Metric {
-                name: format!("backup_service_{}_status", service_name),
-                value: MetricValue::String(match service_status {
-                    Status::Ok => "ok".to_string(),
-                    Status::Inactive => "inactive".to_string(),
-                    Status::Pending => "pending".to_string(),
-                    Status::Warning => "warning".to_string(),
-                    Status::Critical => "critical".to_string(),
-                    Status::Unknown => "unknown".to_string(),
-                    Status::Offline => "offline".to_string(),
-                }),
-                status: service_status,
-                timestamp,
-                description: Some(format!(
-                    "Backup service {} status: {}",
-                    service_name, service.status
-                )),
-                unit: None,
-            });
-
-            // Service exit code
-            metrics.push(Metric {
-                name: format!("backup_service_{}_exit_code", service_name),
-                value: MetricValue::Integer(service.exit_code),
-                status: if service.exit_code == 0 {
-                    Status::Ok
-                } else {
-                    Status::Critical
-                },
-                timestamp,
-                description: Some(format!("Exit code for backup service {}", service_name)),
-                unit: None,
-            });
-
-            // Repository archive count
-            metrics.push(Metric {
-                name: format!("backup_service_{}_archive_count", service_name),
-                value: MetricValue::Integer(service.archive_count),
-                status: Status::Ok,
-                timestamp,
-                description: Some(format!("Number of archives in {} repository", service_name)),
-                unit: Some("archives".to_string()),
-            });
-
-            // Repository size in GB
-            let repo_size_gb = Self::bytes_to_gb(service.repo_size_bytes);
-            metrics.push(Metric {
-                name: format!("backup_service_{}_repo_size_gb", service_name),
-                value: MetricValue::Float(repo_size_gb),
-                status: Status::Ok,
-                timestamp,
-                description: Some(format!("Repository size for {} in GB", service_name)),
-                unit: Some("GB".to_string()),
-            });
-
-            // Repository path for reference
-            metrics.push(Metric {
-                name: format!("backup_service_{}_repo_path", service_name),
-                value: MetricValue::String(service.repo_path.clone()),
-                status: Status::Ok,
-                timestamp,
-                description: Some(format!("Repository path for {}", service_name)),
-                unit: None,
-            });
-        }
-
-        // Total number of services
-        metrics.push(Metric {
-            name: "backup_total_services".to_string(),
-            value: MetricValue::Integer(backup_status.services.len() as i64),
-            status: Status::Ok,
-            timestamp,
-            description: Some("Total number of backup services".to_string()),
-            unit: Some("services".to_string()),
-        });
-
-        // Calculate total repository size
-        let total_size_bytes: u64 = backup_status
-            .services
-            .values()
-            .map(|s| s.repo_size_bytes)
-            .sum();
-        let total_size_gb = Self::bytes_to_gb(total_size_bytes);
-        metrics.push(Metric {
-            name: "backup_total_repo_size_gb".to_string(),
-            value: MetricValue::Float(total_size_gb),
-            status: Status::Ok,
-            timestamp,
-            description: Some("Total size of all backup repositories".to_string()),
-            unit: Some("GB".to_string()),
-        });
-
-        // Disk space metrics for backup directory
-        if let Some(ref disk_space) = backup_status.disk_space {
-            metrics.push(Metric {
-                name: "backup_disk_total_gb".to_string(),
-                value: MetricValue::Float(disk_space.total_gb as f32),
-                status: Status::Ok,
-                timestamp,
-                description: Some("Total disk space available for backups".to_string()),
-                unit: Some("GB".to_string()),
-            });
-
-            metrics.push(Metric {
-                name: "backup_disk_used_gb".to_string(),
-                value: MetricValue::Float(disk_space.used_gb as f32),
-                status: Status::Ok,
-                timestamp,
-                description: Some("Used disk space on backup drive".to_string()),
-                unit: Some("GB".to_string()),
-            });
-
-            metrics.push(Metric {
-                name: "backup_disk_available_gb".to_string(),
-                value: MetricValue::Float(disk_space.available_gb as f32),
-                status: Status::Ok,
-                timestamp,
-                description: Some("Available disk space on backup drive".to_string()),
-                unit: Some("GB".to_string()),
-            });
-
-            metrics.push(Metric {
-                name: "backup_disk_usage_percent".to_string(),
-                value: MetricValue::Float(disk_space.usage_percent as f32),
-                status: if disk_space.usage_percent >= 95.0 {
-                    Status::Critical
-                } else if disk_space.usage_percent >= 85.0 {
-                    Status::Warning
-                } else {
-                    Status::Ok
-                },
-                timestamp,
-                description: Some("Backup disk usage percentage".to_string()),
-                unit: Some("percent".to_string()),
-            });
-
-            // Add disk identification metrics if available from disk_space
-            if let Some(ref product_name) = disk_space.product_name {
-                metrics.push(Metric {
-                    name: "backup_disk_product_name".to_string(),
-                    value: MetricValue::String(product_name.clone()),
-                    status: Status::Ok,
-                    timestamp,
-                    description: Some("Backup disk product name from SMART data".to_string()),
-                    unit: None,
-                });
-            }
-
-            if let Some(ref serial_number) = disk_space.serial_number {
-                metrics.push(Metric {
-                    name: "backup_disk_serial_number".to_string(),
-                    value: MetricValue::String(serial_number.clone()),
-                    status: Status::Ok,
-                    timestamp,
-                    description: Some("Backup disk serial number from SMART data".to_string()),
-                    unit: None,
-                });
-            }
-        }
-
-        // Add standalone disk identification metrics from TOML fields
-        if let Some(ref product_name) = backup_status.disk_product_name {
-            metrics.push(Metric {
-                name: "backup_disk_product_name".to_string(),
-                value: MetricValue::String(product_name.clone()),
-                status: Status::Ok,
-                timestamp,
-                description: Some("Backup disk product name from SMART data".to_string()),
-                unit: None,
-            });
-        }
-
-        if let Some(ref serial_number) = backup_status.disk_serial_number {
-            metrics.push(Metric {
-                name: "backup_disk_serial_number".to_string(),
-                value: MetricValue::String(serial_number.clone()),
-                status: Status::Ok,
-                timestamp,
-                description: Some("Backup disk serial number from SMART data".to_string()),
-                unit: None,
-            });
-        }
-
-        if let Some(wear_percent) = backup_status.disk_wear_percent {
-            let wear_status = if wear_percent >= 90.0 {
-                Status::Critical
-            } else if wear_percent >= 75.0 {
-                Status::Warning
-            } else {
-                Status::Ok
-            };
-            
-            metrics.push(Metric {
-                name: "backup_disk_wear_percent".to_string(),
-                value: MetricValue::Float(wear_percent),
-                status: wear_status,
-                timestamp,
-                description: Some("Backup disk wear percentage from SMART data".to_string()),
-                unit: Some("percent".to_string()),
-            });
-        }
-
-        // Count services by status
-        let mut status_counts = HashMap::new();
-        for service in backup_status.services.values() {
-            *status_counts.entry(service.status.clone()).or_insert(0) += 1;
-        }
-
-        for (status_name, count) in status_counts {
-            metrics.push(Metric {
-                name: format!("backup_services_{}_count", status_name),
-                value: MetricValue::Integer(count),
-                status: Status::Ok,
-                timestamp,
-                description: Some(format!("Number of services with status: {}", status_name)),
-                unit: Some("services".to_string()),
-            });
-        }
-
-        Ok(metrics)
+    async fn collect_structured(&self, agent_data: &mut AgentData) -> Result<(), CollectorError> {
+        debug!("Collecting backup status");
+        self.populate_backup_data(agent_data).await
     }
 }
 
 /// TOML structure for backup status file
-#[derive(Debug, Clone, Deserialize, Serialize)]
-pub struct BackupStatusToml {
+#[derive(Debug, Clone, Serialize, Deserialize)]
+struct BackupStatusToml {
     pub backup_name: String,
     pub start_time: String,
     pub current_time: String,
@@ -456,8 +128,8 @@ pub struct BackupStatusToml {
     pub services: HashMap<String, ServiceStatus>,
 }
 
-#[derive(Debug, Clone, Deserialize, Serialize)]
-pub struct DiskSpace {
+#[derive(Debug, Clone, Serialize, Deserialize)]
+struct DiskSpace {
     pub total_bytes: u64,
     pub used_bytes: u64,
     pub available_bytes: u64,
@@ -465,13 +137,10 @@ pub struct DiskSpace {
     pub used_gb: f64,
     pub available_gb: f64,
     pub usage_percent: f64,
-    // Optional disk identification fields
-    pub product_name: Option<String>,
-    pub serial_number: Option<String>,
 }
 
-#[derive(Debug, Clone, Deserialize, Serialize)]
-pub struct ServiceStatus {
+#[derive(Debug, Clone, Serialize, Deserialize)]
+struct ServiceStatus {
     pub status: String,
     pub exit_code: i64,
     pub repo_path: String,

agent/src/collectors/cpu.rs

@@ -1,5 +1,5 @@
 use async_trait::async_trait;
-use cm_dashboard_shared::{registry, Metric, MetricValue, Status, StatusTracker, HysteresisThresholds};
+use cm_dashboard_shared::{AgentData, Status, HysteresisThresholds};
 
 use tracing::debug;
 
@@ -38,19 +38,31 @@ impl CpuCollector {
         }
     }
 
-    /// Calculate CPU load status using hysteresis thresholds
-    fn calculate_load_status(&self, metric_name: &str, load: f32, status_tracker: &mut StatusTracker) -> Status {
-        status_tracker.calculate_with_hysteresis(metric_name, load, &self.load_thresholds)
+    /// Calculate CPU load status using thresholds
+    fn calculate_load_status(&self, load: f32) -> Status {
+        if load >= self.load_thresholds.critical_high {
+            Status::Critical
+        } else if load >= self.load_thresholds.warning_high {
+            Status::Warning  
+        } else {
+            Status::Ok
+        }
     }
 
-    /// Calculate CPU temperature status using hysteresis thresholds
-    fn calculate_temperature_status(&self, metric_name: &str, temp: f32, status_tracker: &mut StatusTracker) -> Status {
-        status_tracker.calculate_with_hysteresis(metric_name, temp, &self.temperature_thresholds)
+    /// Calculate CPU temperature status using thresholds
+    fn calculate_temperature_status(&self, temp: f32) -> Status {
+        if temp >= self.temperature_thresholds.critical_high {
+            Status::Critical
+        } else if temp >= self.temperature_thresholds.warning_high {
+            Status::Warning
+        } else {
+            Status::Ok
+        }
     }
 
-    /// Collect CPU load averages from /proc/loadavg
+    /// Collect CPU load averages and populate AgentData
     /// Format: "0.52 0.58 0.59 1/257 12345"
-    async fn collect_load_averages(&self, status_tracker: &mut StatusTracker) -> Result<Vec<Metric>, CollectorError> {
+    async fn collect_load_averages(&self, agent_data: &mut AgentData) -> Result<(), CollectorError> {
         let content = utils::read_proc_file("/proc/loadavg")?;
         let parts: Vec<&str> = content.trim().split_whitespace().collect();
 
@@ -65,53 +77,25 @@ impl CpuCollector {
         let load_5min = utils::parse_f32(parts[1])?;
         let load_15min = utils::parse_f32(parts[2])?;
 
-        // Only apply thresholds to 5-minute load average
-        let load_1min_status = Status::Ok;  // No alerting on 1min
-        let load_5min_status = self.calculate_load_status(registry::CPU_LOAD_5MIN, load_5min, status_tracker);  // Only 5min triggers alerts
-        let load_15min_status = Status::Ok;  // No alerting on 15min
+        // Populate CPU data directly
+        agent_data.system.cpu.load_1min = load_1min;
+        agent_data.system.cpu.load_5min = load_5min;
+        agent_data.system.cpu.load_15min = load_15min;
 
-        Ok(vec![
-            Metric::new(
-                registry::CPU_LOAD_1MIN.to_string(),
-                MetricValue::Float(load_1min),
-                load_1min_status,
-            )
-            .with_description("CPU load average over 1 minute".to_string()),
-            Metric::new(
-                registry::CPU_LOAD_5MIN.to_string(),
-                MetricValue::Float(load_5min),
-                load_5min_status,
-            )
-            .with_description("CPU load average over 5 minutes".to_string()),
-            Metric::new(
-                registry::CPU_LOAD_15MIN.to_string(),
-                MetricValue::Float(load_15min),
-                load_15min_status,
-            )
-            .with_description("CPU load average over 15 minutes".to_string()),
-        ])
+        Ok(())
     }
 
-    /// Collect CPU temperature from thermal zones
-    /// Prioritizes x86_pkg_temp over generic thermal zones (legacy behavior)
-    async fn collect_temperature(&self, status_tracker: &mut StatusTracker) -> Result<Option<Metric>, CollectorError> {
+    /// Collect CPU temperature and populate AgentData
+    /// Prioritizes x86_pkg_temp over generic thermal zones
+    async fn collect_temperature(&self, agent_data: &mut AgentData) -> Result<(), CollectorError> {
         // Try x86_pkg_temp first (Intel CPU package temperature)
         if let Ok(temp) = self
             .read_thermal_zone("/sys/class/thermal/thermal_zone0/temp")
             .await
         {
             let temp_celsius = temp as f32 / 1000.0;
-            let status = self.calculate_temperature_status(registry::CPU_TEMPERATURE_CELSIUS, temp_celsius, status_tracker);
-
-            return Ok(Some(
-                Metric::new(
-                    registry::CPU_TEMPERATURE_CELSIUS.to_string(),
-                    MetricValue::Float(temp_celsius),
-                    status,
-                )
-                .with_description("CPU package temperature".to_string())
-                .with_unit("°C".to_string()),
-            ));
+            agent_data.system.cpu.temperature_celsius = Some(temp_celsius);
+            return Ok(());
         }
 
         // Fallback: try other thermal zones
@@ -119,22 +103,14 @@ impl CpuCollector {
             let path = format!("/sys/class/thermal/thermal_zone{}/temp", zone_id);
             if let Ok(temp) = self.read_thermal_zone(&path).await {
                 let temp_celsius = temp as f32 / 1000.0;
-                let status = self.calculate_temperature_status(registry::CPU_TEMPERATURE_CELSIUS, temp_celsius, status_tracker);
-
-                return Ok(Some(
-                    Metric::new(
-                        registry::CPU_TEMPERATURE_CELSIUS.to_string(),
-                        MetricValue::Float(temp_celsius),
-                        status,
-                    )
-                    .with_description(format!("CPU temperature from thermal_zone{}", zone_id))
-                    .with_unit("°C".to_string()),
-                ));
+                agent_data.system.cpu.temperature_celsius = Some(temp_celsius);
+                return Ok(());
             }
         }
 
         debug!("No CPU temperature sensors found");
-        Ok(None)
+        // Leave temperature as None if not available
+        Ok(())
     }
 
     /// Read temperature from thermal zone efficiently
@@ -143,84 +119,77 @@ impl CpuCollector {
         utils::parse_u64(content.trim())
     }
 
-    /// Collect CPU frequency from /proc/cpuinfo or scaling governor
-    async fn collect_frequency(&self) -> Result<Option<Metric>, CollectorError> {
-        // Try scaling frequency first (more accurate for current frequency)
-        if let Ok(freq) =
-            utils::read_proc_file("/sys/devices/system/cpu/cpu0/cpufreq/scaling_cur_freq")
-        {
-            if let Ok(freq_khz) = utils::parse_u64(freq.trim()) {
-                let freq_mhz = freq_khz as f32 / 1000.0;
+    /// Collect CPU C-state (idle depth) and populate AgentData with top 3 C-states by usage
+    async fn collect_cstate(&self, agent_data: &mut AgentData) -> Result<(), CollectorError> {
+        // Read C-state usage from first CPU (representative of overall system)
+        // C-states indicate CPU idle depth: C1=light sleep, C6=deep sleep, C10=deepest
 
-                return Ok(Some(
-                    Metric::new(
-                        registry::CPU_FREQUENCY_MHZ.to_string(),
-                        MetricValue::Float(freq_mhz),
-                        Status::Ok, // Frequency doesn't have status thresholds
-                    )
-                    .with_description("Current CPU frequency".to_string())
-                    .with_unit("MHz".to_string()),
-                ));
+        let mut cstate_times: Vec<(String, u64)> = Vec::new();
+        let mut total_time: u64 = 0;
+
+        // Collect all C-state times from CPU0
+        for state_num in 0..=10 {
+            let time_path = format!("/sys/devices/system/cpu/cpu0/cpuidle/state{}/time", state_num);
+            let name_path = format!("/sys/devices/system/cpu/cpu0/cpuidle/state{}/name", state_num);
+
+            if let Ok(time_str) = utils::read_proc_file(&time_path) {
+                if let Ok(time) = utils::parse_u64(time_str.trim()) {
+                    if let Ok(name) = utils::read_proc_file(&name_path) {
+                        let state_name = name.trim().to_string();
+                        // Skip POLL state (not real idle)
+                        if state_name != "POLL" && time > 0 {
+                            cstate_times.push((state_name, time));
+                            total_time += time;
+                        }
+                    }
+                }
+            } else {
+                // No more states available
+                break;
             }
         }
 
-        // Fallback: parse /proc/cpuinfo for base frequency
-        if let Ok(content) = utils::read_proc_file("/proc/cpuinfo") {
-            for line in content.lines() {
-                if line.starts_with("cpu MHz") {
-                    if let Some(freq_str) = line.split(':').nth(1) {
-                        if let Ok(freq_mhz) = utils::parse_f32(freq_str) {
-                            return Ok(Some(
-                                Metric::new(
-                                    registry::CPU_FREQUENCY_MHZ.to_string(),
-                                    MetricValue::Float(freq_mhz),
-                                    Status::Ok,
-                                )
-                                .with_description(
-                                    "CPU base frequency from /proc/cpuinfo".to_string(),
-                                )
-                                .with_unit("MHz".to_string()),
-                            ));
-                        }
-                    }
-                    break; // Only need first CPU entry
-                }
-            }
-        }
+        // Sort by time descending to get top 3
+        cstate_times.sort_by(|a, b| b.1.cmp(&a.1));
 
-        debug!("CPU frequency not available");
-        Ok(None)
+        // Calculate percentages for top 3 and populate AgentData
+        agent_data.system.cpu.cstates = cstate_times
+            .iter()
+            .take(3)
+            .map(|(name, time)| {
+                let percent = if total_time > 0 {
+                    (*time as f32 / total_time as f32) * 100.0
+                } else {
+                    0.0
+                };
+                cm_dashboard_shared::CStateInfo {
+                    name: name.clone(),
+                    percent,
+                }
+            })
+            .collect();
+
+        Ok(())
     }
 }
 
 #[async_trait]
 impl Collector for CpuCollector {
-
-    async fn collect(&self, status_tracker: &mut StatusTracker) -> Result<Vec<Metric>, CollectorError> {
+    async fn collect_structured(&self, agent_data: &mut AgentData) -> Result<(), CollectorError> {
         debug!("Collecting CPU metrics");
         let start = std::time::Instant::now();
 
-        let mut metrics = Vec::with_capacity(5); // Pre-allocate for efficiency
-
         // Collect load averages (always available)
-        metrics.extend(self.collect_load_averages(status_tracker).await?);
+        self.collect_load_averages(agent_data).await?;
 
         // Collect temperature (optional)
-        if let Some(temp_metric) = self.collect_temperature(status_tracker).await? {
-            metrics.push(temp_metric);
-        }
+        self.collect_temperature(agent_data).await?;
 
-        // Collect frequency (optional)
-        if let Some(freq_metric) = self.collect_frequency().await? {
-            metrics.push(freq_metric);
-        }
+        // Collect C-state (CPU idle depth)
+        self.collect_cstate(agent_data).await?;
 
         let duration = start.elapsed();
-        debug!(
-            "CPU collection completed in {:?} with {} metrics",
-            duration,
-            metrics.len()
-        );
+        debug!("CPU collection completed in {:?}", duration);
 
         // Efficiency check: warn if collection takes too long
         if duration.as_millis() > 1 {
@@ -230,10 +199,14 @@ impl Collector for CpuCollector {
             );
         }
 
-        // Store performance metrics
-        // Performance tracking handled by cache system
+        // Calculate status using thresholds
+        agent_data.system.cpu.load_status = self.calculate_load_status(agent_data.system.cpu.load_1min);
+        agent_data.system.cpu.temperature_status = if let Some(temp) = agent_data.system.cpu.temperature_celsius {
+            self.calculate_temperature_status(temp)
+        } else {
+            Status::Unknown
+        };
 
-        Ok(metrics)
+        Ok(())
     }
-
 }

agent/src/collectors/disk.rs

@@ -1,6 +1,6 @@
 use anyhow::Result;
 use async_trait::async_trait;
-use cm_dashboard_shared::{Metric, MetricValue, Status, StatusTracker, HysteresisThresholds};
+use cm_dashboard_shared::{AgentData, DriveData, FilesystemData, PoolData, HysteresisThresholds, Status};
 
 use crate::config::DiskConfig;
 use std::process::Command;
@@ -10,7 +10,7 @@ use tracing::debug;
 
 use super::{Collector, CollectorError};
 
-/// Storage collector with clean architecture
+/// Storage collector with clean architecture and structured data output
 pub struct DiskCollector {
     config: DiskConfig,
     temperature_thresholds: HysteresisThresholds,
@@ -19,55 +19,44 @@ pub struct DiskCollector {
 /// A physical drive with its filesystems
 #[derive(Debug, Clone)]
 struct PhysicalDrive {
-    device: String,                    // e.g., "nvme0n1", "sda"
+    name: String,                        // e.g., "nvme0n1", "sda"
+    health: String,                      // SMART health status
     filesystems: Vec<Filesystem>,        // mounted filesystems on this drive
-    temperature: Option<f32>,          // drive temperature
-    wear_level: Option<f32>,          // SSD wear level
-    health_status: String,            // SMART health
 }
 
-/// A mergerfs pool
-#[derive(Debug, Clone)]
-struct MergerfsPool {
-    mount_point: String,              // e.g., "/srv/media"
-    total_bytes: u64,                // pool total capacity
-    used_bytes: u64,                 // pool used space
-    data_drives: Vec<DriveInfo>,     // data member drives
-    parity_drives: Vec<DriveInfo>,   // parity drives
-}
-
-/// Individual filesystem on a drive
+/// A filesystem mounted on a drive
 #[derive(Debug, Clone)]
 struct Filesystem {
     mount_point: String,             // e.g., "/", "/boot"
-    total_bytes: u64,                // filesystem capacity
-    used_bytes: u64,                 // filesystem used space
+    usage_percent: f32,              // Usage percentage
+    used_bytes: u64,                 // Used bytes
+    total_bytes: u64,                // Total bytes
 }
 
-/// Drive information for pools
+/// MergerFS pool
 #[derive(Debug, Clone)]
-struct DriveInfo {
-    device: String,                   // e.g., "sdb", "sdc"
-    mount_point: String,             // e.g., "/mnt/disk1"
-    temperature: Option<f32>,        // drive temperature
-    wear_level: Option<f32>,         // SSD wear level  
-    health_status: String,           // SMART health
+struct MergerfsPool {
+    name: String,                    // e.g., "srv_media"
+    mount_point: String,             // e.g., "/srv/media"
+    total_bytes: u64,                // Pool total bytes
+    used_bytes: u64,                 // Pool used bytes
+    data_drives: Vec<PoolDrive>,     // Data drives in pool
+    parity_drives: Vec<PoolDrive>,   // Parity drives in pool
 }
 
-/// Discovered storage topology
-#[derive(Debug)]
-struct StorageTopology {
-    physical_drives: Vec<PhysicalDrive>,
-    mergerfs_pools: Vec<MergerfsPool>,
+/// Drive in a storage pool
+#[derive(Debug, Clone)]
+struct PoolDrive {
+    name: String,                    // Drive name
+    mount_point: String,             // e.g., "/mnt/disk1"
+    temperature_celsius: Option<f32>, // Drive temperature
 }
 
 impl DiskCollector {
     pub fn new(config: DiskConfig) -> Self {
-        let temperature_thresholds = HysteresisThresholds::with_custom_gaps(
+        let temperature_thresholds = HysteresisThresholds::new(
             config.temperature_warning_celsius,
-            5.0,
             config.temperature_critical_celsius,
-            5.0,
         );
         
         Self {
@@ -76,72 +65,88 @@ impl DiskCollector {
         }
     }
 
-    /// Discover all storage using clean workflow: lsblk → df → group
-    fn discover_storage(&self) -> Result<StorageTopology> {
-        debug!("Starting storage discovery");
+    /// Collect all storage data and populate AgentData
+    async fn collect_storage_data(&self, agent_data: &mut AgentData) -> Result<(), CollectorError> {
+        let start_time = Instant::now();
+        debug!("Starting clean storage collection");
 
-        // Step 1: Get all mount points and their backing devices using lsblk
-        let mount_devices = self.get_mount_devices()?;
-        debug!("Found {} mount points", mount_devices.len());
+        // Step 1: Get mount points and their backing devices
+        let mount_devices = self.get_mount_devices().await?;
         
         // Step 2: Get filesystem usage for each mount point using df
-        let filesystem_usage = self.get_filesystem_usage(&mount_devices)?;
-        debug!("Got usage data for {} filesystems", filesystem_usage.len());
+        let mut filesystem_usage = self.get_filesystem_usage(&mount_devices).map_err(|e| CollectorError::Parse {
+            value: "filesystem usage".to_string(),
+            error: format!("Failed to get filesystem usage: {}", e),
+        })?;
         
-        // Step 3: Detect mergerfs pools from /proc/mounts
-        let mergerfs_pools = self.discover_mergerfs_pools()?;
-        debug!("Found {} mergerfs pools", mergerfs_pools.len());
+        // Step 2.5: Add MergerFS mount points that weren't in lsblk output
+        self.add_mergerfs_filesystem_usage(&mut filesystem_usage).map_err(|e| CollectorError::Parse {
+            value: "mergerfs filesystem usage".to_string(),
+            error: format!("Failed to get mergerfs filesystem usage: {}", e),
+        })?;
         
-        // Step 4: Group regular filesystems by physical drive
-        let physical_drives = self.group_by_physical_drive(&mount_devices, &filesystem_usage, &mergerfs_pools)?;
-        debug!("Grouped into {} physical drives", physical_drives.len());
+        // Step 3: Detect MergerFS pools
+        let mergerfs_pools = self.detect_mergerfs_pools(&filesystem_usage).map_err(|e| CollectorError::Parse {
+            value: "mergerfs pools".to_string(),
+            error: format!("Failed to detect mergerfs pools: {}", e),
+        })?;
         
-        Ok(StorageTopology {
-            physical_drives,
-            mergerfs_pools,
-        })
+        // Step 4: Group filesystems by physical drive (excluding mergerfs members)
+        let physical_drives = self.group_by_physical_drive(&mount_devices, &filesystem_usage, &mergerfs_pools).map_err(|e| CollectorError::Parse {
+            value: "physical drives".to_string(),
+            error: format!("Failed to group by physical drive: {}", e),
+        })?;
+        
+        // Step 5: Get SMART data for all drives
+        let smart_data = self.get_smart_data_for_drives(&physical_drives, &mergerfs_pools).await;
+
+        // Step 6: Populate AgentData
+        self.populate_drives_data(&physical_drives, &smart_data, agent_data)?;
+        self.populate_pools_data(&mergerfs_pools, &smart_data, agent_data)?;
+
+        let elapsed = start_time.elapsed();
+        debug!("Storage collection completed in {:?}", elapsed);
+
+        Ok(())
     }
 
-    /// Use lsblk to get mount points and their backing devices
-    fn get_mount_devices(&self) -> Result<HashMap<String, String>> {
-        let output = Command::new("lsblk")
-            .args(&["-n", "-o", "NAME,MOUNTPOINT"])
-            .output()?;
+    /// Get block devices and their mount points using lsblk
+    async fn get_mount_devices(&self) -> Result<HashMap<String, String>, CollectorError> {
+        use super::run_command_with_timeout;
 
-        if !output.status.success() {
-            return Err(anyhow::anyhow!("lsblk command failed"));
-        }
+        let mut cmd = Command::new("lsblk");
+        cmd.args(&["-rn", "-o", "NAME,MOUNTPOINT"]);
+
+        let output = run_command_with_timeout(cmd, 2).await
+            .map_err(|e| CollectorError::SystemRead {
+                path: "block devices".to_string(),
+                error: e.to_string(),
+            })?;
 
         let mut mount_devices = HashMap::new();
-        let output_str = String::from_utf8_lossy(&output.stdout);
-        
-        for line in output_str.lines() {
+        for line in String::from_utf8_lossy(&output.stdout).lines() {
             let parts: Vec<&str> = line.split_whitespace().collect();
             if parts.len() >= 2 {
-                let device_name = parts[0]
-                    .trim_start_matches(&['├', '└', '─', ' '][..]);
+                let device_name = parts[0];
                 let mount_point = parts[1];
                 
-                // Skip unwanted mount points
-                if self.should_skip_mount_point(mount_point) {
+                // Skip swap partitions and unmounted devices
+                if mount_point == "[SWAP]" || mount_point.is_empty() {
                     continue;
                 }
                 
-                mount_devices.insert(mount_point.to_string(), device_name.to_string());
+                // Convert device name to full path
+                let device_path = format!("/dev/{}", device_name);
+                mount_devices.insert(mount_point.to_string(), device_path);
             }
         }
 
+        debug!("Found {} mounted block devices", mount_devices.len());
         Ok(mount_devices)
     }
 
-    /// Check if we should skip this mount point
-    fn should_skip_mount_point(&self, mount_point: &str) -> bool {
-        let skip_prefixes = ["/proc", "/sys", "/dev", "/tmp", "/run"];
-        skip_prefixes.iter().any(|prefix| mount_point.starts_with(prefix))
-    }
-
     /// Use df to get filesystem usage for mount points
-    fn get_filesystem_usage(&self, mount_devices: &HashMap<String, String>) -> Result<HashMap<String, (u64, u64)>> {
+    fn get_filesystem_usage(&self, mount_devices: &HashMap<String, String>) -> anyhow::Result<HashMap<String, (u64, u64)>> {
         let mut filesystem_usage = HashMap::new();
         
         for mount_point in mount_devices.keys() {
@@ -158,38 +163,76 @@ impl DiskCollector {
         Ok(filesystem_usage)
     }
 
-    /// Get filesystem info using df command
-    fn get_filesystem_info(&self, path: &str) -> Result<(u64, u64)> {
-        let output = Command::new("df")
-            .arg("--block-size=1")
-            .arg(path)
-            .output()?;
+    /// Add filesystem usage for MergerFS mount points that aren't in lsblk
+    fn add_mergerfs_filesystem_usage(&self, filesystem_usage: &mut HashMap<String, (u64, u64)>) -> anyhow::Result<()> {
+        let mounts_content = std::fs::read_to_string("/proc/mounts")
+            .map_err(|e| anyhow::anyhow!("Failed to read /proc/mounts: {}", e))?;
         
-        if !output.status.success() {
-            return Err(anyhow::anyhow!("df command failed for {}", path));
+        for line in mounts_content.lines() {
+            let parts: Vec<&str> = line.split_whitespace().collect();
+            if parts.len() >= 3 && parts[2] == "fuse.mergerfs" {
+                let mount_point = parts[1].to_string();
+                
+                // Only add if we don't already have usage data for this mount point
+                if !filesystem_usage.contains_key(&mount_point) {
+                    if let Ok((total, used)) = self.get_filesystem_info(&mount_point) {
+                        debug!("Added MergerFS filesystem usage for {}: {}GB total, {}GB used", 
+                            mount_point, total as f32 / (1024.0 * 1024.0 * 1024.0), used as f32 / (1024.0 * 1024.0 * 1024.0));
+                        filesystem_usage.insert(mount_point, (total, used));
+                    }
+                }
+            }
         }
         
-        let output_str = String::from_utf8(output.stdout)?;
+        Ok(())
+    }
+
+    /// Get filesystem info for a single mount point
+    fn get_filesystem_info(&self, mount_point: &str) -> Result<(u64, u64), CollectorError> {
+        let output = std::process::Command::new("timeout")
+            .args(&["2", "df", "--block-size=1", mount_point])
+            .output()
+            .map_err(|e| CollectorError::SystemRead {
+                path: format!("df {}", mount_point),
+                error: e.to_string(),
+            })?;
+
+        let output_str = String::from_utf8_lossy(&output.stdout);
         let lines: Vec<&str> = output_str.lines().collect();
         
         if lines.len() < 2 {
-            return Err(anyhow::anyhow!("Unexpected df output format"));
+            return Err(CollectorError::Parse {
+                value: output_str.to_string(),
+                error: "Expected at least 2 lines from df output".to_string(),
+            });
         }
 
