fix: added example of usage, fixed formatting

* define Ntfy ingress (naive implementation) based on current target
* use patched Ntfy Helm Chart
* create Ntfy main user only if needed
* add info logs
* better error bubbling
* instrument feature installations
* upgrade prometheus alerting charts if already installed
* harmony_composer params to control deployment `target` and `profile`

Co-authored-by: Ian Letourneau <letourneau.ian@gmail.com>
Co-authored-by: Jean-Gabriel Gill-Couture <jg@nationtech.io>
Reviewed-on: #107

.gitea/workflows/check.yml

@@ -9,7 +9,7 @@ jobs:
   check:
     runs-on: docker
     container:
-      image: hub.nationtech.io/harmony/harmony_composer:latest@sha256:eb0406fcb95c63df9b7c4b19bc50ad7914dd8232ce98e9c9abef628e07c69386
+      image: hub.nationtech.io/harmony/harmony_composer:latest
     steps:
       - name: Checkout code
         uses: actions/checkout@v4

.gitea/workflows/harmony_composer.yaml

@@ -7,7 +7,7 @@ on:
 jobs:
   package_harmony_composer:
     container:
-      image: hub.nationtech.io/harmony/harmony_composer:latest@sha256:eb0406fcb95c63df9b7c4b19bc50ad7914dd8232ce98e9c9abef628e07c69386
+      image: hub.nationtech.io/harmony/harmony_composer:latest
     runs-on: dind
     steps:
       - name: Checkout code

Cargo.lock

@@ -96,6 +96,12 @@ dependencies = [
  "libc",
 ]
 
+[[package]]
+name = "ansi_term"
+version = "0.10.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6b3568b48b7cefa6b8ce125f9bb4989e52fbcc29ebea88df04cc7c5f12f70455"
+
 [[package]]
 name = "anstream"
 version = "0.6.19"
@@ -1259,6 +1265,18 @@ dependencies = [
 name = "example"
 version = "0.0.0"
 
+[[package]]
+name = "example-application-monitoring-with-tenant"
+version = "0.1.0"
+dependencies = [
+ "env_logger",
+ "harmony",
+ "harmony_cli",
+ "logging",
+ "tokio",
+ "url",
+]
+
 [[package]]
 name = "example-cli"
 version = "0.1.0"
@@ -1779,6 +1797,7 @@ dependencies = [
  "k3d-rs",
  "k8s-openapi",
  "kube",
+ "kube-derive",
  "lazy_static",
  "libredfish",
  "log",
@@ -1791,6 +1810,7 @@ dependencies = [
  "reqwest 0.11.27",
  "russh",
  "rust-ipmi",
+ "schemars 0.8.22",
  "semver",
  "serde",
  "serde-value",
@@ -2669,6 +2689,7 @@ dependencies = [
  "k8s-openapi",
  "kube-client",
  "kube-core",
+ "kube-derive",
  "kube-runtime",
 ]
 
@@ -2722,12 +2743,27 @@ dependencies = [
  "http 1.3.1",
  "json-patch",
  "k8s-openapi",
+ "schemars 0.8.22",
  "serde",
  "serde-value",
  "serde_json",
  "thiserror 2.0.12",
 ]
 
+[[package]]
+name = "kube-derive"
+version = "1.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "079fc8c1c397538628309cfdee20696ebdcc26745f9fb17f89b78782205bd995"
+dependencies = [
+ "darling",
+ "proc-macro2",
+ "quote",
+ "serde",
+ "serde_json",
+ "syn",
+]
+
 [[package]]
 name = "kube-runtime"
 version = "1.1.0"
@@ -2843,6 +2879,15 @@ dependencies = [
  "log",
 ]
 
+[[package]]
+name = "logging"
+version = "0.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "461a8beca676e8ab1bd468c92e9b4436d6368e11e96ae038209e520cfe665e46"
+dependencies = [
+ "ansi_term",
+]
+
 [[package]]
 name = "lru"
 version = "0.12.5"
@@ -4140,6 +4185,18 @@ dependencies = [
  "windows-sys 0.59.0",
 ]
 
+[[package]]
+name = "schemars"
+version = "0.8.22"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3fbf2ae1b8bc8e02df939598064d22402220cd5bbcca1c76f7d6a310974d5615"
+dependencies = [
+ "dyn-clone",
+ "schemars_derive",
+ "serde",
+ "serde_json",
+]
+
 [[package]]
 name = "schemars"
 version = "0.9.0"
@@ -4154,9 +4211,9 @@ dependencies = [
 
 [[package]]
 name = "schemars"
-version = "1.0.3"
+version = "1.0.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1375ba8ef45a6f15d83fa8748f1079428295d403d6ea991d09ab100155fbc06d"
+checksum = "82d20c4491bc164fa2f6c5d44565947a52ad80b9505d8e36f8d54c27c739fcd0"
 dependencies = [
  "dyn-clone",
  "ref-cast",
@@ -4164,6 +4221,18 @@ dependencies = [
  "serde_json",
 ]
 
+[[package]]
+name = "schemars_derive"
+version = "0.8.22"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "32e265784ad618884abaea0600a9adf15393368d840e0222d101a072f3f7534d"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "serde_derive_internals",
+ "syn",
+]
+
 [[package]]
 name = "scopeguard"
 version = "1.2.0"
@@ -4296,6 +4365,17 @@ dependencies = [
  "syn",
 ]
 
+[[package]]
+name = "serde_derive_internals"
+version = "0.29.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "18d26a20a969b9e3fdf2fc2d9f21eda6c40e2de84c9408bb5d3b05d499aae711"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
 [[package]]
 name = "serde_json"
 version = "1.0.140"
@@ -4374,7 +4454,7 @@ dependencies = [
  "indexmap 1.9.3",
  "indexmap 2.10.0",
  "schemars 0.9.0",
- "schemars 1.0.3",
+ "schemars 1.0.4",
  "serde",
  "serde_derive",
  "serde_json",

