fixed stuck in loop

.gitea/workflows/build.yml

@@ -3,17 +3,12 @@ name: Rust Cross-Platform Build
 on:
   workflow_dispatch:
   push:
-    branches: [ "development", "main", "feature/*", "bugfix/*", "enhancement/*" ]
+    branches: [ "development", "main", "staging" ]
     tags: [ "v*.*.*" ]
-  pull_request:
-    branches: [ "development", "main" ]
 
 env:
-  CARGO_TERM_COLOR: always
-  RUST_BACKTRACE: 1
   REGISTRY: git.triggermeelmo.com
   IMAGE_NAME: donpat1to/watcher-agent
-  TAG: ${{ github.ref == 'refs/heads/main' && 'latest' || github.ref == 'refs/heads/development' && 'development' || github.ref_type == 'tag' && github.ref_name || 'pr' }}
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}
@@ -54,24 +49,9 @@ jobs:
             exit 1
           fi
 
-  setup-rust:
-    name: Setup Rust Toolchain
-    needs: detect-project
-    if: ${{ !failure() && !cancelled() }}
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-      
-      - name: Install Rust
-        uses: dtolnay/rust-toolchain@stable
-        with:
-          toolchain: stable
-          targets: x86_64-unknown-linux-gnu, x86_64-pc-windows-gnu
-          components: rustfmt, clippy
-
   test:
     name: Run Tests
-    needs: [detect-project, setup-rust]
+    needs: [detect-project]
     if: ${{ !failure() && !cancelled() }}
     runs-on: ubuntu-latest
     steps:
@@ -94,47 +74,9 @@ jobs:
       #  working-directory: ${{ needs.detect-project.outputs.project-dir }}
       #  run: cargo clippy -- -D warnings
 
-  set-tag:
-    name: Set Tag Name
-    runs-on: ubuntu-latest
-    outputs:
-      tag_name: ${{ steps.set_tag.outputs.tag_name }}
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: Determine next semantic version tag
-        id: set_tag
-        run: |
-          git fetch --tags
-
-          # Find latest tag matching vX.Y.Z
-          latest_tag=$(git tag --list 'v*.*.*' --sort=-v:refname | head -n 1)
-          if [[ -z "$latest_tag" ]]; then
-            major=0
-            minor=0
-            patch=0
-          else
-            version="${latest_tag#v}"
-            IFS='.' read -r major minor patch <<< "$version"
-          fi
-
-          if [[ "${GITHUB_REF}" == "refs/heads/main" ]]; then
-            major=$((major + 1))
-            minor=0
-            patch=0
-          elif [[ "${GITHUB_REF}" == "refs/heads/development" ]]; then
-            minor=$((minor + 1))
-            patch=0
-          else
-            patch=$((patch + 1))
-          fi
-
-          new_tag="v${major}.${minor}.${patch}"
-          echo "tag_name=${new_tag}" >> $GITHUB_OUTPUT
-
 #  audit:
 #    name: Security Audit
-#    needs: [detect-project, setup-rust]
+#    needs: [detect-project]
 #    if: ${{ !failure() && !cancelled() }}
 #    runs-on: ubuntu-latest
 #    steps:
@@ -154,7 +96,7 @@ jobs:
 
   build:
     name: Build (${{ matrix.target }})
-    needs: [detect-project, setup-rust, test, audit]
+    needs: [detect-project, test]
     if: ${{ !failure() && !cancelled() }}
     runs-on: ubuntu-latest
     strategy:
@@ -207,13 +149,65 @@ jobs:
           path: |
             ${{ needs.detect-project.outputs.project-dir }}/target/${{ matrix.target }}/release/${{ needs.detect-project.outputs.project-name }}${{ matrix.os == 'windows' && '.exe' || '' }}
 
+  set-tag:
+    name: Set Tag Name
+    needs: [detect-project, build]
+    #if: ${{ !failure() && !cancelled() && github.event_name != 'pull_request' }}
+    runs-on: ubuntu-latest
+    outputs:
+      tag_name: ${{ steps.set_tag.outputs.tag_name }}
+      should_tag: ${{ steps.set_tag.outputs.should_tag }}
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Determine next semantic version tag
+        id: set_tag
+        run: |
+          git fetch --tags
+
+          # Find latest tag matching vX.Y.Z
+          latest_tag=$(git tag --list 'v*.*.*' --sort=-v:refname | head -n 1)
+          if [[ -z "$latest_tag" ]]; then
+            major=0
+            minor=0
+            patch=0
+          else
+            version="${latest_tag#v}"
+            IFS='.' read -r major minor patch <<< "$version"
+          fi
+
+          if [[ "${GITHUB_REF}" == "refs/heads/main" ]]; then
+            major=$((major + 1))
+            minor=0
+            patch=0
+            new_tag="v${major}.${minor}.${patch}"
+            echo "tag_name=${new_tag}" >> $GITHUB_OUTPUT
+            echo "should_tag=true" >> $GITHUB_OUTPUT
+            echo "Creating new major version tag: ${new_tag}"
+            
+          elif [[ "${GITHUB_REF}" == "refs/heads/development" ]]; then
+            minor=$((minor + 1))
+            patch=0
+            new_tag="v${major}.${minor}.${patch}"
+            echo "tag_name=${new_tag}" >> $GITHUB_OUTPUT
+            echo "should_tag=true" >> $GITHUB_OUTPUT
+            echo "Creating new minor version tag: ${new_tag}"
+            
+          elif [[ "${GITHUB_REF}" == "refs/heads/staging" ]]; then
+            patch=$((patch + 1))
+            new_tag="v${major}.${minor}.${patch}"
+            echo "tag_name=${new_tag}" >> $GITHUB_OUTPUT
+            echo "should_tag=true" >> $GITHUB_OUTPUT
+            echo "Creating new patch version tag: ${new_tag}"
+          fi
+
   docker-build:
     name: Build and Push Docker Image
     needs: [detect-project, build, set-tag]
     if: | 
-      always() && 
       needs.detect-project.result == 'success' && 
       needs.build.result == 'success' &&
+      needs.set-tag.outputs.should_tag == 'true' &&
       github.event_name != 'pull_request'
     runs-on: ubuntu-latest
     environment: production
@@ -227,14 +221,14 @@ jobs:
           path: dist/
       
       - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v2
+        uses: docker/setup-buildx-action@v3
       
       - name: Login to Docker Registry
-        uses: docker/login-action@v2
+        uses: docker/login-action@v3
         with:
           registry: ${{ env.REGISTRY }}
-          username: ${{ secrets.DOCKER_USERNAME }}
-          password: ${{ secrets.DOCKER_PASSWORD }}
+          username: ${{ secrets.AUTOMATION_USERNAME }}
+          password: ${{ secrets.AUTOMATION_PASSWORD }}
 
       - name: Build Docker image
         uses: docker/build-push-action@v4
@@ -250,8 +244,7 @@ jobs:
 
   tag:
     name: Create Tag
-    needs: [build, set-tag]
-    if: github.event_name == 'push'
+    needs: [docker-build, build, set-tag]
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
@@ -267,13 +260,13 @@ jobs:
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
         run: |
+          echo "Creating new tag: ${{ needs.set-tag.outputs.tag_name }}"
           git tag ${{ needs.set-tag.outputs.tag_name }}
           git push origin ${{ needs.set-tag.outputs.tag_name }}
 
-
   summary:
     name: Workflow Summary
-    needs: [test, audit, build, docker-build]
+    needs: [test, build, docker-build]
     if: always()
     runs-on: ubuntu-latest
     steps:

WatcherAgent/Cargo.toml

@@ -19,9 +19,11 @@ nvml-wrapper = "0.11"
 nvml-wrapper-sys = "0.9.0"
 anyhow = "1.0.98"
 
-# Docker .env loading
-config = "0.13"
-dotenvy = "0.15"
+regex = "1.11.3"
+
+# Docker API access
+bollard = "0.19"
+futures-util = "0.3"
 
 [target.'cfg(windows)'.dependencies]
 winapi = { version = "0.3", features = ["winuser", "pdh", "ifmib", "iphlpapi", "winerror" ,"wbemcli", "combaseapi"] }

WatcherAgent/src/api.rs

@@ -1,15 +1,47 @@
+/// # API Module
+///
+/// This module provides all HTTP communication between WatcherAgent and the backend server.
+///
+/// ## Responsibilities
+/// - **Registration:** Registers the agent with the backend and retrieves its server ID and IP address.
+/// - **Heartbeat:** Periodically sends heartbeat signals to indicate liveness.
+/// - **Metrics Reporting:** Sends collected hardware and network metrics to the backend.
+/// - **Command Listening:** Polls for and executes remote commands from the backend (e.g., update image, restart container).
+///
+/// ## Usage
+/// These functions are called from the main agent loop and background tasks. All network operations are asynchronous and robust to transient failures.
 use std::time::Duration;
 
+use crate::docker::container;
+use crate::docker::serverclientcomm::handle_server_message;
 use crate::hardware::HardwareInfo;
-use crate::models::{HeartbeatDto, IdResponse, MetricDto, RegistrationDto};
+use crate::models::{
+    Acknowledgment, DockerMetricDto, DockerRegistrationDto, HeartbeatDto, IdResponse, MetricDto,
+    RegistrationDto, ServerMessage,
+};
+
 use anyhow::Result;
 use reqwest::{Client, StatusCode};
 use std::error::Error;
 use tokio::time::sleep;
 
+use bollard::Docker;
+
+/// Registers this agent with the backend server and retrieves its server ID and IP address.
+///
+/// This function collects local hardware information, prepares a registration payload, and sends it to the backend. It will retry registration until successful, handling network errors and server-side failures gracefully.
+///
+/// # Arguments
+/// * `base_url` - The base URL of the backend server (e.g., `https://server.example.com`).
+///
+/// # Returns
+/// * `Result<(i32, String), Box<dyn Error + Send + Sync>>` - Tuple of server ID and registered IP address on success.
+///
+/// # Errors
+/// Returns an error if unable to register after repeated attempts.
 pub async fn register_with_server(
     base_url: &str,
-) -> Result<(i32, String), Box<dyn Error + Send + Sync>> {
+) -> Result<(u16, String), Box<dyn Error + Send + Sync>> {
     // First get local IP
     let ip = local_ip_address::local_ip()?.to_string();
     println!("Local IP address detected: {}", ip);
@@ -27,18 +59,18 @@ pub async fn register_with_server(
 
     // Prepare registration data
     let registration = RegistrationDto {
-        id: server_id,
+        server_id: server_id,
         ip_address: registered_ip.clone(),
         cpu_type: hardware.cpu.name.clone().unwrap_or_default(),
         cpu_cores: (hardware.cpu.cores).unwrap_or_default(),
         gpu_type: hardware.gpu.name.clone().unwrap_or_default(),
-        ram_size: hardware.memory.total.unwrap_or_default(),
+        ram_size: hardware.memory.total_size.unwrap_or_default(),
     };
 
     // Try to register (will retry on failure)
     loop {
         println!("Attempting to register with server...");
-        let url = format!("{}/monitoring/register-agent-by-id", base_url);
+        let url = format!("{}/monitoring/hardware-info", base_url);
         match client.post(&url).json(&registration).send().await {
             Ok(resp) if resp.status().is_success() => {
                 println!("✅ Successfully registered with server.");
@@ -60,15 +92,25 @@ pub async fn register_with_server(
     }
 }
 
+/// Looks up the server ID for the given IP address from the backend server.
+///
+/// This function will retry until a valid response is received, handling network errors and server-side failures.
+///
+/// # Arguments
+/// * `base_url` - The base URL of the backend server.
+/// * `ip` - The local IP address to look up.
+///
+/// # Returns
+/// * `Result<(i32, String), Box<dyn Error + Send + Sync>>` - Tuple of server ID and registered IP address.
 async fn get_server_id_by_ip(
     base_url: &str,
     ip: &str,
-) -> Result<(i32, String), Box<dyn Error + Send + Sync>> {
+) -> Result<(u16, String), Box<dyn Error + Send + Sync>> {
     let client = Client::builder()
         .danger_accept_invalid_certs(true)
         .build()?;
 
