Add VLAN ID display and smart parent assignment for virtual interfaces

Agent changes:
- Parse /proc/net/vlan/config to extract VLAN IDs for interfaces
- Detect primary physical interface via default route
- Auto-assign primary interface as parent for virtual interfaces without explicit parent
- Added vlan_id field to NetworkInterfaceData

Dashboard changes:
- Display VLAN ID in format "interface (vlan X): IP"
- Show VLAN IDs for both nested and standalone virtual interfaces

This ensures virtual interfaces (docker0, tailscale0, etc.) are properly nested
under the primary physical NIC, and VLAN interfaces show their IDs.

Updated to version 0.1.170

.gitea/workflows/release.yml

@@ -0,0 +1,128 @@
+name: Build and Release
+
+on:
+  push:
+    tags:
+      - 'v*'
+  workflow_dispatch:
+    inputs:
+      version:
+        description: 'Version to release (e.g., v0.1.0)'
+        required: true
+        default: 'v0.1.0'
+
+jobs:
+  build-and-release:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Rust
+        uses: actions-rs/toolchain@v1
+        with:
+          toolchain: stable
+          profile: minimal
+          override: true
+
+      - name: Install system dependencies
+        run: |
+          apt-get update
+          apt-get install -y pkg-config libssl-dev libzmq3-dev
+
+      - name: Build workspace (static)
+        run: |
+          export RUSTFLAGS="-C target-feature=+crt-static"
+          cargo build --release --workspace --target x86_64-unknown-linux-gnu
+
+      - name: Create release directory
+        run: |
+          mkdir -p release
+          cp target/x86_64-unknown-linux-gnu/release/cm-dashboard release/cm-dashboard-linux-x86_64
+          cp target/x86_64-unknown-linux-gnu/release/cm-dashboard-agent release/cm-dashboard-agent-linux-x86_64
+
+      - name: Create tarball
+        run: |
+          cd release
+          tar -czf cm-dashboard-linux-x86_64.tar.gz cm-dashboard-linux-x86_64 cm-dashboard-agent-linux-x86_64
+
+      - name: Set version variable
+        id: version
+        run: |
+          if [ "${{ gitea.event_name }}" == "workflow_dispatch" ]; then
+            echo "VERSION=${{ gitea.event.inputs.version }}" >> $GITHUB_OUTPUT
+          else
+            echo "VERSION=${GITHUB_REF#refs/tags/}" >> $GITHUB_OUTPUT
+          fi
+
+      - name: Create Release with curl
+        env:
+          GITEA_TOKEN: ${{ secrets.GITEATOKEN }}
+        run: |
+          VERSION="${{ steps.version.outputs.VERSION }}"
+          
+          # Create release
+          curl -X POST \
+            -H "Authorization: token $GITEA_TOKEN" \
+            -H "Content-Type: application/json" \
+            -d '{
+              "tag_name": "'$VERSION'",
+              "name": "cm-dashboard '$VERSION'",
+              "body": "## cm-dashboard '$VERSION'\n\nPre-built binaries for Linux x86_64:\n- cm-dashboard-linux-x86_64 - Dashboard TUI binary\n- cm-dashboard-agent-linux-x86_64 - Agent daemon binary\n- cm-dashboard-linux-x86_64.tar.gz - Combined tarball"
+            }' \
+            "https://gitea.cmtec.se/api/v1/repos/cm/cm-dashboard/releases"
+          
+          # Get release ID
+          RELEASE_ID=$(curl -s -H "Authorization: token $GITEA_TOKEN" \
+            "https://gitea.cmtec.se/api/v1/repos/cm/cm-dashboard/releases/tags/$VERSION" | \
+            grep -o '"id":[0-9]*' | head -1 | cut -d':' -f2)
+          
+          # Upload binaries
+          curl -X POST \
+            -H "Authorization: token $GITEA_TOKEN" \
+            -F "attachment=@release/cm-dashboard-linux-x86_64" \
+            "https://gitea.cmtec.se/api/v1/repos/cm/cm-dashboard/releases/$RELEASE_ID/assets?name=cm-dashboard-linux-x86_64"
+          
+          curl -X POST \
+            -H "Authorization: token $GITEA_TOKEN" \
+            -F "attachment=@release/cm-dashboard-agent-linux-x86_64" \
+            "https://gitea.cmtec.se/api/v1/repos/cm/cm-dashboard/releases/$RELEASE_ID/assets?name=cm-dashboard-agent-linux-x86_64"
+          
+          curl -X POST \
+            -H "Authorization: token $GITEA_TOKEN" \
+            -F "attachment=@release/cm-dashboard-linux-x86_64.tar.gz" \
+            "https://gitea.cmtec.se/api/v1/repos/cm/cm-dashboard/releases/$RELEASE_ID/assets?name=cm-dashboard-linux-x86_64.tar.gz"
+
+      - name: Update NixOS Configuration
+        env:
+          GITEA_TOKEN: ${{ secrets.GITEATOKEN }}
+        run: |
+          VERSION="${{ steps.version.outputs.VERSION }}"
+          
+          # Clone nixosbox repository
+          git clone https://$GITEA_TOKEN@gitea.cmtec.se/cm/nixosbox.git nixosbox-update
+          cd nixosbox-update
+          
+          # Get hash for the new release tarball
+          TARBALL_URL="https://gitea.cmtec.se/cm/cm-dashboard/releases/download/$VERSION/cm-dashboard-linux-x86_64.tar.gz"
+          
+          # Download tarball to get correct hash
+          curl -L -o cm-dashboard.tar.gz "$TARBALL_URL"
+          # Convert sha256 hex to base64 for Nix hash format using Python
+          NEW_HASH=$(sha256sum cm-dashboard.tar.gz | cut -d' ' -f1)
+          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 = \"$VERSION\"|" services/cm-dashboard.nix
+          sed -i "s|sha256 = \"sha256-[^\"]*\"|sha256 = \"$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 services/cm-dashboard.nix
+          git commit -m "Auto-update cm-dashboard to $VERSION
+
+          - Update version to $VERSION with automated release
+          - Update tarball hash for new static binaries
+          - Automated update from cm-dashboard release workflow"
+          git push

AGENTS.md

@@ -1,3 +0,0 @@
-# Agent Guide
-
-Agents working in this repo must follow the instructions in `CLAUDE.md`.

CLAUDE.md

@@ -2,178 +2,173 @@
 
 ## Overview
 
-A high-performance Rust-based TUI dashboard for monitoring CMTEC infrastructure. Built to replace Glance with a custom solution tailored for our specific monitoring needs and ZMQ-based metric collection.
+A high-performance Rust-based TUI dashboard for monitoring CMTEC infrastructure. Built with ZMQ-based metric collection and individual metrics architecture.
 
-## Implementation Strategy
+## Current Features
 
-### Current Implementation Status
+### Core Functionality
 
-**System Panel Enhancement - COMPLETED** ✅
+- **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
+- **NixOS Integration**: System rebuild via SSH + tmux popup
+- **Backup Monitoring**: Borgbackup status and scheduling
 
-All system panel features successfully implemented:
+### User-Stopped Service Tracking
-- ✅ **NixOS Collector**: Created collector for version and active users  
-- ✅ **System Widget**: Unified widget combining NixOS, CPU, RAM, and Storage
-- ✅ **Build Display**: Shows NixOS build information without codename
-- ✅ **Active Users**: Displays currently logged in users
-- ✅ **Tmpfs Monitoring**: Added /tmp usage to RAM section
-- ✅ **Agent Deployment**: NixOS collector working in production
 
-**Keyboard Navigation and Service Management - COMPLETED** ✅
+- Services stopped via dashboard are marked as "user-stopped"
+- User-stopped services report Status::OK instead of Warning
+- Prevents false alerts during intentional maintenance
+- Persistent storage survives agent restarts
+- Automatic flag clearing when services are restarted via dashboard
 
-All keyboard navigation and service selection features successfully implemented:
+### Custom Service Logs
-- ✅ **Panel Navigation**: Shift+Tab cycles through visible panels only (System → Services → Backup)
-- ✅ **Service Selection**: Up/Down arrows navigate through parent services with visual cursor
-- ✅ **Focus Management**: Selection highlighting only visible when Services panel focused
-- ✅ **Status Preservation**: Service health colors maintained during selection (green/red icons)
-- ✅ **Smart Panel Switching**: Only cycles through panels with data (backup panel conditional)
-- ✅ **Scroll Support**: All panels support content scrolling with proper overflow indicators
 
-**Current Status - October 24, 2025:**
+- Configure service-specific log file paths per host in dashboard config
-- All keyboard navigation features working correctly ✅
+- Press `L` on any service to view custom log files via `tail -f`
-- Service selection cursor implemented with focus-aware highlighting ✅
+- Configuration format in dashboard config:
-- Panel scrolling fixed for System, Services, and Backup panels ✅
-- Build display working: "Build: 25.05.20251004.3bcc93c" ✅
-- Configuration hash display implemented: "Config: d16f0d0" ✅
 
-**Layout Achieved:**
+```toml
-```
+[service_logs]
-NixOS:
+hostname1 = [
-Build: 25.05.20251004.3bcc93c
+  { service_name = "nginx", log_file_path = "/var/log/nginx/access.log" },
-Config: d16f0d0  # Shows actual nixosbox config hash
+  { service_name = "app", log_file_path = "/var/log/myapp/app.log" }
-Active users: cm, simon
+]
-CPU:
+hostname2 = [
-● Load: 0.02 0.31 0.86 • 3000MHz
+  { service_name = "database", log_file_path = "/var/log/postgres/postgres.log" }
-RAM:
+]
-● Usage: 33% 2.6GB/7.6GB  
-● /tmp: 0% 0B/2.0GB  
-Storage:  
-● root (Single):  
- ├─ ● nvme0n1 W: 1%
- └─ ● 18% 167.4GB/928.2GB
 ```
 
-**System panel layout fully implemented with blue tree symbols ✅**
+### Service Management
-**Tree symbols now use consistent blue theming across all panels ✅**
-**Overflow handling restored for all widgets ("... and X more") ✅**
-**Agent hash display working correctly ✅**
 
-### Current Keyboard Navigation Implementation
+- **Direct Control**: Arrow keys (↑↓) or vim keys (j/k) navigate services
+- **Service Actions**:
+  - `s` - Start service (sends UserStart command)
+  - `S` - Stop service (sends UserStop command)
+  - `J` - Show service logs (journalctl in tmux popup)
+  - `L` - Show custom log files (tail -f custom paths in tmux popup)
+  - `R` - Rebuild current host
+- **Visual Status**: Green ● (active), Yellow ◐ (inactive), Red ◯ (failed)
+- **Transitional Icons**: Blue arrows during operations
 
-**Navigation Controls:**
+### Navigation
-- **Tab**: Switch between hosts (cmbox, srv01, srv02, steambox, etc.)
+
-- **Shift+Tab**: Cycle through visible panels (System → Services → Backup → System)
+- **Tab**: Switch between hosts
-- **Up/Down (System/Backup)**: Scroll through panel content
+- **↑↓ or j/k**: Select services
-- **Up/Down (Services)**: Move service selection cursor between parent services
+- **s**: Start selected service (UserStart)
+- **S**: Stop selected service (UserStop)
+- **J**: Show service logs (journalctl)
+- **L**: Show custom log files
+- **R**: Rebuild current host
+- **B**: Run backup on current host
 - **q**: Quit dashboard
 
-**Panel-Specific Features:**
+## Core Architecture Principles
-- **System Panel**: Scrollable content with CPU, RAM, Storage details
-- **Services Panel**: Service selection cursor for parent services only (docker, nginx, postgresql, etc.)
-- **Backup Panel**: Scrollable repository list with proper overflow handling
 
-**Visual Feedback:**
+### Structured Data Architecture (✅ IMPLEMENTED v0.1.131)
-- **Focused Panel**: Blue border and title highlighting
-- **Service Selection**: Blue background with preserved status icon colors (green ● for active, red ● for failed)
-- **Focus-Aware Selection**: Selection highlighting only visible when Services panel focused
-- **Dynamic Statusbar**: Context-aware shortcuts based on focused panel
 
-### Remote Command Execution - WORKING ✅
+Complete migration from string-based metrics to structured JSON data. Eliminates all string parsing bugs and provides type-safe data access.
 
-**All Issues Resolved (as of 2025-10-24):**
+**Previous (String Metrics):**
-- ✅ **ZMQ Command Protocol**: Extended with ServiceControl and SystemRebuild variants
-- ✅ **Agent Handlers**: systemctl and nixos-rebuild execution with maintenance mode
-- ✅ **Dashboard Integration**: Keyboard shortcuts execute commands
-- ✅ **Service Control**: Fixed toggle logic - replaced with separate 's' (start) and 'S' (stop)
-- ✅ **System Rebuild**: Fixed permission issues and sandboxing problems
-- ✅ **Git Clone Approach**: Implemented for nixos-rebuild to avoid directory permissions
-- ✅ **Visual Feedback**: Directional arrows for service status (↑ starting, ↓ stopping, ↻ restarting)
 
-**Keyboard Controls Status:**
+- ❌ Agent sent individual metrics with string names like `disk_nvme0n1_temperature`
-- **Services Panel**: 
+- ❌ Dashboard parsed metric names with underscore counting and string splitting
-  - R (restart) ✅ Working
+- ❌ Complex and error-prone metric filtering and extraction logic
-  - s (start) ✅ Working  
-  - S (stop) ✅ Working
-- **System Panel**: R (nixos-rebuild) ✅ Working with --option sandbox false
-- **Backup Panel**: B (trigger backup) ❓ Not implemented
 
-**Visual Feedback Implementation - IN PROGRESS:**
+**Current (Structured Data):**
 
-Context-appropriate progress indicators for each panel:
+```json
-
+{
-**Services Panel** (Service status transitions):
+  "hostname": "cmbox",
-```
+  "agent_version": "v0.1.131",
-● nginx          active    →  ⏳ nginx      restarting  →  ● nginx          active
+  "timestamp": 1763926877,
-● docker         active    →  ⏳ docker     stopping    →  ● docker         inactive  
+  "system": {
+    "cpu": {
+      "load_1min": 3.5,
+      "load_5min": 3.57,
+      "load_15min": 3.58,
+      "frequency_mhz": 1500,
+      "temperature_celsius": 45.2
+    },
+    "memory": {
+      "usage_percent": 25.0,
+      "total_gb": 23.3,
+      "used_gb": 5.9,
+      "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
+        }
+      ]
+    },
+    "storage": {
+      "drives": [
+        {
+          "name": "nvme0n1",
+          "health": "PASSED",
+          "temperature_celsius": 29.0,
+          "wear_percent": 1.0,
+          "filesystems": [
+            {
+              "mount": "/",
+              "usage_percent": 24.0,
+              "used_gb": 224.9,
+              "total_gb": 928.2
+            }
+          ]
+        }
+      ],
+      "pools": [
+        {
+          "name": "srv_media",
+          "mount": "/srv/media",
+          "type": "mergerfs",
+          "health": "healthy",
+          "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 }]
+        }
+      ]
+    }
+  },
+  "services": [
+    { "name": "sshd", "status": "active", "memory_mb": 4.5, "disk_gb": 0.0 }
+  ],
+  "backup": {
+    "status": "completed",
+    "last_run": 1763920000,
+    "next_scheduled": 1764006400,
+    "total_size_gb": 150.5,
+    "repository_health": "ok"
+  }
+}
 ```
 
-**System Panel** (Build progress in NixOS section):
+- ✅ Agent sends structured JSON over ZMQ (no legacy support)
-```
+- ✅ Type-safe data access: `data.system.storage.drives[0].temperature_celsius`
-NixOS:
+- ✅ Complete metric coverage: CPU, memory, storage, services, backup
-Build: 25.05.20251004.3bcc93c    →    Build: [████████████     ] 65%
+- ✅ Backward compatibility via bridge conversion to existing UI widgets
-Active users: cm, simon               Active users: cm, simon
+- ✅ All string parsing bugs eliminated
-```
-
-**Backup Panel** (OnGoing status with progress):
-```
-Latest backup:              →    Latest backup:
-● 2024-10-23 14:32:15            ● OnGoing  
-└─ Duration: 1.3m                 └─ [██████       ] 60%
-```
-
-**Next Session Priority Tasks:**
-
-**Remaining Features:**
-1. **Command Response Protocol**:
-   - Agent sends command completion/failure back to dashboard via ZMQ
-   - Dashboard updates UI status from ⏳ to ● when commands complete
-   - Clear success/failure status after timeout
-
-2. **Backup Panel Features**:
-   - Implement backup trigger functionality (B key)
-   - Complete visual feedback for backup operations
-   - Add backup progress indicators
-
-**Enhancement Tasks:**
-- Add confirmation dialogs for destructive actions (stop/restart/rebuild)
-- Implement command history/logging
-- Add keyboard shortcuts help overlay
-
-**Future Enhanced Navigation:**
-- Add Page Up/Down for faster scrolling through long service lists
-- Implement search/filter functionality for services
-- Add jump-to-service shortcuts (first letter navigation)
-
-**Future Advanced Features:**
-- Service dependency visualization
-- Historical service status tracking
-- Real-time log viewing integration
-
-## Core Architecture Principles - CRITICAL
-
-### Individual Metrics Philosophy
-
-**NEW ARCHITECTURE**: Agent collects individual metrics, dashboard composes widgets from those metrics.
 
 ### Maintenance Mode
 
-**Purpose:**
-
-- Suppress email notifications during planned maintenance or backups
-- Prevents false alerts when services are intentionally stopped
-
-**Implementation:**
-
 - 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:**
+Usage:
 
 ```bash
 # Enable maintenance mode
 touch /tmp/cm-maintenance
 
-# Run maintenance tasks (backups, service restarts, etc.)
+# Run maintenance tasks
 systemctl stop service
 # ... maintenance work ...
 systemctl start service
@@ -182,43 +177,165 @@ systemctl start service
 rm /tmp/cm-maintenance
 ```
 
-**NixOS Integration:**
+## Development and Deployment Architecture
 
-- Borgbackup script automatically creates/removes maintenance file
+### Development Path
-- Automatic cleanup via trap ensures maintenance mode doesn't stick
-- All cinfiguration are shall be done from nixos config
 
-**ARCHITECTURE ENFORCEMENT**:
+- **Location:** `~/projects/cm-dashboard`
+- **Purpose:** Development workflow only - for committing new code
+- **Access:** Only for developers to commit changes
 
-- **ZERO legacy code reuse** - Fresh implementation following ARCHITECT.md exactly
+### Deployment Path
-- **Individual metrics only** - NO grouped metric structures
-- **Reference-only legacy** - Study old functionality, implement new architecture
-- **Clean slate mindset** - Build as if legacy codebase never existed
 
-**Implementation Rules**:
+- **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
 
-1. **Individual Metrics**: Each metric is collected, transmitted, and stored individually
+### Git Flow
-2. **Agent Status Authority**: Agent calculates status for each metric using thresholds
-3. **Dashboard Composition**: Dashboard widgets subscribe to specific metrics by name
-4. **Status Aggregation**: Dashboard aggregates individual metric statuses for widget status
-   **Testing & Building**:
 
-- **Workspace builds**: `cargo build --workspace` for all testing
+```
-- **Clean compilation**: Remove `target/` between architecture changes
+Development: ~/projects/cm-dashboard → git commit → git push
-- **ZMQ testing**: Test agent-dashboard communication independently
+Deployment:  git pull → /var/lib/cm-dashboard/nixos-config → rebuild
-- **Widget testing**: Verify UI layout matches legacy appearance exactly
+```
 
-**NEVER in New Implementation**:
+## Automated Binary Release System
 
-- Copy/paste ANY code from legacy backup
+CM Dashboard uses automated binary releases instead of source builds.
-- Calculate status in dashboard widgets
-- Hardcode metric names in widgets (use const arrays)
 
-# Important Communication Guidelines
+### Creating New Releases
 
-NEVER write that you have "successfully implemented" something or generate extensive summary text without first verifying with the user that the implementation is correct. This wastes tokens. Keep responses concise.
+```bash
+cd ~/projects/cm-dashboard
+git tag v0.1.X
+git push origin v0.1.X
+```
 
-NEVER implement code without first getting explicit user agreement on the approach. Always ask for confirmation before proceeding with implementation.
+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
+version = "v0.1.X";
+src = pkgs.fetchurl {
+  url = "https://gitea.cmtec.se/cm/cm-dashboard/releases/download/${version}/cm-dashboard-linux-x86_64.tar.gz";
+  sha256 = "sha256-NEW_HASH_HERE";
+};
+```
+
+### Get Release Hash
+
+```bash
+cd ~/projects/nixosbox
+nix-build --no-out-link -E 'with import <nixpkgs> {}; fetchurl {
+  url = "https://gitea.cmtec.se/cm/cm-dashboard/releases/download/v0.1.X/cm-dashboard-linux-x86_64.tar.gz";
+  sha256 = "sha256-AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA=";
+}' 2>&1 | grep "got:"
+```
+
+### Building
+
+**Testing & Building:**
+
+- **Workspace builds**: `nix-shell -p openssl pkg-config --run "cargo build --workspace"`
+- **Clean compilation**: Remove `target/` between major changes
+
+## Enhanced Storage Pool Visualization
+
+### Auto-Discovery Architecture
+
+The dashboard uses automatic storage discovery to eliminate manual configuration complexity while providing intelligent storage pool grouping.
+
+### 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
+4. Store discovered storage topology for continuous monitoring
+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
+- Generate enhanced metrics for dashboard visualization
+
+### 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)
+- Pool health calculation (healthy/degraded/critical)
+- 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
+
+### Configuration
+
+```toml
+[collectors.disk]
+enabled = true
+auto_discover = true  # Default: true
+# Optional exclusions for special filesystems
+exclude_mount_points = ["/tmp", "/proc", "/sys", "/dev"]
+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:
+● 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
+```
+
+## Important Communication Guidelines
+
+Keep responses concise and focused. Avoid extensive implementation summaries unless requested.
 
 ## Commit Message Guidelines
 
@@ -244,60 +361,23 @@ NEVER implement code without first getting explicit user agreement on the approa
 - ✅ "Restructure storage widget with improved layout"
 - ✅ "Update CPU thresholds to production values"
 
-## NixOS Configuration Updates
+## Implementation Rules
 
-When code changes are made to cm-dashboard, the NixOS configuration at `~/nixosbox` must be updated to deploy the changes.
+1. **Agent Status Authority**: Agent calculates status for each metric using thresholds
+2. **Dashboard Composition**: Dashboard widgets subscribe to specific metrics by name
+3. **Status Aggregation**: Dashboard aggregates individual metric statuses for widget status
 
-### Update Process
+**NEVER:**
 
-1. **Get Latest Commit Hash**
+- Copy/paste ANY code from legacy implementations
+- Calculate status in dashboard widgets
+- Hardcode metric names in widgets (use const arrays)
+- Create files unless absolutely necessary for achieving goals
+- Create documentation files unless explicitly requested
 
-   ```bash
+**ALWAYS:**
-   git log -1 --format="%H"
-   ```
 
-2. **Update NixOS Configuration**
+- Prefer editing existing files to creating new ones
-   Edit `~/nixosbox/hosts/common/cm-dashboard.nix`:
+- Follow existing code conventions and patterns
-
+- Use existing libraries and utilities
-   ```nix
+- Follow security best practices
-   src = pkgs.fetchgit {
-     url = "https://gitea.cmtec.se/cm/cm-dashboard.git";
-     rev = "NEW_COMMIT_HASH_HERE";
-     sha256 = "sha256-AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA="; # Placeholder
-   };
-   ```
-
-3. **Get Correct Source Hash**
-   Build with placeholder hash to get the actual hash:
-
-   ```bash
-   cd ~/nixosbox
-   nix-build --no-out-link -E 'with import <nixpkgs> {}; fetchgit {
-     url = "https://gitea.cmtec.se/cm/cm-dashboard.git";
-     rev = "NEW_COMMIT_HASH";
-     sha256 = "sha256-AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA=";
-   }' 2>&1 | grep "got:"
-   ```
-
-   Example output:
-
-   ```
-   error: hash mismatch in fixed-output derivation '/nix/store/...':
-            specified: sha256-AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA=
-               got:    sha256-x8crxNusOUYRrkP9mYEOG+Ga3JCPIdJLkEAc5P1ZxdQ=
-   ```
-
-4. **Update Configuration with Correct Hash**
-   Replace the placeholder with the hash from the error message (the "got:" line).
-
-5. **Commit NixOS Configuration**
-
-   ```bash
-   cd ~/nixosbox
-   git add hosts/common/cm-dashboard.nix
-   git commit -m "Update cm-dashboard to latest version (SHORT_HASH)"
-   git push
-   ```
-
-6. **Rebuild System**
-   The user handles the system rebuild step - this cannot be automated.

Cargo.lock

@@ -17,9 +17,9 @@ dependencies = [
 
 [[package]]
 name = "aho-corasick"
-version = "1.1.3"
+version = "1.1.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8e60d3430d3a69478ad0993f19238d2df97c507009a52b3c10addcd7f6bcb916"
+checksum = "ddd31a130427c27518df266943a5308ed92d4b226cc639f5a8f1002816174301"
 dependencies = [
  "memchr",
 ]
@@ -71,22 +71,22 @@ dependencies = [
 
 [[package]]
 name = "anstyle-query"
-version = "1.1.4"
+version = "1.1.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9e231f6134f61b71076a3eab506c379d4f36122f2af15a9ff04415ea4c3339e2"
+checksum = "40c48f72fd53cd289104fc64099abca73db4166ad86ea0b4341abe65af83dadc"
 dependencies = [
- "windows-sys 0.60.2",
+ "windows-sys 0.61.2",
 ]
 
 [[package]]
 name = "anstyle-wincon"
-version = "3.0.10"
+version = "3.0.11"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3e0633414522a32ffaac8ac6cc8f748e090c5717661fddeea04219e2344f5f2a"
+checksum = "291e6a250ff86cd4a820112fb8898808a366d8f9f58ce16d1f538353ad55747d"
 dependencies = [
  "anstyle",
  "once_cell_polyfill",
- "windows-sys 0.60.2",
+ "windows-sys 0.61.2",
 ]
 
 [[package]]
@@ -95,6 +95,15 @@ version = "1.0.100"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "a23eb6b1614318a8071c9b2521f36b424b2c83db5eb3a0fead4a6c0809af6e61"
 
+[[package]]
+name = "ar_archive_writer"
+version = "0.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f0c269894b6fe5e9d7ada0cf69b5bf847ff35bc25fc271f08e1d080fce80339a"
+dependencies = [
+ "object",
+]
+
 [[package]]
 name = "async-trait"
 version = "0.1.89"
@@ -144,9 +153,9 @@ checksum = "46c5e41b57b8bba42a04676d81cb89e9ee8e859a1a66f80a5a72e1cb76b34d43"
 
 [[package]]
 name = "bytes"
-version = "1.10.1"
+version = "1.11.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d71b6127be86fdcfddb610f7182ac57211d4b18a3e9c82eb2d17662f2227ad6a"
+checksum = "b35204fbdc0b3f4446b89fc1ac2cf84a8a68971995d0bf2e925ec7cd960f9cb3"
 
 [[package]]
 name = "cassowary"
@@ -156,9 +165,9 @@ checksum = "df8670b8c7b9dae1793364eafadf7239c40d669904660c5960d74cfd80b46a53"
 
 [[package]]
 name = "cc"
-version = "1.2.41"
+version = "1.2.46"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ac9fe6cdbb24b6ade63616c0a0688e45bb56732262c158df3c0c4bea4ca47cb7"
+checksum = "b97463e1064cb1b1c1384ad0a0b9c8abd0988e2a91f52606c80ef14aadb63e36"
 dependencies = [
  "find-msvc-tools",
  "jobserver",
@@ -230,9 +239,9 @@ dependencies = [
 
 [[package]]
 name = "clap"
-version = "4.5.49"
+version = "4.5.52"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f4512b90fa68d3a9932cea5184017c5d200f5921df706d45e853537dea51508f"
+checksum = "aa8120877db0e5c011242f96806ce3c94e0737ab8108532a76a3300a01db2ab8"
 dependencies = [
  "clap_builder",
  "clap_derive",
@@ -240,9 +249,9 @@ dependencies = [
 
 [[package]]
 name = "clap_builder"
-version = "4.5.49"
+version = "4.5.52"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0025e98baa12e766c67ba13ff4695a887a1eba19569aad00a472546795bd6730"
+checksum = "02576b399397b659c26064fbc92a75fede9d18ffd5f80ca1cd74ddab167016e1"
 dependencies = [
  "anstream",
  "anstyle",
@@ -270,7 +279,7 @@ checksum = "a1d728cc89cf3aee9ff92b05e62b19ee65a02b5702cff7d5a377e32c6ae29d8d"
 
 [[package]]
 name = "cm-dashboard"
-version = "0.1.0"
+version = "0.1.170"
 dependencies = [
  "anyhow",
  "chrono",
@@ -286,12 +295,13 @@ dependencies = [
  "toml",
  "tracing",
  "tracing-subscriber",
+ "wake-on-lan",
  "zmq",
 ]
 
 [[package]]
 name = "cm-dashboard-agent"
-version = "0.1.0"
+version = "0.1.170"
 dependencies = [
  "anyhow",
  "async-trait",
@@ -314,7 +324,7 @@ dependencies = [
 
 [[package]]
 name = "cm-dashboard-shared"
-version = "0.1.0"
+version = "0.1.170"
 dependencies = [
  "chrono",
  "serde",
@@ -502,9 +512,9 @@ checksum = "37909eebbb50d72f9059c3b6d82c0463f2ff062c9e95845c43a6c9c0355411be"
 
 [[package]]
 name = "find-msvc-tools"
-version = "0.1.4"
+version = "0.1.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "52051878f80a721bb68ebfbc930e07b65ba72f2da88968ea5c06fd6ca3d3a127"
+checksum = "3a3076410a55c90011c298b04d0cfa770b00fa04e1e3c97d3f6c9de105a03844"
 
 [[package]]
 name = "fnv"
@@ -767,9 +777,9 @@ dependencies = [
 
 [[package]]
 name = "icu_collections"
-version = "2.0.0"
+version = "2.1.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "200072f5d0e3614556f94a9930d5dc3e0662a652823904c3a75dc3b0af7fee47"
+checksum = "4c6b649701667bbe825c3b7e6388cb521c23d88644678e83c0c4d0a621a34b43"
 dependencies = [
  "displaydoc",
  "potential_utf",
@@ -780,9 +790,9 @@ dependencies = [
 
 [[package]]
 name = "icu_locale_core"
-version = "2.0.0"
+version = "2.1.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0cde2700ccaed3872079a65fb1a78f6c0a36c91570f28755dda67bc8f7d9f00a"
+checksum = "edba7861004dd3714265b4db54a3c390e880ab658fec5f7db895fae2046b5bb6"
 dependencies = [
  "displaydoc",
  "litemap",
@@ -793,11 +803,10 @@ dependencies = [
 
 [[package]]
 name = "icu_normalizer"
-version = "2.0.0"
+version = "2.1.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "436880e8e18df4d7bbc06d58432329d6458cc84531f7ac5f024e93deadb37979"
+checksum = "5f6c8828b67bf8908d82127b2054ea1b4427ff0230ee9141c54251934ab1b599"
 dependencies = [
- "displaydoc",
  "icu_collections",
  "icu_normalizer_data",
  "icu_properties",
@@ -808,42 +817,38 @@ dependencies = [
 
 [[package]]
 name = "icu_normalizer_data"
-version = "2.0.0"
+version = "2.1.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "00210d6893afc98edb752b664b8890f0ef174c8adbb8d0be9710fa66fbbf72d3"
+checksum = "7aedcccd01fc5fe81e6b489c15b247b8b0690feb23304303a9e560f37efc560a"
 
 [[package]]
 name = "icu_properties"
-version = "2.0.1"
+version = "2.1.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "016c619c1eeb94efb86809b015c58f479963de65bdb6253345c1a1276f22e32b"
+checksum = "e93fcd3157766c0c8da2f8cff6ce651a31f0810eaa1c51ec363ef790bbb5fb99"
 dependencies = [
- "displaydoc",
  "icu_collections",
  "icu_locale_core",
  "icu_properties_data",
  "icu_provider",
- "potential_utf",
  "zerotrie",
  "zerovec",
 ]
 
 [[package]]
 name = "icu_properties_data"
-version = "2.0.1"
+version = "2.1.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "298459143998310acd25ffe6810ed544932242d3f07083eee1084d83a71bd632"
+checksum = "02845b3647bb045f1100ecd6480ff52f34c35f82d9880e029d329c21d1054899"
 
 [[package]]
 name = "icu_provider"
-version = "2.0.0"
+version = "2.1.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "03c80da27b5f4187909049ee2d72f276f0d9f99a42c306bd0131ecfe04d8e5af"
+checksum = "85962cf0ce02e1e0a629cc34e7ca3e373ce20dda4c4d7294bbd0bf1fdb59e614"
 dependencies = [
  "displaydoc",
  "icu_locale_core",
- "stable_deref_trait",
- "tinystr",
  "writeable",
  "yoke",
  "zerofrom",
@@ -884,9 +889,12 @@ dependencies = [
 
 [[package]]
 name = "indoc"
-version = "2.0.6"
+version = "2.0.7"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f4c7245a08504955605670dbf141fceab975f15ca21570696aebe9d2e71576bd"
+checksum = "79cf5c93f93228cf8efb3ba362535fb11199ac548a09ce117c9b1adc3030d706"
+dependencies = [
+ "rustversion",
+]
 
 [[package]]
 name = "ipnet"
@@ -896,9 +904,9 @@ checksum = "469fb0b9cefa57e3ef31275ee7cacb78f2fdca44e4765491884a2b119d4eb130"
 
 [[package]]
 name = "is_terminal_polyfill"
-version = "1.70.1"
+version = "1.70.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7943c866cc5cd64cbc25b2e01621d07fa8eb2a1a23160ee81ce38704e97b8ecf"
+checksum = "a6cb138bb79a146c1bd460005623e142ef0181e3d0219cb493e02f7d08a35695"
 
 [[package]]
 name = "itertools"
@@ -927,9 +935,9 @@ dependencies = [
 
 [[package]]
 name = "js-sys"
-version = "0.3.81"
+version = "0.3.82"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ec48937a97411dcb524a265206ccd4c90bb711fca92b2792c407f268825b9305"
+checksum = "b011eec8cc36da2aab2d5cff675ec18454fad408585853910a202391cf9f8e65"
 dependencies = [
  "once_cell",
  "wasm-bindgen",
@@ -987,9 +995,9 @@ checksum = "df1d3c3b53da64cf5760482273a98e575c651a67eec7f77df96b5b642de8f039"
 
 [[package]]
 name = "litemap"
-version = "0.8.0"
+version = "0.8.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "241eaef5fd12c88705a01fc1066c48c4b36e0dd4377dcdc7ec3942cea7a69956"
+checksum = "6373607a59f0be73a39b6fe456b8192fcc3585f602af20751600e974dd455e77"
 
 [[package]]
 name = "lock_api"
@@ -1103,6 +1111,15 @@ dependencies = [
  "autocfg",
 ]
 
+[[package]]
+name = "object"
+version = "0.32.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a6a622008b6e321afc04970976f62ee297fdbaa6f95318ca343e3eebb9648441"
+dependencies = [
+ "memchr",
+]
+
 [[package]]
 name = "once_cell"
 version = "1.21.3"
@@ -1111,15 +1128,15 @@ checksum = "42f5e15c9953c5e4ccceeb2e7382a716482c34515315f7b03532b8b4e8393d2d"
 
 [[package]]
 name = "once_cell_polyfill"
-version = "1.70.1"
+version = "1.70.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a4895175b425cb1f87721b59f0f286c2092bd4af812243672510e1ac53e2e0ad"
+checksum = "384b8ab6d37215f3c5301a95a4accb5d64aa607f1fcb26a11b5303878451b4fe"
 
 [[package]]
 name = "openssl"
-version = "0.10.74"
+version = "0.10.75"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "24ad14dd45412269e1a30f52ad8f0664f0f4f4a89ee8fe28c3b3527021ebb654"
+checksum = "08838db121398ad17ab8531ce9de97b244589089e290a384c900cb9ff7434328"
 dependencies = [
  "bitflags 2.10.0",
  "cfg-if",
@@ -1149,9 +1166,9 @@ checksum = "d05e27ee213611ffe7d6348b942e8f942b37114c00cc03cec254295a4a17852e"
 
 [[package]]
 name = "openssl-sys"
-version = "0.9.110"
+version = "0.9.111"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0a9f0075ba3c21b09f8e8b2026584b1d18d49388648f2fbbf3c97ea8deced8e2"
+checksum = "82cab2d520aa75e3c58898289429321eb788c3106963d0dc886ec7a5f4adc321"
 dependencies = [
  "cc",
  "libc",
@@ -1261,36 +1278,37 @@ checksum = "7edddbd0b52d732b21ad9a5fab5c704c14cd949e5e9a1ec5929a24fded1b904c"
 
 [[package]]
 name = "potential_utf"
-version = "0.1.3"
+version = "0.1.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "84df19adbe5b5a0782edcab45899906947ab039ccf4573713735ee7de1e6b08a"
+checksum = "b73949432f5e2a09657003c25bca5e19a0e9c84f8058ca374f49e0ebe605af77"
 dependencies = [
  "zerovec",
 ]
 
 [[package]]
 name = "proc-macro2"
-version = "1.0.101"
+version = "1.0.103"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "89ae43fd86e4158d6db51ad8e2b80f313af9cc74f5c0e03ccb87de09998732de"
+checksum = "5ee95bc4ef87b8d5ba32e8b7714ccc834865276eab0aed5c9958d00ec45f49e8"
 dependencies = [
  "unicode-ident",
 ]
 
 [[package]]
 name = "psm"
-version = "0.1.27"
+version = "0.1.28"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e66fcd288453b748497d8fb18bccc83a16b0518e3906d4b8df0a8d42d93dbb1c"
+checksum = "d11f2fedc3b7dafdc2851bc52f277377c5473d378859be234bc7ebb593144d01"
 dependencies = [
+ "ar_archive_writer",
  "cc",
 ]
 
 [[package]]
 name = "quote"
-version = "1.0.41"
+version = "1.0.42"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ce25767e7b499d1b604768e7cde645d14cc8584231ea6b295e9c9eb22c02e1d1"
+checksum = "a338cc41d27e6cc6dce6cefc13a0729dfbb81c262b1f519331575dd80ef3067f"
 dependencies = [
  "proc-macro2",
 ]
@@ -1610,9 +1628,9 @@ dependencies = [
 
 [[package]]
 name = "signal-hook-mio"
-version = "0.2.4"
+version = "0.2.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "34db1a06d485c9142248b7a054f034b349b212551f3dfd19c94d45a754a217cd"
+checksum = "b75a19a7a740b25bc7944bdee6172368f988763b744e3d4dfe753f6b4ece40cc"
 dependencies = [
  "libc",
  "mio 0.8.11",
@@ -1715,9 +1733,9 @@ dependencies = [
 
 [[package]]
 name = "syn"
-version = "2.0.107"
+version = "2.0.110"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2a26dbd934e5451d21ef060c018dae56fc073894c5a7896f882928a76e6d081b"
+checksum = "a99801b5bd34ede4cf3fc688c5919368fea4e4814a4664359503e6015b280aea"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -1825,9 +1843,9 @@ dependencies = [
 
 [[package]]
 name = "tinystr"
-version = "0.8.1"
+version = "0.8.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5d4f6d1145dcb577acf783d4e601bc1d76a13337bb54e6233add580b07344c8b"
+checksum = "42d3e9c45c09de15d06dd8acf5f4e0e399e85927b7f00711024eb7ae10fa4869"
 dependencies = [
  "displaydoc",
  "zerovec",
@@ -1873,9 +1891,9 @@ dependencies = [
 
 [[package]]
 name = "tokio-util"
-version = "0.7.16"
+version = "0.7.17"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "14307c986784f72ef81c89db7d9e28d6ac26d16213b109ea501696195e6e3ce5"
+checksum = "2efa149fe76073d6e8fd97ef4f4eca7b67f599660115591483572e406e165594"
 dependencies = [
  "bytes",
  "futures-core",
@@ -2000,9 +2018,9 @@ checksum = "e421abadd41a4225275504ea4d6566923418b7f05506fbc9c0fe86ba7396114b"
 
 [[package]]
 name = "unicode-ident"
-version = "1.0.19"
+version = "1.0.22"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f63a545481291138910575129486daeaf8ac54aee4387fe7906919f7830c7d9d"
+checksum = "9312f7c4f6ff9069b165498234ce8be658059c6728633667c526e27dc2cf1df5"
 
 [[package]]
 name = "unicode-segmentation"
@@ -2054,9 +2072,9 @@ checksum = "accd4ea62f7bb7a82fe23066fb0957d48ef677f6eeb8215f372f52e48bb32426"
 
 [[package]]
 name = "version-compare"
-version = "0.2.0"
+version = "0.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "852e951cb7832cb45cb1169900d19760cfa39b82bc0ea9c0e5a14ae88411c98b"
+checksum = "03c2856837ef78f57382f06b2b8563a2f512f7185d732608fd9176cb3b8edf0e"
 
 [[package]]
 name = "version_check"
@@ -2064,6 +2082,12 @@ version = "0.9.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "0b928f33d975fc6ad9f86c8f283853ad26bdd5b10b7f1542aa2fa15e2289105a"
 
+[[package]]
+name = "wake-on-lan"
+version = "0.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1ccf60b60ad7e5b1b37372c5134cbcab4db0706c231d212e0c643a077462bc8f"
+
 [[package]]
 name = "walkdir"
 version = "2.5.0"
@@ -2100,9 +2124,9 @@ dependencies = [
 
 [[package]]
 name = "wasm-bindgen"
-version = "0.2.104"
+version = "0.2.105"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c1da10c01ae9f1ae40cbfac0bac3b1e724b320abfcf52229f80b547c0d250e2d"
+checksum = "da95793dfc411fbbd93f5be7715b0578ec61fe87cb1a42b12eb625caa5c5ea60"
 dependencies = [
  "cfg-if",
  "once_cell",
@@ -2111,25 +2135,11 @@ dependencies = [
  "wasm-bindgen-shared",
 ]
 
-[[package]]
-name = "wasm-bindgen-backend"
-version = "0.2.104"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "671c9a5a66f49d8a47345ab942e2cb93c7d1d0339065d4f8139c486121b43b19"
-dependencies = [
- "bumpalo",
- "log",
- "proc-macro2",
- "quote",
- "syn",
- "wasm-bindgen-shared",
-]
-
 [[package]]
 name = "wasm-bindgen-futures"
-version = "0.4.54"
+version = "0.4.55"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7e038d41e478cc73bae0ff9b36c60cff1c98b8f38f8d7e8061e79ee63608ac5c"
+checksum = "551f88106c6d5e7ccc7cd9a16f312dd3b5d36ea8b4954304657d5dfba115d4a0"
 dependencies = [
  "cfg-if",
  "js-sys",
@@ -2140,9 +2150,9 @@ dependencies = [
 
 [[package]]
 name = "wasm-bindgen-macro"
-version = "0.2.104"
+version = "0.2.105"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7ca60477e4c59f5f2986c50191cd972e3a50d8a95603bc9434501cf156a9a119"
+checksum = "04264334509e04a7bf8690f2384ef5265f05143a4bff3889ab7a3269adab59c2"
 dependencies = [
  "quote",
  "wasm-bindgen-macro-support",
@@ -2150,31 +2160,31 @@ dependencies = [
 
 [[package]]
 name = "wasm-bindgen-macro-support"
-version = "0.2.104"
+version = "0.2.105"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9f07d2f20d4da7b26400c9f4a0511e6e0345b040694e8a75bd41d578fa4421d7"
+checksum = "420bc339d9f322e562942d52e115d57e950d12d88983a14c79b86859ee6c7ebc"
 dependencies = [
+ "bumpalo",
  "proc-macro2",
  "quote",
  "syn",
- "wasm-bindgen-backend",
  "wasm-bindgen-shared",
 ]
 
 [[package]]
 name = "wasm-bindgen-shared"
-version = "0.2.104"
+version = "0.2.105"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bad67dc8b2a1a6e5448428adec4c3e84c43e561d8c9ee8a9e5aabeb193ec41d1"
+checksum = "76f218a38c84bcb33c25ec7059b07847d465ce0e0a76b995e134a45adcb6af76"
 dependencies = [
  "unicode-ident",
 ]
 
 [[package]]
 name = "web-sys"
-version = "0.3.81"
+version = "0.3.82"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9367c417a924a74cae129e6a2ae3b47fabb1f8995595ab474029da749a8be120"
+checksum = "3a1f95c0d03a47f4ae1f7a64643a6bb97465d9b740f0fa8f90ea33915c99a9a1"
 dependencies = [
  "js-sys",
  "wasm-bindgen",
@@ -2528,17 +2538,16 @@ checksum = "f17a85883d4e6d00e8a97c586de764dabcc06133f7f1d55dce5cdc070ad7fe59"
 
 [[package]]
 name = "writeable"
-version = "0.6.1"
+version = "0.6.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ea2f10b9bb0928dfb1b42b65e1f9e36f7f54dbdf08457afefb38afcdec4fa2bb"
+checksum = "9edde0db4769d2dc68579893f2306b26c6ecfbe0ef499b013d731b7b9247e0b9"
 
 [[package]]
 name = "yoke"
-version = "0.8.0"
+version = "0.8.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5f41bb01b8226ef4bfd589436a297c53d118f65921786300e427be8d487695cc"
+checksum = "72d6e5c6afb84d73944e5cedb052c4680d5657337201555f9f2a16b7406d4954"
 dependencies = [
- "serde",
  "stable_deref_trait",
  "yoke-derive",
  "zerofrom",
@@ -2546,9 +2555,9 @@ dependencies = [
 
 [[package]]
 name = "yoke-derive"
-version = "0.8.0"
+version = "0.8.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "38da3c9736e16c5d3c8c597a9aaa5d1fa565d0532ae05e27c24aa62fb32c0ab6"
+checksum = "b659052874eb698efe5b9e8cf382204678a0086ebf46982b79d6ca3182927e5d"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -2609,9 +2618,9 @@ dependencies = [
 
 [[package]]
 name = "zerotrie"
-version = "0.2.2"
+version = "0.2.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "36f0bbd478583f79edad978b407914f61b2972f5af6fa089686016be8f9af595"
+checksum = "2a59c17a5562d507e4b54960e8569ebee33bee890c70aa3fe7b97e85a9fd7851"
 dependencies = [
  "displaydoc",
  "yoke",
@@ -2620,9 +2629,9 @@ dependencies = [
 
 [[package]]
 name = "zerovec"
-version = "0.11.4"
+version = "0.11.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e7aa2bd55086f1ab526693ecbe444205da57e25f4489879da80635a46d90e73b"
+checksum = "6c28719294829477f525be0186d13efa9a3c602f7ec202ca9e353d310fb9a002"
 dependencies = [
  "yoke",
  "zerofrom",
@@ -2631,9 +2640,9 @@ dependencies = [
 
 [[package]]
 name = "zerovec-derive"
-version = "0.11.1"
+version = "0.11.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5b96237efa0c878c64bd89c436f661be4e46b2f3eff1ebb976f7ef2321d2f58f"
+checksum = "eadce39539ca5cb3985590102671f2567e659fca9666581ad3411d59207951f3"
 dependencies = [
  "proc-macro2",
  "quote",

README.md

@@ -1,88 +1,108 @@
 # CM Dashboard
 
-A real-time infrastructure monitoring system with intelligent status aggregation and email notifications, built with Rust and ZMQ.
+A high-performance Rust-based TUI dashboard for monitoring CMTEC infrastructure. Built with ZMQ-based metric collection and individual metrics architecture.
 