Dockerfile

@@ -13,6 +13,7 @@ WORKDIR /app
 RUN rustup target add x86_64-pc-windows-gnu
 RUN rustup target add x86_64-unknown-linux-gnu
 RUN rustup component add rustfmt
+RUN rustup component add clippy
 
 RUN apt update
 

check.sh

@@ -1,5 +1,7 @@
 #!/bin/sh
 set -e
+
 cargo check --all-targets --all-features --keep-going
 cargo fmt --check
+cargo clippy
 cargo test

examples/application_monitoring_with_tenant/Cargo.toml

@@ -0,0 +1,14 @@
+[package]
+name = "example-application-monitoring-with-tenant"
+edition = "2024"
+version.workspace = true
+readme.workspace = true
+license.workspace = true
+
+[dependencies]
+env_logger.workspace = true
+harmony = { version = "0.1.0", path = "../../harmony" }
+harmony_cli = { version = "0.1.0", path = "../../harmony_cli" }
+logging = "0.1.0"
+tokio.workspace = true
+url.workspace = true

examples/application_monitoring_with_tenant/src/main.rs

@@ -0,0 +1,55 @@
+use std::{path::PathBuf, str::FromStr, sync::Arc};
+
+use harmony::{
+    data::Id,
+    inventory::Inventory,
+    modules::{
+        application::{ApplicationScore, RustWebFramework, RustWebapp, features::Monitoring},
+        monitoring::alert_channel::webhook_receiver::WebhookReceiver,
+        tenant::TenantScore,
+    },
+    topology::{K8sAnywhereTopology, Url, tenant::TenantConfig},
+};
+
+#[tokio::main]
+async fn main() {
+    //TODO there is a bug where the application is deployed into the namespace matching the
+    //application name and the tenant is created in the namesapce matching the tenant name
+    //in order for the application to be deployed in the tenant namespace the application.name and
+    //the TenantConfig.name must match
+    let tenant = TenantScore {
+        config: TenantConfig {
+            id: Id::from_str("test-tenant-id").unwrap(),
+            name: "example-monitoring".to_string(),
+            ..Default::default()
+        },
+    };
+    let application = Arc::new(RustWebapp {
+        name: "example-monitoring".to_string(),
+        domain: Url::Url(url::Url::parse("https://rustapp.harmony.example.com").unwrap()),
+        project_root: PathBuf::from("./examples/rust/webapp"),
+        framework: Some(RustWebFramework::Leptos),
+    });
+
+    let webhook_receiver = WebhookReceiver {
+        name: "sample-webhook-receiver".to_string(),
+        url: Url::Url(url::Url::parse("https://webhook-doesnt-exist.com").unwrap()),
+    };
+
+    let app = ApplicationScore {
+        features: vec![Box::new(Monitoring {
+            alert_receiver: vec![Box::new(webhook_receiver)],
+            application: application.clone(),
+        })],
+        application,
+    };
+
+    harmony_cli::run(
+        Inventory::autoload(),
+        K8sAnywhereTopology::from_env(),
+        vec![Box::new(tenant), Box::new(app)],
+        None,
+    )
+    .await
+    .unwrap();
+}

examples/kube-rs/src/main.rs

@@ -125,40 +125,47 @@ spec:
                   name: nginx"#,
     )
     .unwrap();
-    return deployment;
+    deployment
 }
 fn nginx_deployment_2() -> Deployment {
-    let mut pod_template = PodTemplateSpec::default();
-    pod_template.metadata = Some(ObjectMeta {
+    let pod_template = PodTemplateSpec {
+        metadata: Some(ObjectMeta {
             labels: Some(BTreeMap::from([(
                 "app".to_string(),
                 "nginx-test".to_string(),
             )])),
             ..Default::default()
-    });
-    pod_template.spec = Some(PodSpec {
+        }),
+        spec: Some(PodSpec {
             containers: vec![Container {
                 name: "nginx".to_string(),
                 image: Some("nginx".to_string()),
                 ..Default::default()
             }],
             ..Default::default()
-    });
-    let mut spec = DeploymentSpec::default();
-    spec.template = pod_template;
-    spec.selector = LabelSelector {
+        }),
+    };
+
+    let spec = DeploymentSpec {
+        template: pod_template,
+        selector: LabelSelector {
             match_expressions: None,
             match_labels: Some(BTreeMap::from([(
                 "app".to_string(),
                 "nginx-test".to_string(),
             )])),
+        },
+        ..Default::default()
     };
 
-    let mut deployment = Deployment::default();
-    deployment.spec = Some(spec);
-    deployment.metadata.name = Some("nginx-test".to_string());
-
-    deployment
+    Deployment {
+        spec: Some(spec),
+        metadata: ObjectMeta {
+            name: Some("nginx-test".to_string()),
+            ..Default::default()
+        },
+        ..Default::default()
+    }
 }
 
 fn nginx_deployment() -> Deployment {

examples/lamp/src/main.rs

@@ -23,7 +23,7 @@ async fn main() {
         // This config can be extended as needed for more complicated configurations
         config: LAMPConfig {
             project_root: "./php".into(),
-            database_size: format!("4Gi").into(),
+            database_size: "4Gi".to_string().into(),
             ..Default::default()
         },
     };

examples/monitoring/src/main.rs

@@ -50,8 +50,8 @@ async fn main() {
 
     let service_monitor_endpoint = ServiceMonitorEndpoint {
         port: Some("80".to_string()),
-        path: "/metrics".to_string(),
-        scheme: HTTPScheme::HTTP,
+        path: Some("/metrics".to_string()),
+        scheme: Some(HTTPScheme::HTTP),
         ..Default::default()
     };
 

examples/monitoring_with_tenant/src/main.rs

@@ -1,4 +1,4 @@
-use std::collections::HashMap;
+use std::{collections::HashMap, str::FromStr};
 
 use harmony::{
     data::Id,
@@ -28,7 +28,7 @@ use harmony::{
 async fn main() {
     let tenant = TenantScore {
         config: TenantConfig {
-            id: Id::from_string("1234".to_string()),
+            id: Id::from_str("1234").unwrap(),
             name: "test-tenant".to_string(),
             resource_limits: ResourceLimits {
                 cpu_request_cores: 6.0,
@@ -53,8 +53,8 @@ async fn main() {
 
