feat(application): HealthMonitor service and hardware integration test

Add HealthMonitor service for tracking system health status with
comprehensive state transition logic and thread-safe operations.
Includes 16 unit tests covering all functionality including concurrent
access scenarios.

Add optional Modbus hardware integration tests with 7 test cases for
real device testing. Tests are marked as ignored and can be run with

Ref: T034, T039, T040 (specs/001-modbus-relay-control/tasks.org)

backend/src/application/health/health_monitor.rs

@@ -0,0 +1,331 @@
+//! Health monitoring service for tracking system health status.
+//!
+//! The `HealthMonitor` service tracks the health status of the Modbus relay controller
+//! by monitoring consecutive errors and transitions between healthy, degraded, and unhealthy states.
+//! This service implements the health monitoring requirements from FR-020 and FR-021.
+
+use std::sync::Arc;
+use tokio::sync::Mutex;
+
+use crate::domain::health::HealthStatus;
+
+/// Health monitor service for tracking system health status.
+///
+/// The `HealthMonitor` service maintains the current health status and provides
+/// methods to track successes and failures, transitioning between states according
+/// to the business rules defined in the domain layer.
+#[derive(Debug, Clone)]
+pub struct HealthMonitor {
+    /// Current health status, protected by a mutex for thread-safe access.
+    current_status: Arc<Mutex<HealthStatus>>,
+}
+
+impl HealthMonitor {
+    /// Creates a new `HealthMonitor` with initial `Healthy` status.
+    #[must_use]
+    pub fn new() -> Self {
+        Self::with_initial_status(HealthStatus::Healthy)
+    }
+
+    /// Creates a new `HealthMonitor` with the specified initial status.
+    #[must_use]
+    pub fn with_initial_status(initial_status: HealthStatus) -> Self {
+        Self {
+            current_status: Arc::new(Mutex::new(initial_status)),
+        }
+    }
+
+    /// Records a successful operation, potentially transitioning to `Healthy` status.
+    ///
+    /// This method transitions the health status according to the following rules:
+    /// - If currently `Healthy`: remains `Healthy`
+    /// - If currently `Degraded`: transitions to `Healthy` (recovery)
+    /// - If currently `Unhealthy`: transitions to `Healthy` (recovery)
+    ///
+    /// # Returns
+    ///
+    /// The new health status after recording the success.
+    pub async fn track_success(&self) -> HealthStatus {
+        let mut status = self.current_status.lock().await;
+        let new_status = status.clone().record_success();
+        *status = new_status.clone();
+        new_status
+    }
+
+    /// Records a failed operation, potentially transitioning to `Degraded` or `Unhealthy` status.
+    ///
+    /// This method transitions the health status according to the following rules:
+    /// - If currently `Healthy`: transitions to `Degraded` with 1 consecutive error
+    /// - If currently `Degraded`: increments consecutive error count
+    /// - If currently `Unhealthy`: remains `Unhealthy`
+    ///
+    /// # Returns
+    ///
+    /// The new health status after recording the failure.
+    pub async fn track_failure(&self) -> HealthStatus {
+        let mut status = self.current_status.lock().await;
+        let new_status = status.clone().record_error();
+        *status = new_status.clone();
+        new_status
+    }
+
+    /// Marks the system as unhealthy with the specified reason.
+    ///
+    /// This method immediately transitions to `Unhealthy` status regardless of
+    /// the current status, providing a way to explicitly mark critical failures.
+    ///
+    /// # Parameters
+    ///
+    /// - `reason`: Human-readable description of the failure reason.
+    ///
+    /// # Returns
+    ///
+    /// The new `Unhealthy` health status.
+    pub async fn mark_unhealthy(&self, reason: impl Into<String>) -> HealthStatus {
+        let mut status = self.current_status.lock().await;
+        let new_status = status.clone().mark_unhealthy(reason);
+        *status = new_status.clone();
+        new_status
+    }
+
+    /// Gets the current health status without modifying it.
+    ///
+    /// # Returns
+    ///
+    /// The current health status.