-## Current Implementation
+## Features
 
-This is a complete rewrite implementing an **individual metrics architecture** where:
+### Core Monitoring
+- **Real-time metrics**: CPU, RAM, Storage, and Service status
+- **Multi-host support**: Monitor multiple servers from single dashboard  
+- **Service management**: Start/stop services with intelligent status tracking
+- **NixOS integration**: System rebuild via SSH + tmux popup
+- **Backup monitoring**: Borgbackup status and scheduling
+- **Email notifications**: Intelligent batching prevents spam
 
-- **Agent** collects individual metrics (e.g., `cpu_load_1min`, `memory_usage_percent`) and calculates status
+### User-Stopped Service Tracking
-- **Dashboard** subscribes to specific metrics and composes widgets
+Services stopped via the dashboard are intelligently tracked to prevent false alerts:
-- **Status Aggregation** provides intelligent email notifications with batching
-- **Persistent Cache** prevents false notifications on restart
 
-## Dashboard Interface
+- **Smart status reporting**: User-stopped services show as Status::OK instead of Warning
+- **Persistent storage**: Tracking survives agent restarts via JSON storage
+- **Automatic management**: Flags cleared when services restarted via dashboard
+- **Maintenance friendly**: No false alerts during intentional service operations
+
+## Architecture
+
+### Individual Metrics Philosophy
+- **Agent**: Collects individual metrics, calculates status using thresholds
+- **Dashboard**: Subscribes to specific metrics, composes widgets from individual data
+- **ZMQ Communication**: Efficient real-time metric transmission
+- **Status Aggregation**: Host-level status calculated from all service metrics
+
+### Components
+
+```
+┌─────────────────┐    ZMQ     ┌─────────────────┐
+│                 │◄──────────►│                 │
+│   Agent         │  Metrics   │   Dashboard     │
+│   - Collectors  │            │   - TUI         │
+│   - Status      │            │   - Widgets     │
+│   - Tracking    │            │   - Commands    │
+│                 │            │                 │
+└─────────────────┘            └─────────────────┘
+         │                              │
+         ▼                              ▼
+┌─────────────────┐            ┌─────────────────┐
+│ JSON Storage    │            │ SSH + tmux      │
+│ - User-stopped  │            │ - Remote rebuild│
+│ - Cache         │            │ - Process       │
+│ - State         │            │   isolation     │
+└─────────────────┘            └─────────────────┘
+```
+
+### Service Control Flow
+
+1. **User Action**: Dashboard sends `UserStart`/`UserStop` commands
+2. **Agent Processing**: 
+   - Marks service as user-stopped (if stopping)
+   - Executes `systemctl start/stop service`
+   - Syncs state to global tracker
+3. **Status Calculation**: 
+   - Systemd collector checks user-stopped flag
+   - Reports Status::OK for user-stopped inactive services
+   - Normal Warning status for system failures
+
+## Interface
 
 ```
 cm-dashboard • ● cmbox ● srv01 ● srv02 ● steambox
 ┌system──────────────────────────────┐┌services─────────────────────────────────────────┐
-│CPU:                                ││Service:                  Status:  RAM:   Disk:  │
+│NixOS:                              ││Service:                  Status:  RAM:   Disk:  │
-│● Load: 0.10 0.52 0.88 • 400.0 MHz  ││● docker                  active   27M    496MB  │
+│Build: 25.05.20251004.3bcc93c       ││● docker                  active   27M    496MB  │
-│RAM:                                ││● docker-registry         active   19M    496MB  │
+│Agent: v0.1.43                      ││● gitea                   active   579M   2.6GB  │
-│● Used: 30% 2.3GB/7.6GB             ││● gitea                   active   579M   2.6GB  │
+│Active users: cm, simon             ││● nginx                   active   28M    24MB   │
-│● tmp: 0.0% 0B/2.0GB                ││● gitea-runner-default    active   11M    2.6GB  │
+│CPU:                                ││  ├─ ● gitea.cmtec.se     51ms                   │
-│Disk nvme0n1:                       ││● haasp-core              active   9M     1MB    │
+│● Load: 0.10 0.52 0.88 • 3000MHz    ││  ├─ ● photos.cmtec.se    41ms                   │
-│● Health: PASSED                    ││● haasp-mqtt              active   3M     1MB    │
+│RAM:                                ││● postgresql              active   112M   357MB  │
-│● Usage @root: 8.3% • 75.4/906.2 GB ││● haasp-webgrid           active   10M    1MB    │
+│● Usage: 33% 2.6GB/7.6GB            ││● redis-immich            user-stopped           │
-│● Usage @boot: 5.9% • 0.1/1.0 GB    ││● immich-server           active   240M   45.1GB │
+│● /tmp: 0% 0B/2.0GB                 ││● sshd                    active   2M     0      │
-│                                    ││● mosquitto               active   1M     1MB    │
+│Storage:                            ││● unifi                   active   594M   495MB  │
-│                                    ││● mysql                   active   38M    225MB  │
+│● root (Single):                    ││                                                 │
-│                                    ││● nginx                   active   28M    24MB   │
+│ ├─ ● nvme0n1 W: 1%                 ││                                                 │
-│                                    ││  ├─ ● gitea.cmtec.se     51ms                   │
+│ └─ ● 18% 167.4GB/928.2GB           ││                                                 │
-│                                    ││  ├─ ● haasp.cmtec.se     43ms                   │
-│                                    ││  ├─ ● haasp.net          43ms                   │
-│                                    ││  ├─ ● pages.cmtec.se     45ms                   │
-└────────────────────────────────────┘│  ├─ ● photos.cmtec.se    41ms                   │
-┌backup──────────────────────────────┐│  ├─ ● unifi.cmtec.se     46ms                   │
-│Latest backup:                      ││  ├─ ● vault.cmtec.se     47ms                   │
-│● Status: OK                        ││  ├─ ● www.kryddorten.se  81ms                   │
-│Duration: 54s • Last: 4h ago        ││  ├─ ● www.mariehall2.se  86ms                   │
-│Disk usage: 48.2GB/915.8GB          ││● postgresql              active   112M   357MB  │
-│P/N: Samsung SSD 870 QVO 1TB        ││● redis-immich            active   8M     45.1GB │
-│S/N: S5RRNF0W800639Y                ││● sshd                    active   2M     0      │
-│● gitea 2 archives 2.7GB            ││● unifi                   active   594M   495MB  │
-│● immich 2 archives 45.0GB          ││● vaultwarden             active   12M    1MB    │
-│● kryddorten 2 archives 67.6MB      ││                                                 │
-│● mariehall2 2 archives 321.8MB     ││                                                 │
-│● nixosbox 2 archives 4.5MB         ││                                                 │
-│● unifi 2 archives 2.9MB            ││                                                 │
-│● vaultwarden 2 archives 305kB      ││                                                 │
 └────────────────────────────────────┘└─────────────────────────────────────────────────┘
 ```
 
-**Navigation**: `←→` switch hosts, `r` refresh, `q` quit
+### Navigation
+- **Tab**: Switch between hosts
+- **↑↓ or j/k**: Navigate services
+- **s**: Start selected service (UserStart)  
+- **S**: Stop selected service (UserStop)
+- **J**: Show service logs (journalctl in tmux popup)
+- **L**: Show custom log files (tail -f custom paths in tmux popup)
+- **R**: Rebuild current host
+- **B**: Run backup on current host
+- **q**: Quit
 
-## Features
+### Status Indicators
-
+- **Green ●**: Active service
-- **Real-time monitoring** - Dashboard updates every 1-2 seconds
+- **Yellow ◐**: Inactive service (system issue)
-- **Individual metric collection** - Granular data for flexible dashboard composition
+- **Red ◯**: Failed service
-- **Intelligent status aggregation** - Host-level status calculated from all services
+- **Blue arrows**: Service transitioning (↑ starting, ↓ stopping, ↻ restarting)
-- **Smart email notifications** - Batched, detailed alerts with service groupings
+- **"user-stopped"**: Service stopped via dashboard (Status::OK)
-- **Persistent state** - Prevents false notifications on restarts
-- **ZMQ communication** - Efficient agent-to-dashboard messaging
-- **Clean TUI** - Terminal-based dashboard with color-coded status indicators
-
-## Architecture
-
-### Core Components
-
-- **Agent** (`cm-dashboard-agent`) - Collects metrics and sends via ZMQ
-- **Dashboard** (`cm-dashboard`) - Real-time TUI display consuming metrics
-- **Shared** (`cm-dashboard-shared`) - Common types and protocol
-- **Status Aggregation** - Intelligent batching and notification management
-- **Persistent Cache** - Maintains state across restarts
-
-### Status Levels
-
-- **🟢 Ok** - Service running normally
-- **🔵 Pending** - Service starting/stopping/reloading
-- **🟡 Warning** - Service issues (high load, memory, disk usage)
-- **🔴 Critical** - Service failed or critical thresholds exceeded
-- **❓ Unknown** - Service state cannot be determined
 
 ## Quick Start
 
-### Build
+### Building
 
 ```bash
 # With Nix (recommended)
@@ -93,21 +113,20 @@ sudo apt install libssl-dev pkg-config  # Ubuntu/Debian
 cargo build --workspace
 ```
 
-### Run
+### Running
 
 ```bash
-# Start agent (requires configuration file)
+# Start agent (requires configuration)
 ./target/debug/cm-dashboard-agent --config /etc/cm-dashboard/agent.toml
 
-# Start dashboard
+# Start dashboard (inside tmux session)
-./target/debug/cm-dashboard --config /path/to/dashboard.toml
+tmux
+./target/debug/cm-dashboard --config /etc/cm-dashboard/dashboard.toml
 ```
 
 ## Configuration
 
-### Agent Configuration (`agent.toml`)
+### Agent Configuration
-
-The agent requires a comprehensive TOML configuration file:
 
 ```toml
 collection_interval_seconds = 2
@@ -116,47 +135,27 @@ collection_interval_seconds = 2
 publisher_port = 6130
 command_port = 6131
 bind_address = "0.0.0.0"
-timeout_ms = 5000
+transmission_interval_seconds = 2
-heartbeat_interval_ms = 30000
 
 [collectors.cpu]
 enabled = true
 interval_seconds = 2
-load_warning_threshold = 9.0
+load_warning_threshold = 5.0
 load_critical_threshold = 10.0
-temperature_warning_threshold = 100.0
-temperature_critical_threshold = 110.0
 
 [collectors.memory]
 enabled = true
 interval_seconds = 2
 usage_warning_percent = 80.0
-usage_critical_percent = 95.0
-
-[collectors.disk]
-enabled = true
-interval_seconds = 300
-usage_warning_percent = 80.0
 usage_critical_percent = 90.0
 
-[[collectors.disk.filesystems]]
-name = "root"
-uuid = "4cade5ce-85a5-4a03-83c8-dfd1d3888d79"
-mount_point = "/"
-fs_type = "ext4"
-monitor = true
-
 [collectors.systemd]
 enabled = true
 interval_seconds = 10
-memory_warning_mb = 1000.0
+service_name_filters = ["nginx*", "postgresql*", "docker*", "sshd*"]
-memory_critical_mb = 2000.0
+excluded_services = ["nginx-config-reload", "systemd-", "getty@"]
-service_name_filters = [
+nginx_latency_critical_ms = 1000.0
-  "nginx", "postgresql", "redis", "docker", "sshd"
+http_timeout_seconds = 10
-]
-excluded_services = [
-  "nginx-config-reload", "sshd-keygen"
-]
 
 [notifications]
 enabled = true
@@ -164,251 +163,203 @@ smtp_host = "localhost"
 smtp_port = 25
 from_email = "{hostname}@example.com"
 to_email = "admin@example.com"
-rate_limit_minutes = 0
+aggregation_interval_seconds = 30
-trigger_on_warnings = true
-trigger_on_failures = true
-recovery_requires_all_ok = true
-suppress_individual_recoveries = true
-
-[status_aggregation]
-enabled = true
-aggregation_method = "worst_case"
-notification_interval_seconds = 30
-
-[cache]
-persist_path = "/var/lib/cm-dashboard/cache.json"
 ```
 
-### Dashboard Configuration (`dashboard.toml`)
+### Dashboard Configuration
 
 ```toml
 [zmq]
-hosts = [
+subscriber_ports = [6130]
-  { name = "server1", address = "192.168.1.100", port = 6130 },
-  { name = "server2", address = "192.168.1.101", port = 6130 }
-]
-connection_timeout_ms = 5000
-reconnect_interval_ms = 10000
 
-[ui]
+[hosts]
-refresh_interval_ms = 1000
+predefined_hosts = ["cmbox", "srv01", "srv02"]
-theme = "dark"
+
+[ssh]
+rebuild_user = "cm"
+rebuild_alias = "nixos-rebuild-cmtec"
+backup_alias = "cm-backup-run"
 ```
 
-## Collectors
+## Technical Implementation
 
-The agent implements several specialized collectors:
+### Collectors
 
-### CPU Collector (`cpu.rs`)
+#### Systemd Collector
+- **Service Discovery**: Uses `systemctl list-unit-files` + `list-units --all`
+- **Status Calculation**: Checks user-stopped flag before assigning Warning status
+- **Memory Tracking**: Per-service memory usage via `systemctl show`
+- **Sub-services**: Nginx site latency, Docker containers
+- **User-stopped Integration**: `UserStoppedServiceTracker::is_service_user_stopped()`
 
-- Load average (1, 5, 15 minute)
+#### User-Stopped Service Tracker
-- CPU temperature monitoring
+- **Storage**: `/var/lib/cm-dashboard/user-stopped-services.json`
-- Real-time process monitoring (top CPU consumers)
+- **Thread Safety**: Global singleton with `Arc<Mutex<>>`
-- Status calculation with configurable thresholds
+- **Persistence**: Automatic save on state changes
+- **Global Access**: Static methods for collector integration
 
-### Memory Collector (`memory.rs`)
+#### Other Collectors
+- **CPU**: Load average, temperature, frequency monitoring
+- **Memory**: RAM/swap usage, tmpfs monitoring  
+- **Disk**: Filesystem usage, SMART health data
+- **NixOS**: Build version, active users, agent version
+- **Backup**: Borgbackup repository status and metrics
 
-- RAM usage (total, used, available)
+### ZMQ Protocol
-- Swap monitoring
-- Real-time process monitoring (top RAM consumers)
-- Memory pressure detection
 
-### Disk Collector (`disk.rs`)
+```rust
+// Metric Message
+#[derive(Serialize, Deserialize)]
+pub struct MetricMessage {
+    pub hostname: String,
+    pub timestamp: u64,
+    pub metrics: Vec<Metric>,
+}
 
-- Filesystem usage per mount point
+// Service Commands
-- SMART health monitoring
+pub enum AgentCommand {
-- Temperature and wear tracking
+    ServiceControl {
-- Configurable filesystem monitoring
+        service_name: String,
+        action: ServiceAction,
+    },
+    SystemRebuild { /* SSH config */ },
+    CollectNow,
+}
 
-### Systemd Collector (`systemd.rs`)
+pub enum ServiceAction {
+    Start,           // System-initiated
+    Stop,            // System-initiated  
+    UserStart,       // User via dashboard (clears user-stopped)
+    UserStop,        // User via dashboard (marks user-stopped)
+    Status,
+}
+```
 
-- Service status monitoring (`active`, `inactive`, `failed`)
+### Maintenance Mode
-- Memory usage per service
-- Service filtering and exclusions
-- Handles transitional states (`Status::Pending`)
 
-### Backup Collector (`backup.rs`)
+Suppress notifications during planned maintenance:
 
-- Reads TOML status files from backup systems
+```bash
-- Archive age verification
+# Enable maintenance mode
-- Disk usage tracking
+touch /tmp/cm-maintenance
-- Repository health monitoring
+
+# Perform maintenance
+systemctl stop service
+# ... work ...
+systemctl start service  
+
+# Disable maintenance mode
+rm /tmp/cm-maintenance
+```
 
 ## Email Notifications
 
 ### Intelligent Batching
+- **Real-time dashboard**: Immediate status updates
+- **Batched emails**: Aggregated every 30 seconds
+- **Smart grouping**: Services organized by severity
+- **Recovery suppression**: Reduces notification spam
 
-The system implements smart notification batching to prevent email spam:
+### Example Alert
-
-- **Real-time dashboard updates** - Status changes appear immediately
-- **Batched email notifications** - Aggregated every 30 seconds
-- **Detailed groupings** - Services organized by severity
-
-### Example Alert Email
-
 ```
-Subject: Status Alert: 2 critical, 1 warning, 15 started
+Subject: Status Alert: 1 critical, 2 warnings, 0 recoveries
 
 Status Summary (30s duration)
 Host Status: Ok → Warning
 
-🔴 CRITICAL ISSUES (2):
+🔴 CRITICAL ISSUES (1):
-  postgresql: Ok → Critical
+  postgresql: Ok → Critical (memory usage 95%)
-  nginx: Warning → Critical
 
-🟡 WARNINGS (1):
+🟡 WARNINGS (2):
-  redis: Ok → Warning (memory usage 85%)
+  nginx: Ok → Warning (high load 8.5)
+  redis: user-stopped → Warning (restarted by system)
 
 ✅ RECOVERIES (0):
 
-🟢 SERVICE STARTUPS (15):
-  docker: Unknown → Ok
-  sshd: Unknown → Ok
-  ...
-
 --
-CM Dashboard Agent
+CM Dashboard Agent v0.1.43
-Generated at 2025-10-21 19:42:42 CET
 ```
 
-## Individual Metrics Architecture
-
-The system follows a **metrics-first architecture**:
-
-### Agent Side
-
-```rust
-// Agent collects individual metrics
-vec![
-    Metric::new("cpu_load_1min".to_string(), MetricValue::Float(2.5), Status::Ok),
-    Metric::new("memory_usage_percent".to_string(), MetricValue::Float(78.5), Status::Warning),
-    Metric::new("service_nginx_status".to_string(), MetricValue::String("active".to_string()), Status::Ok),
-]
-```
-
-### Dashboard Side
-
-```rust
-// Widgets subscribe to specific metrics
-impl Widget for CpuWidget {
-    fn update_from_metrics(&mut self, metrics: &[&Metric]) {
-        for metric in metrics {
-            match metric.name.as_str() {
-                "cpu_load_1min" => self.load_1min = metric.value.as_f32(),
-                "cpu_load_5min" => self.load_5min = metric.value.as_f32(),
-                "cpu_temperature_celsius" => self.temperature = metric.value.as_f32(),
-                _ => {}
-            }
-        }
-    }
-}
-```
-
-## Persistent Cache
-
-The cache system prevents false notifications:
-
-- **Automatic saving** - Saves when service status changes
-- **Persistent storage** - Maintains state across agent restarts
-- **Simple design** - No complex TTL or cleanup logic
-- **Status preservation** - Prevents duplicate notifications
-
 ## Development
 
 ### Project Structure
-
 ```
 cm-dashboard/
-├── agent/                  # Metrics collection agent
+├── agent/                     # Metrics collection agent
 │   ├── src/
-│   │   ├── collectors/     # CPU, memory, disk, systemd, backup
+│   │   ├── collectors/        # CPU, memory, disk, systemd, backup, nixos
-│   │   ├── status/         # Status aggregation and notifications
+│   │   ├── service_tracker.rs # User-stopped service tracking
-│   │   ├── cache/          # Persistent metric caching
+│   │   ├── status/            # Status aggregation and notifications
-│   │   ├── config/         # TOML configuration loading
+│   │   ├── config/            # TOML configuration loading
-│   │   └── notifications/  # Email notification system
+│   │   └── communication/     # ZMQ message handling
-├── dashboard/              # TUI dashboard application
+├── dashboard/                 # TUI dashboard application  
 │   ├── src/
-│   │   ├── ui/widgets/     # CPU, memory, services, backup widgets
+│   │   ├── ui/widgets/        # CPU, memory, services, backup, system
-│   │   ├── metrics/        # Metric storage and filtering
+│   │   ├── communication/     # ZMQ consumption and commands
-│   │   └── communication/  # ZMQ metric consumption
+│   │   └── app.rs            # Main application loop
-├── shared/                 # Shared types and utilities
+├── shared/                    # Shared types and utilities
 │   └── src/
-│       ├── metrics.rs      # Metric, Status, and Value types
+│       ├── metrics.rs         # Metric, Status, StatusTracker types
-│       ├── protocol.rs     # ZMQ message format
+│       ├── protocol.rs        # ZMQ message format
-│       └── cache.rs        # Cache configuration
+│       └── cache.rs           # Cache configuration
-└── README.md              # This file
+└── CLAUDE.md                  # Development guidelines and rules
 ```
 
-### Building
+### Testing
-
 ```bash
-# Debug build
+# Build and test
-cargo build --workspace
+nix-shell -p openssl pkg-config --run "cargo build --workspace"
+nix-shell -p openssl pkg-config --run "cargo test --workspace"
 
-# Release build
+# Code quality
-cargo build --workspace --release
+cargo fmt --all
-
-# Run tests
-cargo test --workspace
-
-# Check code formatting
-cargo fmt --all -- --check
-
-# Run clippy linter
 cargo clippy --workspace -- -D warnings
 ```
 
-### Dependencies
+## Deployment
 
-- **tokio** - Async runtime
+### Automated Binary Releases
-- **zmq** - Message passing between agent and dashboard
+```bash
-- **ratatui** - Terminal user interface
+# Create new release
-- **serde** - Serialization for metrics and config
+cd ~/projects/cm-dashboard
-- **anyhow/thiserror** - Error handling
+git tag v0.1.X
-- **tracing** - Structured logging
+git push origin v0.1.X
-- **lettre** - SMTP email notifications
+```
-- **clap** - Command-line argument parsing
-- **toml** - Configuration file parsing
 
-## NixOS Integration
+This triggers automated:
+- Static binary compilation with `RUSTFLAGS="-C target-feature=+crt-static"`
+- GitHub-style release creation
+- Tarball upload to Gitea
 
-This project is designed for declarative deployment via NixOS:
+### NixOS Integration
-
+Update `~/projects/nixosbox/hosts/services/cm-dashboard.nix`:
-### Configuration Generation
-
-The NixOS module automatically generates the agent configuration:
 
 ```nix
-# hosts/common/cm-dashboard.nix
+version = "v0.1.43";
-services.cm-dashboard-agent = {
+src = pkgs.fetchurl {
-  enable = true;
+  url = "https://gitea.cmtec.se/cm/cm-dashboard/releases/download/${version}/cm-dashboard-linux-x86_64.tar.gz";
-  port = 6130;
+  sha256 = "sha256-HASH";
 };
 ```
 
-### Deployment
+Get hash via:
-
 ```bash
-# Update NixOS configuration
+cd ~/projects/nixosbox
-git add hosts/common/cm-dashboard.nix
+nix-build --no-out-link -E 'with import <nixpkgs> {}; fetchurl {
-git commit -m "Update cm-dashboard configuration"
+  url = "URL_HERE";
-git push
+  sha256 = "sha256-AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA=";
-
+}' 2>&1 | grep "got:"
-# Rebuild system (user-performed)
-sudo nixos-rebuild switch --flake .
 ```
 
 ## Monitoring Intervals
 
-- **CPU/Memory**: 2 seconds (real-time monitoring)
+- **Metrics Collection**: 2 seconds (CPU, memory, services)
-- **Disk usage**: 300 seconds (5 minutes)
+- **Metric Transmission**: 2 seconds (ZMQ publish)
-- **Systemd services**: 10 seconds
+- **Dashboard Updates**: 1 second (UI refresh)
-- **SMART health**: 600 seconds (10 minutes)
+- **Email Notifications**: 30 seconds (batched)
-- **Backup status**: 60 seconds (1 minute)
+- **Disk Monitoring**: 300 seconds (5 minutes)
-- **Email notifications**: 30 seconds (batched)
+- **Service Discovery**: 300 seconds (5 minutes cache)
-- **Dashboard updates**: 1 second (real-time display)
 
 ## License
 
-MIT License - see LICENSE file for details
+MIT License - see LICENSE file for details.
-

TODO.md

@@ -1,63 +0,0 @@
-# TODO
-
-## Systemd filtering (agent)
-
-- remove user systemd collection
-- reduce number of systemctl call
-- Cahnge so only services in include list are detected
-- Filter on exact name
-- Add support for "\*" in filtering
-
-## System panel (agent/dashboard)
-
-use following layout:
-'''
-NixOS:
-Build: xxxxxx
-Agen: xxxxxx
-CPU:
-● Load: 0.02 0.31 0.86
-└─ Freq: 3000MHz
-RAM:
-● Usage: 33% 2.6GB/7.6GB  
- └─ ● /tmp: 0% 0B/2.0GB
-Storage:
-● /:  
- ├─ ● nvme0n1 T: 40C • W: 4%  
- └─ ● 8% 75.0GB/906.2GB
-'''
-
-- Add support to show login/active users
-- Add support to show timestamp/version for latest nixos rebuild
-
-## Backup panel (dashboard)
-
-use following layout:
-'''
-Latest backup:  
-● <timestamp>
-└─ Duration: 1.3m
-Disk:
-● Samsung SSD 870 QVO 1TB  
- ├─ S/N: S5RRNF0W800639Y
-└─ Usage: 50.5GB/915.8GB
-Repos:
-● gitea (4) 5.1GB  
-● immich (4) 45.0GB  
-● kryddorten (4) 67.8MB  
-● mariehall2 (4) 322.7MB
-● nixosbox (4) 5.5MB  
-● unifi (4) 5.7MB  
-● vaultwarden (4) 508kB
-'''
-
-## Keyboard navigation and scrolling (dashboard)
-
-- Add keyboard navigation between panels "Shift-Tab"
-- Add lower statusbar with dynamic updated shortcuts when switchng between panels
-
-## Remote execution (agent/dashboard)
-
-- Add support for send command via dashboard to agent to do nixos rebuid
-- Add support for navigating services in dashboard and trigger start/stop/restart
-- Add support for trigger backup

agent/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "cm-dashboard-agent"
-version = "0.1.0"
+version = "0.1.170"
 edition = "2021"
 
 [dependencies]

agent/src/agent.rs

@@ -4,20 +4,37 @@ use std::time::Duration;
 use tokio::time::interval;
 use tracing::{debug, error, info};
 
-use crate::communication::{AgentCommand, ServiceAction, ZmqHandler};
+use crate::communication::{AgentCommand, 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::status::HostStatusManager;
+use cm_dashboard_shared::AgentData;
-use cm_dashboard_shared::{Metric, MetricMessage};
 
 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,
+    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 {
@@ -38,64 +55,84 @@ impl Agent {
             config.zmq.publisher_port
         );
 
-        // Initialize metric collection manager with cache config
+        // Initialize collectors
-        let metric_manager = MetricCollectionManager::new(&config.collectors, &config).await?;
+        let mut collectors: Vec<Box<dyn Collector>> = Vec::new();
-        info!("Metric collection manager initialized");
+        
+        // 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");
-
         Ok(Self {
             hostname,
             config,
             zmq_handler,
-            metric_manager,
+            collectors,
             notification_manager,
-            host_status_manager,
+            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
+        // Initial collection
-        info!("Performing initial FORCE collection of all metrics at startup");
+        if let Err(e) = self.collect_and_broadcast().await {
-        if let Err(e) = self.collect_all_metrics_force().await {
+            error!("Initial metric collection failed: {}", e);
-            error!("Failed to collect initial metrics: {}", e);
-        } else {
-            info!("Initial metric collection completed - all data cached and ready");
         }
 
-        // Separate intervals for collection and transmission
+        // Set up intervals
-        let mut collection_interval =
+        let mut transmission_interval = interval(Duration::from_secs(
-            interval(Duration::from_secs(self.config.collection_interval_seconds));
+            self.config.collection_interval_seconds,
-        let mut transmission_interval = interval(Duration::from_secs(1)); // ZMQ broadcast every 1 second
+        ));
-        let mut notification_interval = interval(Duration::from_secs(self.config.status_aggregation.notification_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 cached metrics via ZMQ every 1 second
+                    if let Err(e) = self.collect_and_broadcast().await {
-                    if let Err(e) = self.broadcast_all_cached_metrics().await {
+                        error!("Failed to collect and broadcast metrics: {}", e);
-                        error!("Failed to broadcast cached metrics: {}", e);
                     }
                 }
                 _ = notification_interval.tick() => {
-                    // Process batched notifications
+                    // Process any pending notifications
-                    if let Err(e) = self.host_status_manager.process_pending_notifications(&mut self.notification_manager).await {
+                    // NOTE: With structured data, we might need to implement status tracking differently
-                        error!("Failed to process pending notifications: {}", e);
+                    // For now, we skip this until status evaluation is migrated
-                    }
                 }
                 // Handle incoming commands (check periodically)
                 _ = tokio::time::sleep(Duration::from_millis(100)) => {
@@ -114,314 +151,144 @@ impl Agent {
         Ok(())
     }
 
-    async fn collect_all_metrics_force(&mut self) -> Result<()> {
+    /// Collect structured data from all collectors and broadcast via ZMQ
-        info!("Starting FORCE metric collection for startup");
+    async fn collect_and_broadcast(&mut self) -> Result<()> {
+        debug!("Starting structured data collection");
 
-        // Force collect all metrics from all collectors immediately
+        // Initialize empty AgentData
-        let metrics = self.metric_manager.collect_all_metrics_force().await?;
+        let mut agent_data = AgentData::new(self.hostname.clone(), env!("CARGO_PKG_VERSION").to_string());
 
-        if metrics.is_empty() {
+        // Collect data from all collectors
-            error!("No metrics collected during force collection!");
+        for collector in &self.collectors {
-            return Ok(());
+            if let Err(e) = collector.collect_structured(&mut agent_data).await {
+                error!("Collector failed: {}", e);
+                // Continue with other collectors even if one fails
+            }
         }
 
-        info!("Force collected and cached {} metrics", metrics.len());
+        // 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);
+        }
 
-        // Process metrics through status manager
+        // Broadcast the structured data via ZMQ
-        self.process_metrics(&metrics).await;
+        if let Err(e) = self.zmq_handler.publish_agent_data(&agent_data).await {
+            error!("Failed to broadcast agent data: {}", e);
+        } else {
+            debug!("Successfully broadcast structured agent data");
+        }
 
         Ok(())
     }
 
-    async fn collect_metrics_only(&mut self) -> Result<()> {
+    /// Check for status changes and send notifications
-        debug!("Starting metric collection cycle (cache only)");
+    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(),
+        };
 
-        // Collect all metrics from all collectors and cache them
+        // Check for status changes
-        let metrics = self.metric_manager.collect_all_metrics().await?;
+        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?;
 
-        if metrics.is_empty() {
+            self.check_and_notify_status_change(
-            debug!("No metrics collected this cycle");
+                "CPU Temperature", 
-            return Ok(());
+                &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?;
         }
 
-        debug!("Collected and cached {} metrics", metrics.len());
+        // Store current status for next comparison
+        self.previous_status = Some(current_status);
+        Ok(())
+    }
 
-        // Process metrics through status manager
+    /// Check individual status change and send notification if degraded
-        self.process_metrics(&metrics).await;
+    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")
+            );
+
+            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(())
     }
 
-    async fn broadcast_all_cached_metrics(&mut self) -> Result<()> {
+    /// Handle incoming commands from dashboard
-        debug!("Broadcasting all cached metrics via ZMQ");
-
-        // Get all cached metrics from the metric manager
-        let mut cached_metrics = self.metric_manager.get_all_cached_metrics().await?;
-
-        // Add the host status summary metric from status manager
-        let host_status_metric = self.host_status_manager.get_host_status_metric();
-        cached_metrics.push(host_status_metric);
-
-        if cached_metrics.is_empty() {
-            debug!("No cached metrics to broadcast");
-            return Ok(());
-        }
-
-        debug!("Broadcasting {} cached metrics (including host status summary)", cached_metrics.len());
-
-        // Create and send message with all cached data
-        let message = MetricMessage::new(self.hostname.clone(), cached_metrics);
-        self.zmq_handler.publish_metrics(&message).await?;
-
-        debug!("Cached metrics broadcasted successfully");
-        Ok(())
-    }
-
-    async fn process_metrics(&mut self, metrics: &[Metric]) {
-        for metric in metrics {
-            self.host_status_manager.process_metric(metric, &mut self.notification_manager, self.metric_manager.get_cache_manager()).await;
-        }
-    }
-
     async fn handle_commands(&mut self) -> Result<()> {
-        // Try to receive commands (non-blocking)
+        // Try to receive a command (non-blocking)
-        match self.zmq_handler.try_receive_command() {
+        if let Ok(Some(command)) = self.zmq_handler.try_receive_command() {
-            Ok(Some(command)) => {
+            info!("Received command: {:?}", 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);
-            }
-        }
-        Ok(())
-    }
 
-    async fn process_command(&mut self, command: AgentCommand) -> Result<()> {
+            match command {
-        match command {
+                AgentCommand::CollectNow => {
-            AgentCommand::CollectNow => {
+                    info!("Received immediate collection request");
-                info!("Processing CollectNow command");
+                    if let Err(e) = self.collect_and_broadcast().await {
-                if let Err(e) = self.collect_metrics_only().await {
+                        error!("Failed to collect on demand: {}", e);
-                    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
-                );
-                // 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
-            }
-            AgentCommand::ServiceControl { service_name, action } => {
-                info!("Processing ServiceControl command: {} {:?}", service_name, action);
-                if let Err(e) = self.handle_service_control(&service_name, &action).await {
-                    error!("Failed to execute service control: {}", e);
-                }
-            }
-            AgentCommand::SystemRebuild { git_url, git_branch, working_dir, api_key_file } => {
-                info!("Processing SystemRebuild command: {} @ {} -> {}", git_url, git_branch, working_dir);
-                if let Err(e) = self.handle_system_rebuild(&git_url, &git_branch, &working_dir, api_key_file.as_deref()).await {
-                    error!("Failed to execute system rebuild: {}", e);
-                }
-            }
-        }
-        Ok(())
-    }
-
-    /// Handle systemd service control commands
-    async fn handle_service_control(&self, service_name: &str, action: &ServiceAction) -> Result<()> {
-        let action_str = match action {
-            ServiceAction::Start => "start",
-            ServiceAction::Stop => "stop", 
-            ServiceAction::Restart => "restart",
-            ServiceAction::Status => "status",
-        };
-
-        info!("Executing systemctl {} {}", action_str, service_name);
-
-        let output = tokio::process::Command::new("sudo")
-            .arg("systemctl")
-            .arg(action_str)
-            .arg(service_name)
-            .output()
-            .await?;
-
-        if output.status.success() {
-            info!("Service {} {} completed successfully", service_name, action_str);
-            if !output.stdout.is_empty() {
-                debug!("stdout: {}", String::from_utf8_lossy(&output.stdout));
-            }
-        } else {
-            let stderr = String::from_utf8_lossy(&output.stderr);
-            error!("Service {} {} failed: {}", service_name, action_str, stderr);
-            return Err(anyhow::anyhow!("systemctl {} {} failed: {}", action_str, service_name, stderr));
-        }
-
-        // Force refresh metrics after service control to update service status
-        if matches!(action, ServiceAction::Start | ServiceAction::Stop | ServiceAction::Restart) {
-            info!("Triggering metric refresh after service control");
-            // Note: We can't call self.collect_metrics_only() here due to borrowing issues
-            // The next metric collection cycle will pick up the changes
-        }
-
-        Ok(())
-    }
-
-    /// Handle NixOS system rebuild commands with git clone approach
-    async fn handle_system_rebuild(&self, git_url: &str, git_branch: &str, working_dir: &str, api_key_file: Option<&str>) -> Result<()> {
-        info!("Starting NixOS system rebuild: {} @ {} -> {}", git_url, git_branch, working_dir);
-
-        // Enable maintenance mode before rebuild
-        let maintenance_file = "/tmp/cm-maintenance";
-        if let Err(e) = tokio::fs::File::create(maintenance_file).await {
-            error!("Failed to create maintenance mode file: {}", e);
-        } else {
-            info!("Maintenance mode enabled");
-        }
-
-        // Clone or update repository
-        let git_result = self.ensure_git_repository(git_url, git_branch, working_dir, api_key_file).await;
-        
-        // Execute nixos-rebuild if git operation succeeded
-        let rebuild_result = if git_result.is_ok() {
-            info!("Git repository ready, executing nixos-rebuild");
-            tokio::process::Command::new("sudo")
-                .arg("/run/current-system/sw/bin/nixos-rebuild")
-                .arg("switch")
-                .arg("--option")
-                .arg("sandbox")
-                .arg("false")
-                .arg("--flake")
-                .arg(".")
-                .current_dir(working_dir)
-                .output()
-                .await
-        } else {
-            return git_result.and_then(|_| unreachable!());
-        };
-
-        // Always try to remove maintenance mode file
-        if let Err(e) = tokio::fs::remove_file(maintenance_file).await {
-            if e.kind() != std::io::ErrorKind::NotFound {
-                error!("Failed to remove maintenance mode file: {}", e);
-            }
-        } else {
-            info!("Maintenance mode disabled");
-        }
-
-        // Check rebuild result
-        match rebuild_result {
-            Ok(output) => {
-                if output.status.success() {
-                    info!("NixOS rebuild completed successfully");
-                    if !output.stdout.is_empty() {
-                        debug!("rebuild stdout: {}", String::from_utf8_lossy(&output.stdout));
-                    }
-                } else {
-                    let stderr = String::from_utf8_lossy(&output.stderr);
-                    error!("NixOS rebuild failed: {}", stderr);
-                    return Err(anyhow::anyhow!("nixos-rebuild failed: {}", stderr));
-                }
-            }
-            Err(e) => {
-                error!("Failed to execute nixos-rebuild: {}", e);
-                return Err(anyhow::anyhow!("Failed to execute nixos-rebuild: {}", e));
-            }
-        }
-
-        info!("System rebuild completed, triggering metric refresh");
-        Ok(())
-    }
-
-    /// Ensure git repository is cloned and up to date
-    async fn ensure_git_repository(&self, git_url: &str, git_branch: &str, working_dir: &str, api_key_file: Option<&str>) -> Result<()> {
-        use std::path::Path;
-        
-        // Read API key if provided
-        let auth_url = if let Some(key_file) = api_key_file {
-            match tokio::fs::read_to_string(key_file).await {
-                Ok(api_key) => {
-                    let api_key = api_key.trim();
-                    if !api_key.is_empty() {
-                        // Convert https://gitea.cmtec.se/cm/nixosbox.git to https://token@gitea.cmtec.se/cm/nixosbox.git
-                        if git_url.starts_with("https://") {
-                            let url_without_protocol = &git_url[8..]; // Remove "https://"
-                            format!("https://{}@{}", api_key, url_without_protocol)
-                        } else {
-                            info!("API key provided but URL is not HTTPS, using original URL");
-                            git_url.to_string()
-                        }
-                    } else {
-                        info!("API key file is empty, using original URL");
-                        git_url.to_string()
                     }
                 }
-                Err(e) => {
+                AgentCommand::SetInterval { seconds } => {
-                    info!("Could not read API key file {}: {}, using original URL", key_file, e);
+                    info!("Received interval change request: {}s", seconds);
-                    git_url.to_string()
+                    // Note: This would require more complex handling to update the interval
+                    // For now, just acknowledge
+                }
+                AgentCommand::ToggleCollector { name, enabled } => {
+                    info!("Received collector toggle request: {} -> {}", name, enabled);
+                    // Note: This would require more complex handling to enable/disable collectors
+                    // For now, just acknowledge
+                }
+                AgentCommand::Ping => {
+                    info!("Received ping command");
+                    // Maybe send back a pong or status
                 }
             }
-        } else {
-            git_url.to_string()
-        };
-        
-        let git_dir = Path::new(working_dir).join(".git");
-        
-        if git_dir.exists() {
-            info!("Git repository exists, updating to latest {}", git_branch);
-            
-            // Pull latest changes
-            let output = tokio::process::Command::new("git")
-                .arg("pull")
-                .arg("origin")
-                .arg(git_branch)
-                .current_dir(working_dir)
-                .output()
-                .await?;
-                
-            if !output.status.success() {
-                let stderr = String::from_utf8_lossy(&output.stderr);
-                error!("Git pull failed: {}", stderr);
-                return Err(anyhow::anyhow!("Git pull failed: {}", stderr));
-            }
-            
-            info!("Git repository updated successfully");
-        } else {
-            info!("Cloning git repository from {} (branch: {})", git_url, git_branch);
-            
-            // Clone repository with authentication if available
-            let output = tokio::process::Command::new("git")
-                .arg("clone")
-                .arg("--branch")
-                .arg(git_branch)
-                .arg(&auth_url)  // Use authenticated URL
-                .arg(working_dir)
-                .output()
-                .await?;
-                
-            if !output.status.success() {
-                let stderr = String::from_utf8_lossy(&output.stderr);
-                error!("Git clone failed: {}", stderr);
-                return Err(anyhow::anyhow!("Git clone failed: {}", stderr));
-            }
-            
-            info!("Git repository cloned successfully");
         }
-        
         Ok(())
     }
-}
+
+}

agent/src/cache/cached_metric.rs

@@ -1,10 +0,0 @@
-use cm_dashboard_shared::Metric;
-use std::time::Instant;
-
-/// A cached metric with metadata
-#[derive(Debug, Clone)]
-pub struct CachedMetric {
-    pub metric: Metric,
-    pub collected_at: Instant,
-    pub access_count: u64,
-}

agent/src/cache/manager.rs

@@ -1,33 +0,0 @@
-use super::ConfigurableCache;
-use cm_dashboard_shared::{CacheConfig, Metric};
-use std::sync::Arc;
-use tracing::info;
-
-/// Manages metric caching with background tasks
-pub struct MetricCacheManager {
-    cache: Arc<ConfigurableCache>,
-}
-
-impl MetricCacheManager {
-    pub fn new(config: CacheConfig) -> Self {
-        let cache = Arc::new(ConfigurableCache::new(config.clone()));
-
-        Self { cache }
-    }
-
-    /// Start background cache management tasks
-    pub async fn start_background_tasks(&self) {
-        // Temporarily disabled to isolate CPU usage issue
-        info!("Cache manager background tasks disabled for debugging");
-    }
-
-    /// Store metric in cache
-    pub async fn cache_metric(&self, metric: Metric) {
-        self.cache.store_metric(metric).await;
-    }
-
-    /// Get all cached metrics (including expired ones) for broadcasting
-    pub async fn get_all_cached_metrics(&self) -> Vec<Metric> {
-        self.cache.get_all_cached_metrics().await
-    }
-}

agent/src/cache/mod.rs

@@ -1,129 +0,0 @@
-use cm_dashboard_shared::{CacheConfig, Metric};
-use std::collections::HashMap;
-use std::fs;
-use std::path::Path;
-use std::sync::Arc;
-use tokio::sync::RwLock;
-use tracing::{info, warn, error};
-
-/// Simple persistent cache for metrics
-pub struct SimpleCache {
-    metrics: RwLock<HashMap<String, Metric>>,
-    persist_path: String,
-}
-
-impl SimpleCache {
-    pub fn new(config: CacheConfig) -> Self {
-        let cache = Self {
-            metrics: RwLock::new(HashMap::new()),
-            persist_path: config.persist_path,
-        };
-        
-        // Clear cache file on startup to ensure fresh data
-        cache.clear_cache_file();
-        cache
-    }
-
-    /// Store metric in cache
-    pub async fn store_metric(&self, metric: Metric) {
-        let mut metrics = self.metrics.write().await;
-        metrics.insert(metric.name.clone(), metric);
-    }
-
-    /// Get all cached metrics
-    pub async fn get_all_cached_metrics(&self) -> Vec<Metric> {
-        let metrics = self.metrics.read().await;
-        metrics.values().cloned().collect()
-    }
-
-    /// Save cache to disk
-    pub async fn save_to_disk(&self) {
-        let metrics = self.metrics.read().await;
-        
-        // Create directory if needed
-        if let Some(parent) = Path::new(&self.persist_path).parent() {
-            if let Err(e) = fs::create_dir_all(parent) {
-                warn!("Failed to create cache directory {}: {}", parent.display(), e);
-                return;
-            }
-        }
-
-        // Serialize and save
-        match serde_json::to_string_pretty(&*metrics) {
-            Ok(json) => {
-                if let Err(e) = fs::write(&self.persist_path, json) {
-                    error!("Failed to save cache to {}: {}", self.persist_path, e);
-                }
-            }
-            Err(e) => {
-                error!("Failed to serialize cache: {}", e);
-            }
-        }
-    }
-
-    /// Load cache from disk
-    fn load_from_disk(&self) {
-        match fs::read_to_string(&self.persist_path) {
-            Ok(content) => {
-                match serde_json::from_str::<HashMap<String, Metric>>(&content) {
-                    Ok(loaded_metrics) => {
-                        if let Ok(mut metrics) = self.metrics.try_write() {
-                            *metrics = loaded_metrics;
-                            info!("Loaded {} metrics from cache", metrics.len());
-                        }
-                    }
-                    Err(e) => {
-                        warn!("Failed to parse cache file {}: {}", self.persist_path, e);
-                    }
-                }
-            }
-            Err(_) => {
-                info!("No cache file found at {}, starting fresh", self.persist_path);
-            }
-        }
-    }
-
-    /// Clear cache file on startup to ensure fresh data
-    fn clear_cache_file(&self) {
-        if Path::new(&self.persist_path).exists() {
-            match fs::remove_file(&self.persist_path) {
-                Ok(_) => info!("Cleared cache file {} on startup", self.persist_path),
-                Err(e) => warn!("Failed to clear cache file {}: {}", self.persist_path, e),
-            }
-        }
-    }
-}
-
-
-#[derive(Clone)]
-pub struct MetricCacheManager {
-    cache: Arc<SimpleCache>,
-}
-
-impl MetricCacheManager {
-    pub fn new(config: CacheConfig) -> Self {
-        Self {
-            cache: Arc::new(SimpleCache::new(config)),
-        }
-    }
-
-    pub async fn store_metric(&self, metric: Metric) {
-        self.cache.store_metric(metric).await;
-    }
-
-    pub async fn cache_metric(&self, metric: Metric) {
-        self.store_metric(metric).await;
-    }
-
-    pub async fn start_background_tasks(&self) {
-        // No background tasks needed for simple cache
-    }
-
-    pub async fn get_all_cached_metrics(&self) -> Result<Vec<Metric>, anyhow::Error> {
-        Ok(self.cache.get_all_cached_metrics().await)
-    }
-
-    pub async fn save_to_disk(&self) {
-        self.cache.save_to_disk().await;
-    }
-}

agent/src/collectors/backup.rs

@@ -1,407 +1,120 @@
 use async_trait::async_trait;
-use chrono::Utc;
+use cm_dashboard_shared::{AgentData, BackupData, BackupDiskData};
-use cm_dashboard_shared::{Metric, MetricValue, Status, StatusTracker};
 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
+/// Backup collector that reads backup status from TOML files with structured data output
-#[derive(Debug, Clone)]
 pub struct BackupCollector {
-    pub backup_status_file: String,
+    /// Path to backup status file
-    pub max_age_hours: u64,
+    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
+            status_file_path: "/var/lib/backup/backup-status.toml".to_string(),
-                .unwrap_or_else(|| "/var/lib/backup/backup-status.toml".to_string()),
-            max_age_hours,
         }
     }
 
+    /// Read backup status from TOML file
     async fn read_backup_status(&self) -> Result<Option<BackupStatusToml>, CollectorError> {
-        // Check if backup status file exists
+        if !Path::new(&self.status_file_path).exists() {
-        if !std::path::Path::new(&self.backup_status_file).exists() {
+            debug!("Backup status file not found: {}", self.status_file_path);
-            return Ok(None); // File doesn't exist, but this is not an error
+            return Ok(None);
         }
 
-        let content = fs::read_to_string(&self.backup_status_file)
+        let content = fs::read_to_string(&self.status_file_path)
-            .await
             .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 {
+        let status: BackupStatusToml = toml::from_str(&content)
-            value: "backup status TOML".to_string(),
+            .map_err(|e| CollectorError::Parse {
-            error: e.to_string(),
+                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 {
+    /// Convert BackupStatusToml to BackupData and populate AgentData
-        // Parse the start time to check age - handle both RFC3339 and local timestamp formats
+    async fn populate_backup_data(&self, agent_data: &mut AgentData) -> Result<(), CollectorError> {
-        let start_time = match chrono::DateTime::parse_from_rfc3339(&backup_status.start_time) {
+        if let Some(backup_status) = self.read_backup_status().await? {
-            Ok(dt) => dt.with_timezone(&Utc),
+            // Use raw start_time string from TOML
-            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;
-                    }
-                }
-            }
-        };
 
-        let hours_since_backup = Utc::now().signed_duration_since(start_time).num_hours();
+            // 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
+            };
 
-        // Check overall backup status
+            // Calculate total repository size from services
-        match backup_status.status.as_str() {
+            let total_size_gb = backup_status.services
-            "success" => {
+                .values()
-                if hours_since_backup > self.max_age_hours as i64 {
+                .map(|service| service.repo_size_bytes as f32 / (1024.0 * 1024.0 * 1024.0))
-                    Status::Warning // Backup too old
+                .sum::<f32>();
-                } else {
+
-                    Status::Ok
+            let backup_data = BackupData {
-                }
+                status: backup_status.status,
-            }
+                total_size_gb: Some(total_size_gb),
-            "failed" => Status::Critical,
+                repository_health: Some("ok".to_string()), // Derive from status if needed
-            "running" => Status::Ok, // Currently running is OK
+                repository_disk,
-            _ => Status::Unknown,
+                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 {
+            // 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 {
+        Ok(())
-        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)
     }
 }
 
 #[async_trait]
 impl Collector for BackupCollector {
-    fn name(&self) -> &str {
+    async fn collect_structured(&self, agent_data: &mut AgentData) -> Result<(), CollectorError> {
-        "backup"
+        debug!("Collecting backup status");
-    }
+        self.populate_backup_data(agent_data).await
-
-    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::Pending => "pending".to_string(),
-                Status::Warning => "warning".to_string(),
-                Status::Critical => "critical".to_string(),
-                Status::Unknown => "unknown".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::Pending => "pending".to_string(),
-                    Status::Warning => "warning".to_string(),
-                    Status::Critical => "critical".to_string(),
-                    Status::Unknown => "unknown".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,
-            });
-        }
-
-        // 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)
     }
 }
 
 /// TOML structure for backup status file
-#[derive(Debug, Clone, Deserialize, Serialize)]
+#[derive(Debug, Clone, Serialize, Deserialize)]
-pub struct BackupStatusToml {
+struct BackupStatusToml {
     pub backup_name: String,
     pub start_time: String,
     pub current_time: String,
@@ -411,11 +124,12 @@ pub struct BackupStatusToml {
     pub disk_space: Option<DiskSpace>,
     pub disk_product_name: Option<String>,
     pub disk_serial_number: Option<String>,
+    pub disk_wear_percent: Option<f32>,
     pub services: HashMap<String, ServiceStatus>,
 }
 
-#[derive(Debug, Clone, Deserialize, Serialize)]
+#[derive(Debug, Clone, Serialize, Deserialize)]
-pub struct DiskSpace {
+struct DiskSpace {
     pub total_bytes: u64,
     pub used_bytes: u64,
     pub available_bytes: u64,
@@ -423,16 +137,13 @@ 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)]
+#[derive(Debug, Clone, Serialize, Deserialize)]
-pub struct ServiceStatus {
+struct ServiceStatus {
     pub status: String,
     pub exit_code: i64,
     pub repo_path: String,
     pub archive_count: i64,
     pub repo_size_bytes: u64,
-}
+}

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;
 
@@ -15,7 +15,6 @@ use crate::config::CpuConfig;
 /// - No process spawning
 /// - <0.1ms collection time target
 pub struct CpuCollector {
-    name: String,
     load_thresholds: HysteresisThresholds,
     temperature_thresholds: HysteresisThresholds,
 }
@@ -34,25 +33,36 @@ impl CpuCollector {
         );
         
         Self {
-            name: "cpu".to_string(),
             load_thresholds,
             temperature_thresholds,
         }
     }
 
-    /// Calculate CPU load status using hysteresis thresholds
+    /// Calculate CPU load status using thresholds
-    fn calculate_load_status(&self, metric_name: &str, load: f32, status_tracker: &mut StatusTracker) -> Status {
+    fn calculate_load_status(&self, load: f32) -> Status {
-        status_tracker.calculate_with_hysteresis(metric_name, load, &self.load_thresholds)
+        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
+    /// Calculate CPU temperature status using thresholds
-    fn calculate_temperature_status(&self, metric_name: &str, temp: f32, status_tracker: &mut StatusTracker) -> Status {
+    fn calculate_temperature_status(&self, temp: f32) -> Status {
-        status_tracker.calculate_with_hysteresis(metric_name, temp, &self.temperature_thresholds)
+        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();
 
@@ -67,53 +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
+        // Populate CPU data directly
-        let load_1min_status = Status::Ok;  // No alerting on 1min
+        agent_data.system.cpu.load_1min = load_1min;
-        let load_5min_status = self.calculate_load_status(registry::CPU_LOAD_5MIN, load_5min, status_tracker);  // Only 5min triggers alerts
+        agent_data.system.cpu.load_5min = load_5min;
-        let load_15min_status = Status::Ok;  // No alerting on 15min
+        agent_data.system.cpu.load_15min = load_15min;
 
-        Ok(vec![
+        Ok(())
-            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()),
-        ])
     }
 
-    /// Collect CPU temperature from thermal zones
+    /// Collect CPU temperature and populate AgentData
-    /// Prioritizes x86_pkg_temp over generic thermal zones (legacy behavior)
+    /// Prioritizes x86_pkg_temp over generic thermal zones
-    async fn collect_temperature(&self, status_tracker: &mut StatusTracker) -> Result<Option<Metric>, CollectorError> {
+    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);
+            agent_data.system.cpu.temperature_celsius = Some(temp_celsius);
-
+            return Ok(());
-            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()),
-            ));
         }
 
         // Fallback: try other thermal zones
@@ -121,22 +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);
+                agent_data.system.cpu.temperature_celsius = Some(temp_celsius);
-
+                return Ok(());
-                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()),
-                ));
             }
         }
 
         debug!("No CPU temperature sensors found");
-        Ok(None)
+        // Leave temperature as None if not available
+        Ok(())
     }
 
     /// Read temperature from thermal zone efficiently
@@ -145,24 +119,16 @@ impl CpuCollector {
         utils::parse_u64(content.trim())
     }
 