-        let fields: Vec<&str> = lines[1].split_whitespace().collect();
-        if fields.len() < 4 {
-            return Err(anyhow::anyhow!("Unexpected df fields count"));
+        // Parse the data line (skip header)
+        let parts: Vec<&str> = lines[1].split_whitespace().collect();
+        if parts.len() < 4 {
+            return Err(CollectorError::Parse {
+                value: lines[1].to_string(),
+                error: "Expected at least 4 fields in df output".to_string(),
+            });
         }
 
-        let total_bytes = fields[1].parse::<u64>()?;
-        let used_bytes = fields[2].parse::<u64>()?;
+        let total_bytes: u64 = parts[1].parse().map_err(|e| CollectorError::Parse {
+            value: parts[1].to_string(),
+            error: format!("Failed to parse total bytes: {}", e),
+        })?;
+
+        let used_bytes: u64 = parts[2].parse().map_err(|e| CollectorError::Parse {
+            value: parts[2].to_string(),
+            error: format!("Failed to parse used bytes: {}", e),
+        })?;
 
         Ok((total_bytes, used_bytes))
     }
 
-    /// Discover mergerfs pools from /proc/mounts
-    fn discover_mergerfs_pools(&self) -> Result<Vec<MergerfsPool>> {
-        let mounts_content = std::fs::read_to_string("/proc/mounts")?;
+    /// Detect MergerFS pools from mount data
+    fn detect_mergerfs_pools(&self, filesystem_usage: &HashMap<String, (u64, u64)>) -> anyhow::Result<Vec<MergerfsPool>> {
+        let mounts_content = std::fs::read_to_string("/proc/mounts")
+            .map_err(|e| anyhow::anyhow!("Failed to read /proc/mounts: {}", e))?;
         let mut pools = Vec::new();
         
         for line in mounts_content.lines() {
@@ -199,9 +242,22 @@ impl DiskCollector {
                 let device_sources = parts[0]; // e.g., "/mnt/disk1:/mnt/disk2"
                 
                 // Get pool usage
-                let (total_bytes, used_bytes) = self.get_filesystem_info(&mount_point)
+                let (total_bytes, used_bytes) = filesystem_usage.get(&mount_point)
+                    .copied()
                     .unwrap_or((0, 0));
                 
+                // Extract pool name from mount point (e.g., "/srv/media" -> "srv_media")
+                let pool_name = if mount_point == "/" {
+                    "root".to_string()
+                } else {
+                    mount_point.trim_start_matches('/').replace('/', "_")
+                };
+                
+                if pool_name.is_empty() {
+                    debug!("Skipping mergerfs pool with empty name: {}", mount_point);
+                    continue;
+                }
+                
                 // Parse member paths - handle both full paths and numeric references
                 let raw_paths: Vec<String> = device_sources
                     .split(':')
@@ -210,7 +266,7 @@ impl DiskCollector {
                     .collect();
                 
                 // Convert numeric references to actual mount points if needed
-                let mut member_paths = if raw_paths.iter().any(|path| !path.starts_with('/')) {
+                let member_paths = if raw_paths.iter().any(|path| !path.starts_with('/')) {
                     // Handle numeric format like "1:2" by finding corresponding /mnt/disk* paths
                     self.resolve_numeric_mergerfs_paths(&raw_paths)?
                 } else {
@@ -219,11 +275,12 @@ impl DiskCollector {
                 };
                 
                 // For SnapRAID setups, include parity drives that are related to this pool's data drives
+                let mut all_member_paths = member_paths.clone();
                 let related_parity_paths = self.discover_related_parity_drives(&member_paths)?;
-                member_paths.extend(related_parity_paths);
+                all_member_paths.extend(related_parity_paths);
                 
                 // Categorize as data vs parity drives
-                let (data_drives, parity_drives) = match self.categorize_pool_drives(&member_paths) {
+                let (data_drives, parity_drives) = match self.categorize_pool_drives(&all_member_paths) {
                     Ok(drives) => drives,
                     Err(e) => {
                         debug!("Failed to categorize drives for pool {}: {}. Skipping.", mount_point, e);
@@ -232,6 +289,7 @@ impl DiskCollector {
                 };
                 
                 pools.push(MergerfsPool {
+                    name: pool_name,
                     mount_point,
                     total_bytes,
                     used_bytes,
@@ -241,12 +299,419 @@ impl DiskCollector {
             }
         }
         
+        debug!("Found {} mergerfs pools", pools.len());
         Ok(pools)
     }
 
+    /// Group filesystems by physical drive (excluding mergerfs members) - exact old logic
+    fn group_by_physical_drive(
+        &self, 
+        mount_devices: &HashMap<String, String>,
+        filesystem_usage: &HashMap<String, (u64, u64)>,
+        mergerfs_pools: &[MergerfsPool]
+    ) -> anyhow::Result<Vec<PhysicalDrive>> {
+        let mut drive_groups: HashMap<String, Vec<Filesystem>> = HashMap::new();
+        
+        // Get all mergerfs member paths to exclude them - exactly like old code
+        let mut mergerfs_members = std::collections::HashSet::new();
+        for pool in mergerfs_pools {
+            for drive in &pool.data_drives {
+                mergerfs_members.insert(drive.mount_point.clone());
+            }
+            for drive in &pool.parity_drives {
+                mergerfs_members.insert(drive.mount_point.clone());
+            }
+        }
+        
+        // Group filesystems by base device
+        for (mount_point, device) in mount_devices {
+            // Skip mergerfs member mounts
+            if mergerfs_members.contains(mount_point) {
+                continue;
+            }
+            
+            let base_device = self.extract_base_device(device);
+            
+            if let Some((total, used)) = filesystem_usage.get(mount_point) {
+                let usage_percent = (*used as f32 / *total as f32) * 100.0;
+                
+                let filesystem = Filesystem {
+                    mount_point: mount_point.clone(), // Keep actual mount point like "/" and "/boot"
+                    usage_percent,
+                    used_bytes: *used,
+                    total_bytes: *total,
+                };
+                
+                drive_groups.entry(base_device).or_insert_with(Vec::new).push(filesystem);
+            }
+        }
+        
+        // Convert to PhysicalDrive structs
+        let mut physical_drives = Vec::new();
+        for (drive_name, filesystems) in drive_groups {
+            let physical_drive = PhysicalDrive {
+                name: drive_name,
+                health: "UNKNOWN".to_string(), // Will be updated with SMART data
+                filesystems,
+            };
+            physical_drives.push(physical_drive);
+        }
+        
+        physical_drives.sort_by(|a, b| a.name.cmp(&b.name));
+        Ok(physical_drives)
+    }
+
+    /// Extract base device name from device path
+    fn extract_base_device(&self, device: &str) -> String {
+        // Extract base device name (e.g., "/dev/nvme0n1p1" -> "nvme0n1")
+        if let Some(dev_name) = device.strip_prefix("/dev/") {
+            // Remove partition numbers: nvme0n1p1 -> nvme0n1, sda1 -> sda
+            if let Some(pos) = dev_name.find('p') {
+                if dev_name[pos+1..].chars().all(char::is_numeric) {
+                    return dev_name[..pos].to_string();
+                }
+            }
+            // Handle traditional naming: sda1 -> sda
+            let mut result = String::new();
+            for ch in dev_name.chars() {
+                if ch.is_ascii_digit() {
+                    break;
+                }
+                result.push(ch);
+            }
+            if !result.is_empty() {
+                return result;
+            }
+        }
+        device.to_string()
+    }
+
+    /// Get SMART data for drives
+    async fn get_smart_data_for_drives(&self, physical_drives: &[PhysicalDrive], mergerfs_pools: &[MergerfsPool]) -> HashMap<String, SmartData> {
+        let mut smart_data = HashMap::new();
+
+        // Collect all drive names
+        let mut all_drives = std::collections::HashSet::new();
+        for drive in physical_drives {
+            all_drives.insert(drive.name.clone());
+        }
+        for pool in mergerfs_pools {
+            for drive in &pool.data_drives {
+                all_drives.insert(drive.name.clone());
+            }
+            for drive in &pool.parity_drives {
+                all_drives.insert(drive.name.clone());
+            }
+        }
+
+        // Get SMART data for each drive
+        for drive_name in all_drives {
+            if let Ok(data) = self.get_smart_data(&drive_name).await {
+                smart_data.insert(drive_name, data);
+            }
+        }
+
+        smart_data
+    }
+
+    /// Get SMART data for a single drive
+    async fn get_smart_data(&self, drive_name: &str) -> Result<SmartData, CollectorError> {
+        use super::run_command_with_timeout;
+
+        // Use direct smartctl (no sudo) - service has CAP_SYS_RAWIO and CAP_SYS_ADMIN capabilities
+        // For NVMe drives, specify device type explicitly
+        let mut cmd = Command::new("smartctl");
+        if drive_name.starts_with("nvme") {
+            cmd.args(&["-d", "nvme", "-a", &format!("/dev/{}", drive_name)]);
+        } else {
+            cmd.args(&["-a", &format!("/dev/{}", drive_name)]);
+        }
+
+        let output = run_command_with_timeout(cmd, 3).await
+            .map_err(|e| CollectorError::SystemRead {
+                path: format!("SMART data for {}", drive_name),
+                error: e.to_string(),
+            })?;
+
+        let output_str = String::from_utf8_lossy(&output.stdout);
+
+        if !output.status.success() {
+            // Return unknown data rather than failing completely
+            return Ok(SmartData {
+                health: "UNKNOWN".to_string(),
+                serial_number: None,
+                temperature_celsius: None,
+                wear_percent: None,
+            });
+        }
+        
+        let mut health = "UNKNOWN".to_string();
+        let mut serial_number = None;
+        let mut temperature = None;
+        let mut wear_percent = None;
+
+        for line in output_str.lines() {
+            if line.contains("SMART overall-health") {
+                if line.contains("PASSED") {
+                    health = "PASSED".to_string();
+                } else if line.contains("FAILED") {
+                    health = "FAILED".to_string();
+                }
+            }
+            
+            // Serial number parsing (both SATA and NVMe)
+            if line.contains("Serial Number:") {
+                if let Some(serial_part) = line.split("Serial Number:").nth(1) {
+                    let serial_str = serial_part.trim();
+                    if !serial_str.is_empty() {
+                        // Take first whitespace-separated token
+                        if let Some(serial) = serial_str.split_whitespace().next() {
+                            serial_number = Some(serial.to_string());
+                        }
+                    }
+                }
+            }
+            
+            // Temperature parsing for different drive types
+            if line.contains("Temperature_Celsius") || line.contains("Airflow_Temperature_Cel") || line.contains("Temperature_Case") {
+                // Traditional SATA drives: attribute table format
+                if let Some(temp_str) = line.split_whitespace().nth(9) {
+                    if let Ok(temp) = temp_str.parse::<f32>() {
+                        temperature = Some(temp);
+                    }
+                }
+            } else if line.starts_with("Temperature:") {
+                // NVMe drives: simple "Temperature: 27 Celsius" format
+                let parts: Vec<&str> = line.split_whitespace().collect();
+                if parts.len() >= 2 {
+                    if let Ok(temp) = parts[1].parse::<f32>() {
+                        temperature = Some(temp);
+                    }
+                }
+            }
+            
+            // Wear level parsing for SSDs
+            if line.contains("Media_Wearout_Indicator") {
+                // Media_Wearout_Indicator stores remaining life % in column 3 (VALUE)
+                if let Some(wear_str) = line.split_whitespace().nth(3) {
+                    if let Ok(remaining) = wear_str.parse::<f32>() {
+                        wear_percent = Some(100.0 - remaining); // Convert remaining life to wear
+                    }
+                }
+            } else if line.contains("Wear_Leveling_Count") || line.contains("SSD_Life_Left") {
+                // Other wear attributes store value in column 9 (RAW_VALUE)
+                if let Some(wear_str) = line.split_whitespace().nth(9) {
+                    if let Ok(wear) = wear_str.parse::<f32>() {
+                        wear_percent = Some(100.0 - wear); // Convert remaining life to wear
+                    }
+                }
+            }
+            // NVMe wear parsing: "Percentage Used: 1%"
+            if line.contains("Percentage Used:") {
+                if let Some(percent_part) = line.split("Percentage Used:").nth(1) {
+                    if let Some(percent_str) = percent_part.split_whitespace().next() {
+                        if let Some(percent_clean) = percent_str.strip_suffix('%') {
+                            if let Ok(wear) = percent_clean.parse::<f32>() {
+                                wear_percent = Some(wear);
+                            }
+                        }
+                    }
+                }
+            }
+        }
+
+        Ok(SmartData {
+            health,
+            serial_number,
+            temperature_celsius: temperature,
+            wear_percent,
+        })
+    }
+
+    /// Populate drives data into AgentData
+    fn populate_drives_data(&self, physical_drives: &[PhysicalDrive], smart_data: &HashMap<String, SmartData>, agent_data: &mut AgentData) -> Result<(), CollectorError> {
+        for drive in physical_drives {
+            let smart = smart_data.get(&drive.name);
+            
+            let mut filesystems: Vec<FilesystemData> = drive.filesystems.iter().map(|fs| {
+                FilesystemData {
+                    mount: fs.mount_point.clone(), // This preserves "/" and "/boot" correctly
+                    usage_percent: fs.usage_percent,
+                    used_gb: fs.used_bytes as f32 / (1024.0 * 1024.0 * 1024.0),
+                    total_gb: fs.total_bytes as f32 / (1024.0 * 1024.0 * 1024.0),
+                    usage_status: self.calculate_filesystem_usage_status(fs.usage_percent),
+                }
+            }).collect();
+            
+            // Sort filesystems by mount point for consistent display order
+            filesystems.sort_by(|a, b| a.mount.cmp(&b.mount));
+
+            agent_data.system.storage.drives.push(DriveData {
+                name: drive.name.clone(),
+                serial_number: smart.and_then(|s| s.serial_number.clone()),
+                health: smart.map(|s| s.health.clone()).unwrap_or_else(|| drive.health.clone()),
+                temperature_celsius: smart.and_then(|s| s.temperature_celsius),
+                wear_percent: smart.and_then(|s| s.wear_percent),
+                filesystems,
+                temperature_status: smart.and_then(|s| s.temperature_celsius)
+                    .map(|temp| self.calculate_temperature_status(temp))
+                    .unwrap_or(Status::Unknown),
+                health_status: self.calculate_health_status(
+                    smart.map(|s| s.health.as_str()).unwrap_or("UNKNOWN")
+                ),
+            });
+        }
+
+        Ok(())
+    }
+
+    /// Populate pools data into AgentData
+    fn populate_pools_data(&self, mergerfs_pools: &[MergerfsPool], smart_data: &HashMap<String, SmartData>, agent_data: &mut AgentData) -> Result<(), CollectorError> {
+        for pool in mergerfs_pools {
+            // Calculate pool health and statuses based on member drive health
+            let (pool_health, health_status, usage_status, data_drive_data, parity_drive_data) = self.calculate_pool_health(pool, smart_data);
+            
+            let pool_data = PoolData {
+                name: pool.name.clone(),
+                mount: pool.mount_point.clone(),
+                pool_type: format!("mergerfs ({}+{})", pool.data_drives.len(), pool.parity_drives.len()),
+                health: pool_health,
+                usage_percent: if pool.total_bytes > 0 {
+                    (pool.used_bytes as f32 / pool.total_bytes as f32) * 100.0
+                } else { 0.0 },
+                used_gb: pool.used_bytes as f32 / (1024.0 * 1024.0 * 1024.0),
+                total_gb: pool.total_bytes as f32 / (1024.0 * 1024.0 * 1024.0),
+                data_drives: data_drive_data,
+                parity_drives: parity_drive_data,
+                health_status,
+                usage_status,
+            };
+
+            agent_data.system.storage.pools.push(pool_data);
+        }
+
+        Ok(())
+    }
+
+    /// Calculate pool health based on member drive status
+    fn calculate_pool_health(&self, pool: &MergerfsPool, smart_data: &HashMap<String, SmartData>) -> (String, cm_dashboard_shared::Status, cm_dashboard_shared::Status, Vec<cm_dashboard_shared::PoolDriveData>, Vec<cm_dashboard_shared::PoolDriveData>) {
+        let mut failed_data = 0;
+        let mut failed_parity = 0;
+        
+        // Process data drives
+        let data_drive_data: Vec<cm_dashboard_shared::PoolDriveData> = pool.data_drives.iter().map(|d| {
+            let smart = smart_data.get(&d.name);
+            let health = smart.map(|s| s.health.clone()).unwrap_or_else(|| "UNKNOWN".to_string());
+            let temperature = smart.and_then(|s| s.temperature_celsius).or(d.temperature_celsius);
+            
+            if health == "FAILED" {
+                failed_data += 1;
+            }
+            
+            // Calculate drive statuses using config thresholds
+            let health_status = self.calculate_health_status(&health);
+            let temperature_status = temperature.map(|t| self.temperature_thresholds.evaluate(t)).unwrap_or(cm_dashboard_shared::Status::Unknown);
+            
+            cm_dashboard_shared::PoolDriveData {
+                name: d.name.clone(),
+                serial_number: smart.and_then(|s| s.serial_number.clone()),
+                temperature_celsius: temperature,
+                health,
+                wear_percent: smart.and_then(|s| s.wear_percent),
+                health_status,
+                temperature_status,
+            }
+        }).collect();
+        
+        // Process parity drives
+        let parity_drive_data: Vec<cm_dashboard_shared::PoolDriveData> = pool.parity_drives.iter().map(|d| {
+            let smart = smart_data.get(&d.name);
+            let health = smart.map(|s| s.health.clone()).unwrap_or_else(|| "UNKNOWN".to_string());
+            let temperature = smart.and_then(|s| s.temperature_celsius).or(d.temperature_celsius);
+            
+            if health == "FAILED" {
+                failed_parity += 1;
+            }
+            
+            // Calculate drive statuses using config thresholds
+            let health_status = self.calculate_health_status(&health);
+            let temperature_status = temperature.map(|t| self.temperature_thresholds.evaluate(t)).unwrap_or(cm_dashboard_shared::Status::Unknown);
+            
+            cm_dashboard_shared::PoolDriveData {
+                name: d.name.clone(),
+                serial_number: smart.and_then(|s| s.serial_number.clone()),
+                temperature_celsius: temperature,
+                health,
+                wear_percent: smart.and_then(|s| s.wear_percent),
+                health_status,
+                temperature_status,
+            }
+        }).collect();
+        
+        // Calculate overall pool health string and status
+        // SnapRAID logic: can tolerate up to N parity drive failures (where N = number of parity drives)
+        // If data drives fail AND we've lost parity protection, that's critical
+        let (pool_health, health_status) = if failed_data == 0 && failed_parity == 0 {
+            ("healthy".to_string(), cm_dashboard_shared::Status::Ok)
+        } else if failed_data == 0 && failed_parity > 0 {
+            // Parity failed but no data loss - degraded (reduced protection)
+            ("degraded".to_string(), cm_dashboard_shared::Status::Warning)
+        } else if failed_data == 1 && failed_parity == 0 {
+            // One data drive failed, parity intact - degraded (recoverable)
+            ("degraded".to_string(), cm_dashboard_shared::Status::Warning)
+        } else {
+            // Multiple data drives failed OR data+parity failed = data loss risk
+            ("critical".to_string(), cm_dashboard_shared::Status::Critical)
+        };
+        
+        // Calculate pool usage status using config thresholds
+        let usage_percent = if pool.total_bytes > 0 {
+            (pool.used_bytes as f32 / pool.total_bytes as f32) * 100.0
+        } else { 0.0 };
+        
+        let usage_status = if usage_percent >= self.config.usage_critical_percent {
+            cm_dashboard_shared::Status::Critical
+        } else if usage_percent >= self.config.usage_warning_percent {
+            cm_dashboard_shared::Status::Warning
+        } else {
+            cm_dashboard_shared::Status::Ok
+        };
+        
+        (pool_health, health_status, usage_status, data_drive_data, parity_drive_data)
+    }
+
+    /// Calculate filesystem usage status
+    fn calculate_filesystem_usage_status(&self, usage_percent: f32) -> Status {
+        // Use standard filesystem warning/critical thresholds
+        if usage_percent >= 95.0 {
+            Status::Critical
+        } else if usage_percent >= 85.0 {
+            Status::Warning
+        } else {
+            Status::Ok
+        }
+    }
+
+    /// Calculate drive temperature status
+    fn calculate_temperature_status(&self, temperature: f32) -> Status {
+        self.temperature_thresholds.evaluate(temperature)
+    }
+
+    /// Calculate drive health status
+    fn calculate_health_status(&self, health: &str) -> Status {
+        match health {
+            "PASSED" => Status::Ok,
+            "FAILED" => Status::Critical,
+            _ => Status::Unknown,
+        }
+    }
+
     /// Discover parity drives that are related to the given data drives
-    fn discover_related_parity_drives(&self, data_drives: &[String]) -> Result<Vec<String>> {
-        let mount_devices = self.get_mount_devices()?;
+    fn discover_related_parity_drives(&self, data_drives: &[String]) -> anyhow::Result<Vec<String>> {
+        let mount_devices = tokio::task::block_in_place(|| {
+            tokio::runtime::Handle::current().block_on(self.get_mount_devices())
+        }).map_err(|e| anyhow::anyhow!("Failed to get mount devices: {}", e))?;
+        
         let mut related_parity = Vec::new();
         
         // Find parity drives that share the same parent directory as the data drives
@@ -277,7 +742,7 @@ impl DiskCollector {
     }
 
     /// Categorize pool member drives as data vs parity
-    fn categorize_pool_drives(&self, member_paths: &[String]) -> Result<(Vec<DriveInfo>, Vec<DriveInfo>)> {
+    fn categorize_pool_drives(&self, member_paths: &[String]) -> anyhow::Result<(Vec<PoolDrive>, Vec<PoolDrive>)> {
         let mut data_drives = Vec::new();
         let mut parity_drives = Vec::new();
         
@@ -296,11 +761,12 @@ impl DiskCollector {
     }
 
     /// Get drive information for a mount path
-    fn get_drive_info_for_path(&self, path: &str) -> Result<DriveInfo> {
-        // Use lsblk to find the backing device
-        let output = Command::new("lsblk")
-            .args(&["-n", "-o", "NAME,MOUNTPOINT"])
-            .output()?;
+    fn get_drive_info_for_path(&self, path: &str) -> anyhow::Result<PoolDrive> {
+        // Use lsblk to find the backing device with timeout
+        let output = Command::new("timeout")
+            .args(&["2", "lsblk", "-rn", "-o", "NAME,MOUNTPOINT"])
+            .output()
+            .map_err(|e| anyhow::anyhow!("Failed to run lsblk: {}", e))?;
             
         let output_str = String::from_utf8_lossy(&output.stdout);
         let mut device = String::new();
@@ -308,12 +774,7 @@ impl DiskCollector {
         for line in output_str.lines() {
             let parts: Vec<&str> = line.split_whitespace().collect();
             if parts.len() >= 2 && parts[1] == path {
-                device = parts[0]
-                    .trim_start_matches('├')
-                    .trim_start_matches('└')
-                    .trim_start_matches('─')
-                    .trim()
-                    .to_string();
+                device = parts[0].to_string();
                 break;
             }
         }
@@ -323,26 +784,33 @@ impl DiskCollector {
         }
         
         // Extract base device name (e.g., "sda1" -> "sda")
-        let base_device = self.extract_base_device(&device);
+        let base_device = self.extract_base_device(&format!("/dev/{}", device));
         
-        // Get SMART data
-        let (health, temperature, wear) = self.get_smart_data(&format!("/dev/{}", base_device));
+        // Get temperature from SMART data if available
+        let temperature = if let Ok(smart_data) = tokio::task::block_in_place(|| {
+            tokio::runtime::Handle::current().block_on(self.get_smart_data(&base_device))
+        }) {
+            smart_data.temperature_celsius
+        } else {
+            None
+        };
         
-        Ok(DriveInfo {
-            device: base_device,
+        Ok(PoolDrive {
+            name: base_device,
             mount_point: path.to_string(),
-            temperature,
-            wear_level: wear,
-            health_status: health,
+            temperature_celsius: temperature,
         })
     }
 
     /// Resolve numeric mergerfs references like "1:2" to actual mount paths
-    fn resolve_numeric_mergerfs_paths(&self, numeric_refs: &[String]) -> Result<Vec<String>> {
+    fn resolve_numeric_mergerfs_paths(&self, numeric_refs: &[String]) -> anyhow::Result<Vec<String>> {
         let mut resolved_paths = Vec::new();
         
         // Get all mount points that look like /mnt/disk* or /mnt/parity*
-        let mount_devices = self.get_mount_devices()?;
+        let mount_devices = tokio::task::block_in_place(|| {
+            tokio::runtime::Handle::current().block_on(self.get_mount_devices())
+        }).map_err(|e| anyhow::anyhow!("Failed to get mount devices: {}", e))?;
+        
         let mut disk_mounts: Vec<String> = mount_devices.keys()
             .filter(|path| path.starts_with("/mnt/disk") || path.starts_with("/mnt/parity"))
             .cloned()
@@ -365,637 +833,20 @@ impl DiskCollector {
         
         Ok(resolved_paths)
     }
-
-    /// Extract base device name from partition (e.g., "nvme0n1p2" -> "nvme0n1", "sda1" -> "sda")
-    fn extract_base_device(&self, device_name: &str) -> String {
-        // Handle NVMe devices (nvme0n1p1 -> nvme0n1)
-        if device_name.starts_with("nvme") {
-            if let Some(p_pos) = device_name.find('p') {
-                return device_name[..p_pos].to_string();
-            }
-        }
-        
-        // Handle traditional devices (sda1 -> sda)
-        if device_name.len() > 1 {
-            let chars: Vec<char> = device_name.chars().collect();
-            let mut end_idx = chars.len();
-            
-            // Find where the device name ends and partition number begins
-            for (i, &c) in chars.iter().enumerate().rev() {
-                if !c.is_ascii_digit() {
-                    end_idx = i + 1;
-                    break;
-                }
-            }
-            
-            if end_idx > 0 && end_idx < chars.len() {
-                return chars[..end_idx].iter().collect();
-            }
-        }
-        
-        // If no partition detected, return as-is
-        device_name.to_string()
-    }
-
-    /// Group filesystems by physical drive (excluding mergerfs members)
-    fn group_by_physical_drive(
-        &self, 
-        mount_devices: &HashMap<String, String>,
-        filesystem_usage: &HashMap<String, (u64, u64)>,
-        mergerfs_pools: &[MergerfsPool]
-    ) -> Result<Vec<PhysicalDrive>> {
-        let mut drive_groups: HashMap<String, Vec<Filesystem>> = HashMap::new();
-        
-        // Get all mergerfs member paths to exclude them
-        let mut mergerfs_members = std::collections::HashSet::new();
-        for pool in mergerfs_pools {
-            for drive in &pool.data_drives {
-                mergerfs_members.insert(drive.mount_point.clone());
-            }
-            for drive in &pool.parity_drives {
-                mergerfs_members.insert(drive.mount_point.clone());
-            }
-        }
-        
-        // Group filesystems by base device
-        for (mount_point, device) in mount_devices {
-            // Skip mergerfs member mounts
-            if mergerfs_members.contains(mount_point) {
-                continue;
-            }
-            
-            let base_device = self.extract_base_device(device);
-            
-            if let Some((total, used)) = filesystem_usage.get(mount_point) {
-                let filesystem = Filesystem {
-                    mount_point: mount_point.clone(),
-                    total_bytes: *total,
-                    used_bytes: *used,
-                };
-                
-                drive_groups.entry(base_device).or_insert_with(Vec::new).push(filesystem);
-            }
-        }
-        
-        // Convert to PhysicalDrive structs with SMART data
-        let mut physical_drives = Vec::new();
-        for (device, filesystems) in drive_groups {
-            let (health, temperature, wear) = self.get_smart_data(&format!("/dev/{}", device));
-            
-            physical_drives.push(PhysicalDrive {
-                device,
-                filesystems,
-                temperature,
-                wear_level: wear,
-                health_status: health,
-            });
-        }
-        
-        Ok(physical_drives)
-    }
-
-    /// Get SMART data for a drive
-    fn get_smart_data(&self, device_path: &str) -> (String, Option<f32>, Option<f32>) {
-        let output = Command::new("sudo")
-            .arg("smartctl")
-            .arg("-a")
-            .arg(device_path)
-            .output();
-            
-        match output {
-            Ok(result) if result.status.success() => {
-                let stdout = String::from_utf8_lossy(&result.stdout);
-                
-                // Parse health status
-                let health = if stdout.contains("PASSED") {
-                    "PASSED".to_string()
-                } else if stdout.contains("FAILED") {
-                    "FAILED".to_string()
-                } else {
-                    "UNKNOWN".to_string()
-                };
-                
-                // Parse temperature and wear level
-                let temperature = self.parse_temperature_from_smart(&stdout);
-                let wear_level = self.parse_wear_level_from_smart(&stdout);
-                
-                (health, temperature, wear_level)
-            }
-            _ => {
-                debug!("Failed to get SMART data for {}", device_path);
-                ("UNKNOWN".to_string(), None, None)
-            }
-        }
-    }
-
-    /// Parse temperature from SMART output
-    fn parse_temperature_from_smart(&self, smart_output: &str) -> Option<f32> {
-        for line in smart_output.lines() {
-            if line.contains("Temperature_Celsius") || line.contains("Temperature") {
-                let parts: Vec<&str> = line.split_whitespace().collect();
-                if parts.len() >= 10 {
-                    if let Ok(temp) = parts[9].parse::<f32>() {
-                        return Some(temp);
-                    }
-                }
-            }
-            // NVMe format: "Temperature:" (capital T)
-            if line.contains("Temperature:") {
-                if let Some(temp_part) = line.split("Temperature:").nth(1) {
-                    if let Some(temp_str) = temp_part.split_whitespace().next() {
-                        if let Ok(temp) = temp_str.parse::<f32>() {
-                            return Some(temp);
-                        }
-                    }
-                }
-            }
-            // Legacy format: "temperature:" (lowercase)
-            if line.contains("temperature:") {
-                if let Some(temp_part) = line.split("temperature:").nth(1) {
-                    if let Some(temp_str) = temp_part.split_whitespace().next() {
-                        if let Ok(temp) = temp_str.parse::<f32>() {
-                            return Some(temp);
-                        }
-                    }
-                }
-            }
-        }
-        None
-    }
-
-    /// Parse wear level from SMART output
-    fn parse_wear_level_from_smart(&self, smart_output: &str) -> Option<f32> {
-        for line in smart_output.lines() {
-            if line.contains("Percentage Used:") {
-                if let Some(wear_part) = line.split("Percentage Used:").nth(1) {
-                    if let Some(wear_str) = wear_part.split('%').next() {
-                        if let Ok(wear) = wear_str.trim().parse::<f32>() {
-                            return Some(wear);
-                        }
-                    }
-                }
-            }
-            
-            let parts: Vec<&str> = line.split_whitespace().collect();
-            if parts.len() >= 10 {
-                if line.contains("SSD_Life_Left") || line.contains("Percent_Lifetime_Remain") {
-                    if let Ok(remaining) = parts[3].parse::<f32>() {
-                        return Some(100.0 - remaining);
-                    }
-                }
-                if line.contains("Wear_Leveling_Count") {
-                    if let Ok(wear_count) = parts[3].parse::<f32>() {
-                        if wear_count <= 100.0 {
-                            return Some(100.0 - wear_count);
-                        }
-                    }
-                }
-            }
-        }
-        None
-    }
-
-    /// Calculate temperature status with hysteresis
-    fn calculate_temperature_status(&self, metric_name: &str, temperature: f32, status_tracker: &mut StatusTracker) -> Status {
-        status_tracker.calculate_with_hysteresis(metric_name, temperature, &self.temperature_thresholds)
-    }
-
-    /// Convert bytes to human readable format
-    fn bytes_to_human_readable(&self, bytes: u64) -> String {
-        const UNITS: &[&str] = &["B", "K", "M", "G", "T"];
-        let mut size = bytes as f64;
-        let mut unit_index = 0;
-
-        while size >= 1024.0 && unit_index < UNITS.len() - 1 {
-            size /= 1024.0;
-            unit_index += 1;
-        }
-
-        if unit_index == 0 {
-            format!("{:.0}{}", size, UNITS[unit_index])
-        } else {
-            format!("{:.1}{}", size, UNITS[unit_index])
-        }
-    }
-
-    /// Convert bytes to gigabytes
-    fn bytes_to_gb(&self, bytes: u64) -> f32 {
-        bytes as f32 / (1024.0 * 1024.0 * 1024.0)
-    }
 }
 