-    let url = format!("{}/monitoring/server-id-by-ip?ipAddress={}", base_url, ip);
+    let url = format!("{}/monitoring/register?ipAddress={}", base_url, ip);
 
     loop {
         println!("Attempting to fetch server ID for IP {}...", ip);
@@ -111,6 +153,60 @@ async fn get_server_id_by_ip(
     }
 }
 
+pub async fn broadcast_docker_containers(
+    base_url: &str,
+    server_id: u16,
+    container_dto: &mut DockerRegistrationDto,
+) -> Result<(), Box<dyn Error + Send + Sync>> {
+    // First get local IP
+    println!("Preparing to broadcast docker containers...");
+    // Create HTTP client for registration
+    let client = Client::builder()
+        .danger_accept_invalid_certs(true)
+        .build()?;
+
+    // Prepare registration data
+    let container_dto = container_dto;
+    container_dto.server_id = server_id;
+
+    // Try to register (will retry on failure)
+    loop {
+        println!("Attempting to broadcast containers...");
+        let url = format!("{}/monitoring/service-discovery", base_url);
+        match client.post(&url).json(&container_dto).send().await {
+            Ok(resp) if resp.status().is_success() => {
+                println!(
+                    "✅ Successfully broadcasted following docker container: {:?}",
+                    container_dto
+                );
+                return Ok(());
+            }
+            Ok(resp) => {
+                let status = resp.status();
+                let text = resp.text().await.unwrap_or_default();
+                println!(
+                    "⚠️ Broadcasting failed ({}): {} (will retry in 10 seconds)",
+                    status, text
+                );
+            }
+            Err(err) => {
+                println!("⚠️ Broadcasting failed: {} (will retry in 10 seconds)", err);
+            }
+        }
+        sleep(Duration::from_secs(10)).await;
+    }
+}
+
+/// Periodically sends heartbeat signals to the backend server to indicate agent liveness.
+///
+/// This function runs in a background task and will retry on network errors.
+///
+/// # Arguments
+/// * `base_url` - The base URL of the backend server.
+/// * `ip` - The IP address of the agent.
+///
+/// # Returns
+/// * `Result<(), Box<dyn Error + Send + Sync>>` - Ok if heartbeats are sent successfully.
 pub async fn heartbeat_loop(base_url: &str, ip: &str) -> Result<(), Box<dyn Error + Send + Sync>> {
     let client = Client::builder()
         .danger_accept_invalid_certs(true)
@@ -134,6 +230,16 @@ pub async fn heartbeat_loop(base_url: &str, ip: &str) -> Result<(), Box<dyn Erro
     }
 }
 
+/// Sends collected hardware and network metrics to the backend server.
+///
+/// This function is called periodically from the metrics collection loop. It logs the result and retries on network errors.
+///
+/// # Arguments
+/// * `base_url` - The base URL of the backend server.
+/// * `metrics` - The metrics data to send (see [`MetricDto`]).
+///
+/// # Returns
+/// * `Result<(), Box<dyn Error + Send + Sync>>` - Ok if metrics are sent successfully.
 pub async fn send_metrics(
     base_url: &str,
     metrics: &MetricDto,
@@ -153,3 +259,149 @@ pub async fn send_metrics(
 
     Ok(())
 }
+
+/// Polls the backend server for remote commands and executes them.
+///
+/// This function runs in a background task, polling the server for new messages. It acknowledges receipt and execution of each command, and handles errors gracefully.
+///
+/// # Arguments
+/// * `docker` - Reference to a Bollard Docker client.
+/// * `base_url` - The base URL of the backend server.
+///
+/// # Returns
+/// * `Result<(), Box<dyn Error + Send + Sync>>` - Ok if commands are handled successfully.
+pub async fn listening_to_server(
+    docker: &Docker,
+    base_url: &str,
+) -> Result<(), Box<dyn Error + Send + Sync>> {
+    let url = format!("{}/api/message", base_url);
+    let client = reqwest::Client::new();
+
+    loop {
+        // Get message from server
+        let resp = client.get(&url).send().await;
+
+        match resp {
+            Ok(response) => {
+                if response.status().is_success() {
+                    match response.json::<ServerMessage>().await {
+                        Ok(msg) => {
+                            // Acknowledge receipt immediately
+                            if let Err(e) = send_acknowledgment(
+                                &client,
+                                base_url,
+                                &msg.message_id,
+                                "received",
+                                "Message received successfully",
+                            )
+                            .await
+                            {
+                                eprintln!("Failed to send receipt acknowledgment: {}", e);
+                            }
+
+                            // Handle the message
+                            let result = handle_server_message(docker, msg.clone()).await;
+
+                            // Send execution result acknowledgment
+                            let (status, details) = match result {
+                                Ok(_) => ("success", "Message executed successfully".to_string()),
+                                Err(e) => ("error", format!("Execution failed: {}", e)),
+                            };
+
+                            if let Err(e) = send_acknowledgment(
+                                &client,
+                                base_url,
+                                &msg.message_id,
+                                status,
+                                &details,
+                            )
+                            .await
+                            {
+                                eprintln!("Failed to send execution acknowledgment: {}", e);
+                            }
+                        }
+                        Err(e) => {
+                            eprintln!("Failed to parse message: {}", e);
+                        }
+                    }
+                } else if response.status() == reqwest::StatusCode::NO_CONTENT {
+                    // No new messages, continue polling
+                    println!("No new messages from server");
+                } else {
+                    eprintln!("Server returned error status: {}", response.status());
+                }
+            }
+            Err(e) => {
+                eprintln!("Failed to reach server: {}", e);
+            }
+        }
+
+        // Poll every 5 seconds (or use WebSocket for real-time)
+        sleep(Duration::from_secs(5)).await;
+    }
+}
+
+/// Sends an acknowledgment to the backend server for a received or executed command message.
+///
+/// This function is used internally by [`listening_to_server`] to confirm receipt and execution status of commands.
+///
+/// # Arguments
+/// * `client` - Reference to a reqwest HTTP client.
+/// * `base_url` - The base URL of the backend server.
+/// * `message_id` - The ID of the message being acknowledged.
+/// * `status` - Status string (e.g., "received", "success", "error").
+/// * `details` - Additional details about the acknowledgment.
+///
+/// # Returns
+/// * `Result<(), Box<dyn Error + Send + Sync>>` - Ok if acknowledgment is sent successfully.
+pub async fn send_acknowledgment(
+    client: &reqwest::Client,
+    base_url: &str,
+    message_id: &str,
+    status: &str,
+    details: &str,
+) -> Result<(), Box<dyn Error + Send + Sync>> {
+    let ack_url = format!("{}/api/acknowledge", base_url);
+
+    let acknowledgment = Acknowledgment {
+        message_id: message_id.to_string(),
+        status: status.to_string(),
+        details: details.to_string(),
+    };
+
+    let response = client.post(&ack_url).json(&acknowledgment).send().await?;
+
+    if response.status().is_success() {
+        println!(
+            "Acknowledgment sent successfully for message {}",
+            message_id
+        );
+    } else {
+        eprintln!(
+            "Server returned error for acknowledgment: {}",
+            response.status()
+        );
+    }
+
+    Ok(())
+}
+
+pub async fn send_docker_metrics(
+    base_url: &str,
+    docker_metrics: &DockerMetricDto,
+) -> Result<(), Box<dyn Error + Send + Sync>> {
+    let client = Client::new();
+    let url = format!("{}/monitoring/docker-metric", base_url);
+    println!("Docker Metrics: {:?}", docker_metrics);
+
+    match client.post(&url).json(&docker_metrics).send().await {
+        Ok(res) => println!(
+            "✅ Sent docker metrics for server {} | Status: {}",
+            docker_metrics.server_id,
+            res.status()
+        ),
+        Err(err) => eprintln!("❌ Failed to send docker metrics: {}", err),
+    }
+
+    Ok(())
+}

WatcherAgent/src/docker/container.rs

@@ -0,0 +1,214 @@
+//! Docker container utilities for WatcherAgent
+//!
+//! Provides functions to list and process Docker containers using the Bollard library.
+//!
+use crate::docker::stats;
+use crate::docker::stats::{ContainerCpuInfo, ContainerNetworkInfo};
+use crate::models::DockerContainer;
+
+use bollard::query_parameters::{
+    CreateImageOptions, ListContainersOptions, RestartContainerOptions,
+};
+use bollard::Docker;
+use futures_util::StreamExt;
+use std::error::Error;
+
+/// Returns a list of available Docker containers.
+///
+/// # Arguments
+/// * `docker` - Reference to a Bollard Docker client.
+///
+/// # Returns
+/// * `Vec<DockerContainer>` - Vector of Docker container info.
+pub async fn get_available_containers(docker: &Docker) -> Vec<DockerContainer> {
+    println!("=== DOCKER CONTAINER LIST ===");
+
+    let options = Some(ListContainersOptions {
+        all: true,
+        ..Default::default()
+    });
+
+    let containers_list = match docker.list_containers(options).await {
+        Ok(containers) => {
+            println!("Available containers ({}):", containers.len());
+            containers
+                .into_iter()
+                .filter_map(|container| {
+                    container.id.as_ref()?; // Skip if no ID
+
+                    let id = container.id?;
+                    let short_id = if id.len() > 12 { &id[..12] } else { &id };
+
+                    let name = container
+                        .names
+                        .and_then(|names| names.into_iter().next())
+                        .map(|name| name.trim_start_matches('/').to_string())
+                        .unwrap_or_else(|| "unknown".to_string());
+
+                    let image = container
+                        .image
+                        .as_ref()
+                        .map(|img| img.to_string())
+                        .unwrap_or_else(|| "unknown".to_string());
+
+                    Some(DockerContainer {
+                        id: short_id.to_string(),
+                        image: Some(image),
+                        name: Some(name),
+                    })
+                })
+                .collect()
+        }
+        Err(e) => {
+            eprintln!("Failed to list containers: {}", e);
+            Vec::new()
+        }
+    };
+
+    containers_list
+}
+
+/// Pulls a new Docker image and restarts the current container.
+///
+/// # Arguments
+/// * `docker` - Reference to a Bollard Docker client.
+/// * `image` - The name of the Docker image to pull.
+///
+/// # Returns
+/// * `Result<(), Box<dyn Error + Send + Sync>>` - Ok if updated successfully, error otherwise.
+pub async fn update_docker_image(
+    docker: &Docker,
+    image: &str,
+) -> Result<(), Box<dyn Error + Send + Sync>> {
+    println!("Updating to {}", image);
+
+    // 1. Pull new image
+    let mut stream = docker.create_image(
+        Some(CreateImageOptions {
+            from_image: Some(image.to_string()),
+            ..Default::default()
+        }),
+        None,
+        None,
+    );
+
+    // Use the stream with proper trait bounds
+    while let Some(result) = StreamExt::next(&mut stream).await {
+        match result {
+            Ok(progress) => {
+                if let Some(status) = progress.status {
+                    println!("Pull status: {}", status);
+                }
+            }
+            Err(e) => {
+                eprintln!("Error pulling image: {}", e);
+                break;
+            }
+        }
+    }
+
+    // 2. Restart the current container
+    let options = Some(ListContainersOptions {
+        all: true,
+        ..Default::default()
+    });
+    let container_id = docker
+        .list_containers(options)
+        .await?
+        .into_iter()
+        .find_map(|c| {
+            c.image
+                .as_ref()
+                .and_then(|img| if img == image { c.id } else { None })
+        });
+    let _ = restart_container(docker, &container_id.unwrap()).await;
+
+    Ok(())
+}
+
+/// Restarts the agent's own Docker container.
+///
+/// # Arguments
+/// * `docker` - Reference to a Bollard Docker client.
+///
+/// # Returns
+/// * `Result<(), Box<dyn Error + Send + Sync>>` - Ok if restarted successfully, error otherwise.
+pub async fn restart_container(
+    docker: &Docker,
+    container_id: &str,
+) -> Result<(), Box<dyn Error + Send + Sync>> {
+    println!("Restarting container {}", container_id);
+    if let Err(e) = docker
+        .restart_container(
+            &container_id.to_string(),
+            Some(RestartContainerOptions {
+                signal: None,
+                t: Some(0),
+            }),
+        )
+        .await
+    {
+        eprintln!("Failed to restart container: {}", e);
+    }
+
+    Ok(())
+}
+
+/*
+/// Extracts a Docker container ID from a string line.
+///
+/// # Arguments
+/// * `line` - The input string containing a container ID or related info.
+///
+/// # Returns
+/// * `Option<String>` - The extracted container ID if found.
+pub fn extract_client_container_id(line: &str) -> Option<String> {
+    // ...existing code...
+}
+*/
+
+/// Gets network statistics for a specific container
+pub async fn get_network_stats(
+    docker: &Docker,
+    container_id: &str,
+) -> Result<ContainerNetworkInfo, Box<dyn Error + Send + Sync>> {
+    let (_, net_info, _) = stats::get_single_container_stats(docker, container_id).await?;
+
+    if let Some(net_info) = net_info {
+        Ok(net_info)
+    } else {
+        // Return default network info if not found
+        println!("No network info found for container {}", container_id);
+        Ok(ContainerNetworkInfo {
+            container_id: Some(container_id.to_string()),
+            rx_bytes: None,
+            tx_bytes: None,
+            rx_packets: None,
+            tx_packets: None,
+            rx_errors: None,
+            tx_errors: None,
+        })
+    }
+}
+
+/// Gets CPU statistics for a specific container
+pub async fn get_cpu_stats(
+    docker: &Docker,
+    container_id: &str,
+) -> Result<ContainerCpuInfo, Box<dyn Error + Send + Sync>> {
+    let (cpu_info, _, _) = stats::get_single_container_stats(docker, container_id).await?;
+
+    if let Some(cpu_info) = cpu_info {
+        Ok(cpu_info)
+    } else {
+        // Return default CPU info if not found
+        println!("No CPU info found for container {}", container_id);
+        Ok(ContainerCpuInfo {
+            container_id: Some(container_id.to_string()),
+            cpu_usage_percent: None,
+            system_cpu_usage: None,
+            container_cpu_usage: None,
+            online_cpus: None,
+        })
+    }
+}