-    /// Collect CPU frequency from /proc/cpuinfo or scaling governor
+    /// Collect CPU frequency and populate AgentData
-    async fn collect_frequency(&self) -> Result<Option<Metric>, CollectorError> {
+    async fn collect_frequency(&self, agent_data: &mut AgentData) -> Result<(), 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;
-
+                agent_data.system.cpu.frequency_mhz = freq_mhz;
-                return Ok(Some(
+                return Ok(());
-                    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()),
-                ));
             }
         }
 
@@ -172,17 +138,8 @@ impl CpuCollector {
                 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(
+                            agent_data.system.cpu.frequency_mhz = freq_mhz;
-                                Metric::new(
+                            return Ok(());
-                                    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
@@ -191,41 +148,28 @@ impl CpuCollector {
         }
 
         debug!("CPU frequency not available");
-        Ok(None)
+        // Leave frequency as 0.0 if not available
+        Ok(())
     }
 }
 
 #[async_trait]
 impl Collector for CpuCollector {
-    fn name(&self) -> &str {
+    async fn collect_structured(&self, agent_data: &mut AgentData) -> Result<(), CollectorError> {
-        &self.name
-    }
-
-    async fn collect(&self, status_tracker: &mut StatusTracker) -> Result<Vec<Metric>, 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? {
+        self.collect_temperature(agent_data).await?;
-            metrics.push(temp_metric);
-        }
 
         // Collect frequency (optional)
-        if let Some(freq_metric) = self.collect_frequency().await? {
+        self.collect_frequency(agent_data).await?;
-            metrics.push(freq_metric);
-        }
 
         let duration = start.elapsed();
-        debug!(
+        debug!("CPU collection completed in {:?}", duration);
-            "CPU collection completed in {:?} with {} metrics",
-            duration,
-            metrics.len()
-        );
 
         // Efficiency check: warn if collection takes too long
         if duration.as_millis() > 1 {
@@ -235,10 +179,14 @@ impl Collector for CpuCollector {
             );
         }
 
-        // Store performance metrics
+        // Calculate status using thresholds
-        // Performance tracking handled by cache system
+        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

@@ -1,396 +1,682 @@
 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;
 use std::time::Instant;
+use std::collections::HashMap;
 use tracing::debug;
 
 use super::{Collector, CollectorError};
 
-/// Information about a storage pool (mount point with underlying drives)
+/// Storage collector with clean architecture and structured data output
-#[derive(Debug, Clone)]
-struct StoragePool {
-    name: String,            // e.g., "steampool", "root"
-    mount_point: String,     // e.g., "/mnt/steampool", "/"
-    filesystem: String,      // e.g., "mergerfs", "ext4", "zfs", "btrfs"
-    storage_type: String,    // e.g., "mergerfs", "single", "raid", "zfs"
-    size: String,            // e.g., "2.5TB"
-    used: String,            // e.g., "2.1TB"
-    available: String,       // e.g., "400GB"
-    usage_percent: f32,      // e.g., 85.0
-    underlying_drives: Vec<DriveInfo>, // Individual physical drives
-}
-
-/// Information about an individual physical drive
-#[derive(Debug, Clone)]
-struct DriveInfo {
-    device: String,          // e.g., "sda", "nvme0n1"
-    health_status: String,   // e.g., "PASSED", "FAILED"
-    temperature: Option<f32>, // e.g., 45.0°C
-    wear_level: Option<f32>, // e.g., 12.0% (for SSDs)
-}
-
-/// Disk usage collector for monitoring filesystem sizes
 pub struct DiskCollector {
     config: DiskConfig,
     temperature_thresholds: HysteresisThresholds,
-    detected_devices: std::collections::HashMap<String, Vec<String>>, // mount_point -> devices
+}
+
+/// A physical drive with its filesystems
+#[derive(Debug, Clone)]
+struct PhysicalDrive {
+    name: String,                        // e.g., "nvme0n1", "sda"
+    health: String,                      // SMART health status
+    filesystems: Vec<Filesystem>,        // mounted filesystems on this drive
+}
+
+/// A filesystem mounted on a drive
+#[derive(Debug, Clone)]
+struct Filesystem {
+    mount_point: String,             // e.g., "/", "/boot"
+    usage_percent: f32,              // Usage percentage
+    used_bytes: u64,                 // Used bytes
+    total_bytes: u64,                // Total bytes
+}
+
+/// MergerFS pool
+#[derive(Debug, Clone)]
+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
+}
+
+/// 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 {
-        // Create hysteresis thresholds for disk temperature
+        let temperature_thresholds = HysteresisThresholds::new(
-        let temperature_thresholds = HysteresisThresholds::with_custom_gaps(
+            config.temperature_warning_celsius,
-            60.0, // warning at 60°C
+            config.temperature_critical_celsius,
-            5.0,  // 5°C gap for recovery
-            70.0, // critical at 70°C  
-            5.0,  // 5°C gap for recovery
         );
         
-        // Detect devices for all configured filesystems at startup
+        Self {
-        let mut detected_devices = std::collections::HashMap::new();
-        for fs_config in &config.filesystems {
-            if fs_config.monitor {
-                if let Ok(devices) = Self::detect_device_for_mount_point_static(&fs_config.mount_point) {
-                    detected_devices.insert(fs_config.mount_point.clone(), devices);
-                }
-            }
-        }
-        
-        Self { 
             config,
             temperature_thresholds,
-            detected_devices,
         }
     }
 
-    /// Calculate disk temperature status using hysteresis thresholds
+    /// Collect all storage data and populate AgentData
-    fn calculate_temperature_status(&self, metric_name: &str, temperature: f32, status_tracker: &mut StatusTracker) -> Status {
+    async fn collect_storage_data(&self, agent_data: &mut AgentData) -> Result<(), CollectorError> {
-        status_tracker.calculate_with_hysteresis(metric_name, temperature, &self.temperature_thresholds)
+        let start_time = Instant::now();
+        debug!("Starting clean storage collection");
+
+        // 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 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 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 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),
+        })?;
+        
+        // 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(())
     }
 
+    /// Get block devices and their mount points using lsblk
+    async fn get_mount_devices(&self) -> Result<HashMap<String, String>, CollectorError> {
+        let output = Command::new("lsblk")
+            .args(&["-rn", "-o", "NAME,MOUNTPOINT"])
+            .output()
+            .map_err(|e| CollectorError::SystemRead {
+                path: "block devices".to_string(),
+                error: e.to_string(),
+            })?;
 
-    /// Get configured storage pools with individual drive information
+        let mut mount_devices = HashMap::new();
-    fn get_configured_storage_pools(&self) -> Result<Vec<StoragePool>> {
+        for line in String::from_utf8_lossy(&output.stdout).lines() {
-        let mut storage_pools = Vec::new();
+            let parts: Vec<&str> = line.split_whitespace().collect();
-
+            if parts.len() >= 2 {
-        for fs_config in &self.config.filesystems {
+                let device_name = parts[0];
-            if !fs_config.monitor {
+                let mount_point = parts[1];
-                continue;
+                
+                // Skip swap partitions and unmounted devices
+                if mount_point == "[SWAP]" || mount_point.is_empty() {
+                    continue;
+                }
+                
+                // Convert device name to full path
+                let device_path = format!("/dev/{}", device_name);
+                mount_devices.insert(mount_point.to_string(), device_path);
             }
+        }
 
-            // Get filesystem stats for the mount point
+        debug!("Found {} mounted block devices", mount_devices.len());
-            match self.get_filesystem_info(&fs_config.mount_point) {
+        Ok(mount_devices)
-                Ok((total_bytes, used_bytes)) => {
+    }
-                    let available_bytes = total_bytes - used_bytes;
-                    let usage_percent = if total_bytes > 0 {
-                        (used_bytes as f64 / total_bytes as f64) * 100.0
-                    } else {
-                        0.0
-                    };
 
-                    // Convert bytes to human-readable format
+    /// Use df to get filesystem usage for mount points
-                    let size = self.bytes_to_human_readable(total_bytes);
+    fn get_filesystem_usage(&self, mount_devices: &HashMap<String, String>) -> anyhow::Result<HashMap<String, (u64, u64)>> {
-                    let used = self.bytes_to_human_readable(used_bytes);
+        let mut filesystem_usage = HashMap::new();
-                    let available = self.bytes_to_human_readable(available_bytes);
+        
-
+        for mount_point in mount_devices.keys() {
-                    // Get individual drive information using pre-detected devices
+            match self.get_filesystem_info(mount_point) {
-                    let device_names = self.detected_devices.get(&fs_config.mount_point).cloned().unwrap_or_default();
+                Ok((total, used)) => {
-                    let underlying_drives = self.get_drive_info_for_devices(&device_names)?;
+                    filesystem_usage.insert(mount_point.clone(), (total, used));
-
-                    storage_pools.push(StoragePool {
-                        name: fs_config.name.clone(),
-                        mount_point: fs_config.mount_point.clone(),
-                        filesystem: fs_config.fs_type.clone(),
-                        storage_type: fs_config.storage_type.clone(),
-                        size,
-                        used,
-                        available,
-                        usage_percent: usage_percent as f32,
-                        underlying_drives,
-                    });
-
-                    debug!(
-                        "Storage pool '{}' ({}) at {} with {} detected drives",
-                        fs_config.name, fs_config.storage_type, fs_config.mount_point, device_names.len()
-                    );
                 }
                 Err(e) => {
-                    debug!(
+                    debug!("Failed to get filesystem info for {}: {}", mount_point, e);
-                        "Failed to get filesystem info for storage pool '{}': {}",
-                        fs_config.name, e
-                    );
                 }
             }
         }
 
-        Ok(storage_pools)
+        Ok(filesystem_usage)
     }
 
-    /// Get drive information for a list of device names
+    /// Add filesystem usage for MergerFS mount points that aren't in lsblk
-    fn get_drive_info_for_devices(&self, device_names: &[String]) -> Result<Vec<DriveInfo>> {
+    fn add_mergerfs_filesystem_usage(&self, filesystem_usage: &mut HashMap<String, (u64, u64)>) -> anyhow::Result<()> {
-        let mut drives = Vec::new();
+        let mounts_content = std::fs::read_to_string("/proc/mounts")
+            .map_err(|e| anyhow::anyhow!("Failed to read /proc/mounts: {}", e))?;
         
-        for device_name in device_names {
+        for line in mounts_content.lines() {
-            let device_path = format!("/dev/{}", device_name);
-            
-            // Get SMART data for this drive
-            let (health_status, temperature, wear_level) = self.get_smart_data(&device_path);
-            
-            drives.push(DriveInfo {
-                device: device_name.clone(),
-                health_status: health_status.clone(),
-                temperature,
-                wear_level,
-            });
-            
-            debug!(
-                "Drive info for {}: health={}, temp={:?}°C, wear={:?}%",
-                device_name, health_status, temperature, wear_level
-            );
-        }
-        
-        Ok(drives)
-    }
-
-    /// Get SMART data for a drive (health, temperature, wear level)
-    fn get_smart_data(&self, device_path: &str) -> (String, Option<f32>, Option<f32>) {
-        // Try to get SMART data using smartctl
-        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 (look for various temperature indicators)
-                let temperature = self.parse_temperature_from_smart(&stdout);
-                
-                // Parse wear level (for SSDs)
-                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() {
-            // Look for temperature in various formats
-            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 drives might show temperature differently
-            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 (SSD wear leveling)
-    fn parse_wear_level_from_smart(&self, smart_output: &str) -> Option<f32> {
-        for line in smart_output.lines() {
-            // Look for wear leveling indicators
-            if line.contains("Wear_Leveling_Count") || line.contains("Media_Wearout_Indicator") {
-                let parts: Vec<&str> = line.split_whitespace().collect();
-                if parts.len() >= 10 {
-                    if let Ok(wear) = parts[9].parse::<f32>() {
-                        return Some(100.0 - wear); // Convert to percentage used
-                    }
-                }
-            }
-            // NVMe drives might show percentage used directly
-            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);
-                        }
-                    }
-                }
-            }
-        }
-        None
-    }
-
-    /// 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])
-        }
-    }
-
-    /// Detect device backing a mount point using lsblk (static version for startup)
-    fn detect_device_for_mount_point_static(mount_point: &str) -> Result<Vec<String>> {
-        let output = Command::new("lsblk")
-            .args(&["-n", "-o", "NAME,MOUNTPOINT"])
-            .output()?;
-        
-        if !output.status.success() {
-            return Ok(Vec::new());
-        }
-        
-        let output_str = String::from_utf8_lossy(&output.stdout);
-        
-        for line in output_str.lines() {
             let parts: Vec<&str> = line.split_whitespace().collect();
-            if parts.len() >= 2 && parts[1] == mount_point {
+            if parts.len() >= 3 && parts[2] == "fuse.mergerfs" {
-                // Remove tree symbols and extract device name (e.g., "├─nvme0n1p2" -> "nvme0n1p2")
+                let mount_point = parts[1].to_string();
-                let device_name = parts[0]
-                    .trim_start_matches('├')
-                    .trim_start_matches('└')
-                    .trim_start_matches('─')
-                    .trim();
                 
-                // Extract base device name (e.g., "nvme0n1p2" -> "nvme0n1")
+                // Only add if we don't already have usage data for this mount point
-                if let Some(base_device) = Self::extract_base_device(device_name) {
+                if !filesystem_usage.contains_key(&mount_point) {
-                    return Ok(vec![base_device]);
+                    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));
+                    }
                 }
             }
         }
         
-        Ok(Vec::new())
+        Ok(())
     }
 
-    /// Extract base device name from partition (e.g., "nvme0n1p2" -> "nvme0n1", "sda1" -> "sda")
+    /// Get filesystem info for a single mount point
-    fn extract_base_device(device_name: &str) -> Option<String> {
+    fn get_filesystem_info(&self, mount_point: &str) -> Result<(u64, u64), CollectorError> {
-        // Handle NVMe devices (nvme0n1p1 -> nvme0n1)
-        if device_name.starts_with("nvme") {
-            if let Some(p_pos) = device_name.find('p') {
-                return Some(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 Some(chars[..end_idx].iter().collect());
-            }
-        }
-        
-        // If no partition detected, return as-is
-        Some(device_name.to_string())
-    }
-
-    /// Get directory size using du command (efficient for single directory)
-    fn get_directory_size(&self, path: &str) -> Result<u64> {
-        let output = Command::new("du")
-            .arg("-s")
-            .arg("--block-size=1")
-            .arg(path)
-            .output()?;
-
-        // du returns success even with permission denied warnings in stderr
-        // We only care if the command completely failed or produced no stdout
-        let output_str = String::from_utf8(output.stdout)?;
-
-        if output_str.trim().is_empty() {
-            return Err(anyhow::anyhow!(
-                "du command produced no output for {}",
-                path
-            ));
-        }
-
-        let size_str = output_str
-            .split_whitespace()
-            .next()
-            .ok_or_else(|| anyhow::anyhow!("Failed to parse du output"))?;
-
-        let size_bytes = size_str.parse::<u64>()?;
-        Ok(size_bytes)
-    }
-
-    /// 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")
+            .args(&["--block-size=1", mount_point])
-            .arg(path)
+            .output()
-            .output()?;
+            .map_err(|e| CollectorError::SystemRead {
+                path: format!("df {}", mount_point),
+                error: e.to_string(),
+            })?;
 
-        if !output.status.success() {
+        let output_str = String::from_utf8_lossy(&output.stdout);
-            return Err(anyhow::anyhow!("df command failed for {}", path));
-        }
-
-        let output_str = String::from_utf8(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();
+        // Parse the data line (skip header)
-        if fields.len() < 4 {
+        let parts: Vec<&str> = lines[1].split_whitespace().collect();
-            return Err(anyhow::anyhow!("Unexpected df fields count"));
+        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 total_bytes: u64 = parts[1].parse().map_err(|e| CollectorError::Parse {
-        let used_bytes = fields[2].parse::<u64>()?;
+            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))
     }
 
-    /// Calculate status based on usage percentage
+    /// Detect MergerFS pools from mount data
-    fn calculate_usage_status(&self, used_bytes: u64, total_bytes: u64) -> Status {
+    fn detect_mergerfs_pools(&self, filesystem_usage: &HashMap<String, (u64, u64)>) -> anyhow::Result<Vec<MergerfsPool>> {
-        if total_bytes == 0 {
+        let mounts_content = std::fs::read_to_string("/proc/mounts")
-            return Status::Unknown;
+            .map_err(|e| anyhow::anyhow!("Failed to read /proc/mounts: {}", e))?;
+        let mut pools = Vec::new();
+        
+        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();
+                let device_sources = parts[0]; // e.g., "/mnt/disk1:/mnt/disk2"
+                
+                // Get pool usage
+                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(':')
+                    .map(|s| s.trim().to_string())
+                    .filter(|s| !s.is_empty())
+                    .collect();
+                
+                // Convert numeric references to actual mount points if needed
+                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 {
+                    // Already full paths
+                    raw_paths
+                };
+                
+                // 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)?;
+                all_member_paths.extend(related_parity_paths);
+                
+                // Categorize as data vs parity drives
+                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);
+                        continue;
+                    }
+                };
+                
+                pools.push(MergerfsPool {
+                    name: pool_name,
+                    mount_point,
+                    total_bytes,
+                    used_bytes,
+                    data_drives,
+                    parity_drives,
+                });
+            }
+        }
+        
+        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());
+            }
         }
 
-        let usage_percent = (used_bytes as f64 / total_bytes as f64) * 100.0;
+        // 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);
+            }
+        }
 
-        // Thresholds for disk usage
+        smart_data
+    }
+
+    /// Get SMART data for a single drive
+    async fn get_smart_data(&self, drive_name: &str) -> Result<SmartData, CollectorError> {
+        let output = Command::new("sudo")
+            .args(&["smartctl", "-a", &format!("/dev/{}", drive_name)])
+            .output()
+            .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);
+        let error_str = String::from_utf8_lossy(&output.stderr);
+        
+        // Debug logging for SMART command results
+        debug!("SMART output for {}: status={}, stdout_len={}, stderr={}", 
+            drive_name, output.status, output_str.len(), error_str);
+        
+        if !output.status.success() {
+            debug!("SMART command failed for {}: {}", drive_name, error_str);
+            // 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 {
@@ -400,218 +686,161 @@ impl DiskCollector {
         }
     }
 
-    /// Parse size string (e.g., "120G", "45M") to GB value
+    /// Calculate drive temperature status
-    fn parse_size_to_gb(&self, size_str: &str) -> f32 {
+    fn calculate_temperature_status(&self, temperature: f32) -> Status {
-        let size_str = size_str.trim();
+        self.temperature_thresholds.evaluate(temperature)
-        if size_str.is_empty() || size_str == "-" {
+    }
-            return 0.0;
-        }
 
-        // Extract numeric part and unit
+    /// Calculate drive health status
-        let (num_str, unit) = if let Some(last_char) = size_str.chars().last() {
+    fn calculate_health_status(&self, health: &str) -> Status {
-            if last_char.is_alphabetic() {
+        match health {
-                let num_part = &size_str[..size_str.len() - 1];
+            "PASSED" => Status::Ok,
-                let unit_part = &size_str[size_str.len() - 1..];
+            "FAILED" => Status::Critical,
-                (num_part, unit_part)
+            _ => Status::Unknown,
-            } else {
+        }
-                (size_str, "")
+    }
+
+    /// Discover parity drives that are related to the given data drives
+    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
+        for data_path in data_drives {
+            if let Some(parent_dir) = self.get_parent_directory(data_path) {
+                // Look for parity drives in the same parent directory
+                for (mount_point, _device) in &mount_devices {
+                    if mount_point.contains("parity") && mount_point.starts_with(&parent_dir) {
+                        if !related_parity.contains(mount_point) {
+                            related_parity.push(mount_point.clone());
+                        }
+                    }
+                }
             }
-        } else {
-            (size_str, "")
-        };
-
-        let number: f32 = num_str.parse().unwrap_or(0.0);
-
-        match unit.to_uppercase().as_str() {
-            "T" | "TB" => number * 1024.0,
-            "G" | "GB" => number,
-            "M" | "MB" => number / 1024.0,
-            "K" | "KB" => number / (1024.0 * 1024.0),
-            "B" | "" => number / (1024.0 * 1024.0 * 1024.0),
-            _ => number, // Assume GB if unknown unit
         }
+        
+        Ok(related_parity)
+    }
+    
+    /// Get parent directory of a mount path (e.g., "/mnt/disk1" -> "/mnt")
+    fn get_parent_directory(&self, path: &str) -> Option<String> {
+        if let Some(last_slash) = path.rfind('/') {
+            if last_slash > 0 {
+                return Some(path[..last_slash].to_string());
+            }
+        }
+        None
+    }
+
+    /// Categorize pool member drives as data vs parity
+    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();
+        
+        for path in member_paths {
+            let drive_info = self.get_drive_info_for_path(path)?;
+            
+            // Heuristic: if path contains "parity", it's parity
+            if path.to_lowercase().contains("parity") {
+                parity_drives.push(drive_info);
+            } else {
+                data_drives.push(drive_info);
+            }
+        }
+        
+        Ok((data_drives, parity_drives))
+    }
+
+    /// Get drive information for a mount path
+    fn get_drive_info_for_path(&self, path: &str) -> anyhow::Result<PoolDrive> {
+        // Use lsblk to find the backing device
+        let output = Command::new("lsblk")
+            .args(&["-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();
+        
+        for line in output_str.lines() {
+            let parts: Vec<&str> = line.split_whitespace().collect();
+            if parts.len() >= 2 && parts[1] == path {
+                device = parts[0].to_string();
+                break;
+            }
+        }
+        
+        if device.is_empty() {
+            return Err(anyhow::anyhow!("Could not find device for path {}", path));
+        }
+        
+        // Extract base device name (e.g., "sda1" -> "sda")
+        let base_device = self.extract_base_device(&format!("/dev/{}", 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(PoolDrive {
+            name: base_device,
+            mount_point: path.to_string(),
+            temperature_celsius: temperature,
+        })
+    }
+
+    /// Resolve numeric mergerfs references like "1:2" to actual mount paths
+    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 = 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()
+            .collect();
+        disk_mounts.sort(); // Ensure consistent ordering
+        
+        for num_ref in numeric_refs {
+            if let Ok(index) = num_ref.parse::<usize>() {
+                // Convert 1-based index to 0-based
+                if index > 0 && index <= disk_mounts.len() {
+                    resolved_paths.push(disk_mounts[index - 1].clone());
+                }
+            }
+        }
+        
+        // Fallback: if we couldn't resolve, return the original paths
+        if resolved_paths.is_empty() {
+            resolved_paths = numeric_refs.to_vec();
+        }
+        
+        Ok(resolved_paths)
     }
 }
 
 #[async_trait]
 impl Collector for DiskCollector {
-    fn name(&self) -> &str {
+    async fn collect_structured(&self, agent_data: &mut AgentData) -> Result<(), CollectorError> {
-        "disk"
+        self.collect_storage_data(agent_data).await
     }
-
-    async fn collect(&self, status_tracker: &mut StatusTracker) -> Result<Vec<Metric>, CollectorError> {
-        let start_time = Instant::now();
-        debug!("Collecting storage pool and individual drive metrics");
-
-        let mut metrics = Vec::new();
-
-        // Get configured storage pools with individual drive data
-        let storage_pools = match self.get_configured_storage_pools() {
-            Ok(pools) => {
-                debug!("Found {} storage pools", pools.len());
-                pools
-            }
-            Err(e) => {
-                debug!("Failed to get storage pools: {}", e);
-                Vec::new()
-            }
-        };
-
-        // Generate metrics for each storage pool and its underlying drives
-        for storage_pool in &storage_pools {
-            let timestamp = chrono::Utc::now().timestamp() as u64;
-
-            // Storage pool overall metrics
-            let pool_name = &storage_pool.name;
-            
-            // Parse size strings to get actual values for calculations
-            let size_gb = self.parse_size_to_gb(&storage_pool.size);
-            let used_gb = self.parse_size_to_gb(&storage_pool.used);
-            let avail_gb = self.parse_size_to_gb(&storage_pool.available);
-
-            // Calculate status based on configured thresholds
-            let pool_status = if storage_pool.usage_percent >= self.config.usage_critical_percent {
-                Status::Critical
-            } else if storage_pool.usage_percent >= self.config.usage_warning_percent {
-                Status::Warning
-            } else {
-                Status::Ok
-            };
-
-            // Storage pool info metrics
-            metrics.push(Metric {
-                name: format!("disk_{}_mount_point", pool_name),
-                value: MetricValue::String(storage_pool.mount_point.clone()),
-                unit: None,
-                description: Some(format!("Mount: {}", storage_pool.mount_point)),
-                status: Status::Ok,
-                timestamp,
-            });
-
-            metrics.push(Metric {
-                name: format!("disk_{}_filesystem", pool_name),
-                value: MetricValue::String(storage_pool.filesystem.clone()),
-                unit: None,
-                description: Some(format!("FS: {}", storage_pool.filesystem)),
-                status: Status::Ok,
-                timestamp,
-            });
-
-            metrics.push(Metric {
-                name: format!("disk_{}_storage_type", pool_name),
-                value: MetricValue::String(storage_pool.storage_type.clone()),
-                unit: None,
-                description: Some(format!("Type: {}", storage_pool.storage_type)),
-                status: Status::Ok,
-                timestamp,
-            });
-
-            // Storage pool size metrics
-            metrics.push(Metric {
-                name: format!("disk_{}_total_gb", pool_name),
-                value: MetricValue::Float(size_gb),
-                unit: Some("GB".to_string()),
-                description: Some(format!("Total: {}", storage_pool.size)),
-                status: Status::Ok,
-                timestamp,
-            });
-
-            metrics.push(Metric {
-                name: format!("disk_{}_used_gb", pool_name),
-                value: MetricValue::Float(used_gb),
-                unit: Some("GB".to_string()),
-                description: Some(format!("Used: {}", storage_pool.used)),
-                status: pool_status,
-                timestamp,
-            });
-
-            metrics.push(Metric {
-                name: format!("disk_{}_available_gb", pool_name),
-                value: MetricValue::Float(avail_gb),
-                unit: Some("GB".to_string()),
-                description: Some(format!("Available: {}", storage_pool.available)),
-                status: Status::Ok,
-                timestamp,
-            });
-
-            metrics.push(Metric {
-                name: format!("disk_{}_usage_percent", pool_name),
-                value: MetricValue::Float(storage_pool.usage_percent),
-                unit: Some("%".to_string()),
-                description: Some(format!("Usage: {:.1}%", storage_pool.usage_percent)),
-                status: pool_status,
-                timestamp,
-            });
-
-            // Individual drive metrics for this storage pool
-            for drive in &storage_pool.underlying_drives {
-                // Drive health status
-                metrics.push(Metric {
-                    name: format!("disk_{}_{}_health", pool_name, drive.device),
-                    value: MetricValue::String(drive.health_status.clone()),
-                    unit: None,
-                    description: Some(format!("{}: {}", drive.device, drive.health_status)),
-                    status: if drive.health_status == "PASSED" { Status::Ok } 
-                            else if drive.health_status == "FAILED" { Status::Critical }
-                            else { Status::Unknown },
-                    timestamp,
-                });
-
-                // Drive temperature
-                if let Some(temp) = drive.temperature {
-                    let temp_status = self.calculate_temperature_status(
-                        &format!("disk_{}_{}_temperature", pool_name, drive.device),
-                        temp,
-                        status_tracker
-                    );
-                    
-                    metrics.push(Metric {
-                        name: format!("disk_{}_{}_temperature", pool_name, drive.device),
-                        value: MetricValue::Float(temp),
-                        unit: Some("°C".to_string()),
-                        description: Some(format!("{}: {:.0}°C", drive.device, temp)),
-                        status: temp_status,
-                        timestamp,
-                    });
-                }
-
-                // Drive wear level (for SSDs)
-                if let Some(wear) = drive.wear_level {
-                    let wear_status = if wear >= 90.0 { Status::Critical }
-                                     else if wear >= 80.0 { Status::Warning }
-                                     else { Status::Ok };
-                    
-                    metrics.push(Metric {
-                        name: format!("disk_{}_{}_wear_percent", pool_name, drive.device),
-                        value: MetricValue::Float(wear),
-                        unit: Some("%".to_string()),
-                        description: Some(format!("{}: {:.0}% wear", drive.device, wear)),
-                        status: wear_status,
-                        timestamp,
-                    });
-                }
-            }
-        }
-
-        // Add storage pool count metric
-        metrics.push(Metric {
-            name: "disk_count".to_string(),
-            value: MetricValue::Integer(storage_pools.len() as i64),
-            unit: None,
-            description: Some(format!("Total storage pools: {}", storage_pools.len())),
-            status: Status::Ok,
-            timestamp: chrono::Utc::now().timestamp() as u64,
-        });
-
-
-        let collection_time = start_time.elapsed();
-        debug!(
-            "Multi-disk collection completed in {:?} with {} metrics",
-            collection_time,
-            metrics.len()
-        );
-
-        Ok(metrics)
-    }
-
 }
+
+/// 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/disk_old.rs