     let service_monitor_endpoint = ServiceMonitorEndpoint {
         port: Some("80".to_string()),
-        path: "/metrics".to_string(),
-        scheme: HTTPScheme::HTTP,
+        path: Some("/metrics".to_string()),
+        scheme: Some(HTTPScheme::HTTP),
         ..Default::default()
     };
 

examples/remove_rook_osd/Cargo.toml

@@ -0,0 +1,12 @@
+[package]
+name = "example_remove_rook_osd"
+edition = "2024"
+version.workspace = true
+readme.workspace = true
+license.workspace = true
+
+[dependencies]
+harmony = { version = "0.1.0", path = "../../harmony" }
+harmony_cli = { version = "0.1.0", path = "../../harmony_cli" }
+harmony_tui = { version = "0.1.0", path = "../../harmony_tui" }
+tokio.workspace = true

examples/remove_rook_osd/src/main.rs

@@ -0,0 +1,18 @@
+use harmony::{
+    inventory::Inventory, modules::storage::ceph::ceph_remove_osd_score::CephRemoveOsd,
+    topology::K8sAnywhereTopology,
+};
+
+#[tokio::main]
+async fn main() {
+    let ceph_score = CephRemoveOsd {
+        osd_deployment_name: "rook-ceph-osd-2".to_string(),
+        rook_ceph_namespace: "rook-ceph".to_string(),
+    };
+
+    let topology = K8sAnywhereTopology::from_env();
+    let inventory = Inventory::autoload();
+    harmony_cli::run(inventory, topology, vec![Box::new(ceph_score)], None)
+        .await
+        .unwrap();
+}

examples/rust/src/main.rs

@@ -2,10 +2,15 @@ use std::{path::PathBuf, sync::Arc};
 
 use harmony::{
     inventory::Inventory,
-    modules::application::{
+    modules::{
+        application::{
             ApplicationScore, RustWebFramework, RustWebapp,
             features::{ContinuousDelivery, Monitoring},
         },
+        monitoring::alert_channel::{
+            discord_alert_channel::DiscordWebhook, webhook_receiver::WebhookReceiver,
+        },
+    },
     topology::{K8sAnywhereTopology, Url},
 };
 
@@ -18,6 +23,16 @@ async fn main() {
         framework: Some(RustWebFramework::Leptos),
     });
 
+    let discord_receiver = DiscordWebhook {
+        name: "test-discord".to_string(),
+        url: Url::Url(url::Url::parse("https://discord.doesnt.exist.com").unwrap()),
+    };
+
+    let webhook_receiver = WebhookReceiver {
+        name: "sample-webhook-receiver".to_string(),
+        url: Url::Url(url::Url::parse("https://webhook-doesnt-exist.com").unwrap()),
+    };
+
     let app = ApplicationScore {
         features: vec![
             Box::new(ContinuousDelivery {
@@ -25,7 +40,9 @@ async fn main() {
             }),
             Box::new(Monitoring {
                 application: application.clone(),
-            }), // TODO: add backups, multisite ha, etc.
+                alert_receiver: vec![Box::new(discord_receiver), Box::new(webhook_receiver)],
+            }),
+            // TODO add backups, multisite ha, etc
         ],
         application,
     };

examples/tenant/src/main.rs

@@ -1,3 +1,5 @@
+use std::str::FromStr;
+
 use harmony::{
     data::Id,
     inventory::Inventory,
@@ -9,7 +11,7 @@ use harmony::{
 async fn main() {
     let tenant = TenantScore {
         config: TenantConfig {
-            id: Id::from_str("test-tenant-id"),
+            id: Id::from_str("test-tenant-id").unwrap(),
             name: "testtenant".to_string(),
             ..Default::default()
         },

harmony/Cargo.toml

@@ -5,6 +5,9 @@ version.workspace = true
 readme.workspace = true
 license.workspace = true
 
+[features]
+testing = []
+
 [dependencies]
 rand = "0.9"
 hex = "0.4"
@@ -27,7 +30,7 @@ harmony_macros = { path = "../harmony_macros" }
 harmony_types = { path = "../harmony_types" }
 uuid.workspace = true
 url.workspace = true
-kube.workspace = true
+kube = { workspace = true, features = ["derive"] }
 k8s-openapi.workspace = true
 serde_yaml.workspace = true
 http.workspace = true
@@ -58,6 +61,8 @@ tokio-util = "0.7.15"
 strum = { version = "0.27.1", features = ["derive"] }
 tempfile = "3.20.0"
 serde_with = "3.14.0"
+schemars = "0.8.22"
+kube-derive = "1.1.0"
 bollard.workspace = true
 tar.workspace = true
 base64.workspace = true

harmony/src/domain/config.rs

@@ -11,5 +11,5 @@ lazy_static! {
     pub static ref REGISTRY_PROJECT: String =
         std::env::var("HARMONY_REGISTRY_PROJECT").unwrap_or_else(|_| "harmony".to_string());
     pub static ref DRY_RUN: bool =
-        std::env::var("HARMONY_DRY_RUN").map_or(true, |value| value.parse().unwrap_or(true));
+        std::env::var("HARMONY_DRY_RUN").is_ok_and(|value| value.parse().unwrap_or(false));
 }

harmony/src/domain/data/id.rs

@@ -1,5 +1,6 @@
 use rand::distr::Alphanumeric;
 use rand::distr::SampleString;
+use std::str::FromStr;
 use std::time::SystemTime;
 use std::time::UNIX_EPOCH;
 
@@ -23,13 +24,13 @@ pub struct Id {
     value: String,
 }
 
-impl Id {
-    pub fn from_string(value: String) -> Self {
-        Self { value }
-    }
+impl FromStr for Id {
+    type Err = ();
 