WatcherAgent/src/docker/mod.rs

@@ -0,0 +1,235 @@
+/// # Docker Module
+///
+/// This module provides Docker integration for WatcherAgent, including container enumeration, statistics, and lifecycle management.
+///
+/// ## Responsibilities
+/// - **Container Management:** Lists, inspects, and manages Docker containers relevant to the agent.
+/// - **Statistics Aggregation:** Collects network and CPU statistics for all managed containers.
+/// - **Lifecycle Operations:** Supports container restart and ID lookup for agent self-management.
+///
+pub mod container;
+pub mod serverclientcomm;
+pub mod stats;
+
+use crate::models::{
+    DockerCollectMetricDto, DockerContainer, DockerContainerCpuDto, DockerContainerInfo,
+    DockerContainerNetworkDto, DockerContainerRamDto, DockerMetricDto, DockerRegistrationDto,
+};
+use bollard::Docker;
+use std::error::Error;
+
+/// Main Docker manager that holds the Docker client and provides all operations
+#[derive(Debug, Clone)]
+pub struct DockerManager {
+    pub docker: Docker,
+}
+
+impl Default for DockerManager {
+    fn default() -> Self {
+        Self {
+            docker: Docker::connect_with_local_defaults()
+                .unwrap_or_else(|e| panic!("Failed to create default Docker connection: {}", e)),
+        }
+    }
+}
+
+impl DockerManager {
+    /// Creates a new DockerManager instance
+    pub fn new() -> Result<Self, Box<dyn Error + Send + Sync>> {
+        let docker = Docker::connect_with_local_defaults()
+            .map_err(|e| format!("Failed to connect to Docker: {}", e))?;
+
+        Ok(Self { docker })
+    }
+
+    /// Creates a DockerManager instance with optional Docker connection
+    pub fn new_optional() -> Option<Self> {
+        Docker::connect_with_local_defaults()
+            .map(|docker| Self { docker })
+            .ok()
+    }
+
+    /// Finds the Docker container running the agent by image name
+    pub async fn get_client_container(
+        &self,
+    ) -> Result<Option<DockerContainer>, Box<dyn Error + Send + Sync>> {
+        let containers = container::get_available_containers(&self.docker).await;
+        let client_image = "watcher-agent";
+
+        Ok(containers
+            .into_iter()
+            .find(|c| c.clone().image.unwrap().contains(client_image))
+            .map(|container| DockerContainer {
+                id: container.id,
+                image: container.image,
+                name: container.name,
+            }))
+    }
+
+    /// Gets the current client version (image name) if running in Docker
+    pub async fn get_client_version(&self) -> String {
+        match self.get_client_container().await {
+            Ok(Some(container)) => container
+                .image
+                .clone()
+                .unwrap()
+                .split(':')
+                .next()
+                .unwrap_or("unknown")
+                .to_string(),
+            Ok(None) => {
+                println!("Warning: No WatcherAgent container found");
+                "unknown".to_string()
+            }
+            Err(e) => {
+                println!("Warning: Could not get current image version: {}", e);
+                "unknown".to_string()
+            }
+        }
+    }
+
+    /// Checks if Docker is available and the agent is running in a container
+    pub async fn is_dockerized(&self) -> bool {
+        self.get_client_container()
+            .await
+            .map(|c| c.is_some())
+            .unwrap_or(false)
+    }
+
+    /// Gets all available containers as DTOs for registration
+    pub async fn get_containers(
+        &self,
+    ) -> Result<Vec<DockerContainer>, Box<dyn Error + Send + Sync>> {
+        let containers = container::get_available_containers(&self.docker).await;
+
+        Ok(containers
+            .into_iter()
+            .map(|container| DockerContainer {
+                id: container.id,
+                image: container.image,
+                name: container.name,
+            })
+            .collect())
+    }
+
+    /// Gets the number of running containers
+    pub async fn get_container_count(&self) -> Result<usize, Box<dyn Error + Send + Sync>> {
+        let containers = container::get_available_containers(&self.docker).await;
+        Ok(containers.len())
+    }
+
+    /// Restarts a specific container by ID
+    pub async fn restart_container(
+        &self,
+        container_id: &str,
+    ) -> Result<(), Box<dyn Error + Send + Sync>> {
+        container::restart_container(&self.docker, container_id).await
+    }
+
+    /// Collects Docker metrics for all containers
+    pub async fn collect_metrics(&self) -> Result<DockerMetricDto, Box<dyn Error + Send + Sync>> {
+        let containers = self.get_containers().await?;
+        let (cpu_stats, net_stats, mem_stats) = stats::get_container_stats(&self.docker).await?;
+
+        let container_infos_total: Vec<_> = containers
+            .into_iter()
+            .map(|container| {
+                let cpu = cpu_stats
+                    .iter()
+                    .find(|c| c.container_id == Some(container.id.clone()))
+                    .cloned();
+                let network = net_stats
+                    .iter()
+                    .find(|n| n.container_id == Some(container.id.clone()))
+                    .cloned();
+                let ram = mem_stats
+                    .iter()
+                    .find(|m| m.container_id == Some(container.id.clone()))
+                    .cloned();
+
+                DockerContainerInfo {
+                    container: Some(container),
+                    status: None, // Status can be fetched if needed
+                    cpu,
+                    network,
+                    ram,
+                }
+            })
+            .collect();
+
+        let container_infos: Vec<DockerCollectMetricDto> = container_infos_total
+            .into_iter()
+            .map(|info| DockerCollectMetricDto {
+                id: Some(info.container.unwrap().id).unwrap_or("".to_string()),
+                cpu: info
+                    .cpu
+                    .unwrap()
+                    .cpu_usage_percent
+                    .map(|load| DockerContainerCpuDto {
+                        cpu_load: Some(load),
+                    })
+                    .unwrap_or(DockerContainerCpuDto { cpu_load: None }),
+                ram: info
+                    .ram
+                    .unwrap()
+                    .memory_usage_percent
+                    .map(|load| DockerContainerRamDto {
+                        cpu_load: Some(load),
+                    })
+                    .unwrap_or(DockerContainerRamDto { cpu_load: None }),
+                network: DockerContainerNetworkDto {
+                    net_in: info
+                        .network
+                        .as_ref()
+                        .unwrap()
+                        .rx_bytes
+                        .map(|bytes| bytes as f64)
+                        .or(Some(0.0)),
+                    net_out: info
+                        .network
+                        .unwrap()
+                        .tx_bytes
+                        .map(|bytes| bytes as f64)
+                        .or(Some(0.0)),
+                },
+            })
+            .collect();
+        let dto = DockerMetricDto {
+            server_id: 0,
+            containers: serde_json::to_string(&container_infos)?,
+        };
+
+        Ok(dto)
+    }
+
+    pub async fn create_registration_dto(
+        &self,
+    ) -> Result<DockerRegistrationDto, Box<dyn Error + Send + Sync>> {
+        let containers = self.get_containers().await?;
+        let dto = DockerRegistrationDto {
+            server_id: 0,
+            //container_count,
+            containers: serde_json::to_string(&containers)?,
+        };
+
+        Ok(dto)
+    }
+}
+
+// Keep these as utility functions if needed, but they should use DockerManager internally
+impl DockerContainer {
+    /// Returns the container ID
+    pub fn id(&self) -> &str {
+        &self.id
+    }
+
+    /// Returns the image name
+    pub fn image(&self) -> &str {
+        &self.image.as_deref().unwrap_or("unknown")
+    }
+
+    /// Returns the container name
+    pub fn name(&self) -> &str {
+        &self.name.as_deref().unwrap_or("unknown")
+    }
+}

WatcherAgent/src/docker/serverclientcomm.rs

@@ -0,0 +1,59 @@
+//! Server-client communication utilities for WatcherAgent
+//!
+//! Handles server commands, Docker image updates, and container management using the Bollard library.
+//!
+use crate::models::ServerMessage;
+
+use super::container::{restart_container, update_docker_image};
+//use bollard::query_parameters::{CreateImageOptions, RestartContainerOptions};
+use bollard::Docker;
+use std::error::Error;
+
+/// Handles a message from the backend server and dispatches the appropriate action.
+///
+/// # Arguments
+/// * `docker` - Reference to a Bollard Docker client.
+/// * `msg` - The server message to handle.
+///
+/// # Returns
+/// * `Result<(), Box<dyn Error + Send + Sync>>` - Ok if handled successfully, error otherwise.
+pub async fn handle_server_message(
+    docker: &Docker,
+    msg: ServerMessage,
+) -> Result<(), Box<dyn Error + Send + Sync>> {
+    let msg = msg.clone();
+    println!("Handling server message: {:?}", msg);
+
+    // Handle different message types
+    match msg.message_type.as_str() {
+        "update_image" => {
+            if let Some(image_name) = msg.data.get("image").and_then(|v| v.as_str()) {
+                println!("Received update command for image: {}", image_name);
+                // Call your update_docker_image function here
+                update_docker_image(docker, image_name).await?;
+                Ok(())
+            } else {
+                Err("Missing image name in update message".into())
+            }
+        }
+        "restart_container" => {
+            if let Some(image_name) = msg.data.get("image").and_then(|v| v.as_str()) {
+                println!("Received restart command for image: {}", image_name);
+                // Call your update_docker_image function here
+                restart_container(docker, image_name).await?;
+                Ok(())
+            } else {
+                Err("Missing image name in update message".into())
+            }
+        }
+        "stop_agent" => {
+            println!("Received stop agent command");
+            // Implement graceful shutdown
+            std::process::exit(0);
+        }
+        _ => {
+            eprintln!("Unknown message type: {}", msg.message_type);
+            Err(format!("Unknown message type: {}", msg.message_type).into())
+        }
+    }
+}