@@ -0,0 +1,1327 @@
+use anyhow::Result;
+use async_trait::async_trait;
+use cm_dashboard_shared::{Metric, MetricValue, Status, StatusTracker, HysteresisThresholds};
+
+use crate::config::DiskConfig;
+use std::process::Command;
+use std::time::Instant;
+use std::fs;
+use tracing::debug;
+
+use super::{Collector, CollectorError};
+
+/// Mount point information from /proc/mounts
+#[derive(Debug, Clone)]
+struct MountInfo {
+    device: String,      // e.g., "/dev/sda1" or "/mnt/disk1:/mnt/disk2"
+    mount_point: String, // e.g., "/", "/srv/media"
+    fs_type: String,     // e.g., "ext4", "xfs", "fuse.mergerfs"
+}
+
+/// Auto-discovered storage topology
+#[derive(Debug, Clone)]
+struct StorageTopology {
+    single_disks: Vec<MountInfo>,
+    mergerfs_pools: Vec<MergerfsPoolInfo>,
+}
+
+/// MergerFS pool information
+#[derive(Debug, Clone)]
+struct MergerfsPoolInfo {
+    mount_point: String,          // e.g., "/srv/media"
+    data_members: Vec<String>,    // e.g., ["/mnt/disk1", "/mnt/disk2"]
+    parity_disks: Vec<String>,    // e.g., ["/mnt/parity"]
+}
+
+/// Information about a storage pool (mount point with underlying drives)
+#[derive(Debug, Clone)]
+struct StoragePool {
+    name: String,            // e.g., "steampool", "root"
+    mount_point: String,     // e.g., "/mnt/steampool", "/"
+    filesystem: String,      // e.g., "mergerfs", "ext4", "zfs", "btrfs"
+    pool_type: StoragePoolType, // Enhanced pool type with configuration
+    size: String,            // e.g., "2.5TB"
+    used: String,            // e.g., "2.1TB"
+    available: String,       // e.g., "400GB"
+    usage_percent: f32,      // e.g., 85.0
+    underlying_drives: Vec<DriveInfo>, // Individual physical drives
+    pool_health: PoolHealth, // Overall pool health status
+}
+
+/// Enhanced storage pool types with specific configurations
+#[derive(Debug, Clone)]
+enum StoragePoolType {
+    Single,                    // Traditional single disk (legacy)
+    PhysicalDrive {           // Physical drive with multiple filesystems
+        filesystems: Vec<String>,     // Mount points on this drive
+    },
+    MergerfsPool {            // MergerFS with optional parity
+        data_disks: Vec<String>,      // Member disk names (sdb, sdd)
+        parity_disks: Vec<String>,    // Parity disk names (sdc)
+    },
+    #[allow(dead_code)]
+    RaidArray {               // Hardware RAID (future)
+        level: String,               // "RAID1", "RAID5", etc.
+        member_disks: Vec<String>,   
+        spare_disks: Vec<String>,
+    },
+    #[allow(dead_code)]
+    ZfsPool {                 // ZFS pool (future)
+        pool_name: String,
+        vdevs: Vec<String>,
+    }
+}
+
+/// Pool health status for redundant storage
+#[derive(Debug, Clone, Copy, PartialEq)]
+enum PoolHealth {
+    Healthy,           // All drives OK, parity current
+    Degraded,          // One drive failed or parity outdated, still functional
+    Critical,          // Multiple failures, data at risk
+    #[allow(dead_code)]
+    Rebuilding,        // Actively rebuilding/scrubbing (future: SnapRAID status integration)
+    Unknown,           // Cannot determine status
+}
+
+/// Information about an individual physical drive
+#[derive(Debug, Clone)]
+struct DriveInfo {
+    device: String,          // e.g., "sda", "nvme0n1"
+    health_status: String,   // e.g., "PASSED", "FAILED"
+    temperature: Option<f32>, // e.g., 45.0°C
+    wear_level: Option<f32>, // e.g., 12.0% (for SSDs)
+}
+
+/// Disk usage collector for monitoring filesystem sizes
+pub struct DiskCollector {
+    config: DiskConfig,
+    temperature_thresholds: HysteresisThresholds,
+    detected_devices: std::collections::HashMap<String, Vec<String>>, // mount_point -> devices
+    storage_topology: Option<StorageTopology>, // Auto-discovered storage layout
+}
+
+impl DiskCollector {
+    pub fn new(config: DiskConfig) -> Self {
+        // Create hysteresis thresholds for disk temperature from config
+        let temperature_thresholds = HysteresisThresholds::with_custom_gaps(
+            config.temperature_warning_celsius,
+            5.0,  // 5°C gap for recovery
+            config.temperature_critical_celsius,
+            5.0,  // 5°C gap for recovery
+        );
+        
+        // Perform auto-discovery of storage topology
+        let storage_topology = match Self::auto_discover_storage() {
+            Ok(topology) => {
+                debug!("Auto-discovered storage topology: {} single disks, {} mergerfs pools", 
+                       topology.single_disks.len(), topology.mergerfs_pools.len());
+                Some(topology)
+            }
+            Err(e) => {
+                debug!("Failed to auto-discover storage topology: {}", e);
+                None
+            }
+        };
+        
+        // Detect devices for discovered storage
+        let mut detected_devices = std::collections::HashMap::new();
+        if let Some(ref topology) = storage_topology {
+            // Add single disks
+            for disk in &topology.single_disks {
+                if let Ok(devices) = Self::detect_device_for_mount_point_static(&disk.mount_point) {
+                    detected_devices.insert(disk.mount_point.clone(), devices);
+                }
+            }
+            
+            // Add mergerfs pools and their members
+            for pool in &topology.mergerfs_pools {
+                // Detect devices for the pool itself
+                if let Ok(devices) = Self::detect_device_for_mount_point_static(&pool.mount_point) {
+                    detected_devices.insert(pool.mount_point.clone(), devices);
+                }
+                
+                // Detect devices for member disks
+                for member in &pool.data_members {
+                    if let Ok(devices) = Self::detect_device_for_mount_point_static(member) {
+                        detected_devices.insert(member.clone(), devices);
+                    }
+                }
+                
+                // Detect devices for parity disks
+                for parity in &pool.parity_disks {
+                    if let Ok(devices) = Self::detect_device_for_mount_point_static(parity) {
+                        detected_devices.insert(parity.clone(), devices);
+                    }
+                }
+            }
+        } else {
+            // Fallback: use legacy filesystem config detection
+            for fs_config in &config.filesystems {
+                if fs_config.monitor {
+                    if let Ok(devices) = Self::detect_device_for_mount_point_static(&fs_config.mount_point) {
+                        detected_devices.insert(fs_config.mount_point.clone(), devices);
+                    }
+                }
+            }
+        }
+        
+        Self { 
+            config,
+            temperature_thresholds,
+            detected_devices,
+            storage_topology,
+        }
+    }
+
+    /// Auto-discover storage topology by parsing system information
+    fn auto_discover_storage() -> Result<StorageTopology> {
+        let mounts = Self::parse_proc_mounts()?;
+        let mut single_disks = Vec::new();
+        let mut mergerfs_pools = Vec::new();
+        
+        // Filter out unwanted filesystem types and mount points
+        let exclude_fs_types = ["tmpfs", "devtmpfs", "sysfs", "proc", "cgroup", "cgroup2", "devpts"];
+        let exclude_mount_prefixes = ["/proc", "/sys", "/dev", "/tmp", "/run"];
+        
+        for mount in mounts {
+            // Skip excluded filesystem types
+            if exclude_fs_types.contains(&mount.fs_type.as_str()) {
+                continue;
+            }
+            
+            // Skip excluded mount point prefixes
+            if exclude_mount_prefixes.iter().any(|prefix| mount.mount_point.starts_with(prefix)) {
+                continue;
+            }
+            
+            match mount.fs_type.as_str() {
+                "fuse.mergerfs" => {
+                    // Parse mergerfs pool
+                    let data_members = Self::parse_mergerfs_sources(&mount.device);
+                    let parity_disks = Self::detect_parity_disks(&data_members);
+                    
+                    mergerfs_pools.push(MergerfsPoolInfo {
+                        mount_point: mount.mount_point.clone(),
+                        data_members,
+                        parity_disks,
+                    });
+                    
+                    debug!("Discovered mergerfs pool at {}", mount.mount_point);
+                }
+                "ext4" | "xfs" | "btrfs" | "ntfs" | "vfat" => {
+                    // Check if this mount is part of a mergerfs pool
+                    let is_mergerfs_member = mergerfs_pools.iter()
+                        .any(|pool| pool.data_members.contains(&mount.mount_point) || 
+                                   pool.parity_disks.contains(&mount.mount_point));
+                    
+                    if !is_mergerfs_member {
+                        debug!("Discovered single disk at {}", mount.mount_point);
+                        single_disks.push(mount);
+                    }
+                }
+                _ => {
+                    debug!("Skipping unsupported filesystem type: {}", mount.fs_type);
+                }
+            }
+        }
+        
+        Ok(StorageTopology {
+            single_disks,
+            mergerfs_pools,
+        })
+    }
+
+    /// Parse /proc/mounts to get all mount information
+    fn parse_proc_mounts() -> Result<Vec<MountInfo>> {
+        let mounts_content = fs::read_to_string("/proc/mounts")?;
+        let mut mounts = Vec::new();
+        
+        for line in mounts_content.lines() {
+            let parts: Vec<&str> = line.split_whitespace().collect();
+            if parts.len() >= 3 {
+                mounts.push(MountInfo {
+                    device: parts[0].to_string(),
+                    mount_point: parts[1].to_string(),
+                    fs_type: parts[2].to_string(),
+                });
+            }
+        }
+        
+        Ok(mounts)
+    }
+
+    /// Parse mergerfs source string to extract member paths
+    fn parse_mergerfs_sources(source: &str) -> Vec<String> {
+        // MergerFS source format: "/mnt/disk1:/mnt/disk2:/mnt/disk3"
+        source.split(':')
+            .map(|s| s.trim().to_string())
+            .filter(|s| !s.is_empty())
+            .collect()
+    }
+
+    /// Detect potential parity disks based on data member heuristics
+    fn detect_parity_disks(data_members: &[String]) -> Vec<String> {
+        let mut parity_disks = Vec::new();
+        
+        // Heuristic 1: Look for mount points with "parity" in the name
+        if let Ok(mounts) = Self::parse_proc_mounts() {
+            for mount in mounts {
+                if mount.mount_point.to_lowercase().contains("parity") && 
+                   (mount.fs_type == "xfs" || mount.fs_type == "ext4") {
+                    debug!("Detected parity disk by name: {}", mount.mount_point);
+                    parity_disks.push(mount.mount_point);
+                }
+            }
+        }
+        
+        // Heuristic 2: Look for sequential device pattern
+        // If data members are /mnt/disk1, /mnt/disk2, look for /mnt/disk* that's not in data
+        if parity_disks.is_empty() {
+            if let Some(pattern) = Self::extract_mount_pattern(data_members) {
+                if let Ok(mounts) = Self::parse_proc_mounts() {
+                    for mount in mounts {
+                        if mount.mount_point.starts_with(&pattern) && 
+                           !data_members.contains(&mount.mount_point) &&
+                           (mount.fs_type == "xfs" || mount.fs_type == "ext4") {
+                            debug!("Detected parity disk by pattern: {}", mount.mount_point);
+                            parity_disks.push(mount.mount_point);
+                        }
+                    }
+                }
+            }
+        }
+        
+        parity_disks
+    }
+
+    /// Extract common mount point pattern from data members
+    fn extract_mount_pattern(data_members: &[String]) -> Option<String> {
+        if data_members.is_empty() {
+            return None;
+        }
+        
+        // Find common prefix (e.g., "/mnt/disk" from "/mnt/disk1", "/mnt/disk2")
+        let first = &data_members[0];
+        if let Some(last_slash) = first.rfind('/') {
+            let base = &first[..last_slash + 1]; // Include the slash
+            
+            // Check if all members share this base
+            if data_members.iter().all(|member| member.starts_with(base)) {
+                return Some(base.to_string());
+            }
+        }
+        
+        None
+    }
+
+    /// Calculate disk temperature status using hysteresis thresholds
+    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)
+    }
+
+
+    /// Get storage pools using auto-discovered topology or fallback to configuration
+    fn get_configured_storage_pools(&self) -> Result<Vec<StoragePool>> {
+        if let Some(ref topology) = self.storage_topology {
+            self.get_auto_discovered_storage_pools(topology)
+        } else {
+            self.get_legacy_configured_storage_pools()
+        }
+    }
+
+    /// Get storage pools from auto-discovered topology
+    fn get_auto_discovered_storage_pools(&self, topology: &StorageTopology) -> Result<Vec<StoragePool>> {
+        let mut storage_pools = Vec::new();
+
+        // Group single disks by physical drive for unified pool display
+        let grouped_disks = self.group_filesystems_by_physical_drive(&topology.single_disks)?;
+
+        // Process grouped single disks (each physical drive becomes a pool)
+        for (drive_name, filesystems) in grouped_disks {
+            // Create a unified pool for this physical drive
+            let pool = self.create_physical_drive_pool(&drive_name, &filesystems)?;
+            storage_pools.push(pool);
+        }
+
+        // IMPORTANT: Do not create individual filesystem pools when using auto-discovery
+        // All single disk filesystems should be grouped into physical drive pools above
+
+        // Process mergerfs pools (these remain as logical pools)
+        for pool_info in &topology.mergerfs_pools {
+            if let Ok((total_bytes, used_bytes)) = self.get_filesystem_info(&pool_info.mount_point) {
+                let available_bytes = total_bytes - used_bytes;
+                let usage_percent = if total_bytes > 0 {
+                    (used_bytes as f64 / total_bytes as f64) * 100.0
+                } else { 0.0 };
+
+                let size = self.bytes_to_human_readable(total_bytes);
+                let used = self.bytes_to_human_readable(used_bytes);
+                let available = self.bytes_to_human_readable(available_bytes);
+
+                // Collect all member and parity drives
+                let mut all_drives = Vec::new();
+                
+                // Add data member drives
+                for member in &pool_info.data_members {
+                    if let Some(devices) = self.detected_devices.get(member) {
+                        all_drives.extend(devices.clone());
+                    }
+                }
+                
+                // Add parity drives
+                for parity in &pool_info.parity_disks {
+                    if let Some(devices) = self.detected_devices.get(parity) {
+                        all_drives.extend(devices.clone());
+                    }
+                }
+
+                let underlying_drives = self.get_drive_info_for_devices(&all_drives)?;
+                
+                // Calculate pool health
+                let pool_health = self.calculate_mergerfs_pool_health(&pool_info.data_members, &pool_info.parity_disks, &underlying_drives);
+
+                // Generate pool name from mount point
+                let name = pool_info.mount_point.trim_start_matches('/').replace('/', "_");
+
+                storage_pools.push(StoragePool {
+                    name,
+                    mount_point: pool_info.mount_point.clone(),
+                    filesystem: "fuse.mergerfs".to_string(),
+                    pool_type: StoragePoolType::MergerfsPool {
+                        data_disks: pool_info.data_members.iter()
+                            .filter_map(|member| self.detected_devices.get(member).and_then(|devices| devices.first().cloned()))
+                            .collect(),
+                        parity_disks: pool_info.parity_disks.iter()
+                            .filter_map(|parity| self.detected_devices.get(parity).and_then(|devices| devices.first().cloned()))
+                            .collect(),
+                    },
+                    size,
+                    used,
+                    available,
+                    usage_percent: usage_percent as f32,
+                    underlying_drives,
+                    pool_health,
+                });
+
+                debug!("Auto-discovered mergerfs pool: {} with {} data + {} parity disks", 
+                       pool_info.mount_point, pool_info.data_members.len(), pool_info.parity_disks.len());
+            }
+        }
+
+        Ok(storage_pools)
+    }
+
+    /// Group filesystems by their backing physical drive
+    fn group_filesystems_by_physical_drive(&self, filesystems: &[MountInfo]) -> Result<std::collections::HashMap<String, Vec<MountInfo>>> {
+        let mut grouped = std::collections::HashMap::new();
+        
+        for fs in filesystems {
+            // Get the physical drive name for this mount point
+            if let Some(devices) = self.detected_devices.get(&fs.mount_point) {
+                if let Some(device_name) = devices.first() {
+                    // Extract base drive name from detected device
+                    let drive_name = Self::extract_base_device(device_name)
+                        .unwrap_or_else(|| device_name.clone());
+                    
+                    debug!("Grouping filesystem {} (device: {}) under drive: {}", 
+                           fs.mount_point, device_name, drive_name);
+                    
+                    grouped.entry(drive_name).or_insert_with(Vec::new).push(fs.clone());
+                }
+            }
+        }
+        
+        debug!("Filesystem grouping result: {} drives with filesystems: {:?}", 
+               grouped.len(), 
+               grouped.keys().collect::<Vec<_>>());
+        
+        Ok(grouped)
+    }
+
+    /// Create a physical drive pool containing multiple filesystems
+    fn create_physical_drive_pool(&self, drive_name: &str, filesystems: &[MountInfo]) -> Result<StoragePool> {
+        if filesystems.is_empty() {
+            return Err(anyhow::anyhow!("No filesystems for drive {}", drive_name));
+        }
+
+        // Calculate total usage across all filesystems on this drive
+        let mut total_capacity = 0u64;
+        let mut total_used = 0u64;
+        
+        for fs in filesystems {
+            if let Ok((capacity, used)) = self.get_filesystem_info(&fs.mount_point) {
+                total_capacity += capacity;
+                total_used += used;
+            }
+        }
+
+        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 };
+
+        // Get drive information for SMART data
+        let device_names = vec![drive_name.to_string()];
+        let underlying_drives = self.get_drive_info_for_devices(&device_names)?;
+
+        // Collect filesystem mount points for this drive
+        let filesystem_mount_points: Vec<String> = filesystems.iter()
+            .map(|fs| fs.mount_point.clone())
+            .collect();
+
+        Ok(StoragePool {
+            name: drive_name.to_string(),
+            mount_point: format!("(physical drive)"), // Special marker for physical drives
+            filesystem: "physical".to_string(),
+            pool_type: StoragePoolType::PhysicalDrive {
+                filesystems: filesystem_mount_points,
+            },
+            size: self.bytes_to_human_readable(total_capacity),
+            used: self.bytes_to_human_readable(total_used),
+            available: self.bytes_to_human_readable(total_available),
+            usage_percent: usage_percent as f32,
+            pool_health: if underlying_drives.iter().all(|d| d.health_status == "PASSED") {
+                PoolHealth::Healthy
+            } else {
+                PoolHealth::Critical
+            },
+            underlying_drives,
+        })
+    }
+
+    /// Calculate pool health specifically for mergerfs pools
+    fn calculate_mergerfs_pool_health(&self, data_members: &[String], parity_disks: &[String], drives: &[DriveInfo]) -> PoolHealth {
+        // Get device names for data and parity drives
+        let mut data_device_names = Vec::new();
+        let mut parity_device_names = Vec::new();
+        
+        for member in data_members {
+            if let Some(devices) = self.detected_devices.get(member) {
+                data_device_names.extend(devices.clone());
+            }
+        }
+        
+        for parity in parity_disks {
+            if let Some(devices) = self.detected_devices.get(parity) {
+                parity_device_names.extend(devices.clone());
+            }
+        }
+        
+        let failed_data = drives.iter()
+            .filter(|d| data_device_names.contains(&d.device) && d.health_status != "PASSED")
+            .count();
+        let failed_parity = drives.iter()
+            .filter(|d| parity_device_names.contains(&d.device) && d.health_status != "PASSED")
+            .count();
+        
+        match (failed_data, failed_parity) {
+            (0, 0) => PoolHealth::Healthy,
+            (1, 0) => PoolHealth::Degraded,  // Can recover with parity
+            (0, 1) => PoolHealth::Degraded,  // Lost parity protection
+            _ => PoolHealth::Critical,       // Multiple failures
+        }
+    }
+
+    /// Fallback to legacy configuration-based storage pools  
+    fn get_legacy_configured_storage_pools(&self) -> Result<Vec<StoragePool>> {
+        let mut storage_pools = Vec::new();
+        let mut processed_pools = std::collections::HashSet::new();
+
+        // Legacy implementation: use filesystem configuration
+        for fs_config in &self.config.filesystems {
+            if !fs_config.monitor {
+                continue;
+            }
+
+            let (pool_type, skip_in_single_mode) = self.determine_pool_type(&fs_config.storage_type);
+            
+            // Skip member disks if they're part of a pool
+            if skip_in_single_mode {
+                continue;
+            }
+
+            // Check if this pool was already processed (in case of multiple member disks)
+            let pool_key = match &pool_type {
+                StoragePoolType::MergerfsPool { .. } => {
+                    // For mergerfs pools, use the main mount point
+                    if fs_config.fs_type == "fuse.mergerfs" {
+                        fs_config.mount_point.clone()
+                    } else {
+                        continue; // Skip member disks
+                    }
+                }
+                _ => fs_config.mount_point.clone()
+            };
+
+            if processed_pools.contains(&pool_key) {
+                continue;
+            }
+            processed_pools.insert(pool_key.clone());
+
+            // Get filesystem stats for the mount point
+            match self.get_filesystem_info(&fs_config.mount_point) {
+                Ok((total_bytes, used_bytes)) => {
+                    let available_bytes = total_bytes - used_bytes;
+                    let usage_percent = if total_bytes > 0 {
+                        (used_bytes as f64 / total_bytes as f64) * 100.0
+                    } else { 0.0 };
+
+                    // Convert bytes to human-readable format
+                    let size = self.bytes_to_human_readable(total_bytes);
+                    let used = self.bytes_to_human_readable(used_bytes);
+                    let available = self.bytes_to_human_readable(available_bytes);
+
+                    // Get underlying drives based on pool type
+                    let underlying_drives = self.get_pool_drives(&pool_type, &fs_config.mount_point)?;
+                    
+                    // Calculate pool health
+                    let pool_health = self.calculate_pool_health(&pool_type, &underlying_drives);
+                    let drive_count = underlying_drives.len();
+
+                    storage_pools.push(StoragePool {
+                        name: fs_config.name.clone(),
+                        mount_point: fs_config.mount_point.clone(),
+                        filesystem: fs_config.fs_type.clone(),
+                        pool_type: pool_type.clone(),
+                        size,
+                        used,
+                        available,
+                        usage_percent: usage_percent as f32,
+                        underlying_drives,
+                        pool_health,
+                    });
+
+                    debug!(
+                        "Legacy configured storage pool '{}' ({:?}) at {} with {} drives, health: {:?}",
+                        fs_config.name, pool_type, fs_config.mount_point, drive_count, pool_health
+                    );
+                }
+                Err(e) => {
+                    debug!(
+                        "Failed to get filesystem info for storage pool '{}': {}",
+                        fs_config.name, e
+                    );
+                }
+            }
+        }
+
+        Ok(storage_pools)
+    }
+
+    /// Determine the storage pool type from configuration
+    fn determine_pool_type(&self, storage_type: &str) -> (StoragePoolType, bool) {
+        match storage_type {
+            "single" => (StoragePoolType::Single, false),
+            "mergerfs_pool" | "mergerfs" => {
+                // Find associated member disks
+                let data_disks = self.find_pool_member_disks("mergerfs_member");
+                let parity_disks = self.find_pool_member_disks("parity");
+                (StoragePoolType::MergerfsPool { data_disks, parity_disks }, false)
+            }
+            "mergerfs_member" => (StoragePoolType::Single, true), // Skip, part of pool
+            "parity" => (StoragePoolType::Single, true), // Skip, part of pool  
+            "raid1" | "raid5" | "raid6" => {
+                let member_disks = self.find_pool_member_disks(&format!("{}_member", storage_type));
+                (StoragePoolType::RaidArray { 
+                    level: storage_type.to_uppercase(), 
+                    member_disks, 
+                    spare_disks: Vec::new() 
+                }, false)
+            }
+            _ => (StoragePoolType::Single, false) // Default to single
+        }
+    }
+
+    /// Find member disks for a specific storage type
+    fn find_pool_member_disks(&self, member_type: &str) -> Vec<String> {
+        let mut member_disks = Vec::new();
+        
+        for fs_config in &self.config.filesystems {
+            if fs_config.storage_type == member_type && fs_config.monitor {
+                // Get device names for this mount point
+                if let Some(devices) = self.detected_devices.get(&fs_config.mount_point) {
+                    member_disks.extend(devices.clone());
+                }
+            }
+        }
+        
+        member_disks
+    }
+
+    /// Get drive information for a specific pool type
+    fn get_pool_drives(&self, pool_type: &StoragePoolType, mount_point: &str) -> Result<Vec<DriveInfo>> {
+        match pool_type {
+            StoragePoolType::Single => {
+                // Single disk - use detected devices for this mount point
+                let device_names = self.detected_devices.get(mount_point).cloned().unwrap_or_default();
+                self.get_drive_info_for_devices(&device_names)
+            }
+            StoragePoolType::PhysicalDrive { .. } => {
+                // Physical drive - get drive info for the drive directly (mount_point not used)
+                let device_names = vec![mount_point.to_string()];
+                self.get_drive_info_for_devices(&device_names)
+            }
+            StoragePoolType::MergerfsPool { data_disks, parity_disks } => {
+                // Mergerfs pool - collect all member drives
+                let mut all_disks = data_disks.clone();
+                all_disks.extend(parity_disks.clone());
+                self.get_drive_info_for_devices(&all_disks)
+            }
+            StoragePoolType::RaidArray { member_disks, spare_disks, .. } => {
+                // RAID array - collect member and spare drives
+                let mut all_disks = member_disks.clone();
+                all_disks.extend(spare_disks.clone());
+                self.get_drive_info_for_devices(&all_disks)
+            }
+            StoragePoolType::ZfsPool { .. } => {
+                // ZFS pool - use detected devices (future implementation)
+                let device_names = self.detected_devices.get(mount_point).cloned().unwrap_or_default();
+                self.get_drive_info_for_devices(&device_names)
+            }
+        }
+    }
+
+    /// Calculate pool health based on drive status and pool type
+    fn calculate_pool_health(&self, pool_type: &StoragePoolType, drives: &[DriveInfo]) -> PoolHealth {
+        match pool_type {
+            StoragePoolType::Single => {
+                // Single disk - health is just the drive health
+                if drives.is_empty() {
+                    PoolHealth::Unknown
+                } else if drives.iter().all(|d| d.health_status == "PASSED") {
+                    PoolHealth::Healthy
+                } else {
+                    PoolHealth::Critical
+                }
+            }
+            StoragePoolType::PhysicalDrive { .. } => {
+                // Physical drive - health is just the drive health (similar to Single)
+                if drives.is_empty() {
+                    PoolHealth::Unknown
+                } else if drives.iter().all(|d| d.health_status == "PASSED") {
+                    PoolHealth::Healthy
+                } else {
+                    PoolHealth::Critical
+                }
+            }
+            StoragePoolType::MergerfsPool { data_disks, parity_disks } => {
+                let failed_data = drives.iter()
+                    .filter(|d| data_disks.contains(&d.device) && d.health_status != "PASSED")
+                    .count();
+                let failed_parity = drives.iter()
+                    .filter(|d| parity_disks.contains(&d.device) && d.health_status != "PASSED")
+                    .count();
+                
+                match (failed_data, failed_parity) {
+                    (0, 0) => PoolHealth::Healthy,
+                    (1, 0) => PoolHealth::Degraded,  // Can recover with parity
+                    (0, 1) => PoolHealth::Degraded,  // Lost parity protection
+                    _ => PoolHealth::Critical,       // Multiple failures
+                }
+            }
+            StoragePoolType::RaidArray { level, .. } => {
+                let failed_drives = drives.iter().filter(|d| d.health_status != "PASSED").count();
+                
+                // Basic RAID health logic (can be enhanced per RAID level)
+                match failed_drives {
+                    0 => PoolHealth::Healthy,
+                    1 if level.contains('1') || level.contains('5') || level.contains('6') => PoolHealth::Degraded,
+                    _ => PoolHealth::Critical,
+                }
+            }
+            StoragePoolType::ZfsPool { .. } => {
+                // ZFS health would require zpool status parsing (future)
+                if drives.iter().all(|d| d.health_status == "PASSED") {
+                    PoolHealth::Healthy
+                } else {
+                    PoolHealth::Degraded
+                }
+            }
+        }
+    }
+
+    /// Get drive information for a list of device names
+    fn get_drive_info_for_devices(&self, device_names: &[String]) -> Result<Vec<DriveInfo>> {
+        let mut drives = Vec::new();
+        
+        for device_name in device_names {
+            let device_path = format!("/dev/{}", device_name);
+            
+            // Get SMART data for this drive
+            let (health_status, temperature, wear_level) = self.get_smart_data(&device_path);
+            
+            drives.push(DriveInfo {
+                device: device_name.clone(),
+                health_status: health_status.clone(),
+                temperature,
+                wear_level,
+            });
+            
+            debug!(
+                "Drive info for {}: health={}, temp={:?}°C, wear={:?}%",
+                device_name, health_status, temperature, wear_level
+            );
+        }
+        
+        Ok(drives)
+    }
+
+    /// Get SMART data for a drive (health, temperature, wear level)
+    fn get_smart_data(&self, device_path: &str) -> (String, Option<f32>, Option<f32>) {
+        // Try to get SMART data using smartctl
+        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 (look for various temperature indicators)
+                let temperature = self.parse_temperature_from_smart(&stdout);
+                
+                // Parse wear level (for SSDs)
+                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() {
+            // Look for temperature in various formats
+            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 drives might show temperature differently
+            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 (SSD wear leveling)
+    /// Supports both NVMe and SATA SSD wear indicators
+    fn parse_wear_level_from_smart(&self, smart_output: &str) -> Option<f32> {
+        for line in smart_output.lines() {
+            let line = line.trim();
+            
+            // NVMe drives - direct percentage used
+            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);
+                        }
+                    }
+                }
+            }
+            
+            // SATA SSD attributes - parse SMART table format
+            // Format: ID ATTRIBUTE_NAME FLAG VALUE WORST THRESH TYPE UPDATED WHEN_FAILED RAW_VALUE
+            let parts: Vec<&str> = line.split_whitespace().collect();
+            if parts.len() >= 10 {
+                // SSD Life Left / Percent Lifetime Remaining (higher = less wear)
+                if line.contains("SSD_Life_Left") || line.contains("Percent_Lifetime_Remain") {
+                    if let Ok(remaining) = parts[3].parse::<f32>() { // VALUE column
+                        return Some(100.0 - remaining); // Convert remaining to used
+                    }
+                }
+                
+                // Media Wearout Indicator (lower = more wear, normalize to 0-100)
+                if line.contains("Media_Wearout_Indicator") {
+                    if let Ok(remaining) = parts[3].parse::<f32>() { // VALUE column
+                        return Some(100.0 - remaining); // Convert remaining to used
+                    }
+                }
+                
+                // Wear Leveling Count (higher = less wear, but varies by manufacturer)
+                if line.contains("Wear_Leveling_Count") {
+                    if let Ok(wear_count) = parts[3].parse::<f32>() { // VALUE column
+                        // Most SSDs: 100 = new, decreases with wear
+                        if wear_count <= 100.0 {
+                            return Some(100.0 - wear_count);
+                        }
+                    }
+                }
+                
+                // Total LBAs Written - calculate against typical endurance if available
+                // This is more complex and manufacturer-specific, so we skip for now
+            }
+        }
+        None
+    }
+
+    /// 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)
+    }
+
+    /// Detect device backing a mount point using lsblk (static version for startup)
+    fn detect_device_for_mount_point_static(mount_point: &str) -> Result<Vec<String>> {
+        let output = Command::new("lsblk")
+            .args(&["-n", "-o", "NAME,MOUNTPOINT"])
+            .output()?;
+        
+        if !output.status.success() {
+            return Ok(Vec::new());
+        }
+        
+        let output_str = String::from_utf8_lossy(&output.stdout);
+        
+        for line in output_str.lines() {
+            let parts: Vec<&str> = line.split_whitespace().collect();
+            if parts.len() >= 2 && parts[1] == mount_point {
+                // Remove tree symbols and extract device name (e.g., "├─nvme0n1p2" -> "nvme0n1p2")
+                let device_name = parts[0]
+                    .trim_start_matches('├')
+                    .trim_start_matches('└')
+                    .trim_start_matches('─')
+                    .trim();
+                
+                // Extract base device name (e.g., "nvme0n1p2" -> "nvme0n1")
+                if let Some(base_device) = Self::extract_base_device(device_name) {
+                    return Ok(vec![base_device]);
+                }
+            }
+        }
+        
+        Ok(Vec::new())
+    }
+
+    /// Extract base device name from partition (e.g., "nvme0n1p2" -> "nvme0n1", "sda1" -> "sda")
+    fn extract_base_device(device_name: &str) -> Option<String> {
+        // Handle NVMe devices (nvme0n1p1 -> nvme0n1)
+        if device_name.starts_with("nvme") {
+            if let Some(p_pos) = device_name.find('p') {
+                return Some(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 Some(chars[..end_idx].iter().collect());
+            }
+        }
+        
+        // If no partition detected, return as-is
+        Some(device_name.to_string())
+    }
+
+
+    /// 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()?;
+
+        if !output.status.success() {
+            return Err(anyhow::anyhow!("df command failed for {}", path));
+        }
+
+        let output_str = String::from_utf8(output.stdout)?;
+        let lines: Vec<&str> = output_str.lines().collect();
+
+        if lines.len() < 2 {
+            return Err(anyhow::anyhow!("Unexpected df output format"));
+        }
+
+        let fields: Vec<&str> = lines[1].split_whitespace().collect();
+        if fields.len() < 4 {
+            return Err(anyhow::anyhow!("Unexpected df fields count"));
+        }
+
+        let total_bytes = fields[1].parse::<u64>()?;
+        let used_bytes = fields[2].parse::<u64>()?;
+
+        Ok((total_bytes, used_bytes))
+    }
+
+
+    /// Parse size string (e.g., "120G", "45M") to GB value
+    fn parse_size_to_gb(&self, size_str: &str) -> f32 {
+        let size_str = size_str.trim();
+        if size_str.is_empty() || size_str == "-" {
+            return 0.0;
+        }
+
+        // Extract numeric part and unit
+        let (num_str, unit) = if let Some(last_char) = size_str.chars().last() {
+            if last_char.is_alphabetic() {
+                let num_part = &size_str[..size_str.len() - 1];
+                let unit_part = &size_str[size_str.len() - 1..];
+                (num_part, unit_part)
+            } else {
+                (size_str, "")
+            }
+        } else {
+            (size_str, "")
+        };
+
+        let number: f32 = num_str.parse().unwrap_or(0.0);
+
+        match unit.to_uppercase().as_str() {
+            "T" | "TB" => number * 1024.0,
+            "G" | "GB" => number,
+            "M" | "MB" => number / 1024.0,
+            "K" | "KB" => number / (1024.0 * 1024.0),
+            "B" | "" => number / (1024.0 * 1024.0 * 1024.0),
+            _ => number, // Assume GB if unknown unit
+        }
+    }
+}
+
+#[async_trait]
+impl Collector for DiskCollector {
+
+    async fn collect(&self, status_tracker: &mut StatusTracker) -> Result<Vec<Metric>, CollectorError> {
+        let start_time = Instant::now();
+        debug!("Collecting storage pool and individual drive metrics");
+
+        let mut metrics = Vec::new();
+
+        // Get configured storage pools with individual drive data
+        let storage_pools = match self.get_configured_storage_pools() {
+            Ok(pools) => {
+                debug!("Found {} storage pools", pools.len());
+                pools
+            }
+            Err(e) => {
+                debug!("Failed to get storage pools: {}", e);
+                Vec::new()
+            }
+        };
+
+        // Generate metrics for each storage pool and its underlying drives
+        for storage_pool in &storage_pools {
+            let timestamp = chrono::Utc::now().timestamp() as u64;
+
+            // Storage pool overall metrics
+            let pool_name = &storage_pool.name;
+            
+            // Parse size strings to get actual values for calculations
+            let size_gb = self.parse_size_to_gb(&storage_pool.size);
+            let used_gb = self.parse_size_to_gb(&storage_pool.used);
+            let avail_gb = self.parse_size_to_gb(&storage_pool.available);
+
+            // Calculate status based on configured thresholds and pool health
+            let usage_status = if storage_pool.usage_percent >= self.config.usage_critical_percent {
+                Status::Critical
+            } else if storage_pool.usage_percent >= self.config.usage_warning_percent {
+                Status::Warning
+            } else {
+                Status::Ok
+            };
+
+            let pool_status = match storage_pool.pool_health {
+                PoolHealth::Critical => Status::Critical,
+                PoolHealth::Degraded => Status::Warning,
+                PoolHealth::Rebuilding => Status::Warning,
+                PoolHealth::Healthy => usage_status,
+                PoolHealth::Unknown => Status::Unknown,
+            };
+
+            // Storage pool info metrics
+            metrics.push(Metric {
+                name: format!("disk_{}_mount_point", pool_name),
+                value: MetricValue::String(storage_pool.mount_point.clone()),
+                unit: None,
+                description: Some(format!("Mount: {}", storage_pool.mount_point)),
+                status: Status::Ok,
+                timestamp,
+            });
+
+            metrics.push(Metric {
+                name: format!("disk_{}_filesystem", pool_name),
+                value: MetricValue::String(storage_pool.filesystem.clone()),
+                unit: None,
+                description: Some(format!("FS: {}", storage_pool.filesystem)),
+                status: Status::Ok,
+                timestamp,
+            });
+
+            // Enhanced pool type information
+            let pool_type_str = match &storage_pool.pool_type {
+                StoragePoolType::Single => "single".to_string(),
+                StoragePoolType::PhysicalDrive { filesystems } => {
+                    format!("drive ({})", filesystems.len())
+                }
+                StoragePoolType::MergerfsPool { data_disks, parity_disks } => {
+                    format!("mergerfs ({}+{})", data_disks.len(), parity_disks.len())
+                }
+                StoragePoolType::RaidArray { level, member_disks, spare_disks } => {
+                    format!("{} ({}+{})", level, member_disks.len(), spare_disks.len())
+                }
+                StoragePoolType::ZfsPool { pool_name, .. } => {
+                    format!("zfs ({})", pool_name)
+                }
+            };
+
+            metrics.push(Metric {
+                name: format!("disk_{}_pool_type", pool_name),
+                value: MetricValue::String(pool_type_str.clone()),
+                unit: None,
+                description: Some(format!("Type: {}", pool_type_str)),
+                status: Status::Ok,
+                timestamp,
+            });
+
+            // Pool health status
+            let health_str = match storage_pool.pool_health {
+                PoolHealth::Healthy => "healthy",
+                PoolHealth::Degraded => "degraded", 
+                PoolHealth::Critical => "critical",
+                PoolHealth::Rebuilding => "rebuilding",
+                PoolHealth::Unknown => "unknown",
+            };
+
+            metrics.push(Metric {
+                name: format!("disk_{}_pool_health", pool_name),
+                value: MetricValue::String(health_str.to_string()),
+                unit: None,
+                description: Some(format!("Health: {}", health_str)),
+                status: pool_status,
+                timestamp,
+            });
+
+            // Storage pool size metrics
+            metrics.push(Metric {
+                name: format!("disk_{}_total_gb", pool_name),
+                value: MetricValue::Float(size_gb),
+                unit: Some("GB".to_string()),
+                description: Some(format!("Total: {}", storage_pool.size)),
+                status: Status::Ok,
+                timestamp,
+            });
+
+            metrics.push(Metric {
+                name: format!("disk_{}_used_gb", pool_name),
+                value: MetricValue::Float(used_gb),
+                unit: Some("GB".to_string()),
+                description: Some(format!("Used: {}", storage_pool.used)),
+                status: pool_status,
+                timestamp,
+            });
+
+            metrics.push(Metric {
+                name: format!("disk_{}_available_gb", pool_name),
+                value: MetricValue::Float(avail_gb),
+                unit: Some("GB".to_string()),
+                description: Some(format!("Available: {}", storage_pool.available)),
+                status: Status::Ok,
+                timestamp,
+            });
+
+            metrics.push(Metric {
+                name: format!("disk_{}_usage_percent", pool_name),
+                value: MetricValue::Float(storage_pool.usage_percent),
+                unit: Some("%".to_string()),
+                description: Some(format!("Usage: {:.1}%", storage_pool.usage_percent)),
+                status: pool_status,
+                timestamp,
+            });
+
+            // Individual drive metrics for this storage pool
+            for drive in &storage_pool.underlying_drives {
+                // Drive health status
+                metrics.push(Metric {
+                    name: format!("disk_{}_{}_health", pool_name, drive.device),
+                    value: MetricValue::String(drive.health_status.clone()),
+                    unit: None,
+                    description: Some(format!("{}: {}", drive.device, drive.health_status)),
+                    status: if drive.health_status == "PASSED" { Status::Ok } 
+                            else if drive.health_status == "FAILED" { Status::Critical }
+                            else { Status::Unknown },
+                    timestamp,
+                });
+
+                // Drive temperature
+                if let Some(temp) = drive.temperature {
+                    let temp_status = self.calculate_temperature_status(
+                        &format!("disk_{}_{}_temperature", pool_name, drive.device),
+                        temp,
+                        status_tracker
+                    );
+                    
+                    metrics.push(Metric {
+                        name: format!("disk_{}_{}_temperature", pool_name, drive.device),
+                        value: MetricValue::Float(temp),
+                        unit: Some("°C".to_string()),
+                        description: Some(format!("{}: {:.0}°C", drive.device, temp)),
+                        status: temp_status,
+                        timestamp,
+                    });
+                }
+
+                // Drive wear level (for SSDs)
+                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.device),
+                        value: MetricValue::Float(wear),
+                        unit: Some("%".to_string()),
+                        description: Some(format!("{}: {:.0}% wear", drive.device, wear)),
+                        status: wear_status,
+                        timestamp,
+                    });
+                }
+            }
+
+            // Individual filesystem metrics for PhysicalDrive pools
+            if let StoragePoolType::PhysicalDrive { filesystems } = &storage_pool.pool_type {
+                for filesystem_mount in filesystems {
+                    if let Ok((total_bytes, used_bytes)) = self.get_filesystem_info(filesystem_mount) {
+                        let available_bytes = total_bytes - used_bytes;
+                        let usage_percent = if total_bytes > 0 {
+                            (used_bytes as f64 / total_bytes as f64) * 100.0
+                        } else { 0.0 };
+
+                        let filesystem_name = if filesystem_mount == "/" {
+                            "root".to_string()
+                        } else {
+                            filesystem_mount.trim_start_matches('/').replace('/', "_")
+                        };
+
+                        // Calculate filesystem status based on usage
+                        let fs_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
+                        };
+
+                        // Filesystem usage metrics
+                        metrics.push(Metric {
+                            name: format!("disk_{}_fs_{}_usage_percent", pool_name, filesystem_name),
+                            value: MetricValue::Float(usage_percent as f32),
+                            unit: Some("%".to_string()),
+                            description: Some(format!("{}: {:.0}%", filesystem_mount, usage_percent)),
+                            status: fs_status.clone(),
+                            timestamp,
+                        });
+
+                        metrics.push(Metric {
+                            name: format!("disk_{}_fs_{}_used_gb", pool_name, filesystem_name),
+                            value: MetricValue::Float(self.bytes_to_gb(used_bytes)),
+                            unit: Some("GB".to_string()),
+                            description: Some(format!("{}: {}GB used", filesystem_mount, self.bytes_to_human_readable(used_bytes))),
+                            status: Status::Ok,
+                            timestamp,
+                        });
+
+                        metrics.push(Metric {
+                            name: format!("disk_{}_fs_{}_total_gb", pool_name, filesystem_name),
+                            value: MetricValue::Float(self.bytes_to_gb(total_bytes)),
+                            unit: Some("GB".to_string()),
+                            description: Some(format!("{}: {}GB total", filesystem_mount, self.bytes_to_human_readable(total_bytes))),
+                            status: Status::Ok,
+                            timestamp,
+                        });
+
+                        metrics.push(Metric {
+                            name: format!("disk_{}_fs_{}_available_gb", pool_name, filesystem_name),
+                            value: MetricValue::Float(self.bytes_to_gb(available_bytes)),
+                            unit: Some("GB".to_string()),
+                            description: Some(format!("{}: {}GB available", filesystem_mount, self.bytes_to_human_readable(available_bytes))),
+                            status: Status::Ok,
+                            timestamp,
+                        });
+
+                        metrics.push(Metric {
+                            name: format!("disk_{}_fs_{}_mount_point", pool_name, filesystem_name),
+                            value: MetricValue::String(filesystem_mount.clone()),
+                            unit: None,
+                            description: Some(format!("Mount: {}", filesystem_mount)),
+                            status: Status::Ok,
+                            timestamp,
+                        });
+                    }
+                }
+            }
+        }
+
+        // Add storage pool count metric
+        metrics.push(Metric {
+            name: "disk_count".to_string(),
+            value: MetricValue::Integer(storage_pools.len() as i64),
+            unit: None,
+            description: Some(format!("Total storage pools: {}", storage_pools.len())),
+            status: Status::Ok,
+            timestamp: chrono::Utc::now().timestamp() as u64,
+        });
+
+
+        let collection_time = start_time.elapsed();
+        debug!(
+            "Multi-disk collection completed in {:?} with {} metrics",
+            collection_time,
+            metrics.len()
+        );
+
+        Ok(metrics)
+    }
+}

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;
 
@@ -10,48 +10,26 @@ use crate::config::MemoryConfig;
 ///
 /// EFFICIENCY OPTIMIZATIONS:
 /// - Single /proc/meminfo read for all memory metrics
-/// - Minimal string parsing with split operations
+/// - Minimal string allocations
-/// - Pre-calculated KB to GB conversion
+/// - No process spawning for basic metrics
-/// - No regex or complex parsing
+/// - <0.5ms collection time target
-/// - <0.1ms collection time target
 pub struct MemoryCollector {
-    name: String,
     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
+        // Create hysteresis thresholds with 10% gap for recovery
-        let usage_thresholds = HysteresisThresholds::with_custom_gaps(
+        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 {
-            name: "memory".to_string(),
             usage_thresholds,
         }
     }
 
-    /// 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> {
@@ -98,212 +76,141 @@ impl MemoryCollector {
         Ok(info)
     }
 
-    /// Convert KB to GB efficiently (avoiding floating point in hot path)
+    /// Populate memory data directly into AgentData
-    fn kb_to_gb(kb: u64) -> f32 {
+    async fn populate_memory_data(&self, info: &MemoryInfo, agent_data: &mut AgentData) -> Result<(), CollectorError> {
-        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);
-
         // Calculate derived values
-        let used_kb = info.total_kb - info.available_kb;
+        let available = info.available_kb;
-        let usage_percent = (used_kb as f32 / info.total_kb as f32) * 100.0;
+        let used = info.total_kb - available;
-        let usage_status = self.calculate_usage_status(registry::MEMORY_USAGE_PERCENT, usage_percent, status_tracker);
+        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
+        // Populate swap data if available
-        let total_gb = Self::kb_to_gb(info.total_kb);
+        agent_data.system.memory.swap_total_gb = info.swap_total_kb as f32 / (1024.0 * 1024.0);
-        let used_gb = Self::kb_to_gb(used_kb);
+        agent_data.system.memory.swap_used_gb = (info.swap_total_kb - info.swap_free_kb) as f32 / (1024.0 * 1024.0);
-        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);
 
-        // Memory usage percentage (primary metric with status)
+        Ok(())
-        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()),
-            );
-        }
-
-        // Monitor tmpfs (/tmp) usage
-        if let Ok(tmpfs_metrics) = self.get_tmpfs_metrics() {
-            metrics.extend(tmpfs_metrics);
-        }
-
-        metrics
     }
 
-    /// Get tmpfs (/tmp) usage metrics  
+    /// Populate tmpfs data into AgentData
-    fn get_tmpfs_metrics(&self) -> Result<Vec<Metric>, CollectorError> {
+    async fn populate_tmpfs_data(&self, agent_data: &mut AgentData) -> Result<(), CollectorError> {
-        use std::process::Command;
+        // Discover all tmpfs mount points
+        let tmpfs_mounts = self.discover_tmpfs_mounts()?;
         
-        let output = Command::new("df")
+        if tmpfs_mounts.is_empty() {
-            .arg("--block-size=1")
+            debug!("No tmpfs mounts found to monitor");
-            .arg("/tmp")
+            return Ok(());
+        }
+
+        // Get usage data for all tmpfs mounts at once using df
+        let mut df_args = vec!["df", "--output=target,size,used", "--block-size=1"];
+        df_args.extend(tmpfs_mounts.iter().map(|s| s.as_str()));
+
+        let df_output = std::process::Command::new(df_args[0])
+            .args(&df_args[1..])
             .output()
             .map_err(|e| CollectorError::SystemRead {
-                path: "/tmp".to_string(),
+                path: "tmpfs mounts".to_string(),
                 error: e.to_string(),
             })?;
 
-        if !output.status.success() {
+        let df_str = String::from_utf8_lossy(&df_output.stdout);
-            return Ok(Vec::new()); // Return empty if /tmp not available
+        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 parts: Vec<&str> = df_lines[i].split_whitespace().collect();
+            if parts.len() < 3 {
+                debug!("Invalid df output for tmpfs mount: {}", mount_point);
+                continue;
+            }
+
+            let total_bytes: u64 = parts[1].parse().unwrap_or(0);
+            let used_bytes: u64 = parts[2].parse().unwrap_or(0);
+
+            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 = (used_bytes as f32 / total_bytes as f32) * 100.0;
+
+            // Add to tmpfs list
+            agent_data.system.memory.tmpfs.push(TmpfsData {
+                mount: mount_point.clone(),
+                usage_percent,
+                used_gb,
+                total_gb,
+            });
         }
 
-        let output_str = String::from_utf8(output.stdout)
+        // Sort tmpfs mounts by mount point for consistent display order
-            .map_err(|e| CollectorError::Parse {
+        agent_data.system.memory.tmpfs.sort_by(|a, b| a.mount.cmp(&b.mount));
-                value: "df output".to_string(),
-                error: e.to_string(),
-            })?;
 
-        let lines: Vec<&str> = output_str.lines().collect();
+        Ok(())
-        if lines.len() < 2 {
+    }
-            return Ok(Vec::new());
+
+    /// 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());
+                }
+            }
         }
 
-        let fields: Vec<&str> = lines[1].split_whitespace().collect();
+        debug!("Discovered {} tmpfs mounts: {:?}", tmpfs_mounts.len(), tmpfs_mounts);
-        if fields.len() < 4 {
+        Ok(tmpfs_mounts)
-            return Ok(Vec::new());
+    }
-        }
 
-        let total_bytes: u64 = fields[1].parse()
+    /// Determine if a tmpfs mount point should be monitored
-            .map_err(|e: std::num::ParseIntError| CollectorError::Parse {
+    fn should_monitor_tmpfs(&self, mount_point: &str) -> bool {
-                value: fields[1].to_string(),
+        // Include commonly useful tmpfs mounts
-                error: e.to_string(),
+        matches!(mount_point, 
-            })?;
+            "/tmp" | "/var/tmp" | "/dev/shm" | "/run" | "/var/log"
-        let used_bytes: u64 = fields[2].parse()
+        ) || mount_point.starts_with("/run/user/") // User session tmpfs
-            .map_err(|e: std::num::ParseIntError| CollectorError::Parse {
+    }
-                value: fields[2].to_string(),
-                error: e.to_string(),
-            })?;
 
-        let total_gb = total_bytes as f32 / (1024.0 * 1024.0 * 1024.0);
+    /// Calculate memory usage status based on thresholds
-        let used_gb = used_bytes as f32 / (1024.0 * 1024.0 * 1024.0);
+    fn calculate_memory_status(&self, usage_percent: f32) -> Status {
-        let usage_percent = if total_bytes > 0 {
+        self.usage_thresholds.evaluate(usage_percent)
-            (used_bytes as f32 / total_bytes as f32) * 100.0
-        } else {
-            0.0
-        };
-
-        let mut metrics = Vec::new();
-        let timestamp = chrono::Utc::now().timestamp() as u64;
-
-        metrics.push(Metric {
-            name: "memory_tmp_usage_percent".to_string(),
-            value: MetricValue::Float(usage_percent),
-            unit: Some("%".to_string()),
-            description: Some("tmpfs /tmp usage percentage".to_string()),
-            status: Status::Ok,
-            timestamp,
-        });
-
-        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,
-        });
-
-        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(metrics)
     }
 }
 
 #[async_trait]
 impl Collector for MemoryCollector {
-    fn name(&self) -> &str {
+    async fn collect_structured(&self, agent_data: &mut AgentData) -> Result<(), CollectorError> {
-        &self.name
-    }
-
-    async fn collect(&self, status_tracker: &mut StatusTracker) -> Result<Vec<Metric>, 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
+        // Populate memory data directly
-        let metrics = self.calculate_metrics(&info, status_tracker);
+        self.populate_memory_data(&info, agent_data).await?;
+
+        // Collect tmpfs data  
+        self.populate_tmpfs_data(agent_data).await?;
 
         let duration = start.elapsed();
-        debug!(
+        debug!("Memory collection completed in {:?}", duration);
-            "Memory collection completed in {:?} with {} metrics",
-            duration,
-            metrics.len()
-        );
 
         // Efficiency check: warn if collection takes too long
         if duration.as_millis() > 1 {
@@ -313,10 +220,21 @@ impl Collector for MemoryCollector {
             );
         }
 
-        // Store performance metrics
+        // Calculate status using thresholds
-        // Performance tracking handled by cache system
+        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

@@ -1,5 +1,5 @@
 use async_trait::async_trait;
-use cm_dashboard_shared::{Metric, StatusTracker};
+use cm_dashboard_shared::{AgentData};
 
 
 pub mod backup;
@@ -7,22 +7,18 @@ 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;
 
 
-/// Base trait for all collectors with extreme efficiency requirements
+/// Base trait for all collectors with direct structured data output
 #[async_trait]
 pub trait Collector: Send + Sync {
-    /// Name of this collector
+    /// Collect data and populate AgentData directly with status evaluation
-    fn name(&self) -> &str;
+    async fn collect_structured(&self, agent_data: &mut AgentData) -> Result<(), CollectorError>;
-
-    /// Collect all metrics this collector provides
-    async fn collect(&self, status_tracker: &mut StatusTracker) -> Result<Vec<Metric>, 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("ip").args(["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("ip").args(["-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

@@ -1,232 +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:
+/// This collector gathers NixOS-specific information like:
-/// - NixOS version and build information
+/// - System generation/build information
-/// - Currently active/logged in users
+/// - Version information
-pub struct NixOSCollector {
+/// - Agent version from Nix store path
-    config: NixOSConfig,
+pub struct NixOSCollector;
-}
 
 impl NixOSCollector {
-    pub fn new(config: NixOSConfig) -> Self {
+    pub fn new(_config: crate::config::NixOSConfig) -> Self {
-        Self { config }
+        Self
     }
 
-    /// Get NixOS build information
+    /// Collect NixOS system information and populate AgentData
-    fn get_nixos_build_info(&self) -> Result<String, Box<dyn std::error::Error>> {
+    async fn collect_nixos_info(&self, agent_data: &mut AgentData) -> Result<(), CollectorError> {
-        // Get nixos-version output directly
+        debug!("Collecting NixOS system information");
-        let output = Command::new("nixos-version").output()?;
-        
-        if !output.status.success() {
-            return Err("nixos-version command failed".into());
-        }
 
-        let version_line = String::from_utf8_lossy(&output.stdout);
+        // Set hostname (this is universal, not NixOS-specific)
-        let version = version_line.trim();
+        agent_data.hostname = self.get_hostname().await.unwrap_or_else(|| "unknown".to_string());
-        
+
-        if version.is_empty() {
+        // Set agent version from environment or Nix store path
-            return Err("Empty nixos-version output".into());
+        agent_data.agent_version = self.get_agent_version().await;
-        }
+
-        
+        // Set NixOS build/generation information
-        // Remove codename part (e.g., "(Warbler)")
+        agent_data.build_version = self.get_nixos_generation().await;
-        let clean_version = if let Some(pos) = version.find(" (") {
+
-            version[..pos].to_string()
+        // Set current timestamp
-        } else {
+        agent_data.timestamp = chrono::Utc::now().timestamp() as u64;
-            version.to_string()
+
-        };
+        Ok(())
-        
-        Ok(clean_version)
     }
 
-    /// Get agent hash from binary path
+    /// Get system hostname
-    fn get_agent_hash(&self) -> Result<String, Box<dyn std::error::Error>> {
+    async fn get_hostname(&self) -> Option<String> {
-        // Get the path of the current executable
+        match fs::read_to_string("/etc/hostname") {
-        let exe_path = std::env::current_exe()?;
+            Ok(hostname) => Some(hostname.trim().to_string()),
-        let exe_str = exe_path.to_string_lossy();
+            Err(_) => {
-        
+                // Fallback to hostname command
-        // Extract Nix store hash from path like /nix/store/fn804fh332mp8gz06qawminpj20xl25h-cm-dashboard-0.1.0/bin/cm-dashboard-agent
+                match Command::new("hostname").output() {
-        if let Some(store_path) = exe_str.strip_prefix("/nix/store/") {
+                    Ok(output) => Some(String::from_utf8_lossy(&output.stdout).trim().to_string()),
-            if let Some(dash_pos) = store_path.find('-') {
+                    Err(_) => None,
-                return Ok(store_path[..dash_pos].to_string());
-            }
-        }
-        
-        // Fallback to "unknown" if not in Nix store
-        Ok("unknown".to_string())
-    }
-
-    /// Get configuration hash from deployed nix store system
-    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("Could not extract hash from nix store path".into())
     }
 
-    /// Get currently active users
+    /// Get agent version from Nix store path or environment
-    fn get_active_users(&self) -> Result<Vec<String>, Box<dyn std::error::Error>> {
+    async fn get_agent_version(&self) -> String {
-        let output = Command::new("who").output()?;
+        // Try to extract version from the current executable path (Nix store)
-        
+        if let Ok(current_exe) = std::env::current_exe() {
-        if !output.status.success() {
+            if let Some(exe_path) = current_exe.to_str() {
-            return Err("who command failed".into());
+                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
-        let who_output = String::from_utf8_lossy(&output.stdout);
+                    if let Some(store_part) = exe_path.strip_prefix("/nix/store/") {
-        let mut users = std::collections::HashSet::new();
+                        if let Some(dash_pos) = store_part.find('-') {
-
+                            let package_part = &store_part[dash_pos + 1..];
-        for line in who_output.lines() {
+                            if let Some(bin_pos) = package_part.find("/bin/") {
-            if let Some(username) = line.split_whitespace().next() {
+                                let package_name = &package_part[..bin_pos];
-                if !username.is_empty() {
+                                // Extract version from package name
-                    users.insert(username.to_string());
+                                if let Some(version_start) = package_name.rfind("-v") {
+                                    return package_name[version_start + 1..].to_string();
+                                }
+                            }
+                        }
+                    }
                 }
             }
         }
 
-        Ok(users.into_iter().collect())
+        // 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 fs::read_to_string(commit_file) {
+            Ok(content) => {
+                let commit_hash = content.trim();
+                if commit_hash.len() >= 7 {
+                    debug!("Found git commit hash: {}", commit_hash);
+                    Some(commit_hash.to_string())
+                } else {
+                    debug!("Git commit hash too short: {}", commit_hash);
+                    None
+                }
+            }
+            Err(e) => {
+                debug!("Failed to read git commit file {}: {}", commit_file, e);
+                None
+            }
+        }
     }
 }
 
 #[async_trait]
 impl Collector for NixOSCollector {
-    fn name(&self) -> &str {
+    async fn collect_structured(&self, agent_data: &mut AgentData) -> Result<(), CollectorError> {
-        "nixos"
+        self.collect_nixos_info(agent_data).await
-    }
-
-    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 NixOS build information
-        match self.get_nixos_build_info() {
-            Ok(build_info) => {
-                metrics.push(Metric {
-                    name: "system_nixos_build".to_string(),
-                    value: MetricValue::String(build_info),
-                    unit: None,
-                    description: Some("NixOS build information".to_string()),
-                    status: Status::Ok,
-                    timestamp,
-                });
-            }
-            Err(e) => {
-                debug!("Failed to get NixOS build info: {}", e);
-                metrics.push(Metric {
-                    name: "system_nixos_build".to_string(),
-                    value: MetricValue::String("unknown".to_string()),
-                    unit: None,
-                    description: Some("NixOS build (failed to detect)".to_string()),
-                    status: Status::Unknown,
-                    timestamp,
-                });
-            }
-        }
-
-        // Collect active users
-        match self.get_active_users() {
-            Ok(users) => {
-                let users_str = users.join(", ");
-                metrics.push(Metric {
-                    name: "system_active_users".to_string(),
-                    value: MetricValue::String(users_str),
-                    unit: None,
-                    description: Some("Currently active users".to_string()),
-                    status: Status::Ok,
-                    timestamp,
-                });
-            }
-            Err(e) => {
-                debug!("Failed to get active users: {}", e);
-                metrics.push(Metric {
-                    name: "system_active_users".to_string(),
-                    value: MetricValue::String("unknown".to_string()),
-                    unit: None,
-                    description: Some("Active users (failed to detect)".to_string()),
-                    status: Status::Unknown,
-                    timestamp,
-                });
-            }
-        }
-
-        // Collect config hash
-        match self.get_config_hash() {
-            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)
     }
 }

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>,
@@ -18,21 +18,25 @@ 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 (30 seconds)
+    /// How often to check nginx site latency (configurable)
     nginx_check_interval_seconds: u64,
 }
 
@@ -42,25 +46,125 @@ struct ServiceStatusInfo {
     load_state: String,
     active_state: String,
     sub_state: String,
-    description: String,
 }
 
 impl SystemdCollector {
     pub fn new(config: SystemdConfig) -> Self {
+        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,
+            discovery_interval_seconds: config.interval_seconds,
+            nginx_site_metrics: Vec::new(),
+            last_nginx_check_time: None,
+            nginx_check_interval_seconds: config.nginx_check_interval_seconds,
+        };
+
         Self {
-            state: RwLock::new(ServiceCacheState {
+            state: RwLock::new(state),
-                monitored_services: Vec::new(),
-                service_status_cache: std::collections::HashMap::new(),
-                last_discovery_time: None,
-                discovery_interval_seconds: config.interval_seconds,
-                nginx_site_metrics: Vec::new(),
-                last_nginx_check_time: None,
-                nginx_check_interval_seconds: 30, // 30 seconds for nginx sites
-            }),
             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((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 mut sub_services = Vec::new();
+
+                    // Sub-service metrics for specific services (always include cached results)
+                    if service_name.contains("nginx") && active_status == "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,
+                            });
+                        }
+                    }
+
+                    if service_name.contains("docker") && active_status == "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,
+                            });
+                        }
+                    }
+
+                    // Create complete service data
+                    let service_data = ServiceData {
+                        name: service_name.clone(),
+                        memory_mb,
+                        disk_gb,
+                        user_stopped: false, // TODO: Integrate with service tracker
+                        service_status: self.calculate_service_status(service_name, &active_status),
+                        sub_services,
+                    };
+
+                    // 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);
+                }
+            }
+        }
+        
+        // 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
@@ -77,25 +181,19 @@ 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!(
+                        debug!("Auto-discovered {} services to monitor: {:?}", 
-                            "Auto-discovered {} services to monitor: {:?}",
+                            state.monitored_services.len(), state.monitored_services);
-                            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
                 }
             }
         }
@@ -105,8 +203,8 @@ impl SystemdCollector {
         Ok(state.monitored_services.clone())
     }
 
-    /// Get nginx site metrics, checking them if cache is expired
+    /// Get nginx site metrics, checking them if cache is expired (like old working version)
-    fn get_nginx_site_metrics(&self) -> Vec<Metric> {
+    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
@@ -121,11 +219,7 @@ 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!(
+                let fresh_metrics = self.get_nginx_sites_internal();
-                    "Refreshing nginx site latency metrics (interval: {}s)",
-                    state.nginx_check_interval_seconds
-                );
-                let fresh_metrics = self.get_nginx_sites();
                 state.nginx_site_metrics = fresh_metrics;
                 state.last_nginx_check_time = Some(Instant::now());
             }
@@ -134,159 +228,97 @@ 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
-        // Get all services (includes inactive, running, failed - everything)
+        let unit_files_output = Command::new("systemctl")
-        let units_output = Command::new("systemctl")
+            .args(&["list-unit-files", "--type=service", "--no-pager", "--plain"])
-            .arg("list-units")
-            .arg("--type=service")
-            .arg("--all")
-            .arg("--no-pager")
-            .arg("--plain")
             .output()?;
 
-        if !units_output.status.success() {
+        if !unit_files_output.status.success() {
-            return Err(anyhow::anyhow!("systemctl system command failed"));
+            return Err(anyhow::anyhow!("systemctl list-unit-files command failed"));
         }
 
-        let units_str = String::from_utf8(units_output.stdout)?;
+        // Second: Get runtime status of all units
+        let units_status_output = Command::new("systemctl")
+            .args(&["list-units", "--type=service", "--all", "--no-pager", "--plain"])
+            .output()?;
+
+        if !units_status_output.status.success() {
+            return Err(anyhow::anyhow!("systemctl list-units command failed"));
+        }
+
+        let unit_files_str = String::from_utf8(unit_files_output.stdout)?;
+        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 services and cache their status information
+        // 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());
+            }
+        }
+
+        // Parse runtime status for all units
         let mut status_cache = std::collections::HashMap::new();
-        
+        for line in units_status_str.lines() {
-        for line in units_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");
-                
-                // 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();
-                let description = if fields.len() > 4 {
-                    fields[4..].join(" ")
-                } else {
-                    "".to_string()
-                };
 
-                // Cache the status information
                 status_cache.insert(service_name.to_string(), ServiceStatusInfo {
-                    load_state: load_state.clone(),
+                    load_state,
-                    active_state: active_state.clone(),
+                    active_state,
-                    sub_state: sub_state.clone(),
+                    sub_state,
-                    description,
                 });
-
-                all_service_names.insert(service_name.to_string());
-                debug!("Parsed service: {} (load:{}, active:{}, sub:{})", service_name, load_state, active_state, sub_state);
             }
         }
 
-
+        // For services found in unit files but not in runtime status, set default inactive status
-        // Now process all discovered services
         for service_name in &all_service_names {
-                debug!("Processing service: '{}'", service_name);
+            if !status_cache.contains_key(service_name) {
-
+                status_cache.insert(service_name.to_string(), ServiceStatusInfo {
-                // Skip excluded services first
+                    load_state: "not-loaded".to_string(),
-                let mut is_excluded = false;
+                    active_state: "inactive".to_string(),
-                for excluded in excluded_services {
+                    sub_state: "dead".to_string(),
-                    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))
-    }
-
-    /// 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];
-                service_name.starts_with(prefix)
-            } else if pattern.starts_with('*') {
-                // Pattern like "*backup" - match if service ends with "backup"
-                let suffix = &pattern[1..];
-                service_name.ends_with(suffix)
-            } else {
-                // Pattern like "nginx*backup" - simple glob matching
-                self.simple_glob_match(service_name, pattern)
             }
-        } else {
-            // Exact match (existing behavior)
-            service_name == pattern
-        }
-    }
-
-    /// Simple glob pattern matching for patterns with * in 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;
+        // Process all discovered services and apply filters
-        for (i, part) in parts.iter().enumerate() {
+        for service_name in &all_service_names {
-            if part.is_empty() {
+            // Skip excluded services first
+            let mut is_excluded = false;
+            for excluded in excluded_services {
+                if service_name.contains(excluded) {
+                    is_excluded = true;
+                    break;
+                }
+            }
+
+            if is_excluded {
                 continue;
             }
 
-            if i == 0 {
+            // Check if this service matches our filter patterns (supports wildcards)
-                // First part must match at start
+            for pattern in service_name_filters {
-                if !text[pos..].starts_with(part) {
+                if self.matches_pattern(service_name, pattern) {
-                    return false;
+                    services.push(service_name.to_string());
-                }
+                    break;
-                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
+
+        Ok((services, status_cache))
     }
 
     /// Get service status from cache (if available) or fallback to systemctl
@@ -305,70 +337,111 @@ impl SystemdCollector {
             }
         }
 
-        // Fallback to systemctl if not in cache (shouldn't happen during normal operation)
+        // Fallback to systemctl if not in cache
-        debug!("Service '{}' not found in cache, falling back to systemctl", service);
         let output = Command::new("systemctl")
-            .arg("is-active")
+            .args(&["is-active", &format!("{}.service", service)])
-            .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")
+            .args(&["show", &format!("{}.service", service), "--property=LoadState,ActiveState,SubState"])
-        .arg(format!("{}.service", service))
+            .output()?;
-        .arg("--property=LoadState,ActiveState,SubState")
-        .output()?;
 
         let detailed_info = String::from_utf8(output.stdout)?;
         Ok((active_status, detailed_info))
     }
 
-    /// Calculate service status
+    /// Check if service name matches pattern (supports wildcards like nginx*)
-    fn calculate_service_status(&self, active_status: &str) -> Status {
+    fn matches_pattern(&self, service_name: &str, pattern: &str) -> bool {
-        match active_status.to_lowercase().as_str() {
+        if pattern.contains('*') {
-            "active" => Status::Ok,
+            if pattern.ends_with('*') {
-            "inactive" | "dead" => Status::Warning,
+                // Pattern like "nginx*" - match if service starts with "nginx"
-            "failed" | "error" => Status::Critical,
+                let prefix = &pattern[..pattern.len() - 1];
-            "activating" | "deactivating" | "reloading" | "start" | "stop" | "restart" => Status::Pending,
+                service_name.starts_with(prefix)
-            _ => Status::Unknown,
+            } else if pattern.starts_with('*') {
+                // Pattern like "*backup" - match if service ends with "backup"
+                let suffix = &pattern[1..];
+                service_name.ends_with(suffix)
+            } else {
+                // Pattern like "nginx*backup" - simple glob matching
+                self.simple_glob_match(service_name, pattern)
+            }
+        } else {
+            // Exact match
+            service_name == pattern
         }
     }
 
-    /// Get service memory usage (if available)
+    /// Simple glob matching for patterns with * in the middle
-    fn get_service_memory(&self, service: &str) -> Option<f32> {
+    fn simple_glob_match(&self, text: &str, pattern: &str) -> bool {
-        let output = Command::new("systemctl")
+        let parts: Vec<&str> = pattern.split('*').collect();
-            .arg("show")
+        let mut pos = 0;
-            .arg(format!("{}.service", service))
+        
-            .arg("--property=MemoryCurrent")
+        for part in parts {
-            .output()
+            if part.is_empty() {
-            .ok()?;
+                continue;
+            }
+            if let Some(found_pos) = text[pos..].find(part) {
+                pos += found_pos + part.len();
+            } else {
+                return false;
+            }
+        }
+        true
+    }
 
-        let output_str = String::from_utf8(output.stdout).ok()?;
+    /// 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("MemoryCurrent=") {
+            if line.starts_with("WorkingDirectory=") && !line.contains("[not set]") {
-                let memory_str = line.trim_start_matches("MemoryCurrent=");
+                let dir = line.strip_prefix("WorkingDirectory=").unwrap_or("");
-                if let Ok(memory_bytes) = memory_str.parse::<u64>() {
+                if !dir.is_empty() && dir != "/" {
-                    return Some(memory_bytes as f32 / (1024.0 * 1024.0)); // Convert to MB
+                    return Ok(self.get_directory_size(dir).unwrap_or(0.0));
                 }
             }
         }
-        None
+
+        Ok(0.0)
     }
-
+    
-
+    /// Get size of a directory in GB
-    /// Get directory size in GB with permission-aware logging
+    fn get_directory_size(&self, path: &str) -> Option<f32> {
-    fn get_directory_size(&self, dir: &str) -> Option<f32> {
+        let output = Command::new("sudo")
-        let output = Command::new("sudo").arg("du").arg("-sb").arg(dir).output().ok()?;
+            .args(&["du", "-sb", path])
+            .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);
+                debug!("Permission denied accessing directory: {}", path);
             } else {
-                debug!("Failed to get size for directory {}: {}", dir, stderr);
+                debug!("Failed to get size for directory {}: {}", path, stderr);
             }
             return None;
         }
@@ -388,271 +461,98 @@ impl SystemdCollector {
         }
     }
 
-    /// Get service disk usage - simplified and configuration-driven
+    /// Calculate service status, taking user-stopped services into account
-    fn get_service_disk_usage(&self, service: &str) -> Option<f32> {
+    fn calculate_service_status(&self, service_name: &str, active_status: &str) -> Status {
-        // 1. Check if service has configured directories (exact match only)
+        match active_status.to_lowercase().as_str() {
-        if let Some(dirs) = self.config.service_directories.get(service) {
+            "active" => Status::Ok,
-            // Service has configured paths - use the first accessible one
+            "inactive" | "dead" => {
-            for dir in dirs {
+                debug!("Service '{}' is inactive - treating as Inactive status", service_name);
-                if let Some(size) = self.get_directory_size(dir) {
+                Status::Inactive
-                    return Some(size);
+            },
-                }
+            "failed" | "error" => Status::Critical,
-            }
+            "activating" | "deactivating" | "reloading" | "starting" | "stopping" => {
-            // If configured paths failed, return None (shows as 0)
+                debug!("Service '{}' is transitioning - treating as Pending", service_name);
-            return Some(0.0);
+                Status::Pending
+            },
+            _ => Status::Unknown,
         }
+    }
 