+    pub async fn get_status(&self) -> HealthStatus {
+        let status = self.current_status.lock().await;
+        status.clone()
+    }
+
+    /// Checks if the system is currently healthy.
+    ///
+    /// # Returns
+    ///
+    /// `true` if the current status is `Healthy`, `false` otherwise.
+    pub async fn is_healthy(&self) -> bool {
+        let status = self.current_status.lock().await;
+        status.is_healthy()
+    }
+
+    /// Checks if the system is currently degraded.
+    ///
+    /// # Returns
+    ///
+    /// `true` if the current status is `Degraded`, `false` otherwise.
+    pub async fn is_degraded(&self) -> bool {
+        let status = self.current_status.lock().await;
+        status.is_degraded()
+    }
+
+    /// Checks if the system is currently unhealthy.
+    ///
+    /// # Returns
+    ///
+    /// `true` if the current status is `Unhealthy`, `false` otherwise.
+    pub async fn is_unhealthy(&self) -> bool {
+        let status = self.current_status.lock().await;
+        status.is_unhealthy()
+    }
+}
+
+impl Default for HealthMonitor {
+    fn default() -> Self {
+        Self::new()
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[tokio::test]
+    async fn test_health_monitor_initial_state() {
+        let monitor = HealthMonitor::new();
+        let status = monitor.get_status().await;
+        assert!(status.is_healthy());
+    }
+
+    #[tokio::test]
+    async fn test_health_monitor_with_initial_status() {
+        let initial_status = HealthStatus::degraded(3);
+        let monitor = HealthMonitor::with_initial_status(initial_status.clone());
+        let status = monitor.get_status().await;
+        assert_eq!(status, initial_status);
+    }
+
+    #[tokio::test]
+    async fn test_track_success_from_healthy() {
+        let monitor = HealthMonitor::new();
+        let status = monitor.track_success().await;
+        assert!(status.is_healthy());
+    }
+
+    #[tokio::test]
+    async fn test_track_success_from_degraded() {
+        let monitor = HealthMonitor::with_initial_status(HealthStatus::degraded(5));
+        let status = monitor.track_success().await;
+        assert!(status.is_healthy());
+    }
+
+    #[tokio::test]
+    async fn test_track_success_from_unhealthy() {
+        let monitor = HealthMonitor::with_initial_status(HealthStatus::unhealthy("Test failure"));
+        let status = monitor.track_success().await;
+        assert!(status.is_healthy());
+    }
+
+    #[tokio::test]
+    async fn test_track_failure_from_healthy() {
+        let monitor = HealthMonitor::new();
+        let status = monitor.track_failure().await;
+        assert!(status.is_degraded());
+        assert_eq!(status, HealthStatus::degraded(1));
+    }
+
+    #[tokio::test]
+    async fn test_track_failure_from_degraded() {
+        let monitor = HealthMonitor::with_initial_status(HealthStatus::degraded(2));
+        let status = monitor.track_failure().await;
+        assert!(status.is_degraded());
+        assert_eq!(status, HealthStatus::degraded(3));
+    }
+
+    #[tokio::test]
+    async fn test_track_failure_from_unhealthy() {
+        let monitor =
+            HealthMonitor::with_initial_status(HealthStatus::unhealthy("Critical failure"));
+        let status = monitor.track_failure().await;
+        assert!(status.is_unhealthy());
+        assert_eq!(status, HealthStatus::unhealthy("Critical failure"));
+    }
+
+    #[tokio::test]
+    async fn test_mark_unhealthy() {
+        let monitor = HealthMonitor::new();
+        let status = monitor.mark_unhealthy("Device disconnected").await;
+        assert!(status.is_unhealthy());
+        assert_eq!(status, HealthStatus::unhealthy("Device disconnected"));
+    }
+
+    #[tokio::test]
+    async fn test_mark_unhealthy_overwrites_previous() {
+        let monitor = HealthMonitor::with_initial_status(HealthStatus::degraded(3));
+        let status = monitor.mark_unhealthy("New failure").await;
+        assert!(status.is_unhealthy());
+        assert_eq!(status, HealthStatus::unhealthy("New failure"));
+    }
+
+    #[tokio::test]
+    async fn test_get_status() {
+        let monitor = HealthMonitor::with_initial_status(HealthStatus::degraded(2));
+        let status = monitor.get_status().await;