WatcherAgent/src/docker/stats/cpu.rs

@@ -0,0 +1,99 @@
+use super::ContainerCpuInfo;
+use bollard::query_parameters::{ListContainersOptions, StatsOptions};
+use bollard::Docker;
+use futures_util::stream::TryStreamExt;
+use std::error::Error;
+
+/// Get CPU statistics for all containers
+pub async fn get_all_containers_cpu_stats(
+    docker: &Docker,
+) -> Result<Vec<ContainerCpuInfo>, Box<dyn Error + Send + Sync>> {
+    let containers = docker
+        .list_containers(Some(ListContainersOptions {
+            all: true,
+            ..Default::default()
+        }))
+        .await?;
+
+    let mut cpu_infos = Vec::new();
+
+    for container in containers {
+        let id = container.id.unwrap_or_default();
+
+        // Skip if no ID
+        if id.is_empty() {
+            continue;
+        }
+
+        if let Some(cpu_info) = get_single_container_cpu_stats(docker, &id).await? {
+            cpu_infos.push(cpu_info);
+        }
+    }
+
+    Ok(cpu_infos)
+}
+
+/// Get CPU statistics for a specific container
+pub async fn get_single_container_cpu_stats(
+    docker: &Docker,
+    container_id: &str,
+) -> Result<Option<ContainerCpuInfo>, Box<dyn Error + Send + Sync>> {
+    let mut stats_stream = docker.stats(
+        container_id,
+        Some(StatsOptions {
+            stream: false,
+            one_shot: true,
+        }),
+    );
+
+    if let Some(stats) = stats_stream.try_next().await? {
+        if let (Some(cpu_stats), Some(precpu_stats)) = (&stats.cpu_stats, &stats.precpu_stats) {
+            if let (Some(cpu_usage), Some(pre_cpu_usage)) =
+                (&cpu_stats.cpu_usage, &precpu_stats.cpu_usage)
+            {
+                let cpu_delta = cpu_usage
+                    .total_usage
+                    .unwrap_or(0)
+                    .saturating_sub(pre_cpu_usage.total_usage.unwrap_or(0));
+
+                let system_delta = cpu_stats
+                    .system_cpu_usage
+                    .unwrap_or(0)
+                    .saturating_sub(precpu_stats.system_cpu_usage.unwrap_or(0));
+
+                let online_cpus = cpu_stats.online_cpus.unwrap_or(1);
+
+                let cpu_percent = if system_delta > 0 && online_cpus > 0 {
+                    (cpu_delta as f64 / system_delta as f64) * online_cpus as f64 * 100.0
+                } else {
+                    0.0
+                };
+
+                return Ok(Some(ContainerCpuInfo {
+                    container_id: Some(container_id.to_string()),
+                    cpu_usage_percent: Some(cpu_percent),
+                    system_cpu_usage: Some(cpu_stats.system_cpu_usage.unwrap_or(0)),
+                    container_cpu_usage: Some(cpu_usage.total_usage.unwrap_or(0)),
+                    online_cpus: Some(online_cpus),
+                }));
+            }
+        }
+    }
+
+    Ok(None)
+}
+
+/// Get average CPU usage across all containers
+pub async fn get_average_cpu_usage(docker: &Docker) -> Result<f64, Box<dyn Error + Send + Sync>> {
+    let cpu_infos = get_all_containers_cpu_stats(docker).await?;
+
+    if cpu_infos.is_empty() {
+        return Ok(0.0);
+    }
+
+    let total_cpu: f64 = cpu_infos
+        .iter()
+        .map(|cpu| cpu.cpu_usage_percent.unwrap())
+        .sum();
+    Ok(total_cpu / cpu_infos.len() as f64)
+}

WatcherAgent/src/docker/stats/mod.rs

@@ -0,0 +1,90 @@
+pub mod cpu;
+pub mod network;
+pub mod ram;
+
+use serde::{Deserialize, Serialize};
+
+#[derive(Debug, Serialize, Deserialize, Clone)]
+pub struct ContainerCpuInfo {
+    pub container_id: Option<String>,
+    pub cpu_usage_percent: Option<f64>,
+    pub system_cpu_usage: Option<u64>,
+    pub container_cpu_usage: Option<u64>,
+    pub online_cpus: Option<u32>,
+}
+
+#[derive(Debug, Serialize, Deserialize, Clone)]
+pub struct ContainerNetworkInfo {
+    pub container_id: Option<String>,
+    pub rx_bytes: Option<u64>,
+    pub tx_bytes: Option<u64>,
+    pub rx_packets: Option<u64>,
+    pub tx_packets: Option<u64>,
+    pub rx_errors: Option<u64>,
+    pub tx_errors: Option<u64>,
+}
+
+#[derive(Debug, Serialize, Deserialize, Clone)]
+pub struct ContainerMemoryInfo {
+    pub container_id: Option<String>,
+    pub memory_usage: Option<u64>,
+    pub memory_limit: Option<u64>,
+    pub memory_usage_percent: Option<f64>,
+}
+
+use bollard::Docker;
+use std::error::Error;
+
+/// Get container statistics for all containers using an existing Docker client
+pub async fn get_container_stats(
+    docker: &Docker,
+) -> Result<
+    (
+        Vec<ContainerCpuInfo>,
+        Vec<ContainerNetworkInfo>,
+        Vec<ContainerMemoryInfo>,
+    ),
+    Box<dyn Error + Send + Sync>,
+> {
+    let cpu_infos = cpu::get_all_containers_cpu_stats(docker).await?;
+    let net_infos = network::get_all_containers_network_stats(docker).await?;
+    let mem_infos = ram::get_all_containers_memory_stats(docker).await?;
+
+    Ok((cpu_infos, net_infos, mem_infos))
+}
+
+/// Get container statistics for a specific container
+pub async fn get_single_container_stats(
+    docker: &Docker,
+    container_id: &str,
+) -> Result<
+    (
+        Option<ContainerCpuInfo>,
+        Option<ContainerNetworkInfo>,
+        Option<ContainerMemoryInfo>,
+    ),
+    Box<dyn Error + Send + Sync>,
+> {
+    let cpu_info = cpu::get_single_container_cpu_stats(docker, container_id).await?;
+    let net_info = network::get_single_container_network_stats(docker, container_id).await?;
+    let mem_info = ram::get_single_container_memory_stats(docker, container_id).await?;
+
+    Ok((cpu_info, net_info, mem_info))
+}
+
+/// Get total network statistics across all containers
+pub async fn get_total_network_stats(
+    docker: &Docker,
+) -> Result<(u64, u64), Box<dyn Error + Send + Sync>> {
+    network::get_total_network_stats(docker).await
+}
+
+/// Get average CPU usage across all containers
+pub async fn get_average_cpu_usage(docker: &Docker) -> Result<f64, Box<dyn Error + Send + Sync>> {
+    cpu::get_average_cpu_usage(docker).await
+}
+
+/// Get total memory usage across all containers
+pub async fn get_total_memory_usage(docker: &Docker) -> Result<u64, Box<dyn Error + Send + Sync>> {
+    ram::get_total_memory_usage(docker).await
+}

WatcherAgent/src/docker/stats/network.rs

@@ -0,0 +1,79 @@
+use super::ContainerNetworkInfo;
+use bollard::query_parameters::{ListContainersOptions, StatsOptions};
+use bollard::Docker;
+use futures_util::stream::TryStreamExt;
+use std::error::Error;
+
+/// Get network statistics for all containers
+pub async fn get_all_containers_network_stats(
+    docker: &Docker,
+) -> Result<Vec<ContainerNetworkInfo>, Box<dyn Error + Send + Sync>> {
+    let containers = docker
+        .list_containers(Some(ListContainersOptions {
+            all: true,
+            ..Default::default()
+        }))
+        .await?;
+
+    let mut net_infos = Vec::new();
+
+    for container in containers {
+        let id = container.id.unwrap_or_default();
+
+        // Skip if no ID
+        if id.is_empty() {
+            continue;
+        }
+
+        if let Some(net_info) = get_single_container_network_stats(docker, &id).await? {
+            net_infos.push(net_info);
+        }
+    }
+
+    Ok(net_infos)
+}
+
+/// Get network statistics for a specific container
+pub async fn get_single_container_network_stats(
+    docker: &Docker,
+    container_id: &str,
+) -> Result<Option<ContainerNetworkInfo>, Box<dyn Error + Send + Sync>> {
+    let mut stats_stream = docker.stats(
+        container_id,
+        Some(StatsOptions {
+            stream: false,
+            one_shot: true,
+        }),
+    );
+
+    if let Some(stats) = stats_stream.try_next().await? {
+        if let Some(networks) = stats.networks {
+            // Take the first network interface (usually eth0)
+            if let Some((_name, net)) = networks.into_iter().next() {
+                return Ok(Some(ContainerNetworkInfo {
+                    container_id: Some(container_id.to_string()),
+                    rx_bytes: net.rx_bytes,
+                    tx_bytes: net.tx_bytes,
+                    rx_packets: net.rx_packets,
+                    tx_packets: net.tx_packets,
+                    rx_errors: net.rx_errors,
+                    tx_errors: net.tx_errors,
+                }));
+            }
+        }
+    }
+
+    Ok(None)
+}
+
+/// Get total network statistics across all containers
+pub async fn get_total_network_stats(
+    docker: &Docker,
+) -> Result<(u64, u64), Box<dyn Error + Send + Sync>> {
+    let net_infos = get_all_containers_network_stats(docker).await?;
+
+    let total_rx: u64 = net_infos.iter().map(|net| net.rx_bytes.unwrap()).sum();
+    let total_tx: u64 = net_infos.iter().map(|net| net.tx_bytes.unwrap()).sum();
+
+    Ok((total_rx, total_tx))
+}

WatcherAgent/src/docker/stats/ram.rs

@@ -0,0 +1,77 @@
+use super::ContainerMemoryInfo;
+use bollard::query_parameters::{ListContainersOptions, StatsOptions};
+use bollard::Docker;
+use futures_util::stream::TryStreamExt;
+use std::error::Error;
+
+/// Get memory statistics for all containers
+pub async fn get_all_containers_memory_stats(
+    docker: &Docker,
+) -> Result<Vec<ContainerMemoryInfo>, Box<dyn Error + Send + Sync>> {
+    let containers = docker
+        .list_containers(Some(ListContainersOptions {
+            all: true,
+            ..Default::default()
+        }))
+        .await?;
+
+    let mut mem_infos = Vec::new();
+
+    for container in containers {
+        let id = container.id.unwrap_or_default();
+
+        // Skip if no ID
+        if id.is_empty() {
+            continue;
+        }
+
+        if let Some(mem_info) = get_single_container_memory_stats(docker, &id).await? {
+            mem_infos.push(mem_info);
+        }
+    }
+
+    Ok(mem_infos)
+}
+
+/// Get memory statistics for a specific container
+pub async fn get_single_container_memory_stats(
+    docker: &Docker,
+    container_id: &str,
+) -> Result<Option<ContainerMemoryInfo>, Box<dyn Error + Send + Sync>> {
+    let mut stats_stream = docker.stats(
+        container_id,
+        Some(StatsOptions {
+            stream: false,
+            one_shot: true,
+        }),
+    );
+
+    if let Some(stats) = stats_stream.try_next().await? {
+        if let Some(memory_stats) = &stats.memory_stats {
+            let memory_usage = memory_stats.usage.unwrap_or(0);
+            let memory_limit = memory_stats.limit.unwrap_or(1); // Avoid division by zero
+
+            let memory_usage_percent = if memory_limit > 0 {
+                (memory_usage as f64 / memory_limit as f64) * 100.0
+            } else {
+                0.0
+            };
+
+            return Ok(Some(ContainerMemoryInfo {
+                container_id: Some(container_id.to_string()),
+                memory_usage: Some(memory_usage),
+                memory_limit: Some(memory_limit),
+                memory_usage_percent: Some(memory_usage_percent),
+            }));
+        }
+    }
+
+    Ok(None)
+}
+
+/// Get total memory usage across all containers
+pub async fn get_total_memory_usage(docker: &Docker) -> Result<u64, Box<dyn Error + Send + Sync>> {
+    let mem_infos = get_all_containers_memory_stats(docker).await?;
+    let total_memory: u64 = mem_infos.iter().map(|mem| mem.memory_usage.unwrap()).sum();
+    Ok(total_memory)
+}