-        // 2. No configured path - use systemctl WorkingDirectory
+    /// 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")
-            .arg("show")
+            .args(&["show", &format!("{}.service", service_name), "--property=MemoryCurrent"])
-            .arg(format!("{}.service", service))
-            .arg("--property=WorkingDirectory")
             .output()
-            .ok()?;
+            .map_err(|e| CollectorError::SystemRead {
+                path: format!("memory usage for {}", service_name),
+                error: e.to_string(),
+            })?;
 
-        let output_str = String::from_utf8(output.stdout).ok()?;
+        let output_str = String::from_utf8_lossy(&output.stdout);
+        
         for line in output_str.lines() {
-            if line.starts_with("WorkingDirectory=") && !line.contains("[not set]") {
+            if line.starts_with("MemoryCurrent=") {
-                let dir = line.trim_start_matches("WorkingDirectory=");
+                if let Some(mem_str) = line.strip_prefix("MemoryCurrent=") {
-                if !dir.is_empty() && dir != "/" {
+                    if mem_str != "[not set]" {
-                    return self.get_directory_size(dir);
+                        if let Ok(memory_bytes) = mem_str.parse::<u64>() {
+                            return Ok(memory_bytes as f32 / (1024.0 * 1024.0)); // Convert to MB
+                        }
+                    }
                 }
             }
         }
 
-        None
+        Ok(0.0)
     }
 
+    /// 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
-
-#[async_trait]
-impl Collector for SystemdCollector {
-    fn name(&self) -> &str {
-        "systemd"
-    }
-
-    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);
-            }
-        };
-
-        // 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(&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)
     }
 
-}
+    /// 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
+        }
+    }
 
-impl SystemdCollector {
+    /// Get nginx sites with latency checks (internal - no caching)
-    /// Get nginx sites with latency checks
+    fn get_nginx_sites_internal(&self) -> Vec<(String, f32)> {
-    fn get_nginx_sites(&self) -> Vec<Metric> {
+        let mut sites = Vec::new();
-        let mut metrics = Vec::new();
-        let timestamp = chrono::Utc::now().timestamp() as u64;
 
         // Discover nginx sites from configuration
-        let sites = self.discover_nginx_sites();
+        let discovered_sites = self.discover_nginx_sites();
 
-        for (site_name, url) in &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) => {
-                    let status = if latency_ms < 500.0 {
+                    sites.push((site_name.clone(), latency_ms));
-                        Status::Ok
-                    } else if latency_ms < 2000.0 {
-                        Status::Warning
-                    } 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,
-                    });
                 }
                 Err(_) => {
-                    // Site is unreachable
+                    // Site is unreachable - use -1.0 to indicate error (like old version)
-                    metrics.push(Metric {
+                    sites.push((site_name.clone(), -1.0));
-                        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
+        sites
     }
 
-    /// Get docker containers as sub-services
+    /// Discover nginx sites from configuration
-    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;
-            }
-
-            let parts: Vec<&str> = line.split(',').collect();
-            if parts.len() >= 2 {
-                let container_name = parts[0].trim();
-                let status_str = parts[1].trim();
-
-                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,
-                });
-            }
-        }
-
-        metrics
-    }
-
-    /// Check site latency using HTTP GET requests
-    fn check_site_latency(&self, url: &str) -> Result<f32, Box<dyn std::error::Error>> {
-        use std::time::Duration;
-        use std::time::Instant;
-
-        let start = Instant::now();
-
-        // Create HTTP client with timeouts (similar to legacy implementation)
-        let client = reqwest::blocking::Client::builder()
-            .timeout(Duration::from_secs(10))
-            .connect_timeout(Duration::from_secs(10))
-            .redirect(reqwest::redirect::Policy::limited(10))
-            .build()?;
-
-        // Make GET request and measure latency
-        let response = client.get(url).send()?;
-        let latency = start.elapsed().as_millis() as f32;
-
-        // Check if response is successful (2xx or 3xx status codes)
-        if response.status().is_success() || response.status().is_redirection() {
-            Ok(latency)
-        } else {
-            Err(format!(
-                "HTTP request failed for {} with status: {}",
-                url,
-                response.status()
-            )
-            .into())
-        }
-    }
-
-    /// Discover nginx sites from configuration files (like the old working implementation)
     fn discover_nginx_sites(&self) -> Vec<(String, String)> {
-        use tracing::debug;
-
         // 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,
@@ -672,12 +572,25 @@ impl SystemdCollector {
         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()?;
+
+        if !output.status.success() {
+            debug!("nginx -T failed");
+            return None;
+        }
+
+        Some(String::from_utf8_lossy(&output.stdout).to_string())
+    }
+
     /// Get nginx config from systemd service definition (NixOS compatible)
     fn get_nginx_config_from_systemd(&self) -> Option<String> {
-        use tracing::debug;
+        let output = Command::new("systemctl")
-
+            .args(&["show", "nginx", "--property=ExecStart", "--no-pager"])
-        let output = std::process::Command::new("systemctl")
-            .args(["show", "nginx", "--property=ExecStart", "--no-pager"])
             .output()
             .ok()?;
 
@@ -693,13 +606,9 @@ impl SystemdCollector {
         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).ok();
-                    return std::fs::read_to_string(&config_path)
-                        .map_err(|e| debug!("Failed to read config file {}: {}", config_path, e))
-                        .ok();
                 }
             }
         }
@@ -709,8 +618,6 @@ impl SystemdCollector {
 
     /// 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);
@@ -742,26 +649,8 @@ impl SystemdCollector {
         None
     }
 
-    /// Fallback: get nginx config via nginx -T command
-    fn get_nginx_config_via_command(&self) -> Option<String> {
-        use tracing::debug;
-
-        let output = std::process::Command::new("nginx")
-            .args(["-T"])
-            .output()
-            .ok()?;
-
-        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;
@@ -785,7 +674,6 @@ impl SystemdCollector {
 
     /// 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;
@@ -816,7 +704,6 @@ impl SystemdCollector {
                 }
             }
 
-
             // Check for redirects (skip redirect-only servers)
             if trimmed.contains("return") && (trimmed.contains("301") || trimmed.contains("302")) {
                 has_redirect = true;
@@ -833,4 +720,95 @@ impl SystemdCollector {
 
         None
     }
+
+    /// Check site latency using HTTP GET requests
+    fn check_site_latency(&self, url: &str) -> Result<f32, Box<dyn std::error::Error>> {
+        use std::time::Duration;
+        use std::time::Instant;
+
+        let start = Instant::now();
+
+        // Create HTTP client with timeouts from configuration
+        let client = reqwest::blocking::Client::builder()
+            .timeout(Duration::from_secs(self.config.http_timeout_seconds))
+            .connect_timeout(Duration::from_secs(self.config.http_connect_timeout_seconds))
+            .redirect(reqwest::redirect::Policy::limited(10))
+            .build()?;
+
+        // Make GET request and measure latency
+        let response = client.get(url).send()?;
+        let latency = start.elapsed().as_millis() as f32;
+
+        // Check if response is successful (2xx or 3xx status codes)
+        if response.status().is_success() || response.status().is_redirection() {
+            Ok(latency)
+        } else {
+            Err(format!(
+                "HTTP request failed for {} with status: {}",
+                url,
+                response.status()
+            )
+            .into())
+        }
+    }
+
+    /// Get docker containers as sub-services
+    fn get_docker_containers(&self) -> Vec<(String, String)> {
+        let mut containers = Vec::new();
+
+        // Check if docker is available (use sudo for permissions)
+        let output = Command::new("sudo")
+            .args(&["docker", "ps", "--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") {
+                    "warning" // Match original: Exited → Warning, not inactive
+                } else {
+                    "failed" // Other states → failed
+                };
+                
+                containers.push((format!("docker_{}", container_name), container_status.to_string()));
+            }
+        }
+
+        containers
+    }
 }
+
+#[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
+        }
+    }
+}

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

@@ -1,5 +1,5 @@
 use anyhow::Result;
-use cm_dashboard_shared::{MessageEnvelope, MetricMessage};
+use cm_dashboard_shared::{AgentData, MessageEnvelope};
 use tracing::{debug, info};
 use zmq::{Context, Socket, SocketType};
 
@@ -43,17 +43,17 @@ impl ZmqHandler {
         })
     }
 
-    /// Publish metrics message via ZMQ
+
-    pub async fn publish_metrics(&self, message: &MetricMessage) -> Result<()> {
+    /// Publish agent data via ZMQ
+    pub async fn publish_agent_data(&self, data: &AgentData) -> Result<()> {
         debug!(
-            "Publishing {} metrics for host {}",
+            "Publishing agent data for host {}",
-            message.metrics.len(),
+            data.hostname
-            message.hostname
         );
 
-        // Create message envelope
+        // Create message envelope for agent data
-        let envelope = MessageEnvelope::metrics(message.clone())
+        let envelope = MessageEnvelope::agent_data(data.clone())
-            .map_err(|e| anyhow::anyhow!("Failed to create message envelope: {}", e))?;
+            .map_err(|e| anyhow::anyhow!("Failed to create agent data envelope: {}", e))?;
 
         // Serialize envelope
         let serialized = serde_json::to_vec(&envelope)?;
@@ -61,12 +61,10 @@ impl ZmqHandler {
         // Send via ZMQ
         self.publisher.send(&serialized, 0)?;
 
-        debug!("Published metrics message ({} bytes)", serialized.len());
+        debug!("Published agent data message ({} bytes)", serialized.len());
         Ok(())
     }
 
-    /// Send heartbeat (placeholder for future use)
-
     /// Try to receive a command (non-blocking)
     pub fn try_receive_command(&self) -> Result<Option<AgentCommand>> {
         match self.command_receiver.recv_bytes(zmq::DONTWAIT) {
@@ -99,25 +97,4 @@ pub enum AgentCommand {
     ToggleCollector { name: String, enabled: bool },
     /// Request status/health check
     Ping,
-    /// Control systemd service
-    ServiceControl {
-        service_name: String,
-        action: ServiceAction,
-    },
-    /// Rebuild NixOS system
-    SystemRebuild {
-        git_url: String,
-        git_branch: String,
-        working_dir: String,
-        api_key_file: Option<String>,
-    },
-}
-
-/// Service control actions
-#[derive(Debug, Clone, serde::Deserialize, serde::Serialize)]
-pub enum ServiceAction {
-    Start,
-    Stop,
-    Restart,
-    Status,
 }

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 {
@@ -15,7 +13,6 @@ pub struct AgentConfig {
     pub collectors: CollectorConfig,
     pub cache: CacheConfig,
     pub notifications: NotificationConfig,
-    pub status_aggregation: HostStatusConfig,
     pub collection_interval_seconds: u64,
 }
 
@@ -25,8 +22,10 @@ pub struct ZmqConfig {
     pub publisher_port: u16,
     pub command_port: u16,
     pub bind_address: String,
-    pub timeout_ms: u64,
+    pub transmission_interval_seconds: u64,
-    pub heartbeat_interval_ms: u64,
+    /// Heartbeat transmission interval in seconds for host connectivity detection
+    #[serde(default = "default_heartbeat_interval_seconds")]
+    pub heartbeat_interval_seconds: u64,
 }
 
 /// Collector configuration
@@ -36,7 +35,6 @@ pub struct CollectorConfig {
     pub memory: MemoryConfig,
     pub disk: DiskConfig,
     pub systemd: SystemdConfig,
-    pub smart: SmartConfig,
     pub backup: BackupConfig,
     pub network: NetworkConfig,
     pub nixos: NixOSConfig,
@@ -73,8 +71,14 @@ pub struct DiskConfig {
     pub usage_warning_percent: f32,
     /// Disk usage critical threshold (percentage)
     pub usage_critical_percent: f32,
-    /// Filesystem configurations
+    /// Filesystem configurations (optional - auto-discovery used if empty)
+    #[serde(default)]
     pub filesystems: Vec<FilesystemConfig>,
+    /// SMART monitoring thresholds
+    pub temperature_warning_celsius: f32,
+    pub temperature_critical_celsius: f32,
+    pub wear_warning_percent: f32,
+    pub wear_critical_percent: f32,
 }
 
 /// Filesystem configuration entry
@@ -100,18 +104,12 @@ pub struct SystemdConfig {
     pub memory_critical_mb: f32,
     pub service_directories: std::collections::HashMap<String, Vec<String>>,
     pub host_user_mapping: String,
+    pub nginx_check_interval_seconds: u64,
+    pub http_timeout_seconds: u64,
+    pub http_connect_timeout_seconds: u64,
+    pub nginx_latency_critical_ms: f32,
 }
 
-/// SMART collector configuration
-#[derive(Debug, Clone, Serialize, Deserialize)]
-pub struct SmartConfig {
-    pub enabled: bool,
-    pub interval_seconds: u64,
-    pub temperature_warning_celsius: f32,
-    pub temperature_critical_celsius: f32,
-    pub wear_warning_percent: f32,
-    pub wear_critical_percent: f32,
-}
 
 /// NixOS collector configuration
 #[derive(Debug, Clone, Serialize, Deserialize)]
@@ -145,6 +143,23 @@ pub struct NotificationConfig {
     pub from_email: String,
     pub to_email: String,
     pub rate_limit_minutes: u64,
+    /// Email notification batching interval in seconds (default: 60)
+    pub aggregation_interval_seconds: u64,
+    /// List of metric names to exclude from email notifications
+    #[serde(default)]
+    pub exclude_email_metrics: Vec<String>,
+    /// Path to maintenance mode file that suppresses email notifications when present
+    #[serde(default = "default_maintenance_mode_file")]
+    pub maintenance_mode_file: String,
+}
+
+
+fn default_heartbeat_interval_seconds() -> u64 {
+    5
+}
+
+fn default_maintenance_mode_file() -> String {
+    "/tmp/cm-maintenance".to_string()
 }
 
 impl AgentConfig {

agent/src/config/validation.rs

@@ -19,10 +19,6 @@ pub fn validate_config(config: &AgentConfig) -> Result<()> {
         bail!("ZMQ bind address cannot be empty");
     }
 
-    if config.zmq.timeout_ms == 0 {
-        bail!("ZMQ timeout cannot be 0");
-    }
-
     // Validate collection interval
     if config.collection_interval_seconds == 0 {
         bail!("Collection interval cannot be 0");
@@ -83,6 +79,13 @@ pub fn validate_config(config: &AgentConfig) -> Result<()> {
         }
     }
 
+    // Validate systemd configuration
+    if config.collectors.systemd.enabled {
+        if config.collectors.systemd.nginx_latency_critical_ms <= 0.0 {
+            bail!("Nginx latency critical threshold must be positive");
+        }
+    }
+
     // Validate SMTP configuration
     if config.notifications.enabled {
         if config.notifications.smtp_host.is_empty() {

agent/src/main.rs

@@ -4,20 +4,33 @@ use tracing::{error, info};
 use tracing_subscriber::EnvFilter;
 
 mod agent;
-mod cache;
 mod collectors;
 mod communication;
 mod config;
-mod metrics;
 mod notifications;
-mod status;
 
 use agent::Agent;
 
+/// Get version showing cm-dashboard-agent package hash for easy deployment verification
+fn get_version() -> &'static str {
+    // Get the path of the current executable
+    let exe_path = std::env::current_exe().expect("Failed to get executable path");
+    let exe_str = exe_path.to_string_lossy();
+    
+    // Extract Nix store hash from path like /nix/store/HASH-cm-dashboard-v0.1.8/bin/cm-dashboard-agent
+    let hash_part = exe_str.strip_prefix("/nix/store/").expect("Not a nix store path");
+    let hash = hash_part.split('-').next().expect("Invalid nix store path format");
+    assert!(hash.len() >= 8, "Hash too short");
+    
+    // Return first 8 characters of nix store hash
+    let short_hash = hash[..8].to_string();
+    Box::leak(short_hash.into_boxed_str())
+}
+
 #[derive(Parser)]
 #[command(name = "cm-dashboard-agent")]
 #[command(about = "CM Dashboard metrics agent with individual metric collection")]
-#[command(version)]
+#[command(version = get_version())]
 struct Cli {
     /// Increase logging verbosity (-v, -vv)
     #[arg(short, long, action = clap::ArgAction::Count)]

agent/src/metrics/mod.rs

@@ -1,27 +1,32 @@
 use anyhow::Result;
 use cm_dashboard_shared::{Metric, StatusTracker};
-use std::collections::HashMap;
+use std::time::{Duration, Instant};
-use std::time::Instant;
 use tracing::{debug, error, info};
 
-use crate::cache::MetricCacheManager;
 use crate::collectors::{
     backup::BackupCollector, cpu::CpuCollector, disk::DiskCollector, memory::MemoryCollector,
     nixos::NixOSCollector, systemd::SystemdCollector, Collector,
 };
 use crate::config::{AgentConfig, CollectorConfig};
 
-/// Manages all metric collectors with intelligent caching
+/// Collector with timing information
+struct TimedCollector {
+    collector: Box<dyn Collector>,
+    interval: Duration,
+    last_collection: Option<Instant>,
+    name: String,
+}
+
+/// Manages all metric collectors with individual intervals
 pub struct MetricCollectionManager {
-    collectors: Vec<Box<dyn Collector>>,
+    collectors: Vec<TimedCollector>,
-    cache_manager: MetricCacheManager,
-    last_collection_times: HashMap<String, Instant>,
     status_tracker: StatusTracker,
+    cached_metrics: Vec<Metric>,
 }
 
 impl MetricCollectionManager {
-    pub async fn new(config: &CollectorConfig, agent_config: &AgentConfig) -> Result<Self> {
+    pub async fn new(config: &CollectorConfig, _agent_config: &AgentConfig) -> Result<Self> {
-        let mut collectors: Vec<Box<dyn Collector>> = Vec::new();
+        let mut collectors: Vec<TimedCollector> = Vec::new();
 
         // Benchmark mode - only enable specific collector based on env var
         let benchmark_mode = std::env::var("BENCHMARK_COLLECTOR").ok();
@@ -31,7 +36,12 @@ impl MetricCollectionManager {
                 // CPU collector only
                 if config.cpu.enabled {
                     let cpu_collector = CpuCollector::new(config.cpu.clone());
-                    collectors.push(Box::new(cpu_collector));
+                    collectors.push(TimedCollector {
+                        collector: Box::new(cpu_collector),
+                        interval: Duration::from_secs(config.cpu.interval_seconds),
+                        last_collection: None,
+                        name: "CPU".to_string(),
+                    });
                     info!("BENCHMARK: CPU collector only");
                 }
             }
@@ -39,20 +49,35 @@ impl MetricCollectionManager {
                 // Memory collector only
                 if config.memory.enabled {
                     let memory_collector = MemoryCollector::new(config.memory.clone());
-                    collectors.push(Box::new(memory_collector));
+                    collectors.push(TimedCollector {
+                        collector: Box::new(memory_collector),
+                        interval: Duration::from_secs(config.memory.interval_seconds),
+                        last_collection: None,
+                        name: "Memory".to_string(),
+                    });
                     info!("BENCHMARK: Memory collector only");
                 }
             }
             Some("disk") => {
                 // Disk collector only
                 let disk_collector = DiskCollector::new(config.disk.clone());
-                collectors.push(Box::new(disk_collector));
+                collectors.push(TimedCollector {
+                    collector: Box::new(disk_collector),
+                    interval: Duration::from_secs(config.disk.interval_seconds),
+                    last_collection: None,
+                    name: "Disk".to_string(),
+                });
                 info!("BENCHMARK: Disk collector only");
             }
             Some("systemd") => {
                 // Systemd collector only
                 let systemd_collector = SystemdCollector::new(config.systemd.clone());
-                collectors.push(Box::new(systemd_collector));
+                collectors.push(TimedCollector {
+                    collector: Box::new(systemd_collector),
+                    interval: Duration::from_secs(config.systemd.interval_seconds),
+                    last_collection: None,
+                    name: "Systemd".to_string(),
+                });
                 info!("BENCHMARK: Systemd collector only");
             }
             Some("backup") => {
@@ -62,7 +87,12 @@ impl MetricCollectionManager {
                         config.backup.backup_paths.first().cloned(),
                         config.backup.max_age_hours,
                     );
-                    collectors.push(Box::new(backup_collector));
+                    collectors.push(TimedCollector {
+                        collector: Box::new(backup_collector),
+                        interval: Duration::from_secs(config.backup.interval_seconds),
+                        last_collection: None,
+                        name: "Backup".to_string(),
+                    });
                     info!("BENCHMARK: Backup collector only");
                 }
             }
@@ -74,57 +104,81 @@ impl MetricCollectionManager {
                 // Normal mode - all collectors
                 if config.cpu.enabled {
                     let cpu_collector = CpuCollector::new(config.cpu.clone());
-                    collectors.push(Box::new(cpu_collector));
+                    collectors.push(TimedCollector {
-                    info!("CPU collector initialized");
+                        collector: Box::new(cpu_collector),
+                        interval: Duration::from_secs(config.cpu.interval_seconds),
+                        last_collection: None,
+                        name: "CPU".to_string(),
+                    });
+                    info!("CPU collector initialized with {}s interval", config.cpu.interval_seconds);
                 }
 
                 if config.memory.enabled {
                     let memory_collector = MemoryCollector::new(config.memory.clone());
-                    collectors.push(Box::new(memory_collector));
+                    collectors.push(TimedCollector {
-                    info!("Memory collector initialized");
+                        collector: Box::new(memory_collector),
+                        interval: Duration::from_secs(config.memory.interval_seconds),
+                        last_collection: None,
+                        name: "Memory".to_string(),
+                    });
+                    info!("Memory collector initialized with {}s interval", config.memory.interval_seconds);
                 }
 
                 let disk_collector = DiskCollector::new(config.disk.clone());
-                collectors.push(Box::new(disk_collector));
+                collectors.push(TimedCollector {
-                info!("Disk collector initialized");
+                    collector: Box::new(disk_collector),
+                    interval: Duration::from_secs(config.disk.interval_seconds),
+                    last_collection: None,
+                    name: "Disk".to_string(),
+                });
+                info!("Disk collector initialized with {}s interval", config.disk.interval_seconds);
 
                 let systemd_collector = SystemdCollector::new(config.systemd.clone());
-                collectors.push(Box::new(systemd_collector));
+                collectors.push(TimedCollector {
-                info!("Systemd collector initialized");
+                    collector: Box::new(systemd_collector),
+                    interval: Duration::from_secs(config.systemd.interval_seconds),
+                    last_collection: None,
+                    name: "Systemd".to_string(),
+                });
+                info!("Systemd collector initialized with {}s interval", config.systemd.interval_seconds);
 
                 if config.backup.enabled {
                     let backup_collector = BackupCollector::new(
                         config.backup.backup_paths.first().cloned(),
                         config.backup.max_age_hours,
                     );
-                    collectors.push(Box::new(backup_collector));
+                    collectors.push(TimedCollector {
-                    info!("Backup collector initialized");
+                        collector: Box::new(backup_collector),
+                        interval: Duration::from_secs(config.backup.interval_seconds),
+                        last_collection: None,
+                        name: "Backup".to_string(),
+                    });
+                    info!("Backup collector initialized with {}s interval", config.backup.interval_seconds);
                 }
 
                 if config.nixos.enabled {
                     let nixos_collector = NixOSCollector::new(config.nixos.clone());
-                    collectors.push(Box::new(nixos_collector));
+                    collectors.push(TimedCollector {
-                    info!("NixOS collector initialized");
+                        collector: Box::new(nixos_collector),
+                        interval: Duration::from_secs(config.nixos.interval_seconds),
+                        last_collection: None,
+                        name: "NixOS".to_string(),
+                    });
+                    info!("NixOS collector initialized with {}s interval", config.nixos.interval_seconds);
                 }
+
             }
         }
 
-        // Initialize cache manager with configuration
-        let cache_manager = MetricCacheManager::new(agent_config.cache.clone());
-
-        // Start background cache tasks
-        cache_manager.start_background_tasks().await;
-
         info!(
-            "Metric collection manager initialized with {} collectors and caching enabled",
+            "Metric collection manager initialized with {} collectors",
             collectors.len()
         );
 
         Ok(Self {
             collectors,
-            cache_manager,
-            last_collection_times: HashMap::new(),
             status_tracker: StatusTracker::new(),
+            cached_metrics: Vec::new(),
         })
     }
 
@@ -133,129 +187,80 @@ impl MetricCollectionManager {
         let mut all_metrics = Vec::new();
         let now = Instant::now();
 
-        info!(
+        for timed_collector in &mut self.collectors {
-            "Force collecting from ALL {} collectors for startup",
+            match timed_collector.collector.collect(&mut self.status_tracker).await {
-            self.collectors.len()
-        );
-
-        // Force collection from every collector regardless of intervals
-        for collector in &self.collectors {
-            let collector_name = collector.name();
-
-            match collector.collect(&mut self.status_tracker).await {
                 Ok(metrics) => {
-                    info!(
+                    let metric_count = metrics.len();
-                        "Force collected {} metrics from {} collector",
-                        metrics.len(),
-                        collector_name
-                    );
-
-                    // Cache all new metrics
-                    for metric in &metrics {
-                        self.cache_manager.cache_metric(metric.clone()).await;
-                    }
-
                     all_metrics.extend(metrics);
-                    self.last_collection_times
+                    timed_collector.last_collection = Some(now);
-                        .insert(collector_name.to_string(), now);
+                    debug!("Force collected {} metrics from {}", metric_count, timed_collector.name);
                 }
                 Err(e) => {
-                    error!(
+                    error!("Collector {} failed: {}", timed_collector.name, e);
-                        "Collector '{}' failed during force collection: {}",
-                        collector_name, e
-                    );
-                    // Continue with other collectors even if one fails
                 }
             }
         }
-
+        
-        info!(
+        // Cache the collected metrics
-            "Force collection completed: {} total metrics cached",
+        self.cached_metrics = all_metrics.clone();
-            all_metrics.len()
-        );
         Ok(all_metrics)
     }
 
-    /// Collect metrics from all collectors with intelligent caching
+    /// Collect metrics from collectors whose intervals have elapsed
-    pub async fn collect_all_metrics(&mut self) -> Result<Vec<Metric>> {
+    pub async fn collect_metrics_timed(&mut self) -> Result<Vec<Metric>> {
         let mut all_metrics = Vec::new();
         let now = Instant::now();
 
-        // Collecting metrics from collectors (debug logging disabled for performance)
+        for timed_collector in &mut self.collectors {
-
+            let should_collect = match timed_collector.last_collection {
-        // Keep track of which collector types we're collecting fresh data from
+                None => true, // First collection
-        let mut collecting_fresh = std::collections::HashSet::new();
+                Some(last_time) => now.duration_since(last_time) >= timed_collector.interval,
-
-        // For each collector, check if we need to collect based on time intervals
-        for collector in &self.collectors {
-            let collector_name = collector.name();
-
-            // Determine cache interval for this collector type based on data volatility
-            let cache_interval_secs = match collector_name {
-                "cpu" | "memory" => 5,    // Fast updates for volatile metrics
-                "systemd" => 30,          // Service status changes less frequently
-                "disk" => 300,            // SMART data changes very slowly (5 minutes)
-                "backup" => 600,          // Backup status changes rarely (10 minutes)
-                _ => 30,                  // Default: moderate frequency
             };
 
-            let should_collect =
-                if let Some(last_time) = self.last_collection_times.get(collector_name) {
-                    now.duration_since(*last_time).as_secs() >= cache_interval_secs
-                } else {
-                    true // First collection
-                };
-
             if should_collect {
-                collecting_fresh.insert(collector_name.to_string());
+                match timed_collector.collector.collect(&mut self.status_tracker).await {
-                match collector.collect(&mut self.status_tracker).await {
                     Ok(metrics) => {
-                        // Collector returned fresh metrics (debug logging disabled for performance)
+                        let metric_count = metrics.len();
-
-                        // Cache all new metrics
-                        for metric in &metrics {
-                            self.cache_manager.cache_metric(metric.clone()).await;
-                        }
-
                         all_metrics.extend(metrics);
-                        self.last_collection_times
+                        timed_collector.last_collection = Some(now);
-                            .insert(collector_name.to_string(), now);
+                        debug!(
+                            "Collected {} metrics from {} ({}s interval)",
+                            metric_count,
+                            timed_collector.name,
+                            timed_collector.interval.as_secs()
+                        );
                     }
                     Err(e) => {
-                        error!("Collector '{}' failed: {}", collector_name, e);
+                        error!("Collector {} failed: {}", timed_collector.name, e);
-                        // Continue with other collectors even if one fails
+                        // Update last_collection time even on failure to prevent immediate retries
+                        timed_collector.last_collection = Some(now);
                     }
                 }
-            } else {
-                let _elapsed = self
-                    .last_collection_times
-                    .get(collector_name)
-                    .map(|t| now.duration_since(*t).as_secs())
-                    .unwrap_or(0);
-                // Collector skipped (debug logging disabled for performance)
             }
         }
-
+        
-        // For 2-second intervals, skip cached metrics to avoid duplicates
+        // Update cache with newly collected metrics
-        // (Cache system disabled for realtime updates)
+        if !all_metrics.is_empty() {
-
+            // Merge new metrics with cached metrics (replace by name)
-        // Collected metrics total (debug logging disabled for performance)
+            for new_metric in &all_metrics {
+                // Remove any existing metric with the same name
+                self.cached_metrics.retain(|cached| cached.name != new_metric.name);
+                // Add the new metric
+                self.cached_metrics.push(new_metric.clone());
+            }
+        }
+        
         Ok(all_metrics)
     }
 
-
+    /// Collect metrics from all collectors (legacy method for compatibility)
-    /// Get all cached metrics from the cache manager
+    pub async fn collect_all_metrics(&mut self) -> Result<Vec<Metric>> {
-    pub async fn get_all_cached_metrics(&self) -> Result<Vec<Metric>> {
+        self.collect_metrics_timed().await
-        let cached_metrics = self.cache_manager.get_all_cached_metrics().await?;
-        debug!(
-            "Retrieved {} cached metrics for broadcast",
-            cached_metrics.len()
-        );
-        Ok(cached_metrics)
     }
-
+    
-    pub fn get_cache_manager(&self) -> &MetricCacheManager {
+    /// Get cached metrics without triggering fresh collection
-        &self.cache_manager
+    pub fn get_cached_metrics(&self) -> Vec<Metric> {
+        self.cached_metrics.clone()
     }
 
 }

agent/src/notifications/mod.rs

@@ -59,6 +59,6 @@ impl NotificationManager {
     }
 
     fn is_maintenance_mode(&self) -> bool {
-        std::fs::metadata("/tmp/cm-maintenance").is_ok()
+        std::fs::metadata(&self.config.maintenance_mode_file).is_ok()
     }
 }

agent/src/status/mod.rs

@@ -9,7 +9,6 @@ use chrono::Utc;
 pub struct HostStatusConfig {
     pub enabled: bool,
     pub aggregation_method: String, // "worst_case"
-    pub notification_interval_seconds: u64,
 }
 
 impl Default for HostStatusConfig {
@@ -17,7 +16,6 @@ impl Default for HostStatusConfig {
         Self {
             enabled: true,
             aggregation_method: "worst_case".to_string(),
-            notification_interval_seconds: 30,
         }
     }
 }
@@ -70,7 +68,7 @@ impl HostStatusManager {
 
     /// Update the status of a specific service and recalculate host status
     /// Updates real-time status and buffers changes for email notifications
-    pub fn update_service_status(&mut self, service: String, status: Status, cache_manager: Option<&crate::cache::MetricCacheManager>) {
+    pub fn update_service_status(&mut self, service: String, status: Status) {
         if !self.config.enabled {
             return;
         }
@@ -82,14 +80,6 @@ impl HostStatusManager {
             return;
         }
 
-        // Save cache when status changes (clone cache manager reference for async)
-        if let Some(cache) = cache_manager {
-            let cache = cache.clone();
-            tokio::spawn(async move {
-                cache.save_to_disk().await;
-            });
-        }
-
         // Initialize batch if this is the first change
         if self.batch_start_time.is_none() {
             self.batch_start_time = Some(Instant::now());
@@ -168,25 +158,62 @@ impl HostStatusManager {
 
 
 
-    /// Process a metric - updates status (notifications handled separately via batching)
+    /// Process a metric - updates status and queues for aggregated notifications if status changed
-    pub async fn process_metric(&mut self, metric: &Metric, _notification_manager: &mut crate::notifications::NotificationManager, cache_manager: &crate::cache::MetricCacheManager) {
+    pub async fn process_metric(&mut self, metric: &Metric, _notification_manager: &mut crate::notifications::NotificationManager) -> bool {
-        // Just update status - notifications are handled by process_pending_notifications
+        let old_service_status = self.service_statuses.get(&metric.name).copied();
-        self.update_service_status(metric.name.clone(), metric.status, Some(cache_manager));
+        let old_host_status = self.current_host_status;
+        let new_service_status = metric.status;
+        
+        // Update status (this recalculates host status internally)
+        self.update_service_status(metric.name.clone(), new_service_status);
+        
+        let new_host_status = self.current_host_status;
+        let mut status_changed = false;
+        
+        // Check if service status actually changed (ignore first-time status setting)
+        if let Some(old_service_status) = old_service_status {
+            if old_service_status != new_service_status {
+                debug!("Service status change detected for {}: {:?} -> {:?}", metric.name, old_service_status, new_service_status);
+                
+                // Queue change for aggregated notification (not immediate)
+                self.queue_status_change(&metric.name, old_service_status, new_service_status);
+                
+                status_changed = true;
+            }
+        } else {
+            debug!("Initial status set for {}: {:?}", metric.name, new_service_status);
+        }
+        
+        // Check if host status changed (this should trigger immediate transmission)
+        if old_host_status != new_host_status {
+            debug!("Host status change detected: {:?} -> {:?}", old_host_status, new_host_status);
+            status_changed = true;
+        }
+        
+        status_changed // Return true if either service or host status changed
     }
 
-    /// Process pending notifications - call this at notification intervals
+    /// Queue status change for aggregated notification
+    fn queue_status_change(&mut self, metric_name: &str, old_status: Status, new_status: Status) {
+        // Add to pending changes for aggregated notification
+        let entry = self.pending_changes.entry(metric_name.to_string()).or_insert((old_status, old_status, 0));
+        entry.1 = new_status; // Update final status
+        entry.2 += 1; // Increment change count
+        
+        // Set batch start time if this is the first change
+        if self.batch_start_time.is_none() {
+            self.batch_start_time = Some(Instant::now());
+        }
+    }
+
+
+    /// Process pending notifications - legacy method, now rarely used
     pub async fn process_pending_notifications(&mut self, notification_manager: &mut crate::notifications::NotificationManager) -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
         if !self.config.enabled || self.pending_changes.is_empty() {
             return Ok(());
         }
 
-        let batch_start = self.batch_start_time.unwrap_or_else(Instant::now);
+        // Process notifications immediately without interval batching
-        let batch_duration = batch_start.elapsed();
-        
-        // Only process if enough time has passed
-        if batch_duration.as_secs() < self.config.notification_interval_seconds {
-            return Ok(());
-        }
 
         // Create aggregated status changes
         let aggregated = self.create_aggregated_changes();
@@ -245,11 +272,13 @@ impl HostStatusManager {
     /// Check if a status change is significant enough for notification
     fn is_significant_change(&self, old_status: Status, new_status: Status) -> bool {
         match (old_status, new_status) {
-            // Always notify on problems
+            // Don't notify on transitions from Unknown (startup/restart scenario)
+            (Status::Unknown, _) => false,
+            // Always notify on problems (but not from Unknown)
             (_, Status::Warning) | (_, Status::Critical) => true,
             // Only notify on recovery if it's from a problem state to OK and all services are OK
             (Status::Warning | Status::Critical, Status::Ok) => self.current_host_status == Status::Ok,
-            // Don't notify on startup or other transitions
+            // Don't notify on other transitions
             _ => false,
         }
     }
@@ -347,8 +376,8 @@ impl HostStatusManager {
             details.push('\n');
         }
 
-        // Show recoveries
+        // Show recoveries only if host status is now OK (all services recovered)
-        if !recovery_changes.is_empty() {
+        if !recovery_changes.is_empty() && aggregated.host_status_final == Status::Ok {
             details.push_str(&format!("✅ RECOVERIES ({}):\n", recovery_changes.len()));
             for change in recovery_changes {
                 details.push_str(&format!("  {}\n", change));

dashboard/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "cm-dashboard"
-version = "0.1.0"
+version = "0.1.170"
 edition = "2021"
 
 [dependencies]
@@ -18,4 +18,5 @@ tracing-subscriber = { workspace = true }
 ratatui = { workspace = true }
 crossterm = { workspace = true }
 toml = { workspace = true }
-gethostname = { workspace = true }
+gethostname = { workspace = true }
+wake-on-lan = "0.2"

dashboard/src/app.rs

@@ -9,14 +9,13 @@ use std::io;
 use std::time::{Duration, Instant};
 use tracing::{debug, error, info, warn};
 
-use crate::communication::{AgentCommand, ServiceAction, ZmqCommandSender, ZmqConsumer};
+use crate::communication::{ZmqConsumer};
 use crate::config::DashboardConfig;
 use crate::metrics::MetricStore;
-use crate::ui::{TuiApp, UiCommand};
+use crate::ui::TuiApp;
 
 pub struct Dashboard {
     zmq_consumer: ZmqConsumer,
-    zmq_command_sender: ZmqCommandSender,
     metric_store: MetricStore,
     tui_app: Option<TuiApp>,
     terminal: Option<Terminal<CrosstermBackend<io::Stdout>>>,
@@ -58,20 +57,9 @@ impl Dashboard {
             }
         };
 
-        // Initialize ZMQ command sender
-        let zmq_command_sender = match ZmqCommandSender::new(&config.zmq) {
-            Ok(sender) => sender,
-            Err(e) => {
-                error!("Failed to initialize ZMQ command sender: {}", e);
-                return Err(e);
-            }
-        };
-
-        // Connect to predefined hosts from configuration
-        let hosts = config.hosts.predefined_hosts.clone();
 
         // Try to connect to hosts but don't fail if none are available
-        match zmq_consumer.connect_to_predefined_hosts(&hosts).await {
+        match zmq_consumer.connect_to_predefined_hosts(&config.hosts).await {
             Ok(_) => info!("Successfully connected to ZMQ hosts"),
             Err(e) => {
                 warn!(
@@ -91,7 +79,7 @@ impl Dashboard {
             (None, None)
         } else {
             // Initialize TUI app
-            let tui_app = TuiApp::new();
+            let tui_app = TuiApp::new(config.clone());
 
             // Setup terminal
             if let Err(e) = enable_raw_mode() {
@@ -127,7 +115,6 @@ impl Dashboard {
 
         Ok(Self {
             zmq_consumer,
-            zmq_command_sender,
             metric_store,
             tui_app,
             terminal,
@@ -137,18 +124,14 @@ impl Dashboard {
         })
     }
 
-    /// Send a command to a specific agent
-    pub async fn send_command(&mut self, hostname: &str, command: AgentCommand) -> Result<()> {
-        self.zmq_command_sender
-            .send_command(hostname, command)
-            .await
-    }
 
     pub async fn run(&mut self) -> Result<()> {
         info!("Starting dashboard main loop");
 
         let mut last_metrics_check = Instant::now();
         let metrics_check_interval = Duration::from_millis(100); // Check for metrics every 100ms
+        let mut last_heartbeat_check = Instant::now();
+        let heartbeat_check_interval = Duration::from_secs(1); // Check for host connectivity every 1 second
 
         loop {
             // Handle terminal events (keyboard input) only if not headless
@@ -158,16 +141,10 @@ impl Dashboard {
                         match event::read() {
                             Ok(event) => {
                                 if let Some(ref mut tui_app) = self.tui_app {
-                                    // Handle input and check for commands
+                                    // Handle input
                                     match tui_app.handle_input(event) {
-                                        Ok(Some(command)) => {
+                                        Ok(_) => {
-                                            // Execute the command
+                                            // Check if we should quit
-                                            if let Err(e) = self.execute_ui_command(command).await {
-                                                error!("Failed to execute UI command: {}", e);
-                                            }
-                                        }
-                                        Ok(None) => {
-                                            // No command, check if we should quit
                                             if tui_app.should_quit() {
                                                 info!("Quit requested, exiting dashboard");
                                                 break;
@@ -191,89 +168,95 @@ impl Dashboard {
                         break;
                     }
                 }
+
+                // Render UI immediately after handling input for responsive feedback
+                if let Some(ref mut terminal) = self.terminal {
+                    if let Some(ref mut tui_app) = self.tui_app {
+                        if let Err(e) = terminal.draw(|frame| {
+                            tui_app.render(frame, &self.metric_store);
+                        }) {
+                            error!("Error rendering TUI after input: {}", e);
+                        }
+                    }
+                }
             }
 
             // Check for new metrics
             if last_metrics_check.elapsed() >= metrics_check_interval {
-                if let Ok(Some(metric_message)) = self.zmq_consumer.receive_metrics().await {
+                if let Ok(Some(agent_data)) = self.zmq_consumer.receive_agent_data().await {
                     debug!(
-                        "Received metrics from {}: {} metrics",
+                        "Received agent data from {}",
-                        metric_message.hostname,
+                        agent_data.hostname
-                        metric_message.metrics.len()
                     );
 
-                    // Check if this is the first time we've seen this host
+                    // Track first contact with host (no command needed - agent sends data every 2s)
                     let is_new_host = !self
                         .initial_commands_sent
-                        .contains(&metric_message.hostname);
+                        .contains(&agent_data.hostname);
 
                     if is_new_host {
                         info!(
-                            "First contact with host {}, sending initial CollectNow command",
+                            "First contact with host {} - data will update automatically",
-                            metric_message.hostname
+                            agent_data.hostname
                         );
+                        self.initial_commands_sent
+                            .insert(agent_data.hostname.clone());
+                    }
 
-                        // Send CollectNow command for immediate refresh
+                    // Store structured data directly
-                        if let Err(e) = self
+                    self.metric_store.store_agent_data(agent_data);
-                            .send_command(&metric_message.hostname, AgentCommand::CollectNow)
+
-                            .await
+                    // Check for agent version mismatches across hosts
-                        {
+                    if let Some((current_version, outdated_hosts)) = self.metric_store.get_version_mismatches() {
-                            error!(
+                        for outdated_host in &outdated_hosts {
-                                "Failed to send initial CollectNow command to {}: {}",
+                            warn!("Host {} has outdated agent version (current: {})", outdated_host, current_version);
-                                metric_message.hostname, e
-                            );
-                        } else {
-                            info!(
-                                "✓ Sent initial CollectNow command to {}",
-                                metric_message.hostname
-                            );
-                            self.initial_commands_sent
-                                .insert(metric_message.hostname.clone());
                         }
                     }
 
-                    // Update metric store
+                    // Update TUI with new metrics (only if not headless)
-                    self.metric_store
-                        .update_metrics(&metric_message.hostname, metric_message.metrics);
-
-                    // Update TUI with new hosts and metrics (only if not headless)
                     if let Some(ref mut tui_app) = self.tui_app {
-                        let mut connected_hosts = self
-                            .metric_store
-                            .get_connected_hosts(Duration::from_secs(30));
-                        
-                        // Add hosts that are rebuilding but may be temporarily disconnected
-                        // Use extended timeout (5 minutes) for rebuilding hosts
-                        let rebuilding_hosts = self
-                            .metric_store
-                            .get_connected_hosts(Duration::from_secs(300));
-                        
-                        for host in rebuilding_hosts {
-                            if !connected_hosts.contains(&host) {
-                                // Check if this host is rebuilding in the UI
-                                if tui_app.is_host_rebuilding(&host) {
-                                    connected_hosts.push(host);
-                                }
-                            }
-                        }
-                        
-                        tui_app.update_hosts(connected_hosts);
                         tui_app.update_metrics(&self.metric_store);
                     }
                 }
+                
+                // Also check for command output messages
+                if let Ok(Some(cmd_output)) = self.zmq_consumer.receive_command_output().await {
+                    debug!(
+                        "Received command output from {}: {}",
+                        cmd_output.hostname,
+                        cmd_output.output_line
+                    );
+
+                    // Command output (terminal popup removed - output not displayed)
+                }
+                
                 last_metrics_check = Instant::now();
             }
 
+            // Check for host connectivity changes (heartbeat timeouts) periodically
+            if last_heartbeat_check.elapsed() >= heartbeat_check_interval {
+                let timeout = Duration::from_secs(self.config.zmq.heartbeat_timeout_seconds);
+                
+                // Clean up metrics for offline hosts
+                self.metric_store.cleanup_offline_hosts(timeout);
+                
+                if let Some(ref mut tui_app) = self.tui_app {
+                    let connected_hosts = self.metric_store.get_connected_hosts(timeout);
+                    tui_app.update_hosts(connected_hosts);
+                }
+                last_heartbeat_check = Instant::now();
+            }
+
             // Render TUI (only if not headless)
             if !self.headless {
-                if let (Some(ref mut terminal), Some(ref mut tui_app)) =
+                if let Some(ref mut terminal) = self.terminal {
-                    (&mut self.terminal, &mut self.tui_app)
+                    if let Some(ref mut tui_app) = self.tui_app {
-                {
+                        if let Err(e) = terminal.draw(|frame| {
-                    if let Err(e) = terminal.draw(|frame| {
+                            tui_app.render(frame, &self.metric_store);
-                        tui_app.render(frame, &self.metric_store);
+                        }) {
-                    }) {
+                            error!("Error rendering TUI: {}", e);
-                        error!("Error rendering TUI: {}", e);
+                            break;
-                        break;
+                        }
                     }
                 }
             }
@@ -286,67 +269,7 @@ impl Dashboard {
         Ok(())
     }
 
-    /// Execute a UI command by sending it to the appropriate agent
-    async fn execute_ui_command(&self, command: UiCommand) -> Result<()> {
-        match command {
-            UiCommand::ServiceRestart { hostname, service_name } => {
-                info!("Sending restart command for service {} on {}", service_name, hostname);
-                let agent_command = AgentCommand::ServiceControl {
-                    service_name,
-                    action: ServiceAction::Restart,
-                };
-                self.zmq_command_sender.send_command(&hostname, agent_command).await?;
-            }
-            UiCommand::ServiceStart { hostname, service_name } => {
-                info!("Sending start command for service {} on {}", service_name, hostname);
-                let agent_command = AgentCommand::ServiceControl {
-                    service_name: service_name.clone(),
-                    action: ServiceAction::Start,
-                };
-                self.zmq_command_sender.send_command(&hostname, agent_command).await?;
-            }
-            UiCommand::ServiceStop { hostname, service_name } => {
-                info!("Sending stop command for service {} on {}", service_name, hostname);
-                let agent_command = AgentCommand::ServiceControl {
-                    service_name: service_name.clone(),
-                    action: ServiceAction::Stop,
-                };
-                self.zmq_command_sender.send_command(&hostname, agent_command).await?;
-            }
-            UiCommand::SystemRebuild { hostname } => {
-                info!("Sending system rebuild command to {}", hostname);
-                let agent_command = AgentCommand::SystemRebuild { 
-                    git_url: self.config.system.nixos_config_git_url.clone(),
-                    git_branch: self.config.system.nixos_config_branch.clone(),
-                    working_dir: self.config.system.nixos_config_working_dir.clone(),
-                    api_key_file: self.config.system.nixos_config_api_key_file.clone(),
-                };
-                self.zmq_command_sender.send_command(&hostname, agent_command).await?;
-            }
-            UiCommand::TriggerBackup { hostname } => {
-                info!("Trigger backup requested for {}", hostname);
-                // TODO: Implement backup trigger command
-                info!("Backup trigger not yet implemented");
-            }
-        }
-        Ok(())
-    }
 
-    /// Get current service status from metrics to determine start/stop action
-    fn get_service_status(&self, hostname: &str, service_name: &str) -> Option<String> {
-        let metrics = self.metric_store.get_metrics_for_host(hostname);
-        
-        // Look for systemd service status metric
-        for metric in metrics {
-            if metric.name == format!("systemd_{}_status", service_name) {
-                if let cm_dashboard_shared::MetricValue::String(status) = &metric.value {
-                    return Some(status.clone());
-                }
-            }
-        }
-        
-        None
-    }
 }
 
 impl Drop for Dashboard {

dashboard/src/communication/mod.rs

@@ -1,43 +1,10 @@
 use anyhow::Result;
-use cm_dashboard_shared::{MessageEnvelope, MessageType, MetricMessage};
+use cm_dashboard_shared::{AgentData, CommandOutputMessage, MessageEnvelope, MessageType};
 use tracing::{debug, error, info, warn};
 use zmq::{Context, Socket, SocketType};
 
 use crate::config::ZmqConfig;
 
-/// Commands that can be sent to agents
-#[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,
-    /// Control systemd service
-    ServiceControl {
-        service_name: String,
-        action: ServiceAction,
-    },
-    /// Rebuild NixOS system
-    SystemRebuild {
-        git_url: String,
-        git_branch: String,
-        working_dir: String,
-        api_key_file: Option<String>,
-    },
-}
-
-/// Service control actions
-#[derive(Debug, Clone, serde::Deserialize, serde::Serialize)]
-pub enum ServiceAction {
-    Start,
-    Stop,
-    Restart,
-    Status,
-}
 
 /// ZMQ consumer for receiving metrics from agents
 pub struct ZmqConsumer {
@@ -83,13 +50,14 @@ impl ZmqConsumer {
         }
     }
 
-    /// Connect to predefined hosts
+
-    pub async fn connect_to_predefined_hosts(&mut self, hosts: &[String]) -> Result<()> {
+    /// Connect to predefined hosts using their configuration
+    pub async fn connect_to_predefined_hosts(&mut self, hosts: &std::collections::HashMap<String, crate::config::HostDetails>) -> Result<()> {
         let default_port = self.config.subscriber_ports[0];
 
-        for hostname in hosts {
+        for (hostname, host_details) in hosts {
-            // Try to connect, but don't fail if some hosts are unreachable
+            // Try to connect using configured IP, but don't fail if some hosts are unreachable
-            if let Err(e) = self.connect_to_host(hostname, default_port).await {
+            if let Err(e) = self.connect_to_host_with_details(hostname, host_details, default_port).await {
                 warn!("Could not connect to {}: {}", hostname, e);
             }
         }
@@ -103,8 +71,54 @@ impl ZmqConsumer {
         Ok(())
     }
 