+        assert_eq!(status, HealthStatus::degraded(2));
+    }
+
+    #[tokio::test]
+    async fn test_is_healthy() {
+        let healthy_monitor = HealthMonitor::new();
+        assert!(healthy_monitor.is_healthy().await);
+
+        let degraded_monitor = HealthMonitor::with_initial_status(HealthStatus::degraded(1));
+        assert!(!degraded_monitor.is_healthy().await);
+
+        let unhealthy_monitor =
+            HealthMonitor::with_initial_status(HealthStatus::unhealthy("Failure"));
+        assert!(!unhealthy_monitor.is_healthy().await);
+    }
+
+    #[tokio::test]
+    async fn test_is_degraded() {
+        let healthy_monitor = HealthMonitor::new();
+        assert!(!healthy_monitor.is_degraded().await);
+
+        let degraded_monitor = HealthMonitor::with_initial_status(HealthStatus::degraded(1));
+        assert!(degraded_monitor.is_degraded().await);
+
+        let unhealthy_monitor =
+            HealthMonitor::with_initial_status(HealthStatus::unhealthy("Failure"));
+        assert!(!unhealthy_monitor.is_degraded().await);
+    }
+
+    #[tokio::test]
+    async fn test_is_unhealthy() {
+        let healthy_monitor = HealthMonitor::new();
+        assert!(!healthy_monitor.is_unhealthy().await);
+
+        let degraded_monitor = HealthMonitor::with_initial_status(HealthStatus::degraded(1));
+        assert!(!degraded_monitor.is_unhealthy().await);
+
+        let unhealthy_monitor =
+            HealthMonitor::with_initial_status(HealthStatus::unhealthy("Failure"));
+        assert!(unhealthy_monitor.is_unhealthy().await);
+    }
+
+    #[tokio::test]
+    async fn test_state_transitions_sequence() {
+        let monitor = HealthMonitor::new();
+
+        // Start healthy
+        assert!(monitor.is_healthy().await);
+
+        // First failure -> Degraded with 1 error
+        let status = monitor.track_failure().await;
+        assert!(status.is_degraded());
+        assert_eq!(status, HealthStatus::degraded(1));
+
+        // Second failure -> Degraded with 2 errors
+        let status = monitor.track_failure().await;
+        assert_eq!(status, HealthStatus::degraded(2));
+
+        // Third failure -> Degraded with 3 errors
+        let status = monitor.track_failure().await;
+        assert_eq!(status, HealthStatus::degraded(3));
+
+        // Recovery -> Healthy
+        let status = monitor.track_success().await;
+        assert!(status.is_healthy());
+
+        // Another failure -> Degraded with 1 error
+        let status = monitor.track_failure().await;
+        assert_eq!(status, HealthStatus::degraded(1));
+
+        // Mark as unhealthy -> Unhealthy
+        let status = monitor.mark_unhealthy("Critical error").await;
+        assert!(status.is_unhealthy());
+
+        // Recovery from unhealthy -> Healthy
+        let status = monitor.track_success().await;
+        assert!(status.is_healthy());
+    }
+
+    #[tokio::test]
+    async fn test_concurrent_access() {
+        let monitor = HealthMonitor::new();
+
+        // Create multiple tasks that access the monitor concurrently
+        // We need to clone the monitor for each task since tokio::spawn requires 'static
+        let monitor1 = monitor.clone();
+        let monitor2 = monitor.clone();
+        let monitor3 = monitor.clone();
+        let monitor4 = monitor.clone();
+
+        let task1 = tokio::spawn(async move { monitor1.track_failure().await });
+        let task2 = tokio::spawn(async move { monitor2.track_failure().await });
+        let task3 = tokio::spawn(async move { monitor3.track_success().await });
+        let task4 = tokio::spawn(async move { monitor4.get_status().await });
+
+        // Wait for all tasks to complete
+        let (result1, result2, result3, result4) = tokio::join!(task1, task2, task3, task4);
+
+        // All operations should complete without panicking
+        result1.expect("Task should complete successfully");
+        result2.expect("Task should complete successfully");
+        result3.expect("Task should complete successfully");
+        result4.expect("Task should complete successfully");
+
+        // Final status should be healthy (due to the success operation)
+        let final_status = monitor.get_status().await;
+        assert!(final_status.is_healthy());
+    }
+}