WatcherAgent/src/hardware/cpu.rs

@@ -2,6 +2,29 @@ use anyhow::Result;
 use std::error::Error;
 use sysinfo::System;
 
+/// # CPU Hardware Module
+///
+/// This module provides CPU information collection for WatcherAgent, including load, temperature, and system uptime.
+///
+/// ## Responsibilities
+/// - **CPU Detection:** Identifies CPU model and core count.
+/// - **Metric Collection:** Queries CPU load, temperature, and uptime.
+/// - **Error Handling:** Graceful fallback if metrics are unavailable.
+///
+/// ## Units
+/// - `current_load`: CPU usage as a percentage (**0.0–100.0**)
+/// - `current_temp`: CPU temperature in **degrees Celsius (°C)**
+/// - `uptime`: System uptime in **seconds (s)**
+///
+/// CPU statistics for the host system.
+///
+/// # Fields
+/// - `name`: CPU model name (string)
+/// - `cores`: Number of physical CPU cores (integer)
+/// - `current_load`: CPU usage as a percentage (**0.0–100.0**)
+/// - `current_temp`: CPU temperature in **degrees Celsius (°C)**
+/// - `uptime`: System uptime in **seconds (s)**
+/// - `host_name`: Hostname of the system (string)
 #[derive(Debug)]
 pub struct CpuInfo {
     pub name: Option<String>,
@@ -12,6 +35,10 @@ pub struct CpuInfo {
     pub host_name: Option<String>,
 }
 
+/// Collects CPU information (model, cores, load, temperature, uptime).
+///
+/// # Returns
+/// * `Result<CpuInfo, Box<dyn Error + Send + Sync>>` - CPU statistics or error if unavailable.
 pub async fn get_cpu_info() -> Result<CpuInfo, Box<dyn Error + Send + Sync>> {
     let mut sys = System::new_all();
 
@@ -33,12 +60,23 @@ pub async fn get_cpu_info() -> Result<CpuInfo, Box<dyn Error + Send + Sync>> {
     })
 }
 
+/// Queries system for current CPU load (percentage).
+///
+/// # Arguments
+/// * `sys` - Mutable reference to sysinfo::System
+///
+/// # Returns
+/// * `Result<f64, Box<dyn Error + Send + Sync>>` - CPU load as percentage.
 pub async fn get_cpu_load(sys: &mut System) -> Result<f64, Box<dyn Error + Send + Sync>> {
     sys.refresh_cpu_all();
     tokio::task::yield_now().await; // Allow other tasks to run
     Ok(sys.global_cpu_usage() as f64)
 }
 
+/// Attempts to read CPU temperature from system sensors (Linux only).
+///
+/// # Returns
+/// * `Result<f64, Box<dyn Error + Send + Sync>>` - CPU temperature in degrees Celsius (°C).
 pub async fn get_cpu_temp() -> Result<f64, Box<dyn Error + Send + Sync>> {
     println!("Attempting to get CPU temperature...");
 

WatcherAgent/src/hardware/disk.rs

@@ -1,130 +1,165 @@
-use std::error::Error;
+use crate::models::DiskInfoDetailed;
 
+use std::error::Error;
 use anyhow::Result;
 use sysinfo::DiskUsage;
-use sysinfo::{Component, Components, Disk, Disks, System};
+use sysinfo::{Component, Components, Disk, Disks};
+use serde::Serialize;
 
-#[derive(Debug)]
+
+/// # Disk Hardware Module
+///
+/// This module provides disk information collection for WatcherAgent, including total and per-disk statistics and temperature data.
+///
+/// ## Responsibilities
+/// - **Disk Enumeration:** Lists all physical disks and their properties.
+/// - **Usage Calculation:** Computes total and per-disk usage, available space, and usage percentage.
+/// - **Temperature Monitoring:** Associates disk components with temperature sensors if available.
+///
+/// ## Units
+/// - All sizes are in **bytes** unless otherwise noted.
+/// - Temperatures are in **degrees Celsius (°C)**.
+///
+/// Summary of disk statistics for the system.
+///
+/// # Fields
+/// - `total_size`: Total disk size in bytes (all disks > 100MB)
+/// - `total_used`: Total used disk space in bytes
+/// - `total_available`: Total available disk space in bytes
+/// - `total_usage`: Usage percentage (0.0–100.0)
+/// - `detailed_info`: Vector of [`DiskInfoDetailed`] for each disk
+#[derive(Serialize, Debug)]
 pub struct DiskInfo {
-    pub total: Option<f64>,
-    pub used: Option<f64>,
-    pub free: Option<f64>,
+    pub total_size: Option<f64>,
+    pub total_used: Option<f64>,
+    pub total_available: Option<f64>,
+    pub total_usage: Option<f64>,
+    pub detailed_info: Vec<DiskInfoDetailed>,
 }
 
-pub async fn get_disk_info() -> Result<DiskInfo> {
+/// Collects disk information for all detected disks, including usage and temperature.
+///
+/// This function enumerates all disks, calculates usage statistics, and attempts to associate temperature sensors with disk components.
+///
+/// # Returns
+/// * `Result<DiskInfo, Box<dyn std::error::Error + Send + Sync>>` - Disk statistics and details, or error if collection fails.
+pub async fn get_disk_info() -> Result<DiskInfo, Box<dyn std::error::Error + Send + Sync>> {
     let disks = Disks::new_with_refreshed_list();
-    let _disk_types = [
-        sysinfo::DiskKind::HDD,
-        sysinfo::DiskKind::SSD,
-        sysinfo::DiskKind::Unknown(0),
-    ];
-
-    let (_, _, _, _) = get_disk_utitlization().unwrap();
-
-    let mut total = 0;
-    let mut used = 0;
+    let mut detailed_info = Vec::new();
     
+    // Collect detailed disk information
     for disk in disks.list() {
-        if disk.total_space() > 100 * 1024 * 1024 {
-            // > 100MB
-            total += disk.total_space();
-            used += disk.total_space() - disk.available_space();
+        if disk.kind() == sysinfo::DiskKind::Unknown(0) {
+            continue;
+        }
+        
+        let disk_used = disk.total_space() - disk.available_space();
+        detailed_info.push(DiskInfoDetailed {
+            disk_name: disk.name().to_string_lossy().into_owned(),
+            disk_kind: format!("{:?}", disk.kind()),
+            disk_total_space: disk.total_space() as f64,
+            disk_available_space: disk.available_space() as f64,
+            disk_used_space: disk_used as f64,
+            disk_mount_point: disk.mount_point().to_string_lossy().into_owned(),
+            component_disk_label: String::new(),
+            component_disk_temperature: 0.0,
+        });
+    }
+    
+    // Get component temperatures
+    let components = Components::new_with_refreshed_list();
+    for component in &components {
+        if let Some(temperature) = component.temperature() {
+            // Update detailed info with temperature data if it matches a disk component
+            for disk_info in &mut detailed_info {
+                if component.label().contains(&disk_info.disk_name) {
+                    disk_info.component_disk_label = component.label().to_string();
+                    disk_info.component_disk_temperature = temperature;
                 }
             }
+        }
+    }
+    
+    // Calculate totals (only disks > 100MB)
+    let (total_size, total_used, total_available) = calculate_disk_totals(&disks);
+    
+    let (total_size, total_used, total_available, total_usage) = if total_size > 0.0 {
+        (total_size, total_used, total_available, (total_used / total_size) * 100.0)
+    } else {
+        match get_disk_info_fallback() {
+            Ok(fallback_data) => fallback_data,
+            Err(_) => (0.0, 0.0, 0.0, 0.0), // Default values if fallback fails
+        }
+    };
     
     Ok(DiskInfo {
-        total: Some(total as f64),
-        used: Some(used as f64),
-        free: Some((total - used) as f64),
+        total_size: if total_size > 0.0 { Some(total_size) } else { None },
+        total_used: if total_used > 0.0 { Some(total_used) } else { None },
+        total_available: if total_available > 0.0 { Some(total_available) } else { None },
+        total_usage: if total_usage > 0.0 { Some(total_usage) } else { None },
+        detailed_info,
     })
 }
 
-pub fn get_disk_utitlization() -> Result<(f64, f64, f64, f64), Box<dyn Error>> {
-    let mut sys = System::new();
-    sys.refresh_all();
-    let mut count = 0;
-
+fn calculate_disk_totals(disks: &Disks) -> (f64, f64, f64) {
     let mut total_size = 0u64;
     let mut total_used = 0u64;
     let mut total_available = 0u64;
     
-    let disks = Disks::new_with_refreshed_list();
     for disk in disks.list() {
-        // Only print disks with known kind
-        if disk.kind() == sysinfo::DiskKind::Unknown(0) {
-            continue;
-        }
-        println!(
-            "Disk_Name: {:?}:\n---- Disk_Kind: {},\n---- Total: {},\n---- Available: {},\n---- Used: {}, \n---- Mount_Point: {:?}",
-            disk.name(),
-            disk.kind(),
-            disk.total_space(),
-            disk.available_space(),
-            disk.total_space() - disk.available_space(),
-            disk.mount_point()
-        );
-    }
-    let components = Components::new_with_refreshed_list();
-    for component in &components {
-        if let Some(temperature) = component.temperature() {
-            println!(
-                "Component_Label: {}, Temperature: {}°C",
-                component.label(),
-                temperature
-            );
+        if disk.total_space() > 100 * 1024 * 1024 { // > 100MB
+            total_size += disk.total_space();
+            total_available += disk.available_space();
+            total_used += disk.total_space() - disk.available_space();
         }
     }
     
-    // Berechnungen
-    let total_size = if count > 0 {
-        total_size as f64 // in Bytes
-    } else {
-        // Fallback: Versuche df unter Linux
-        println!("Fallback: Using 'df' command to get disk info.");
+    (total_size as f64, total_used as f64, total_available as f64)
+}
+
 #[cfg(target_os = "linux")]
-        {
+fn get_disk_info_fallback() -> Result<(f64, f64, f64, f64), Box<dyn Error + Send + Sync>> {
     use std::process::Command;
-            if let Ok(output) = Command::new("df")
+    
+    let output = Command::new("df")
         .arg("-B1")
-                .arg("--output=size,used")
-                .output()
-            {
+        .arg("--output=size,used,avail")
+        .output()?;
+        
     let stdout = String::from_utf8_lossy(&output.stdout);
+    let mut total_size = 0u64;
+    let mut total_used = 0u64;
+    let mut total_available = 0u64;
+    let mut count = 0;
+    
     for line in stdout.lines().skip(1) {
         let parts: Vec<&str> = line.split_whitespace().collect();
-                    if parts.len() == 2 {
-                        if let (Ok(size), Ok(used)) =
-                            (parts[0].parse::<u64>(), parts[1].parse::<u64>())
-                        {
+        if parts.len() >= 3 {
+            if let (Ok(size), Ok(used), Ok(avail)) = (
+                parts[0].parse::<u64>(),
+                parts[1].parse::<u64>(),
+                parts[2].parse::<u64>(),
+            ) {
                 total_size += size;
                 total_used += used;
+                total_available += avail;
                 count += 1;
             }
         }
     }
-                total_size as f64 // in Bytes
-            } else {
-                0.0
-            }
-        }
-        #[cfg(not(target_os = "linux"))]
-        {
-            0.0
-        }
-    };
     