 #[async_trait]
 impl Collector for DiskCollector {
-    async fn collect(&self, status_tracker: &mut StatusTracker) -> Result<Vec<Metric>, CollectorError> {
-        let start_time = Instant::now();
-        debug!("Starting clean storage collection");
-
-        let mut metrics = Vec::new();
-        let timestamp = chrono::Utc::now().timestamp() as u64;
-
-        // Discover storage topology
-        let topology = match self.discover_storage() {
-            Ok(topology) => topology,
-            Err(e) => {
-                tracing::error!("Storage discovery failed: {}", e);
-                return Ok(metrics);
-            }
-        };
-
-        // Generate metrics for physical drives
-        for drive in &topology.physical_drives {
-            self.generate_physical_drive_metrics(&mut metrics, drive, timestamp, status_tracker);
-        }
-
-        // Generate metrics for mergerfs pools
-        for pool in &topology.mergerfs_pools {
-            self.generate_mergerfs_pool_metrics(&mut metrics, pool, timestamp, status_tracker);
-        }
-
-        // Add total storage count
-        let total_storage = topology.physical_drives.len() + topology.mergerfs_pools.len();
-        metrics.push(Metric {
-            name: "disk_count".to_string(),
-            value: MetricValue::Integer(total_storage as i64),
-            unit: None,
-            description: Some(format!("Total storage: {} drives, {} pools", topology.physical_drives.len(), topology.mergerfs_pools.len())),
-            status: Status::Ok,
-            timestamp,
-        });
-
-        let collection_time = start_time.elapsed();
-        debug!("Clean storage collection completed in {:?} with {} metrics", collection_time, metrics.len());
-
-        Ok(metrics)
+    async fn collect_structured(&self, agent_data: &mut AgentData) -> Result<(), CollectorError> {
+        self.collect_storage_data(agent_data).await
     }
 }
 
-impl DiskCollector {
-    /// Generate metrics for a physical drive and its filesystems
-    fn generate_physical_drive_metrics(
-        &self,
-        metrics: &mut Vec<Metric>,
-        drive: &PhysicalDrive,
-        timestamp: u64,
-        status_tracker: &mut StatusTracker
-    ) {
-        let drive_name = &drive.device;
-        
-        // Calculate drive totals
-        let total_capacity: u64 = drive.filesystems.iter().map(|fs| fs.total_bytes).sum();
-        let total_used: u64 = drive.filesystems.iter().map(|fs| fs.used_bytes).sum();
-        let total_available = total_capacity.saturating_sub(total_used);
-        let usage_percent = if total_capacity > 0 {
-            (total_used as f64 / total_capacity as f64) * 100.0
-        } else { 0.0 };
-        
-        // Drive health status
-        let health_status = if drive.health_status == "PASSED" { Status::Ok } 
-                           else if drive.health_status == "FAILED" { Status::Critical }
-                           else { Status::Unknown };
-        
-        // Usage status
-        let usage_status = if usage_percent >= self.config.usage_critical_percent as f64 {
-            Status::Critical
-        } else if usage_percent >= self.config.usage_warning_percent as f64 {
-            Status::Warning
-        } else {
-            Status::Ok
-        };
-        
-        let drive_status = if health_status == Status::Critical { Status::Critical } else { usage_status };
-
-        // Drive info metrics
-        metrics.push(Metric {
-            name: format!("disk_{}_health", drive_name),
-            value: MetricValue::String(drive.health_status.clone()),
-            unit: None,
-            description: Some(format!("{}: {}", drive_name, drive.health_status)),
-            status: health_status,
-            timestamp,
-        });
-
-        // Drive temperature
-        if let Some(temp) = drive.temperature {
-            let temp_status = self.calculate_temperature_status(
-                &format!("disk_{}_temperature", drive_name), temp, status_tracker
-            );
-            metrics.push(Metric {
-                name: format!("disk_{}_temperature", drive_name),
-                value: MetricValue::Float(temp),
-                unit: Some("°C".to_string()),
-                description: Some(format!("{}: {:.0}°C", drive_name, temp)),
-                status: temp_status,
-                timestamp,
-            });
-        }
-
-        // Drive wear level
-        if let Some(wear) = drive.wear_level {
-            let wear_status = if wear >= self.config.wear_critical_percent { Status::Critical }
-                             else if wear >= self.config.wear_warning_percent { Status::Warning }
-                             else { Status::Ok };
-            metrics.push(Metric {
-                name: format!("disk_{}_wear_percent", drive_name),
-                value: MetricValue::Float(wear),
-                unit: Some("%".to_string()),
-                description: Some(format!("{}: {:.0}% wear", drive_name, wear)),
-                status: wear_status,
-                timestamp,
-            });
-        }
-
-        // Drive capacity metrics
-        metrics.push(Metric {
-            name: format!("disk_{}_total_gb", drive_name),
-            value: MetricValue::Float(self.bytes_to_gb(total_capacity)),
-            unit: Some("GB".to_string()),
-            description: Some(format!("{}: {}", drive_name, self.bytes_to_human_readable(total_capacity))),
-            status: Status::Ok,
-            timestamp,
-        });
-
-        metrics.push(Metric {
-            name: format!("disk_{}_used_gb", drive_name),
-            value: MetricValue::Float(self.bytes_to_gb(total_used)),
-            unit: Some("GB".to_string()),
-            description: Some(format!("{}: {}", drive_name, self.bytes_to_human_readable(total_used))),
-            status: drive_status.clone(),
-            timestamp,
-        });
-
-        metrics.push(Metric {
-            name: format!("disk_{}_available_gb", drive_name),
-            value: MetricValue::Float(self.bytes_to_gb(total_available)),
-            unit: Some("GB".to_string()),
-            description: Some(format!("{}: {}", drive_name, self.bytes_to_human_readable(total_available))),
-            status: Status::Ok,
-            timestamp,
-        });
-
-        metrics.push(Metric {
-            name: format!("disk_{}_usage_percent", drive_name),
-            value: MetricValue::Float(usage_percent as f32),
-            unit: Some("%".to_string()),
-            description: Some(format!("{}: {:.1}%", drive_name, usage_percent)),
-            status: drive_status,
-            timestamp,
-        });
-
-        // Pool type indicator
-        metrics.push(Metric {
-            name: format!("disk_{}_pool_type", drive_name),
-            value: MetricValue::String(format!("drive ({})", drive.filesystems.len())),
-            unit: None,
-            description: Some(format!("Type: physical drive")),
-            status: Status::Ok,
-            timestamp,
-        });
-
-        // Individual filesystem metrics
-        for filesystem in &drive.filesystems {
-            let fs_name = if filesystem.mount_point == "/" {
-                "root".to_string()
-            } else {
-                filesystem.mount_point.trim_start_matches('/').replace('/', "_")
-            };
-
-            let fs_usage_percent = if filesystem.total_bytes > 0 {
-                (filesystem.used_bytes as f64 / filesystem.total_bytes as f64) * 100.0
-            } else { 0.0 };
-
-            let fs_status = if fs_usage_percent >= self.config.usage_critical_percent as f64 {
-                Status::Critical
-            } else if fs_usage_percent >= self.config.usage_warning_percent as f64 {
-                Status::Warning
-            } else {
-                Status::Ok
-            };
-
-            metrics.push(Metric {
-                name: format!("disk_{}_fs_{}_usage_percent", drive_name, fs_name),
-                value: MetricValue::Float(fs_usage_percent as f32),
-                unit: Some("%".to_string()),
-                description: Some(format!("{}: {:.0}%", filesystem.mount_point, fs_usage_percent)),
-                status: fs_status.clone(),
-                timestamp,
-            });
-
-            metrics.push(Metric {
-                name: format!("disk_{}_fs_{}_used_gb", drive_name, fs_name),
-                value: MetricValue::Float(self.bytes_to_gb(filesystem.used_bytes)),
-                unit: Some("GB".to_string()),
-                description: Some(format!("{}: {}", filesystem.mount_point, self.bytes_to_human_readable(filesystem.used_bytes))),
-                status: fs_status.clone(),
-                timestamp,
-            });
-
-            metrics.push(Metric {
-                name: format!("disk_{}_fs_{}_total_gb", drive_name, fs_name),
-                value: MetricValue::Float(self.bytes_to_gb(filesystem.total_bytes)),
-                unit: Some("GB".to_string()),
-                description: Some(format!("{}: {}", filesystem.mount_point, self.bytes_to_human_readable(filesystem.total_bytes))),
-                status: fs_status.clone(),
-                timestamp,
-            });
-
-            let fs_available = filesystem.total_bytes.saturating_sub(filesystem.used_bytes);
-            metrics.push(Metric {
-                name: format!("disk_{}_fs_{}_available_gb", drive_name, fs_name),
-                value: MetricValue::Float(self.bytes_to_gb(fs_available)),
-                unit: Some("GB".to_string()),
-                description: Some(format!("{}: {}", filesystem.mount_point, self.bytes_to_human_readable(fs_available))),
-                status: Status::Ok,
-                timestamp,
-            });
-
-            metrics.push(Metric {
-                name: format!("disk_{}_fs_{}_mount_point", drive_name, fs_name),
-                value: MetricValue::String(filesystem.mount_point.clone()),
-                unit: None,
-                description: Some(format!("Mount: {}", filesystem.mount_point)),
-                status: Status::Ok,
-                timestamp,
-            });
-        }
-    }
-
-    /// Generate metrics for a mergerfs pool
-    fn generate_mergerfs_pool_metrics(
-        &self,
-        metrics: &mut Vec<Metric>,
-        pool: &MergerfsPool,
-        timestamp: u64,
-        status_tracker: &mut StatusTracker
-    ) {
-        // Use consistent pool naming: extract mount point without leading slash
-        let pool_name = if pool.mount_point == "/" {
-            "root".to_string()
-        } else {
-            pool.mount_point.trim_start_matches('/').replace('/', "_")
-        };
-        
-        if pool_name.is_empty() {
-            return;
-        }
-
-        let usage_percent = if pool.total_bytes > 0 {
-            (pool.used_bytes as f64 / pool.total_bytes as f64) * 100.0
-        } else { 0.0 };
-
-        // Calculate pool health based on drive health
-        let failed_data = pool.data_drives.iter()
-            .filter(|d| d.health_status != "PASSED")
-            .count();
-        let failed_parity = pool.parity_drives.iter()
-            .filter(|d| d.health_status != "PASSED")
-            .count();
-
-        let pool_health = match (failed_data, failed_parity) {
-            (0, 0) => Status::Ok,
-            (1, 0) | (0, 1) => Status::Warning,
-            _ => Status::Critical,
-        };
-
-        let usage_status = if usage_percent >= self.config.usage_critical_percent as f64 {
-            Status::Critical
-        } else if usage_percent >= self.config.usage_warning_percent as f64 {
-            Status::Warning
-        } else {
-            Status::Ok
-        };
-
-        let pool_status = if pool_health == Status::Critical { Status::Critical } else { usage_status };
-
-        // Pool metrics
-        metrics.push(Metric {
-            name: format!("disk_{}_mount_point", pool_name),
-            value: MetricValue::String(pool.mount_point.clone()),
-            unit: None,
-            description: Some(format!("Mount: {}", pool.mount_point)),
-            status: Status::Ok,
-            timestamp,
-        });
-
-        metrics.push(Metric {
-            name: format!("disk_{}_pool_type", pool_name),
-            value: MetricValue::String(format!("mergerfs ({}+{})", pool.data_drives.len(), pool.parity_drives.len())),
-            unit: None,
-            description: Some("Type: mergerfs".to_string()),
-            status: Status::Ok,
-            timestamp,
-        });
-
-        metrics.push(Metric {
-            name: format!("disk_{}_pool_health", pool_name),
-            value: MetricValue::String(match pool_health {
-                Status::Ok => "healthy".to_string(),
-                Status::Warning => "degraded".to_string(),
-                Status::Critical => "critical".to_string(),
-                _ => "unknown".to_string(),
-            }),
-            unit: None,
-            description: Some("Pool health".to_string()),
-            status: pool_health,
-            timestamp,
-        });
-
-        metrics.push(Metric {
-            name: format!("disk_{}_total_gb", pool_name),
-            value: MetricValue::Float(self.bytes_to_gb(pool.total_bytes)),
-            unit: Some("GB".to_string()),
-            description: Some(format!("Total: {}", self.bytes_to_human_readable(pool.total_bytes))),
-            status: Status::Ok,
-            timestamp,
-        });
-
-        metrics.push(Metric {
-            name: format!("disk_{}_used_gb", pool_name),
-            value: MetricValue::Float(self.bytes_to_gb(pool.used_bytes)),
-            unit: Some("GB".to_string()),
-            description: Some(format!("Used: {}", self.bytes_to_human_readable(pool.used_bytes))),
-            status: pool_status.clone(),
-            timestamp,
-        });
-
-        let available_bytes = pool.total_bytes.saturating_sub(pool.used_bytes);
-        metrics.push(Metric {
-            name: format!("disk_{}_available_gb", pool_name),
-            value: MetricValue::Float(self.bytes_to_gb(available_bytes)),
-            unit: Some("GB".to_string()),
-            description: Some(format!("Available: {}", self.bytes_to_human_readable(available_bytes))),
-            status: Status::Ok,
-            timestamp,
-        });
-
-        metrics.push(Metric {
-            name: format!("disk_{}_usage_percent", pool_name),
-            value: MetricValue::Float(usage_percent as f32),
-            unit: Some("%".to_string()),
-            description: Some(format!("Usage: {:.1}%", usage_percent)),
-            status: pool_status,
-            timestamp,
-        });
-
-        // Individual drive metrics
-        for drive in &pool.data_drives {
-            self.generate_pool_drive_metrics(metrics, &pool_name, &drive.device, drive, timestamp, status_tracker);
-        }
-
-        for drive in &pool.parity_drives {
-            self.generate_pool_drive_metrics(metrics, &pool_name, &drive.device, drive, timestamp, status_tracker);
-        }
-    }
-
-    /// Generate metrics for drives in mergerfs pools
-    fn generate_pool_drive_metrics(
-        &self,
-        metrics: &mut Vec<Metric>,
-        pool_name: &str,
-        drive_role: &str,
-        drive: &DriveInfo,
-        timestamp: u64,
-        status_tracker: &mut StatusTracker
-    ) {
-        let drive_health = if drive.health_status == "PASSED" { Status::Ok }
-                          else if drive.health_status == "FAILED" { Status::Critical }
-                          else { Status::Unknown };
-
-        metrics.push(Metric {
-            name: format!("disk_{}_{}_health", pool_name, drive_role),
-            value: MetricValue::String(drive.health_status.clone()),
-            unit: None,
-            description: Some(format!("{}: {}", drive.device, drive.health_status)),
-            status: drive_health,
-            timestamp,
-        });
-
-        if let Some(temp) = drive.temperature {
-            let temp_status = self.calculate_temperature_status(
-                &format!("disk_{}_{}_temperature", pool_name, drive_role), temp, status_tracker
-            );
-            metrics.push(Metric {
-                name: format!("disk_{}_{}_temperature", pool_name, drive_role),
-                value: MetricValue::Float(temp),
-                unit: Some("°C".to_string()),
-                description: Some(format!("{}: {:.0}°C", drive.device, temp)),
-                status: temp_status,
-                timestamp,
-            });
-        }
-
-        if let Some(wear) = drive.wear_level {
-            let wear_status = if wear >= self.config.wear_critical_percent { Status::Critical }
-                             else if wear >= self.config.wear_warning_percent { Status::Warning }
-                             else { Status::Ok };
-            metrics.push(Metric {
-                name: format!("disk_{}_{}_wear_percent", pool_name, drive_role),
-                value: MetricValue::Float(wear),
-                unit: Some("%".to_string()),
-                description: Some(format!("{}: {:.0}% wear", drive.device, wear)),
-                status: wear_status,
-                timestamp,
-            });
-        }
-    }
+/// SMART data for a drive
+#[derive(Debug, Clone)]
+struct SmartData {
+    health: String,
+    serial_number: Option<String>,
+    temperature_celsius: Option<f32>,
+    wear_percent: Option<f32>,
 }

agent/src/collectors/memory.rs

@@ -1,5 +1,5 @@
 use async_trait::async_trait;
-use cm_dashboard_shared::{registry, Metric, MetricValue, Status, StatusTracker, HysteresisThresholds};
+use cm_dashboard_shared::{AgentData, TmpfsData, HysteresisThresholds, Status};
 
 use tracing::debug;
 
@@ -10,34 +10,19 @@ use crate::config::MemoryConfig;
 ///
 /// EFFICIENCY OPTIMIZATIONS:
 /// - Single /proc/meminfo read for all memory metrics
-/// - Minimal string parsing with split operations
-/// - Pre-calculated KB to GB conversion
-/// - No regex or complex parsing
-/// - <0.1ms collection time target
+/// - Minimal string allocations
+/// - No process spawning for basic metrics
+/// - <0.5ms collection time target
 pub struct MemoryCollector {
     usage_thresholds: HysteresisThresholds,
 }
 
-/// Memory information parsed from /proc/meminfo
-#[derive(Debug, Default)]
-struct MemoryInfo {
-    total_kb: u64,
-    available_kb: u64,
-    free_kb: u64,
-    buffers_kb: u64,
-    cached_kb: u64,
-    swap_total_kb: u64,
-    swap_free_kb: u64,
-}
-
 impl MemoryCollector {
     pub fn new(config: MemoryConfig) -> Self {
-        // Create hysteresis thresholds with 5% gap for memory usage
-        let usage_thresholds = HysteresisThresholds::with_custom_gaps(
+        // Create hysteresis thresholds with 10% gap for recovery
+        let usage_thresholds = HysteresisThresholds::new(
             config.usage_warning_percent,
-            5.0, // 5% gap for warning recovery
             config.usage_critical_percent,
-            5.0, // 5% gap for critical recovery
         );
         
         Self {
@@ -45,11 +30,6 @@ impl MemoryCollector {
         }
     }
 
-    /// Calculate memory usage status using hysteresis thresholds
-    fn calculate_usage_status(&self, metric_name: &str, usage_percent: f32, status_tracker: &mut StatusTracker) -> Status {
-        status_tracker.calculate_with_hysteresis(metric_name, usage_percent, &self.usage_thresholds)
-    }
-
     /// Parse /proc/meminfo efficiently
     /// Format: "MemTotal:       16384000 kB"
     async fn parse_meminfo(&self) -> Result<MemoryInfo, CollectorError> {
@@ -96,212 +76,141 @@ impl MemoryCollector {
         Ok(info)
     }
 
-    /// Convert KB to GB efficiently (avoiding floating point in hot path)
-    fn kb_to_gb(kb: u64) -> f32 {
-        kb as f32 / 1_048_576.0 // 1024 * 1024
-    }
-
-    /// Calculate memory metrics from parsed info
-    fn calculate_metrics(&self, info: &MemoryInfo, status_tracker: &mut StatusTracker) -> Vec<Metric> {
-        let mut metrics = Vec::with_capacity(6);
-
+    /// Populate memory data directly into AgentData
+    async fn populate_memory_data(&self, info: &MemoryInfo, agent_data: &mut AgentData) -> Result<(), CollectorError> {
         // Calculate derived values
-        let used_kb = info.total_kb - info.available_kb;
-        let usage_percent = (used_kb as f32 / info.total_kb as f32) * 100.0;
-        let usage_status = self.calculate_usage_status(registry::MEMORY_USAGE_PERCENT, usage_percent, status_tracker);
+        let available = info.available_kb;
+        let used = info.total_kb - available;
+        let usage_percent = (used as f32 / info.total_kb as f32) * 100.0;
 
-        let swap_used_kb = info.swap_total_kb - info.swap_free_kb;
+        // Populate basic memory fields
+        agent_data.system.memory.usage_percent = usage_percent;
+        agent_data.system.memory.total_gb = info.total_kb as f32 / (1024.0 * 1024.0);
+        agent_data.system.memory.used_gb = used as f32 / (1024.0 * 1024.0);
 
-        // Convert to GB for metrics
-        let total_gb = Self::kb_to_gb(info.total_kb);
-        let used_gb = Self::kb_to_gb(used_kb);
-        let available_gb = Self::kb_to_gb(info.available_kb);
-        let swap_total_gb = Self::kb_to_gb(info.swap_total_kb);
-        let swap_used_gb = Self::kb_to_gb(swap_used_kb);
+        // Populate swap data if available
+        agent_data.system.memory.swap_total_gb = info.swap_total_kb as f32 / (1024.0 * 1024.0);
+        agent_data.system.memory.swap_used_gb = (info.swap_total_kb - info.swap_free_kb) as f32 / (1024.0 * 1024.0);
 
-        // Memory usage percentage (primary metric with status)
-        metrics.push(
-            Metric::new(
-                registry::MEMORY_USAGE_PERCENT.to_string(),
-                MetricValue::Float(usage_percent),
-                usage_status,
-            )
-            .with_description("Memory usage percentage".to_string())
-            .with_unit("%".to_string()),
-        );
-
-        // Total memory
-        metrics.push(
-            Metric::new(
-                registry::MEMORY_TOTAL_GB.to_string(),
-                MetricValue::Float(total_gb),
-                Status::Ok, // Total memory doesn't have status
-            )
-            .with_description("Total system memory".to_string())
-            .with_unit("GB".to_string()),
-        );
-
-        // Used memory
-        metrics.push(
-            Metric::new(
-                registry::MEMORY_USED_GB.to_string(),
-                MetricValue::Float(used_gb),
-                Status::Ok, // Used memory absolute value doesn't have status
-            )
-            .with_description("Used system memory".to_string())
-            .with_unit("GB".to_string()),
-        );
-
-        // Available memory
-        metrics.push(
-            Metric::new(
-                registry::MEMORY_AVAILABLE_GB.to_string(),
-                MetricValue::Float(available_gb),
-                Status::Ok, // Available memory absolute value doesn't have status
-            )
-            .with_description("Available system memory".to_string())
-            .with_unit("GB".to_string()),
-        );
-
-        // Swap metrics (only if swap exists)
-        if info.swap_total_kb > 0 {
-            metrics.push(
-                Metric::new(
-                    registry::MEMORY_SWAP_TOTAL_GB.to_string(),
-                    MetricValue::Float(swap_total_gb),
-                    Status::Ok,
-                )
-                .with_description("Total swap space".to_string())
-                .with_unit("GB".to_string()),
-            );
-
-            metrics.push(
-                Metric::new(
-                    registry::MEMORY_SWAP_USED_GB.to_string(),
-                    MetricValue::Float(swap_used_gb),
-                    Status::Ok,
-                )
-                .with_description("Used swap space".to_string())
-                .with_unit("GB".to_string()),
-            );
+        Ok(())
     }
 
-        // Monitor tmpfs (/tmp) usage
-        if let Ok(tmpfs_metrics) = self.get_tmpfs_metrics(status_tracker) {
-            metrics.extend(tmpfs_metrics);
+    /// Populate tmpfs data into AgentData
+    async fn populate_tmpfs_data(&self, agent_data: &mut AgentData) -> Result<(), CollectorError> {
+        // Discover all tmpfs mount points
+        let tmpfs_mounts = self.discover_tmpfs_mounts()?;
+        
+        if tmpfs_mounts.is_empty() {
+            debug!("No tmpfs mounts found to monitor");
+            return Ok(());
         }
 
-        metrics
-    }
+        // Get usage data for all tmpfs mounts at once using df (with 2 second timeout)
+        let mut df_args = vec!["2", "df", "--output=target,size,used", "--block-size=1"];
+        df_args.extend(tmpfs_mounts.iter().map(|s| s.as_str()));
 
-    /// Get tmpfs (/tmp) usage metrics  
-    fn get_tmpfs_metrics(&self, status_tracker: &mut StatusTracker) -> Result<Vec<Metric>, CollectorError> {
-        use std::process::Command;
-        
-        let output = Command::new("df")
-            .arg("--block-size=1")
-            .arg("/tmp")
+        let df_output = std::process::Command::new("timeout")
+            .args(&df_args[..])
             .output()
             .map_err(|e| CollectorError::SystemRead {
-                path: "/tmp".to_string(),
+                path: "tmpfs mounts".to_string(),
                 error: e.to_string(),
             })?;
 
-        if !output.status.success() {
-            return Ok(Vec::new()); // Return empty if /tmp not available
+        let df_str = String::from_utf8_lossy(&df_output.stdout);
+        let df_lines: Vec<&str> = df_str.lines().skip(1).collect(); // Skip header
+
+        // Process each tmpfs mount
+        for (i, mount_point) in tmpfs_mounts.iter().enumerate() {
+            if i >= df_lines.len() {
+                debug!("Not enough df output lines for tmpfs mount: {}", mount_point);
+                continue;
             }
 
-        let output_str = String::from_utf8(output.stdout)
-            .map_err(|e| CollectorError::Parse {
-                value: "df output".to_string(),
-                error: e.to_string(),
-            })?;
-
-        let lines: Vec<&str> = output_str.lines().collect();
-        if lines.len() < 2 {
-            return Ok(Vec::new());
+            let parts: Vec<&str> = df_lines[i].split_whitespace().collect();
+            if parts.len() < 3 {
+                debug!("Invalid df output for tmpfs mount: {}", mount_point);
+                continue;
             }
 
-        let fields: Vec<&str> = lines[1].split_whitespace().collect();
-        if fields.len() < 4 {
-            return Ok(Vec::new());
-        }
+            let total_bytes: u64 = parts[1].parse().unwrap_or(0);
+            let used_bytes: u64 = parts[2].parse().unwrap_or(0);
 
-        let total_bytes: u64 = fields[1].parse()
-            .map_err(|e: std::num::ParseIntError| CollectorError::Parse {
-                value: fields[1].to_string(),
-                error: e.to_string(),
-            })?;
-        let used_bytes: u64 = fields[2].parse()
-            .map_err(|e: std::num::ParseIntError| CollectorError::Parse {
-                value: fields[2].to_string(),
-                error: e.to_string(),
-            })?;
+            if total_bytes == 0 {
+                continue;
+            }
 
             let total_gb = total_bytes as f32 / (1024.0 * 1024.0 * 1024.0);
             let used_gb = used_bytes as f32 / (1024.0 * 1024.0 * 1024.0);
-        let usage_percent = if total_bytes > 0 {
-            (used_bytes as f32 / total_bytes as f32) * 100.0
-        } else {
-            0.0
-        };
+            let usage_percent = (used_bytes as f32 / total_bytes as f32) * 100.0;
 
-        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: tmp_status,
-            timestamp,
+            // Add to tmpfs list
+            agent_data.system.memory.tmpfs.push(TmpfsData {
+                mount: mount_point.clone(),
+                usage_percent,
+                used_gb,
+                total_gb,
             });
+        }
 
-        metrics.push(Metric {
-            name: "memory_tmp_used_gb".to_string(),
-            value: MetricValue::Float(used_gb),
-            unit: Some("GB".to_string()),
-            description: Some("tmpfs /tmp used space".to_string()),
-            status: Status::Ok,
-            timestamp,
-        });
+        // Sort tmpfs mounts by mount point for consistent display order
+        agent_data.system.memory.tmpfs.sort_by(|a, b| a.mount.cmp(&b.mount));
 
-        metrics.push(Metric {
-            name: "memory_tmp_total_gb".to_string(),
-            value: MetricValue::Float(total_gb),
-            unit: Some("GB".to_string()),
-            description: Some("tmpfs /tmp total space".to_string()),
-            status: Status::Ok,
-            timestamp,
-        });
+        Ok(())
+    }
 
-        Ok(metrics)
+    /// Discover all tmpfs mount points from /proc/mounts
+    fn discover_tmpfs_mounts(&self) -> Result<Vec<String>, CollectorError> {
+        let content = utils::read_proc_file("/proc/mounts")?;
+        let mut tmpfs_mounts = Vec::new();
+
+        for line in content.lines() {
+            let fields: Vec<&str> = line.split_whitespace().collect();
+            if fields.len() >= 3 && fields[2] == "tmpfs" {
+                let mount_point = fields[1];
+                
+                // Filter out system/internal tmpfs mounts that aren't useful for monitoring
+                if self.should_monitor_tmpfs(mount_point) {
+                    tmpfs_mounts.push(mount_point.to_string());
+                }
+            }
+        }
+
+        debug!("Discovered {} tmpfs mounts: {:?}", tmpfs_mounts.len(), tmpfs_mounts);
+        Ok(tmpfs_mounts)
+    }
+
+    /// Determine if a tmpfs mount point should be monitored
+    fn should_monitor_tmpfs(&self, mount_point: &str) -> bool {
+        // Include commonly useful tmpfs mounts
+        matches!(mount_point, 
+            "/tmp" | "/var/tmp" | "/dev/shm" | "/run" | "/var/log"
+        ) || mount_point.starts_with("/run/user/") // User session tmpfs
+    }
+
+    /// Calculate memory usage status based on thresholds
+    fn calculate_memory_status(&self, usage_percent: f32) -> Status {
+        self.usage_thresholds.evaluate(usage_percent)
     }
 }
 
 #[async_trait]
 impl Collector for MemoryCollector {
-
-    async fn collect(&self, status_tracker: &mut StatusTracker) -> Result<Vec<Metric>, CollectorError> {
+    async fn collect_structured(&self, agent_data: &mut AgentData) -> Result<(), CollectorError> {
         debug!("Collecting memory metrics");
         let start = std::time::Instant::now();
 
         // Parse memory info from /proc/meminfo
         let info = self.parse_meminfo().await?;
 
-        // Calculate all metrics from parsed info
-        let metrics = self.calculate_metrics(&info, status_tracker);
+        // Populate memory data directly
+        self.populate_memory_data(&info, agent_data).await?;
+
+        // Collect tmpfs data  
+        self.populate_tmpfs_data(agent_data).await?;
 
         let duration = start.elapsed();
-        debug!(
-            "Memory collection completed in {:?} with {} metrics",
-            duration,
-            metrics.len()
-        );
+        debug!("Memory collection completed in {:?}", duration);
 
         // Efficiency check: warn if collection takes too long
         if duration.as_millis() > 1 {
@@ -311,10 +220,21 @@ impl Collector for MemoryCollector {
             );
         }
 
-        // Store performance metrics
-        // Performance tracking handled by cache system
+        // Calculate status using thresholds
+        agent_data.system.memory.usage_status = self.calculate_memory_status(agent_data.system.memory.usage_percent);
 
-        Ok(metrics)
+        Ok(())
     }
-
+}
+
+/// Internal structure for parsing /proc/meminfo
+#[derive(Default)]
+struct MemoryInfo {
+    total_kb: u64,
+    available_kb: u64,
+    free_kb: u64,
+    buffers_kb: u64,
+    cached_kb: u64,
+    swap_total_kb: u64,
+    swap_free_kb: u64,
 }

agent/src/collectors/mod.rs

@@ -1,25 +1,40 @@
 use async_trait::async_trait;
-use cm_dashboard_shared::{Metric, StatusTracker};
-
+use cm_dashboard_shared::{AgentData};
+use std::process::{Command, Output};
+use std::time::Duration;
+use tokio::time::timeout;
 
 pub mod backup;
 pub mod cpu;
 pub mod disk;
 pub mod error;
 pub mod memory;
+pub mod network;
 pub mod nixos;
 pub mod systemd;
 
 pub use error::CollectorError;
 
+/// Run a command with a timeout to prevent blocking
+pub async fn run_command_with_timeout(mut cmd: Command, timeout_secs: u64) -> std::io::Result<Output> {
+    let timeout_duration = Duration::from_secs(timeout_secs);
 