backend/src/application/health/mod.rs

@@ -0,0 +1,6 @@
+//! Health monitoring application layer.
+//!
+//! This module contains the health monitoring service that tracks the system's
+//! health status and manages state transitions between healthy, degraded, and unhealthy states.
+
+pub mod health_monitor;

backend/src/application/mod.rs

@@ -11,6 +11,11 @@
 //! - **Use case driven**: Each module represents a specific business use case
 //! - **Testable in isolation**: Can be tested with mock infrastructure implementations
 //!
+//! # Submodules
+//!
+//! - `health`: Health monitoring service
+//!   - `health_monitor`: Tracks system health status and state transitions
+//!
 //! # Planned Submodules
 //!
 //! - `relay`: Relay control use cases
@@ -58,3 +63,5 @@
 //! - Architecture: `specs/constitution.md` - Hexagonal Architecture principles
 //! - Use cases: `specs/001-modbus-relay-control/plan.md` - Implementation plan
 //! - Domain types: [`crate::domain`] - Domain entities and value objects
+
+pub mod health;

backend/src/infrastructure/modbus/client_test.rs

@@ -10,6 +10,10 @@ use super::*;
 mod t025a_connection_setup_tests {
     use super::*;
 
+    static HOST: &str = "192.168.1.200";
+    static PORT: u16 = 502;
+    static SLAVE_ID: u8 = 1;
+
     /// T025a Test 1: `new()` with valid config connects successfully
     ///
     /// This test verifies that `ModbusRelayController::new()` can establish
@@ -21,13 +25,10 @@ mod t025a_connection_setup_tests {
     #[ignore = "Requires running Modbus TCP server"]
     async fn test_new_with_valid_config_connects_successfully() {
         // Arrange: Use localhost test server
-        let host = "127.0.0.1";
-        let port = 5020; // Test Modbus TCP port
-        let slave_id = 1;
         let timeout_secs = 5;
 
         // Act: Attempt to create controller
-        let result = ModbusRelayController::new(host, port, slave_id, timeout_secs).await;
+        let result = ModbusRelayController::new(HOST, PORT, SLAVE_ID, timeout_secs).await;
 
         // Assert: Connection should succeed
         assert!(
@@ -45,12 +46,10 @@ mod t025a_connection_setup_tests {
     async fn test_new_with_invalid_host_returns_connection_error() {
         // Arrange: Use invalid host format
         let host = "not a valid host!!!";
-        let port = 502;
-        let slave_id = 1;
         let timeout_secs = 5;
 
         // Act: Attempt to create controller
-        let result = ModbusRelayController::new(host, port, slave_id, timeout_secs).await;
+        let result = ModbusRelayController::new(host, PORT, SLAVE_ID, timeout_secs).await;
 
         // Assert: Should return ConnectionError
         assert!(result.is_err(), "Expected ConnectionError for invalid host");
@@ -74,13 +73,11 @@ mod t025a_connection_setup_tests {
     async fn test_new_with_unreachable_host_returns_connection_error() {
         // Arrange: Use localhost with a closed port (port 1 is typically closed)
         // This gives instant "connection refused" instead of waiting for TCP timeout
-        let host = "127.0.0.1";
         let port = 1; // Closed port for instant connection failure
-        let slave_id = 1;
         let timeout_secs = 1;
 
         // Act: Attempt to create controller
-        let result = ModbusRelayController::new(host, port, slave_id, timeout_secs).await;
+        let result = ModbusRelayController::new(HOST, port, SLAVE_ID, timeout_secs).await;
 