-    pub fn from_str(value: &str) -> Self {
-        Self::from_string(value.to_string())
+    fn from_str(s: &str) -> Result<Self, Self::Err> {
+        Ok(Id {
+            value: s.to_string(),
+        })
     }
 }
 

harmony/src/domain/data/version.rs

@@ -47,7 +47,7 @@ impl serde::Serialize for Version {
 
 impl std::fmt::Display for Version {
     fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
-        return self.value.fmt(f);
+        self.value.fmt(f)
     }
 }
 

harmony/src/domain/hardware/mod.rs

@@ -35,10 +35,9 @@ impl PhysicalHost {
 
     pub fn cluster_mac(&self) -> MacAddress {
         self.network
-            .get(0)
+            .first()
             .expect("Cluster physical host should have a network interface")
             .mac_address
-            .clone()
     }
 
     pub fn cpu(mut self, cpu_count: Option<u64>) -> Self {

harmony/src/domain/instrumentation.rs

@@ -2,28 +2,42 @@ use log::debug;
 use once_cell::sync::Lazy;
 use tokio::sync::broadcast;
 
-use super::interpret::{InterpretError, Outcome};
+use crate::modules::application::ApplicationFeatureStatus;
+
+use super::{
+    interpret::{InterpretError, Outcome},
+    topology::TopologyStatus,
+};
 
 #[derive(Debug, Clone)]
 pub enum HarmonyEvent {
     HarmonyStarted,
-    PrepareTopologyStarted {
-        topology: String,
-    },
-    TopologyPrepared {
-        topology: String,
-        outcome: Outcome,
-    },
+    HarmonyFinished,
     InterpretExecutionStarted {
+        execution_id: String,
         topology: String,
         interpret: String,
+        score: String,
         message: String,
     },
     InterpretExecutionFinished {
+        execution_id: String,
         topology: String,
         interpret: String,
+        score: String,
         outcome: Result<Outcome, InterpretError>,
     },
+    TopologyStateChanged {
+        topology: String,
+        status: TopologyStatus,
+        message: Option<String>,
+    },
+    ApplicationFeatureStateChanged {
+        topology: String,
+        application: String,
+        feature: String,
+        status: ApplicationFeatureStatus,
+    },
 }
 
 static HARMONY_EVENT_BUS: Lazy<broadcast::Sender<HarmonyEvent>> = Lazy::new(|| {
@@ -33,10 +47,15 @@ static HARMONY_EVENT_BUS: Lazy<broadcast::Sender<HarmonyEvent>> = Lazy::new(|| {
 });
 
 pub fn instrument(event: HarmonyEvent) -> Result<(), &'static str> {
+    if cfg!(any(test, feature = "testing")) {
+        let _ = event; // Suppress the "unused variable" warning for `event`
+        Ok(())
+    } else {
         match HARMONY_EVENT_BUS.send(event) {
             Ok(_) => Ok(()),
             Err(_) => Err("send error: no subscribers"),
         }
+    }
 }
 
 pub async fn subscribe<F, Fut>(name: &str, mut handler: F)

harmony/src/domain/interpret/mod.rs

@@ -7,6 +7,7 @@ use super::{
     data::{Id, Version},
     executors::ExecutorError,
     inventory::Inventory,
+    topology::PreparationError,
 };
 
 pub enum InterpretName {
@@ -23,6 +24,14 @@ pub enum InterpretName {
     TenantInterpret,
     Application,
     ArgoCD,
+    Alerting,
+    Ntfy,
+    HelmChart,
+    HelmCommand,
+    K8sResource,
+    Lamp,
+    ApplicationMonitoring,
+    K8sPrometheusCrdAlerting,
 }
 
 impl std::fmt::Display for InterpretName {
@@ -41,6 +50,14 @@ impl std::fmt::Display for InterpretName {
             InterpretName::TenantInterpret => f.write_str("Tenant"),
             InterpretName::Application => f.write_str("Application"),
             InterpretName::ArgoCD => f.write_str("ArgoCD"),
+            InterpretName::Alerting => f.write_str("Alerting"),
+            InterpretName::Ntfy => f.write_str("Ntfy"),
+            InterpretName::HelmChart => f.write_str("HelmChart"),
+            InterpretName::HelmCommand => f.write_str("HelmCommand"),
+            InterpretName::K8sResource => f.write_str("K8sResource"),
+            InterpretName::Lamp => f.write_str("LAMP"),
+            InterpretName::ApplicationMonitoring => f.write_str("ApplicationMonitoring"),
+            InterpretName::K8sPrometheusCrdAlerting => f.write_str("K8sPrometheusCrdAlerting"),
         }
     }
 }
@@ -113,6 +130,14 @@ impl std::fmt::Display for InterpretError {
 }
 impl Error for InterpretError {}
 
+impl From<PreparationError> for InterpretError {
+    fn from(value: PreparationError) -> Self {
+        Self {
+            msg: format!("InterpretError : {value}"),
+        }
+    }
+}
+
 impl From<ExecutorError> for InterpretError {
     fn from(value: ExecutorError) -> Self {
         Self {

harmony/src/domain/maestro/mod.rs

@@ -1,14 +1,14 @@
-use std::sync::{Arc, Mutex, RwLock};
+use std::sync::{Arc, RwLock};
 
 use log::{debug, warn};
 
-use crate::instrumentation::{self, HarmonyEvent};
+use crate::topology::TopologyStatus;
 
 use super::{
-    interpret::{InterpretError, InterpretStatus, Outcome},
+    interpret::{InterpretError, Outcome},
     inventory::Inventory,
     score::Score,
-    topology::Topology,
+    topology::{PreparationError, PreparationOutcome, Topology, TopologyState},
 };
 
 type ScoreVec<T> = Vec<Box<dyn Score<T>>>;
@@ -17,7 +17,7 @@ pub struct Maestro<T: Topology> {
     inventory: Inventory,
     topology: T,
     scores: Arc<RwLock<ScoreVec<T>>>,
-    topology_preparation_result: Mutex<Option<Outcome>>,
+    topology_state: TopologyState,
 }
 
 impl<T: Topology> Maestro<T> {
@@ -25,42 +25,47 @@ impl<T: Topology> Maestro<T> {
     ///
     /// This should rarely be used. Most of the time Maestro::initialize should be used instead.
     pub fn new_without_initialization(inventory: Inventory, topology: T) -> Self {
+        let topology_name = topology.name().to_string();
+
         Self {
             inventory,
             topology,
             scores: Arc::new(RwLock::new(Vec::new())),
-            topology_preparation_result: None.into(),
+            topology_state: TopologyState::new(topology_name),
         }
     }
 