-    let usage = if total_size > 0.0 {
+    let usage = if total_size > 0 {
         (total_used as f64 / total_size as f64) * 100.0
     } else {
         0.0
     };
     
-    Ok((
-        total_size,
-        total_used as f64,
-        total_available as f64,
-        usage as f64,
-    )) // Disk-Temp bleibt 0.0 ohne spezielle Hardware
+    Ok((total_size as f64, total_used as f64, total_available as f64, usage))
+}
+
+#[cfg(not(target_os = "linux"))]
+fn get_disk_info_fallback() -> Result<(f64, f64, f64, f64), Box<dyn Error + Send + Sync>> {
+    Ok((0.0, 0.0, 0.0, 0.0))
 }
 
 pub fn _get_disk_temp_for_component(component: &Component) -> Option<f64> {

WatcherAgent/src/hardware/gpu.rs

@@ -2,6 +2,29 @@ use anyhow::Result;
 use nvml_wrapper::Nvml;
 use std::error::Error;
 
+/// # GPU Hardware Module
+///
+/// This module provides GPU information collection for WatcherAgent, including load, temperature, and VRAM statistics.
+///
+/// ## Responsibilities
+/// - **GPU Detection:** Identifies GPU model and capabilities.
+/// - **Metric Collection:** Queries GPU load, temperature, and VRAM usage using NVML (NVIDIA only).
+/// - **Error Handling:** Graceful fallback if GPU or NVML is unavailable.
+///
+/// ## Units
+/// - `current_load`: GPU usage as a percentage (**0.0–100.0**)
+/// - `current_temp`: GPU temperature in **degrees Celsius (°C)**
+/// - `vram_total`: Total VRAM in **bytes**
+/// - `vram_used`: Used VRAM in **bytes**
+///
+/// GPU statistics for the host system.
+///
+/// # Fields
+/// - `name`: GPU model name (string)
+/// - `current_load`: GPU usage as a percentage (**0.0–100.0**)
+/// - `current_temp`: GPU temperature in **degrees Celsius (°C)**
+/// - `vram_total`: Total VRAM in **bytes**
+/// - `vram_used`: Used VRAM in **bytes**
 #[derive(Debug)]
 pub struct GpuInfo {
     pub name: Option<String>,
@@ -11,6 +34,12 @@ pub struct GpuInfo {
     pub vram_used: Option<f64>,
 }
 
+/// Collects GPU information (load, temperature, VRAM) using NVML.
+///
+/// This function attempts to query the first NVIDIA GPU using NVML. If unavailable, it returns a fallback with only the detected GPU name.
+///
+/// # Returns
+/// * `Result<GpuInfo, Box<dyn Error + Send + Sync>>` - GPU statistics or fallback if unavailable.
 pub async fn get_gpu_info() -> Result<GpuInfo, Box<dyn Error + Send + Sync>> {
     match get_gpu_metrics() {
         Ok((gpu_temp, gpu_load, vram_used, vram_total)) => {
@@ -37,6 +66,10 @@ pub async fn get_gpu_info() -> Result<GpuInfo, Box<dyn Error + Send + Sync>> {
     }
 }
 
+/// Queries NVML for GPU metrics: temperature, load, VRAM used/total.
+///
+/// # Returns
+/// * `Result<(f64, f64, f64, f64), Box<dyn Error + Send + Sync>>` - Tuple of (temperature °C, load %, VRAM used bytes, VRAM total bytes).
 pub fn get_gpu_metrics() -> Result<(f64, f64, f64, f64), Box<dyn Error + Send + Sync>> {
     let nvml = Nvml::init();
     if let Ok(nvml) = nvml {

WatcherAgent/src/hardware/memory.rs

@@ -3,25 +3,56 @@ use std::error::Error;
 use anyhow::Result;
 use sysinfo::System;
 
+/// # Memory Hardware Module
+///
+/// This module provides memory information collection for WatcherAgent, including total, used, and free RAM.
+///
+/// ## Responsibilities
+/// - **Memory Detection:** Queries system for total, used, and free RAM.
+/// - **Usage Calculation:** Computes memory usage percentage.
+/// - **Error Handling:** Graceful fallback if metrics are unavailable.
+///
+/// ## Units
+/// - `total`, `used`, `free`: RAM in **bytes**
+///
+/// Memory statistics for the host system.
+///
+/// # Fields
+/// - `total`: Total RAM in **bytes**
+/// - `used`: Used RAM in **bytes**
+/// - `free`: Free RAM in **bytes**
 #[derive(Debug)]
 pub struct MemoryInfo {
-    pub total: Option<f64>,
+    pub total_size: Option<f64>,
     pub used: Option<f64>,
     pub free: Option<f64>,
+    pub current_load: Option<f64>,
 }
 
-pub async fn get_memory_info() -> Result<MemoryInfo> {
+/// Collects memory information (total, used, free RAM).
+///
+/// # Returns
+/// * `Result<MemoryInfo>` - Memory statistics or error if unavailable.
+pub async fn get_memory_info() -> Result<MemoryInfo, Box<dyn Error + Send + Sync>> {
     let mut sys = System::new();
     sys.refresh_memory();
 
     Ok(MemoryInfo {
-        total: Some(sys.total_memory() as f64),
+        total_size: Some(sys.total_memory() as f64),
         used: Some(sys.used_memory() as f64),
         free: Some(sys.free_memory() as f64),
+        current_load: Some(get_memory_usage(&mut sys).unwrap() as f64)
     })
 }
 
-pub fn _get_memory_usage(sys: &mut System) -> Result<f64, Box<dyn Error + Send + Sync>> {
+/// Computes memory usage percentage from sysinfo::System.
+///
+/// # Arguments
+/// * `sys` - Mutable reference to sysinfo::System
+///
+/// # Returns
+/// * `Result<f64, Box<dyn Error + Send + Sync>>` - Memory usage as percentage.
+pub fn get_memory_usage(sys: &mut System) -> Result<f64, Box<dyn Error + Send + Sync>> {
     sys.refresh_memory();
     Ok((sys.used_memory() as f64 / sys.total_memory() as f64) * 100.0)
 }

WatcherAgent/src/hardware/mod.rs

@@ -14,6 +14,23 @@ pub use memory::get_memory_info;
 pub use network::get_network_info;
 pub use network::NetworkMonitor;
 
+/// # Hardware Module
+///
+/// This module aggregates all hardware subsystems for WatcherAgent, providing unified collection and access to CPU, GPU, memory, disk, and network statistics.
+///
+/// ## Responsibilities
+/// - **Subsystem Aggregation:** Combines all hardware modules into a single struct for easy access.
+/// - **Unified Collection:** Provides a single async method to collect all hardware metrics at once.
+///
+/// Aggregated hardware statistics for the host system.
+///
+/// # Fields
+/// - `cpu`: CPU statistics (see [`CpuInfo`])
+/// - `gpu`: GPU statistics (see [`GpuInfo`])
+/// - `memory`: Memory statistics (see [`MemoryInfo`])
+/// - `disk`: Disk statistics (see [`DiskInfo`])
+/// - `network`: Network statistics (see [`NetworkInfo`])
+/// - `network_monitor`: Rolling monitor for network bandwidth
 #[derive(Debug)]
 pub struct HardwareInfo {
     pub cpu: cpu::CpuInfo,
@@ -25,6 +42,10 @@ pub struct HardwareInfo {
 }
 
 impl HardwareInfo {
+    /// Collects all hardware statistics asynchronously.
+    ///
+    /// # Returns
+    /// * `Result<HardwareInfo, Box<dyn Error + Send + Sync>>` - Aggregated hardware statistics or error if any subsystem fails.
     pub async fn collect() -> Result<Self, Box<dyn Error + Send + Sync>> {
         let mut network_monitor = network::NetworkMonitor::new();
         Ok(Self {

WatcherAgent/src/hardware/network.rs

@@ -2,6 +2,24 @@ use std::error::Error;
 use std::result::Result;
 use std::time::Instant;
 
+/// # Network Hardware Module
+///
+/// This module provides network information collection for WatcherAgent, including interface enumeration and bandwidth statistics.
+///
+/// ## Responsibilities
+/// - **Interface Detection:** Lists all network interfaces.
+/// - **Bandwidth Monitoring:** Tracks receive/transmit rates using a rolling monitor.
+/// - **Error Handling:** Graceful fallback if metrics are unavailable.
+///
+/// ## Units
+/// - `rx_rate`, `tx_rate`: Network bandwidth in **bytes per second (B/s)**
+///
+/// Network statistics for the host system.
+///
+/// # Fields
+/// - `interfaces`: List of network interface names (strings)
+/// - `rx_rate`: Receive bandwidth in **bytes per second (B/s)**
+/// - `tx_rate`: Transmit bandwidth in **bytes per second (B/s)**
 #[derive(Debug)]
 pub struct NetworkInfo {
     pub interfaces: Option<Vec<String>>,
@@ -9,6 +27,13 @@ pub struct NetworkInfo {
     pub tx_rate: Option<f64>,
 }
 
+
+/// Rolling monitor for network bandwidth statistics.
+///
+/// # Fields
+/// - `prev_rx`: Previous received bytes
+/// - `prev_tx`: Previous transmitted bytes
+/// - `last_update`: Timestamp of last update
 #[derive(Debug)]
 pub struct NetworkMonitor {
     prev_rx: u64,
@@ -23,6 +48,7 @@ impl Default for NetworkMonitor {
 }
 
 impl NetworkMonitor {
+    /// Creates a new `NetworkMonitor` for bandwidth tracking.
     pub fn new() -> Self {
         Self {
             prev_rx: 0,
@@ -31,6 +57,10 @@ impl NetworkMonitor {
         }
     }
 
+    /// Updates the network usage statistics and returns current rx/tx rates.
+    ///
+    /// # Returns
+    /// * `Result<(f64, f64), Box<dyn Error>>` - Tuple of (rx_rate, tx_rate) in bytes per second.
     pub fn update_usage(&mut self) -> Result<(f64, f64), Box<dyn Error>> {
         let (current_rx, current_tx) = get_network_bytes()?;
         let elapsed = self.last_update.elapsed().as_secs_f64();
@@ -55,6 +85,13 @@ impl NetworkMonitor {
     }
 }
 
+/// Collects network information (interfaces, rx/tx rates) using a monitor.
+///
+/// # Arguments
+/// * `monitor` - Mutable reference to a `NetworkMonitor`
+///
+/// # Returns
+/// * `Result<NetworkInfo, Box<dyn Error>>` - Network statistics or error if unavailable.
 pub async fn get_network_info(monitor: &mut NetworkMonitor) -> Result<NetworkInfo, Box<dyn Error>> {
     let (rx_rate, tx_rate) = monitor.update_usage()?;
     Ok(NetworkInfo {