         // Assert: Should return ConnectionError
         assert!(
@@ -100,13 +97,10 @@ mod t025a_connection_setup_tests {
     #[ignore = "Requires running Modbus TCP server or refactoring to expose timeout"]
     async fn test_new_stores_correct_timeout_duration() {
         // Arrange
-        let host = "127.0.0.1";
-        let port = 5020;
-        let slave_id = 1;
         let timeout_secs = 10;
 
         // Act
-        let controller = ModbusRelayController::new(host, port, slave_id, timeout_secs)
+        let controller = ModbusRelayController::new(HOST, PORT, SLAVE_ID, timeout_secs)
             .await
             .expect("Failed to create controller");
 
@@ -137,6 +131,10 @@ mod t025b_read_coils_timeout_tests {
         types::RelayId,
     };
 
+    static HOST: &str = "192.168.1.200";
+    static PORT: u16 = 502;
+    static SLAVE_ID: u8 = 1;
+
     /// T025b Test 1: `read_coils_with_timeout()` returns coil values on success
     ///
     /// This test verifies that reading coils succeeds when the Modbus server
@@ -147,7 +145,7 @@ mod t025b_read_coils_timeout_tests {
     #[ignore = "Requires running Modbus TCP server with known state"]
     async fn test_read_coils_returns_coil_values_on_success() {
         // Arrange: Connect to test server
-        let controller = ModbusRelayController::new("127.0.0.1", 5020, 1, 5)
+        let controller = ModbusRelayController::new(HOST, PORT, SLAVE_ID, 5)
             .await
             .expect("Failed to connect to test server");
 
@@ -251,6 +249,10 @@ mod t025c_write_single_coil_timeout_tests {
         types::{RelayId, RelayState},
     };
 
+    static HOST: &str = "192.168.1.200";
+    static PORT: u16 = 502;
+    static SLAVE_ID: u8 = 1;
+
     /// T025c Test 1: `write_single_coil_with_timeout()` succeeds for valid write
     ///
     /// This test verifies that writing to a coil succeeds when the Modbus server
@@ -261,7 +263,7 @@ mod t025c_write_single_coil_timeout_tests {
     #[ignore = "Requires running Modbus TCP server"]
     async fn test_write_single_coil_succeeds_for_valid_write() {
         // Arrange: Connect to test server
-        let controller = ModbusRelayController::new("127.0.0.1", 5020, 1, 5)
+        let controller = ModbusRelayController::new(HOST, PORT, SLAVE_ID, 5)
             .await
             .expect("Failed to connect to test server");
 
@@ -336,6 +338,10 @@ mod t025d_read_relay_state_tests {
         types::{RelayId, RelayState},
     };
 
+    static HOST: &str = "192.168.1.200";
+    static PORT: u16 = 502;
+    static SLAVE_ID: u8 = 1;
+
     /// T025d Test 1: `read_relay_state(RelayId(1))` returns On when coil is true
     ///
     /// This test verifies that a true coil value is correctly converted to `RelayState::On`.
@@ -409,7 +415,7 @@ mod t025d_read_relay_state_tests {
     #[ignore = "Requires Modbus server with specific relay states"]
     async fn test_read_state_correctly_maps_relay_id_to_modbus_address() {
         // Arrange: Connect to test server with known relay states
-        let controller = ModbusRelayController::new("127.0.0.1", 5020, 1, 5)
+        let controller = ModbusRelayController::new(HOST, PORT, SLAVE_ID, 5)
             .await
             .expect("Failed to connect to test server");
 
@@ -434,6 +440,10 @@ mod t025e_write_relay_state_tests {
         types::{RelayId, RelayState},
     };
 
+    static HOST: &str = "192.168.1.200";
+    static PORT: u16 = 502;
+    static SLAVE_ID: u8 = 1;
+
     /// T025e Test 1: `write_relay_state(RelayId(1)`, `RelayState::On`) writes true to coil
     ///
     /// This test verifies that `RelayState::On` is correctly converted to a true coil value.
@@ -441,7 +451,7 @@ mod t025e_write_relay_state_tests {
     #[ignore = "Requires Modbus server that can verify written values"]
     async fn test_write_state_on_writes_true_to_coil() {
         // Arrange: Connect to test server
-        let controller = ModbusRelayController::new("127.0.0.1", 5020, 1, 5)
+        let controller = ModbusRelayController::new(HOST, PORT, SLAVE_ID, 5)
             .await
             .expect("Failed to connect to test server");
 