-/// Base trait for all collectors with extreme efficiency requirements
+    match timeout(timeout_duration, tokio::task::spawn_blocking(move || cmd.output())).await {
+        Ok(Ok(result)) => result,
+        Ok(Err(e)) => Err(std::io::Error::new(std::io::ErrorKind::Other, e)),
+        Err(_) => Err(std::io::Error::new(
+            std::io::ErrorKind::TimedOut,
+            format!("Command timed out after {} seconds", timeout_secs)
+        )),
+    }
+}
+
+
+/// Base trait for all collectors with direct structured data output
 #[async_trait]
 pub trait Collector: Send + Sync {
-    /// Collect all metrics this collector provides
-    async fn collect(&self, status_tracker: &mut StatusTracker) -> Result<Vec<Metric>, CollectorError>;
-
-
+    /// Collect data and populate AgentData directly with status evaluation
+    async fn collect_structured(&self, agent_data: &mut AgentData) -> Result<(), CollectorError>;
 }
 
 /// CPU efficiency rules for all collectors

agent/src/collectors/network.rs

@@ -0,0 +1,224 @@
+use async_trait::async_trait;
+use cm_dashboard_shared::{AgentData, NetworkInterfaceData, Status};
+use std::process::Command;
+use tracing::debug;
+
+use super::{Collector, CollectorError};
+use crate::config::NetworkConfig;
+
+/// Network interface collector with physical/virtual classification and link status
+pub struct NetworkCollector {
+    _config: NetworkConfig,
+}
+
+impl NetworkCollector {
+    pub fn new(config: NetworkConfig) -> Self {
+        Self { _config: config }
+    }
+
+    /// Check if interface is physical (not virtual)
+    fn is_physical_interface(name: &str) -> bool {
+        // Physical interface patterns
+        matches!(
+            &name[..],
+            s if s.starts_with("eth")
+                || s.starts_with("ens")
+                || s.starts_with("enp")
+                || s.starts_with("wlan")
+                || s.starts_with("wlp")
+                || s.starts_with("eno")
+                || s.starts_with("enx")
+        )
+    }
+
+    /// Get link status for an interface
+    fn get_link_status(interface: &str) -> Status {
+        let operstate_path = format!("/sys/class/net/{}/operstate", interface);
+
+        match std::fs::read_to_string(&operstate_path) {
+            Ok(state) => {
+                let state = state.trim();
+                match state {
+                    "up" => Status::Ok,
+                    "down" => Status::Inactive,
+                    "unknown" => Status::Warning,
+                    _ => Status::Unknown,
+                }
+            }
+            Err(_) => Status::Unknown,
+        }
+    }
+
+    /// Get the primary physical interface (the one with default route)
+    fn get_primary_physical_interface() -> Option<String> {
+        match Command::new("timeout").args(["2", "ip", "route", "show", "default"]).output() {
+            Ok(output) if output.status.success() => {
+                let output_str = String::from_utf8_lossy(&output.stdout);
+                // Parse: "default via 192.168.1.1 dev eno1 ..."
+                for line in output_str.lines() {
+                    if line.starts_with("default") {
+                        if let Some(dev_pos) = line.find(" dev ") {
+                            let after_dev = &line[dev_pos + 5..];
+                            if let Some(space_pos) = after_dev.find(' ') {
+                                let interface = &after_dev[..space_pos];
+                                // Only return if it's a physical interface
+                                if Self::is_physical_interface(interface) {
+                                    return Some(interface.to_string());
+                                }
+                            } else {
+                                // No space after interface name (end of line)
+                                let interface = after_dev.trim();
+                                if Self::is_physical_interface(interface) {
+                                    return Some(interface.to_string());
+                                }
+                            }
+                        }
+                    }
+                }
+                None
+            }
+            _ => None,
+        }
+    }
+
+    /// Parse VLAN configuration from /proc/net/vlan/config
+    /// Returns a map of interface name -> VLAN ID
+    fn parse_vlan_config() -> std::collections::HashMap<String, u16> {
+        let mut vlan_map = std::collections::HashMap::new();
+
+        if let Ok(contents) = std::fs::read_to_string("/proc/net/vlan/config") {
+            for line in contents.lines().skip(2) {  // Skip header lines
+                let parts: Vec<&str> = line.split('|').collect();
+                if parts.len() >= 2 {
+                    let interface_name = parts[0].trim();
+                    let vlan_id_str = parts[1].trim();
+
+                    if let Ok(vlan_id) = vlan_id_str.parse::<u16>() {
+                        vlan_map.insert(interface_name.to_string(), vlan_id);
+                    }
+                }
+            }
+        }
+
+        vlan_map
+    }
+
+    /// Collect network interfaces using ip command
+    async fn collect_interfaces(&self) -> Vec<NetworkInterfaceData> {
+        let mut interfaces = Vec::new();
+
+        // Parse VLAN configuration
+        let vlan_map = Self::parse_vlan_config();
+
+        match Command::new("timeout").args(["2", "ip", "-j", "addr"]).output() {
+            Ok(output) if output.status.success() => {
+                let json_str = String::from_utf8_lossy(&output.stdout);
+
+                if let Ok(json_data) = serde_json::from_str::<serde_json::Value>(&json_str) {
+                    if let Some(ifaces) = json_data.as_array() {
+                        for iface in ifaces {
+                            let name = iface["ifname"].as_str().unwrap_or("").to_string();
+
+                            // Skip loopback, empty names, and ifb* interfaces
+                            if name.is_empty() || name == "lo" || name.starts_with("ifb") {
+                                continue;
+                            }
+
+                            // Parse parent interface from @parent notation (e.g., lan@enp0s31f6)
+                            let (interface_name, parent_interface) = if let Some(at_pos) = name.find('@') {
+                                let (child, parent) = name.split_at(at_pos);
+                                (child.to_string(), Some(parent[1..].to_string()))
+                            } else {
+                                (name.clone(), None)
+                            };
+
+                            let mut ipv4_addresses = Vec::new();
+                            let mut ipv6_addresses = Vec::new();
+
+                            // Extract IP addresses
+                            if let Some(addr_info) = iface["addr_info"].as_array() {
+                                for addr in addr_info {
+                                    if let Some(family) = addr["family"].as_str() {
+                                        if let Some(local) = addr["local"].as_str() {
+                                            match family {
+                                                "inet" => ipv4_addresses.push(local.to_string()),
+                                                "inet6" => {
+                                                    // Skip link-local IPv6 addresses (fe80::)
+                                                    if !local.starts_with("fe80:") {
+                                                        ipv6_addresses.push(local.to_string());
+                                                    }
+                                                }
+                                                _ => {}
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+
+                            // Determine if physical and get status
+                            let is_physical = Self::is_physical_interface(&interface_name);
+
+                            // Only filter out virtual interfaces without IPs
+                            // Physical interfaces should always be shown even if down/no IPs
+                            if !is_physical && ipv4_addresses.is_empty() && ipv6_addresses.is_empty() {
+                                continue;
+                            }
+
+                            let link_status = if is_physical {
+                                Self::get_link_status(&name)
+                            } else {
+                                Status::Unknown  // Virtual interfaces don't have meaningful link status
+                            };
+
+                            // Look up VLAN ID from the map (use original name before @ parsing)
+                            let vlan_id = vlan_map.get(&name).copied();
+
+                            interfaces.push(NetworkInterfaceData {
+                                name: interface_name,
+                                ipv4_addresses,
+                                ipv6_addresses,
+                                is_physical,
+                                link_status,
+                                parent_interface,
+                                vlan_id,
+                            });
+                        }
+                    }
+                }
+            }
+            Err(e) => {
+                debug!("Failed to execute ip command: {}", e);
+            }
+            Ok(output) => {
+                debug!("ip command failed with status: {}", output.status);
+            }
+        }
+
+        // Assign primary physical interface as parent to virtual interfaces without explicit parent
+        let primary_interface = Self::get_primary_physical_interface();
+        if let Some(primary) = primary_interface {
+            for interface in interfaces.iter_mut() {
+                // Only assign parent to virtual interfaces that don't already have one
+                if !interface.is_physical && interface.parent_interface.is_none() {
+                    interface.parent_interface = Some(primary.clone());
+                }
+            }
+        }
+
+        interfaces
+    }
+}
+
+#[async_trait]
+impl Collector for NetworkCollector {
+    async fn collect_structured(&self, agent_data: &mut AgentData) -> Result<(), CollectorError> {
+        debug!("Collecting network interface data");
+
+        // Collect all network interfaces
+        let interfaces = self.collect_interfaces().await;
+
+        agent_data.system.network.interfaces = interfaces;
+
+        Ok(())
+    }
+}

agent/src/collectors/nixos.rs

@@ -1,172 +1,111 @@
 use async_trait::async_trait;
-use cm_dashboard_shared::{Metric, MetricValue, Status, StatusTracker};
+use cm_dashboard_shared::AgentData;
+use std::fs;
 use std::process::Command;
 use tracing::debug;
 
 use super::{Collector, CollectorError};
-use crate::config::NixOSConfig;
 
-/// NixOS system information collector
+/// NixOS system information collector with structured data output
 ///
-/// Collects NixOS-specific system information including:
-/// - NixOS version and build information
-pub struct NixOSCollector {
-}
+/// This collector gathers NixOS-specific information like:
+/// - System generation/build information
+/// - Version information
+/// - Agent version from Nix store path
+pub struct NixOSCollector;
 
 impl NixOSCollector {
-    pub fn new(_config: NixOSConfig) -> Self {
-        Self {}
+    pub fn new(_config: crate::config::NixOSConfig) -> Self {
+        Self
     }
 
+    /// Collect NixOS system information and populate AgentData
+    async fn collect_nixos_info(&self, agent_data: &mut AgentData) -> Result<(), CollectorError> {
+        debug!("Collecting NixOS system information");
 
-    /// Get agent hash from binary path
-    fn get_agent_hash(&self) -> Result<String, Box<dyn std::error::Error>> {
-        // Get the path of the current executable
-        let exe_path = std::env::current_exe()?;
-        let exe_str = exe_path.to_string_lossy();
+        // Set hostname (this is universal, not NixOS-specific)
+        agent_data.hostname = self.get_hostname().await.unwrap_or_else(|| "unknown".to_string());
 
-        // Extract Nix store hash from path like /nix/store/fn804fh332mp8gz06qawminpj20xl25h-cm-dashboard-0.1.0/bin/cm-dashboard-agent
-        if let Some(store_path) = exe_str.strip_prefix("/nix/store/") {
-            if let Some(dash_pos) = store_path.find('-') {
-                return Ok(store_path[..dash_pos].to_string());
+        // Set agent version from environment or Nix store path
+        agent_data.agent_version = self.get_agent_version().await;
+
+        // Set NixOS build/generation information
+        agent_data.build_version = self.get_nixos_generation().await;
+
+        // Set current timestamp
+        agent_data.timestamp = chrono::Utc::now().timestamp() as u64;
+
+        Ok(())
+    }
+
+    /// Get system hostname
+    async fn get_hostname(&self) -> Option<String> {
+        match fs::read_to_string("/etc/hostname") {
+            Ok(hostname) => Some(hostname.trim().to_string()),
+            Err(_) => {
+                // Fallback to hostname command (with 2 second timeout)
+                match Command::new("timeout").args(["2", "hostname"]).output() {
+                    Ok(output) => Some(String::from_utf8_lossy(&output.stdout).trim().to_string()),
+                    Err(_) => None,
+                }
+            }
         }
     }
 
-        // Fallback to "unknown" if not in Nix store
-        Ok("unknown".to_string())
+    /// Get agent version from Nix store path or environment
+    async fn get_agent_version(&self) -> String {
+        // Try to extract version from the current executable path (Nix store)
+        if let Ok(current_exe) = std::env::current_exe() {
+            if let Some(exe_path) = current_exe.to_str() {
+                if exe_path.starts_with("/nix/store/") {
+                    // Extract version from Nix store path
+                    // Path format: /nix/store/hash-cm-dashboard-agent-v0.1.138/bin/cm-dashboard-agent
+                    if let Some(store_part) = exe_path.strip_prefix("/nix/store/") {
+                        if let Some(dash_pos) = store_part.find('-') {
+                            let package_part = &store_part[dash_pos + 1..];
+                            if let Some(bin_pos) = package_part.find("/bin/") {
+                                let package_name = &package_part[..bin_pos];
+                                // Extract version from package name
+                                if let Some(version_start) = package_name.rfind("-v") {
+                                    return package_name[version_start + 1..].to_string();
+                                }
+                            }
+                        }
+                    }
+                }
+            }
         }
 
-    /// Get configuration hash from deployed nix store system
-    /// Get git commit hash from rebuild process
-    fn get_git_commit(&self) -> Result<String, Box<dyn std::error::Error>> {
+        // Fallback to environment variable or default
+        std::env::var("CM_DASHBOARD_VERSION").unwrap_or_else(|_| "unknown".to_string())
+    }
+
+    /// Get NixOS system generation (build) information from git commit
+    async fn get_nixos_generation(&self) -> Option<String> {
+        // Try to read git commit hash from file written during rebuild
         let commit_file = "/var/lib/cm-dashboard/git-commit";
-        match std::fs::read_to_string(commit_file) {
+        match fs::read_to_string(commit_file) {
             Ok(content) => {
                 let commit_hash = content.trim();
                 if commit_hash.len() >= 7 {
-                    Ok(commit_hash.to_string())
+                    debug!("Found git commit hash: {}", commit_hash);
+                    Some(commit_hash.to_string())
                 } else {
-                    Err("Git commit hash too short".into())
+                    debug!("Git commit hash too short: {}", commit_hash);
+                    None
                 }
             }
-            Err(e) => Err(format!("Failed to read git commit file: {}", e).into())
-        }
-    }
-
-    fn get_config_hash(&self) -> Result<String, Box<dyn std::error::Error>> {
-        // Read the symlink target of /run/current-system to get nix store path
-        let output = Command::new("readlink")
-            .arg("/run/current-system")
-            .output()?;
-        
-        if !output.status.success() {
-            return Err("readlink command failed".into());
-        }
-        
-        let binding = String::from_utf8_lossy(&output.stdout);
-        let store_path = binding.trim();
-        
-        // Extract hash from nix store path
-        // Format: /nix/store/HASH-nixos-system-HOSTNAME-VERSION
-        if let Some(hash_part) = store_path.strip_prefix("/nix/store/") {
-            if let Some(hash) = hash_part.split('-').next() {
-                if hash.len() >= 8 {
-                    // Return first 8 characters of nix store hash
-                    return Ok(hash[..8].to_string());
+            Err(e) => {
+                debug!("Failed to read git commit file {}: {}", commit_file, e);
+                None
             }
         }
     }
-        
-        Err("Could not extract hash from nix store path".into())
-    }
-
 }
 
 #[async_trait]
 impl Collector for NixOSCollector {
-
-    async fn collect(&self, _status_tracker: &mut StatusTracker) -> Result<Vec<Metric>, CollectorError> {
-        debug!("Collecting NixOS system information");
-        let mut metrics = Vec::new();
-        let timestamp = chrono::Utc::now().timestamp() as u64;
-
-        // Collect git commit information (shows what's actually deployed)
-        match self.get_git_commit() {
-            Ok(git_commit) => {
-                metrics.push(Metric {
-                    name: "system_nixos_build".to_string(),
-                    value: MetricValue::String(git_commit),
-                    unit: None,
-                    description: Some("Git commit hash of deployed configuration".to_string()),
-                    status: Status::Ok,
-                    timestamp,
-                });
-            }
-            Err(e) => {
-                debug!("Failed to get git commit: {}", e);
-                metrics.push(Metric {
-                    name: "system_nixos_build".to_string(),
-                    value: MetricValue::String("unknown".to_string()),
-                    unit: None,
-                    description: Some("Git commit hash (failed to detect)".to_string()),
-                    status: Status::Unknown,
-                    timestamp,
-                });
-            }
-        }
-
-
-        // Collect config hash
-        match self.get_config_hash() {
-            Ok(hash) => {
-                metrics.push(Metric {
-                    name: "system_config_hash".to_string(),
-                    value: MetricValue::String(hash),
-                    unit: None,
-                    description: Some("NixOS deployed configuration hash".to_string()),
-                    status: Status::Ok,
-                    timestamp,
-                });
-            }
-            Err(e) => {
-                debug!("Failed to get config hash: {}", e);
-                metrics.push(Metric {
-                    name: "system_config_hash".to_string(),
-                    value: MetricValue::String("unknown".to_string()),
-                    unit: None,
-                    description: Some("Deployed config hash (failed to detect)".to_string()),
-                    status: Status::Unknown,
-                    timestamp,
-                });
-            }
-        }
-
-        // Collect agent hash
-        match self.get_agent_hash() {
-            Ok(hash) => {
-                metrics.push(Metric {
-                    name: "system_agent_hash".to_string(),
-                    value: MetricValue::String(hash),
-                    unit: None,
-                    description: Some("Agent Nix store hash".to_string()),
-                    status: Status::Ok,
-                    timestamp,
-                });
-            }
-            Err(e) => {
-                debug!("Failed to get agent hash: {}", e);
-                metrics.push(Metric {
-                    name: "system_agent_hash".to_string(),
-                    value: MetricValue::String("unknown".to_string()),
-                    unit: None,
-                    description: Some("Agent hash (failed to detect)".to_string()),
-                    status: Status::Unknown,
-                    timestamp,
-                });
-            }
-        }
-
-        debug!("Collected {} NixOS metrics", metrics.len());
-        Ok(metrics)
+    async fn collect_structured(&self, agent_data: &mut AgentData) -> Result<(), CollectorError> {
+        self.collect_nixos_info(agent_data).await
     }
 }

agent/src/collectors/systemd.rs

@@ -1,6 +1,6 @@
 use anyhow::Result;
 use async_trait::async_trait;
-use cm_dashboard_shared::{Metric, MetricValue, Status, StatusTracker};
+use cm_dashboard_shared::{AgentData, ServiceData, SubServiceData, SubServiceMetric, Status};
 use std::process::Command;
 use std::sync::RwLock;
 use std::time::Instant;
@@ -9,7 +9,7 @@ use tracing::debug;
 use super::{Collector, CollectorError};
 use crate::config::SystemdConfig;
 
-/// Systemd collector for monitoring systemd services
+/// Systemd collector for monitoring systemd services with structured data output
 pub struct SystemdCollector {
     /// Cached state with thread-safe interior mutability
     state: RwLock<ServiceCacheState>,
@@ -18,18 +18,22 @@ pub struct SystemdCollector {
 }
 
 /// Internal state for service caching
-#[derive(Debug)]
+#[derive(Debug, Clone)]
 struct ServiceCacheState {
+    /// Last collection time for performance tracking
+    last_collection: Option<Instant>,
+    /// Cached complete service data with sub-services
+    cached_service_data: Vec<ServiceData>,
     /// Interesting services to monitor (cached after discovery)
     monitored_services: Vec<String>,
     /// Cached service status information from discovery
     service_status_cache: std::collections::HashMap<String, ServiceStatusInfo>,
     /// Last time services were discovered
     last_discovery_time: Option<Instant>,
-    /// How often to rediscover services (5 minutes)
+    /// How often to rediscover services (from config)
     discovery_interval_seconds: u64,
     /// Cached nginx site latency metrics
-    nginx_site_metrics: Vec<Metric>,
+    nginx_site_metrics: Vec<(String, f32)>,
     /// Last time nginx sites were checked
     last_nginx_check_time: Option<Instant>,
     /// How often to check nginx site latency (configurable)
@@ -39,15 +43,17 @@ struct ServiceCacheState {
 /// Cached service status information from systemctl list-units
 #[derive(Debug, Clone)]
 struct ServiceStatusInfo {
-    load_state: String,
     active_state: String,
-    sub_state: String,
+    memory_bytes: Option<u64>,
+    restart_count: Option<u32>,
+    start_timestamp: Option<u64>,
 }
 
 impl SystemdCollector {
     pub fn new(config: SystemdConfig) -> Self {
-        Self {
-            state: RwLock::new(ServiceCacheState {
+        let state = ServiceCacheState {
+            last_collection: None,
+            cached_service_data: Vec::new(),
             monitored_services: Vec::new(),
             service_status_cache: std::collections::HashMap::new(),
             last_discovery_time: None,
@@ -55,11 +61,142 @@ impl SystemdCollector {
             nginx_site_metrics: Vec::new(),
             last_nginx_check_time: None,
             nginx_check_interval_seconds: config.nginx_check_interval_seconds,
-            }),
+        };
+
+        Self {
+            state: RwLock::new(state),
             config,
         }
     }
 
+    /// Collect service data and populate AgentData
+    async fn collect_service_data(&self, agent_data: &mut AgentData) -> Result<(), CollectorError> {
+        let start_time = Instant::now();
+        debug!("Collecting systemd services metrics");
+
+        // Get cached services (discovery only happens when needed)
+        let monitored_services = match self.get_monitored_services() {
+            Ok(services) => services,
+            Err(e) => {
+                debug!("Failed to get monitored services: {}", e);
+                return Ok(());
+            }
+        };
+
+        // Collect service data for each monitored service
+        let mut complete_service_data = Vec::new();
+        for service_name in &monitored_services {
+            match self.get_service_status(service_name) {
+                Ok(status_info) => {
+                    let mut sub_services = Vec::new();
+
+                    // Calculate uptime if we have start timestamp
+                    let uptime_seconds = status_info.start_timestamp.and_then(|start| {
+                        let now = std::time::SystemTime::now()
+                            .duration_since(std::time::UNIX_EPOCH)
+                            .ok()?
+                            .as_secs();
+                        Some(now.saturating_sub(start))
+                    });
+
+                    // Sub-service metrics for specific services (always include cached results)
+                    if service_name.contains("nginx") && status_info.active_state == "active" {
+                        let nginx_sites = self.get_nginx_site_metrics();
+                        for (site_name, latency_ms) in nginx_sites {
+                            let site_status = if latency_ms >= 0.0 && latency_ms < self.config.nginx_latency_critical_ms {
+                                "active"
+                            } else {
+                                "failed"
+                            };
+                            
+                            let mut metrics = Vec::new();
+                            metrics.push(SubServiceMetric {
+                                label: "latency_ms".to_string(),
+                                value: latency_ms,
+                                unit: Some("ms".to_string()),
+                            });
+                            
+                            sub_services.push(SubServiceData {
+                                name: site_name.clone(),
+                                service_status: self.calculate_service_status(&site_name, &site_status),
+                                metrics,
+                                service_type: "nginx_site".to_string(),
+                            });
+                        }
+                    }
+
+                    if service_name.contains("docker") && status_info.active_state == "active" {
+                        let docker_containers = self.get_docker_containers();
+                        for (container_name, container_status) in docker_containers {
+                            // For now, docker containers have no additional metrics
+                            // Future: could add memory_mb, cpu_percent, restart_count, etc.
+                            let metrics = Vec::new();
+
+                            sub_services.push(SubServiceData {
+                                name: container_name.clone(),
+                                service_status: self.calculate_service_status(&container_name, &container_status),
+                                metrics,
+                                service_type: "container".to_string(),
+                            });
+                        }
+
+                        // Add Docker images
+                        let docker_images = self.get_docker_images();
+                        for (image_name, image_status, image_size_mb) in docker_images {
+                            let mut metrics = Vec::new();
+                            metrics.push(SubServiceMetric {
+                                label: "size".to_string(),
+                                value: image_size_mb,
+                                unit: Some("MB".to_string()),
+                            });
+
+                            sub_services.push(SubServiceData {
+                                name: image_name.to_string(),
+                                service_status: self.calculate_service_status(&image_name, &image_status),
+                                metrics,
+                                service_type: "image".to_string(),
+                            });
+                        }
+                    }
+
+                    // Create complete service data
+                    let service_data = ServiceData {
+                        name: service_name.clone(),
+                        user_stopped: false, // TODO: Integrate with service tracker
+                        service_status: self.calculate_service_status(service_name, &status_info.active_state),
+                        sub_services,
+                        memory_bytes: status_info.memory_bytes,
+                        restart_count: status_info.restart_count,
+                        uptime_seconds,
+                    };
+
+                    // Add to AgentData and cache
+                    agent_data.services.push(service_data.clone());
+                    complete_service_data.push(service_data);
+                }
+                Err(e) => {
+                    debug!("Failed to get status for service {}: {}", service_name, e);
+                }
+            }
+        }
+
+        // Sort services alphabetically by name
+        agent_data.services.sort_by(|a, b| a.name.cmp(&b.name));
+        complete_service_data.sort_by(|a, b| a.name.cmp(&b.name));
+
+        // Update cached state
+        {
+            let mut state = self.state.write().unwrap();
+            state.last_collection = Some(start_time);
+            state.cached_service_data = complete_service_data;
+        }
+
+        let elapsed = start_time.elapsed();
+        debug!("Systemd collection completed in {:?} with {} services", elapsed, agent_data.services.len());
+
+        Ok(())
+    }
+
     /// Get monitored services, discovering them if needed or cache is expired
     fn get_monitored_services(&self) -> Result<Vec<String>> {
         // Check if we need discovery without holding the lock
@@ -76,25 +213,19 @@ impl SystemdCollector {
 
         if needs_discovery {
             debug!("Discovering systemd services (cache expired or first run)");
-            // Call discover_services_internal which doesn't update state
             match self.discover_services_internal() {
                 Ok((services, status_cache)) => {
-                    // Update state with discovered services in a separate scope
                     if let Ok(mut state) = self.state.write() {
                         state.monitored_services = services.clone();
                         state.service_status_cache = status_cache;
                         state.last_discovery_time = Some(Instant::now());
-                        debug!(
-                            "Auto-discovered {} services to monitor: {:?}",
-                            state.monitored_services.len(),
-                            state.monitored_services
-                        );
+                        debug!("Auto-discovered {} services to monitor: {:?}", 
+                            state.monitored_services.len(), state.monitored_services);
                         return Ok(services);
                     }
                 }
                 Err(e) => {
                     debug!("Failed to discover services, using cached list: {}", e);
-                    // Continue with existing cached services if discovery fails
                 }
             }
         }
@@ -104,8 +235,8 @@ impl SystemdCollector {
         Ok(state.monitored_services.clone())
     }
 
-    /// Get nginx site metrics, checking them if cache is expired
-    fn get_nginx_site_metrics(&self) -> Vec<Metric> {
+    /// Get nginx site metrics, checking them if cache is expired (like old working version)
+    fn get_nginx_site_metrics(&self) -> Vec<(String, f32)> {
         let mut state = self.state.write().unwrap();
 
         // Check if we need to refresh nginx site metrics
@@ -120,11 +251,7 @@ impl SystemdCollector {
         if needs_refresh {
             // Only check nginx sites if nginx service is active
             if state.monitored_services.iter().any(|s| s.contains("nginx")) {
-                debug!(
-                    "Refreshing nginx site latency metrics (interval: {}s)",
-                    state.nginx_check_interval_seconds
-                );
-                let fresh_metrics = self.get_nginx_sites();
+                let fresh_metrics = self.get_nginx_sites_internal();
                 state.nginx_site_metrics = fresh_metrics;
                 state.last_nginx_check_time = Some(Instant::now());
             }
@@ -133,29 +260,20 @@ impl SystemdCollector {
         state.nginx_site_metrics.clone()
     }
 
-    /// Auto-discover interesting services to monitor (internal version that doesn't update state)
+    /// Auto-discover interesting services to monitor
     fn discover_services_internal(&self) -> Result<(Vec<String>, std::collections::HashMap<String, ServiceStatusInfo>)> {
-        debug!("Starting systemd service discovery with status caching");
-        
-        // First: Get all service unit files (includes services that have never been started)
-        let unit_files_output = Command::new("systemctl")
-            .arg("list-unit-files")
-            .arg("--type=service")
-            .arg("--no-pager")
-            .arg("--plain")
+        // First: Get all service unit files (with 3 second timeout)
+        let unit_files_output = Command::new("timeout")
+            .args(&["3", "systemctl", "list-unit-files", "--type=service", "--no-pager", "--plain"])
             .output()?;
 
         if !unit_files_output.status.success() {
             return Err(anyhow::anyhow!("systemctl list-unit-files command failed"));
         }
 
-        // Second: Get runtime status of all units
-        let units_status_output = Command::new("systemctl")
-            .arg("list-units")
-            .arg("--type=service")
-            .arg("--all")
-            .arg("--no-pager")
-            .arg("--plain")
+        // Second: Get runtime status of all units (with 3 second timeout)
+        let units_status_output = Command::new("timeout")
+            .args(&["3", "systemctl", "list-units", "--type=service", "--all", "--no-pager", "--plain"])
             .output()?;
 
         if !units_status_output.status.success() {
@@ -166,19 +284,16 @@ impl SystemdCollector {
         let units_status_str = String::from_utf8(units_status_output.stdout)?;
         let mut services = Vec::new();
 
-        // Use configuration instead of hardcoded values
         let excluded_services = &self.config.excluded_services;
         let service_name_filters = &self.config.service_name_filters;
 
-        // Parse all service unit files to get complete service list
+        // Parse all service unit files
         let mut all_service_names = std::collections::HashSet::new();
-        
         for line in unit_files_str.lines() {
             let fields: Vec<&str> = line.split_whitespace().collect();
             if fields.len() >= 2 && fields[0].ends_with(".service") {
                 let service_name = fields[0].trim_end_matches(".service");
                 all_service_names.insert(service_name.to_string());
-                debug!("Found service unit file: {}", service_name);
             }
         }
 
@@ -188,20 +303,14 @@ impl SystemdCollector {
             let fields: Vec<&str> = line.split_whitespace().collect();
             if fields.len() >= 4 && fields[0].ends_with(".service") {
                 let service_name = fields[0].trim_end_matches(".service");
-                
-                // Extract status information from systemctl list-units output
-                let load_state = fields.get(1).unwrap_or(&"unknown").to_string();
                 let active_state = fields.get(2).unwrap_or(&"unknown").to_string();
-                let sub_state = fields.get(3).unwrap_or(&"unknown").to_string();
 
-                // Cache the status information
                 status_cache.insert(service_name.to_string(), ServiceStatusInfo {
-                    load_state: load_state.clone(),
-                    active_state: active_state.clone(),
-                    sub_state: sub_state.clone(),
+                    active_state,
+                    memory_bytes: None,
+                    restart_count: None,
+                    start_timestamp: None,
                 });
-
-                debug!("Got runtime status for service: {} (load:{}, active:{}, sub:{})", service_name, load_state, active_state, sub_state);
             }
         }
 
@@ -209,62 +318,100 @@ impl SystemdCollector {
         for service_name in &all_service_names {
             if !status_cache.contains_key(service_name) {
                 status_cache.insert(service_name.to_string(), ServiceStatusInfo {
-                    load_state: "not-loaded".to_string(),
                     active_state: "inactive".to_string(),
-                    sub_state: "dead".to_string(),
+                    memory_bytes: None,
+                    restart_count: None,
+                    start_timestamp: None,
                 });
-                debug!("Service {} found in unit files but not runtime - marked as inactive", service_name);
             }
         }
 
-
-        // Now process all discovered services
+        // Process all discovered services and apply filters
         for service_name in &all_service_names {
-                debug!("Processing service: '{}'", service_name);
-
             // Skip excluded services first
             let mut is_excluded = false;
             for excluded in excluded_services {
                 if service_name.contains(excluded) {
-                        debug!(
-                            "EXCLUDING service '{}' because it matches pattern '{}'",
-                            service_name, excluded
-                        );
                     is_excluded = true;
                     break;
                 }
             }
 
             if is_excluded {
-                    debug!("Skipping excluded service: '{}'", service_name);
                 continue;
             }
 
             // Check if this service matches our filter patterns (supports wildcards)
             for pattern in service_name_filters {
                 if self.matches_pattern(service_name, pattern) {
-                        debug!(
-                            "INCLUDING service '{}' because it matches pattern '{}'",
-                            service_name, pattern
-                        );
                     services.push(service_name.to_string());
                     break;
                 }
             }
         }
 
-        debug!("Service discovery completed: found {} matching services: {:?}", services.len(), services);
-        if services.is_empty() {
-            debug!("No services found matching the configured filters - this may indicate a parsing issue");
+        Ok((services, status_cache))
     }
 