WatcherAgent/src/main.rs

@@ -1,18 +1,55 @@
-/// WatcherAgent - A Rust-based system monitoring agent
-/// This agent collects hardware metrics and sends them to a backend server.
-/// It supports CPU, GPU, RAM, disk, and network metrics.
+/// # WatcherAgent
+///
+/// **WatcherAgent** is a cross-platform system monitoring agent written in Rust.
+///
+/// ## Overview
+/// This agent collects real-time hardware metrics (CPU, GPU, RAM, disk, network) and communicates with a backend server for registration, reporting, and remote control. It is designed for deployment in environments where automated monitoring and remote management of system resources is required.
+///
+/// ## Features
+/// - **Hardware Metrics:** Collects CPU, GPU, RAM, disk, and network statistics using platform-specific APIs.
+/// - **Docker Integration:** Detects and manages its own Docker container, supports image updates and container restarts.
+/// - **Server Communication:** Registers with a backend server, sends periodic heartbeats, and reports metrics securely.
+/// - **Remote Commands:** Listens for and executes commands from the backend (e.g., update image, restart container, stop agent).
+///
+/// ## Modules
+/// - [`api`]: Handles HTTP communication with the backend server (registration, heartbeat, metrics, commands).
+/// - [`hardware`]: Collects hardware metrics from the host system (CPU, GPU, RAM, disk, network).
+/// - [`metrics`]: Orchestrates metric collection and reporting.
+/// - [`models`]: Defines data structures for server communication and metrics.
+/// - [`docker`]: Integrates with Docker for container management and agent lifecycle.
+///
+/// ## Usage
+/// Run the agent with the backend server URL as an argument:
+/// ```sh
+/// watcheragent <server-url>
+/// ```
+///
+/// The agent will register itself, start collecting metrics, and listen for remote commands.
 pub mod api;
+pub mod docker;
 pub mod hardware;
 pub mod metrics;
 pub mod models;
 
+use bollard::Docker;
 use std::env;
 use std::error::Error;
-use std::marker::Send;
-use std::marker::Sync;
-use std::result::Result;
+use std::sync::Arc;
 use tokio::task::JoinHandle;
 
+/// Awaits a spawned asynchronous task and flattens its nested `Result` type.
+///
+/// This utility is used to handle the result of a `tokio::spawn`ed task that itself returns a `Result`,
+/// propagating any errors from both the task and its execution.
+///
+/// # Type Parameters
+/// * `T` - The type returned by the task on success.
+///
+/// # Arguments
+/// * `handle` - The `JoinHandle` of the spawned task.
+///
+/// # Returns
+/// * `Result<T, Box<dyn Error + Send + Sync>>` - The result of the task, or an error if the task failed or panicked.
 async fn flatten<T>(
     handle: JoinHandle<Result<T, Box<dyn Error + Send + Sync>>>,
 ) -> Result<T, Box<dyn Error + Send + Sync>> {
@@ -23,29 +60,84 @@ async fn flatten<T>(
     }
 }
 
+/// Main entry point for the WatcherAgent application.
+///
+/// This function performs the following steps:
+/// 1. Initializes the Docker client for container management.
+/// 2. Detects the current running image version.
+/// 3. Parses command-line arguments to obtain the backend server URL.
+/// 4. Registers the agent with the backend server and retrieves its server ID and IP address.
+/// 5. Spawns background tasks for:
+///     - Listening for remote commands from the server
+///     - Sending periodic heartbeat signals
+///     - Collecting and reporting hardware metrics
+/// 6. Waits for all background tasks to complete and logs their results.
+///
+/// # Arguments
+/// * `server-url` - The URL of the backend server to register and report metrics to (passed as a command-line argument).
+///
+/// # Errors
+/// Returns an error if registration or any background task fails, or if required arguments are missing.
 #[tokio::main]
 async fn main() -> Result<(), Box<dyn Error + Send + Sync>> {
+    // Parse command-line arguments
     let args: Vec<String> = env::args().collect();
-
-    // args[0] is the binary name, args[1] is the first actual argument
     if args.len() < 2 {
         eprintln!("Usage: {} <server-url>", args[0]);
         return Err("Missing server URL argument".into());
     }
-
     let server_url = &args[1];
     println!("Server URL: {:?}", server_url);
 
-    // Registration
+    // Registration with backend server
     let (server_id, ip) = match api::register_with_server(&server_url).await {
-        Ok((id, ip)) => (id, ip),
+        Ok((id, ip)) => {
+            println!("Registered with server. ID: {}, IP: {}", id, ip);
+            (id, ip)
+        }
         Err(e) => {
             eprintln!("Fehler bei der Registrierung am Server: {e}");
             return Err(e);
         }
     };
 
+    // Initialize Docker (optional - agent can run without Docker)
+    let docker_manager = docker::DockerManager::new_optional();
+
+    // Get current image version
+    let client_version = if let Some(ref docker_manager) = docker_manager {
+        docker_manager.get_client_version().await
+    } else {
+        "unknown".to_string()
+    };
+    println!("Client Version: {}", client_version);
+
+    // Prepare Docker registration DTO
+    let container_dto = if let Some(ref docker_manager) = docker_manager {
+        docker_manager.create_registration_dto().await?
+    } else {
+        models::DockerRegistrationDto {
+            server_id: 0,
+            //container_count: 0, --- IGNORE ---
+            containers: "[]".to_string(),
+        }
+    };
+    let _ =
+        api::broadcast_docker_containers(server_url, server_id, &mut container_dto.clone()).await?;
+
     // Start background tasks
+    // Start server listening for commands (only if Docker is available)
+    let listening_handle = if let Some(ref docker_manager) = docker_manager {
+        tokio::spawn({
+            let docker = docker_manager.docker.clone();
+            let server_url = server_url.to_string();
+            async move { api::listening_to_server(&docker, &server_url).await }
+        })
+    } else {
+        println!("Docker not available, skipping server command listener.");
+        tokio::spawn(async { Ok(()) }) // Dummy task
+    };
+
     // Start heartbeat in background
     let heartbeat_handle = tokio::spawn({
         let ip = ip.clone();
@@ -58,20 +150,23 @@ async fn main() -> Result<(), Box<dyn Error + Send + Sync>> {
     let metrics_handle = tokio::spawn({
         let ip = ip.clone();
         let server_url = server_url.to_string();
+        let docker_manager = docker_manager.as_ref().cloned().unwrap();
         async move {
-            let mut collector = metrics::Collector::new(server_id, ip);
+            let mut collector = metrics::Collector::new(server_id, ip, docker_manager);
             collector.run(&server_url).await
         }
     });
 
-    // Warte auf beide Tasks und prüfe explizit auf Fehler
-    let (heartbeat_handle, metrics_handle) =
-        tokio::try_join!(flatten(heartbeat_handle), flatten(metrics_handle))?;
+    // Wait for all tasks and check for errors
+    let (listening_result, heartbeat_result, metrics_result) = tokio::try_join!(
+        flatten(listening_handle),
+        flatten(heartbeat_handle),
+        flatten(metrics_handle)
+    )?;
 
-    let (heartbeat, metrics) = (heartbeat_handle, metrics_handle);
     println!(
-        "All tasks completed successfully: {:?}, {:?}.",
-        heartbeat, metrics
+        "All tasks completed: listening={:?}, heartbeat={:?}, metrics={:?}",
+        listening_result, heartbeat_result, metrics_result
     );
 
     println!("All tasks completed successfully.");

WatcherAgent/src/metrics.rs

@@ -1,26 +1,66 @@
+/// # Metrics Module
+///
+/// This module orchestrates the collection and reporting of hardware and network metrics for WatcherAgent.
+///
+/// ## Responsibilities
+/// - **Metric Collection:** Gathers real-time statistics from all hardware subsystems (CPU, GPU, RAM, disk, network).
+/// - **Reporting:** Periodically sends metrics to the backend server using the API module.
+/// - **Error Handling:** Robust to hardware failures and network errors, with retry logic and logging.
+///
+/// ## Usage
+/// The [`Collector`] struct is instantiated in the main loop and runs as a background task, continuously collecting and reporting metrics.
 use std::error::Error;
 use std::time::Duration;
 
 use crate::api;
+use crate::docker::DockerManager;
+//use crate::docker::DockerInfo;
 use crate::hardware::network::NetworkMonitor;
 use crate::hardware::HardwareInfo;
-use crate::models::MetricDto;
+use crate::models::{DockerMetricDto, MetricDto};
 
+/// Main orchestrator for hardware and network metric collection and reporting.
+///
+/// The `Collector` struct manages the state required to collect metrics and send them to the backend server. It maintains a network monitor for bandwidth tracking, the agent's server ID, and its IP address.
+///
+/// # Fields
+/// - `network_monitor`: Tracks network usage rates (rx/tx).
+/// - `server_id`: Unique server ID assigned by the backend.
+/// - `ip_address`: IP address of the agent.
 pub struct Collector {
+    docker_manager: DockerManager,
     network_monitor: NetworkMonitor,
-    server_id: i32,
+    server_id: u16,
     ip_address: String,
 }
 
 impl Collector {
-    pub fn new(server_id: i32, ip_address: String) -> Self {
+    /// Creates a new `Collector` instance for metric collection and reporting.
+    ///
+    /// # Arguments
+    /// * `server_id` - The server ID assigned by the backend.
+    /// * `ip_address` - The IP address of the agent.
+    ///
+    /// # Returns
+    /// A new `Collector` ready to collect and report metrics.
+    pub fn new(server_id: u16, ip_address: String, docker_manager: DockerManager) -> Self {
         Self {
+            docker_manager,
             network_monitor: NetworkMonitor::new(),
             server_id,
             ip_address,
         }
     }
 
+    /// Runs the main metrics collection loop, periodically sending metrics to the backend server.
+    ///
+    /// This function continuously collects hardware and network metrics, sends them to the backend, and handles errors gracefully. It uses a configurable interval and retries on failures.
+    ///
+    /// # Arguments
+    /// * `base_url` - The base URL of the backend server.
+    ///
+    /// # Returns
+    /// * `Result<(), Box<dyn Error + Send + Sync>>` - Ok if metrics are sent successfully.
     pub async fn run(&mut self, base_url: &str) -> Result<(), Box<dyn Error + Send + Sync>> {
         loop {
             println!(
@@ -35,11 +75,26 @@ impl Collector {
                     continue;
                 }
             };
+            let docker_metrics = match self.docker_collect().await {
+                Ok(metrics) => metrics,
+                Err(e) => {
+                    eprintln!("Error collecting docker metrics: {}", e);
+                    tokio::time::sleep(Duration::from_secs(10)).await;
+                    continue;
+                }
+            };
             api::send_metrics(base_url, &metrics).await?;
+            api::send_docker_metrics(base_url, &docker_metrics).await?;
             tokio::time::sleep(Duration::from_secs(20)).await;
         }
     }
 
+    /// Collects hardware and network metrics from all subsystems.
+    ///
+    /// This function queries the hardware module for CPU, GPU, RAM, disk, and network statistics, and packages them into a [`MetricDto`] for reporting.
+    ///
+    /// # Returns
+    /// * `Result<MetricDto, Box<dyn Error + Send + Sync>>` - The collected metrics or an error if hardware info is unavailable.
     pub async fn collect(&mut self) -> Result<MetricDto, Box<dyn Error + Send + Sync>> {
         let hardware = match HardwareInfo::collect().await {
             Ok(hw) => hw,
@@ -59,14 +114,24 @@ impl Collector {
             gpu_load: hardware.gpu.current_load.unwrap_or_default(),
             gpu_temp: hardware.gpu.current_temp.unwrap_or_default(),
             gpu_vram_size: hardware.gpu.vram_total.unwrap_or_default(),
-            gpu_vram_usage: hardware.gpu.vram_used.unwrap_or_default(),
-            ram_load: hardware.memory.used.unwrap_or_default(),
-            ram_size: hardware.memory.total.unwrap_or_default(),
-            disk_size: hardware.disk.total.unwrap_or_default(),
-            disk_usage: hardware.disk.used.unwrap_or_default(),
+            gpu_vram_load: hardware.gpu.current_load.unwrap_or_default(),
+            ram_load: hardware.memory.current_load.unwrap_or_default(),
+            ram_size: hardware.memory.total_size.unwrap_or_default(),
+            disk_size: hardware.disk.total_size.unwrap_or_default(),
+            disk_usage: hardware.disk.total_usage.unwrap_or_default(),
             disk_temp: 0.0, // not supported
             net_rx: hardware.network.rx_rate.unwrap_or_default(),
             net_tx: hardware.network.tx_rate.unwrap_or_default(),
         })
     }
+
+    /// NOTE: This is a compilation-safe stub. Implement the Docker collection using your
+    /// DockerManager API and container helpers when available.
+    pub async fn docker_collect(&self) -> Result<DockerMetricDto, Box<dyn Error + Send + Sync>> {
+        let metrics = self.docker_manager.collect_metrics().await?;
+        Ok(DockerMetricDto {
+            server_id: self.server_id,
+            containers: metrics.containers,
+        })
+    }
 }