@@ -475,7 +485,7 @@ mod t025e_write_relay_state_tests {
     #[ignore = "Requires Modbus server that can verify written values"]
     async fn test_write_state_off_writes_false_to_coil() {
         // Arrange: Connect to test server
-        let controller = ModbusRelayController::new("127.0.0.1", 5020, 1, 5)
+        let controller = ModbusRelayController::new(HOST, PORT, SLAVE_ID, 5)
             .await
             .expect("Failed to connect to test server");
 
@@ -509,7 +519,7 @@ mod t025e_write_relay_state_tests {
     #[ignore = "Requires Modbus server"]
     async fn test_write_state_correctly_maps_relay_id_to_modbus_address() {
         // Arrange: Connect to test server
-        let controller = ModbusRelayController::new("127.0.0.1", 5020, 1, 5)
+        let controller = ModbusRelayController::new(HOST, PORT, SLAVE_ID, 5)
             .await
             .expect("Failed to connect to test server");
 
@@ -537,7 +547,7 @@ mod t025e_write_relay_state_tests {
     #[ignore = "Requires Modbus server"]
     async fn test_write_state_can_toggle_relay_multiple_times() {
         // Arrange: Connect to test server
-        let controller = ModbusRelayController::new("127.0.0.1", 5020, 1, 5)
+        let controller = ModbusRelayController::new(HOST, PORT, SLAVE_ID, 5)
             .await
             .expect("Failed to connect to test server");
 
@@ -571,12 +581,16 @@ mod t025e_write_relay_state_tests {
 mod write_all_states_validation_tests {
     use super::*;
 
+    static HOST: &str = "192.168.1.200";
+    static PORT: u16 = 502;
+    static SLAVE_ID: u8 = 1;
+
     /// Test: `write_all_states()` returns `InvalidInput` when given 0 states
     #[tokio::test]
     #[ignore = "Requires Modbus server"]
     async fn test_write_all_states_with_empty_vector_returns_invalid_input() {
         // Arrange: Connect to test server
-        let controller = ModbusRelayController::new("127.0.0.1", 5020, 1, 5)
+        let controller = ModbusRelayController::new(HOST, PORT, SLAVE_ID, 5)
             .await
             .expect("Failed to connect to test server");
 
@@ -596,7 +610,7 @@ mod write_all_states_validation_tests {
     #[ignore = "Requires Modbus server"]
     async fn test_write_all_states_with_7_states_returns_invalid_input() {
         // Arrange: Connect to test server
-        let controller = ModbusRelayController::new("127.0.0.1", 5020, 1, 5)
+        let controller = ModbusRelayController::new(HOST, PORT, SLAVE_ID, 5)
             .await
             .expect("Failed to connect to test server");
 
@@ -626,7 +640,7 @@ mod write_all_states_validation_tests {
     #[ignore = "Requires Modbus server"]
     async fn test_write_all_states_with_9_states_returns_invalid_input() {
         // Arrange: Connect to test server
-        let controller = ModbusRelayController::new("127.0.0.1", 5020, 1, 5)
+        let controller = ModbusRelayController::new(HOST, PORT, SLAVE_ID, 5)
             .await
             .expect("Failed to connect to test server");
 
@@ -656,7 +670,7 @@ mod write_all_states_validation_tests {
     #[ignore = "Requires Modbus server"]
     async fn test_write_all_states_with_8_states_succeeds() {
         // Arrange: Connect to test server
-        let controller = ModbusRelayController::new("127.0.0.1", 5020, 1, 5)
+        let controller = ModbusRelayController::new(HOST, PORT, SLAVE_ID, 5)
             .await
             .expect("Failed to connect to test server");