-        Ok((services, status_cache))
+    /// Get service status with detailed metrics from systemctl
+    fn get_service_status(&self, service: &str) -> Result<ServiceStatusInfo> {
+        // Always fetch fresh data to get detailed metrics (memory, restarts, uptime)
+        // Note: Cache in service_status_cache only has basic active_state from discovery,
+        // with all detailed metrics set to None. We need fresh systemctl show data.
+
+        let output = Command::new("timeout")
+            .args(&[
+                "2",
+                "systemctl",
+                "show",
+                &format!("{}.service", service),
+                "--property=LoadState,ActiveState,SubState,MemoryCurrent,NRestarts,ExecMainStartTimestamp"
+            ])
+            .output()?;
+
+        let output_str = String::from_utf8(output.stdout)?;
+
+        // Parse properties
+        let mut active_state = String::new();
+        let mut memory_bytes = None;
+        let mut restart_count = None;
+        let mut start_timestamp = None;
+
+        for line in output_str.lines() {
+            if let Some(value) = line.strip_prefix("ActiveState=") {
+                active_state = value.to_string();
+            } else if let Some(value) = line.strip_prefix("MemoryCurrent=") {
+                if value != "[not set]" {
+                    memory_bytes = value.parse().ok();
+                }
+            } else if let Some(value) = line.strip_prefix("NRestarts=") {
+                restart_count = value.parse().ok();
+            } else if let Some(value) = line.strip_prefix("ExecMainStartTimestamp=") {
+                if value != "[not set]" && !value.is_empty() {
+                    // Parse timestamp to seconds since epoch
+                    if let Ok(output) = Command::new("date")
+                        .args(&["+%s", "-d", value])
+                        .output()
+                    {
+                        if let Ok(timestamp_str) = String::from_utf8(output.stdout) {
+                            start_timestamp = timestamp_str.trim().parse().ok();
+                        }
+                    }
+                }
+            }
+        }
+
+        Ok(ServiceStatusInfo {
+            active_state,
+            memory_bytes,
+            restart_count,
+            start_timestamp,
+        })
     }
 
     /// Check if service name matches pattern (supports wildcards like nginx*)
     fn matches_pattern(&self, service_name: &str, pattern: &str) -> bool {
         if pattern.contains('*') {
-            // Wildcard pattern matching
             if pattern.ends_with('*') {
                 // Pattern like "nginx*" - match if service starts with "nginx"
                 let prefix = &pattern[..pattern.len() - 1];
@@ -278,81 +425,29 @@ impl SystemdCollector {
                 self.simple_glob_match(service_name, pattern)
             }
         } else {
-            // Exact match (existing behavior)
+            // Exact match
             service_name == pattern
         }
     }
 
-    /// Simple glob pattern matching for patterns with * in middle
+    /// Simple glob matching for patterns with * in the middle
     fn simple_glob_match(&self, text: &str, pattern: &str) -> bool {
         let parts: Vec<&str> = pattern.split('*').collect();
-        if parts.is_empty() {
-            return false;
-        }
-
         let mut pos = 0;
-        for (i, part) in parts.iter().enumerate() {
+        
+        for part in parts {
             if part.is_empty() {
                 continue;
             }
-
-            if i == 0 {
-                // First part must match at start
-                if !text[pos..].starts_with(part) {
-                    return false;
-                }
-                pos += part.len();
-            } else if i == parts.len() - 1 {
-                // Last part must match at end
-                return text[pos..].ends_with(part);
-            } else {
-                // Middle part must be found somewhere
             if let Some(found_pos) = text[pos..].find(part) {
                 pos += found_pos + part.len();
             } else {
                 return false;
             }
         }
-        }
         true
     }
 
-    /// Get service status from cache (if available) or fallback to systemctl
-    fn get_service_status(&self, service: &str) -> Result<(String, String)> {
-        // Try to get status from cache first
-        if let Ok(state) = self.state.read() {
-            if let Some(cached_info) = state.service_status_cache.get(service) {
-                let active_status = cached_info.active_state.clone();
-                let detailed_info = format!(
-                    "LoadState={}\nActiveState={}\nSubState={}",
-                    cached_info.load_state,
-                    cached_info.active_state,
-                    cached_info.sub_state
-                );
-                return Ok((active_status, detailed_info));
-            }
-        }
-
-        // Fallback to systemctl if not in cache (shouldn't happen during normal operation)
-        debug!("Service '{}' not found in cache, falling back to systemctl", service);
-        let output = Command::new("systemctl")
-            .arg("is-active")
-            .arg(format!("{}.service", service))
-            .output()?;
-
-        let active_status = String::from_utf8(output.stdout)?.trim().to_string();
-
-        // Get more detailed info
-        let output = Command::new("systemctl")
-        .arg("show")
-        .arg(format!("{}.service", service))
-        .arg("--property=LoadState,ActiveState,SubState")
-        .output()?;
-
-        let detailed_info = String::from_utf8(output.stdout)?;
-        Ok((active_status, detailed_info))
-    }
-
     /// 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() {
@@ -362,7 +457,7 @@ impl SystemdCollector {
                 Status::Inactive
             },
             "failed" | "error" => Status::Critical,
-            "activating" | "deactivating" | "reloading" | "start" | "stop" | "restart" => {
+            "activating" | "deactivating" | "reloading" | "starting" | "stopping" => {
                 debug!("Service '{}' is transitioning - treating as Pending", service_name);
                 Status::Pending
             },
@@ -370,86 +465,110 @@ impl SystemdCollector {
         }
     }
 
-    /// Get service memory usage (if available)
-    fn get_service_memory(&self, service: &str) -> Option<f32> {
-        let output = Command::new("systemctl")
-            .arg("show")
-            .arg(format!("{}.service", service))
-            .arg("--property=MemoryCurrent")
+    /// Check if service collection cache should be updated
+    fn should_update_cache(&self) -> bool {
+        let state = self.state.read().unwrap();
+
+        match state.last_collection {
+            None => true,
+            Some(last) => {
+                let cache_duration = std::time::Duration::from_secs(30);
+                last.elapsed() > cache_duration
+            }
+        }
+    }
+
+    /// Get cached complete service data with sub-services if available and fresh
+    fn get_cached_complete_services(&self) -> Option<Vec<ServiceData>> {
+        if !self.should_update_cache() {
+            let state = self.state.read().unwrap();
+            Some(state.cached_service_data.clone())
+        } else {
+            None
+        }
+    }
+
+    /// Get nginx sites with latency checks (internal - no caching)
+    fn get_nginx_sites_internal(&self) -> Vec<(String, f32)> {
+        let mut sites = Vec::new();
+
+        // Discover nginx sites from configuration
+        let discovered_sites = self.discover_nginx_sites();
+
+        // Always add all discovered sites, even if checks fail (like old version)
+        for (site_name, url) in &discovered_sites {
+            match self.check_site_latency(url) {
+                Ok(latency_ms) => {
+                    sites.push((site_name.clone(), latency_ms));
+                }
+                Err(_) => {
+                    // Site is unreachable - use -1.0 to indicate error (like old version)
+                    sites.push((site_name.clone(), -1.0));
+                }
+            }
+        }
+
+        sites
+    }
+
+    /// Discover nginx sites from configuration
+    fn discover_nginx_sites(&self) -> Vec<(String, String)> {
+        // Use the same approach as the old working agent: get nginx config from systemd
+        let config_content = match self.get_nginx_config_from_systemd() {
+            Some(content) => content,
+            None => {
+                debug!("Could not get nginx config from systemd, trying nginx -T fallback");
+                match self.get_nginx_config_via_command() {
+                    Some(content) => content,
+                    None => {
+                        debug!("Could not get nginx config via any method");
+                        return Vec::new();
+                    }
+                }
+            }
+        };
+
+        // Parse the config content to extract sites
+        self.parse_nginx_config_for_sites(&config_content)
+    }
+
+    /// Fallback: get nginx config via nginx -T command
+    fn get_nginx_config_via_command(&self) -> Option<String> {
+        let output = Command::new("nginx")
+            .args(&["-T"])
             .output()
             .ok()?;
 
-        let output_str = String::from_utf8(output.stdout).ok()?;
-        for line in output_str.lines() {
-            if line.starts_with("MemoryCurrent=") {
-                let memory_str = line.trim_start_matches("MemoryCurrent=");
-                if let Ok(memory_bytes) = memory_str.parse::<u64>() {
-                    return Some(memory_bytes as f32 / (1024.0 * 1024.0)); // Convert to MB
-                }
-            }
-        }
-        None
-    }
-
-
-    /// Get directory size in GB with permission-aware logging
-    fn get_directory_size(&self, dir: &str) -> Option<f32> {
-        let output = Command::new("sudo").arg("du").arg("-sb").arg(dir).output().ok()?;
-
         if !output.status.success() {
-            // Log permission errors for debugging but don't spam logs
-            let stderr = String::from_utf8_lossy(&output.stderr);
-            if stderr.contains("Permission denied") {
-                debug!("Permission denied accessing directory: {}", dir);
-            } else {
-                debug!("Failed to get size for directory {}: {}", dir, stderr);
-            }
+            debug!("nginx -T failed");
             return None;
         }
 
-        let output_str = String::from_utf8(output.stdout).ok()?;
-        let size_str = output_str.split_whitespace().next()?;
-        if let Ok(size_bytes) = size_str.parse::<u64>() {
-            let size_gb = size_bytes as f32 / (1024.0 * 1024.0 * 1024.0);
-            // Return size even if very small (minimum 0.001 GB = 1MB for visibility)
-            if size_gb > 0.0 {
-                Some(size_gb.max(0.001))
-            } else {
-                None
-            }
-        } else {
-            None
-        }
+        Some(String::from_utf8_lossy(&output.stdout).to_string())
     }
 
-    /// Get service disk usage - simplified and configuration-driven
-    fn get_service_disk_usage(&self, service: &str) -> Option<f32> {
-        // 1. Check if service has configured directories (exact match only)
-        if let Some(dirs) = self.config.service_directories.get(service) {
-            // Service has configured paths - use the first accessible one
-            for dir in dirs {
-                if let Some(size) = self.get_directory_size(dir) {
-                    return Some(size);
-                }
-            }
-            // If configured paths failed, return None (shows as 0)
-            return Some(0.0);
-        }
-
-        // 2. No configured path - use systemctl WorkingDirectory
+    /// Get nginx config from systemd service definition (NixOS compatible)
+    fn get_nginx_config_from_systemd(&self) -> Option<String> {
         let output = Command::new("systemctl")
-            .arg("show")
-            .arg(format!("{}.service", service))
-            .arg("--property=WorkingDirectory")
+            .args(&["show", "nginx", "--property=ExecStart", "--no-pager"])
             .output()
             .ok()?;
 
-        let output_str = String::from_utf8(output.stdout).ok()?;
-        for line in output_str.lines() {
-            if line.starts_with("WorkingDirectory=") && !line.contains("[not set]") {
-                let dir = line.trim_start_matches("WorkingDirectory=");
-                if !dir.is_empty() && dir != "/" {
-                    return self.get_directory_size(dir);
+        if !output.status.success() {
+            debug!("Failed to get nginx ExecStart from systemd");
+            return None;
+        }
+
+        let stdout = String::from_utf8_lossy(&output.stdout);
+        debug!("systemctl show nginx output: {}", stdout);
+
+        // Parse ExecStart to extract -c config path
+        for line in stdout.lines() {
+            if line.starts_with("ExecStart=") {
+                debug!("Found ExecStart line: {}", line);
+                if let Some(config_path) = self.extract_config_path_from_exec_start(line) {
+                    debug!("Extracted config path: {}", config_path);
+                    return std::fs::read_to_string(&config_path).ok();
                 }
             }
         }
@@ -457,194 +576,109 @@ impl SystemdCollector {
         None
     }
 
+    /// Extract config path from ExecStart line
+    fn extract_config_path_from_exec_start(&self, exec_start: &str) -> Option<String> {
+        // Remove ExecStart= prefix
+        let exec_part = exec_start.strip_prefix("ExecStart=")?;
+        debug!("Parsing exec part: {}", exec_part);
 
+        // Handle NixOS format: ExecStart={ path=...; argv[]=...nginx -c /config; ... }
+        if exec_part.contains("argv[]=") {
+            // Extract the part after argv[]=
+            let argv_start = exec_part.find("argv[]=")?;
+            let argv_part = &exec_part[argv_start + 7..]; // Skip "argv[]="
+            debug!("Found NixOS argv part: {}", argv_part);
 
-
-
-
-}
-
-#[async_trait]
-impl Collector for SystemdCollector {
-
-    async fn collect(&self, _status_tracker: &mut StatusTracker) -> Result<Vec<Metric>, CollectorError> {
-        let start_time = Instant::now();
-        debug!("Collecting systemd services metrics");
-
-        let mut metrics = Vec::new();
-
-        // Get cached services (discovery only happens when needed)
-        let monitored_services = match self.get_monitored_services() {
-            Ok(services) => services,
-            Err(e) => {
-                debug!("Failed to get monitored services: {}", e);
-                return Ok(metrics);
+            // Look for -c flag followed by config path
+            if let Some(c_pos) = argv_part.find(" -c ") {
+                let after_c = &argv_part[c_pos + 4..];
+                // Find the config path (until next space or semicolon)
+                let config_path = after_c.split([' ', ';']).next()?;
+                return Some(config_path.to_string());
             }
-        };
-
-        // Collect individual metrics for each monitored service (status, memory, disk only)
-        for service in &monitored_services {
-            match self.get_service_status(service) {
-                Ok((active_status, _detailed_info)) => {
-                    let status = self.calculate_service_status(service, &active_status);
-
-                    // Individual service status metric
-                    metrics.push(Metric {
-                        name: format!("service_{}_status", service),
-                        value: MetricValue::String(active_status.clone()),
-                        unit: None,
-                        description: Some(format!("Service {} status", service)),
-                        status,
-                        timestamp: chrono::Utc::now().timestamp() as u64,
-                    });
-
-                    // Service memory usage (if available)
-                    if let Some(memory_mb) = self.get_service_memory(service) {
-                        metrics.push(Metric {
-                            name: format!("service_{}_memory_mb", service),
-                            value: MetricValue::Float(memory_mb),
-                            unit: Some("MB".to_string()),
-                            description: Some(format!("Service {} memory usage", service)),
-                            status: Status::Ok,
-                            timestamp: chrono::Utc::now().timestamp() as u64,
-                        });
-                    }
-
-                    // Service disk usage (comprehensive detection)
-                    if let Some(disk_gb) = self.get_service_disk_usage(service) {
-                        metrics.push(Metric {
-                            name: format!("service_{}_disk_gb", service),
-                            value: MetricValue::Float(disk_gb),
-                            unit: Some("GB".to_string()),
-                            description: Some(format!("Service {} disk usage", service)),
-                            status: Status::Ok,
-                            timestamp: chrono::Utc::now().timestamp() as u64,
-                        });
-                    }
-
-                    // Sub-service metrics for specific services
-                    if service.contains("nginx") && active_status == "active" {
-                        metrics.extend(self.get_nginx_site_metrics());
-                    }
-
-                    if service.contains("docker") && active_status == "active" {
-                        metrics.extend(self.get_docker_containers());
-                    }
-                }
-                Err(e) => {
-                    debug!("Failed to get status for service {}: {}", service, e);
-                }
-            }
-        }
-
-        let collection_time = start_time.elapsed();
-        debug!(
-            "Systemd collection completed in {:?} with {} individual service metrics",
-            collection_time,
-            metrics.len()
-        );
-
-        Ok(metrics)
-    }
-
-}
-
-impl SystemdCollector {
-    /// Get nginx sites with latency checks
-    fn get_nginx_sites(&self) -> Vec<Metric> {
-        let mut metrics = Vec::new();
-        let timestamp = chrono::Utc::now().timestamp() as u64;
-
-        // Discover nginx sites from configuration
-        let sites = self.discover_nginx_sites();
-
-        for (site_name, url) in &sites {
-            match self.check_site_latency(url) {
-                Ok(latency_ms) => {
-                    let status = if latency_ms < self.config.nginx_latency_critical_ms {
-                        Status::Ok
         } else {
-                        Status::Critical
-                    };
-
-                    metrics.push(Metric {
-                        name: format!("service_nginx_{}_latency_ms", site_name),
-                        value: MetricValue::Float(latency_ms),
-                        unit: Some("ms".to_string()),
-                        description: Some(format!("Response time for {}", url)),
-                        status,
-                        timestamp,
-                    });
+            // Handle traditional format: ExecStart=/path/nginx -c /config
+            debug!("Parsing traditional format");
+            if let Some(c_pos) = exec_part.find(" -c ") {
+                let after_c = &exec_part[c_pos + 4..];
+                let config_path = after_c.split_whitespace().next()?;
+                return Some(config_path.to_string());
+            }
+        }
+
+        None
+    }
+
+    /// Parse nginx config content to extract server names and build site list
+    fn parse_nginx_config_for_sites(&self, config_content: &str) -> Vec<(String, String)> {
+        let mut sites = Vec::new();
+        let lines: Vec<&str> = config_content.lines().collect();
+        let mut i = 0;
+
+        debug!("Parsing nginx config with {} lines", lines.len());
+
+        while i < lines.len() {
+            let line = lines[i].trim();
+            if line.starts_with("server") && line.contains("{") {
+                if let Some(server_name) = self.parse_server_block(&lines, &mut i) {
+                    let url = format!("https://{}", server_name);
+                    sites.push((server_name.clone(), url));
+                }
+            }
+            i += 1;
+        }
+
+        debug!("Discovered {} nginx sites total", sites.len());
+        sites
+    }
+
+    /// Parse a server block to extract the primary server_name
+    fn parse_server_block(&self, lines: &[&str], start_index: &mut usize) -> Option<String> {
+        let mut server_names = Vec::new();
+        let mut has_redirect = false;
+        let mut i = *start_index + 1;
+        let mut brace_count = 1;
+
+        // Parse until we close the server block
+        while i < lines.len() && brace_count > 0 {
+            let trimmed = lines[i].trim();
+
+            // Track braces
+            brace_count += trimmed.matches('{').count();
+            brace_count -= trimmed.matches('}').count();
+
+            // Extract server_name
+            if trimmed.starts_with("server_name") {
+                if let Some(names_part) = trimmed.strip_prefix("server_name") {
+                    let names_clean = names_part.trim().trim_end_matches(';');
+                    for name in names_clean.split_whitespace() {
+                        if name != "_"
+                            && !name.is_empty()
+                            && name.contains('.')
+                            && !name.starts_with('$')
+                        {
+                            server_names.push(name.to_string());
+                            debug!("Found server_name in block: {}", name);
                         }
-                Err(_) => {
-                    // Site is unreachable
-                    metrics.push(Metric {
-                        name: format!("service_nginx_{}_latency_ms", site_name),
-                        value: MetricValue::Float(-1.0), // Use -1 to indicate error
-                        unit: Some("ms".to_string()),
-                        description: Some(format!("Response time for {} (unreachable)", url)),
-                        status: Status::Critical,
-                        timestamp,
-                    });
                     }
                 }
             }
 
-        metrics
+            // Check for redirects (skip redirect-only servers)
+            if trimmed.contains("return") && (trimmed.contains("301") || trimmed.contains("302")) {
+                has_redirect = true;
             }
 
-    /// Get docker containers as sub-services
-    fn get_docker_containers(&self) -> Vec<Metric> {
-        let mut metrics = Vec::new();
-        let timestamp = chrono::Utc::now().timestamp() as u64;
-
-        // Check if docker is available
-        let output = Command::new("docker")
-            .arg("ps")
-            .arg("--format")
-            .arg("{{.Names}},{{.Status}}")
-            .output();
-
-        let output = match output {
-            Ok(out) if out.status.success() => out,
-            _ => return metrics, // Docker not available or failed
-        };
-
-        let output_str = match String::from_utf8(output.stdout) {
-            Ok(s) => s,
-            Err(_) => return metrics,
-        };
-
-        for line in output_str.lines() {
-            if line.trim().is_empty() {
-                continue;
+            i += 1;
         }
 
-            let parts: Vec<&str> = line.split(',').collect();
-            if parts.len() >= 2 {
-                let container_name = parts[0].trim();
-                let status_str = parts[1].trim();
+        *start_index = i - 1;
 
-                let status = if status_str.contains("Up") {
-                    Status::Ok
-                } else if status_str.contains("Exited") {
-                    Status::Warning
-                } else {
-                    Status::Critical
-                };
-
-                metrics.push(Metric {
-                    name: format!("service_docker_{}_status", container_name),
-                    value: MetricValue::String(status_str.to_string()),
-                    unit: None,
-                    description: Some(format!("Docker container {} status", container_name)),
-                    status,
-                    timestamp,
-                });
-            }
+        if !server_names.is_empty() && !has_redirect {
+            return Some(server_names[0].clone());
         }
 
-        metrics
+        None
     }
 
     /// Check site latency using HTTP GET requests
@@ -678,188 +712,144 @@ impl SystemdCollector {
         }
     }
 
-    /// Discover nginx sites from configuration files (like the old working implementation)
-    fn discover_nginx_sites(&self) -> Vec<(String, String)> {
-        use tracing::debug;
+    /// Get docker containers as sub-services
+    fn get_docker_containers(&self) -> Vec<(String, String)> {
+        let mut containers = Vec::new();
 
-        // Use the same approach as the old working agent: get nginx config from systemd
-        let config_content = match self.get_nginx_config_from_systemd() {
-            Some(content) => content,
-            None => {
-                debug!("Could not get nginx config from systemd, trying nginx -T fallback");
-                match self.get_nginx_config_via_command() {
-                    Some(content) => content,
-                    None => {
-                        debug!("Could not get nginx config via any method");
-                        return Vec::new();
+        // Check if docker is available (cm-agent user is in docker group)
+        // Use -a to show ALL containers (running and stopped) with 3 second timeout
+        let output = Command::new("timeout")
+            .args(&["3", "docker", "ps", "-a", "--format", "{{.Names}},{{.Status}}"])
+            .output();
+
+        let output = match output {
+            Ok(out) if out.status.success() => out,
+            _ => return containers, // Docker not available or failed
+        };
+
+        let output_str = match String::from_utf8(output.stdout) {
+            Ok(s) => s,
+            Err(_) => return containers,
+        };
+
+        for line in output_str.lines() {
+            if line.trim().is_empty() {
+                continue;
+            }
+
+            let parts: Vec<&str> = line.split(',').collect();
+            if parts.len() >= 2 {
+                let container_name = parts[0].trim();
+                let status_str = parts[1].trim();
+
+                let container_status = if status_str.contains("Up") {
+                    "active"
+                } else if status_str.contains("Exited") || status_str.contains("Created") {
+                    "inactive" // Stopped/created containers are inactive
+                } else {
+                    "failed" // Other states (restarting, paused, dead) → failed
+                };
+                
+                containers.push((format!("docker_{}", container_name), container_status.to_string()));
             }
         }
+
+        containers
+    }
+
+    /// Get docker images as sub-services
+    fn get_docker_images(&self) -> Vec<(String, String, f32)> {
+        let mut images = Vec::new();
+        // Check if docker is available (cm-agent user is in docker group) with 3 second timeout
+        let output = Command::new("timeout")
+            .args(&["3", "docker", "images", "--format", "{{.Repository}}:{{.Tag}},{{.Size}}"])
+            .output();
+
+        let output = match output {
+            Ok(out) if out.status.success() => out,
+            Ok(_) => {
+                return images;
+            }
+            Err(_) => {
+                return images;
             }
         };
 
-        // Parse the config content to extract sites
-        self.parse_nginx_config_for_sites(&config_content)
+        let output_str = match String::from_utf8(output.stdout) {
+            Ok(s) => s,
+            Err(_) => return images,
+        };
+
+        for line in output_str.lines() {
+            if line.trim().is_empty() {
+                continue;
             }
 
-    /// Get nginx config from systemd service definition (NixOS compatible)
-    fn get_nginx_config_from_systemd(&self) -> Option<String> {
-        use tracing::debug;
+            let parts: Vec<&str> = line.split(',').collect();
+            if parts.len() >= 2 {
+                let image_name = parts[0].trim();
+                let size_str = parts[1].trim();
 
-        let output = std::process::Command::new("systemctl")
-            .args(["show", "nginx", "--property=ExecStart", "--no-pager"])
-            .output()
-            .ok()?;
-
-        if !output.status.success() {
-            debug!("Failed to get nginx ExecStart from systemd");
-            return None;
+                // Skip <none>:<none> images (dangling images)
+                if image_name.contains("<none>") {
+                    continue;
                 }
 
-        let stdout = String::from_utf8_lossy(&output.stdout);
-        debug!("systemctl show nginx output: {}", stdout);
+                // Parse size to MB (sizes come as "142MB", "1.5GB", "512kB", etc.)
+                let size_mb = self.parse_docker_size(size_str);
 
-        // Parse ExecStart to extract -c config path
-        for line in stdout.lines() {
-            if line.starts_with("ExecStart=") {
-                debug!("Found ExecStart line: {}", line);
-                // Handle both traditional and NixOS systemd formats
-                if let Some(config_path) = self.extract_config_path_from_exec_start(line) {
-                    debug!("Extracted config path: {}", config_path);
-                    // Read the config file
-                    return std::fs::read_to_string(&config_path)
-                        .map_err(|e| debug!("Failed to read config file {}: {}", config_path, e))
-                        .ok();
-                }
-            }
-        }
-
-        None
-    }
-
-    /// Extract config path from ExecStart line
-    fn extract_config_path_from_exec_start(&self, exec_start: &str) -> Option<String> {
-        use tracing::debug;
-
-        // Remove ExecStart= prefix
-        let exec_part = exec_start.strip_prefix("ExecStart=")?;
-        debug!("Parsing exec part: {}", exec_part);
-
-        // Handle NixOS format: ExecStart={ path=...; argv[]=...nginx -c /config; ... }
-        if exec_part.contains("argv[]=") {
-            // Extract the part after argv[]=
-            let argv_start = exec_part.find("argv[]=")?;
-            let argv_part = &exec_part[argv_start + 7..]; // Skip "argv[]="
-            debug!("Found NixOS argv part: {}", argv_part);
-
-            // Look for -c flag followed by config path
-            if let Some(c_pos) = argv_part.find(" -c ") {
-                let after_c = &argv_part[c_pos + 4..];
-                // Find the config path (until next space or semicolon)
-                let config_path = after_c.split([' ', ';']).next()?;
-                return Some(config_path.to_string());
-            }
-        } else {
-            // Handle traditional format: ExecStart=/path/nginx -c /config
-            debug!("Parsing traditional format");
-            if let Some(c_pos) = exec_part.find(" -c ") {
-                let after_c = &exec_part[c_pos + 4..];
-                let config_path = after_c.split_whitespace().next()?;
-                return Some(config_path.to_string());
+                images.push((
+                    image_name.to_string(),
+                    "inactive".to_string(), // Images are informational - use inactive for neutral display
+                    size_mb
+                ));
             }
         }
 
-        None
+        images
     }
 
-    /// Fallback: get nginx config via nginx -T command
-    fn get_nginx_config_via_command(&self) -> Option<String> {
-        use tracing::debug;
+    /// Parse Docker size string to MB
+    fn parse_docker_size(&self, size_str: &str) -> f32 {
+        let size_upper = size_str.to_uppercase();
 
-        let output = std::process::Command::new("nginx")
-            .args(["-T"])
-            .output()
-            .ok()?;
+        // Extract numeric part and unit
+        let mut num_str = String::new();
+        let mut unit = String::new();
 
-        if !output.status.success() {
-            debug!("nginx -T failed");
-            return None;
-        }
-
-        Some(String::from_utf8_lossy(&output.stdout).to_string())
-    }
-
-    /// Parse nginx config content to extract server names and build site list
-    fn parse_nginx_config_for_sites(&self, config_content: &str) -> Vec<(String, String)> {
-        use tracing::debug;
-        let mut sites = Vec::new();
-        let lines: Vec<&str> = config_content.lines().collect();
-        let mut i = 0;
-
-        debug!("Parsing nginx config with {} lines", lines.len());
-
-        while i < lines.len() {
-            let line = lines[i].trim();
-            if line.starts_with("server") && line.contains("{") {
-                if let Some(server_name) = self.parse_server_block(&lines, &mut i) {
-                    let url = format!("https://{}", server_name);
-                    sites.push((server_name.clone(), url));
-                }
-            }
-            i += 1;
-        }
-
-        debug!("Discovered {} nginx sites total", sites.len());
-        sites
-    }
-
-    /// Parse a server block to extract the primary server_name
-    fn parse_server_block(&self, lines: &[&str], start_index: &mut usize) -> Option<String> {
-        use tracing::debug;
-        let mut server_names = Vec::new();
-        let mut has_redirect = false;
-        let mut i = *start_index + 1;
-        let mut brace_count = 1;
-
-        // Parse until we close the server block
-        while i < lines.len() && brace_count > 0 {
-            let trimmed = lines[i].trim();
-
-            // Track braces
-            brace_count += trimmed.matches('{').count();
-            brace_count -= trimmed.matches('}').count();
-
-            // Extract server_name
-            if trimmed.starts_with("server_name") {
-                if let Some(names_part) = trimmed.strip_prefix("server_name") {
-                    let names_clean = names_part.trim().trim_end_matches(';');
-                    for name in names_clean.split_whitespace() {
-                        if name != "_"
-                            && !name.is_empty()
-                            && name.contains('.')
-                            && !name.starts_with('$')
-                        {
-                            server_names.push(name.to_string());
-                            debug!("Found server_name in block: {}", name);
-                        }
-                    }
+        for ch in size_upper.chars() {
+            if ch.is_ascii_digit() || ch == '.' {
+                num_str.push(ch);
+            } else if ch.is_alphabetic() {
+                unit.push(ch);
             }
         }
 
+        let value: f32 = num_str.parse().unwrap_or(0.0);
 