-    pub async fn initialize(inventory: Inventory, topology: T) -> Result<Self, InterpretError> {
-        let instance = Self::new_without_initialization(inventory, topology);
+    pub async fn initialize(inventory: Inventory, topology: T) -> Result<Self, PreparationError> {
+        let mut instance = Self::new_without_initialization(inventory, topology);
         instance.prepare_topology().await?;
         Ok(instance)
     }
 
     /// Ensures the associated Topology is ready for operations.
     /// Delegates the readiness check and potential setup actions to the Topology.
-    pub async fn prepare_topology(&self) -> Result<Outcome, InterpretError> {
-        instrumentation::instrument(HarmonyEvent::PrepareTopologyStarted {
-            topology: self.topology.name().to_string(),
-        })
-        .unwrap();
+    async fn prepare_topology(&mut self) -> Result<PreparationOutcome, PreparationError> {
+        self.topology_state.prepare();
 
-        let outcome = self.topology.ensure_ready().await?;
+        let result = self.topology.ensure_ready().await;
 
-        instrumentation::instrument(HarmonyEvent::TopologyPrepared {
-            topology: self.topology.name().to_string(),
-            outcome: outcome.clone(),
-        })
-        .unwrap();
-
-        self.topology_preparation_result
-            .lock()
-            .unwrap()
-            .replace(outcome.clone());
+        match result {
+            Ok(outcome) => {
+                match outcome.clone() {
+                    PreparationOutcome::Success { details } => {
+                        self.topology_state.success(details);
+                    }
+                    PreparationOutcome::Noop => {
+                        self.topology_state.noop();
+                    }
+                };
                 Ok(outcome)
             }
+            Err(err) => {
+                self.topology_state.error(err.to_string());
+                Err(err)
+            }
+        }
+    }
 
     pub fn register_all(&mut self, mut scores: ScoreVec<T>) {
         let mut score_mut = self.scores.write().expect("Should acquire lock");
@@ -68,15 +73,7 @@ impl<T: Topology> Maestro<T> {
     }
 
     fn is_topology_initialized(&self) -> bool {
-        let result = self.topology_preparation_result.lock().unwrap();
-        if let Some(outcome) = result.as_ref() {
-            match outcome.status {
-                InterpretStatus::SUCCESS => return true,
-                _ => return false,
-            }
-        } else {
-            false
-        }
+        self.topology_state.status == TopologyStatus::Success
     }
 
     pub async fn interpret(&self, score: Box<dyn Score<T>>) -> Result<Outcome, InterpretError> {
@@ -87,10 +84,8 @@ impl<T: Topology> Maestro<T> {
                 self.topology.name(),
             );
         }
-        debug!("Running score {score:?}");
-        let interpret = score.create_interpret();
-        debug!("Launching interpret {interpret:?}");
-        let result = interpret.execute(&self.inventory, &self.topology).await;
+        debug!("Interpreting score {score:?}");
+        let result = score.interpret(&self.inventory, &self.topology).await;
         debug!("Got result {result:?}");
         result
     }

harmony/src/domain/score.rs

@@ -1,22 +1,62 @@
 use std::collections::BTreeMap;
 
+use async_trait::async_trait;
 use serde::Serialize;
 use serde_value::Value;
 
-use super::{interpret::Interpret, topology::Topology};
+use super::{
+    data::Id,
+    instrumentation::{self, HarmonyEvent},
+    interpret::{Interpret, InterpretError, Outcome},
+    inventory::Inventory,
+    topology::Topology,
+};
 
+#[async_trait]
 pub trait Score<T: Topology>:
     std::fmt::Debug + ScoreToString<T> + Send + Sync + CloneBoxScore<T> + SerializeScore<T>
 {
-    fn create_interpret(&self) -> Box<dyn Interpret<T>>;
+    async fn interpret(
+        &self,
+        inventory: &Inventory,
+        topology: &T,
+    ) -> Result<Outcome, InterpretError> {
+        let id = Id::default();
+        let interpret = self.create_interpret();
+
+        instrumentation::instrument(HarmonyEvent::InterpretExecutionStarted {
+            execution_id: id.clone().to_string(),
+            topology: topology.name().into(),
+            interpret: interpret.get_name().to_string(),
+            score: self.name(),
+            message: format!("{} running...", interpret.get_name()),
+        })
+        .unwrap();
+        let result = interpret.execute(inventory, topology).await;
+
+        instrumentation::instrument(HarmonyEvent::InterpretExecutionFinished {
+            execution_id: id.clone().to_string(),
+            topology: topology.name().into(),
+            interpret: interpret.get_name().to_string(),
+            score: self.name(),
+            outcome: result.clone(),
+        })
+        .unwrap();
+
+        result
+    }
+
     fn name(&self) -> String;
+
+    #[doc(hidden)]
+    fn create_interpret(&self) -> Box<dyn Interpret<T>>;
 }
 
 pub trait SerializeScore<T: Topology> {
     fn serialize(&self) -> Value;
 }
 
-impl<'de, S, T> SerializeScore<T> for S
+impl<S, T> SerializeScore<T> for S
 where
     T: Topology,
     S: Score<T> + Serialize,
@@ -24,7 +64,7 @@ where
     fn serialize(&self) -> Value {
         // TODO not sure if this is the right place to handle the error or it should bubble
         // up?
-        serde_value::to_value(&self).expect("Score should serialize successfully")
+        serde_value::to_value(self).expect("Score should serialize successfully")
     }
 }
 

harmony/src/domain/topology/ha_cluster.rs

@@ -4,8 +4,6 @@ use harmony_types::net::MacAddress;
 use log::info;
 
 use crate::executors::ExecutorError;
-use crate::interpret::InterpretError;
-use crate::interpret::Outcome;
 
 use super::DHCPStaticEntry;
 use super::DhcpServer;
@@ -19,6 +17,8 @@ use super::K8sclient;
 use super::LoadBalancer;
 use super::LoadBalancerService;
 use super::LogicalHost;
+use super::PreparationError;
+use super::PreparationOutcome;
 use super::Router;
 use super::TftpServer;
 