-    /// Receive metrics from any connected agent (non-blocking)
+    /// Connect to a host using its configuration details
-    pub async fn receive_metrics(&mut self) -> Result<Option<MetricMessage>> {
+    pub async fn connect_to_host_with_details(&mut self, hostname: &str, host_details: &crate::config::HostDetails, port: u16) -> Result<()> {
+        // Get primary connection IP only - no fallbacks
+        let primary_ip = host_details.get_connection_ip(hostname);
+        
+        // Connect directly without fallback attempts
+        self.connect_to_host(&primary_ip, port).await
+    }
+
+    /// Receive command output from any connected agent (non-blocking)  
+    pub async fn receive_command_output(&mut self) -> Result<Option<CommandOutputMessage>> {
+        match self.subscriber.recv_bytes(zmq::DONTWAIT) {
+            Ok(data) => {
+                // Deserialize envelope
+                let envelope: MessageEnvelope = serde_json::from_slice(&data)
+                    .map_err(|e| anyhow::anyhow!("Failed to deserialize envelope: {}", e))?;
+
+                // Check message type
+                match envelope.message_type {
+                    MessageType::CommandOutput => {
+                        let cmd_output = envelope
+                            .decode_command_output()
+                            .map_err(|e| anyhow::anyhow!("Failed to decode command output: {}", e))?;
+
+                        debug!(
+                            "Received command output from {}: {}",
+                            cmd_output.hostname,
+                            cmd_output.output_line
+                        );
+
+                        Ok(Some(cmd_output))
+                    }
+                    _ => Ok(None), // Not a command output message
+                }
+            }
+            Err(zmq::Error::EAGAIN) => {
+                // No message available (non-blocking mode)
+                Ok(None)
+            }
+            Err(e) => {
+                error!("ZMQ receive error: {}", e);
+                Err(anyhow::anyhow!("ZMQ receive error: {}", e))
+            }
+        }
+    }
+
+    /// Receive agent data (non-blocking)
+    pub async fn receive_agent_data(&mut self) -> Result<Option<AgentData>> {
         match self.subscriber.recv_bytes(zmq::DONTWAIT) {
             Ok(data) => {
                 debug!("Received {} bytes from ZMQ", data.len());
@@ -115,25 +129,27 @@ impl ZmqConsumer {
 
                 // Check message type
                 match envelope.message_type {
-                    MessageType::Metrics => {
+                    MessageType::AgentData => {
-                        let metrics = envelope
+                        let agent_data = envelope
-                            .decode_metrics()
+                            .decode_agent_data()
-                            .map_err(|e| anyhow::anyhow!("Failed to decode metrics: {}", e))?;
+                            .map_err(|e| anyhow::anyhow!("Failed to decode agent data: {}", e))?;
 
                         debug!(
-                            "Received {} metrics from {}",
+                            "Received agent data from host {}",
-                            metrics.metrics.len(),
+                            agent_data.hostname
-                            metrics.hostname
                         );
-
+                        Ok(Some(agent_data))
-                        Ok(Some(metrics))
                     }
                     MessageType::Heartbeat => {
                         debug!("Received heartbeat");
-                        Ok(None) // Don't return heartbeats as metrics
+                        Ok(None) // Don't return heartbeats
+                    }
+                    MessageType::CommandOutput => {
+                        debug!("Received command output (will be handled by receive_command_output)");
+                        Ok(None) // Command output handled by separate method
                     }
                     _ => {
-                        debug!("Received non-metrics message: {:?}", envelope.message_type);
+                        debug!("Received unsupported message: {:?}", envelope.message_type);
                         Ok(None)
                     }
                 }
@@ -148,44 +164,6 @@ impl ZmqConsumer {
             }
         }
     }
+
 }
 
-/// ZMQ command sender for sending commands to agents
-pub struct ZmqCommandSender {
-    context: Context,
-}
-
-impl ZmqCommandSender {
-    pub fn new(_config: &ZmqConfig) -> Result<Self> {
-        let context = Context::new();
-
-        info!("ZMQ command sender initialized");
-
-        Ok(Self { context })
-    }
-
-    /// Send a command to a specific agent
-    pub async fn send_command(&self, hostname: &str, command: AgentCommand) -> Result<()> {
-        // Create a new PUSH socket for this command (ZMQ best practice)
-        let socket = self.context.socket(SocketType::PUSH)?;
-
-        // Set socket options
-        socket.set_linger(1000)?; // Wait up to 1 second on close
-        socket.set_sndtimeo(5000)?; // 5 second send timeout
-
-        // Connect to agent's command port (6131)
-        let address = format!("tcp://{}:6131", hostname);
-        socket.connect(&address)?;
-
-        // Serialize command
-        let serialized = serde_json::to_vec(&command)?;
-
-        // Send command
-        socket.send(&serialized, 0)?;
-
-        info!("Sent command {:?} to agent at {}", command, hostname);
-
-        // Socket will be automatically closed when dropped
-        Ok(())
-    }
-}

dashboard/src/config/mod.rs

@@ -6,20 +6,40 @@ use std::path::Path;
 #[derive(Debug, Clone, Serialize, Deserialize)]
 pub struct DashboardConfig {
     pub zmq: ZmqConfig,
-    pub hosts: HostsConfig,
+    pub hosts: std::collections::HashMap<String, HostDetails>,
     pub system: SystemConfig,
+    pub ssh: SshConfig,
+    pub service_logs: std::collections::HashMap<String, Vec<ServiceLogConfig>>,
 }
 
 /// ZMQ consumer configuration
 #[derive(Debug, Clone, Serialize, Deserialize)]
 pub struct ZmqConfig {
     pub subscriber_ports: Vec<u16>,
+    /// Heartbeat timeout in seconds - hosts considered offline if no heartbeat received within this time
+    #[serde(default = "default_heartbeat_timeout_seconds")]
+    pub heartbeat_timeout_seconds: u64,
 }
 
-/// Hosts configuration
+fn default_heartbeat_timeout_seconds() -> u64 {
+    10 // Default to 10 seconds - allows for multiple missed heartbeats
+}
+
+/// Individual host configuration details
 #[derive(Debug, Clone, Serialize, Deserialize)]
-pub struct HostsConfig {
+pub struct HostDetails {
-    pub predefined_hosts: Vec<String>,
+    pub mac_address: Option<String>,
+    /// Primary IP address (local network)
+    pub ip: Option<String>,
+}
+
+
+impl HostDetails {
+    /// Get the IP address for connection (uses ip field or hostname as fallback)
+    pub fn get_connection_ip(&self, hostname: &str) -> String {
+        self.ip.as_ref().unwrap_or(&hostname.to_string()).clone()
+    }
+
 }
 
 /// System configuration
@@ -31,6 +51,21 @@ pub struct SystemConfig {
     pub nixos_config_api_key_file: Option<String>,
 }
 
+/// SSH configuration for rebuild and backup operations
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct SshConfig {
+    pub rebuild_user: String,
+    pub rebuild_cmd: String,
+    pub service_manage_cmd: String,
+}
+
+/// Service log file configuration per host
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct ServiceLogConfig {
+    pub service_name: String,
+    pub log_file_path: String,
+}
+
 impl DashboardConfig {
     pub fn load_from_file<P: AsRef<Path>>(path: P) -> Result<Self> {
         let path = path.as_ref();
@@ -52,8 +87,3 @@ impl Default for ZmqConfig {
     }
 }
 
-impl Default for HostsConfig {
-    fn default() -> Self {
-        panic!("Dashboard configuration must be loaded from file - no hardcoded defaults allowed")
-    }
-}

dashboard/src/main.rs

@@ -1,5 +1,6 @@
 use anyhow::Result;
 use clap::Parser;
+use std::process;
 use tracing::{error, info};
 use tracing_subscriber::EnvFilter;
 
@@ -11,6 +12,29 @@ mod ui;
 
 use app::Dashboard;
 
+
+/// Check if running inside tmux session
+fn check_tmux_session() {
+    // Check for TMUX environment variable which is set when inside a tmux session
+    if std::env::var("TMUX").is_err() {
+        eprintln!("╭─────────────────────────────────────────────────────────────╮");
+        eprintln!("│                        ⚠️  TMUX REQUIRED                      │");
+        eprintln!("├─────────────────────────────────────────────────────────────┤");
+        eprintln!("│  CM Dashboard must be run inside a tmux session for proper   │");
+        eprintln!("│  terminal handling and remote operation functionality.       │");
+        eprintln!("│                                                             │");
+        eprintln!("│  Please start a tmux session first:                        │");
+        eprintln!("│    tmux new-session -d -s dashboard cm-dashboard           │");
+        eprintln!("│    tmux attach-session -t dashboard                        │");
+        eprintln!("│                                                             │");
+        eprintln!("│  Or simply:                                                 │");
+        eprintln!("│    tmux                                                     │");
+        eprintln!("│    cm-dashboard                                             │");
+        eprintln!("╰─────────────────────────────────────────────────────────────╯");
+        process::exit(1);
+    }
+}
+
 #[derive(Parser)]
 #[command(name = "cm-dashboard")]
 #[command(about = "CM Dashboard TUI with individual metric consumption")]
@@ -52,6 +76,11 @@ async fn main() -> Result<()> {
             .init();
     }
 
+    // Check for tmux session requirement (only for TUI mode)
+    if !cli.headless {
+        check_tmux_session();
+    }
+
     if cli.headless || cli.verbose > 0 {
         info!("CM Dashboard starting with individual metrics architecture...");
     }

dashboard/src/metrics/store.rs

@@ -1,4 +1,4 @@
-use cm_dashboard_shared::Metric;
+use cm_dashboard_shared::AgentData;
 use std::collections::HashMap;
 use std::time::{Duration, Instant};
 use tracing::{debug, info, warn};
@@ -7,12 +7,12 @@ use super::MetricDataPoint;
 
 /// Central metric storage for the dashboard
 pub struct MetricStore {
-    /// Current metrics: hostname -> metric_name -> metric
+    /// Current structured data: hostname -> AgentData
-    current_metrics: HashMap<String, HashMap<String, Metric>>,
+    current_agent_data: HashMap<String, AgentData>,
     /// Historical metrics for trending
     historical_metrics: HashMap<String, Vec<MetricDataPoint>>,
-    /// Last update timestamp per host
+    /// Last heartbeat timestamp per host
-    last_update: HashMap<String, Instant>,
+    last_heartbeat: HashMap<String, Instant>,
     /// Configuration
     max_metrics_per_host: usize,
     history_retention: Duration,
@@ -21,89 +21,91 @@ pub struct MetricStore {
 impl MetricStore {
     pub fn new(max_metrics_per_host: usize, history_retention_hours: u64) -> Self {
         Self {
-            current_metrics: HashMap::new(),
+            current_agent_data: HashMap::new(),
             historical_metrics: HashMap::new(),
-            last_update: HashMap::new(),
+            last_heartbeat: HashMap::new(),
             max_metrics_per_host,
             history_retention: Duration::from_secs(history_retention_hours * 3600),
         }
     }
 
-    /// Update metrics for a specific host
+
-    pub fn update_metrics(&mut self, hostname: &str, metrics: Vec<Metric>) {
+    /// Store structured agent data directly
+    pub fn store_agent_data(&mut self, agent_data: AgentData) {
         let now = Instant::now();
+        let hostname = agent_data.hostname.clone();
 
-        debug!("Updating {} metrics for host {}", metrics.len(), hostname);
+        debug!("Storing structured data for host {}", hostname);
 
-        // Get or create host entry
+        // Store the structured data directly
-        let host_metrics = self
+        self.current_agent_data.insert(hostname.clone(), agent_data);
-            .current_metrics
-            .entry(hostname.to_string())
-            .or_insert_with(HashMap::new);
 
-        // Get or create historical entry
+        // Update heartbeat timestamp
+        self.last_heartbeat.insert(hostname.clone(), now);
+        debug!("Updated heartbeat for host {}", hostname);
+
+        // Add to history
         let host_history = self
             .historical_metrics
-            .entry(hostname.to_string())
+            .entry(hostname.clone())
             .or_insert_with(Vec::new);
+        host_history.push(MetricDataPoint { received_at: now });
 
-        // Update current metrics and add to history
+        // Cleanup old data
-        for metric in metrics {
+        self.cleanup_host_data(&hostname);
-            let metric_name = metric.name.clone();
 
-            // Store current metric
+        info!("Stored structured data for {}", hostname);
-            host_metrics.insert(metric_name.clone(), metric.clone());
-
-            // Add to history
-            host_history.push(MetricDataPoint { received_at: now });
-        }
-
-        // Update last update timestamp
-        self.last_update.insert(hostname.to_string(), now);
-
-        // Get metrics count before cleanup
-        let metrics_count = host_metrics.len();
-
-        // Cleanup old history and enforce limits
-        self.cleanup_host_data(hostname);
-
-        info!(
-            "Updated metrics for {}: {} current metrics",
-            hostname, metrics_count
-        );
-    }
-
-    /// Get current metric for a specific host
-    pub fn get_metric(&self, hostname: &str, metric_name: &str) -> Option<&Metric> {
-        self.current_metrics.get(hostname)?.get(metric_name)
     }
 
 
-    /// Get all current metrics for a host as a vector
+
-    pub fn get_metrics_for_host(&self, hostname: &str) -> Vec<&Metric> {
+
-        if let Some(metrics_map) = self.current_metrics.get(hostname) {
+    /// Get current structured data for a host
-            metrics_map.values().collect()
+    pub fn get_agent_data(&self, hostname: &str) -> Option<&AgentData> {
-        } else {
+        self.current_agent_data.get(hostname)
-            Vec::new()
-        }
     }
 
-    /// Get connected hosts (hosts with recent updates)
+
+    /// Get connected hosts (hosts with recent heartbeats)
     pub fn get_connected_hosts(&self, timeout: Duration) -> Vec<String> {
         let now = Instant::now();
 
-        self.last_update
+        self.last_heartbeat
             .iter()
-            .filter_map(|(hostname, &last_update)| {
+            .filter_map(|(hostname, &last_heartbeat)| {
-                if now.duration_since(last_update) <= timeout {
+                if now.duration_since(last_heartbeat) <= timeout {
                     Some(hostname.clone())
                 } else {
+                    debug!("Host {} considered offline - last heartbeat was {:?} ago", 
+                           hostname, now.duration_since(last_heartbeat));
                     None
                 }
             })
             .collect()
     }
 
+    /// Clean up data for offline hosts
+    pub fn cleanup_offline_hosts(&mut self, timeout: Duration) {
+        let now = Instant::now();
+        let mut hosts_to_cleanup = Vec::new();
+
+        // Find hosts that are offline (no recent heartbeat)
+        for (hostname, &last_heartbeat) in &self.last_heartbeat {
+            if now.duration_since(last_heartbeat) > timeout {
+                hosts_to_cleanup.push(hostname.clone());
+            }
+        }
+
+        // Clear data for offline hosts
+        for hostname in hosts_to_cleanup {
+            if let Some(_agent_data) = self.current_agent_data.remove(&hostname) {
+                info!("Cleared structured data for offline host: {}", hostname);
+            }
+            // Keep heartbeat timestamp for reconnection detection
+            // Don't remove from last_heartbeat to track when host was last seen
+        }
+    }
+
     /// Cleanup old data and enforce limits
     fn cleanup_host_data(&mut self, hostname: &str) {
         let now = Instant::now();
@@ -124,4 +126,48 @@ impl MetricStore {
             }
         }
     }
+
+    /// Get agent versions from all hosts for cross-host comparison
+    pub fn get_agent_versions(&self) -> HashMap<String, String> {
+        let mut versions = HashMap::new();
+        
+        for (hostname, agent_data) in &self.current_agent_data {
+            versions.insert(hostname.clone(), agent_data.agent_version.clone());
+        }
+        
+        versions
+    }
+
+    /// Check for agent version mismatches across hosts
+    pub fn get_version_mismatches(&self) -> Option<(String, Vec<String>)> {
+        let versions = self.get_agent_versions();
+        
+        if versions.len() < 2 {
+            return None; // Need at least 2 hosts to compare
+        }
+        
+        // Find the most common version (assume it's the "current" version)
+        let mut version_counts = HashMap::new();
+        for version in versions.values() {
+            *version_counts.entry(version.clone()).or_insert(0) += 1;
+        }
+        
+        let most_common_version = version_counts
+            .iter()
+            .max_by_key(|(_, count)| *count)
+            .map(|(version, _)| version.clone())?;
+        
+        // Find hosts with different versions
+        let outdated_hosts: Vec<String> = versions
+            .iter()
+            .filter(|(_, version)| *version != &most_common_version)
+            .map(|(hostname, _)| hostname.clone())
+            .collect();
+        
+        if outdated_hosts.is_empty() {
+            None
+        } else {
+            Some((most_common_version, outdated_hosts))
+        }
+    }
 }

dashboard/src/ui/mod.rs

@@ -1,5 +1,5 @@
 use anyhow::Result;
-use crossterm::event::{Event, KeyCode, KeyModifiers};
+use crossterm::event::{Event, KeyCode};
 use ratatui::{
     layout::{Constraint, Direction, Layout, Rect},
     style::Style,
@@ -7,80 +7,23 @@ use ratatui::{
     Frame,
 };
 use std::collections::HashMap;
-use std::time::{Duration, Instant};
+use std::time::Instant;
 use tracing::info;
+use wake_on_lan::MagicPacket;
 
 pub mod theme;
 pub mod widgets;
 
+use crate::config::DashboardConfig;
 use crate::metrics::MetricStore;
-use cm_dashboard_shared::{Metric, Status};
+use cm_dashboard_shared::Status;
-use theme::{Components, Layout as ThemeLayout, StatusIcons, Theme, Typography};
+use theme::{Components, Layout as ThemeLayout, Theme, Typography};
-use widgets::{BackupWidget, ServicesWidget, SystemWidget, Widget};
+use widgets::{ServicesWidget, SystemWidget, Widget};
 
-/// Commands that can be triggered from the UI
-#[derive(Debug, Clone)]
-pub enum UiCommand {
-    ServiceRestart { hostname: String, service_name: String },
-    ServiceStart { hostname: String, service_name: String },
-    ServiceStop { hostname: String, service_name: String },
-    SystemRebuild { hostname: String },
-    TriggerBackup { hostname: String },
-}
 
-/// Command execution status for visual feedback
-#[derive(Debug, Clone)]
-pub enum CommandStatus {
-    /// Command is executing
-    InProgress { command_type: CommandType, target: String, start_time: std::time::Instant },
-    /// Command completed successfully
-    Success { command_type: CommandType, target: String, duration: std::time::Duration, completed_at: std::time::Instant },
-    /// Command failed
-    Failed { command_type: CommandType, target: String, error: String, failed_at: std::time::Instant },
-}
 
-/// Types of commands for status tracking
-#[derive(Debug, Clone)]
-pub enum CommandType {
-    ServiceRestart,
-    ServiceStart,
-    ServiceStop,
-    SystemRebuild,
-    BackupTrigger,
-}
 
 /// Panel types for focus management
-#[derive(Debug, Clone, Copy, PartialEq, Eq)]
-pub enum PanelType {
-    System,
-    Services,
-    Backup,
-}
-
-impl PanelType {
-    /// Get all panel types in order
-    pub fn all() -> [PanelType; 3] {
-        [PanelType::System, PanelType::Services, PanelType::Backup]
-    }
-    
-    /// Get the next panel in cycle (System → Services → Backup → System)
-    pub fn next(self) -> PanelType {
-        match self {
-            PanelType::System => PanelType::Services,
-            PanelType::Services => PanelType::Backup,
-            PanelType::Backup => PanelType::System,
-        }
-    }
-    
-    /// Get the previous panel in cycle (System ← Services ← Backup ← System)
-    pub fn previous(self) -> PanelType {
-        match self {
-            PanelType::System => PanelType::Backup,
-            PanelType::Services => PanelType::System,
-            PanelType::Backup => PanelType::Services,
-        }
-    }
-}
 
 /// Widget states for a specific host
 #[derive(Clone)]
@@ -89,16 +32,8 @@ pub struct HostWidgets {
     pub system_widget: SystemWidget,
     /// Services widget state
     pub services_widget: ServicesWidget,
-    /// Backup widget state
-    pub backup_widget: BackupWidget,
-    /// Scroll offsets for each panel
-    pub system_scroll_offset: usize,
-    pub services_scroll_offset: usize,
-    pub backup_scroll_offset: usize,
     /// Last update time for this host
     pub last_update: Option<Instant>,
-    /// Active command status for visual feedback
-    pub command_status: Option<CommandStatus>,
 }
 
 impl HostWidgets {
@@ -106,16 +41,12 @@ impl HostWidgets {
         Self {
             system_widget: SystemWidget::new(),
             services_widget: ServicesWidget::new(),
-            backup_widget: BackupWidget::new(),
-            system_scroll_offset: 0,
-            services_scroll_offset: 0,
-            backup_scroll_offset: 0,
             last_update: None,
-            command_status: None,
         }
     }
 }
 
+
 /// Main TUI application
 pub struct TuiApp {
     /// Widget states per host (hostname -> HostWidgets)
@@ -126,25 +57,39 @@ pub struct TuiApp {
     available_hosts: Vec<String>,
     /// Host index for navigation
     host_index: usize,
-    /// Currently focused panel
-    focused_panel: PanelType,
     /// Should quit application
     should_quit: bool,
     /// Track if user manually navigated away from localhost
     user_navigated_away: bool,
+    /// Dashboard configuration
+    config: DashboardConfig,
+    /// Cached localhost hostname to avoid repeated system calls
+    localhost: String,
 }
 
 impl TuiApp {
-    pub fn new() -> Self {
+    pub fn new(config: DashboardConfig) -> Self {
-        Self {
+        let localhost = gethostname::gethostname().to_string_lossy().to_string();
+        let mut app = Self {
             host_widgets: HashMap::new(),
             current_host: None,
-            available_hosts: Vec::new(),
+            available_hosts: config.hosts.keys().cloned().collect(),
             host_index: 0,
-            focused_panel: PanelType::System, // Start with System panel focused
             should_quit: false,
             user_navigated_away: false,
+            config,
+            localhost,
+        };
+        
+        // Sort predefined hosts
+        app.available_hosts.sort();
+        
+        // Initialize with first host if available
+        if !app.available_hosts.is_empty() {
+            app.current_host = Some(app.available_hosts[0].clone());
         }
+        
+        app
     }
 
     /// Get or create host widgets for the given hostname
@@ -154,74 +99,16 @@ impl TuiApp {
             .or_insert_with(HostWidgets::new)
     }
 
-    /// Update widgets with metrics from store (only for current host)
+    /// Update widgets with structured data from store (only for current host)
     pub fn update_metrics(&mut self, metric_store: &MetricStore) {
-        // Check for command timeouts first
-        self.check_command_timeouts();
-        
-        // Check for rebuild completion by agent hash change
-        self.check_rebuild_completion(metric_store);
-        
         if let Some(hostname) = self.current_host.clone() {
-            // Only update widgets if we have metrics for this host
+            // Get structured data for this host
-            let all_metrics = metric_store.get_metrics_for_host(&hostname);
+            if let Some(agent_data) = metric_store.get_agent_data(&hostname) {
-            if !all_metrics.is_empty() {
-                // Get metrics first while hostname is borrowed
-                let cpu_metrics: Vec<&Metric> = all_metrics
-                    .iter()
-                    .filter(|m| {
-                        m.name.starts_with("cpu_")
-                            || m.name.contains("c_state_")
-                            || m.name.starts_with("process_top_")
-                    })
-                    .copied()
-                    .collect();
-                let memory_metrics: Vec<&Metric> = all_metrics
-                    .iter()
-                    .filter(|m| m.name.starts_with("memory_") || m.name.starts_with("disk_tmp_"))
-                    .copied()
-                    .collect();
-                let service_metrics: Vec<&Metric> = all_metrics
-                    .iter()
-                    .filter(|m| m.name.starts_with("service_"))
-                    .copied()
-                    .collect();
-                let all_backup_metrics: Vec<&Metric> = all_metrics
-                    .iter()
-                    .filter(|m| m.name.starts_with("backup_"))
-                    .copied()
-                    .collect();
-
-                // Now get host widgets and update them
                 let host_widgets = self.get_or_create_host_widgets(&hostname);
 
-                // Collect all system metrics (CPU, memory, NixOS, disk/storage)
+                // Update all widgets with structured data directly
-                let mut system_metrics = cpu_metrics;
+                host_widgets.system_widget.update_from_agent_data(agent_data);
-                system_metrics.extend(memory_metrics);
+                host_widgets.services_widget.update_from_agent_data(agent_data);
-                
-                // Add NixOS metrics - using exact matching for build display fix
-                let nixos_metrics: Vec<&Metric> = all_metrics
-                    .iter()
-                    .filter(|m| m.name == "system_nixos_build" || m.name == "system_active_users" || m.name == "system_agent_hash")
-                    .copied()
-                    .collect();
-                system_metrics.extend(nixos_metrics);
-                
-                // Add disk/storage metrics
-                let disk_metrics: Vec<&Metric> = all_metrics
-                    .iter()
-                    .filter(|m| m.name.starts_with("disk_"))
-                    .copied()
-                    .collect();
-                system_metrics.extend(disk_metrics);
-
-                host_widgets.system_widget.update_from_metrics(&system_metrics);
-                host_widgets
-                    .services_widget
-                    .update_from_metrics(&service_metrics);
-                host_widgets
-                    .backup_widget
-                    .update_from_metrics(&all_backup_metrics);
 
                 host_widgets.last_update = Some(Instant::now());
             }
@@ -229,30 +116,28 @@ impl TuiApp {
     }
 
     /// Update available hosts with localhost prioritization
-    pub fn update_hosts(&mut self, hosts: Vec<String>) {
+    pub fn update_hosts(&mut self, discovered_hosts: Vec<String>) {
-        // Sort hosts alphabetically
+        // Start with configured hosts (always visible)
-        let mut sorted_hosts = hosts.clone();
+        let mut all_hosts: Vec<String> = self.config.hosts.keys().cloned().collect();
         
-        // Keep hosts that are undergoing SystemRebuild even if they're offline
+        // Add any discovered hosts that aren't already configured
-        for (hostname, host_widgets) in &self.host_widgets {
+        for host in discovered_hosts {
-            if let Some(CommandStatus::InProgress { command_type: CommandType::SystemRebuild, .. }) = &host_widgets.command_status {
+            if !all_hosts.contains(&host) {
-                if !sorted_hosts.contains(hostname) {
+                all_hosts.push(host);
-                    sorted_hosts.push(hostname.clone());
-                }
             }
         }
         
-        sorted_hosts.sort();
+        
-        self.available_hosts = sorted_hosts;
+        all_hosts.sort();
+        self.available_hosts = all_hosts;
         
         // Get the current hostname (localhost) for auto-selection
-        let localhost = gethostname::gethostname().to_string_lossy().to_string();
         if !self.available_hosts.is_empty() {
-            if self.available_hosts.contains(&localhost) && !self.user_navigated_away {
+            if self.available_hosts.contains(&self.localhost) && !self.user_navigated_away {
                 // Localhost is available and user hasn't navigated away - switch to it
-                self.current_host = Some(localhost.clone());
+                self.current_host = Some(self.localhost.clone());
                 // Find the actual index of localhost in the sorted list
-                self.host_index = self.available_hosts.iter().position(|h| h == &localhost).unwrap_or(0);
+                self.host_index = self.available_hosts.iter().position(|h| h == &self.localhost).unwrap_or(0);
             } else if self.current_host.is_none() {
                 // No current host - select first available (which is localhost if available)
                 self.current_host = Some(self.available_hosts[0].clone());
@@ -272,7 +157,7 @@ impl TuiApp {
     }
 
     /// Handle keyboard input
-    pub fn handle_input(&mut self, event: Event) -> Result<Option<UiCommand>> {
+    pub fn handle_input(&mut self, event: Event) -> Result<()> {
         if let Event::Key(key) = event {
             match key.code {
                 KeyCode::Char('q') => {
@@ -285,78 +170,197 @@ impl TuiApp {
                     self.navigate_host(1);
                 }
                 KeyCode::Char('r') => {
-                    match self.focused_panel {
+                    // System rebuild command - works on any panel for current host
-                        PanelType::System => {
+                    if let Some(hostname) = self.current_host.clone() {
-                            // System rebuild command
+                        let connection_ip = self.get_connection_ip(&hostname);
-                            if let Some(hostname) = self.current_host.clone() {
+                        // Create command that shows logo, rebuilds, and waits for user input
-                                self.start_command(&hostname, CommandType::SystemRebuild, hostname.clone());
+                        let logo_and_rebuild = format!(
-                                return Ok(Some(UiCommand::SystemRebuild { hostname }));
+                            "echo 'Rebuilding system: {} ({})' && ssh -tt {}@{} \"bash -ic '{}'\"",
-                            }
+                            hostname,
-                        }
+                            connection_ip,
-                        PanelType::Services => {
+                            self.config.ssh.rebuild_user,
-                            // Service restart command
+                            connection_ip,
-                            if let (Some(service_name), Some(hostname)) = (self.get_selected_service(), self.current_host.clone()) {
+                            self.config.ssh.rebuild_cmd
-                                self.start_command(&hostname, CommandType::ServiceRestart, service_name.clone());
+                        );
-                                return Ok(Some(UiCommand::ServiceRestart { hostname, service_name }));
+                        
-                            }
+                        std::process::Command::new("tmux")
-                        }
+                            .arg("split-window")
-                        _ => {
+                            .arg("-v")
-                            info!("Manual refresh requested");
+                            .arg("-p")
-                        }
+                            .arg("30")
+                            .arg(&logo_and_rebuild)
+                            .spawn()
+                            .ok(); // Ignore errors, tmux will handle them
+                    }
+                }
+                KeyCode::Char('B') => {
+                    // Backup command - works on any panel for current host
+                    if let Some(hostname) = self.current_host.clone() {
+                        let connection_ip = self.get_connection_ip(&hostname);
+                        // Create command that shows logo, runs backup, and waits for user input
+                        let logo_and_backup = format!(
+                            "echo 'Running backup: {} ({})' && ssh -tt {}@{} \"bash -ic '{}'\"",
+                            hostname,
+                            connection_ip,
+                            self.config.ssh.rebuild_user,
+                            connection_ip,
+                            format!("{} start borgbackup", self.config.ssh.service_manage_cmd)
+                        );
+                        
+                        std::process::Command::new("tmux")
+                            .arg("split-window")
+                            .arg("-v")
+                            .arg("-p")
+                            .arg("30")
+                            .arg(&logo_and_backup)
+                            .spawn()
+                            .ok(); // Ignore errors, tmux will handle them
                     }
                 }
                 KeyCode::Char('s') => {
-                    if self.focused_panel == PanelType::Services {
+                    // Service start command via SSH with progress display
-                        // Service start command
+                    if let (Some(service_name), Some(hostname)) = (self.get_selected_service(), self.current_host.clone()) {
-                        if let (Some(service_name), Some(hostname)) = (self.get_selected_service(), self.current_host.clone()) {
+                        let connection_ip = self.get_connection_ip(&hostname);
-                            self.start_command(&hostname, CommandType::ServiceStart, service_name.clone());
+                        let service_start_command = format!(
-                            return Ok(Some(UiCommand::ServiceStart { hostname, service_name }));
+                            "echo 'Starting service: {} on {}' && ssh -tt {}@{} \"bash -ic '{} start {}'\"",
-                        }
+                            service_name,
+                            hostname,
+                            self.config.ssh.rebuild_user,
+                            connection_ip,
+                            self.config.ssh.service_manage_cmd,
+                            service_name
+                        );
+                        
+                        std::process::Command::new("tmux")
+                            .arg("split-window")
+                            .arg("-v")
+                            .arg("-p")
+                            .arg("30")
+                            .arg(&service_start_command)
+                            .spawn()
+                            .ok(); // Ignore errors, tmux will handle them
                     }
                 }
                 KeyCode::Char('S') => {
-                    if self.focused_panel == PanelType::Services {
+                    // Service stop command via SSH with progress display
-                        // Service stop command
+                    if let (Some(service_name), Some(hostname)) = (self.get_selected_service(), self.current_host.clone()) {
-                        if let (Some(service_name), Some(hostname)) = (self.get_selected_service(), self.current_host.clone()) {
+                        let connection_ip = self.get_connection_ip(&hostname);
-                            self.start_command(&hostname, CommandType::ServiceStop, service_name.clone());
+                        let service_stop_command = format!(
-                            return Ok(Some(UiCommand::ServiceStop { hostname, service_name }));
+                            "echo 'Stopping service: {} on {}' && ssh -tt {}@{} \"bash -ic '{} stop {}'\"",
+                            service_name,
+                            hostname,
+                            self.config.ssh.rebuild_user,
+                            connection_ip,
+                            self.config.ssh.service_manage_cmd,
+                            service_name
+                        );
+                        
+                        std::process::Command::new("tmux")
+                            .arg("split-window")
+                            .arg("-v")
+                            .arg("-p")
+                            .arg("30")
+                            .arg(&service_stop_command)
+                            .spawn()
+                            .ok(); // Ignore errors, tmux will handle them
+                    }
+                }
+                KeyCode::Char('L') => {
+                    // Show service logs via service-manage script in tmux split window
+                    if let (Some(service_name), Some(hostname)) = (self.get_selected_service(), self.current_host.clone()) {
+                        let connection_ip = self.get_connection_ip(&hostname);
+                        let logs_command = format!(
+                            "ssh -tt {}@{} '{} logs {}'",
+                            self.config.ssh.rebuild_user,
+                            connection_ip,
+                            self.config.ssh.service_manage_cmd,
+                            service_name
+                        );
+                        
+                        std::process::Command::new("tmux")
+                            .arg("split-window")
+                            .arg("-v")
+                            .arg("-p")
+                            .arg("30")
+                            .arg(&logs_command)
+                            .spawn()
+                            .ok(); // Ignore errors, tmux will handle them
+                    }
+                }
+                KeyCode::Char('w') => {
+                    // Wake on LAN for offline hosts
+                    if let Some(hostname) = self.current_host.clone() {
+                        // Check if host has MAC address configured
+                        if let Some(host_details) = self.config.hosts.get(&hostname) {
+                            if let Some(mac_address) = &host_details.mac_address {
+                                // Parse MAC address and send WoL packet
+                                let mac_bytes = Self::parse_mac_address(mac_address);
+                                match mac_bytes {
+                                    Ok(mac) => {
+                                        match MagicPacket::new(&mac).send() {
+                                            Ok(_) => {
+                                                info!("WakeOnLAN packet sent successfully to {} ({})", hostname, mac_address);
+                                            }
+                                            Err(e) => {
+                                                tracing::error!("Failed to send WakeOnLAN packet to {}: {}", hostname, e);
+                                            }
+                                        }
+                                    }
+                                    Err(_) => {
+                                        tracing::error!("Invalid MAC address format for {}: {}", hostname, mac_address);
+                                    }
+                                }
+                            }
                         }
                     }
                 }
-                KeyCode::Char('b') => {
+                KeyCode::Char('t') => {
-                    if self.focused_panel == PanelType::Backup {
+                    // Open SSH terminal session in tmux window
-                        // Trigger backup
+                    if let Some(hostname) = self.current_host.clone() {
-                        if let Some(hostname) = self.current_host.clone() {
+                        let connection_ip = self.get_connection_ip(&hostname);
-                            self.start_command(&hostname, CommandType::BackupTrigger, hostname.clone());
+                        let ssh_command = format!(
-                            return Ok(Some(UiCommand::TriggerBackup { hostname }));
+                            "echo 'Opening SSH terminal to: {}' && ssh -tt {}@{}",
-                        }
+                            hostname,
+                            self.config.ssh.rebuild_user,
+                            connection_ip
+                        );
+                        
+                        std::process::Command::new("tmux")
+                            .arg("split-window")
+                            .arg("-v")
+                            .arg("-p")
+                            .arg("30") // Use 30% like other commands
+                            .arg(&ssh_command)
+                            .spawn()
+                            .ok(); // Ignore errors, tmux will handle them
                     }
                 }
                 KeyCode::Tab => {
-                    if key.modifiers.contains(KeyModifiers::SHIFT) {
+                    // Tab cycles to next host
-                        // Shift+Tab cycles through panels
+                    self.navigate_host(1);
-                        self.next_panel();
+                }
-                    } else {
+                KeyCode::Up | KeyCode::Char('k') => {
-                        // Tab cycles to next host
+                    // Move service selection up
-                        self.navigate_host(1);
+                    if let Some(hostname) = self.current_host.clone() {
+                        let host_widgets = self.get_or_create_host_widgets(&hostname);
+                        host_widgets.services_widget.select_previous();
                     }
                 }
-                KeyCode::BackTab => {
+                KeyCode::Down | KeyCode::Char('j') => {
-                    // BackTab (Shift+Tab on some terminals) also cycles panels
+                    // Move service selection down
-                    self.next_panel();
+                    if let Some(hostname) = self.current_host.clone() {
-                }
+                        let total_services = {
-                KeyCode::Up => {
+                            let host_widgets = self.get_or_create_host_widgets(&hostname);
-                    // Scroll up in focused panel
+                            host_widgets.services_widget.get_total_services_count()
-                    self.scroll_focused_panel(-1);
+                        };
-                }
+                        let host_widgets = self.get_or_create_host_widgets(&hostname);
-                KeyCode::Down => {
+                        host_widgets.services_widget.select_next(total_services);
-                    // Scroll down in focused panel
+                    }
-                    self.scroll_focused_panel(1);
                 }
                 _ => {}
             }
         }
-        Ok(None)
+        Ok(())
     }
 
     /// Navigate between hosts
@@ -379,9 +383,8 @@ impl TuiApp {
         self.current_host = Some(self.available_hosts[self.host_index].clone());
         
         // Check if user navigated away from localhost
-        let localhost = gethostname::gethostname().to_string_lossy().to_string();
         if let Some(ref current) = self.current_host {
-            if current != &localhost {
+            if current != &self.localhost {
                 self.user_navigated_away = true;
             } else {
                 self.user_navigated_away = false; // User navigated back to localhost
@@ -391,66 +394,9 @@ impl TuiApp {
         info!("Switched to host: {}", self.current_host.as_ref().unwrap());
     }
 
-    /// Check if a host is currently rebuilding
-    pub fn is_host_rebuilding(&self, hostname: &str) -> bool {
-        if let Some(host_widgets) = self.host_widgets.get(hostname) {
-            matches!(
-                &host_widgets.command_status,
-                Some(CommandStatus::InProgress { command_type: CommandType::SystemRebuild, .. })
-            )
-        } else {
-            false
-        }
-    }
 
-    /// Switch to next panel (Shift+Tab) - only cycles through visible panels
-    pub fn next_panel(&mut self) {
-        let visible_panels = self.get_visible_panels();
-        if visible_panels.len() <= 1 {
-            return; // Can't switch if only one or no panels visible
-        }
-        
-        // Find current panel index in visible panels
-        if let Some(current_index) = visible_panels.iter().position(|&p| p == self.focused_panel) {
-            // Move to next visible panel
-            let next_index = (current_index + 1) % visible_panels.len();
-            self.focused_panel = visible_panels[next_index];
-        } else {
-            // Current panel not visible, switch to first visible panel
-            self.focused_panel = visible_panels[0];
-        }
-        
-        info!("Switched to panel: {:?}", self.focused_panel);
-    }
 
-    /// Switch to previous panel (Shift+Tab in reverse) - only cycles through visible panels
-    pub fn previous_panel(&mut self) {
-        let visible_panels = self.get_visible_panels();
-        if visible_panels.len() <= 1 {
-            return; // Can't switch if only one or no panels visible
-        }
-        
-        // Find current panel index in visible panels
-        if let Some(current_index) = visible_panels.iter().position(|&p| p == self.focused_panel) {
-            // Move to previous visible panel
-            let prev_index = if current_index == 0 {
-                visible_panels.len() - 1
-            } else {
-                current_index - 1
-            };
-            self.focused_panel = visible_panels[prev_index];
-        } else {
-            // Current panel not visible, switch to last visible panel
-            self.focused_panel = visible_panels[visible_panels.len() - 1];
-        }
-        
-        info!("Switched to panel: {:?}", self.focused_panel);
-    }
 
-    /// Get the currently focused panel
-    pub fn get_focused_panel(&self) -> PanelType {
-        self.focused_panel
-    }
 
     /// Get the currently selected service name from the services widget
     fn get_selected_service(&self) -> Option<String> {
@@ -462,188 +408,17 @@ impl TuiApp {
         None
     }
 
-    /// Get command status for current host
-    pub fn get_command_status(&self) -> Option<&CommandStatus> {
-        if let Some(hostname) = &self.current_host {
-            if let Some(host_widgets) = self.host_widgets.get(hostname) {
-                return host_widgets.command_status.as_ref();
-            }
-        }
-        None
-    }
 
     /// Should quit application
     pub fn should_quit(&self) -> bool {
         self.should_quit
     }
 
-    /// Start command execution and track status for visual feedback
-    pub fn start_command(&mut self, hostname: &str, command_type: CommandType, target: String) {
-        if let Some(host_widgets) = self.host_widgets.get_mut(hostname) {
-            host_widgets.command_status = Some(CommandStatus::InProgress {
-                command_type,
-                target,
-                start_time: Instant::now(),
-            });
-        }
-    }
 
-    /// Mark command as completed successfully
-    pub fn complete_command(&mut self, hostname: &str) {
-        if let Some(host_widgets) = self.host_widgets.get_mut(hostname) {
-            if let Some(CommandStatus::InProgress { command_type, target, start_time }) = &host_widgets.command_status {
-                let duration = start_time.elapsed();
-                host_widgets.command_status = Some(CommandStatus::Success {
-                    command_type: command_type.clone(),
-                    target: target.clone(),
-                    duration,
-                    completed_at: Instant::now(),
-                });
-            }
-        }
-    }
 
-    /// Mark command as failed
-    pub fn fail_command(&mut self, hostname: &str, error: String) {
-        if let Some(host_widgets) = self.host_widgets.get_mut(hostname) {
-            if let Some(CommandStatus::InProgress { command_type, target, .. }) = &host_widgets.command_status {
-                host_widgets.command_status = Some(CommandStatus::Failed {
-                    command_type: command_type.clone(),
-                    target: target.clone(),
-                    error,
-                    failed_at: Instant::now(),
-                });
-            }
-        }
-    }
 
-    /// Check for command timeouts and automatically clear them
-    pub fn check_command_timeouts(&mut self) {
-        let now = Instant::now();
-        let mut hosts_to_clear = Vec::new();
-        
-        for (hostname, host_widgets) in &self.host_widgets {
-            if let Some(CommandStatus::InProgress { command_type, start_time, .. }) = &host_widgets.command_status {
-                let timeout_duration = match command_type {
-                    CommandType::SystemRebuild => Duration::from_secs(300), // 5 minutes for rebuilds
-                    _ => Duration::from_secs(30), // 30 seconds for service commands
-                };
-                
-                if now.duration_since(*start_time) > timeout_duration {
-                    hosts_to_clear.push(hostname.clone());
-                }
-            }
-            // Also clear success/failed status after display time
-            else if let Some(CommandStatus::Success { completed_at, .. }) = &host_widgets.command_status {
-                if now.duration_since(*completed_at) > Duration::from_secs(3) {
-                    hosts_to_clear.push(hostname.clone());
-                }
-            }
-            else if let Some(CommandStatus::Failed { failed_at, .. }) = &host_widgets.command_status {
-                if now.duration_since(*failed_at) > Duration::from_secs(5) {
-                    hosts_to_clear.push(hostname.clone());
-                }
-            }
-        }
-        
-        // Clear timed out commands
-        for hostname in hosts_to_clear {
-            if let Some(host_widgets) = self.host_widgets.get_mut(&hostname) {
-                host_widgets.command_status = None;
-            }
-        }
-    }
 
-    /// Check for rebuild completion by detecting agent hash changes
-    pub fn check_rebuild_completion(&mut self, metric_store: &MetricStore) {
-        let mut hosts_to_complete = Vec::new();
-        
-        for (hostname, host_widgets) in &self.host_widgets {
-            if let Some(CommandStatus::InProgress { command_type: CommandType::SystemRebuild, .. }) = &host_widgets.command_status {
-                // Check if agent hash has changed (indicating successful rebuild)
-                if let Some(agent_hash_metric) = metric_store.get_metric(hostname, "system_agent_hash") {
-                    if let cm_dashboard_shared::MetricValue::String(current_hash) = &agent_hash_metric.value {
-                        // Compare with stored hash (if we have one)
-                        if let Some(stored_hash) = host_widgets.system_widget.get_agent_hash() {
-                            if current_hash != stored_hash {
-                                // Agent hash changed - rebuild completed successfully
-                                hosts_to_complete.push(hostname.clone());
-                            }
-                        }
-                    }
-                }
-            }
-        }
-        
-        // Mark rebuilds as completed
-        for hostname in hosts_to_complete {
-            self.complete_command(&hostname);
-        }
-    }
 
-    /// Scroll the focused panel up or down
-    pub fn scroll_focused_panel(&mut self, direction: i32) {
-        if let Some(hostname) = self.current_host.clone() {
-            let focused_panel = self.focused_panel; // Get the value before borrowing
-            let host_widgets = self.get_or_create_host_widgets(&hostname);
-            
-            match focused_panel {
-                PanelType::System => {
-                    if direction > 0 {
-                        host_widgets.system_scroll_offset = host_widgets.system_scroll_offset.saturating_add(1);
-                    } else {
-                        host_widgets.system_scroll_offset = host_widgets.system_scroll_offset.saturating_sub(1);
-                    }
-                    info!("System panel scroll offset: {}", host_widgets.system_scroll_offset);
-                }
-                PanelType::Services => {
-                    // For services panel, Up/Down moves selection cursor, not scroll
-                    let total_services = host_widgets.services_widget.get_total_services_count();
-                    
-                    if direction > 0 {
-                        host_widgets.services_widget.select_next(total_services);
-                        info!("Services selection moved down");
-                    } else {
-                        host_widgets.services_widget.select_previous();
-                        info!("Services selection moved up");
-                    }
-                }
-                PanelType::Backup => {
-                    if direction > 0 {
-                        host_widgets.backup_scroll_offset = host_widgets.backup_scroll_offset.saturating_add(1);
-                    } else {
-                        host_widgets.backup_scroll_offset = host_widgets.backup_scroll_offset.saturating_sub(1);
-                    }
-                    info!("Backup panel scroll offset: {}", host_widgets.backup_scroll_offset);
-                }
-            }
-        }
-    }
-
-    /// Get total count of services for bounds checking
-    fn get_total_services_count(&self, hostname: &str) -> usize {
-        if let Some(host_widgets) = self.host_widgets.get(hostname) {
-            host_widgets.services_widget.get_total_services_count()
-        } else {
-            0
-        }
-    }
-
-    /// Get list of currently visible panels
-    fn get_visible_panels(&self) -> Vec<PanelType> {
-        let mut visible_panels = vec![PanelType::System, PanelType::Services];
-        
-        // Check if backup panel should be shown
-        if let Some(hostname) = &self.current_host {
-            if let Some(host_widgets) = self.host_widgets.get(hostname) {
-                if host_widgets.backup_widget.has_data() {
-                    visible_panels.push(PanelType::Backup);
-                }
-            }
-        }
-        
-        visible_panels
-    }
 
     /// Render the dashboard (real btop-style multi-panel layout)
     pub fn render(&mut self, frame: &mut Frame, metric_store: &MetricStore) {
@@ -675,56 +450,45 @@ impl TuiApp {
             ])
             .split(main_chunks[1]); // main_chunks[1] is now the content area (between title and statusbar)
 
-        // Check if backup panel should be shown
+        // Check if current host is offline
-        let show_backup = if let Some(hostname) = self.current_host.clone() {
+        let current_host_offline = if let Some(hostname) = self.current_host.clone() {
-            let host_widgets = self.get_or_create_host_widgets(&hostname);
+            self.calculate_host_status(&hostname, metric_store) == Status::Offline
-            host_widgets.backup_widget.has_data()
         } else {
-            false
+            true // No host selected is considered offline
         };
 
-        // Left side: dynamic layout based on backup data availability
+        // If host is offline, render wake-up message instead of panels
-        let left_chunks = if show_backup {
+        if current_host_offline {
-            // Show both system and backup panels
+            self.render_offline_host_message(frame, main_chunks[1]);
-            ratatui::layout::Layout::default()
+            self.render_btop_title(frame, main_chunks[0], metric_store);
-                .direction(Direction::Vertical)
+            self.render_statusbar(frame, main_chunks[2]);
-                .constraints([
+            return;
-                    Constraint::Percentage(ThemeLayout::SYSTEM_PANEL_HEIGHT), // System section
+        }
-                    Constraint::Percentage(ThemeLayout::BACKUP_PANEL_HEIGHT), // Backup section
+
-                ])
+        // Left side: system panel only (full height)
-                .split(content_chunks[0])
+        let left_chunks = ratatui::layout::Layout::default()
-        } else {
+            .direction(Direction::Vertical)
-            // Show only system panel (full height)
+            .constraints([Constraint::Percentage(100)]) // System section takes full height
-            ratatui::layout::Layout::default()
+            .split(content_chunks[0]);
-                .direction(Direction::Vertical)
-                .constraints([Constraint::Percentage(100)]) // System section takes full height
-                .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() {
-            let is_focused = self.focused_panel == PanelType::Services;
+            let is_focused = true; // Always show service selection
-            let (scroll_offset, command_status) = {
-                let host_widgets = self.get_or_create_host_widgets(&hostname);
-                (host_widgets.services_scroll_offset, host_widgets.command_status.clone())
-            };
             let host_widgets = self.get_or_create_host_widgets(&hostname);
             host_widgets
                 .services_widget
-                .render_with_command_status(frame, content_chunks[1], is_focused, scroll_offset, command_status.as_ref()); // Services takes full right side
+                .render(frame, content_chunks[1], is_focused); // Services takes full right side
         }
 
         // Render statusbar at the bottom
         self.render_statusbar(frame, main_chunks[2]); // main_chunks[2] is the statusbar area
+
     }
 
     /// Render btop-style minimal title with host status colors
@@ -735,113 +499,101 @@ impl TuiApp {
 
         if self.available_hosts.is_empty() {
             let title_text = "cm-dashboard • no hosts discovered";
-            let title = Paragraph::new(title_text).style(Typography::title());
+            let title = Paragraph::new(title_text)
+                .style(Style::default().fg(Theme::background()).bg(Theme::status_color(Status::Unknown)));
             frame.render_widget(title, area);
             return;
         }
 
-        // Create spans for each host with status indicators
+        // Calculate worst-case status across all hosts (excluding offline)
-        let mut spans = vec![Span::styled("cm-dashboard • ", Typography::title())];
+        let mut worst_status = Status::Ok;
+        for host in &self.available_hosts {
+            let host_status = self.calculate_host_status(host, metric_store);
+            // Don't include offline hosts in status aggregation
+            if host_status != Status::Offline {
+                worst_status = Status::aggregate(&[worst_status, host_status]);
+            }
+        }
 
+        // Use the worst status color as background
+        let background_color = Theme::status_color(worst_status);
+
+        // Split the title bar into left and right sections
+        let chunks = Layout::default()
+            .direction(Direction::Horizontal)
+            .constraints([Constraint::Length(22), Constraint::Min(0)])
+            .split(area);
+
+        // Left side: "cm-dashboard" text with version
+        let title_text = format!(" cm-dashboard v{}", env!("CARGO_PKG_VERSION"));
+        let left_span = Span::styled(
+            &title_text, 
+            Style::default().fg(Theme::background()).bg(background_color).add_modifier(Modifier::BOLD)
+        );
+        let left_title = Paragraph::new(Line::from(vec![left_span]))
+            .style(Style::default().bg(background_color));
+        frame.render_widget(left_title, chunks[0]);
+
+        // Right side: hosts with status indicators
+        let mut host_spans = Vec::new();
+        
         for (i, host) in self.available_hosts.iter().enumerate() {
             if i > 0 {
-                spans.push(Span::styled(" ", Typography::title()));
+                host_spans.push(Span::styled(
+                    " ", 
+                    Style::default().fg(Theme::background()).bg(background_color)
+                ));
             }
 