-            // Check for redirects (skip redirect-only servers)
-            if trimmed.contains("return") && (trimmed.contains("301") || trimmed.contains("302")) {
-                has_redirect = true;
+        // Convert to MB
+        match unit.as_str() {
+            "KB" | "K" => value / 1024.0,
+            "MB" | "M" => value,
+            "GB" | "G" => value * 1024.0,
+            "TB" | "T" => value * 1024.0 * 1024.0,
+            _ => value, // Assume bytes if no unit
+        }
+    }
+}
+
+#[async_trait]
+impl Collector for SystemdCollector {
+    async fn collect_structured(&self, agent_data: &mut AgentData) -> Result<(), CollectorError> {
+        // Use cached complete data if available and fresh
+        if let Some(cached_complete_services) = self.get_cached_complete_services() {
+            for service_data in cached_complete_services {
+                agent_data.services.push(service_data);
+            }
+            Ok(())
+        } else {
+            // Collect fresh data
+            self.collect_service_data(agent_data).await
         }
-
-            i += 1;
-        }
-
-        *start_index = i - 1;
-
-        if !server_names.is_empty() && !has_redirect {
-            return Some(server_names[0].clone());
-        }
-
-        None
     }
 }

agent/src/collectors/systemd_old.rs

@@ -0,0 +1,403 @@
+use anyhow::Result;
+use async_trait::async_trait;
+use cm_dashboard_shared::{AgentData, ServiceData, Status};
+use std::process::Command;
+use std::sync::RwLock;
+use std::time::Instant;
+use tracing::debug;
+
+use super::{Collector, CollectorError};
+use crate::config::SystemdConfig;
+
+/// Systemd collector for monitoring systemd services with structured data output
+pub struct SystemdCollector {
+    /// Cached state with thread-safe interior mutability
+    state: RwLock<ServiceCacheState>,
+    /// Configuration for service monitoring
+    config: SystemdConfig,
+}
+
+/// Internal state for service caching
+#[derive(Debug, Clone)]
+struct ServiceCacheState {
+    /// Last collection time for performance tracking
+    last_collection: Option<Instant>,
+    /// Cached service data
+    services: Vec<ServiceInfo>,
+    /// Interesting services to monitor (cached after discovery)
+    monitored_services: Vec<String>,
+    /// Cached service status information from discovery
+    service_status_cache: std::collections::HashMap<String, ServiceStatusInfo>,
+    /// Last time services were discovered
+    last_discovery_time: Option<Instant>,
+    /// How often to rediscover services (from config)
+    discovery_interval_seconds: u64,
+}
+
+/// Cached service status information from systemctl list-units
+#[derive(Debug, Clone)]
+struct ServiceStatusInfo {
+    load_state: String,
+    active_state: String,
+    sub_state: String,
+}
+
+/// Internal service information
+#[derive(Debug, Clone)]
+struct ServiceInfo {
+    name: String,
+    status: String,           // "active", "inactive", "failed", etc.
+    memory_mb: f32,          // Memory usage in MB
+    disk_gb: f32,            // Disk usage in GB (usually 0 for services)
+}
+
+impl SystemdCollector {
+    pub fn new(config: SystemdConfig) -> Self {
+        let state = ServiceCacheState {
+            last_collection: None,
+            services: Vec::new(),
+            monitored_services: Vec::new(),
+            service_status_cache: std::collections::HashMap::new(),
+            last_discovery_time: None,
+            discovery_interval_seconds: config.interval_seconds,
+        };
+        
+        Self {
+            state: RwLock::new(state),
+            config,
+        }
+    }
+
+    /// Collect service data and populate AgentData
+    async fn collect_service_data(&self, agent_data: &mut AgentData) -> Result<(), CollectorError> {
+        let start_time = Instant::now();
+        debug!("Collecting systemd services metrics");
+
+        // Get cached services (discovery only happens when needed)
+        let monitored_services = match self.get_monitored_services() {
+            Ok(services) => services,
+            Err(e) => {
+                debug!("Failed to get monitored services: {}", e);
+                return Ok(());
+            }
+        };
+
+        // Collect service data for each monitored service
+        let mut services = Vec::new();
+        for service_name in &monitored_services {
+            match self.get_service_status(service_name) {
+                Ok((active_status, _detailed_info)) => {
+                    let memory_mb = self.get_service_memory_usage(service_name).await.unwrap_or(0.0);
+                    let disk_gb = self.get_service_disk_usage(service_name).await.unwrap_or(0.0);
+                    
+                    let service_info = ServiceInfo {
+                        name: service_name.clone(),
+                        status: active_status,
+                        memory_mb,
+                        disk_gb,
+                    };
+                    services.push(service_info);
+                }
+                Err(e) => {
+                    debug!("Failed to get status for service {}: {}", service_name, e);
+                }
+            }
+        }
+        
+        // Update cached state
+        {
+            let mut state = self.state.write().unwrap();
+            state.last_collection = Some(start_time);
+            state.services = services.clone();
+        }
+
+        // Populate AgentData with service information
+        for service in services {
+            agent_data.services.push(ServiceData {
+                name: service.name.clone(),
+                status: service.status.clone(),
+                memory_mb: service.memory_mb,
+                disk_gb: service.disk_gb,
+                user_stopped: false, // TODO: Integrate with service tracker
+                service_status: self.calculate_service_status(&service.name, &service.status),
+            });
+        }
+
+        let elapsed = start_time.elapsed();
+        debug!("Systemd collection completed in {:?} with {} services", elapsed, agent_data.services.len());
+
+        Ok(())
+    }
+
+    /// Get systemd services information
+    async fn get_systemd_services(&self) -> Result<Vec<ServiceInfo>, CollectorError> {
+        let mut services = Vec::new();
+
+        // Get ALL service unit files (includes inactive services)
+        let unit_files_output = Command::new("systemctl")
+            .args(&["list-unit-files", "--type=service", "--no-pager", "--plain"])
+            .output()
+            .map_err(|e| CollectorError::SystemRead {
+                path: "systemctl list-unit-files".to_string(),
+                error: e.to_string(),
+            })?;
+
+        // Get runtime status of ALL units (including inactive)
+        let status_output = Command::new("systemctl")
+            .args(&["list-units", "--type=service", "--all", "--no-pager", "--plain"])
+            .output()
+            .map_err(|e| CollectorError::SystemRead {
+                path: "systemctl list-units --all".to_string(),
+                error: e.to_string(),
+            })?;
+
+        let unit_files_str = String::from_utf8_lossy(&unit_files_output.stdout);
+        let status_str = String::from_utf8_lossy(&status_output.stdout);
+        
+        // Parse all service unit files to get complete service list
+        let mut all_service_names = std::collections::HashSet::new();
+        for line in unit_files_str.lines() {
+            let fields: Vec<&str> = line.split_whitespace().collect();
+            if fields.len() >= 2 && fields[0].ends_with(".service") {
+                let service_name = fields[0].trim_end_matches(".service");
+                all_service_names.insert(service_name.to_string());
+            }
+        }
+
+        // Parse runtime status for all units
+        let mut status_cache = std::collections::HashMap::new();
+        for line in status_str.lines() {
+            let fields: Vec<&str> = line.split_whitespace().collect();
+            if fields.len() >= 4 && fields[0].ends_with(".service") {
+                let service_name = fields[0].trim_end_matches(".service");
+                let load_state = fields.get(1).unwrap_or(&"unknown").to_string();
+                let active_state = fields.get(2).unwrap_or(&"unknown").to_string();
+                let sub_state = fields.get(3).unwrap_or(&"unknown").to_string();
+                status_cache.insert(service_name.to_string(), (load_state, active_state, sub_state));
+            }
+        }
+
+        // For services found in unit files but not in runtime status, set default inactive status
+        for service_name in &all_service_names {
+            if !status_cache.contains_key(service_name) {
+                status_cache.insert(service_name.to_string(), (
+                    "not-loaded".to_string(),
+                    "inactive".to_string(), 
+                    "dead".to_string()
+                ));
+            }
+        }
+
+        // Process all discovered services and apply filters
+        for service_name in &all_service_names {
+            if self.should_monitor_service(service_name) {
+                if let Some((load_state, active_state, sub_state)) = status_cache.get(service_name) {
+                    let memory_mb = self.get_service_memory_usage(service_name).await.unwrap_or(0.0);
+                    let disk_gb = self.get_service_disk_usage(service_name).await.unwrap_or(0.0);
+                    
+                    let normalized_status = self.normalize_service_status(active_state, sub_state);
+                    let service_info = ServiceInfo {
+                        name: service_name.to_string(),
+                        status: normalized_status,
+                        memory_mb,
+                        disk_gb,
+                    };
+
+                    services.push(service_info);
+                }
+            }
+        }
+
+        Ok(services)
+    }
+
+    /// Check if a service should be monitored based on configuration filters with wildcard support
+    fn should_monitor_service(&self, service_name: &str) -> bool {
+        // If no filters configured, monitor nothing (to prevent noise)
+        if self.config.service_name_filters.is_empty() {
+            return false;
+        }
+        
+        // Check if service matches any of the configured patterns
+        for pattern in &self.config.service_name_filters {
+            if self.matches_pattern(service_name, pattern) {
+                return true;
+            }
+        }
+        
+        false
+    }
+    
+    /// Check if service name matches pattern (supports wildcards like nginx*)
+    fn matches_pattern(&self, service_name: &str, pattern: &str) -> bool {
+        if pattern.ends_with('*') {
+            let prefix = &pattern[..pattern.len() - 1];
+            service_name.starts_with(prefix)
+        } else {
+            service_name == pattern
+        }
+    }
+    
+    /// Get disk usage for a specific service
+    async fn get_service_disk_usage(&self, service_name: &str) -> Result<f32, CollectorError> {
+        // Check if this service has configured directory paths
+        if let Some(dirs) = self.config.service_directories.get(service_name) {
+            // Service has configured paths - use the first accessible one
+            for dir in dirs {
+                if let Some(size) = self.get_directory_size(dir) {
+                    return Ok(size);
+                }
+            }
+            // If configured paths failed, return 0
+            return Ok(0.0);
+        }
+
+        // No configured path - try to get WorkingDirectory from systemctl
+        let output = Command::new("systemctl")
+            .args(&["show", &format!("{}.service", service_name), "--property=WorkingDirectory"])
+            .output()
+            .map_err(|e| CollectorError::SystemRead {
+                path: format!("WorkingDirectory for {}", service_name),
+                error: e.to_string(),
+            })?;
+
+        let output_str = String::from_utf8_lossy(&output.stdout);
+        for line in output_str.lines() {
+            if line.starts_with("WorkingDirectory=") && !line.contains("[not set]") {
+                let dir = line.strip_prefix("WorkingDirectory=").unwrap_or("");
+                if !dir.is_empty() {
+                    return Ok(self.get_directory_size(dir).unwrap_or(0.0));
+                }
+            }
+        }
+
+        Ok(0.0)
+    }
+    
+    /// Get size of a directory in GB
+    fn get_directory_size(&self, path: &str) -> Option<f32> {
+        let output = Command::new("du")
+            .args(&["-sb", path])
+            .output()
+            .ok()?;
+
+        if !output.status.success() {
+            return None;
+        }
+
+        let output_str = String::from_utf8_lossy(&output.stdout);
+        let parts: Vec<&str> = output_str.split_whitespace().collect();
+        if let Some(size_str) = parts.first() {
+            if let Ok(size_bytes) = size_str.parse::<u64>() {
+                return Some(size_bytes as f32 / (1024.0 * 1024.0 * 1024.0));
+            }
+        }
+
+        None
+    }
+
+    /// 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,
+            "inactive" | "dead" => {
+                debug!("Service '{}' is inactive - treating as Inactive status", service_name);
+                Status::Inactive
+            },
+            "failed" | "error" => Status::Critical,
+            "activating" | "deactivating" | "reloading" | "starting" | "stopping" => {
+                debug!("Service '{}' is transitioning - treating as Pending", service_name);
+                Status::Pending
+            },
+            _ => Status::Unknown,
+        }
+    }
+
+    /// Get memory usage for a specific service
+    async fn get_service_memory_usage(&self, service_name: &str) -> Result<f32, CollectorError> {
+        let output = Command::new("systemctl")
+            .args(&["show", &format!("{}.service", service_name), "--property=MemoryCurrent"])
+            .output()
+            .map_err(|e| CollectorError::SystemRead {
+                path: format!("memory usage for {}", service_name),
+                error: e.to_string(),
+            })?;
+
+        let output_str = String::from_utf8_lossy(&output.stdout);
+        
+        for line in output_str.lines() {
+            if line.starts_with("MemoryCurrent=") {
+                if let Some(mem_str) = line.strip_prefix("MemoryCurrent=") {
+                    if mem_str != "[not set]" {
+                        if let Ok(memory_bytes) = mem_str.parse::<u64>() {
+                            return Ok(memory_bytes as f32 / (1024.0 * 1024.0)); // Convert to MB
+                        }
+                    }
+                }
+            }
+        }
+
+        Ok(0.0)
+    }
+
+    /// Normalize service status to standard values
+    fn normalize_service_status(&self, active_state: &str, sub_state: &str) -> String {
+        match (active_state, sub_state) {
+            ("active", "running") => "active".to_string(),
+            ("active", _) => "active".to_string(),
+            ("inactive", "dead") => "inactive".to_string(),
+            ("inactive", _) => "inactive".to_string(),
+            ("failed", _) => "failed".to_string(),
+            ("activating", _) => "starting".to_string(),
+            ("deactivating", _) => "stopping".to_string(),
+            _ => format!("{}:{}", active_state, sub_state),
+        }
+    }
+
+    /// Check if service collection cache should be updated
+    fn should_update_cache(&self) -> bool {
+        let state = self.state.read().unwrap();
+        
+        match state.last_collection {
+            None => true,
+            Some(last) => {
+                let cache_duration = std::time::Duration::from_secs(30);
+                last.elapsed() > cache_duration
+            }
+        }
+    }
+
+    /// Get cached service data if available and fresh
+    fn get_cached_services(&self) -> Option<Vec<ServiceInfo>> {
+        if !self.should_update_cache() {
+            let state = self.state.read().unwrap();
+            Some(state.services.clone())
+        } else {
+            None
+        }
+    }
+}
+
+#[async_trait]
+impl Collector for SystemdCollector {
+    async fn collect_structured(&self, agent_data: &mut AgentData) -> Result<(), CollectorError> {
+        // Use cached data if available and fresh
+        if let Some(cached_services) = self.get_cached_services() {
+            debug!("Using cached systemd services data");
+            for service in cached_services {
+                agent_data.services.push(ServiceData {
+                    name: service.name.clone(),
+                    status: service.status.clone(),
+                    memory_mb: service.memory_mb,
+                    disk_gb: service.disk_gb,
+                    user_stopped: false, // TODO: Integrate with service tracker
+                    service_status: self.calculate_service_status(&service.name, &service.status),
+                });
+            }
+            Ok(())
+        } else {
+            // Collect fresh data
+            self.collect_service_data(agent_data).await
+        }
+    }
+}

agent/src/communication/mod.rs

@@ -5,10 +5,9 @@ use zmq::{Context, Socket, SocketType};
 
 use crate::config::ZmqConfig;
 
-/// ZMQ communication handler for publishing metrics and receiving commands
+/// ZMQ communication handler for publishing metrics
 pub struct ZmqHandler {
     publisher: Socket,
-    command_receiver: Socket,
 }
 
 impl ZmqHandler {
@@ -26,20 +25,8 @@ impl ZmqHandler {
         publisher.set_sndhwm(1000)?; // High water mark for outbound messages
         publisher.set_linger(1000)?; // Linger time on close
 
-        // Create command receiver socket (PULL socket to receive commands from dashboard)
-        let command_receiver = context.socket(SocketType::PULL)?;
-        let cmd_bind_address = format!("tcp://{}:{}", config.bind_address, config.command_port);
-        command_receiver.bind(&cmd_bind_address)?;
-
-        info!("ZMQ command receiver bound to {}", cmd_bind_address);
-
-        // Set non-blocking mode for command receiver
-        command_receiver.set_rcvtimeo(0)?; // Non-blocking receive
-        command_receiver.set_linger(1000)?;
-
         Ok(Self {
             publisher,
-            command_receiver,
         })
     }
 
@@ -65,36 +52,4 @@ impl ZmqHandler {
         Ok(())
     }
 
-    /// Try to receive a command (non-blocking)
-    pub fn try_receive_command(&self) -> Result<Option<AgentCommand>> {
-        match self.command_receiver.recv_bytes(zmq::DONTWAIT) {
-            Ok(bytes) => {
-                debug!("Received command message ({} bytes)", bytes.len());
-
-                let command: AgentCommand = serde_json::from_slice(&bytes)
-                    .map_err(|e| anyhow::anyhow!("Failed to deserialize command: {}", e))?;
-
-                debug!("Parsed command: {:?}", command);
-                Ok(Some(command))
-            }
-            Err(zmq::Error::EAGAIN) => {
-                // No message available (non-blocking)
-                Ok(None)
-            }
-            Err(e) => Err(anyhow::anyhow!("ZMQ receive error: {}", e)),
-        }
-    }
-}
-
-/// Commands that can be sent to the agent
-#[derive(Debug, Clone, serde::Deserialize, serde::Serialize)]
-pub enum AgentCommand {
-    /// Request immediate metric collection
-    CollectNow,
-    /// Change collection interval
-    SetInterval { seconds: u64 },
-    /// Enable/disable a collector
-    ToggleCollector { name: String, enabled: bool },
-    /// Request status/health check
-    Ping,
 }

agent/src/config/defaults.rs

@@ -1,2 +0,0 @@
-// This file is now empty - all configuration values come from config files
-// No hardcoded defaults are used

agent/src/config/mod.rs

@@ -6,8 +6,6 @@ use std::path::Path;
 pub mod loader;
 pub mod validation;
 
-use crate::status::HostStatusConfig;
-
 /// Main agent configuration
 #[derive(Debug, Clone, Serialize, Deserialize)]
 pub struct AgentConfig {
@@ -15,15 +13,12 @@ pub struct AgentConfig {
     pub collectors: CollectorConfig,
     pub cache: CacheConfig,
     pub notifications: NotificationConfig,
-    pub status_aggregation: HostStatusConfig,
-    pub collection_interval_seconds: u64,
 }
 
 /// ZMQ communication configuration
 #[derive(Debug, Clone, Serialize, Deserialize)]
 pub struct ZmqConfig {
     pub publisher_port: u16,
-    pub command_port: u16,
     pub bind_address: String,
     pub transmission_interval_seconds: u64,
     /// Heartbeat transmission interval in seconds for host connectivity detection

agent/src/config/validation.rs

@@ -7,21 +7,13 @@ pub fn validate_config(config: &AgentConfig) -> Result<()> {
         bail!("ZMQ publisher port cannot be 0");
     }
 
-    if config.zmq.command_port == 0 {
-        bail!("ZMQ command port cannot be 0");
-    }
-
-    if config.zmq.publisher_port == config.zmq.command_port {
-        bail!("ZMQ publisher and command ports cannot be the same");
-    }
-
     if config.zmq.bind_address.is_empty() {
         bail!("ZMQ bind address cannot be empty");
     }
 
-    // Validate collection interval
-    if config.collection_interval_seconds == 0 {
-        bail!("Collection interval cannot be 0");
+    // Validate ZMQ transmission interval
+    if config.zmq.transmission_interval_seconds == 0 {
+        bail!("ZMQ transmission interval cannot be 0");
     }
 
     // Validate CPU thresholds

agent/src/main.rs

@@ -7,10 +7,7 @@ mod agent;
 mod collectors;
 mod communication;
 mod config;
-mod metrics;
 mod notifications;
-mod service_tracker;
-mod status;
 
 use agent::Agent;
 

agent/src/service_tracker.rs

@@ -1,164 +0,0 @@
-use anyhow::Result;
-use serde::{Deserialize, Serialize};
-use std::collections::HashSet;
-use std::fs;
-use std::path::Path;
-use std::sync::{Arc, Mutex, OnceLock};
-use tracing::{debug, info, warn};
-
-/// Shared instance for global access
-static GLOBAL_TRACKER: OnceLock<Arc<Mutex<UserStoppedServiceTracker>>> = OnceLock::new();
-
-/// Tracks services that have been stopped by user action
-/// These services should be treated as OK status instead of Warning
-#[derive(Debug)]
-pub struct UserStoppedServiceTracker {
-    /// Set of services stopped by user action
-    user_stopped_services: HashSet<String>,
-    /// Path to persistent storage file
-    storage_path: String,
-}
-
-/// Serializable data structure for persistence
-#[derive(Debug, Serialize, Deserialize)]
-struct UserStoppedData {
-    services: Vec<String>,
-}
-
-impl UserStoppedServiceTracker {
-    /// Create new tracker with default storage path
-    pub fn new() -> Self {
-        Self::with_storage_path("/var/lib/cm-dashboard/user-stopped-services.json")
-    }
-
-    /// Initialize global instance (called by agent)
-    pub fn init_global() -> Result<Self> {
-        let tracker = Self::new();
-        
-        // Set global instance
-        let global_instance = Arc::new(Mutex::new(tracker));
-        if GLOBAL_TRACKER.set(global_instance).is_err() {
-            warn!("Global service tracker was already initialized");
-        }
-        
-        // Return a new instance for the agent to use
-        Ok(Self::new())
-    }
-
-    /// Check if a service is user-stopped (global access for collectors)
-    pub fn is_service_user_stopped(service_name: &str) -> bool {
-        if let Some(global) = GLOBAL_TRACKER.get() {
-            if let Ok(tracker) = global.lock() {
-                tracker.is_user_stopped(service_name)
-            } else {
-                debug!("Failed to lock global service tracker");
-                false
-            }
-        } else {
-            debug!("Global service tracker not initialized");
-            false
-        }
-    }
-
-    /// Update global tracker (called by agent when tracker state changes)
-    pub fn update_global(updated_tracker: &UserStoppedServiceTracker) {
-        if let Some(global) = GLOBAL_TRACKER.get() {
-            if let Ok(mut tracker) = global.lock() {
-                tracker.user_stopped_services = updated_tracker.user_stopped_services.clone();
-            } else {
-                debug!("Failed to lock global service tracker for update");
-            }
-        } else {
-            debug!("Global service tracker not initialized for update");
-        }
-    }
-
-    /// Create new tracker with custom storage path
-    pub fn with_storage_path<P: AsRef<Path>>(storage_path: P) -> Self {
-        let storage_path = storage_path.as_ref().to_string_lossy().to_string();
-        let mut tracker = Self {
-            user_stopped_services: HashSet::new(),
-            storage_path,
-        };
-
-        // Load existing data from storage
-        if let Err(e) = tracker.load_from_storage() {
-            warn!("Failed to load user-stopped services from storage: {}", e);
-            info!("Starting with empty user-stopped services list");
-        }
-
-        tracker
-    }
-
-
-    /// Clear user-stopped flag for a service (when user starts it)
-    pub fn clear_user_stopped(&mut self, service_name: &str) -> Result<()> {
-        if self.user_stopped_services.remove(service_name) {
-            info!("Cleared user-stopped flag for service '{}'", service_name);
-            self.save_to_storage()?;
-            debug!("Service '{}' user-stopped flag cleared and saved to storage", service_name);
-        } else {
-            debug!("Service '{}' was not marked as user-stopped", service_name);
-        }
-        Ok(())
-    }
-
-    /// Check if a service is marked as user-stopped
-    pub fn is_user_stopped(&self, service_name: &str) -> bool {
-        let is_stopped = self.user_stopped_services.contains(service_name);
-        debug!("Service '{}' user-stopped status: {}", service_name, is_stopped);
-        is_stopped
-    }
-
-
-    /// Save current state to persistent storage
-    fn save_to_storage(&self) -> Result<()> {
-        // Create parent directory if it doesn't exist
-        if let Some(parent_dir) = Path::new(&self.storage_path).parent() {
-            if !parent_dir.exists() {
-                fs::create_dir_all(parent_dir)?;
-                debug!("Created parent directory: {}", parent_dir.display());
-            }
-        }
-
-        let data = UserStoppedData {
-            services: self.user_stopped_services.iter().cloned().collect(),
-        };
-
-        let json_data = serde_json::to_string_pretty(&data)?;
-        fs::write(&self.storage_path, json_data)?;
-
-        debug!(
-            "Saved {} user-stopped services to {}",
-            data.services.len(),
-            self.storage_path
-        );
-        Ok(())
-    }
-
-    /// Load state from persistent storage
-    fn load_from_storage(&mut self) -> Result<()> {
-        if !Path::new(&self.storage_path).exists() {
-            debug!("Storage file {} does not exist, starting fresh", self.storage_path);
-            return Ok(());
-        }
-
-        let json_data = fs::read_to_string(&self.storage_path)?;
-        let data: UserStoppedData = serde_json::from_str(&json_data)?;
-
-        self.user_stopped_services = data.services.into_iter().collect();
-
-        info!(
-            "Loaded {} user-stopped services from {}",
-            self.user_stopped_services.len(),
-            self.storage_path
-        );
-
-        if !self.user_stopped_services.is_empty() {
-            debug!("User-stopped services: {:?}", self.user_stopped_services);
-        }
-
-        Ok(())
-    }
-}
-

dashboard/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "cm-dashboard"
-version = "0.1.138"
+version = "0.1.211"
 edition = "2021"
 
 [dependencies]

dashboard/src/app.rs

@@ -20,13 +20,12 @@ pub struct Dashboard {
     tui_app: Option<TuiApp>,
     terminal: Option<Terminal<CrosstermBackend<io::Stdout>>>,
     headless: bool,
-    raw_data: bool,
     initial_commands_sent: std::collections::HashSet<String>,
     config: DashboardConfig,
 }
 
 impl Dashboard {
-    pub async fn new(config_path: Option<String>, headless: bool, raw_data: bool) -> Result<Self> {
+    pub async fn new(config_path: Option<String>, headless: bool) -> Result<Self> {
         info!("Initializing dashboard");
 
         // Load configuration - try default path if not specified
@@ -120,7 +119,6 @@ impl Dashboard {
             tui_app,
             terminal,
             headless,
-            raw_data,
             initial_commands_sent: std::collections::HashSet::new(),
             config,
         })
@@ -205,13 +203,6 @@ impl Dashboard {
                             .insert(agent_data.hostname.clone());
                     }
 
-                    // Show raw data if requested (before processing)
-                    if self.raw_data {
-                        println!("RAW AGENT DATA FROM {}:", agent_data.hostname);
-                        println!("{}", serde_json::to_string_pretty(&agent_data).unwrap_or_else(|e| format!("Serialization error: {}", e)));
-                        println!("{}", "─".repeat(80));
-                    }
-
                     // Store structured data directly
                     self.metric_store.store_agent_data(agent_data);
 
@@ -224,7 +215,7 @@ impl Dashboard {
 
                     // Update TUI with new metrics (only if not headless)
                     if let Some(ref mut tui_app) = self.tui_app {
-                        tui_app.update_metrics(&self.metric_store);
+                        tui_app.update_metrics(&mut self.metric_store);
                     }
                 }
                 

dashboard/src/main.rs

@@ -51,10 +51,6 @@ struct Cli {
     /// Run in headless mode (no TUI, just logging)
     #[arg(long)]
     headless: bool,
-
-    /// Show raw agent data in headless mode
-    #[arg(long)]
-    raw_data: bool,
 }
 
 #[tokio::main]
@@ -90,7 +86,7 @@ async fn main() -> Result<()> {
     }
 
     // Create and run dashboard
-    let mut dashboard = Dashboard::new(cli.config, cli.headless, cli.raw_data).await?;
+    let mut dashboard = Dashboard::new(cli.config, cli.headless).await?;
 
     // Setup graceful shutdown
     let ctrl_c = async {

dashboard/src/metrics/store.rs

@@ -5,6 +5,14 @@ use tracing::{debug, info, warn};
 
 use super::MetricDataPoint;
 
+/// ZMQ communication statistics per host
+#[derive(Debug, Clone)]
+pub struct ZmqStats {
+    pub packets_received: u64,
+    pub last_packet_time: Instant,
+    pub last_packet_age_secs: f64,
+}
+
 /// Central metric storage for the dashboard
 pub struct MetricStore {
     /// Current structured data: hostname -> AgentData
@@ -13,6 +21,8 @@ pub struct MetricStore {
     historical_metrics: HashMap<String, Vec<MetricDataPoint>>,
     /// Last heartbeat timestamp per host
     last_heartbeat: HashMap<String, Instant>,
+    /// ZMQ communication statistics per host
+    zmq_stats: HashMap<String, ZmqStats>,
     /// Configuration
     max_metrics_per_host: usize,
     history_retention: Duration,
@@ -24,6 +34,7 @@ impl MetricStore {
             current_agent_data: HashMap::new(),
             historical_metrics: HashMap::new(),
             last_heartbeat: HashMap::new(),
+            zmq_stats: HashMap::new(),
             max_metrics_per_host,
             history_retention: Duration::from_secs(history_retention_hours * 3600),
         }
@@ -44,6 +55,16 @@ impl MetricStore {
         self.last_heartbeat.insert(hostname.clone(), now);
         debug!("Updated heartbeat for host {}", hostname);
 
+        // Update ZMQ stats
+        let stats = self.zmq_stats.entry(hostname.clone()).or_insert(ZmqStats {
+            packets_received: 0,
+            last_packet_time: now,
+            last_packet_age_secs: 0.0,
+        });
+        stats.packets_received += 1;
+        stats.last_packet_time = now;
+        stats.last_packet_age_secs = 0.0; // Just received
+
         // Add to history
         let host_history = self
             .historical_metrics
@@ -65,6 +86,15 @@ impl MetricStore {
         self.current_agent_data.get(hostname)
     }
 
+    /// Get ZMQ communication statistics for a host
+    pub fn get_zmq_stats(&mut self, hostname: &str) -> Option<ZmqStats> {
+        let now = Instant::now();
+        self.zmq_stats.get_mut(hostname).map(|stats| {
+            // Update packet age
+            stats.last_packet_age_secs = now.duration_since(stats.last_packet_time).as_secs_f64();
+            stats.clone()
+        })
+    }
 
     /// Get connected hosts (hosts with recent heartbeats)
     pub fn get_connected_hosts(&self, timeout: Duration) -> Vec<String> {

dashboard/src/ui/mod.rs

@@ -18,7 +18,7 @@ use crate::config::DashboardConfig;
 use crate::metrics::MetricStore;
 use cm_dashboard_shared::Status;
 use theme::{Components, Layout as ThemeLayout, Theme, Typography};
-use widgets::{BackupWidget, ServicesWidget, SystemWidget, Widget};
+use widgets::{ServicesWidget, SystemWidget, Widget};
 
 
 
@@ -32,8 +32,6 @@ pub struct HostWidgets {
     pub system_widget: SystemWidget,
     /// Services widget state
     pub services_widget: ServicesWidget,
-    /// Backup widget state
-    pub backup_widget: BackupWidget,
     /// Last update time for this host
     pub last_update: Option<Instant>,
 }
@@ -43,7 +41,6 @@ impl HostWidgets {
         Self {
             system_widget: SystemWidget::new(),
             services_widget: ServicesWidget::new(),
-            backup_widget: BackupWidget::new(),
             last_update: None,
         }
     }
@@ -103,7 +100,7 @@ impl TuiApp {
     }
 
     /// Update widgets with structured data from store (only for current host)
-    pub fn update_metrics(&mut self, metric_store: &MetricStore) {
+    pub fn update_metrics(&mut self, metric_store: &mut MetricStore) {
         if let Some(hostname) = self.current_host.clone() {
             // Get structured data for this host
             if let Some(agent_data) = metric_store.get_agent_data(&hostname) {
@@ -112,7 +109,14 @@ impl TuiApp {
                 // Update all widgets with structured data directly
                 host_widgets.system_widget.update_from_agent_data(agent_data);
                 host_widgets.services_widget.update_from_agent_data(agent_data);
-                host_widgets.backup_widget.update_from_agent_data(agent_data);
+
+                // Update ZMQ stats
+                if let Some(zmq_stats) = metric_store.get_zmq_stats(&hostname) {
+                    host_widgets.system_widget.update_zmq_stats(
+                        zmq_stats.packets_received,
+                        zmq_stats.last_packet_age_secs
+                    );
+                }
 
                 host_widgets.last_update = Some(Instant::now());
             }
@@ -469,40 +473,17 @@ impl TuiApp {
             return;
         }
 
-        // Check if backup panel should be shown
-        let show_backup = if let Some(hostname) = self.current_host.clone() {
-            let host_widgets = self.get_or_create_host_widgets(&hostname);
-            host_widgets.backup_widget.has_data()
-        } else {
-            false
-        };
-
-        // Left side: dynamic layout based on backup data availability
-        let left_chunks = if show_backup {
-            // Show both system and backup panels
-            ratatui::layout::Layout::default()
-                .direction(Direction::Vertical)
-                .constraints([
-                    Constraint::Percentage(ThemeLayout::SYSTEM_PANEL_HEIGHT), // System section
-                    Constraint::Percentage(ThemeLayout::BACKUP_PANEL_HEIGHT), // Backup section
-                ])
-                .split(content_chunks[0])
-        } else {
-            // Show only system panel (full height)
-            ratatui::layout::Layout::default()
+        // Left side: system panel only (full height)
+        let left_chunks = ratatui::layout::Layout::default()
             .direction(Direction::Vertical)
             .constraints([Constraint::Percentage(100)]) // System section takes full height
-                .split(content_chunks[0])
-        };
+            .split(content_chunks[0]);
 
         // Render title bar
         self.render_btop_title(frame, main_chunks[0], metric_store);
 
-        // Render new panel layout
+        // Render system panel
         self.render_system_panel(frame, left_chunks[0], metric_store);
-        if show_backup && left_chunks.len() > 1 {
-            self.render_backup_panel(frame, left_chunks[1]);
-        }
 
         // Render services widget for current host
         if let Some(hostname) = self.current_host.clone() {
@@ -669,17 +650,6 @@ impl TuiApp {
         }
     }
 
-    fn render_backup_panel(&mut self, frame: &mut Frame, area: Rect) {
-        let backup_block = Components::widget_block("backup");
-        let inner_area = backup_block.inner(area);
-        frame.render_widget(backup_block, area);
-
-        // Get current host widgets for backup widget
-        if let Some(hostname) = self.current_host.clone() {
-            let host_widgets = self.get_or_create_host_widgets(&hostname);
-            host_widgets.backup_widget.render(frame, inner_area);
-        }
-    }
 
     /// Render offline host message with wake-up option
     fn render_offline_host_message(&self, frame: &mut Frame, area: Rect) {

dashboard/src/ui/theme.rs

@@ -225,9 +225,6 @@ impl Layout {
     pub const LEFT_PANEL_WIDTH: u16 = 45;
     /// Right panel percentage (services)
     pub const RIGHT_PANEL_WIDTH: u16 = 55;
-    /// System vs backup split (equal)
-    pub const SYSTEM_PANEL_HEIGHT: u16 = 50;
-    pub const BACKUP_PANEL_HEIGHT: u16 = 50;
 }
 