@@ -48,7 +48,7 @@ impl Topology for HAClusterTopology {
     fn name(&self) -> &str {
         "HAClusterTopology"
     }
-    async fn ensure_ready(&self) -> Result<Outcome, InterpretError> {
+    async fn ensure_ready(&self) -> Result<PreparationOutcome, PreparationError> {
         todo!(
             "ensure_ready, not entirely sure what it should do here, probably something like verify that the hosts are reachable and all services are up and ready."
         )
@@ -244,10 +244,12 @@ impl Topology for DummyInfra {
         todo!()
     }
 
-    async fn ensure_ready(&self) -> Result<Outcome, InterpretError> {
+    async fn ensure_ready(&self) -> Result<PreparationOutcome, PreparationError> {
         let dummy_msg = "This is a dummy infrastructure that does nothing";
         info!("{dummy_msg}");
-        Ok(Outcome::success(dummy_msg.to_string()))
+        Ok(PreparationOutcome::Success {
+            details: dummy_msg.into(),
+        })
     }
 }
 

harmony/src/domain/topology/k8s.rs

@@ -1,12 +1,11 @@
 use derive_new::new;
-use futures_util::StreamExt;
 use k8s_openapi::{
     ClusterResourceScope, NamespaceResourceScope,
     api::{apps::v1::Deployment, core::v1::Pod},
 };
 use kube::{
     Client, Config, Error, Resource,
-    api::{Api, AttachParams, ListParams, Patch, PatchParams, ResourceExt},
+    api::{Api, AttachParams, DeleteParams, ListParams, Patch, PatchParams, ResourceExt},
     config::{KubeConfigOptions, Kubeconfig},
     core::ErrorResponse,
     runtime::reflector::Lookup,
@@ -17,14 +16,25 @@ use kube::{
     runtime::wait::await_condition,
 };
 use log::{debug, error, trace};
-use serde::de::DeserializeOwned;
-use similar::{DiffableStr, TextDiff};
+use serde::{Serialize, de::DeserializeOwned};
+use serde_json::json;
+use similar::TextDiff;
+use tokio::io::AsyncReadExt;
 
 #[derive(new, Clone)]
 pub struct K8sClient {
     client: Client,
 }
 
+impl Serialize for K8sClient {
+    fn serialize<S>(&self, _serializer: S) -> Result<S::Ok, S::Error>
+    where
+        S: serde::Serializer,
+    {
+        todo!()
+    }
+}
+
 impl std::fmt::Debug for K8sClient {
     fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
         // This is a poor man's debug implementation for now as kube::Client does not provide much
@@ -43,6 +53,66 @@ impl K8sClient {
         })
     }
 
+    pub async fn get_deployment(
+        &self,
+        name: &str,
+        namespace: Option<&str>,
+    ) -> Result<Option<Deployment>, Error> {
+        let deps: Api<Deployment> = if let Some(ns) = namespace {
+            Api::namespaced(self.client.clone(), ns)
+        } else {
+            Api::default_namespaced(self.client.clone())
+        };
+        Ok(deps.get_opt(name).await?)
+    }
+
+    pub async fn get_pod(&self, name: &str, namespace: Option<&str>) -> Result<Option<Pod>, Error> {
+        let pods: Api<Pod> = if let Some(ns) = namespace {
+            Api::namespaced(self.client.clone(), ns)
+        } else {
+            Api::default_namespaced(self.client.clone())
+        };
+        Ok(pods.get_opt(name).await?)
+    }
+
+    pub async fn scale_deployment(
+        &self,
+        name: &str,
+        namespace: Option<&str>,
+        replicas: u32,
+    ) -> Result<(), Error> {
+        let deployments: Api<Deployment> = if let Some(ns) = namespace {
+            Api::namespaced(self.client.clone(), ns)
+        } else {
+            Api::default_namespaced(self.client.clone())
+        };
+
+        let patch = json!({
+            "spec": {
+                "replicas": replicas
+            }
+        });
+        let pp = PatchParams::default();
+        let scale = Patch::Apply(&patch);
+        deployments.patch_scale(name, &pp, &scale).await?;
+        Ok(())
+    }
+
+    pub async fn delete_deployment(
+        &self,
+        name: &str,
+        namespace: Option<&str>,
+    ) -> Result<(), Error> {
+        let deployments: Api<Deployment> = if let Some(ns) = namespace {
+            Api::namespaced(self.client.clone(), ns)
+        } else {
+            Api::default_namespaced(self.client.clone())
+        };
+        let delete_params = DeleteParams::default();
+        deployments.delete(name, &delete_params).await?;
+        Ok(())
+    }
+
     pub async fn wait_until_deployment_ready(
         &self,
         name: String,
@@ -58,13 +128,75 @@ impl K8sClient {
         }
 
         let establish = await_condition(api, name.as_str(), conditions::is_deployment_completed());
-        let t = if let Some(t) = timeout { t } else { 300 };
+        let t = timeout.unwrap_or(300);
         let res = tokio::time::timeout(std::time::Duration::from_secs(t), establish).await;
 