-            // Check if this host has a command status that affects the icon
+            // Always show normal status icon based on metrics (no command status at host level)
-            let (status_icon, status_color) = if let Some(host_widgets) = self.host_widgets.get(host) {
+            let host_status = self.calculate_host_status(host, metric_store);
-                match &host_widgets.command_status {
+            let status_icon = StatusIcons::get_icon(host_status);
-                    Some(CommandStatus::InProgress { command_type: CommandType::SystemRebuild, .. }) => {
-                        // Show blue circular arrow during rebuild
-                        ("↻", Theme::highlight())
-                    }
-                    Some(CommandStatus::Success { command_type: CommandType::SystemRebuild, .. }) => {
-                        // Show green checkmark for successful rebuild
-                        ("✓", Theme::success())
-                    }
-                    Some(CommandStatus::Failed { command_type: CommandType::SystemRebuild, .. }) => {
-                        // Show red X for failed rebuild
-                        ("✗", Theme::error())
-                    }
-                    _ => {
-                        // Normal status icon based on metrics
-                        let host_status = self.calculate_host_status(host, metric_store);
-                        (StatusIcons::get_icon(host_status), Theme::status_color(host_status))
-                    }
-                }
-            } else {
-                // No host widgets yet, use normal status
-                let host_status = self.calculate_host_status(host, metric_store);
-                (StatusIcons::get_icon(host_status), Theme::status_color(host_status))
-            };
 
-            // Add status icon
+            // Add status icon with background color as foreground against status background
-            spans.push(Span::styled(
+            host_spans.push(Span::styled(
                 format!("{} ", status_icon),
-                Style::default().fg(status_color),
+                Style::default().fg(Theme::background()).bg(background_color),
             ));
 
             if Some(host) == self.current_host.as_ref() {
-                // Selected host in bold bright white
+                // Selected host in bold background color against status background
-                spans.push(Span::styled(
+                host_spans.push(Span::styled(
                     host.clone(),
-                    Typography::title().add_modifier(Modifier::BOLD),
+                    Style::default()
+                        .fg(Theme::background())
+                        .bg(background_color)
+                        .add_modifier(Modifier::BOLD),
                 ));
             } else {
-                // Other hosts in normal style with status color
+                // Other hosts in normal background color against status background
-                spans.push(Span::styled(
+                host_spans.push(Span::styled(
                     host.clone(),
-                    Style::default().fg(status_color),
+                    Style::default().fg(Theme::background()).bg(background_color),
                 ));
             }
         }
 
-        let title_line = Line::from(spans);
+        // Add right padding
-        let title = Paragraph::new(vec![title_line]);
+        host_spans.push(Span::styled(
+            " ", 
+            Style::default().fg(Theme::background()).bg(background_color)
+        ));
 
-        frame.render_widget(title, area);
+        let host_line = Line::from(host_spans);
+        let host_title = Paragraph::new(vec![host_line])
+            .style(Style::default().bg(background_color))
+            .alignment(ratatui::layout::Alignment::Right);
+        frame.render_widget(host_title, chunks[1]);
     }
 
-    /// Calculate overall status for a host based on its metrics
+    /// Calculate overall status for a host based on its structured data
     fn calculate_host_status(&self, hostname: &str, metric_store: &MetricStore) -> Status {
-        let metrics = metric_store.get_metrics_for_host(hostname);
+        // Check if we have structured data for this host
-
+        if let Some(_agent_data) = metric_store.get_agent_data(hostname) {
-        if metrics.is_empty() {
+            // Return OK since we have data
-            return Status::Unknown;
-        }
-
-        // First check if we have the aggregated host status summary from the agent
-        if let Some(host_summary_metric) = metric_store.get_metric(hostname, "host_status_summary") {
-            return host_summary_metric.status;
-        }
-
-        // Fallback to old aggregation logic with proper Pending handling
-        let mut has_critical = false;
-        let mut has_warning = false;
-        let mut has_pending = false;
-        let mut ok_count = 0;
-
-        for metric in &metrics {
-            match metric.status {
-                Status::Critical => has_critical = true,
-                Status::Warning => has_warning = true,
-                Status::Pending => has_pending = true,
-                Status::Ok => ok_count += 1,
-                Status::Unknown => {} // Ignore unknown for aggregation
-            }
-        }
-
-        // Priority order: Critical > Warning > Pending > Ok > Unknown
-        if has_critical {
-            Status::Critical
-        } else if has_warning {
-            Status::Warning
-        } else if has_pending {
-            Status::Pending
-        } else if ok_count > 0 {
             Status::Ok
         } else {
-            Status::Unknown
+            Status::Offline
         }
     }
 
@@ -862,363 +614,129 @@ impl TuiApp {
         let mut shortcuts = Vec::new();
         
         // Global shortcuts
-        shortcuts.push("Tab: Switch Host".to_string());
+        shortcuts.push("Tab: Host".to_string());
-        shortcuts.push("Shift+Tab: Switch Panel".to_string());
+        shortcuts.push("↑↓/jk: Select".to_string());
-        
+        shortcuts.push("r: Rebuild".to_string());
-        // Scroll shortcuts (always available)
+        shortcuts.push("B: Backup".to_string());
-        shortcuts.push("↑↓: Scroll".to_string());
+        shortcuts.push("s/S: Start/Stop".to_string());
-        
+        shortcuts.push("L: Logs".to_string());
-        // Panel-specific shortcuts
+        shortcuts.push("t: Terminal".to_string());
-        match self.focused_panel {
+        shortcuts.push("w: Wake".to_string());
-            PanelType::System => {
-                shortcuts.push("R: Rebuild".to_string());
-            }
-            PanelType::Services => {
-                shortcuts.push("S: Start".to_string());
-                shortcuts.push("Shift+S: Stop".to_string());
-                shortcuts.push("R: Restart".to_string());
-            }
-            PanelType::Backup => {
-                shortcuts.push("B: Trigger Backup".to_string());
-            }
-        }
         
         // Always show quit
-        shortcuts.push("Q: Quit".to_string());
+        shortcuts.push("q: Quit".to_string());
         
         shortcuts
     }
 
     fn render_system_panel(&mut self, frame: &mut Frame, area: Rect, _metric_store: &MetricStore) {
-        let system_block = if self.focused_panel == PanelType::System {
+        let system_block = Components::widget_block("system");
-            Components::focused_widget_block("system")
-        } else {
-            Components::widget_block("system")
-        };
         let inner_area = system_block.inner(area);
         frame.render_widget(system_block, area);
         // Get current host widgets, create if none exist
         if let Some(hostname) = self.current_host.clone() {
-            let scroll_offset = {
+            // Clone the config to avoid borrowing issues
-                let host_widgets = self.get_or_create_host_widgets(&hostname);
+            let config = self.config.clone();
-                host_widgets.system_scroll_offset
-            };
             let host_widgets = self.get_or_create_host_widgets(&hostname);
-            host_widgets.system_widget.render_with_scroll(frame, inner_area, scroll_offset);
+            host_widgets.system_widget.render(frame, inner_area, &hostname, Some(&config));
         }
     }
 
-    fn render_backup_panel(&mut self, frame: &mut Frame, area: Rect) {
-        let backup_block = if self.focused_panel == PanelType::Backup {
-            Components::focused_widget_block("backup")
-        } else {
-            Components::widget_block("backup")
-        };
-        let inner_area = backup_block.inner(area);
-        frame.render_widget(backup_block, area);
 
-        // Get current host widgets for backup widget
+    /// Render offline host message with wake-up option
-        if let Some(hostname) = self.current_host.clone() {
+    fn render_offline_host_message(&self, frame: &mut Frame, area: Rect) {
-            let scroll_offset = {
+        use ratatui::layout::Alignment;
-                let host_widgets = self.get_or_create_host_widgets(&hostname);
+        use ratatui::style::Modifier;
-                host_widgets.backup_scroll_offset
+        use ratatui::text::{Line, Span};
-            };
+        use ratatui::widgets::{Block, Borders, Paragraph};
-            let host_widgets = self.get_or_create_host_widgets(&hostname);
+
-            host_widgets.backup_widget.render_with_scroll(frame, inner_area, scroll_offset);
+        // Get hostname for message
+        let hostname = self.current_host.as_ref()
+            .map(|h| h.as_str())
+            .unwrap_or("Unknown");
+
+        // Check if host has MAC address for wake-on-LAN
+        let has_mac = self.current_host.as_ref()
+            .and_then(|hostname| self.config.hosts.get(hostname))
+            .and_then(|details| details.mac_address.as_ref())
+            .is_some();
+
+        // Create message content
+        let mut lines = vec![
+            Line::from(Span::styled(
+                format!("Host '{}' is offline", hostname),
+                Style::default().fg(Theme::muted_text()).add_modifier(Modifier::BOLD),
+            )),
+            Line::from(""),
+        ];
+
+        if has_mac {
+            lines.push(Line::from(Span::styled(
+                "Press 'w' to wake up host",
+                Style::default().fg(Theme::primary_text()).add_modifier(Modifier::BOLD),
+            )));
+        } else {
+            lines.push(Line::from(Span::styled(
+                "No MAC address configured - cannot wake up",
+                Style::default().fg(Theme::muted_text()),
+            )));
+        }
+
+        // Create centered message
+        let message = Paragraph::new(lines)
+            .block(Block::default()
+                .borders(Borders::ALL)
+                .border_style(Style::default().fg(Theme::muted_text()))
+                .title(" Offline Host ")
+                .title_style(Style::default().fg(Theme::muted_text()).add_modifier(Modifier::BOLD)))
+            .style(Style::default().bg(Theme::background()).fg(Theme::primary_text()))
+            .alignment(Alignment::Center);
+
+        // Center the message in the available area
+        let popup_area = ratatui::layout::Layout::default()
+            .direction(Direction::Vertical)
+            .constraints([
+                Constraint::Percentage(40),
+                Constraint::Length(6),
+                Constraint::Percentage(40),
+            ])
+            .split(area)[1];
+
+        let popup_area = ratatui::layout::Layout::default()
+            .direction(Direction::Horizontal)
+            .constraints([
+                Constraint::Percentage(25),
+                Constraint::Percentage(50),
+                Constraint::Percentage(25),
+            ])
+            .split(popup_area)[1];
+
+        frame.render_widget(message, popup_area);
+    }
+
+    /// Parse MAC address string (e.g., "AA:BB:CC:DD:EE:FF") to [u8; 6]
+    /// Get the connection IP for a hostname based on host configuration
+    fn get_connection_ip(&self, hostname: &str) -> String {
+        if let Some(host_details) = self.config.hosts.get(hostname) {
+            host_details.get_connection_ip(hostname)
+        } else {
+            hostname.to_string()
         }
     }
 
-    fn render_storage_section(&self, frame: &mut Frame, area: Rect, metric_store: &MetricStore) {
+    fn parse_mac_address(mac_str: &str) -> Result<[u8; 6], &'static str> {
-        if area.height < 2 {
+        let parts: Vec<&str> = mac_str.split(':').collect();
-            return;
+        if parts.len() != 6 {
+            return Err("MAC address must have 6 parts separated by colons");
         }
 
-        if let Some(ref hostname) = self.current_host {
+        let mut mac = [0u8; 6];
-            // Discover storage pools from metrics (look for disk_{pool}_usage_percent patterns)
+        for (i, part) in parts.iter().enumerate() {
-            let mut storage_pools: std::collections::HashMap<String, Vec<String>> = 
+            match u8::from_str_radix(part, 16) {
-                std::collections::HashMap::new();
+                Ok(byte) => mac[i] = byte,
-            
+                Err(_) => return Err("Invalid hexadecimal byte in MAC address"),
-            let all_metrics = metric_store.get_metrics_for_host(hostname);
-            
-            // Find storage pools by looking for usage metrics
-            for metric in &all_metrics {
-                if metric.name.starts_with("disk_") && metric.name.ends_with("_usage_percent") {
-                    let pool_name = metric.name
-                        .strip_prefix("disk_")
-                        .and_then(|s| s.strip_suffix("_usage_percent"))
-                        .unwrap_or_default()
-                        .to_string();
-                    
-                    if !pool_name.is_empty() && pool_name != "tmp" {
-                        storage_pools.entry(pool_name.clone()).or_insert_with(Vec::new);
-                    }
-                }
             }
-            
-            // Find individual drives for each pool
-            for metric in &all_metrics {
-                if metric.name.starts_with("disk_") && metric.name.contains("_") && metric.name.ends_with("_health") {
-                    // Parse disk_{pool}_{drive}_health format
-                    let parts: Vec<&str> = metric.name.split('_').collect();
-                    if parts.len() >= 4 && parts[0] == "disk" && parts[parts.len()-1] == "health" {
-                        // Extract pool name (everything between "disk_" and "_{drive}_health")
-                        let drive_name = parts[parts.len()-2].to_string();
-                        let pool_part_end = parts.len() - 2;
-                        let pool_name = parts[1..pool_part_end].join("_");
-                        
-                        if let Some(drives) = storage_pools.get_mut(&pool_name) {
-                            if !drives.contains(&drive_name) {
-                                drives.push(drive_name);
-                            }
-                        }
-                    }
-                }
-            }
-
-            // Check if we found any storage pools
-            if storage_pools.is_empty() {
-                // No storage pools found - show error/waiting message
-                let content_chunks = ratatui::layout::Layout::default()
-                    .direction(Direction::Vertical)
-                    .constraints([Constraint::Length(1), Constraint::Min(0)])
-                    .split(area);
-
-                let storage_title = Paragraph::new("Storage:").style(Typography::widget_title());
-                frame.render_widget(storage_title, content_chunks[0]);
-
-                let no_storage_spans =
-                    StatusIcons::create_status_spans(Status::Unknown, "No storage pools detected");
-                let no_storage_para = Paragraph::new(ratatui::text::Line::from(no_storage_spans));
-                frame.render_widget(no_storage_para, content_chunks[1]);
-                return;
-            }
-
-            let available_lines = area.height as usize;
-            let mut constraints = Vec::new();
-            let mut pools_to_show = Vec::new();
-            let mut current_line = 0;
-
-            // Sort storage pools by name for consistent ordering
-            let mut sorted_pools: Vec<_> = storage_pools.iter().collect();
-            sorted_pools.sort_by_key(|(pool_name, _)| pool_name.as_str());
-            
-            // Add section title if we have pools
-            let mut title_added = false;
-            
-            for (pool_name, drives) in sorted_pools {
-                // Calculate lines needed: pool header + drives + usage line (+ section title if first)
-                let section_title_lines = if !title_added { 1 } else { 0 };
-                let lines_for_this_pool = section_title_lines + 1 + drives.len() + 1;
-                
-                if current_line + lines_for_this_pool <= available_lines {
-                    pools_to_show.push((pool_name.clone(), drives.clone()));
-
-                    // Add section title constraint if this is the first pool
-                    if !title_added {
-                        constraints.push(Constraint::Length(1)); // "Storage:" section title
-                        title_added = true;
-                    }
-
-                    // Add constraints for this pool
-                    constraints.push(Constraint::Length(1)); // Pool header with status
-                    for _ in 0..drives.len() {
-                        constraints.push(Constraint::Length(1)); // Drive line with tree symbol
-                    }
-                    constraints.push(Constraint::Length(1)); // Usage line with end tree symbol
-
-                    current_line += lines_for_this_pool;
-                } else {
-                    break; // Can't fit more pools
-                }
-            }
-
-            // Add remaining space if any
-            if constraints.len() < available_lines {
-                constraints.push(Constraint::Min(0));
-            }
-
-            let content_chunks = ratatui::layout::Layout::default()
-                .direction(Direction::Vertical)
-                .constraints(constraints)
-                .split(area);
-
-            let mut chunk_index = 0;
-
-            // Render "Storage:" section title if we have pools
-            if !pools_to_show.is_empty() {
-                let storage_title = Paragraph::new("Storage:").style(Typography::widget_title());
-                frame.render_widget(storage_title, content_chunks[chunk_index]);
-                chunk_index += 1;
-            }
-
-            // Display each storage pool with tree structure
-            for (pool_name, drives) in &pools_to_show {
-                // Pool header with status icon and type
-                let pool_display_name = if pool_name == "root" {
-                    "root".to_string()
-                } else {
-                    pool_name.clone()
-                };
-                
-                let pool_type = if drives.len() > 1 { "multi-drive" } else { "Single" };
-                
-                // Get pool status from usage metric
-                let pool_status = metric_store
-                    .get_metric(hostname, &format!("disk_{}_usage_percent", pool_name))
-                    .map(|m| m.status)
-                    .unwrap_or(Status::Unknown);
-                
-                // Create pool header with status icon
-                let pool_status_icon = StatusIcons::get_icon(pool_status);
-                let pool_status_color = Theme::status_color(pool_status);
-                let pool_header_text = format!("{} ({}):", pool_display_name, pool_type);
-                
-                let pool_header_spans = vec![
-                    ratatui::text::Span::styled(
-                        format!("{} ", pool_status_icon),
-                        Style::default().fg(pool_status_color),
-                    ),
-                    ratatui::text::Span::styled(
-                        pool_header_text,
-                        Style::default().fg(Theme::primary_text()),
-                    ),
-                ];
-                let pool_header_para = Paragraph::new(ratatui::text::Line::from(pool_header_spans));
-                frame.render_widget(pool_header_para, content_chunks[chunk_index]);
-                chunk_index += 1;
-
-                // Individual drive lines with tree symbols
-                let mut sorted_drives = drives.clone();
-                sorted_drives.sort();
-                for (_drive_idx, drive_name) in sorted_drives.iter().enumerate() {
-                    // Get drive health status
-                    let drive_health_metric = metric_store
-                        .get_metric(hostname, &format!("disk_{}_{}_health", pool_name, drive_name));
-                    let drive_status = drive_health_metric
-                        .map(|m| m.status)
-                        .unwrap_or(Status::Unknown);
-                    
-                    // Get drive temperature
-                    let temp_text = metric_store
-                        .get_metric(hostname, &format!("disk_{}_{}_temperature", pool_name, drive_name))
-                        .and_then(|m| m.value.as_f32())
-                        .map(|temp| format!(" T:{:.0}°C", temp))
-                        .unwrap_or_default();
-
-                    // Get drive wear level (SSDs)
-                    let wear_text = metric_store
-                        .get_metric(hostname, &format!("disk_{}_{}_wear_percent", pool_name, drive_name))
-                        .and_then(|m| m.value.as_f32())
-                        .map(|wear| format!(" W:{:.0}%", wear))
-                        .unwrap_or_default();
-
-                    // Build drive line with tree symbol
-                    let tree_symbol = "├─";
-                    let drive_status_icon = StatusIcons::get_icon(drive_status);
-                    let drive_status_color = Theme::status_color(drive_status);
-                    let drive_text = format!("{}{}{}", drive_name, temp_text, wear_text);
-                    
-                    let drive_spans = vec![
-                        ratatui::text::Span::styled("  ", Style::default()), // 2-space indentation
-                        ratatui::text::Span::styled(
-                            format!("{} ", tree_symbol),
-                            Style::default().fg(Theme::muted_text()),
-                        ),
-                        ratatui::text::Span::styled(
-                            format!("{} ", drive_status_icon),
-                            Style::default().fg(drive_status_color),
-                        ),
-                        ratatui::text::Span::styled(
-                            drive_text,
-                            Style::default().fg(Theme::primary_text()),
-                        ),
-                    ];
-                    let drive_para = Paragraph::new(ratatui::text::Line::from(drive_spans));
-                    frame.render_widget(drive_para, content_chunks[chunk_index]);
-                    chunk_index += 1;
-                }
-
-                // Usage line with end tree symbol and status icon
-                let usage_percent = metric_store
-                    .get_metric(hostname, &format!("disk_{}_usage_percent", pool_name))
-                    .and_then(|m| m.value.as_f32())
-                    .unwrap_or(0.0);
-
-                let used_gb = metric_store
-                    .get_metric(hostname, &format!("disk_{}_used_gb", pool_name))
-                    .and_then(|m| m.value.as_f32())
-                    .unwrap_or(0.0);
-
-                let total_gb = metric_store
-                    .get_metric(hostname, &format!("disk_{}_total_gb", pool_name))
-                    .and_then(|m| m.value.as_f32())
-                    .unwrap_or(0.0);
-
-                let usage_status = metric_store
-                    .get_metric(hostname, &format!("disk_{}_usage_percent", pool_name))
-                    .map(|m| m.status)
-                    .unwrap_or(Status::Unknown);
-
-                // Format usage with proper units
-                let (used_display, total_display, unit) = if total_gb < 1.0 {
-                    (used_gb * 1024.0, total_gb * 1024.0, "MB")
-                } else {
-                    (used_gb, total_gb, "GB")
-                };
-
-                let end_tree_symbol = "└─";
-                let usage_status_icon = StatusIcons::get_icon(usage_status);
-                let usage_status_color = Theme::status_color(usage_status);
-                let usage_text = format!("{:.1}% {:.1}{}/{:.1}{}", 
-                    usage_percent, used_display, unit, total_display, unit);
-                
-                let usage_spans = vec![
-                    ratatui::text::Span::styled("  ", Style::default()), // 2-space indentation
-                    ratatui::text::Span::styled(
-                        format!("{} ", end_tree_symbol),
-                        Style::default().fg(Theme::muted_text()),
-                    ),
-                    ratatui::text::Span::styled(
-                        format!("{} ", usage_status_icon),
-                        Style::default().fg(usage_status_color),
-                    ),
-                    ratatui::text::Span::styled(
-                        usage_text,
-                        Style::default().fg(Theme::primary_text()),
-                    ),
-                ];
-                let usage_para = Paragraph::new(ratatui::text::Line::from(usage_spans));
-                frame.render_widget(usage_para, content_chunks[chunk_index]);
-                chunk_index += 1;
-            }
-
-            // Show truncation indicator if we couldn't display all pools
-            if pools_to_show.len() < storage_pools.len() {
-                if let Some(last_chunk) = content_chunks.last() {
-                    let truncated_count = storage_pools.len() - pools_to_show.len();
-                    let truncated_text = format!(
-                        "... and {} more pool{}",
-                        truncated_count,
-                        if truncated_count == 1 { "" } else { "s" }
-                    );
-                    let truncated_para = Paragraph::new(truncated_text).style(Typography::muted());
-                    frame.render_widget(truncated_para, *last_chunk);
-                }
-            }
-        } else {
-            // No host connected
-            let content_chunks = ratatui::layout::Layout::default()
-                .direction(Direction::Vertical)
-                .constraints([Constraint::Length(1), Constraint::Min(0)])
-                .split(area);
-
-            let storage_title = Paragraph::new("Storage:").style(Typography::widget_title());
-            frame.render_widget(storage_title, content_chunks[0]);
-
-            let no_host_spans =
-                StatusIcons::create_status_spans(Status::Unknown, "No host connected");
-            let no_host_para = Paragraph::new(ratatui::text::Line::from(no_host_spans));
-            frame.render_widget(no_host_para, content_chunks[1]);
         }
+        Ok(mac)
     }
 }

dashboard/src/ui/theme.rs

@@ -143,10 +143,12 @@ impl Theme {
     pub fn status_color(status: Status) -> Color {
         match status {
             Status::Ok => Self::success(),
+            Status::Inactive => Self::muted_text(), // Gray for inactive services in service list
             Status::Pending => Self::highlight(), // Blue for pending
             Status::Warning => Self::warning(),
             Status::Critical => Self::error(),
             Status::Unknown => Self::muted_text(),
+            Status::Offline => Self::muted_text(), // Dark gray for offline
         }
     }
 
@@ -223,13 +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;
-    /// System panel CPU section height
-    pub const CPU_SECTION_HEIGHT: u16 = 2;
-    /// System panel memory section height  
-    pub const MEMORY_SECTION_HEIGHT: u16 = 3;
 }
 
 /// Typography system
@@ -246,10 +241,12 @@ impl StatusIcons {
     pub fn get_icon(status: Status) -> &'static str {
         match status {
             Status::Ok => "●",
+            Status::Inactive => "○", // Empty circle for inactive services
             Status::Pending => "◉", // Hollow circle for pending
             Status::Warning => "◐",
-            Status::Critical => "◯",
+            Status::Critical => "!",
             Status::Unknown => "?",
+            Status::Offline => "○", // Empty circle for offline
         }
     }
 
@@ -258,10 +255,12 @@ impl StatusIcons {
         let icon = Self::get_icon(status);
         let status_color = match status {
             Status::Ok => Theme::success(),         // Green
+            Status::Inactive => Theme::muted_text(), // Gray for inactive services
             Status::Pending => Theme::highlight(),       // Blue
             Status::Warning => Theme::warning(),    // Yellow
             Status::Critical => Theme::error(),     // Red
             Status::Unknown => Theme::muted_text(), // Gray
+            Status::Offline => Theme::muted_text(), // Dark gray for offline
         };
 
         vec![
@@ -293,27 +292,9 @@ impl Components {
             )
     }
 
-    /// Widget block with focus indicator (blue border)
-    pub fn focused_widget_block(title: &str) -> Block<'_> {
-        Block::default()
-            .title(title)
-            .borders(Borders::ALL)
-            .style(Style::default().fg(Theme::highlight()).bg(Theme::background())) // Blue border for focus
-            .title_style(
-                Style::default()
-                    .fg(Theme::highlight()) // Blue title for focus
-                    .bg(Theme::background()),
-            )
-    }
 }
 
 impl Typography {
-    /// Main title style (dashboard header)
-    pub fn title() -> Style {
-        Style::default()
-            .fg(Theme::primary_text())
-            .bg(Theme::background())
-    }
 
     /// Widget title style (panel headers) - bold bright white
     pub fn widget_title() -> Style {

dashboard/src/ui/widgets/backup.rs

@@ -1,486 +0,0 @@
-use cm_dashboard_shared::{Metric, Status};
-use ratatui::{
-    layout::Rect,
-    widgets::Paragraph,
-    Frame,
-};
-use tracing::debug;
-
-use super::Widget;
-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 number of backup services
-    total_services: 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 filesystem label
-    backup_disk_filesystem_label: Option<String>,
-    /// Number of completed services
-    services_completed_count: Option<i64>,
-    /// Number of failed services
-    services_failed_count: Option<i64>,
-    /// Number of disabled services
-    services_disabled_count: Option<i64>,
-    /// 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,
-    exit_code: Option<i64>,
-    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_services: 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_filesystem_label: None,
-            services_completed_count: None,
-            services_failed_count: None,
-            services_disabled_count: 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 timestamp for display
-    fn format_last_run(&self) -> String {
-        match self.last_run_timestamp {
-            Some(timestamp) => {
-                let duration = chrono::Utc::now().timestamp() - timestamp;
-                if duration < 3600 {
-                    format!("{}m ago", duration / 60)
-                } else if duration < 86400 {
-                    format!("{}h ago", duration / 3600)
-                } else {
-                    format!("{}d ago", duration / 86400)
-                }
-            }
-            None => "—".to_string(),
-        }
-    }
-
-    /// Format disk usage in format "usedGB/totalGB"
-    fn format_repo_size(&self) -> String {
-        match (self.backup_disk_used_gb, self.backup_disk_total_gb) {
-            (Some(used_gb), Some(total_gb)) => {
-                let used_str = Self::format_size_with_proper_units(used_gb);
-                let total_str = Self::format_size_with_proper_units(total_gb);
-                format!("{}/{}", used_str, total_str)
-            }
-            (Some(used_gb), None) => {
-                // Fallback to just used size if total not available
-                Self::format_size_with_proper_units(used_gb)
-            }
-            _ => "—".to_string(),
-        }
-    }
-
-    /// 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)
-        }
-    }
-
-    /// Format product name display
-    fn format_product_name(&self) -> String {
-        if let Some(ref product_name) = self.backup_disk_product_name {
-            format!("P/N: {}", product_name)
-        } else {
-            "P/N: Unknown".to_string()
-        }
-    }
-
-    /// Format serial number display
-    fn format_serial_number(&self) -> String {
-        if let Some(ref serial) = self.backup_disk_serial_number {
-            format!("S/N: {}", serial)
-        } else {
-            "S/N: Unknown".to_string()
-        }
-    }
-
-    /// Extract service name from metric name (e.g., "backup_service_gitea_status" -> "gitea")
-    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("_exit_code") {
-                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_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_services" => {
-                    self.total_services = 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_filesystem_label" => {
-                    self.backup_disk_filesystem_label = Some(metric.value.as_string());
-                }
-                "backup_services_completed_count" => {
-                    self.services_completed_count = metric.value.as_i64();
-                }
-                "backup_services_failed_count" => {
-                    self.services_failed_count = metric.value.as_i64();
-                }
-                "backup_services_disabled_count" => {
-                    self.services_disabled_count = metric.value.as_i64();
-                }
-                _ => {
-                    // 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,
-                                exit_code: None,
-                                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("_exit_code") {
-                            entry.exit_code = metric.value.as_i64();
-                        } 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;
-
-        self.has_data = !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
-            );
-        }
-    }
-
-    fn render(&mut self, frame: &mut Frame, area: Rect) {
-        self.render_with_scroll(frame, area, 0);
-    }
-}
-
-impl BackupWidget {
-    /// Render with scroll offset support
-    pub fn render_with_scroll(&mut self, frame: &mut Frame, area: Rect, scroll_offset: usize) {
-        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));
-
-            // Serial number as sub-item
-            if let Some(serial) = &self.backup_disk_serial_number {
-                lines.push(ratatui::text::Line::from(vec![
-                    ratatui::text::Span::styled("  ├─ ", Typography::tree()),
-                    ratatui::text::Span::styled(format!("S/N: {}", serial), Typography::secondary())
-                ]));
-            }
-
-            // Usage as sub-item
-            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);
-                lines.push(ratatui::text::Line::from(vec![
-                    ratatui::text::Span::styled("  └─ ", Typography::tree()),
-                    ratatui::text::Span::styled(format!("Usage: {}/{}", used_str, total_str), 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;
-        
-        // Calculate scroll boundaries
-        let max_scroll = if total_lines > available_height {
-            total_lines - available_height
-        } else {
-            total_lines.saturating_sub(1)
-        };
-        let effective_scroll = scroll_offset.min(max_scroll);
-        
-        // Apply scrolling if needed
-        if scroll_offset > 0 || total_lines > available_height {
-            let mut visible_lines: Vec<_> = lines
-                .into_iter()
-                .skip(effective_scroll)
-                .take(available_height)
-                .collect();
-            
-            // Add scroll indicator if there are hidden lines
-            if total_lines > available_height {
-                let hidden_above = effective_scroll;
-                let hidden_below = total_lines.saturating_sub(effective_scroll + available_height);
-                
-                if (hidden_above > 0 || hidden_below > 0) && !visible_lines.is_empty() {
-                    let scroll_text = if hidden_above > 0 && hidden_below > 0 {
-                        format!("... {} above, {} below", hidden_above, hidden_below)
-                    } else if hidden_above > 0 {
-                        format!("... {} more above", hidden_above)
-                    } else {
-                        format!("... {} more below", hidden_below)
-                    };
-                    
-                    // Replace last line with scroll indicator
-                    visible_lines.pop();
-                    visible_lines.push(ratatui::text::Line::from(vec![
-                        ratatui::text::Span::styled(scroll_text, Typography::muted())
-                    ]));
-                }
-            }
-            
-            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

@@ -1,139 +0,0 @@
-use cm_dashboard_shared::{Metric, Status};
-use ratatui::{
-    layout::{Constraint, Direction, Layout, Rect},
-    widgets::Paragraph,
-    Frame,
-};
-use tracing::debug;
-
-use super::Widget;
-use crate::ui::theme::{StatusIcons, Typography};
-
-/// CPU widget displaying load, temperature, and frequency
-#[derive(Clone)]
-pub struct CpuWidget {
-    /// CPU load averages (1, 5, 15 minutes)
-    load_1min: Option<f32>,
-    load_5min: Option<f32>,
-    load_15min: Option<f32>,
-    /// CPU temperature in Celsius
-    temperature: Option<f32>,
-    /// CPU frequency in MHz
-    frequency: Option<f32>,
-    /// Aggregated status
-    status: Status,
-    /// Last update indicator
-    has_data: bool,
-}
-
-impl CpuWidget {
-    pub fn new() -> Self {
-        Self {
-            load_1min: None,
-            load_5min: None,
-            load_15min: None,
-            temperature: None,
-            frequency: None,
-            status: Status::Unknown,
-            has_data: false,
-        }
-    }
-
-    /// Format load average for display
-    fn format_load(&self) -> String {
-        match (self.load_1min, self.load_5min, self.load_15min) {
-            (Some(l1), Some(l5), Some(l15)) => {
-                format!("{:.2} {:.2} {:.2}", l1, l5, l15)
-            }
-            _ => "— — —".to_string(),
-        }
-    }
-
-    /// Format frequency for display
-    fn format_frequency(&self) -> String {
-        match self.frequency {
-            Some(freq) => format!("{:.1} MHz", freq),
-            None => "— MHz".to_string(),
-        }
-    }
-}
-
-impl Widget for CpuWidget {
-    fn update_from_metrics(&mut self, metrics: &[&Metric]) {
-        debug!("CPU widget updating with {} metrics", metrics.len());
-
-        // Reset status aggregation
-        let mut statuses = Vec::new();
-
-        for metric in metrics {
-            match metric.name.as_str() {
-                "cpu_load_1min" => {
-                    if let Some(value) = metric.value.as_f32() {
-                        self.load_1min = Some(value);
-                        statuses.push(metric.status);
-                    }
-                }
-                "cpu_load_5min" => {
-                    if let Some(value) = metric.value.as_f32() {
-                        self.load_5min = Some(value);
-                        statuses.push(metric.status);
-                    }
-                }
-                "cpu_load_15min" => {
-                    if let Some(value) = metric.value.as_f32() {
-                        self.load_15min = Some(value);
-                        statuses.push(metric.status);
-                    }
-                }
-                "cpu_temperature_celsius" => {
-                    if let Some(value) = metric.value.as_f32() {
-                        self.temperature = Some(value);
-                        statuses.push(metric.status);
-                    }
-                }
-                "cpu_frequency_mhz" => {
-                    if let Some(value) = metric.value.as_f32() {
-                        self.frequency = Some(value);
-                        statuses.push(metric.status);
-                    }
-                }
-                _ => {}
-            }
-        }
-
-        // Aggregate status
-        self.status = if statuses.is_empty() {
-            Status::Unknown
-        } else {
-            Status::aggregate(&statuses)
-        };
-
-        self.has_data = !metrics.is_empty();
-
-        debug!(
-            "CPU widget updated: load={:?}, temp={:?}, freq={:?}, status={:?}",
-            self.load_1min, self.temperature, self.frequency, self.status
-        );
-    }
-
-    fn render(&mut self, frame: &mut Frame, area: Rect) {
-        let content_chunks = Layout::default()
-            .direction(Direction::Vertical)
-            .constraints([Constraint::Length(1), Constraint::Length(1)])
-            .split(area);
-        let cpu_title = Paragraph::new("CPU:").style(Typography::widget_title());
-        frame.render_widget(cpu_title, content_chunks[0]);
-        let load_freq_spans = StatusIcons::create_status_spans(
-            self.status,
-            &format!("Load: {} • {}", self.format_load(), self.format_frequency()),
-        );
-        let load_freq_para = Paragraph::new(ratatui::text::Line::from(load_freq_spans));
-        frame.render_widget(load_freq_para, content_chunks[1]);
-    }
-}
-
-impl Default for CpuWidget {
-    fn default() -> Self {
-        Self::new()
-    }
-}

dashboard/src/ui/widgets/memory.rs

@@ -1,253 +0,0 @@
-use cm_dashboard_shared::{Metric, Status};
-use ratatui::{
-    layout::{Constraint, Direction, Layout, Rect},
-    widgets::Paragraph,
-    Frame,
-};
-use tracing::debug;
-
-use super::Widget;
-use crate::ui::theme::{StatusIcons, Typography};
-
-/// Memory widget displaying usage, totals, and swap information
-#[derive(Clone)]
-pub struct MemoryWidget {
-    /// Memory usage percentage
-    usage_percent: Option<f32>,
-    /// Total memory in GB
-    total_gb: Option<f32>,
-    /// Used memory in GB
-    used_gb: Option<f32>,
-    /// Available memory in GB
-    available_gb: Option<f32>,
-    /// Total swap in GB
-    swap_total_gb: Option<f32>,
-    /// Used swap in GB
-    swap_used_gb: Option<f32>,
-    /// /tmp directory size in MB
-    tmp_size_mb: Option<f32>,
-    /// /tmp total size in MB
-    tmp_total_mb: Option<f32>,
-    /// /tmp usage percentage
-    tmp_usage_percent: Option<f32>,
-    /// Aggregated status
-    status: Status,
-    /// Last update indicator
-    has_data: bool,
-}
-
-impl MemoryWidget {
-    pub fn new() -> Self {
-        Self {
-            usage_percent: None,
-            total_gb: None,
-            used_gb: None,
-            available_gb: None,
-            swap_total_gb: None,
-            swap_used_gb: None,
-            tmp_size_mb: None,
-            tmp_total_mb: None,
-            tmp_usage_percent: None,
-            status: Status::Unknown,
-            has_data: false,
-        }
-    }
-
-    /// Get memory usage percentage for gauge
-    fn get_memory_percentage(&self) -> u16 {
-        match self.usage_percent {
-            Some(percent) => percent.min(100.0).max(0.0) as u16,
-            None => {
-                // Calculate from used/total if percentage not available
-                match (self.used_gb, self.total_gb) {
-                    (Some(used), Some(total)) if total > 0.0 => {
-                        let percent = (used / total * 100.0).min(100.0).max(0.0);
-                        percent as u16
-                    }
-                    _ => 0,
-                }
-            }
-        }
-    }
-
-    /// Format size with proper units (kB/MB/GB)
-    fn format_size_units(size_mb: f32) -> String {
-        if size_mb >= 1024.0 {
-            // Convert to GB
-            let size_gb = size_mb / 1024.0;
-            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 in bytes
-            let size_bytes = size_mb * 1024.0 * 1024.0;
-            format!("{:.0}B", size_bytes)
-        }
-    }
-
-    /// Format /tmp usage as "xx% yyykB/MB/GB/zzzGB"
-    fn format_tmp_usage(&self) -> String {
-        match (self.tmp_usage_percent, self.tmp_size_mb, self.tmp_total_mb) {
-            (Some(percent), Some(used_mb), Some(total_mb)) => {
-                let used_str = Self::format_size_units(used_mb);
-                let total_str = Self::format_size_units(total_mb);
-                format!("{:.1}% {}/{}", percent, used_str, total_str)
-            }
-            (Some(percent), Some(used_mb), None) => {
-                let used_str = Self::format_size_units(used_mb);
-                format!("{:.1}% {}", percent, used_str)
-            }
-            (None, Some(used_mb), Some(total_mb)) => {
-                let used_str = Self::format_size_units(used_mb);
-                let total_str = Self::format_size_units(total_mb);
-                format!("{}/{}", used_str, total_str)
-            }
-            (None, Some(used_mb), None) => Self::format_size_units(used_mb),
-            _ => "—".to_string(),
-        }
-    }
-
-    /// Get tmp status based on usage percentage
-    fn get_tmp_status(&self) -> Status {
-        if let Some(tmp_percent) = self.tmp_usage_percent {
-            if tmp_percent >= 90.0 {
-                Status::Critical
-            } else if tmp_percent >= 70.0 {
-                Status::Warning
-            } else {
-                Status::Ok
-            }
-        } else {
-            Status::Unknown
-        }
-    }
-}
-
-impl Widget for MemoryWidget {
-    fn update_from_metrics(&mut self, metrics: &[&Metric]) {
-        debug!("Memory widget updating with {} metrics", metrics.len());
-
-        // Reset status aggregation
-        let mut statuses = Vec::new();
-
-        for metric in metrics {
-            match metric.name.as_str() {
-                "memory_usage_percent" => {
-                    if let Some(value) = metric.value.as_f32() {
-                        self.usage_percent = Some(value);
-                        statuses.push(metric.status);
-                    }
-                }
-                "memory_total_gb" => {
-                    if let Some(value) = metric.value.as_f32() {
-                        self.total_gb = Some(value);
-                        statuses.push(metric.status);
-                    }
-                }
-                "memory_used_gb" => {
-                    if let Some(value) = metric.value.as_f32() {
-                        self.used_gb = Some(value);
-                        statuses.push(metric.status);
-                    }
-                }
-                "memory_available_gb" => {
-                    if let Some(value) = metric.value.as_f32() {
-                        self.available_gb = Some(value);
-                        statuses.push(metric.status);
-                    }
-                }
-                "memory_swap_total_gb" => {
-                    if let Some(value) = metric.value.as_f32() {
-                        self.swap_total_gb = Some(value);
-                        statuses.push(metric.status);
-                    }
-                }
-                "memory_swap_used_gb" => {
-                    if let Some(value) = metric.value.as_f32() {
-                        self.swap_used_gb = Some(value);
-                        statuses.push(metric.status);
-                    }
-                }
-                "disk_tmp_size_mb" => {
-                    if let Some(value) = metric.value.as_f32() {
-                        self.tmp_size_mb = Some(value);
-                        statuses.push(metric.status);
-                    }
-                }
-                "disk_tmp_total_mb" => {
-                    if let Some(value) = metric.value.as_f32() {
-                        self.tmp_total_mb = Some(value);
-                        statuses.push(metric.status);
-                    }
-                }
-                "disk_tmp_usage_percent" => {
-                    if let Some(value) = metric.value.as_f32() {
-                        self.tmp_usage_percent = Some(value);
-                        statuses.push(metric.status);
-                    }
-                }
-                _ => {}
-            }
-        }
-
-        // Aggregate status
-        self.status = if statuses.is_empty() {
-            Status::Unknown
-        } else {
-            Status::aggregate(&statuses)
-        };
-
-        self.has_data = !metrics.is_empty();
-
-        debug!("Memory widget updated: usage={:?}%, total={:?}GB, swap_total={:?}GB, tmp={:?}/{:?}MB, status={:?}",
-               self.usage_percent, self.total_gb, self.swap_total_gb, self.tmp_size_mb, self.tmp_total_mb, self.status);
-    }
-
-    fn render(&mut self, frame: &mut Frame, area: Rect) {
-        let content_chunks = Layout::default()
-            .direction(Direction::Vertical)
-            .constraints([
-                Constraint::Length(1),
-                Constraint::Length(1),
-                Constraint::Length(1),
-            ])
-            .split(area);
-        let mem_title = Paragraph::new("RAM:").style(Typography::widget_title());
-        frame.render_widget(mem_title, content_chunks[0]);
-
-        // Format used and total memory with smart units, percentage, and status icon
-        let used_str = self
-            .used_gb
-            .map_or("—".to_string(), |v| Self::format_size_units(v * 1024.0)); // Convert GB to MB for formatting
-        let total_str = self
-            .total_gb
-            .map_or("—".to_string(), |v| Self::format_size_units(v * 1024.0)); // Convert GB to MB for formatting
-        let percentage = self.get_memory_percentage();
-        let mem_details_spans = StatusIcons::create_status_spans(
-            self.status,
-            &format!("Used: {}% {}/{}", percentage, used_str, total_str),
-        );
-        let mem_details_para = Paragraph::new(ratatui::text::Line::from(mem_details_spans));
-        frame.render_widget(mem_details_para, content_chunks[1]);
-
-        // /tmp usage line with status icon
-        let tmp_status = self.get_tmp_status();
-        let tmp_spans = StatusIcons::create_status_spans(
-            tmp_status,
-            &format!("tmp: {}", self.format_tmp_usage()),
-        );
-        let tmp_para = Paragraph::new(ratatui::text::Line::from(tmp_spans));
-        frame.render_widget(tmp_para, content_chunks[2]);
-    }
-}
-
-impl Default for MemoryWidget {
-    fn default() -> Self {
-        Self::new()
-    }
-}

dashboard/src/ui/widgets/mod.rs

@@ -1,21 +1,13 @@
-use cm_dashboard_shared::Metric;
+use cm_dashboard_shared::AgentData;
-use ratatui::{layout::Rect, Frame};
 
-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;
 
-/// Widget trait for UI components that display metrics
+/// Widget trait for UI components that display structured data
 pub trait Widget {
-    /// Update widget with new metrics data
+    /// Update widget with structured agent data
-    fn update_from_metrics(&mut self, metrics: &[&Metric]);
+    fn update_from_agent_data(&mut self, agent_data: &AgentData);
-
-    /// Render the widget to a terminal frame
-    fn render(&mut self, frame: &mut Frame, area: Rect);
 }

dashboard/src/ui/widgets/services.rs

@@ -1,4 +1,5 @@
 use cm_dashboard_shared::{Metric, Status};
+use super::Widget;
 use ratatui::{
     layout::{Constraint, Direction, Layout, Rect},
     widgets::Paragraph,
@@ -7,9 +8,7 @@ use ratatui::{
 use std::collections::HashMap;
 use tracing::debug;
 
-use super::Widget;
 use crate::ui::theme::{Components, StatusIcons, Theme, Typography};
-use crate::ui::{CommandStatus, CommandType};
 use ratatui::style::Style;
 
 /// Services widget displaying hierarchical systemd service statuses
@@ -29,10 +28,9 @@ 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,
 }
 
@@ -48,6 +46,7 @@ impl ServicesWidget {
     }
 
     /// Extract service name and determine if it's a parent or sub-service
+    #[allow(dead_code)]
     fn extract_service_info(metric_name: &str) -> Option<(String, Option<String>)> {
         if metric_name.starts_with("service_") {
             if let Some(end_pos) = metric_name
@@ -113,13 +112,15 @@ impl ServicesWidget {
             name.to_string()
         };
 
-        // Parent services always show active/inactive status
+        // Convert Status enum to display text
         let status_str = match info.widget_status {
-            Status::Ok => "active".to_string(),
+            Status::Ok => "active",
-            Status::Pending => "pending".to_string(),
+            Status::Inactive => "inactive", 
-            Status::Warning => "inactive".to_string(),
+            Status::Critical => "failed",
-            Status::Critical => "failed".to_string(),
+            Status::Pending => "pending",
-            Status::Unknown => "unknown".to_string(),
+            Status::Warning => "warning",
+            Status::Unknown => "unknown",
+            Status::Offline => "offline",
         };
 
         format!(
@@ -128,40 +129,7 @@ impl ServicesWidget {
         )
     }
 
-    /// Get status icon for service, considering command status for visual feedback
+
-    fn get_service_icon_and_status(&self, service_name: &str, info: &ServiceInfo, command_status: Option<&CommandStatus>) -> (String, String, ratatui::prelude::Color) {
-        // Check if this service is currently being operated on
-        if let Some(status) = command_status {
-            match status {
-                CommandStatus::InProgress { command_type, target, .. } => {
-                    if target == service_name {
-                        // Only show special icons for service commands
-                        if let Some((icon, status_text)) = match command_type {
-                            CommandType::ServiceRestart => Some(("↻", "restarting")),
-                            CommandType::ServiceStart => Some(("↑", "starting")), 
-                            CommandType::ServiceStop => Some(("↓", "stopping")),
-                            _ => None, // Don't handle non-service commands here
-                        } {
-                            return (icon.to_string(), status_text.to_string(), Theme::highlight());
-                        }
-                    }
-                }
-                _ => {} // Success/Failed states will show normal status
-            }
-        }
-        
-        // Normal status display
-        let icon = StatusIcons::get_icon(info.widget_status);
-        let status_color = match info.widget_status {
-            Status::Ok => Theme::success(),
-            Status::Pending => Theme::highlight(),
-            Status::Warning => Theme::warning(),
-            Status::Critical => Theme::error(),
-            Status::Unknown => Theme::muted_text(),
-        };
-        
-        (icon.to_string(), info.status.clone(), status_color)
-    }
 
     /// Create spans for sub-service with icon next to name
     fn create_sub_service_spans(
@@ -169,17 +137,6 @@ impl ServicesWidget {
         name: &str,
         info: &ServiceInfo,
         is_last: bool,
-    ) -> Vec<ratatui::text::Span<'static>> {
-        self.create_sub_service_spans_with_status(name, info, is_last, None)
-    }
-
-    /// Create spans for sub-service with icon next to name, considering command status
-    fn create_sub_service_spans_with_status(
-        &self,
-        name: &str,
-        info: &ServiceInfo,
-        is_last: bool,
-        command_status: Option<&CommandStatus>,
     ) -> Vec<ratatui::text::Span<'static>> {
         // Truncate long sub-service names to fit layout (accounting for indentation)
         let short_name = if name.len() > 18 {
@@ -188,19 +145,38 @@ impl ServicesWidget {
             name.to_string()
         };
 
-        // Get status icon and text, considering command status
+        // Get status icon and text
-        let (icon, mut status_str, status_color) = self.get_service_icon_and_status(name, info, command_status);
+        let icon = StatusIcons::get_icon(info.widget_status);
+        let status_color = match info.widget_status {
+            Status::Ok => Theme::success(),
+            Status::Inactive => Theme::muted_text(),
+            Status::Pending => Theme::highlight(),
+            Status::Warning => Theme::warning(),
+            Status::Critical => Theme::error(),
+            Status::Unknown => Theme::muted_text(),
+            Status::Offline => Theme::muted_text(),
+        };
 
-        // For sub-services, prefer latency if available (unless command is in progress)
+        // Display metrics or status for sub-services
-        if command_status.is_none() {
+        let status_str = if !info.metrics.is_empty() {
-            if let Some(latency) = info.latency_ms {
+            // Show first metric with label and unit
-                status_str = if latency < 0.0 {
+            let (label, value, unit) = &info.metrics[0];
-                    "timeout".to_string()
+            match unit {
-                } else {
+                Some(u) => format!("{}: {:.1} {}", label, value, u),
-                    format!("{:.0}ms", latency)
+                None => format!("{}: {:.1}", label, value),
-                };
             }
-        }
+        } else {
+            // 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 { "├─" };
 
         vec![
@@ -248,33 +224,13 @@ impl ServicesWidget {
     }
 
     /// Get currently selected service name (for actions)
+    /// Only returns parent service names since only parent services can be selected
     pub fn get_selected_service(&self) -> Option<String> {
-        // Build the same display list to find the selected service
+        // Only parent services can be selected, so just get the parent service at selected_index
-        let mut display_lines: Vec<(String, Status, bool, Option<(ServiceInfo, bool)>)> = Vec::new();
-        
         let mut parent_services: Vec<_> = self.parent_services.iter().collect();
         parent_services.sort_by(|(a, _), (b, _)| a.cmp(b));
-
-        for (parent_name, parent_info) in parent_services {
-            display_lines.push((parent_name.clone(), parent_info.widget_status, false, None));
-            
-            if let Some(sub_list) = self.sub_services.get(parent_name) {
-                let mut sorted_subs = sub_list.clone();
-                sorted_subs.sort_by(|(a, _), (b, _)| a.cmp(b));
-                
-                for (i, (sub_name, sub_info)) in sorted_subs.iter().enumerate() {
-                    let is_last_sub = i == sorted_subs.len() - 1;
-                    display_lines.push((
-                        format!("{}_{}", parent_name, sub_name), // Use parent_sub format for sub-services
-                        sub_info.widget_status,
-                        true,
-                        Some((sub_info.clone(), is_last_sub)),
-                    ));
-                }
-            }
-        }
         