 /// Typography system

dashboard/src/ui/widgets/backup.rs

@@ -1,418 +0,0 @@
-use cm_dashboard_shared::{Metric, Status};
-use super::Widget;
-use ratatui::{
-    layout::Rect,
-    widgets::Paragraph,
-    Frame,
-};
-use tracing::debug;
-
-use crate::ui::theme::{StatusIcons, Typography};
-
-/// Backup widget displaying backup status, services, and repository information
-#[derive(Clone)]
-pub struct BackupWidget {
-    /// Overall backup status
-    overall_status: Status,
-    /// Last backup duration in seconds
-    duration_seconds: Option<i64>,
-    /// Last backup timestamp
-    last_run_timestamp: Option<i64>,
-    /// Total repository size in GB
-    total_repo_size_gb: Option<f32>,
-    /// Total disk space for backups in GB
-    backup_disk_total_gb: Option<f32>,
-    /// Used disk space for backups in GB
-    backup_disk_used_gb: Option<f32>,
-    /// Backup disk product name from SMART data
-    backup_disk_product_name: Option<String>,
-    /// Backup disk serial number from SMART data
-    backup_disk_serial_number: Option<String>,
-    /// Backup disk wear percentage from SMART data
-    backup_disk_wear_percent: Option<f32>,
-    /// All individual service metrics for detailed display
-    service_metrics: Vec<ServiceMetricData>,
-    /// Last update indicator
-    has_data: bool,
-}
-
-#[derive(Debug, Clone)]
-struct ServiceMetricData {
-    name: String,
-    status: Status,
-    archive_count: Option<i64>,
-    repo_size_gb: Option<f32>,
-}
-
-impl BackupWidget {
-    pub fn new() -> Self {
-        Self {
-            overall_status: Status::Unknown,
-            duration_seconds: None,
-            last_run_timestamp: None,
-            total_repo_size_gb: None,
-            backup_disk_total_gb: None,
-            backup_disk_used_gb: None,
-            backup_disk_product_name: None,
-            backup_disk_serial_number: None,
-            backup_disk_wear_percent: None,
-            service_metrics: Vec::new(),
-            has_data: false,
-        }
-    }
-
-    /// Check if the backup widget has any data to display
-    pub fn has_data(&self) -> bool {
-        self.has_data
-    }
-
-
-
-
-
-    /// Format size with proper units (xxxkB/MB/GB/TB)
-    fn format_size_with_proper_units(size_gb: f32) -> String {
-        if size_gb >= 1000.0 {
-            // TB range
-            format!("{:.1}TB", size_gb / 1000.0)
-        } else if size_gb >= 1.0 {
-            // GB range
-            format!("{:.1}GB", size_gb)
-        } else if size_gb >= 0.001 {
-            // MB range (size_gb * 1024 = MB)
-            let size_mb = size_gb * 1024.0;
-            format!("{:.1}MB", size_mb)
-        } else if size_gb >= 0.000001 {
-            // kB range (size_gb * 1024 * 1024 = kB)
-            let size_kb = size_gb * 1024.0 * 1024.0;
-            format!("{:.0}kB", size_kb)
-        } else {
-            // B range (size_gb * 1024^3 = bytes)
-            let size_bytes = size_gb * 1024.0 * 1024.0 * 1024.0;
-            format!("{:.0}B", size_bytes)
-        }
-    }
-
-
-
-    /// Extract service name from metric name (e.g., "backup_service_gitea_status" -> "gitea")
-    #[allow(dead_code)]
-    fn extract_service_name(metric_name: &str) -> Option<String> {
-        if metric_name.starts_with("backup_service_") {
-            let name_part = &metric_name[15..]; // Remove "backup_service_" prefix
-
-            // Try to extract service name by removing known suffixes
-            if let Some(service_name) = name_part.strip_suffix("_status") {
-                Some(service_name.to_string())
-            } else if let Some(service_name) = name_part.strip_suffix("_archive_count") {
-                Some(service_name.to_string())
-            } else if let Some(service_name) = name_part.strip_suffix("_repo_size_gb") {
-                Some(service_name.to_string())
-            } else if let Some(service_name) = name_part.strip_suffix("_repo_path") {
-                Some(service_name.to_string())
-            } else {
-                None
-            }
-        } else {
-            None
-        }
-    }
-}
-
-impl Widget for BackupWidget {
-    fn update_from_agent_data(&mut self, agent_data: &cm_dashboard_shared::AgentData) {
-        self.has_data = true;
-        
-        let backup = &agent_data.backup;
-        self.overall_status = Status::Ok;
-        
-        if let Some(size) = backup.total_size_gb {
-            self.total_repo_size_gb = Some(size);
-        }
-        
-        if let Some(last_run) = backup.last_run {
-            self.last_run_timestamp = Some(last_run as i64);
-        }
-    }
-}
-
-impl BackupWidget {
-    #[allow(dead_code)]
-    fn update_from_metrics(&mut self, metrics: &[&Metric]) {
-        debug!("Backup widget updating with {} metrics", metrics.len());
-        for metric in metrics {
-            debug!(
-                "Backup metric: {} = {:?} (status: {:?})",
-                metric.name, metric.value, metric.status
-            );
-        }
-
-        // Also debug the service_data after processing
-        debug!("Processing individual service metrics...");
-
-        // Log how many metrics are backup service metrics
-        let service_metric_count = metrics
-            .iter()
-            .filter(|m| m.name.starts_with("backup_service_"))
-            .count();
-        debug!(
-            "Found {} backup_service_ metrics out of {} total backup metrics",
-            service_metric_count,
-            metrics.len()
-        );
-
-        // Reset service metrics
-        self.service_metrics.clear();
-        let mut service_data: std::collections::HashMap<String, ServiceMetricData> =
-            std::collections::HashMap::new();
-
-        for metric in metrics {
-            match metric.name.as_str() {
-                "backup_overall_status" => {
-                    let status_str = metric.value.as_string();
-                    self.overall_status = match status_str.as_str() {
-                        "ok" => Status::Ok,
-                        "warning" => Status::Warning,
-                        "critical" => Status::Critical,
-                        _ => Status::Unknown,
-                    };
-                }
-                "backup_duration_seconds" => {
-                    self.duration_seconds = metric.value.as_i64();
-                }
-                "backup_last_run_timestamp" => {
-                    self.last_run_timestamp = metric.value.as_i64();
-                }
-                "backup_total_repo_size_gb" => {
-                    self.total_repo_size_gb = metric.value.as_f32();
-                }
-                "backup_disk_total_gb" => {
-                    self.backup_disk_total_gb = metric.value.as_f32();
-                }
-                "backup_disk_used_gb" => {
-                    self.backup_disk_used_gb = metric.value.as_f32();
-                }
-                "backup_disk_product_name" => {
-                    self.backup_disk_product_name = Some(metric.value.as_string());
-                }
-                "backup_disk_serial_number" => {
-                    self.backup_disk_serial_number = Some(metric.value.as_string());
-                }
-                "backup_disk_wear_percent" => {
-                    self.backup_disk_wear_percent = metric.value.as_f32();
-                }
-                _ => {
-                    // Handle individual service metrics
-                    if let Some(service_name) = Self::extract_service_name(&metric.name) {
-                        debug!(
-                            "Extracted service name '{}' from metric '{}'",
-                            service_name, metric.name
-                        );
-                        let entry = service_data.entry(service_name.clone()).or_insert_with(|| {
-                            ServiceMetricData {
-                                name: service_name,
-                                status: Status::Unknown,
-                                    archive_count: None,
-                                repo_size_gb: None,
-                            }
-                        });
-
-                        if metric.name.ends_with("_status") {
-                            entry.status = metric.status;
-                            debug!("Set status for {}: {:?}", entry.name, entry.status);
-                        } else if metric.name.ends_with("_archive_count") {
-                            entry.archive_count = metric.value.as_i64();
-                            debug!(
-                                "Set archive_count for {}: {:?}",
-                                entry.name, entry.archive_count
-                            );
-                        } else if metric.name.ends_with("_repo_size_gb") {
-                            entry.repo_size_gb = metric.value.as_f32();
-                            debug!(
-                                "Set repo_size_gb for {}: {:?}",
-                                entry.name, entry.repo_size_gb
-                            );
-                        }
-                    } else {
-                        debug!(
-                            "Could not extract service name from metric: {}",
-                            metric.name
-                        );
-                    }
-                }
-            }
-        }
-
-        // Convert service data to sorted vector
-        let mut services: Vec<ServiceMetricData> = service_data.into_values().collect();
-        services.sort_by(|a, b| a.name.cmp(&b.name));
-        self.service_metrics = services;
-
-        // Only show backup panel if we have meaningful backup data
-        self.has_data = !metrics.is_empty() && (
-            self.last_run_timestamp.is_some() ||
-            self.total_repo_size_gb.is_some() ||
-            !self.service_metrics.is_empty()
-        );
-
-        debug!(
-            "Backup widget updated: status={:?}, services={}, total_size={:?}GB",
-            self.overall_status,
-            self.service_metrics.len(),
-            self.total_repo_size_gb
-        );
-
-        // Debug individual service data
-        for service in &self.service_metrics {
-            debug!(
-                "Service {}: status={:?}, archives={:?}, size={:?}GB",
-                service.name, service.status, service.archive_count, service.repo_size_gb
-            );
-        }
-    }
-
-}
-
-impl BackupWidget {
-    /// Render backup widget
-    pub fn render(&mut self, frame: &mut Frame, area: Rect) {
-        let mut lines = Vec::new();
-
-        // Latest backup section
-        lines.push(ratatui::text::Line::from(vec![
-            ratatui::text::Span::styled("Latest backup:", Typography::widget_title())
-        ]));
-        
-        // Timestamp with status icon
-        let timestamp_text = if let Some(timestamp) = self.last_run_timestamp {
-            self.format_timestamp(timestamp)
-        } else {
-            "Unknown".to_string()
-        };
-        let timestamp_spans = StatusIcons::create_status_spans(
-            self.overall_status,
-            &timestamp_text
-        );
-        lines.push(ratatui::text::Line::from(timestamp_spans));
-
-        // Duration as sub-item
-        if let Some(duration) = self.duration_seconds {
-            let duration_text = self.format_duration(duration);
-            lines.push(ratatui::text::Line::from(vec![
-                ratatui::text::Span::styled("  └─ ", Typography::tree()),
-                ratatui::text::Span::styled(format!("Duration: {}", duration_text), Typography::secondary())
-            ]));
-        }
-
-        // Disk section
-        lines.push(ratatui::text::Line::from(vec![
-            ratatui::text::Span::styled("Disk:", Typography::widget_title())
-        ]));
-
-        // Disk product name with status
-        if let Some(product) = &self.backup_disk_product_name {
-            let disk_spans = StatusIcons::create_status_spans(
-                Status::Ok, // Assuming disk is OK if we have data
-                product
-            );
-            lines.push(ratatui::text::Line::from(disk_spans));
-
-            // Collect sub-items to determine tree structure
-            let mut sub_items = Vec::new();
-            
-            if let Some(serial) = &self.backup_disk_serial_number {
-                sub_items.push(format!("S/N: {}", serial));
-            }
-            
-            if let Some(wear) = self.backup_disk_wear_percent {
-                sub_items.push(format!("Wear: {:.0}%", wear));
-            }
-            
-            if let (Some(used), Some(total)) = (self.backup_disk_used_gb, self.backup_disk_total_gb) {
-                let used_str = Self::format_size_with_proper_units(used);
-                let total_str = Self::format_size_with_proper_units(total);
-                sub_items.push(format!("Usage: {}/{}", used_str, total_str));
-            }
-            
-            // Render sub-items with proper tree structure
-            let num_items = sub_items.len();
-            for (i, item) in sub_items.into_iter().enumerate() {
-                let is_last = i == num_items - 1;
-                let tree_char = if is_last { "  └─ " } else { "  ├─ " };
-                lines.push(ratatui::text::Line::from(vec![
-                    ratatui::text::Span::styled(tree_char, Typography::tree()),
-                    ratatui::text::Span::styled(item, Typography::secondary())
-                ]));
-            }
-        }
-
-        // Repos section
-        lines.push(ratatui::text::Line::from(vec![
-            ratatui::text::Span::styled("Repos:", Typography::widget_title())
-        ]));
-
-        // Add all repository lines (no truncation here - scroll will handle display)
-        for service in &self.service_metrics {
-            if let (Some(archives), Some(size_gb)) = (service.archive_count, service.repo_size_gb) {
-                let size_str = Self::format_size_with_proper_units(size_gb);
-                let repo_text = format!("{} ({}) {}", service.name, archives, size_str);
-                let repo_spans = StatusIcons::create_status_spans(service.status, &repo_text);
-                lines.push(ratatui::text::Line::from(repo_spans));
-            }
-        }
-
-        // Apply scroll offset
-        let total_lines = lines.len();
-        let available_height = area.height as usize;
-        
-        // Show only what fits, with "X more below" if needed
-        if total_lines > available_height {
-            let lines_for_content = available_height.saturating_sub(1); // Reserve one line for "more below"
-            let mut visible_lines: Vec<_> = lines
-                .into_iter()
-                .take(lines_for_content)
-                .collect();
-            
-            let hidden_below = total_lines.saturating_sub(lines_for_content);
-            if hidden_below > 0 {
-                let more_line = ratatui::text::Line::from(vec![
-                    ratatui::text::Span::styled(format!("... {} more below", hidden_below), Typography::muted())
-                ]);
-                visible_lines.push(more_line);
-            }
-            
-            let paragraph = Paragraph::new(ratatui::text::Text::from(visible_lines));
-            frame.render_widget(paragraph, area);
-        } else {
-            let paragraph = Paragraph::new(ratatui::text::Text::from(lines));
-            frame.render_widget(paragraph, area);
-        }
-    }
-}
-
-impl BackupWidget {
-    /// Format timestamp for display
-    fn format_timestamp(&self, timestamp: i64) -> String {
-        let datetime = chrono::DateTime::from_timestamp(timestamp, 0)
-            .unwrap_or_else(|| chrono::Utc::now());
-        datetime.format("%Y-%m-%d %H:%M:%S").to_string()
-    }
-
-    /// Format duration in seconds to human readable format
-    fn format_duration(&self, duration_seconds: i64) -> String {
-        let minutes = duration_seconds / 60;
-        let seconds = duration_seconds % 60;
-        
-        if minutes > 0 {
-            format!("{}.{}m", minutes, seconds / 6) // Show 1 decimal for minutes
-        } else {
-            format!("{}s", seconds)
-        }
-    }
-}
-
-impl Default for BackupWidget {
-    fn default() -> Self {
-        Self::new()
-    }
-}

dashboard/src/ui/widgets/cpu.rs

@@ -1 +0,0 @@
-// This file is intentionally left minimal - CPU functionality is handled by the SystemWidget

dashboard/src/ui/widgets/memory.rs

@@ -1 +0,0 @@
-// This file is intentionally left minimal - Memory functionality is handled by the SystemWidget

dashboard/src/ui/widgets/mod.rs

@@ -1,12 +1,8 @@
 use cm_dashboard_shared::AgentData;
 
-pub mod backup;
-pub mod cpu;
-pub mod memory;
 pub mod services;
 pub mod system;
 
-pub use backup::BackupWidget;
 pub use services::ServicesWidget;
 pub use system::SystemWidget;
 

dashboard/src/ui/widgets/services.rs

@@ -28,11 +28,12 @@ pub struct ServicesWidget {
 
 #[derive(Clone)]
 struct ServiceInfo {
-    status: String,
-    memory_mb: Option<f32>,
-    disk_gb: Option<f32>,
-    latency_ms: Option<f32>,
+    metrics: Vec<(String, f32, Option<String>)>, // (label, value, unit)
     widget_status: Status,
+    service_type: String, // "nginx_site", "container", "image", or empty for parent services
+    memory_bytes: Option<u64>,
+    restart_count: Option<u32>,
+    uptime_seconds: Option<u64>,
 }
 
 impl ServicesWidget {
@@ -52,8 +53,6 @@ impl ServicesWidget {
         if metric_name.starts_with("service_") {
             if let Some(end_pos) = metric_name
                 .rfind("_status")
-                .or_else(|| metric_name.rfind("_memory_mb"))
-                .or_else(|| metric_name.rfind("_disk_gb"))
                 .or_else(|| metric_name.rfind("_latency_ms"))
             {
                 let service_part = &metric_name[8..end_pos]; // Remove "service_" prefix
@@ -76,36 +75,8 @@ impl ServicesWidget {
         None
     }
 
-    /// Format disk size with appropriate units (kB/MB/GB)
-    fn format_disk_size(size_gb: f32) -> String {
-        let size_mb = size_gb * 1024.0; // Convert GB to MB
-
-        if size_mb >= 1024.0 {
-            // Show as GB
-            format!("{:.1}GB", size_gb)
-        } else if size_mb >= 1.0 {
-            // Show as MB
-            format!("{:.0}MB", size_mb)
-        } else if size_mb >= 0.001 {
-            // Convert to kB
-            let size_kb = size_mb * 1024.0;
-            format!("{:.0}kB", size_kb)
-        } else {
-            // Show very small sizes as bytes
-            let size_bytes = size_mb * 1024.0 * 1024.0;
-            format!("{:.0}B", size_bytes)
-        }
-    }
-
     /// Format parent service line - returns text without icon for span formatting
     fn format_parent_service_line(&self, name: &str, info: &ServiceInfo) -> String {
-        let memory_str = info
-            .memory_mb
-            .map_or("0M".to_string(), |m| format!("{:.0}M", m));
-        let disk_str = info
-            .disk_gb
-            .map_or("0".to_string(), |d| Self::format_disk_size(d));
-
         // Truncate long service names to fit layout (account for icon space)
         let short_name = if name.len() > 22 {
             format!("{}...", &name[..19])
@@ -113,15 +84,54 @@ impl ServicesWidget {
             name.to_string()
         };
 
-        // Parent services always show actual systemctl status
+        // Convert Status enum to display text
         let status_str = match info.widget_status {
-            Status::Pending => "pending".to_string(),
-            _ => info.status.clone(), // Use actual status from agent (active/inactive/failed)
+            Status::Ok => "active",
+            Status::Inactive => "inactive",
+            Status::Critical => "failed",
+            Status::Pending => "pending",
+            Status::Warning => "warning",
+            Status::Unknown => "unknown",
+            Status::Offline => "offline",
         };
 
+        // Format memory
+        let memory_str = info.memory_bytes.map_or("-".to_string(), |bytes| {
+            let mb = bytes as f64 / (1024.0 * 1024.0);
+            if mb >= 1000.0 {
+                format!("{:.1}G", mb / 1024.0)
+            } else {
+                format!("{:.0}M", mb)
+            }
+        });
+
+        // Format uptime
+        let uptime_str = info.uptime_seconds.map_or("-".to_string(), |secs| {
+            let days = secs / 86400;
+            let hours = (secs % 86400) / 3600;
+            let mins = (secs % 3600) / 60;
+
+            if days > 0 {
+                format!("{}d{}h", days, hours)
+            } else if hours > 0 {
+                format!("{}h{}m", hours, mins)
+            } else {
+                format!("{}m", mins)
+            }
+        });
+
+        // Format restarts (show "!" if > 0 to indicate instability)
+        let restart_str = info.restart_count.map_or("-".to_string(), |count| {
+            if count > 0 {
+                format!("!{}", count)
+            } else {
+                "0".to_string()
+            }
+        });
+
         format!(
-            "{:<23} {:<10} {:<8} {:<8}",
-            short_name, status_str, memory_str, disk_str
+            "{:<23} {:<10} {:<8} {:<8} {:<5}",
+            short_name, status_str, memory_str, uptime_str, restart_str
         )
     }
 
@@ -153,18 +163,57 @@ impl ServicesWidget {
             Status::Offline => Theme::muted_text(),
         };
 
-        // For sub-services, prefer latency if available
-        let status_str = if let Some(latency) = info.latency_ms {
-            if latency < 0.0 {
-                "timeout".to_string()
-            } else {
-                format!("{:.0}ms", latency)
+        // Display metrics or status for sub-services
+        let status_str = if !info.metrics.is_empty() {
+            // Show first metric with label and unit
+            let (label, value, unit) = &info.metrics[0];
+            match unit {
+                Some(u) => format!("{}: {:.1} {}", label, value, u),
+                None => format!("{}: {:.1}", label, value),
             }
         } else {
-            info.status.clone()
+            // Convert Status enum to display text for sub-services
+            match info.widget_status {
+                Status::Ok => "active",
+                Status::Inactive => "inactive",
+                Status::Critical => "failed",
+                Status::Pending => "pending",
+                Status::Warning => "warning",
+                Status::Unknown => "unknown",
+                Status::Offline => "offline",
+            }.to_string()
         };
         let tree_symbol = if is_last { "└─" } else { "├─" };
 
+        // Docker images use docker whale icon
+        if info.service_type == "image" {
+            vec![
+                // Indentation and tree prefix
+                ratatui::text::Span::styled(
+                    format!("  {} ", tree_symbol),
+                    Typography::tree(),
+                ),
+                // Docker icon (simple character for performance)
+                ratatui::text::Span::styled(
+                    "D ".to_string(),
+                    Style::default().fg(Theme::highlight()).bg(Theme::background()),
+                ),
+                // Service name
+                ratatui::text::Span::styled(
+                    format!("{:<18} ", short_name),
+                    Style::default()
+                        .fg(Theme::secondary_text())
+                        .bg(Theme::background()),
+                ),
+                // Status/metrics text
+                ratatui::text::Span::styled(
+                    status_str,
+                    Style::default()
+                        .fg(Theme::secondary_text())
+                        .bg(Theme::background()),
+                ),
+            ]
+        } else {
             vec![
                 // Indentation and tree prefix
                 ratatui::text::Span::styled(
@@ -192,6 +241,7 @@ impl ServicesWidget {
                 ),
             ]
         }
+    }
 
     /// Move selection up
     pub fn select_previous(&mut self) {
@@ -262,18 +312,52 @@ impl Widget for ServicesWidget {
         self.sub_services.clear();
         
         for service in &agent_data.services {
-            let service_info = ServiceInfo {
-                status: service.status.clone(),
-                memory_mb: Some(service.memory_mb),
-                disk_gb: Some(service.disk_gb),
-                latency_ms: None,
-                widget_status: Status::Ok,
+            // Store parent service
+            let parent_info = ServiceInfo {
+                metrics: Vec::new(), // Parent services don't have custom metrics
+                widget_status: service.service_status,
+                service_type: String::new(), // Parent services have no type
+                memory_bytes: service.memory_bytes,
+                restart_count: service.restart_count,
+                uptime_seconds: service.uptime_seconds,
             };
+            self.parent_services.insert(service.name.clone(), parent_info);
 
-            self.parent_services.insert(service.name.clone(), service_info);
+            // Process sub-services if any
+            if !service.sub_services.is_empty() {
+                let mut sub_list = Vec::new();
+                for sub_service in &service.sub_services {
+                    // Convert metrics to display format
+                    let metrics: Vec<(String, f32, Option<String>)> = sub_service.metrics.iter()
+                        .map(|m| (m.label.clone(), m.value, m.unit.clone()))
+                        .collect();
+
+                    let sub_info = ServiceInfo {
+                        metrics,
+                        widget_status: sub_service.service_status,
+                        service_type: sub_service.service_type.clone(),
+                        memory_bytes: None, // Sub-services don't have individual metrics yet
+                        restart_count: None,
+                        uptime_seconds: None,
+                    };
+                    sub_list.push((sub_service.name.clone(), sub_info));
+                }
+                self.sub_services.insert(service.name.clone(), sub_list);
+            }
         }
         
-        self.status = Status::Ok;
+        // Aggregate status from all services
+        let mut all_statuses = Vec::new();
+        all_statuses.extend(self.parent_services.values().map(|info| info.widget_status));
+        for sub_list in self.sub_services.values() {
+            all_statuses.extend(sub_list.iter().map(|(_, info)| info.widget_status));
+        }
+        
+        self.status = if all_statuses.is_empty() {
+            Status::Unknown
+        } else {
+            Status::aggregate(&all_statuses)
+        };
     }
 }
 
@@ -294,24 +378,16 @@ impl ServicesWidget {
                             self.parent_services
                                 .entry(parent_service)
                                 .or_insert(ServiceInfo {
-                                    status: "unknown".to_string(),
-                                    memory_mb: None,
-                                    disk_gb: None,
-                                    latency_ms: None,
+                                    metrics: Vec::new(),
                                     widget_status: Status::Unknown,
+                                    service_type: String::new(),
+                                    memory_bytes: None,
+                                    restart_count: None,
+                                    uptime_seconds: None,
                                 });
 
                         if metric.name.ends_with("_status") {
-                            service_info.status = metric.value.as_string();
                             service_info.widget_status = metric.status;
-                        } else if metric.name.ends_with("_memory_mb") {
-                            if let Some(memory) = metric.value.as_f32() {
-                                service_info.memory_mb = Some(memory);
-                            }
-                        } else if metric.name.ends_with("_disk_gb") {
-                            if let Some(disk) = metric.value.as_f32() {
-                                service_info.disk_gb = Some(disk);
-                            }
                         }
                     }
                     Some(sub_name) => {
@@ -331,32 +407,19 @@ impl ServicesWidget {
                             sub_service_list.push((
                                 sub_name.clone(),
                                 ServiceInfo {
-                                    status: "unknown".to_string(),
-                                    memory_mb: None,
-                                    disk_gb: None,
-                                    latency_ms: None,
+                                    metrics: Vec::new(),
                                     widget_status: Status::Unknown,
+                                    service_type: String::new(), // Unknown type in legacy path
+                                    memory_bytes: None,
+                                    restart_count: None,
+                                    uptime_seconds: None,
                                 },
                             ));
                             &mut sub_service_list.last_mut().unwrap().1
                         };
 
                         if metric.name.ends_with("_status") {
-                            sub_service_info.status = metric.value.as_string();
                             sub_service_info.widget_status = metric.status;
-                        } else if metric.name.ends_with("_memory_mb") {
-                            if let Some(memory) = metric.value.as_f32() {
-                                sub_service_info.memory_mb = Some(memory);
-                            }
-                        } else if metric.name.ends_with("_disk_gb") {
-                            if let Some(disk) = metric.value.as_f32() {
-                                sub_service_info.disk_gb = Some(disk);
-                            }
-                        } else if metric.name.ends_with("_latency_ms") {
-                            if let Some(latency) = metric.value.as_f32() {
-                                sub_service_info.latency_ms = Some(latency);
-                                sub_service_info.widget_status = metric.status;
-                            }
                         }
                     }
                 }
@@ -415,8 +478,8 @@ impl ServicesWidget {
 
         // Header
         let header = format!(
-            "{:<25} {:<10} {:<8} {:<8}",
-            "Service:", "Status:", "RAM:", "Disk:"
+            "{:<25} {:<10} {:<8} {:<8} {:<5}",
+            "Service:", "Status:", "RAM:", "Uptime:", "↻:"
         );
         let header_para = Paragraph::new(header).style(Typography::muted());
         frame.render_widget(header_para, content_chunks[0]);

dashboard/src/ui/widgets/system.rs

@@ -8,18 +8,25 @@ use ratatui::{
 
 use crate::ui::theme::{StatusIcons, Typography};
 
-/// System widget displaying NixOS info, CPU, RAM, and Storage in unified layout
+/// System widget displaying NixOS info, Network, CPU, RAM, and Storage in unified layout
 #[derive(Clone)]
 pub struct SystemWidget {
     // NixOS information
     nixos_build: Option<String>,
     agent_hash: Option<String>,
 
+    // ZMQ communication stats
+    zmq_packets_received: Option<u64>,
+    zmq_last_packet_age: Option<f64>,
+
+    // Network interfaces
+    network_interfaces: Vec<cm_dashboard_shared::NetworkInterfaceData>,
+
     // CPU metrics
     cpu_load_1min: Option<f32>,
     cpu_load_5min: Option<f32>,
     cpu_load_15min: Option<f32>,
-    cpu_frequency: Option<f32>,
+    cpu_cstates: Vec<cm_dashboard_shared::CStateInfo>,
     cpu_status: Status,
     
     // Memory metrics
@@ -37,6 +44,17 @@ pub struct SystemWidget {
     // Storage metrics (collected from disk metrics)
     storage_pools: Vec<StoragePool>,
     
+    // Backup metrics
+    backup_status: String,
+    backup_start_time_raw: Option<String>,
+    backup_disk_serial: Option<String>,
+    backup_disk_usage_percent: Option<f32>,
+    backup_disk_used_gb: Option<f32>,
+    backup_disk_total_gb: Option<f32>,
+    backup_disk_wear_percent: Option<f32>,
+    backup_disk_temperature: Option<f32>,
+    backup_last_size_gb: Option<f32>,
+    
     // Overall status
     has_data: bool,
 }
@@ -46,7 +64,9 @@ struct StoragePool {
     name: String,
     mount_point: String,
     pool_type: String, // "single", "mergerfs (2+1)", "RAID5 (3+1)", etc.
-    drives: Vec<StorageDrive>,
+    drives: Vec<StorageDrive>, // For physical drives
+    data_drives: Vec<StorageDrive>, // For MergerFS pools
+    parity_drives: Vec<StorageDrive>, // For MergerFS pools
     filesystems: Vec<FileSystem>, // For physical drive pools: individual filesystem children
     usage_percent: Option<f32>,
     used_gb: Option<f32>,
@@ -76,10 +96,13 @@ impl SystemWidget {
         Self {
             nixos_build: None,
             agent_hash: None,
+            zmq_packets_received: None,
+            zmq_last_packet_age: None,
+            network_interfaces: Vec::new(),
             cpu_load_1min: None,
             cpu_load_5min: None,
             cpu_load_15min: None,
-            cpu_frequency: None,
+            cpu_cstates: Vec::new(),
             cpu_status: Status::Unknown,
             memory_usage_percent: None,
             memory_used_gb: None,
@@ -91,6 +114,15 @@ impl SystemWidget {
             tmp_status: Status::Unknown,
             tmpfs_mounts: Vec::new(),
             storage_pools: Vec::new(),
+            backup_status: "unknown".to_string(),
+            backup_start_time_raw: None,
+            backup_disk_serial: None,
+            backup_disk_usage_percent: None,
+            backup_disk_used_gb: None,
+            backup_disk_total_gb: None,
+            backup_disk_wear_percent: None,
+            backup_disk_temperature: None,
+            backup_last_size_gb: None,
             has_data: false,
         }
     }
@@ -105,12 +137,22 @@ impl SystemWidget {
         }
     }
 
-    /// Format CPU frequency
-    fn format_cpu_frequency(&self) -> String {
-        match self.cpu_frequency {
-            Some(freq) => format!("{:.0} MHz", freq),
-            None => "— MHz".to_string(),
+    /// Format CPU C-states (idle depth) with percentages
+    fn format_cpu_cstate(&self) -> String {
+        if self.cpu_cstates.is_empty() {
+            return "—".to_string();
         }
+
+        // Format top 3 C-states with percentages: "C10:79% C8:10% C6:8%"
+        // Strip suffixes like "_ACPI" from state names
+        self.cpu_cstates
+            .iter()
+            .map(|cs| {
+                let clean_name = cs.name.split('_').next().unwrap_or(&cs.name);
+                format!("{}:{:.0}%", clean_name, cs.percent)
+            })
+            .collect::<Vec<_>>()
+            .join(" ")
     }
 
     /// Format memory usage
@@ -128,6 +170,12 @@ impl SystemWidget {
     pub fn _get_agent_hash(&self) -> Option<&String> {
         self.agent_hash.as_ref()
     }
+
+    /// Update ZMQ communication statistics
+    pub fn update_zmq_stats(&mut self, packets_received: u64, last_packet_age_secs: f64) {
+        self.zmq_packets_received = Some(packets_received);
+        self.zmq_last_packet_age = Some(last_packet_age_secs);
+    }
 }
 
 use super::Widget;
@@ -139,12 +187,18 @@ impl Widget for SystemWidget {
         // Extract agent version
         self.agent_hash = Some(agent_data.agent_version.clone());
         
+        // Extract build version
+        self.nixos_build = agent_data.build_version.clone();
+
+        // Extract network interfaces
+        self.network_interfaces = agent_data.system.network.interfaces.clone();
+
         // Extract CPU data directly
         let cpu = &agent_data.system.cpu;
         self.cpu_load_1min = Some(cpu.load_1min);
         self.cpu_load_5min = Some(cpu.load_5min);
         self.cpu_load_15min = Some(cpu.load_15min);
-        self.cpu_frequency = Some(cpu.frequency_mhz);
+        self.cpu_cstates = cpu.cstates.clone();
         self.cpu_status = Status::Ok;
 
         // Extract memory data directly
@@ -167,6 +221,28 @@ impl Widget for SystemWidget {
 