-        if let Ok(r) = res {
-            return Ok(());
+        if res.is_ok() {
+            Ok(())
         } else {
-            return Err("timed out while waiting for deployment".to_string());
+            Err("timed out while waiting for deployment".to_string())
+        }
+    }
+
+    /// Will execute a commond in the first pod found that matches the specified label
+    /// '{label}={name}'
+    pub async fn exec_app_capture_output(
+        &self,
+        name: String,
+        label: String,
+        namespace: Option<&str>,
+        command: Vec<&str>,
+    ) -> Result<String, String> {
+        let api: Api<Pod>;
+
+        if let Some(ns) = namespace {
+            api = Api::namespaced(self.client.clone(), ns);
+        } else {
+            api = Api::default_namespaced(self.client.clone());
+        }
+        let pod_list = api
+            .list(&ListParams::default().labels(format!("{label}={name}").as_str()))
+            .await
+            .expect("couldn't get list of pods");
+
+        let res = api
+            .exec(
+                pod_list
+                    .items
+                    .first()
+                    .expect("couldn't get pod")
+                    .name()
+                    .expect("couldn't get pod name")
+                    .into_owned()
+                    .as_str(),
+                command,
+                &AttachParams::default().stdout(true).stderr(true),
+            )
+            .await;
+        match res {
+            Err(e) => Err(e.to_string()),
+            Ok(mut process) => {
+                let status = process
+                    .take_status()
+                    .expect("Couldn't get status")
+                    .await
+                    .expect("Couldn't unwrap status");
+
+                if let Some(s) = status.status {
+                    let mut stdout_buf = String::new();
+                    if let Some(mut stdout) = process.stdout().take() {
+                        stdout.read_to_string(&mut stdout_buf).await;
+                    }
+                    debug!("Status: {} - {:?}", s, status.details);
+                    if s == "Success" {
+                        Ok(stdout_buf)
+                    } else {
+                        Err(s)
+                    }
+                } else {
+                    Err("Couldn't get inner status of pod exec".to_string())
+                }
+            }
         }
     }
 
@@ -103,7 +235,7 @@ impl K8sClient {
             .await;
 
         match res {
-            Err(e) => return Err(e.to_string()),
+            Err(e) => Err(e.to_string()),
             Ok(mut process) => {
                 let status = process
                     .take_status()
@@ -112,14 +244,10 @@ impl K8sClient {
                     .expect("Couldn't unwrap status");
 
                 if let Some(s) = status.status {
-                    debug!("Status: {}", s);
-                    if s == "Success" {
-                        return Ok(());
+                    debug!("Status: {} - {:?}", s, status.details);
+                    if s == "Success" { Ok(()) } else { Err(s) }
                 } else {
-                        return Err(s);
-                    }
-                } else {
-                    return Err("Couldn't get inner status of pod exec".to_string());
+                    Err("Couldn't get inner status of pod exec".to_string())
                 }
             }
         }
@@ -160,8 +288,9 @@ impl K8sClient {
                     trace!("Received current value {current:#?}");
                     // The resource exists, so we calculate and display a diff.
                     println!("\nPerforming dry-run for resource: '{}'", name);
-                    let mut current_yaml = serde_yaml::to_value(&current)
-                        .expect(&format!("Could not serialize current value : {current:#?}"));
+                    let mut current_yaml = serde_yaml::to_value(&current).unwrap_or_else(|_| {
+                        panic!("Could not serialize current value : {current:#?}")
+                    });
                     if current_yaml.is_mapping() && current_yaml.get("status").is_some() {
                         let map = current_yaml.as_mapping_mut().unwrap();
                         let removed = map.remove_entry("status");
@@ -228,7 +357,7 @@ impl K8sClient {
         }
     }
 
-    pub async fn apply_many<K>(&self, resource: &Vec<K>, ns: Option<&str>) -> Result<Vec<K>, Error>
+    pub async fn apply_many<K>(&self, resource: &[K], ns: Option<&str>) -> Result<Vec<K>, Error>
     where
         K: Resource + Clone + std::fmt::Debug + DeserializeOwned + serde::Serialize,
         <K as Resource>::Scope: ApplyStrategy<K>,
@@ -244,7 +373,7 @@ impl K8sClient {
 
     pub async fn apply_yaml_many(
         &self,
-        yaml: &Vec<serde_yaml::Value>,
+        #[allow(clippy::ptr_arg)] yaml: &Vec<serde_yaml::Value>,
         ns: Option<&str>,
     ) -> Result<(), Error> {
         for y in yaml.iter() {

harmony/src/domain/topology/k8s_anywhere.rs

@@ -7,22 +7,40 @@ use tokio::sync::OnceCell;
 
 use crate::{
     executors::ExecutorError,
-    interpret::{InterpretError, Outcome},
+    interpret::InterpretStatus,
     inventory::Inventory,
-    modules::k3d::K3DInstallationScore,
+    modules::{
+        k3d::K3DInstallationScore,
+        monitoring::kube_prometheus::crd::{
+            crd_alertmanager_config::CRDPrometheus,
+            prometheus_operator::prometheus_operator_helm_chart_score,
+        },
+        prometheus::{
+            k8s_prometheus_alerting_score::K8sPrometheusCRDAlertingScore,
+            prometheus::PrometheusApplicationMonitoring,
+        },
+    },
     score::Score,
 };
 
 use super::{
-    DeploymentTarget, HelmCommand, K8sclient, MultiTargetTopology, Topology,
+    DeploymentTarget, HelmCommand, K8sclient, MultiTargetTopology, PreparationError,
+    PreparationOutcome, Topology,
     k8s::K8sClient,
-    tenant::{TenantConfig, TenantManager, k8s::K8sTenantManager},
+    oberservability::monitoring::AlertReceiver,
+    tenant::{
+        TenantConfig, TenantManager,
+        k8s::K8sTenantManager,
+        network_policy::{
+            K3dNetworkPolicyStrategy, NetworkPolicyStrategy, NoopNetworkPolicyStrategy,
+        },
+    },
 };
 
 #[derive(Clone, Debug)]
 struct K8sState {
     client: Arc<K8sClient>,
-    _source: K8sSource,
+    source: K8sSource,
     message: String,
 }
 