-        display_lines.get(self.selected_index).map(|(name, _, _, _)| name.clone())
+        parent_services.get(self.selected_index).map(|(name, _)| name.to_string())
     }
 
     /// Get total count of selectable services (parent services only, not sub-services)
@@ -283,6 +239,7 @@ impl ServicesWidget {
         self.parent_services.len()
     }
 
+
     /// Calculate which parent service index corresponds to a display line index
     fn calculate_parent_service_index(&self, display_line_index: &usize) -> usize {
         // Build the same display list to map line index to parent service index
@@ -313,6 +270,59 @@ impl ServicesWidget {
 }
 
 impl Widget for ServicesWidget {
+    fn update_from_agent_data(&mut self, agent_data: &cm_dashboard_shared::AgentData) {
+        self.has_data = true;
+        self.parent_services.clear();
+        self.sub_services.clear();
+        
+        for service in &agent_data.services {
+            // Store parent service
+            let parent_info = ServiceInfo {
+                memory_mb: Some(service.memory_mb),
+                disk_gb: Some(service.disk_gb),
+                metrics: Vec::new(), // Parent services don't have custom metrics
+                widget_status: service.service_status,
+            };
+            self.parent_services.insert(service.name.clone(), parent_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 {
+                        memory_mb: None, // Not used for sub-services
+                        disk_gb: None,   // Not used for sub-services
+                        metrics,
+                        widget_status: sub_service.service_status,
+                    };
+                    sub_list.push((sub_service.name.clone(), sub_info));
+                }
+                self.sub_services.insert(service.name.clone(), sub_list);
+            }
+        }
+        
+        // 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)
+        };
+    }
+}
+
+impl ServicesWidget {
+    #[allow(dead_code)]
     fn update_from_metrics(&mut self, metrics: &[&Metric]) {
         debug!("Services widget updating with {} metrics", metrics.len());
 
@@ -328,15 +338,13 @@ impl Widget for 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,
                                 });
 
                         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() {
@@ -365,10 +373,9 @@ impl Widget for 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,
                                 },
                             ));
@@ -376,7 +383,6 @@ impl Widget for ServicesWidget {
                         };
 
                         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() {
@@ -386,11 +392,6 @@ impl Widget for ServicesWidget {
                             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;
-                            }
                         }
                     }
                 }
@@ -432,24 +433,13 @@ impl Widget for ServicesWidget {
         );
     }
 
-    fn render(&mut self, frame: &mut Frame, area: Rect) {
-        self.render_with_focus(frame, area, false);
-    }
 }
 
 impl ServicesWidget {
-    /// Render with optional focus indicator and scroll support
-    pub fn render_with_focus(&mut self, frame: &mut Frame, area: Rect, is_focused: bool) {
-        self.render_with_focus_and_scroll(frame, area, is_focused, 0);
-    }
 
-    /// Render with focus, scroll, and command status for visual feedback
+    /// Render with focus
-    pub fn render_with_command_status(&mut self, frame: &mut Frame, area: Rect, is_focused: bool, scroll_offset: usize, command_status: Option<&CommandStatus>) {
+    pub fn render(&mut self, frame: &mut Frame, area: Rect, is_focused: bool) {
-        let services_block = if is_focused {
+        let services_block = Components::widget_block("services");
-            Components::focused_widget_block("services")
-        } else {
-            Components::widget_block("services")
-        };
         let inner_area = services_block.inner(area);
         frame.render_widget(services_block, area);
 
@@ -473,199 +463,12 @@ impl ServicesWidget {
             return;
         }
 
-        // Use the existing render logic but with command status
+        // Render the services list
-        self.render_services_with_status(frame, content_chunks[1], is_focused, scroll_offset, command_status);
+        self.render_services(frame, content_chunks[1], is_focused);
     }
 
-    /// Render services list with command status awareness
+    /// Render services list
-    fn render_services_with_status(&mut self, frame: &mut Frame, area: Rect, is_focused: bool, scroll_offset: usize, command_status: Option<&CommandStatus>) {
+    fn render_services(&mut self, frame: &mut Frame, area: Rect, is_focused: bool) {
-        // Build hierarchical service list for display (same as existing logic)
-        let mut display_lines: Vec<(String, Status, bool, Option<(ServiceInfo, bool)>)> = Vec::new();
-
-        // Sort parent services alphabetically for consistent order
-        let mut parent_services: Vec<_> = self.parent_services.iter().collect();
-        parent_services.sort_by(|(a, _), (b, _)| a.cmp(b));
-
-        for (parent_name, parent_info) in parent_services {
-            // Add parent service line
-            let parent_line = self.format_parent_service_line(parent_name, parent_info);
-            display_lines.push((parent_line, parent_info.widget_status, false, None)); // false = not sub-service
-
-            // Add sub-services for this parent (if any)
-            if let Some(sub_list) = self.sub_services.get(parent_name) {
-                // Sort sub-services by name for consistent display
-                let mut sorted_subs = sub_list.clone();
-                sorted_subs.sort_by(|(a, _), (b, _)| a.cmp(b));
-
-                for (i, (sub_name, sub_info)) in sorted_subs.iter().enumerate() {
-                    let is_last_sub = i == sorted_subs.len() - 1;
-                    // Store sub-service info for custom span rendering
-                    display_lines.push((
-                        sub_name.clone(),
-                        sub_info.widget_status,
-                        true,
-                        Some((sub_info.clone(), is_last_sub)),
-                    )); // true = sub-service, with is_last info
-                }
-            }
-        }
-
-        // Apply scroll offset and render visible lines (same as existing logic)
-        let available_lines = area.height as usize;
-        let total_lines = display_lines.len();
-        
-        // Calculate scroll boundaries
-        let max_scroll = if total_lines > available_lines {
-            total_lines - available_lines
-        } else {
-            total_lines.saturating_sub(1)
-        };
-        let effective_scroll = scroll_offset.min(max_scroll);
-        
-        // Get visible lines after scrolling
-        let visible_lines: Vec<_> = display_lines
-            .iter()
-            .skip(effective_scroll)
-            .take(available_lines)
-            .collect();
-        
-        let lines_to_show = visible_lines.len();
-
-        if lines_to_show > 0 {
-            let service_chunks = Layout::default()
-                .direction(Direction::Vertical)
-                .constraints(vec![Constraint::Length(1); lines_to_show])
-                .split(area);
-
-            for (i, (line_text, line_status, is_sub, sub_info)) in visible_lines.iter().enumerate()
-            {
-                let actual_index = effective_scroll + i; // Real index in the full list
-                
-                // Only parent services can be selected - calculate parent service index
-                let is_selected = if !*is_sub {
-                    // This is a parent service - count how many parent services came before this one
-                    let parent_index = self.calculate_parent_service_index(&actual_index);
-                    parent_index == self.selected_index
-                } else {
-                    false // Sub-services are never selected
-                };
-                
-                let mut spans = if *is_sub && sub_info.is_some() {
-                    // Use custom sub-service span creation WITH command status
-                    let (service_info, is_last) = sub_info.as_ref().unwrap();
-                    self.create_sub_service_spans_with_status(line_text, service_info, *is_last, command_status)
-                } else {
-                    // Parent services - check if this parent service has a command in progress
-                    let service_spans = if let Some(status) = command_status {
-                        match status {
-                            CommandStatus::InProgress { target, .. } => {
-                                if target == line_text {
-                                    // Create spans with progress status
-                                    let (icon, status_text, status_color) = self.get_service_icon_and_status(line_text, &ServiceInfo { 
-                                        status: "".to_string(), 
-                                        memory_mb: None, 
-                                        disk_gb: None, 
-                                        latency_ms: None, 
-                                        widget_status: *line_status 
-                                    }, command_status);
-                                    vec![
-                                        ratatui::text::Span::styled(format!("{} ", icon), Style::default().fg(status_color)),
-                                        ratatui::text::Span::styled(line_text.clone(), Style::default().fg(Theme::primary_text())),
-                                        ratatui::text::Span::styled(format!(" {}", status_text), Style::default().fg(status_color)),
-                                    ]
-                                } else {
-                                    StatusIcons::create_status_spans(*line_status, line_text)
-                                }
-                            }
-                            _ => StatusIcons::create_status_spans(*line_status, line_text)
-                        }
-                    } else {
-                        StatusIcons::create_status_spans(*line_status, line_text)
-                    };
-                    service_spans
-                };
-                
-                // Apply selection highlighting to parent services only, preserving status icon color
-                // Only show selection when Services panel is focused
-                if is_selected && !*is_sub && is_focused {
-                    for (i, span) in spans.iter_mut().enumerate() {
-                        if i == 0 {
-                            // First span is the status icon - preserve its color
-                            span.style = span.style.bg(Theme::highlight());
-                        } else {
-                            // Other spans (text) get full selection highlighting
-                            span.style = span.style
-                                .bg(Theme::highlight())
-                                .fg(Theme::background());
-                        }
-                    }
-                }
-                
-                let service_para = Paragraph::new(ratatui::text::Line::from(spans));
-                
-                frame.render_widget(service_para, service_chunks[i]);
-            }
-        }
-
-        // Show scroll indicator if there are more services than we can display (same as existing)
-        if total_lines > available_lines {
-            let hidden_above = effective_scroll;
-            let hidden_below = total_lines.saturating_sub(effective_scroll + available_lines);
-            
-            if hidden_above > 0 || hidden_below > 0 {
-                let scroll_text = if hidden_above > 0 && hidden_below > 0 {
-                    format!("... {} above, {} below", hidden_above, hidden_below)
-                } else if hidden_above > 0 {
-                    format!("... {} more above", hidden_above)
-                } else {
-                    format!("... {} more below", hidden_below)
-                };
-                
-                if available_lines > 0 && lines_to_show > 0 {
-                    let last_line_area = Rect {
-                        x: area.x,
-                        y: area.y + (lines_to_show - 1) as u16,
-                        width: area.width,
-                        height: 1,
-                    };
-                    
-                    let scroll_para = Paragraph::new(scroll_text).style(Typography::muted());
-                    frame.render_widget(scroll_para, last_line_area);
-                }
-            }
-        }
-    }
-
-    /// Render with focus indicator and scroll offset
-    pub fn render_with_focus_and_scroll(&mut self, frame: &mut Frame, area: Rect, is_focused: bool, scroll_offset: usize) {
-        let services_block = if is_focused {
-            Components::focused_widget_block("services")
-        } else {
-            Components::widget_block("services")
-        };
-        let inner_area = services_block.inner(area);
-        frame.render_widget(services_block, area);
-
-        let content_chunks = Layout::default()
-            .direction(Direction::Vertical)
-            .constraints([Constraint::Length(1), Constraint::Min(0)])
-            .split(inner_area);
-
-        // Header
-        let header = format!(
-            "{:<25} {:<10} {:<8} {:<8}",
-            "Service:", "Status:", "RAM:", "Disk:"
-        );
-        let header_para = Paragraph::new(header).style(Typography::muted());
-        frame.render_widget(header_para, content_chunks[0]);
-
-        // Check if we have any services to display
-        if self.parent_services.is_empty() && self.sub_services.is_empty() {
-            let empty_text = Paragraph::new("No process data").style(Typography::muted());
-            frame.render_widget(empty_text, content_chunks[1]);
-            return;
-        }
-
         // Build hierarchical service list for display
         let mut display_lines: Vec<(String, Status, bool, Option<(ServiceInfo, bool)>)> = Vec::new();
 
@@ -676,7 +479,7 @@ impl ServicesWidget {
         for (parent_name, parent_info) in parent_services {
             // Add parent service line
             let parent_line = self.format_parent_service_line(parent_name, parent_info);
-            display_lines.push((parent_line, parent_info.widget_status, false, None)); // false = not sub-service
+            display_lines.push((parent_line, parent_info.widget_status, false, None));
 
             // Add sub-services for this parent (if any)
             if let Some(sub_list) = self.sub_services.get(parent_name) {
@@ -697,36 +500,37 @@ impl ServicesWidget {
             }
         }
 
-        // Apply scroll offset and render visible lines
+        // Show only what fits, with "X more below" if needed
-        let available_lines = content_chunks[1].height as usize;
+        let available_lines = area.height as usize;
         let total_lines = display_lines.len();
         
-        // Calculate scroll boundaries
+        // Reserve one line for "X more below" if needed
-        let max_scroll = if total_lines > available_lines {
+        let lines_for_content = if total_lines > available_lines {
-            total_lines - available_lines
+            available_lines.saturating_sub(1)
         } else {
-            total_lines.saturating_sub(1)
+            available_lines
         };
-        let effective_scroll = scroll_offset.min(max_scroll);
         
-        // Get visible lines after scrolling
         let visible_lines: Vec<_> = display_lines
             .iter()
-            .skip(effective_scroll)
+            .take(lines_for_content)
-            .take(available_lines)
             .collect();
         
+        let hidden_below = total_lines.saturating_sub(lines_for_content);
+        
         let lines_to_show = visible_lines.len();
 
         if lines_to_show > 0 {
+            // Add space for "X more below" message if needed
+            let total_chunks_needed = if hidden_below > 0 { lines_to_show + 1 } else { lines_to_show };
             let service_chunks = Layout::default()
                 .direction(Direction::Vertical)
-                .constraints(vec![Constraint::Length(1); lines_to_show])
+                .constraints(vec![Constraint::Length(1); total_chunks_needed])
-                .split(content_chunks[1]);
+                .split(area);
 
             for (i, (line_text, line_status, is_sub, sub_info)) in visible_lines.iter().enumerate()
             {
-                let actual_index = effective_scroll + i; // Real index in the full list
+                let actual_index = i; // Simple index since we're not scrolling
                 
                 // Only parent services can be selected - calculate parent service index
                 let is_selected = if !*is_sub {
@@ -742,17 +546,19 @@ impl ServicesWidget {
                     let (service_info, is_last) = sub_info.as_ref().unwrap();
                     self.create_sub_service_spans(line_text, service_info, *is_last)
                 } else {
-                    // Use regular status spans for parent services
+                    // Parent services - use normal status spans
                     StatusIcons::create_status_spans(*line_status, line_text)
                 };
                 
-                // Apply selection highlighting to parent services only, preserving status icon color
+                // Apply selection highlighting to parent services only
                 // Only show selection when Services panel is focused
                 if is_selected && !*is_sub && is_focused {
                     for (i, span) in spans.iter_mut().enumerate() {
                         if i == 0 {
-                            // First span is the status icon - preserve its color
+                            // First span is the status icon - use background color for visibility against blue selection
-                            span.style = span.style.bg(Theme::highlight());
+                            span.style = span.style
+                                .bg(Theme::highlight())
+                                .fg(Theme::background());
                         } else {
                             // Other spans (text) get full selection highlighting
                             span.style = span.style
@@ -766,33 +572,12 @@ impl ServicesWidget {
                 
                 frame.render_widget(service_para, service_chunks[i]);
             }
-        }
-
-        // Show scroll indicator if there are more services than we can display
-        if total_lines > available_lines {
-            let hidden_above = effective_scroll;
-            let hidden_below = total_lines.saturating_sub(effective_scroll + available_lines);
             
-            if hidden_above > 0 || hidden_below > 0 {
+            // Show "X more below" message if content was truncated
-                let scroll_text = if hidden_above > 0 && hidden_below > 0 {
+            if hidden_below > 0 {
-                    format!("... {} above, {} below", hidden_above, hidden_below)
+                let more_text = format!("... {} more below", hidden_below);
-                } else if hidden_above > 0 {
+                let more_para = Paragraph::new(more_text).style(Typography::muted());
-                    format!("... {} more above", hidden_above)
+                frame.render_widget(more_para, service_chunks[lines_to_show]);
-                } else {
-                    format!("... {} more below", hidden_below)
-                };
-                
-                if available_lines > 0 && lines_to_show > 0 {
-                    let last_line_area = Rect {
-                        x: content_chunks[1].x,
-                        y: content_chunks[1].y + (lines_to_show - 1) as u16,
-                        width: content_chunks[1].width,
-                        height: 1,
-                    };
-                    
-                    let scroll_para = Paragraph::new(scroll_text).style(Typography::muted());
-                    frame.render_widget(scroll_para, last_line_area);
-                }
             }
         }
     }

dashboard/src/ui/widgets/system.rs

@@ -1,4 +1,4 @@
-use cm_dashboard_shared::{Metric, MetricValue, Status};
+use cm_dashboard_shared::Status;
 use ratatui::{
     layout::Rect,
     text::{Line, Span, Text},
@@ -6,18 +6,18 @@ use ratatui::{
     Frame,
 };
 
-use super::Widget;
 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>,
-    config_hash: Option<String>,
-    active_users: Option<String>,
     agent_hash: Option<String>,
-    
+
+    // Network interfaces
+    network_interfaces: Vec<cm_dashboard_shared::NetworkInterfaceData>,
+
     // CPU metrics
     cpu_load_1min: Option<f32>,
     cpu_load_5min: Option<f32>,
@@ -33,10 +33,24 @@ pub struct SystemWidget {
     tmp_used_gb: Option<f32>,
     tmp_total_gb: Option<f32>,
     memory_status: Status,
+    tmp_status: Status,
+    /// All tmpfs mounts (for auto-discovery support)
+    tmpfs_mounts: Vec<cm_dashboard_shared::TmpfsData>,
     
     // 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,
 }
@@ -45,8 +59,11 @@ pub struct SystemWidget {
 struct StoragePool {
     name: String,
     mount_point: String,
-    pool_type: String, // "Single", "Raid0", etc.
+    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>,
     total_gb: Option<f32>,
@@ -61,13 +78,21 @@ struct StorageDrive {
     status: Status,
 }
 
+#[derive(Clone)]
+struct FileSystem {
+    mount_point: String,
+    usage_percent: Option<f32>,
+    used_gb: Option<f32>,
+    total_gb: Option<f32>,
+    status: Status,
+}
+
 impl SystemWidget {
     pub fn new() -> Self {
         Self {
             nixos_build: None,
-            config_hash: None,
-            active_users: None,
             agent_hash: None,
+            network_interfaces: Vec::new(),
             cpu_load_1min: None,
             cpu_load_5min: None,
             cpu_load_15min: None,
@@ -80,7 +105,18 @@ impl SystemWidget {
             tmp_used_gb: None,
             tmp_total_gb: None,
             memory_status: Status::Unknown,
+            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,
         }
     }
@@ -113,203 +149,355 @@ impl SystemWidget {
         }
     }
 
-    /// Format /tmp usage
-    fn format_tmp_usage(&self) -> String {
-        match (self.tmp_usage_percent, self.tmp_used_gb, self.tmp_total_gb) {
-            (Some(pct), Some(used), Some(total)) => {
-                let used_str = if used < 0.1 {
-                    format!("{:.0}B", used * 1024.0) // Show as MB if very small
-                } else {
-                    format!("{:.1}GB", used)
-                };
-                format!("{:.0}% {}/{:.1}GB", pct, used_str, total)
-            }
-            _ => "—% —GB/—GB".to_string(),
-        }
-    }
 
     /// Get the current agent hash for rebuild completion detection
-    pub fn get_agent_hash(&self) -> Option<&String> {
+    pub fn _get_agent_hash(&self) -> Option<&String> {
         self.agent_hash.as_ref()
     }
+}
 
-    /// Get mount point for a pool name
+use super::Widget;
-    fn get_mount_point_for_pool(&self, pool_name: &str) -> String {
+
-        match pool_name {
+impl Widget for SystemWidget {
-            "root" => "/".to_string(),
+    fn update_from_agent_data(&mut self, agent_data: &cm_dashboard_shared::AgentData) {
-            "steampool" => "/mnt/steampool".to_string(),
+        self.has_data = true;
-            "steampool_1" => "/steampool_1".to_string(),
+
-            "steampool_2" => "/steampool_2".to_string(),
+        // Extract agent version
-            _ => format!("/{}", pool_name), // Default fallback
+        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_status = Status::Ok;
+
+        // Extract memory data directly
+        let memory = &agent_data.system.memory;
+        self.memory_usage_percent = Some(memory.usage_percent);
+        self.memory_used_gb = Some(memory.used_gb);
+        self.memory_total_gb = Some(memory.total_gb);
+        self.memory_status = Status::Ok;
+
+        // Store all tmpfs mounts for display
+        self.tmpfs_mounts = memory.tmpfs.clone();
+        
+        // Extract tmpfs data (maintain backward compatibility for /tmp)
+        if let Some(tmp_data) = memory.tmpfs.iter().find(|t| t.mount == "/tmp") {
+            self.tmp_usage_percent = Some(tmp_data.usage_percent);
+            self.tmp_used_gb = Some(tmp_data.used_gb);
+            self.tmp_total_gb = Some(tmp_data.total_gb);
+            self.tmp_status = Status::Ok;
+        }
+
+        // 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;
         }
     }
+}
 
-    /// Parse storage metrics into pools and drives
+impl SystemWidget {
-    fn update_storage_from_metrics(&mut self, metrics: &[&Metric]) {
+    /// Convert structured storage data to internal format
+    fn update_storage_from_agent_data(&mut self, agent_data: &cm_dashboard_shared::AgentData) {
         let mut pools: std::collections::HashMap<String, StoragePool> = std::collections::HashMap::new();
         
-        for metric in metrics {
+        // Convert drives
-            if metric.name.starts_with("disk_") {
+        for drive in &agent_data.system.storage.drives {
-                if let Some(pool_name) = self.extract_pool_name(&metric.name) {
+            let mut pool = StoragePool {
-                    let mount_point = self.get_mount_point_for_pool(&pool_name);
+                name: drive.name.clone(),
-                    let pool = pools.entry(pool_name.clone()).or_insert_with(|| StoragePool {
+                mount_point: drive.name.clone(),
-                        name: pool_name.clone(),
+                pool_type: "drive".to_string(),
-                        mount_point: mount_point.clone(),
+                drives: Vec::new(),
-                        pool_type: "Single".to_string(), // Default, could be enhanced
+                data_drives: Vec::new(),
-                        drives: Vec::new(),
+                parity_drives: Vec::new(),
-                        usage_percent: None,
+                filesystems: Vec::new(),
-                        used_gb: None,
+                usage_percent: None,
-                        total_gb: None,
+                used_gb: None,
-                        status: Status::Unknown,
+                total_gb: None,
-                    });
+                status: Status::Ok,
+            };
 
-                    // Parse different metric types
+            // Add drive info
-                    if metric.name.contains("_usage_percent") {
+            let display_name = drive.serial_number.as_ref()
-                        if let MetricValue::Float(usage) = metric.value {
+                .map(|s| truncate_serial(s))
-                            pool.usage_percent = Some(usage);
+                .unwrap_or(drive.name.clone());
-                            pool.status = metric.status.clone();
+            let storage_drive = StorageDrive {
-                        }
+                name: display_name,
-                    } else if metric.name.contains("_used_gb") {
+                temperature: drive.temperature_celsius,
-                        if let MetricValue::Float(used) = metric.value {
+                wear_percent: drive.wear_percent,
-                            pool.used_gb = Some(used);
+                status: Status::Ok,
-                        }
+            };
-                    } else if metric.name.contains("_total_gb") {
+            pool.drives.push(storage_drive);
-                        if let MetricValue::Float(total) = metric.value {
+
-                            pool.total_gb = Some(total);
+            // Calculate totals from filesystems
-                        }
+            let total_used: f32 = drive.filesystems.iter().map(|fs| fs.used_gb).sum();
-                    } else if metric.name.contains("_temperature") {
+            let total_size: f32 = drive.filesystems.iter().map(|fs| fs.total_gb).sum();
-                        if let Some(drive_name) = self.extract_drive_name(&metric.name) {
+            let average_usage = if total_size > 0.0 { (total_used / total_size) * 100.0 } else { 0.0 };
-                            // Find existing drive or create new one
+
-                            let drive_exists = pool.drives.iter().any(|d| d.name == drive_name);
+            pool.usage_percent = Some(average_usage);
-                            if !drive_exists {
+            pool.used_gb = Some(total_used);
-                                pool.drives.push(StorageDrive {
+            pool.total_gb = Some(total_size);
-                                    name: drive_name.clone(),
+
-                                    temperature: None,
+            // Add filesystems
-                                    wear_percent: None,
+            for fs in &drive.filesystems {
-                                    status: Status::Unknown,
+                let filesystem = FileSystem {
-                                });
+                    mount_point: fs.mount.clone(),
-                            }
+                    usage_percent: Some(fs.usage_percent),
-                            
+                    used_gb: Some(fs.used_gb),
-                            if let Some(drive) = pool.drives.iter_mut().find(|d| d.name == drive_name) {
+                    total_gb: Some(fs.total_gb),
-                                if let MetricValue::Float(temp) = metric.value {
+                    status: Status::Ok,
-                                    drive.temperature = Some(temp);
+                };
-                                    drive.status = metric.status.clone();
+                pool.filesystems.push(filesystem);
-                                }
-                            }
-                        }
-                    } else if metric.name.contains("_wear_percent") {
-                        if let Some(drive_name) = self.extract_drive_name(&metric.name) {
-                            // Find existing drive or create new one
-                            let drive_exists = pool.drives.iter().any(|d| d.name == drive_name);
-                            if !drive_exists {
-                                pool.drives.push(StorageDrive {
-                                    name: drive_name.clone(),
-                                    temperature: None,
-                                    wear_percent: None,
-                                    status: Status::Unknown,
-                                });
-                            }
-                            
-                            if let Some(drive) = pool.drives.iter_mut().find(|d| d.name == drive_name) {
-                                if let MetricValue::Float(wear) = metric.value {
-                                    drive.wear_percent = Some(wear);
-                                    drive.status = metric.status.clone();
-                                }
-                            }
-                        }
-                    }
-                }
             }
+
+            pools.insert(drive.name.clone(), pool);
         }
 
-        // Convert to sorted vec for consistent ordering
+        // 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();
-        pool_list.sort_by(|a, b| a.name.cmp(&b.name)); // Sort alphabetically by name
+        pool_list.sort_by(|a, b| a.name.cmp(&b.name));
         self.storage_pools = pool_list;
     }
 
-    /// Extract pool name from disk metric name
+    /// Render storage section with enhanced tree structure
-    fn extract_pool_name(&self, metric_name: &str) -> Option<String> {
+    fn render_storage(&self) -> Vec<Line<'_>> {
-        if let Some(captures) = metric_name.strip_prefix("disk_") {
-            if let Some(pos) = captures.find('_') {
-                return Some(captures[..pos].to_string());
-            }
-        }
-        None
-    }
-
-    /// Extract drive name from disk metric name  
-    fn extract_drive_name(&self, metric_name: &str) -> Option<String> {
-        // Pattern: disk_pool_drive_metric
-        let parts: Vec<&str> = metric_name.split('_').collect();
-        if parts.len() >= 3 && parts[0] == "disk" {
-            return Some(parts[2].to_string());
-        }
-        None
-    }
-
-    /// Render storage section with tree structure
-    fn render_storage(&self) -> Vec<Line> {
         let mut lines = Vec::new();
 
         for pool in &self.storage_pools {
-            // Pool header line
+            // Pool header line with type and health
-            let usage_text = match (pool.usage_percent, pool.used_gb, pool.total_gb) {
+            let pool_label = if pool.pool_type == "drive" {
-                (Some(pct), Some(used), Some(total)) => {
+                // For physical drives, show the drive name with temperature and wear percentage if available
-                    format!("{:.0}% {:.1}GB/{:.1}GB", pct, used, total)
+                // 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));
+                    }
+                    if let Some(wear) = drive.wear_percent {
+                        drive_details.push(format!("W: {}%", wear as i32));
+                    }
+
+                    if !drive_details.is_empty() {
+                        format!("{} {}", drive.name, drive_details.join(" "))
+                    } else {
+                        drive.name.clone()
+                    }
+                } else {
+                    pool.name.clone()
                 }
-                _ => "—% —GB/—GB".to_string(),
-            };
-            
-            let pool_label = if pool.pool_type.to_lowercase() == "single" {
-                format!("{}:", pool.mount_point)
             } else {
-                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(),
+            let pool_spans = StatusIcons::create_status_spans(pool.status.clone(), &pool_label);
-                &pool_label
-            );
             lines.push(Line::from(pool_spans));
 
-            // Drive lines with tree structure
+            // Show individual filesystems for physical drives (matching CLAUDE.md format)
-            let has_usage_line = pool.usage_percent.is_some();
+            if pool.pool_type == "drive" {
-            for (i, drive) in pool.drives.iter().enumerate() {
+                // Show filesystem entries like: ├─ ● /: 55% 250.5GB/456.4GB
-                let is_last_drive = i == pool.drives.len() - 1;
+                for (i, filesystem) in pool.filesystems.iter().enumerate() {
-                let tree_symbol = if is_last_drive && !has_usage_line { "└─" } else { "├─" };
+                    let is_last = i == pool.filesystems.len() - 1;
+                    let tree_symbol = if is_last { "  └─ " } else { "  ├─ " };
+                    
+                    let fs_text = format!("{}: {:.0}% {:.1}GB/{:.1}GB", 
+                        filesystem.mount_point, 
+                        filesystem.usage_percent.unwrap_or(0.0), 
+                        filesystem.used_gb.unwrap_or(0.0), 
+                        filesystem.total_gb.unwrap_or(0.0));
+                    
+                    let mut fs_spans = vec![
+                        Span::styled(tree_symbol, Typography::tree()),
+                    ];
+                    fs_spans.extend(StatusIcons::create_status_spans(
+                        filesystem.status.clone(), 
+                        &fs_text
+                    ));
+                    lines.push(Line::from(fs_spans));
+                }
+            } else {
+                // 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
                 
-                let mut drive_info = Vec::new();
+                // Pool total usage
-                if let Some(temp) = drive.temperature {
+                let total_text = format!("{:.0}% {:.1}GB/{:.1}GB",
-                    drive_info.push(format!("T: {:.0}C", temp));
+                    pool.usage_percent.unwrap_or(0.0),
-                }
+                    pool.used_gb.unwrap_or(0.0),
-                if let Some(wear) = drive.wear_percent {
+                    pool.total_gb.unwrap_or(0.0)
-                    drive_info.push(format!("W: {:.0}%", wear));
+                );
-                }
+                let mut total_spans = vec![
-                let drive_text = if drive_info.is_empty() {
+                    Span::styled("  ├─ ", Typography::tree()),
-                    drive.name.clone()
-                } else {
-                    format!("{} {}", drive.name, drive_info.join(" • "))
-                };
-
-                let mut drive_spans = vec![
-                    Span::raw("  "),
-                    Span::styled(tree_symbol, Typography::tree()),
-                    Span::raw(" "),
                 ];
-                drive_spans.extend(StatusIcons::create_status_spans(drive.status.clone(), &drive_text));
+                total_spans.extend(StatusIcons::create_status_spans(Status::Ok, &total_text));
-                lines.push(Line::from(drive_spans));
+                lines.push(Line::from(total_spans));
-            }
 
-            // Usage line
+                // Data drives - at same level as parity
-            if pool.usage_percent.is_some() {
+                let has_parity = !pool.parity_drives.is_empty();
-                let tree_symbol = "└─";
+                for (i, drive) in pool.data_drives.iter().enumerate() {
-                let mut usage_spans = vec![
+                    let is_last_data = i == pool.data_drives.len() - 1;
-                    Span::raw("  "),
+                    let mut drive_details = Vec::new();
-                    Span::styled(tree_symbol, Typography::tree()),
+                    if let Some(temp) = drive.temperature {
-                    Span::raw(" "),
+                        drive_details.push(format!("T: {}°C", temp as i32));
-                ];
+                    }
-                usage_spans.extend(StatusIcons::create_status_spans(pool.status.clone(), &usage_text));
+                    if let Some(wear) = drive.wear_percent {
-                lines.push(Line::from(usage_spans));
+                        drive_details.push(format!("W: {}%", wear as i32));
+                    }
+
+                    let drive_text = if !drive_details.is_empty() {
+                        format!("Data_{}: {} {}", i + 1, drive.name, drive_details.join(" "))
+                    } else {
+                        format!("Data_{}: {}", i + 1, drive.name)
+                    };
+
+                    // 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()),
+                    ];
+                    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));
+                    }
+                }
             }
         }
 
@@ -317,146 +505,289 @@ impl SystemWidget {
     }
 }
 
-impl Widget for SystemWidget {
+/// Truncate serial number to last 8 characters
-    fn update_from_metrics(&mut self, metrics: &[&Metric]) {
+fn truncate_serial(serial: &str) -> String {
-        self.has_data = !metrics.is_empty();
+    let len = serial.len();
-
+    if len > 8 {
-        for metric in metrics {
+        serial[len - 8..].to_string()
-            match metric.name.as_str() {
+    } else {
-                // NixOS metrics
+        serial.to_string()
-                "system_nixos_build" => {
-                    if let MetricValue::String(build) = &metric.value {
-                        self.nixos_build = Some(build.clone());
-                    }
-                }
-                "system_config_hash" => {
-                    if let MetricValue::String(hash) = &metric.value {
-                        self.config_hash = Some(hash.clone());
-                    }
-                }
-                "system_active_users" => {
-                    if let MetricValue::String(users) = &metric.value {
-                        self.active_users = Some(users.clone());
-                    }
-                }
-                "system_agent_hash" => {
-                    if let MetricValue::String(hash) = &metric.value {
-                        self.agent_hash = Some(hash.clone());
-                    }
-                }
-                
-                // CPU metrics
-                "cpu_load_1min" => {
-                    if let MetricValue::Float(load) = metric.value {
-                        self.cpu_load_1min = Some(load);
-                        self.cpu_status = metric.status.clone();
-                    }
-                }
-                "cpu_load_5min" => {
-                    if let MetricValue::Float(load) = metric.value {
-                        self.cpu_load_5min = Some(load);
-                    }
-                }
-                "cpu_load_15min" => {
-                    if let MetricValue::Float(load) = metric.value {
-                        self.cpu_load_15min = Some(load);
-                    }
-                }
-                "cpu_frequency_mhz" => {
-                    if let MetricValue::Float(freq) = metric.value {
-                        self.cpu_frequency = Some(freq);
-                    }
-                }
-                
-                // Memory metrics
-                "memory_usage_percent" => {
-                    if let MetricValue::Float(usage) = metric.value {
-                        self.memory_usage_percent = Some(usage);
-                        self.memory_status = metric.status.clone();
-                    }
-                }
-                "memory_used_gb" => {
-                    if let MetricValue::Float(used) = metric.value {
-                        self.memory_used_gb = Some(used);
-                    }
-                }
-                "memory_total_gb" => {
-                    if let MetricValue::Float(total) = metric.value {
-                        self.memory_total_gb = Some(total);
-                    }
-                }
-                
-                // Tmpfs metrics
-                "memory_tmp_usage_percent" => {
-                    if let MetricValue::Float(usage) = metric.value {
-                        self.tmp_usage_percent = Some(usage);
-                    }
-                }
-                "memory_tmp_used_gb" => {
-                    if let MetricValue::Float(used) = metric.value {
-                        self.tmp_used_gb = Some(used);
-                    }
-                }
-                "memory_tmp_total_gb" => {
-                    if let MetricValue::Float(total) = metric.value {
-                        self.tmp_total_gb = Some(total);
-                    }
-                }
-                _ => {}
-            }
-        }
-
-        // Update storage from all disk metrics
-        self.update_storage_from_metrics(metrics);
-    }
-
-    fn render(&mut self, frame: &mut Frame, area: Rect) {
-        self.render_with_scroll(frame, area, 0);
     }
 }
 
 impl SystemWidget {
-    /// Render with scroll offset support
+    /// Render backup section for display
-    pub fn render_with_scroll(&mut self, frame: &mut Frame, area: Rect, scroll_offset: usize) {
+    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 standalone_virtual: Vec<_> = virtual_interfaces.iter()
+            .filter(|i| i.parent_interface.is_none())
+            .collect();
+
+        // 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 children: Vec<_> = virtual_interfaces.iter()
+                .filter(|vi| {
+                    if let Some(parent) = &vi.parent_interface {
+                        parent == &interface.name
+                    } else {
+                        false
+                    }
+                })
+                .collect();
+
+            // 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>) {
         let mut lines = Vec::new();
 
         // NixOS section
         lines.push(Line::from(vec![
-            Span::styled("NixOS:", Typography::widget_title())
+            Span::styled(format!("NixOS {}:", hostname), Typography::widget_title())
         ]));
         
         let build_text = self.nixos_build.as_deref().unwrap_or("unknown");
         lines.push(Line::from(vec![
             Span::styled(format!("Build: {}", build_text), Typography::secondary())
         ]));
-
+        
-        let config_text = self.config_hash.as_deref().unwrap_or("unknown");
+        let agent_version_text = self.agent_hash.as_deref().unwrap_or("unknown");
         lines.push(Line::from(vec![
-            Span::styled(format!("Config: {}", config_text), Typography::secondary())
+            Span::styled(format!("Agent: {}", agent_version_text), Typography::secondary())
-        ]));
-
-        let agent_hash_text = self.agent_hash.as_deref().unwrap_or("unknown");
-        let short_hash = if agent_hash_text.len() > 8 && agent_hash_text != "unknown" {
-            &agent_hash_text[..8]
-        } else {
-            agent_hash_text
-        };
-        lines.push(Line::from(vec![
-            Span::styled(format!("Agent: {}", short_hash), Typography::secondary())
         ]));
 
         // CPU section
         lines.push(Line::from(vec![
             Span::styled("CPU:", Typography::widget_title())
         ]));
-        
+
         let load_text = self.format_cpu_load();
         let cpu_spans = StatusIcons::create_status_spans(
             self.cpu_status.clone(),
             &format!("Load: {}", load_text)
         );
         lines.push(Line::from(cpu_spans));
-        
+
         let freq_text = self.format_cpu_frequency();
         lines.push(Line::from(vec![
             Span::styled("  └─ ", Typography::tree()),
@@ -467,7 +798,7 @@ impl SystemWidget {
         lines.push(Line::from(vec![
             Span::styled("RAM:", Typography::widget_title())
         ]));
-        
+
         let memory_text = self.format_memory_usage();
         let memory_spans = StatusIcons::create_status_spans(
             self.memory_status.clone(),
@@ -475,84 +806,79 @@ impl SystemWidget {
         );
         lines.push(Line::from(memory_spans));
 
-        let tmp_text = self.format_tmp_usage();
+        // Display all tmpfs mounts
-        let mut tmp_spans = vec![
+        for (i, tmpfs) in self.tmpfs_mounts.iter().enumerate() {
-            Span::styled("  └─ ", Typography::tree()),
+            let is_last = i == self.tmpfs_mounts.len() - 1;
-        ];
+            let tree_symbol = if is_last { "  └─ " } else { "  ├─ " };
-        tmp_spans.extend(StatusIcons::create_status_spans(
+
-            self.memory_status.clone(),
+            let usage_text = if tmpfs.total_gb > 0.0 {
-            &format!("/tmp: {}", tmp_text)
+                format!("{:.0}% {:.1}GB/{:.1}GB",
-        ));
+                    tmpfs.usage_percent,
-        lines.push(Line::from(tmp_spans));
+                    tmpfs.used_gb,
+                    tmpfs.total_gb)
+            } else {
+                "— —/—".to_string()
+            };
+
+            let mut tmpfs_spans = vec![
+                Span::styled(tree_symbol, Typography::tree()),
+            ];
+            tmpfs_spans.extend(StatusIcons::create_status_spans(
+                Status::Ok, // TODO: Calculate status based on usage_percent
+                &format!("{}: {}", tmpfs.mount, usage_text)
+            ));
+            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())
         ]));
         
-        // Storage items with overflow handling
+        // Storage items - let main overflow logic handle truncation
         let storage_lines = self.render_storage();
-        let remaining_space = area.height.saturating_sub(lines.len() as u16);
+        lines.extend(storage_lines);
-        
+
-        if storage_lines.len() <= remaining_space as usize {
+        // Backup section (if available)
-            // All storage lines fit
+        if self.backup_status != "unavailable" && self.backup_status != "unknown" {
-            lines.extend(storage_lines);
+            lines.push(Line::from(vec![
-        } else if remaining_space >= 2 {
+                Span::styled("Backup:", Typography::widget_title())
-            // Show what we can and add overflow indicator
+            ]));
-            let lines_to_show = (remaining_space - 1) as usize; // Reserve 1 line for overflow
+
-            lines.extend(storage_lines.iter().take(lines_to_show).cloned());
+            let backup_lines = self.render_backup();
-            
+            lines.extend(backup_lines);
-            // Count hidden pools
-            let mut hidden_pools = 0;
-            let mut current_pool = String::new();
-            for (i, line) in storage_lines.iter().enumerate() {
-                if i >= lines_to_show {
-                    // Check if this line represents a new pool (no indentation)
-                    if let Some(first_span) = line.spans.first() {
-                        let text = first_span.content.as_ref();
-                        if !text.starts_with("  ") && text.contains(':') {
-                            let pool_name = text.split(':').next().unwrap_or("").trim();
-                            if pool_name != current_pool {
-                                hidden_pools += 1;
-                                current_pool = pool_name.to_string();
-                            }
-                        }
-                    }
-                }
-            }
-            
-            if hidden_pools > 0 {
-                let overflow_text = format!(
-                    "... and {} more pool{}",
-                    hidden_pools,
-                    if hidden_pools == 1 { "" } else { "s" }
-                );
-                lines.push(Line::from(vec![
-                    Span::styled(overflow_text, Typography::muted())
-                ]));
-            }
         }
 
         // Apply scroll offset
         let total_lines = lines.len();
         let available_height = area.height as usize;
         
-        // Always apply scrolling if scroll_offset > 0, even if content fits
+        // Show only what fits, with "X more below" if needed
-        if scroll_offset > 0 || total_lines > available_height {
+        if total_lines > available_height {
-            let max_scroll = if total_lines > available_height {
+            let lines_for_content = available_height.saturating_sub(1); // Reserve one line for "more below"
-                total_lines - available_height
+            let mut visible_lines: Vec<Line> = lines
-            } else {
-                total_lines.saturating_sub(1)
-            };
-            let effective_scroll = scroll_offset.min(max_scroll);
-            
-            // Take only the visible portion after scrolling
-            let visible_lines: Vec<Line> = lines
                 .into_iter()
-                .skip(effective_scroll)
+                .take(lines_for_content)
-                .take(available_height)
                 .collect();
-                
+            
+            let hidden_below = total_lines.saturating_sub(lines_for_content);
+            if hidden_below > 0 {
+                let more_line = Line::from(vec![
+                    Span::styled(format!("... {} more below", hidden_below), Typography::muted())
+                ]);
+                visible_lines.push(more_line);
+            }
+            
             let paragraph = Paragraph::new(Text::from(visible_lines));
             frame.render_widget(paragraph, area);
         } else {

shared/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "cm-dashboard-shared"
-version = "0.1.0"
+version = "0.1.170"
 edition = "2021"
 
 [dependencies]

shared/src/agent_data.rs

@@ -0,0 +1,231 @@
+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>,
+    pub backup: BackupData,
+}
+
+/// 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 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 temperature_celsius: Option<f32>,
+    pub load_status: Status,
+    pub temperature_status: Status,
+}
+
+/// Memory monitoring data
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct MemoryData {
+    pub usage_percent: f32,
+    pub total_gb: f32,
+    pub used_gb: f32,
+    pub available_gb: f32,
+    pub swap_total_gb: f32,
+    pub swap_used_gb: f32,
+    pub tmpfs: Vec<TmpfsData>,
+    pub usage_status: Status,
+}
+
+/// Tmpfs filesystem data
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct TmpfsData {
+    pub mount: String,
+    pub usage_percent: f32,
+    pub used_gb: f32,
+    pub total_gb: f32,
+}
+
+/// Storage monitoring data
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct StorageData {
+    pub drives: Vec<DriveData>,
+    pub pools: Vec<PoolData>,
+}
+
+/// Individual drive data
+#[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
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct FilesystemData {
+    pub mount: String,
+    pub usage_percent: f32,
+    pub used_gb: f32,
+    pub total_gb: f32,
+    pub usage_status: Status,
+}
+
+/// Storage pool (MergerFS, RAID, etc.)
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct PoolData {
+    pub name: String,
+    pub mount: String,
+    pub pool_type: String, // "mergerfs", "raid", etc.
+    pub health: String,
+    pub usage_percent: f32,
+    pub used_gb: f32,
+    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 memory_mb: f32,
+    pub disk_gb: f32,
+    pub user_stopped: bool,
+    pub service_status: Status,
+    pub sub_services: Vec<SubServiceData>,
+}
+
+/// 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>,
+}
+
+/// 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 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 {
+    /// Create new agent data with current timestamp
+    pub fn new(hostname: String, agent_version: String) -> Self {
+        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,
+                    temperature_celsius: None,
+                    load_status: Status::Unknown,
+                    temperature_status: Status::Unknown,
+                },
+                memory: MemoryData {
+                    usage_percent: 0.0,
+                    total_gb: 0.0,
+                    used_gb: 0.0,
+                    available_gb: 0.0,
+                    swap_total_gb: 0.0,
+                    swap_used_gb: 0.0,
+                    tmpfs: Vec::new(),
+                    usage_status: Status::Unknown,
+                },
+                storage: StorageData {
+                    drives: Vec::new(),
+                    pools: Vec::new(),
+                },
+            },
+            services: Vec::new(),
+            backup: BackupData {
+                status: "unknown".to_string(),
+                total_size_gb: None,
+                repository_health: None,
+                repository_disk: None,
+                last_backup_size_gb: None,
+                start_time_raw: None,
+            },
+        }
+    }
+}

shared/src/lib.rs

@@ -1,8 +1,10 @@
+pub mod agent_data;
 pub mod cache;
 pub mod error;
 pub mod metrics;
 pub mod protocol;
 
+pub use agent_data::*;
 pub use cache::*;
 pub use error::*;
 pub use metrics::*;

shared/src/metrics.rs

@@ -82,11 +82,13 @@ impl MetricValue {
 /// Health status for metrics
 #[derive(Debug, Clone, Copy, Serialize, Deserialize, PartialEq, Eq, PartialOrd, Ord)]
 pub enum Status {
-    Ok,
+    Inactive, // Lowest priority
-    Pending,
+    Unknown,  // 
-    Warning,
+    Offline,  // 
-    Critical,
+    Pending,  // 
-    Unknown,
+    Ok,       // 5th place - good status has higher priority than unknown states
+    Warning,  // 
+    Critical, // Highest priority
 }
 
 impl Status {
@@ -129,6 +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,
@@ -180,6 +193,16 @@ impl HysteresisThresholds {
                     Status::Ok
                 }
             }
+            Status::Inactive => {
+                // Inactive services use normal thresholds like first measurement
+                if value >= self.critical_high {
+                    Status::Critical
+                } else if value >= self.warning_high {
+                    Status::Warning
+                } else {
+                    Status::Ok
+                }
+            }
             Status::Pending => {
                 // Service transitioning, use normal thresholds like first measurement
                 if value >= self.critical_high {
@@ -190,6 +213,16 @@ impl HysteresisThresholds {
                     Status::Ok
                 }
             }
+            Status::Offline => {
+                // Host coming back online, use normal thresholds like first measurement
+                if value >= self.critical_high {
+                    Status::Critical
+                } else if value >= self.warning_high {
+                    Status::Warning
+                } else {
+                    Status::Ok
+                }
+            }
         }
     }
 }

shared/src/protocol.rs

@@ -1,20 +1,31 @@
-use crate::metrics::Metric;
+use crate::agent_data::AgentData;
 use serde::{Deserialize, Serialize};
 
-/// Message sent from agent to dashboard via ZMQ
+/// Message sent from agent to dashboard via ZMQ  
+/// Always structured data - no legacy metrics support
+pub type AgentMessage = AgentData;
+
+/// Command output streaming message
 #[derive(Debug, Clone, Serialize, Deserialize)]
-pub struct MetricMessage {
+pub struct CommandOutputMessage {
     pub hostname: String,
+    pub command_id: String,
+    pub command_type: String,
+    pub output_line: String,
+    pub is_complete: bool,
     pub timestamp: u64,
-    pub metrics: Vec<Metric>,
 }
 
-impl MetricMessage {
+
-    pub fn new(hostname: String, metrics: Vec<Metric>) -> Self {
+impl CommandOutputMessage {
+    pub fn new(hostname: String, command_id: String, command_type: String, output_line: String, is_complete: bool) -> Self {
         Self {
             hostname,
+            command_id,
+            command_type,
+            output_line,
+            is_complete,
             timestamp: chrono::Utc::now().timestamp() as u64,
-            metrics,
         }
     }
 }
@@ -35,8 +46,8 @@ pub enum Command {
 pub enum CommandResponse {
     /// Acknowledgment of command
     Ack,
-    /// Metrics response
+    /// Agent data response
-    Metrics(Vec<Metric>),
+    AgentData(AgentData),
     /// Pong response to ping
     Pong,
     /// Error response
@@ -52,17 +63,18 @@ pub struct MessageEnvelope {
 
 #[derive(Debug, Serialize, Deserialize)]
 pub enum MessageType {
-    Metrics,
+    AgentData,
     Command,
     CommandResponse,
+    CommandOutput,
     Heartbeat,
 }
 
 impl MessageEnvelope {
-    pub fn metrics(message: MetricMessage) -> Result<Self, crate::SharedError> {
+    pub fn agent_data(data: AgentData) -> Result<Self, crate::SharedError> {
         Ok(Self {
-            message_type: MessageType::Metrics,
+            message_type: MessageType::AgentData,
-            payload: serde_json::to_vec(&message)?,
+            payload: serde_json::to_vec(&data)?,
         })
     }
 
@@ -80,6 +92,13 @@ impl MessageEnvelope {
         })
     }
 
+    pub fn command_output(message: CommandOutputMessage) -> Result<Self, crate::SharedError> {
+        Ok(Self {
+            message_type: MessageType::CommandOutput,
+            payload: serde_json::to_vec(&message)?,
+        })
+    }
+
     pub fn heartbeat() -> Result<Self, crate::SharedError> {
         Ok(Self {
             message_type: MessageType::Heartbeat,
@@ -87,11 +106,11 @@ impl MessageEnvelope {
         })
     }
 
-    pub fn decode_metrics(&self) -> Result<MetricMessage, crate::SharedError> {
+    pub fn decode_agent_data(&self) -> Result<AgentData, crate::SharedError> {
         match self.message_type {
-            MessageType::Metrics => Ok(serde_json::from_slice(&self.payload)?),
+            MessageType::AgentData => Ok(serde_json::from_slice(&self.payload)?),
             _ => Err(crate::SharedError::Protocol {
-                message: "Expected metrics message".to_string(),
+                message: "Expected agent data message".to_string(),
             }),
         }
     }
@@ -113,4 +132,13 @@ impl MessageEnvelope {
             }),
         }
     }
+
+    pub fn decode_command_output(&self) -> Result<CommandOutputMessage, crate::SharedError> {
+        match self.message_type {
+            MessageType::CommandOutput => Ok(serde_json::from_slice(&self.payload)?),
+            _ => Err(crate::SharedError::Protocol {
+                message: "Expected command output message".to_string(),
+            }),
+        }
+    }
 }