WatcherAgent/src/models.rs

@@ -1,10 +1,31 @@
+/// # Models Module
+///
+/// This module defines all data structures (DTOs) used for communication between WatcherAgent and the backend server, as well as hardware metrics and Docker container info.
+///
+/// ## Responsibilities
+/// - **DTOs:** Define payloads for registration, metrics, heartbeat, and server commands.
+/// - **Units:** All struct fields are documented with their units for clarity and API compatibility.
+/// - **Docker Info:** Structures for representing Docker container state and statistics.
+///
+/// ## Usage
+/// These types are serialized/deserialized for HTTP communication and used throughout the agent for data exchange.
+use crate::docker::stats;
+
 use serde::{Deserialize, Serialize};
 
-// Data structures matching the C# DTOs
+/// Registration data sent to the backend server.
+///
+/// ## Units
+/// - `id`: Unique server identifier (integer)
+/// - `ip_address`: IPv4 or IPv6 address (string)
+/// - `cpu_type`: CPU model name (string)
+/// - `cpu_cores`: Number of physical CPU cores (integer)
+/// - `gpu_type`: GPU model name (string)
+/// - `ram_size`: Total RAM size in **megabytes (MB)**
 #[derive(Serialize, Debug)]
 pub struct RegistrationDto {
     #[serde(rename = "id")]
-    pub id: i32,
+    pub server_id: u16,
     #[serde(rename = "ipAddress")]
     pub ip_address: String,
     #[serde(rename = "cpuType")]
@@ -17,10 +38,28 @@ pub struct RegistrationDto {
     pub ram_size: f64,
 }
 
+/// Hardware and network metrics data sent to the backend server.
+///
+/// ## Units
+/// - `server_id`: Unique server identifier (integer)
+/// - `ip_address`: IPv4 or IPv6 address (string)
+/// - `cpu_load`: CPU usage as a percentage (**0.0–100.0**)
+/// - `cpu_temp`: CPU temperature in **degrees Celsius (°C)**
+/// - `gpu_load`: GPU usage as a percentage (**0.0–100.0**)
+/// - `gpu_temp`: GPU temperature in **degrees Celsius (°C)**
+/// - `gpu_vram_size`: Total GPU VRAM in **bytes**
+/// - `gpu_vram_load`: GPU Usage of VRAM as a percentage (**0.0–100.0**)
+/// - `ram_load`: RAM usage as a percentage (**0.0–100.0**)
+/// - `ram_size`: Total RAM in **bytes**
+/// - `disk_size`: Total disk size in **bytes**
+/// - `disk_usage`: Used disk space in **bytes**
+/// - `disk_temp`: Disk temperature in **degrees Celsius (°C)** (if available)
+/// - `net_rx`: Network receive rate in **bytes per second (B/s)**
+/// - `net_tx`: Network transmit rate in **bytes per second (B/s)**
 #[derive(Serialize, Debug)]
 pub struct MetricDto {
     #[serde(rename = "serverId")]
-    pub server_id: i32,
+    pub server_id: u16,
     #[serde(rename = "ipAddress")]
     pub ip_address: String,
     #[serde(rename = "cpu_Load")]
@@ -33,8 +72,8 @@ pub struct MetricDto {
     pub gpu_temp: f64,
     #[serde(rename = "gpu_Vram_Size")]
     pub gpu_vram_size: f64,
-    #[serde(rename = "gpu_Vram_Usage")]
-    pub gpu_vram_usage: f64,
+    #[serde(rename = "gpu_Vram_Load")]
+    pub gpu_vram_load: f64,
     #[serde(rename = "ram_Load")]
     pub ram_load: f64,
     #[serde(rename = "ram_Size")]
@@ -51,19 +90,55 @@ pub struct MetricDto {
     pub net_tx: f64,
 }
 
+/// Detailed disk information for each detected disk.
+///
+/// ## Units
+/// - `disk_total_space`: Total disk space in **bytes**
+/// - `disk_available_space`: Available disk space in **bytes**
+/// - `disk_used_space`: Used disk space in **bytes**
+/// - `component_disk_temperature`: Disk temperature in **degrees Celsius (°C)**
+#[derive(Serialize, Debug)]
+pub struct DiskInfoDetailed {
+    pub disk_name: String,
+    pub disk_kind: String,
+    pub disk_total_space: f64,
+    pub disk_available_space: f64,
+    pub disk_used_space: f64,
+    pub disk_mount_point: String,
+    pub component_disk_label: String,
+    pub component_disk_temperature: f32,
+}
+
+/// Response containing server ID and IP address.
+///
+/// ## Units
+/// - `id`: Unique server identifier (integer)
+/// - `ip_address`: IPv4 or IPv6 address (string)
 #[derive(Deserialize)]
 pub struct IdResponse {
-    pub id: i32,
+    pub id: u16,
     #[serde(rename = "ipAddress")]
     pub ip_address: String,
 }
 
+/// Heartbeat message data sent to the backend server.
+///
+/// ## Units
+/// - `ip_address`: IPv4 or IPv6 address (string)
 #[derive(Serialize)]
 pub struct HeartbeatDto {
     #[serde(rename = "IpAddress")]
     pub ip_address: String,
 }
 
+/// Hardware summary data for diagnostics and registration.
+///
+/// ## Units
+/// - `cpu_type`: CPU model name (string)
+/// - `cpu_cores`: Number of physical CPU cores (integer)
+/// - `gpu_type`: GPU model name (string)
+/// - `ram_size`: Total RAM size in **megabytes (MB)**
+/// - `ip_address`: IPv4 or IPv6 address (string)
 #[derive(Serialize, Debug)]
 pub struct HardwareDto {
     pub cpu_type: String,
@@ -72,3 +147,119 @@ pub struct HardwareDto {
     pub ram_size: f64,
     pub ip_address: String,
 }
+
+/// Command message received from the backend server.
+///
+/// ## Fields
+/// - `message_type`: Type of command (e.g., "update_image", "restart_container", "stop_agent")
+/// - `data`: Command payload (arbitrary JSON)
+/// - `message_id`: Unique identifier for acknowledgment
+#[derive(Debug, Deserialize, Clone)]
+pub struct ServerMessage {
+    // Define your message structure here
+    pub message_type: String,
+    pub data: serde_json::Value,
+    pub message_id: String, // Add an ID for acknowledgment
+}
+
+/// Acknowledgment payload sent to the backend server for command messages.
+///
+/// ## Fields
+/// - `message_id`: Unique identifier of the acknowledged message
+/// - `status`: Status string ("success", "error", etc.)
+/// - `details`: Additional details or error messages
+#[derive(Debug, Serialize, Clone)]
+pub struct Acknowledgment {
+    pub message_id: String,
+    pub status: String, // "success" or "error"
+    pub details: String,
+}
+
+/// Docker container information for agent and managed containers.
+///
+/// ## Fields
+/// - `ID`: Container ID (first 12 hex digits, integer)
+/// - `image`: Docker image name (string)
+/// - `Name`: Container name (string)
+/// - `Status`: Container status ("running", "stopped", etc.)
+/// - `_net_in`: Network receive rate in **bytes per second (B/s)**
+/// - `_net_out`: Network transmit rate in **bytes per second (B/s)**
+/// - `_cpu_load`: CPU usage as a percentage (**0.0–100.0**)
+#[derive(Debug, Serialize, Clone)]
+pub struct DockerRegistrationDto {
+    /// Unique server identifier (integer)
+    pub server_id: u16,
+    /// Number of currently running containers
+    //      pub container_count: usize, --- IGNORE ---
+    /// json stringified array of DockerContainer
+    ///
+    /// ## Json Example
+    /// json format: [{"id":"234dsf234","image":"nginx:latest","name":"webserver"},...]
+    ///
+    /// ## Fields
+    /// id: unique container ID (first 12 hex digits)
+    /// image: docker image name
+    /// name: container name
+    pub containers: String, // Vec<DockerContainer>,
+}
+
+#[derive(Debug, Serialize, Clone)]
+pub struct DockerMetricDto {
+    pub server_id: u16,
+    /// json stringified array of DockerContainer
+    ///
+    /// ## Json Example
+    /// json format: [{"id":"234dsf234","status":"running","image":"nginx:latest","name":"webserver","network":{"net_in":1024,"net_out":2048},"cpu":{"cpu_load":12.5},"ram":{"ram_load":10.0}},...]
+    ///
+    /// ## Fields
+    /// id: unique container ID (first 12 hex digits)
+    /// status: "running";"stopped";others
+    /// image: docker image name
+    /// name: container name
+    /// network: network stats
+    /// cpu: cpu stats
+    /// ram: ram stats
+    pub containers: String, // Vec<DockerContainerInfo>,
+}
+
+#[derive(Debug, Serialize, Clone)]
+
+pub struct DockerCollectMetricDto {
+    pub id: String,
+    pub cpu: DockerContainerCpuDto,
+    pub ram: DockerContainerRamDto,
+    pub network: DockerContainerNetworkDto,
+}
+
+#[derive(Debug, Serialize, Clone)]
+pub struct DockerContainerCpuDto {
+    pub cpu_load: Option<f64>,
+}
+
+#[derive(Debug, Serialize, Clone)]
+pub struct DockerContainerRamDto {
+    pub cpu_load: Option<f64>,
+}
+
+#[derive(Debug, Serialize, Clone)]
+
+pub struct DockerContainerNetworkDto {
+    pub net_in: Option<f64>,
+    pub net_out: Option<f64>,
+}
+
+#[derive(Debug, Serialize, Clone)]
+pub struct DockerContainerInfo {
+    pub container: Option<DockerContainer>,
+    pub status: Option<String>, // "running";"stopped";others
+    pub network: Option<stats::ContainerNetworkInfo>,
+    pub cpu: Option<stats::ContainerCpuInfo>,
+    pub ram: Option<stats::ContainerMemoryInfo>,
+}
+
+#[derive(Debug, Serialize, Clone)]
+pub struct DockerContainer {
+    pub id: String,
+    pub image: Option<String>,
+    pub name: Option<String>,
+}

docker-compose.yaml

@@ -0,0 +1,23 @@
+watcher-agent:
+    image: git.triggermeelmo.com/donpat1to/watcher-agent:development
+    container_name: watcher-agent
+    restart: always
+    privileged: true  # Grants full hardware access (use with caution)
+    env_file: .env
+    pid: "host"
+    volumes:
+      # Mount critical system paths for hardware monitoring
+      - /sys:/sys:ro                                # CPU/GPU temps, sensors
+      - /proc:/proc                                 # Process/CPU stats
+      - /dev:/dev:ro                                # Disk/GPU device access
+      - /var/run/docker.sock:/var/run/docker.sock   # Docker API access
+      - /:/root:ro                                  # Access to for df-command
+      # Application volumes
+      - ./config:/app/config:ro
+      - ./logs:/app/logs
+    network_mode: host  # Uses host network (for correct IP/interface detection)
+    healthcheck:
+      test: ["CMD", "/usr/local/bin/WatcherAgent", "healthcheck"]
+      interval: 30s
+      timeout: 3s
+      retries: 3