         // Convert storage data to internal format
         self.update_storage_from_agent_data(agent_data);
+
+        // Extract backup data
+        let backup = &agent_data.backup;
+        self.backup_status = backup.status.clone();
+        self.backup_start_time_raw = backup.start_time_raw.clone();
+        self.backup_last_size_gb = backup.last_backup_size_gb;
+
+        if let Some(disk) = &backup.repository_disk {
+            self.backup_disk_serial = Some(disk.serial.clone());
+            self.backup_disk_usage_percent = Some(disk.usage_percent);
+            self.backup_disk_used_gb = Some(disk.used_gb);
+            self.backup_disk_total_gb = Some(disk.total_gb);
+            self.backup_disk_wear_percent = disk.wear_percent;
+            self.backup_disk_temperature = disk.temperature_celsius;
+        } else {
+            self.backup_disk_serial = None;
+            self.backup_disk_usage_percent = None;
+            self.backup_disk_used_gb = None;
+            self.backup_disk_total_gb = None;
+            self.backup_disk_wear_percent = None;
+            self.backup_disk_temperature = None;
+        }
     }
 }
 
@@ -182,6 +258,8 @@ impl SystemWidget {
                 mount_point: drive.name.clone(),
                 pool_type: "drive".to_string(),
                 drives: Vec::new(),
+                data_drives: Vec::new(),
+                parity_drives: Vec::new(),
                 filesystems: Vec::new(),
                 usage_percent: None,
                 used_gb: None,
@@ -190,8 +268,11 @@ impl SystemWidget {
             };
 
             // Add drive info
+            let display_name = drive.serial_number.as_ref()
+                .map(|s| truncate_serial(s))
+                .unwrap_or(drive.name.clone());
             let storage_drive = StorageDrive {
-                name: drive.name.clone(),
+                name: display_name,
                 temperature: drive.temperature_celsius,
                 wear_percent: drive.wear_percent,
                 status: Status::Ok,
@@ -222,7 +303,85 @@ impl SystemWidget {
             pools.insert(drive.name.clone(), pool);
         }
 
-        // Convert pools
+        // Convert pools (MergerFS, RAID, etc.)
+        for pool in &agent_data.system.storage.pools {
+            // Use agent-calculated status (combined health and usage status)
+            let pool_status = if pool.health_status == Status::Critical || pool.usage_status == Status::Critical {
+                Status::Critical
+            } else if pool.health_status == Status::Warning || pool.usage_status == Status::Warning {
+                Status::Warning
+            } else if pool.health_status == Status::Ok && pool.usage_status == Status::Ok {
+                Status::Ok
+            } else {
+                Status::Unknown
+            };
+            
+            let mut storage_pool = StoragePool {
+                name: pool.name.clone(),
+                mount_point: pool.mount.clone(),
+                pool_type: pool.pool_type.clone(),
+                drives: Vec::new(),
+                data_drives: Vec::new(),
+                parity_drives: Vec::new(),
+                filesystems: Vec::new(),
+                usage_percent: Some(pool.usage_percent),
+                used_gb: Some(pool.used_gb),
+                total_gb: Some(pool.total_gb),
+                status: pool_status,
+            };
+
+            // Add data drives - use agent-calculated status
+            for drive in &pool.data_drives {
+                // Use combined health and temperature status
+                let drive_status = if drive.health_status == Status::Critical || drive.temperature_status == Status::Critical {
+                    Status::Critical
+                } else if drive.health_status == Status::Warning || drive.temperature_status == Status::Warning {
+                    Status::Warning
+                } else if drive.health_status == Status::Ok && drive.temperature_status == Status::Ok {
+                    Status::Ok
+                } else {
+                    Status::Unknown
+                };
+
+                let display_name = drive.serial_number.as_ref()
+                    .map(|s| truncate_serial(s))
+                    .unwrap_or(drive.name.clone());
+                let storage_drive = StorageDrive {
+                    name: display_name,
+                    temperature: drive.temperature_celsius,
+                    wear_percent: drive.wear_percent,
+                    status: drive_status,
+                };
+                storage_pool.data_drives.push(storage_drive);
+            }
+
+            // Add parity drives - use agent-calculated status
+            for drive in &pool.parity_drives {
+                // Use combined health and temperature status
+                let drive_status = if drive.health_status == Status::Critical || drive.temperature_status == Status::Critical {
+                    Status::Critical
+                } else if drive.health_status == Status::Warning || drive.temperature_status == Status::Warning {
+                    Status::Warning
+                } else if drive.health_status == Status::Ok && drive.temperature_status == Status::Ok {
+                    Status::Ok
+                } else {
+                    Status::Unknown
+                };
+
+                let display_name = drive.serial_number.as_ref()
+                    .map(|s| truncate_serial(s))
+                    .unwrap_or(drive.name.clone());
+                let storage_drive = StorageDrive {
+                    name: display_name,
+                    temperature: drive.temperature_celsius,
+                    wear_percent: drive.wear_percent,
+                    status: drive_status,
+                };
+                storage_pool.parity_drives.push(storage_drive);
+            }
+
+            pools.insert(pool.name.clone(), storage_pool);
+        }
 
         // Store pools
         let mut pool_list: Vec<StoragePool> = pools.into_values().collect();
@@ -236,14 +395,10 @@ impl SystemWidget {
 
         for pool in &self.storage_pools {
             // Pool header line with type and health
-            let pool_label = if pool.pool_type.starts_with("drive (") {
+            let pool_label = if pool.pool_type == "drive" {
                 // For physical drives, show the drive name with temperature and wear percentage if available
-                // Look for any drive with temp/wear data (physical drives may have drives named after the pool)
-                let drive_info = pool.drives.iter()
-                    .find(|d| d.name == pool.name)
-                    .or_else(|| pool.drives.first());
-
-                if let Some(drive) = drive_info {
+                // Physical drives only have one drive entry
+                if let Some(drive) = pool.drives.first() {
                     let mut drive_details = Vec::new();
                     if let Some(temp) = drive.temperature {
                         drive_details.push(format!("T: {}°C", temp as i32));
@@ -253,23 +408,23 @@ impl SystemWidget {
                     }
 
                     if !drive_details.is_empty() {
-                        format!("{} {}", pool.name, drive_details.join(" "))
+                        format!("{} {}", drive.name, drive_details.join(" "))
                     } else {
-                        pool.name.clone()
+                        drive.name.clone()
                     }
                 } else {
                     pool.name.clone()
                 }
             } else {
-                // For mergerfs pools, show pool name with format
-                format!("{} ({})", pool.mount_point, pool.pool_type)
+                // For mergerfs pools, show pool type with mount point
+                format!("mergerfs {}:", pool.mount_point)
             };
 
             let pool_spans = StatusIcons::create_status_spans(pool.status.clone(), &pool_label);
             lines.push(Line::from(pool_spans));
 
             // Show individual filesystems for physical drives (matching CLAUDE.md format)
-            if pool.pool_type.starts_with("drive") {
+            if pool.pool_type == "drive" {
                 // Show filesystem entries like: ├─ ● /: 55% 250.5GB/456.4GB
                 for (i, filesystem) in pool.filesystems.iter().enumerate() {
                     let is_last = i == pool.filesystems.len() - 1;
@@ -291,41 +446,31 @@ impl SystemWidget {
                     lines.push(Line::from(fs_spans));
                 }
             } else {
-                // For mergerfs pools, show data drives and parity drives in tree structure
-                if !pool.drives.is_empty() {
-                    // Group drives by type based on naming conventions or show all as data drives
-                    let (data_drives, parity_drives): (Vec<_>, Vec<_>) = pool.drives.iter()
-                        .partition(|d| !d.name.contains("parity") && !d.name.starts_with("sdc"));
+                // For mergerfs pools, show structure matching CLAUDE.md format:
+                // ● mergerfs (2+1):
+                //   ├─ Total: ● 63% 2355.2GB/3686.4GB
+                //   ├─ Data Disks:
+                //   │  ├─ ● sdb T: 24°C W: 5%
+                //   │  └─ ● sdd T: 27°C W: 5%
+                //   ├─ Parity: ● sdc T: 24°C W: 5%
+                //   └─ Mount: /srv/media
                 
-                    if !data_drives.is_empty() {
-                        lines.push(Line::from(vec![
-                            Span::styled("  ├─ Data Disks:", Typography::secondary())
-                        ]));
-                        for (i, drive) in data_drives.iter().enumerate() {
-                            render_pool_drive(drive, i == data_drives.len() - 1 && parity_drives.is_empty(), &mut lines);
-                        }
-                    }
-
-                    if !parity_drives.is_empty() {
-                        lines.push(Line::from(vec![
-                            Span::styled("  └─ Parity:", Typography::secondary())
-                        ]));
-                        for (i, drive) in parity_drives.iter().enumerate() {
-                            render_pool_drive(drive, i == parity_drives.len() - 1, &mut lines);
-                        }
-                    }
-                }
-            }
-        }
-
-        lines
-    }
-}
-
-/// Helper function to render a drive in a storage pool
-fn render_pool_drive(drive: &StorageDrive, is_last: bool, lines: &mut Vec<Line<'_>>) {
-    let tree_symbol = if is_last { "    └─" } else { "    ├─" };
+                // Pool total usage
+                let total_text = format!("{:.0}% {:.1}GB/{:.1}GB",
+                    pool.usage_percent.unwrap_or(0.0),
+                    pool.used_gb.unwrap_or(0.0),
+                    pool.total_gb.unwrap_or(0.0)
+                );
+                let mut total_spans = vec![
+                    Span::styled("  ├─ ", Typography::tree()),
+                ];
+                total_spans.extend(StatusIcons::create_status_spans(Status::Ok, &total_text));
+                lines.push(Line::from(total_spans));
 
+                // Data drives - at same level as parity
+                let has_parity = !pool.parity_drives.is_empty();
+                for (i, drive) in pool.data_drives.iter().enumerate() {
+                    let is_last_data = i == pool.data_drives.len() - 1;
                     let mut drive_details = Vec::new();
                     if let Some(temp) = drive.temperature {
                         drive_details.push(format!("T: {}°C", temp as i32));
@@ -335,22 +480,327 @@ fn render_pool_drive(drive: &StorageDrive, is_last: bool, lines: &mut Vec<Line<'
                     }
 
                     let drive_text = if !drive_details.is_empty() {
-        format!("● {} {}", drive.name, drive_details.join(" "))
+                        format!("Data_{}: {} {}", i + 1, drive.name, drive_details.join(" "))
                     } else {
-        format!("● {}", drive.name)
+                        format!("Data_{}: {}", i + 1, drive.name)
                     };
 
-    let mut drive_spans = vec![
+                    // Last data drive uses └─ if there's no parity, otherwise ├─
+                    let tree_symbol = if is_last_data && !has_parity { "  └─ " } else { "  ├─ " };
+                    let mut data_spans = vec![
                         Span::styled(tree_symbol, Typography::tree()),
-        Span::raw(" "),
                     ];
-    drive_spans.extend(StatusIcons::create_status_spans(drive.status.clone(), &drive_text));
-    lines.push(Line::from(drive_spans));
+                    data_spans.extend(StatusIcons::create_status_spans(drive.status.clone(), &drive_text));
+                    lines.push(Line::from(data_spans));
+                }
+
+                // Parity drives - last item(s)
+                if !pool.parity_drives.is_empty() {
+                    for (i, drive) in pool.parity_drives.iter().enumerate() {
+                        let is_last = i == pool.parity_drives.len() - 1;
+                        let mut drive_details = Vec::new();
+                        if let Some(temp) = drive.temperature {
+                            drive_details.push(format!("T: {}°C", temp as i32));
+                        }
+                        if let Some(wear) = drive.wear_percent {
+                            drive_details.push(format!("W: {}%", wear as i32));
+                        }
+
+                        let drive_text = if !drive_details.is_empty() {
+                            format!("Parity: {} {}", drive.name, drive_details.join(" "))
+                        } else {
+                            format!("Parity: {}", drive.name)
+                        };
+
+                        let tree_symbol = if is_last { "  └─ " } else { "  ├─ " };
+                        let mut parity_spans = vec![
+                            Span::styled(tree_symbol, Typography::tree()),
+                        ];
+                        parity_spans.extend(StatusIcons::create_status_spans(drive.status.clone(), &drive_text));
+                        lines.push(Line::from(parity_spans));
+                    }
+                }
+            }
+        }
+
+        lines
+    }
+}
+
+/// Truncate serial number to last 8 characters
+fn truncate_serial(serial: &str) -> String {
+    let len = serial.len();
+    if len > 8 {
+        serial[len - 8..].to_string()
+    } else {
+        serial.to_string()
+    }
 }
 
 impl SystemWidget {
+    /// Render backup section for display
+    fn render_backup(&self) -> Vec<Line<'_>> {
+        let mut lines = Vec::new();
+
+        // First line: serial number with temperature and wear
+        if let Some(serial) = &self.backup_disk_serial {
+            let truncated_serial = truncate_serial(serial);
+            let mut details = Vec::new();
+            if let Some(temp) = self.backup_disk_temperature {
+                details.push(format!("T: {}°C", temp as i32));
+            }
+            if let Some(wear) = self.backup_disk_wear_percent {
+                details.push(format!("W: {}%", wear as i32));
+            }
+
+            let disk_text = if !details.is_empty() {
+                format!("{} {}", truncated_serial, details.join(" "))
+            } else {
+                truncated_serial
+            };
+
+            let backup_status = match self.backup_status.as_str() {
+                "completed" | "success" => Status::Ok,
+                "running" => Status::Pending,
+                "failed" => Status::Critical,
+                _ => Status::Unknown,
+            };
+
+            let disk_spans = StatusIcons::create_status_spans(backup_status, &disk_text);
+            lines.push(Line::from(disk_spans));
+
+            // Show backup time from TOML if available
+            if let Some(start_time) = &self.backup_start_time_raw {
+                let time_text = if let Some(size) = self.backup_last_size_gb {
+                    format!("Time: {} ({:.1}GB)", start_time, size)
+                } else {
+                    format!("Time: {}", start_time)
+                };
+                
+                lines.push(Line::from(vec![
+                    Span::styled("  ├─ ", Typography::tree()),
+                    Span::styled(time_text, Typography::secondary())
+                ]));
+            }
+
+            // Usage information
+            if let (Some(used), Some(total), Some(usage_percent)) = (
+                self.backup_disk_used_gb, 
+                self.backup_disk_total_gb,
+                self.backup_disk_usage_percent
+            ) {
+                let usage_text = format!("Usage: {:.0}% {:.0}GB/{:.0}GB", usage_percent, used, total);
+                let usage_spans = StatusIcons::create_status_spans(Status::Ok, &usage_text);
+                let mut full_spans = vec![
+                    Span::styled("  └─ ", Typography::tree()),
+                ];
+                full_spans.extend(usage_spans);
+                lines.push(Line::from(full_spans));
+            }
+        }
+
+        lines
+    }
+
+    /// Compress IPv4 addresses from same subnet
+    /// Example: "192.168.30.1, 192.168.30.100" -> "192.168.30.1, 100"
+    fn compress_ipv4_addresses(addresses: &[String]) -> String {
+        if addresses.is_empty() {
+            return String::new();
+        }
+
+        if addresses.len() == 1 {
+            return addresses[0].clone();
+        }
+
+        let mut result = Vec::new();
+        let mut last_prefix = String::new();
+
+        for addr in addresses {
+            let parts: Vec<&str> = addr.split('.').collect();
+            if parts.len() == 4 {
+                let prefix = format!("{}.{}.{}", parts[0], parts[1], parts[2]);
+
+                if prefix == last_prefix {
+                    // Same subnet, show only last octet
+                    result.push(parts[3].to_string());
+                } else {
+                    // Different subnet, show full IP
+                    result.push(addr.clone());
+                    last_prefix = prefix;
+                }
+            } else {
+                // Invalid IP format, show as-is
+                result.push(addr.clone());
+            }
+        }
+
+        result.join(", ")
+    }
+
+    /// Render network section for display with physical/virtual grouping
+    fn render_network(&self) -> Vec<Line<'_>> {
+        let mut lines = Vec::new();
+
+        if self.network_interfaces.is_empty() {
+            return lines;
+        }
+
+        // Separate physical and virtual interfaces
+        let physical: Vec<_> = self.network_interfaces.iter().filter(|i| i.is_physical).collect();
+        let virtual_interfaces: Vec<_> = self.network_interfaces.iter().filter(|i| !i.is_physical).collect();
+
+        // Find standalone virtual interfaces (those without a parent)
+        let mut standalone_virtual: Vec<_> = virtual_interfaces.iter()
+            .filter(|i| i.parent_interface.is_none())
+            .collect();
+
+        // Sort standalone virtual: VLANs first (by VLAN ID), then others alphabetically
+        standalone_virtual.sort_by(|a, b| {
+            match (a.vlan_id, b.vlan_id) {
+                (Some(vlan_a), Some(vlan_b)) => vlan_a.cmp(&vlan_b),
+                (Some(_), None) => std::cmp::Ordering::Less,
+                (None, Some(_)) => std::cmp::Ordering::Greater,
+                (None, None) => a.name.cmp(&b.name),
+            }
+        });
+
+        // Render physical interfaces with their children
+        for (phy_idx, interface) in physical.iter().enumerate() {
+            let is_last_physical = phy_idx == physical.len() - 1 && standalone_virtual.is_empty();
+
+            // Physical interface header with status icon
+            let mut header_spans = vec![];
+            header_spans.extend(StatusIcons::create_status_spans(
+                interface.link_status.clone(),
+                &format!("{}:", interface.name)
+            ));
+            lines.push(Line::from(header_spans));
+
+            // Find child interfaces for this physical interface
+            let mut children: Vec<_> = virtual_interfaces.iter()
+                .filter(|vi| {
+                    if let Some(parent) = &vi.parent_interface {
+                        parent == &interface.name
+                    } else {
+                        false
+                    }
+                })
+                .collect();
+
+            // Sort children: VLANs first (by VLAN ID), then others alphabetically
+            children.sort_by(|a, b| {
+                match (a.vlan_id, b.vlan_id) {
+                    (Some(vlan_a), Some(vlan_b)) => vlan_a.cmp(&vlan_b),
+                    (Some(_), None) => std::cmp::Ordering::Less,
+                    (None, Some(_)) => std::cmp::Ordering::Greater,
+                    (None, None) => a.name.cmp(&b.name),
+                }
+            });
+
+            // Count total items under this physical interface (IPs + children)
+            let ip_count = interface.ipv4_addresses.len() + interface.ipv6_addresses.len();
+            let total_children = ip_count + children.len();
+            let mut child_index = 0;
+
+            // IPv4 addresses on the physical interface itself
+            for ipv4 in &interface.ipv4_addresses {
+                child_index += 1;
+                let is_last = child_index == total_children && is_last_physical;
+                let tree_symbol = if is_last { "  └─ " } else { "  ├─ " };
+                lines.push(Line::from(vec![
+                    Span::styled(tree_symbol, Typography::tree()),
+                    Span::styled(format!("ip: {}", ipv4), Typography::secondary()),
+                ]));
+            }
+
+            // IPv6 addresses on the physical interface itself
+            for ipv6 in &interface.ipv6_addresses {
+                child_index += 1;
+                let is_last = child_index == total_children && is_last_physical;
+                let tree_symbol = if is_last { "  └─ " } else { "  ├─ " };
+                lines.push(Line::from(vec![
+                    Span::styled(tree_symbol, Typography::tree()),
+                    Span::styled(format!("ip: {}", ipv6), Typography::secondary()),
+                ]));
+            }
+
+            // Child virtual interfaces (VLANs, etc.)
+            for child in children {
+                child_index += 1;
+                let is_last = child_index == total_children && is_last_physical;
+                let tree_symbol = if is_last { "  └─ " } else { "  ├─ " };
+
+                let ip_text = if !child.ipv4_addresses.is_empty() {
+                    Self::compress_ipv4_addresses(&child.ipv4_addresses)
+                } else if !child.ipv6_addresses.is_empty() {
+                    child.ipv6_addresses.join(", ")
+                } else {
+                    String::new()
+                };
+
+                // Format: "name (vlan X): IP" or "name: IP"
+                let child_text = if let Some(vlan_id) = child.vlan_id {
+                    if !ip_text.is_empty() {
+                        format!("{} (vlan {}): {}", child.name, vlan_id, ip_text)
+                    } else {
+                        format!("{} (vlan {}):", child.name, vlan_id)
+                    }
+                } else {
+                    if !ip_text.is_empty() {
+                        format!("{}: {}", child.name, ip_text)
+                    } else {
+                        format!("{}:", child.name)
+                    }
+                };
+
+                lines.push(Line::from(vec![
+                    Span::styled(tree_symbol, Typography::tree()),
+                    Span::styled(child_text, Typography::secondary()),
+                ]));
+            }
+        }
+
+        // Render standalone virtual interfaces (those without a parent)
+        for (virt_idx, interface) in standalone_virtual.iter().enumerate() {
+            let is_last = virt_idx == standalone_virtual.len() - 1;
+            let tree_symbol = if is_last { "  └─ " } else { "  ├─ " };
+
+            // Virtual interface with IPs
+            let ip_text = if !interface.ipv4_addresses.is_empty() {
+                Self::compress_ipv4_addresses(&interface.ipv4_addresses)
+            } else if !interface.ipv6_addresses.is_empty() {
+                interface.ipv6_addresses.join(", ")
+            } else {
+                String::new()
+            };
+
+            // Format: "name (vlan X): IP" or "name: IP"
+            let interface_text = if let Some(vlan_id) = interface.vlan_id {
+                if !ip_text.is_empty() {
+                    format!("{} (vlan {}): {}", interface.name, vlan_id, ip_text)
+                } else {
+                    format!("{} (vlan {}):", interface.name, vlan_id)
+                }
+            } else {
+                if !ip_text.is_empty() {
+                    format!("{}: {}", interface.name, ip_text)
+                } else {
+                    format!("{}:", interface.name)
+                }
+            };
+
+            lines.push(Line::from(vec![
+                Span::styled(tree_symbol, Typography::tree()),
+                Span::styled(interface_text, Typography::secondary()),
+            ]));
+        }
+
+        lines
+    }
+
     /// Render system widget
-    pub fn render(&mut self, frame: &mut Frame, area: Rect, hostname: &str, config: Option<&crate::config::DashboardConfig>) {
+    pub fn render(&mut self, frame: &mut Frame, area: Rect, hostname: &str, _config: Option<&crate::config::DashboardConfig>) {
         let mut lines = Vec::new();
 
         // NixOS section
@@ -368,16 +818,17 @@ impl SystemWidget {
             Span::styled(format!("Agent: {}", agent_version_text), Typography::secondary())
         ]));
 
-        // Display detected connection IP
-        if let Some(config) = config {
-            if let Some(host_details) = config.hosts.get(hostname) {
-                let detected_ip = host_details.get_connection_ip(hostname);
+        // ZMQ communication stats
+        if let (Some(packets), Some(age)) = (self.zmq_packets_received, self.zmq_last_packet_age) {
+            let age_text = if age < 1.0 {
+                format!("{:.0}ms ago", age * 1000.0)
+            } else {
+                format!("{:.1}s ago", age)
+            };
             lines.push(Line::from(vec![
-                    Span::styled(format!("IP: {}", detected_ip), Typography::secondary())
+                Span::styled(format!("ZMQ: {} pkts, last {}", packets, age_text), Typography::secondary())
             ]));
         }
-        }
-        
 
         // CPU section
         lines.push(Line::from(vec![
@@ -391,10 +842,10 @@ impl SystemWidget {
         );
         lines.push(Line::from(cpu_spans));
 
-        let freq_text = self.format_cpu_frequency();
+        let cstate_text = self.format_cpu_cstate();
         lines.push(Line::from(vec![
             Span::styled("  └─ ", Typography::tree()),
-            Span::styled(format!("Freq: {}", freq_text), Typography::secondary())
+            Span::styled(format!("C-state: {}", cstate_text), Typography::secondary())
         ]));
 
         // RAM section
@@ -433,6 +884,16 @@ impl SystemWidget {
             lines.push(Line::from(tmpfs_spans));
         }
 
+        // Network section
+        if !self.network_interfaces.is_empty() {
+            lines.push(Line::from(vec![
+                Span::styled("Network:", Typography::widget_title())
+            ]));
+
+            let network_lines = self.render_network();
+            lines.extend(network_lines);
+        }
+
         // Storage section
         lines.push(Line::from(vec![
             Span::styled("Storage:", Typography::widget_title())
@@ -442,6 +903,16 @@ impl SystemWidget {
         let storage_lines = self.render_storage();
         lines.extend(storage_lines);
 
+        // Backup section (if available)
+        if self.backup_status != "unavailable" && self.backup_status != "unknown" {
+            lines.push(Line::from(vec![
+                Span::styled("Backup:", Typography::widget_title())
+            ]));
+
+            let backup_lines = self.render_backup();
+            lines.extend(backup_lines);
+        }
+
         // Apply scroll offset
         let total_lines = lines.len();
         let available_height = area.height as usize;

shared/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "cm-dashboard-shared"
-version = "0.1.138"
+version = "0.1.211"
 edition = "2021"
 
 [dependencies]

shared/src/agent_data.rs

@@ -1,10 +1,12 @@
 use serde::{Deserialize, Serialize};
+use crate::Status;
 
 /// Complete structured data from an agent
 #[derive(Debug, Clone, Serialize, Deserialize)]
 pub struct AgentData {
     pub hostname: String,
     pub agent_version: String,
+    pub build_version: Option<String>,
     pub timestamp: u64,
     pub system: SystemData,
     pub services: Vec<ServiceData>,
@@ -14,19 +16,47 @@ pub struct AgentData {
 /// System-level monitoring data
 #[derive(Debug, Clone, Serialize, Deserialize)]
 pub struct SystemData {
+    pub network: NetworkData,
     pub cpu: CpuData,
     pub memory: MemoryData,
     pub storage: StorageData,
 }
 
+/// Network interface monitoring data
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct NetworkData {
+    pub interfaces: Vec<NetworkInterfaceData>,
+}
+
+/// Individual network interface data
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct NetworkInterfaceData {
+    pub name: String,
+    pub ipv4_addresses: Vec<String>,
+    pub ipv6_addresses: Vec<String>,
+    pub is_physical: bool,
+    pub link_status: Status,
+    pub parent_interface: Option<String>,
+    pub vlan_id: Option<u16>,
+}
+
+/// CPU C-state usage information
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct CStateInfo {
+    pub name: String,
+    pub percent: f32,
+}
+
 /// CPU monitoring data
 #[derive(Debug, Clone, Serialize, Deserialize)]
 pub struct CpuData {
     pub load_1min: f32,
     pub load_5min: f32,
     pub load_15min: f32,
-    pub frequency_mhz: f32,
+    pub cstates: Vec<CStateInfo>, // C-state usage percentages (C1, C6, C10, etc.) - indicates CPU idle depth distribution
     pub temperature_celsius: Option<f32>,
+    pub load_status: Status,
+    pub temperature_status: Status,
 }
 
 /// Memory monitoring data
@@ -39,6 +69,7 @@ pub struct MemoryData {
     pub swap_total_gb: f32,
     pub swap_used_gb: f32,
     pub tmpfs: Vec<TmpfsData>,
+    pub usage_status: Status,
 }
 
 /// Tmpfs filesystem data
@@ -61,10 +92,13 @@ pub struct StorageData {
 #[derive(Debug, Clone, Serialize, Deserialize)]
 pub struct DriveData {
     pub name: String,
+    pub serial_number: Option<String>,
     pub health: String,
     pub temperature_celsius: Option<f32>,
     pub wear_percent: Option<f32>,
     pub filesystems: Vec<FilesystemData>,
+    pub temperature_status: Status,
+    pub health_status: Status,
 }
 
 /// Filesystem on a drive
@@ -74,6 +108,7 @@ pub struct FilesystemData {
     pub usage_percent: f32,
     pub used_gb: f32,
     pub total_gb: f32,
+    pub usage_status: Status,
 }
 
 /// Storage pool (MergerFS, RAID, etc.)
@@ -88,35 +123,76 @@ pub struct PoolData {
     pub total_gb: f32,
     pub data_drives: Vec<PoolDriveData>,
     pub parity_drives: Vec<PoolDriveData>,
+    pub health_status: Status,
+    pub usage_status: Status,
 }
 
 /// Drive in a storage pool
 #[derive(Debug, Clone, Serialize, Deserialize)]
 pub struct PoolDriveData {
     pub name: String,
+    pub serial_number: Option<String>,
     pub temperature_celsius: Option<f32>,
     pub wear_percent: Option<f32>,
     pub health: String,
+    pub health_status: Status,
+    pub temperature_status: Status,
 }
 
 /// Service monitoring data
 #[derive(Debug, Clone, Serialize, Deserialize)]
 pub struct ServiceData {
     pub name: String,
-    pub status: String, // "active", "inactive", "failed"
-    pub memory_mb: f32,
-    pub disk_gb: f32,
     pub user_stopped: bool,
+    pub service_status: Status,
+    pub sub_services: Vec<SubServiceData>,
+    /// Memory usage in bytes (from MemoryCurrent)
+    pub memory_bytes: Option<u64>,
+    /// Number of service restarts (from NRestarts)
+    pub restart_count: Option<u32>,
+    /// Uptime in seconds (calculated from ExecMainStartTimestamp)
+    pub uptime_seconds: Option<u64>,
+}
+
+/// Sub-service data (nginx sites, docker containers, etc.)
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct SubServiceData {
+    pub name: String,
+    pub service_status: Status,
+    pub metrics: Vec<SubServiceMetric>,
+    /// Type of sub-service: "nginx_site", "container", "image"
+    #[serde(default)]
+    pub service_type: String,
+}
+
+/// Individual metric for a sub-service
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct SubServiceMetric {
+    pub label: String,
+    pub value: f32,
+    pub unit: Option<String>,
 }
 
 /// Backup system data
 #[derive(Debug, Clone, Serialize, Deserialize)]
 pub struct BackupData {
     pub status: String,
-    pub last_run: Option<u64>,
-    pub next_scheduled: Option<u64>,
     pub total_size_gb: Option<f32>,
     pub repository_health: Option<String>,
+    pub repository_disk: Option<BackupDiskData>,
+    pub last_backup_size_gb: Option<f32>,
+    pub start_time_raw: Option<String>,
+}
+
+/// Backup repository disk information
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct BackupDiskData {
+    pub serial: String,
+    pub usage_percent: f32,
+    pub used_gb: f32,
+    pub total_gb: f32,
+    pub wear_percent: Option<f32>,
+    pub temperature_celsius: Option<f32>,
 }
 
 impl AgentData {
@@ -125,14 +201,20 @@ impl AgentData {
         Self {
             hostname,
             agent_version,
+            build_version: None,
             timestamp: chrono::Utc::now().timestamp() as u64,
             system: SystemData {
+                network: NetworkData {
+                    interfaces: Vec::new(),
+                },
                 cpu: CpuData {
                     load_1min: 0.0,
                     load_5min: 0.0,
                     load_15min: 0.0,
-                    frequency_mhz: 0.0,
+                    cstates: Vec::new(),
                     temperature_celsius: None,
+                    load_status: Status::Unknown,
+                    temperature_status: Status::Unknown,
                 },
                 memory: MemoryData {
                     usage_percent: 0.0,
@@ -142,6 +224,7 @@ impl AgentData {
                     swap_total_gb: 0.0,
                     swap_used_gb: 0.0,
                     tmpfs: Vec::new(),
+                    usage_status: Status::Unknown,
                 },
                 storage: StorageData {
                     drives: Vec::new(),
@@ -151,10 +234,11 @@ impl AgentData {
             services: Vec::new(),
             backup: BackupData {
                 status: "unknown".to_string(),
-                last_run: None,
-                next_scheduled: None,
                 total_size_gb: None,
                 repository_health: None,
+                repository_disk: None,
+                last_backup_size_gb: None,
+                start_time_raw: None,
             },
         }
     }

shared/src/metrics.rs

@@ -131,6 +131,17 @@ impl HysteresisThresholds {
         }
     }
 
+    /// Evaluate value against thresholds to determine status
+    pub fn evaluate(&self, value: f32) -> Status {
+        if value >= self.critical_high {
+            Status::Critical
+        } else if value >= self.warning_high {
+            Status::Warning
+        } else {
+            Status::Ok
+        }
+    }
+
     pub fn with_custom_gaps(warning_high: f32, warning_gap: f32, critical_high: f32, critical_gap: f32) -> Self {
         Self {
             warning_high,