@@ -56,8 +74,42 @@ impl K8sclient for K8sAnywhereTopology {
     }
 }
 
+#[async_trait]
+impl PrometheusApplicationMonitoring<CRDPrometheus> for K8sAnywhereTopology {
+    async fn install_prometheus(
+        &self,
+        sender: &CRDPrometheus,
+        inventory: &Inventory,
+        receivers: Option<Vec<Box<dyn AlertReceiver<CRDPrometheus>>>>,
+    ) -> Result<PreparationOutcome, PreparationError> {
+        let po_result = self.ensure_prometheus_operator(sender).await?;
+
+        if po_result == PreparationOutcome::Noop {
+            debug!("Skipping Prometheus CR installation due to missing operator.");
+            return Ok(po_result);
+        }
+
+        let result = self
+            .get_k8s_prometheus_application_score(sender.clone(), receivers)
+            .await
+            .interpret(inventory, self)
+            .await;
+
+        match result {
+            Ok(outcome) => match outcome.status {
+                InterpretStatus::SUCCESS => Ok(PreparationOutcome::Success {
+                    details: outcome.message,
+                }),
+                InterpretStatus::NOOP => Ok(PreparationOutcome::Noop),
+                _ => Err(PreparationError::new(outcome.message)),
+            },
+            Err(err) => Err(PreparationError::new(err.to_string())),
+        }
+    }
+}
+
 impl Serialize for K8sAnywhereTopology {
-    fn serialize<S>(&self, serializer: S) -> Result<S::Ok, S::Error>
+    fn serialize<S>(&self, _serializer: S) -> Result<S::Ok, S::Error>
     where
         S: serde::Serializer,
     {
@@ -82,6 +134,19 @@ impl K8sAnywhereTopology {
         }
     }
 
+    async fn get_k8s_prometheus_application_score(
+        &self,
+        sender: CRDPrometheus,
+        receivers: Option<Vec<Box<dyn AlertReceiver<CRDPrometheus>>>>,
+    ) -> K8sPrometheusCRDAlertingScore {
+        K8sPrometheusCRDAlertingScore {
+            sender,
+            receivers: receivers.unwrap_or_default(),
+            service_monitors: vec![],
+            prometheus_rules: vec![],
+        }
+    }
+
     fn is_helm_available(&self) -> Result<(), String> {
         let version_result = Command::new("helm")
             .arg("version")
@@ -110,15 +175,23 @@ impl K8sAnywhereTopology {
         K3DInstallationScore::default()
     }
 
-    async fn try_install_k3d(&self) -> Result<(), InterpretError> {
-        self.get_k3d_installation_score()
-            .create_interpret()
-            .execute(&Inventory::empty(), self)
-            .await?;
-        Ok(())
+    async fn try_install_k3d(&self) -> Result<(), PreparationError> {
+        let result = self
+            .get_k3d_installation_score()
+            .interpret(&Inventory::empty(), self)
+            .await;
+
+        match result {
+            Ok(outcome) => match outcome.status {
+                InterpretStatus::SUCCESS => Ok(()),
+                InterpretStatus::NOOP => Ok(()),
+                _ => Err(PreparationError::new(outcome.message)),
+            },
+            Err(err) => Err(PreparationError::new(err.to_string())),
+        }
     }
 
-    async fn try_get_or_install_k8s_client(&self) -> Result<Option<K8sState>, InterpretError> {
+    async fn try_get_or_install_k8s_client(&self) -> Result<Option<K8sState>, PreparationError> {
         let k8s_anywhere_config = &self.config;
 
         // TODO this deserves some refactoring, it is becoming a bit hard to figure out
@@ -128,16 +201,16 @@ impl K8sAnywhereTopology {
         } else {
             if let Some(kubeconfig) = &k8s_anywhere_config.kubeconfig {
                 debug!("Loading kubeconfig {kubeconfig}");
-                match self.try_load_kubeconfig(&kubeconfig).await {
+                match self.try_load_kubeconfig(kubeconfig).await {
                     Some(client) => {
                         return Ok(Some(K8sState {
                             client: Arc::new(client),
-                            _source: K8sSource::Kubeconfig,
+                            source: K8sSource::Kubeconfig,
                             message: format!("Loaded k8s client from kubeconfig {kubeconfig}"),
                         }));
                     }
                     None => {
-                        return Err(InterpretError::new(format!(
+                        return Err(PreparationError::new(format!(
                             "Failed to load kubeconfig from {kubeconfig}"
                         )));
                     }
@@ -174,7 +247,7 @@ impl K8sAnywhereTopology {
         let state = match k3d.get_client().await {
             Ok(client) => K8sState {
                 client: Arc::new(K8sClient::new(client)),
-                _source: K8sSource::LocalK3d,
+                source: K8sSource::LocalK3d,
                 message: "K8s client ready".to_string(),
             },
             Err(_) => todo!(),
@@ -183,15 +256,21 @@ impl K8sAnywhereTopology {
         Ok(Some(state))
     }
 
-    async fn ensure_k8s_tenant_manager(&self) -> Result<(), String> {
-        if let Some(_) = self.tenant_manager.get() {
+    async fn ensure_k8s_tenant_manager(&self, k8s_state: &K8sState) -> Result<(), String> {
+        if self.tenant_manager.get().is_some() {
             return Ok(());
         }
 
         self.tenant_manager
             .get_or_try_init(async || -> Result<K8sTenantManager, String> {
                 let k8s_client = self.k8s_client().await?;
-                Ok(K8sTenantManager::new(k8s_client))
+                let network_policy_strategy: Box<dyn NetworkPolicyStrategy> = match k8s_state.source
+                {
+                    K8sSource::LocalK3d => Box::new(K3dNetworkPolicyStrategy::new()),
+                    K8sSource::Kubeconfig => Box::new(NoopNetworkPolicyStrategy::new()),
+                };
+
+                Ok(K8sTenantManager::new(k8s_client, network_policy_strategy))
             })
             .await?;
 
@@ -206,6 +285,55 @@ impl K8sAnywhereTopology {
             )),
         }
     }
+
+    async fn ensure_prometheus_operator(
+        &self,
+        sender: &CRDPrometheus,
+    ) -> Result<PreparationOutcome, PreparationError> {
+        let status = Command::new("sh")
+            .args(["-c", "kubectl get crd -A | grep -i prometheuses"])
+            .status()
+            .map_err(|e| PreparationError::new(format!("could not connect to cluster: {}", e)))?;
+
+        if !status.success() {
+            if let Some(Some(k8s_state)) = self.k8s_state.get() {
+                match k8s_state.source {
+                    K8sSource::LocalK3d => {
+                        debug!("installing prometheus operator");
+                        let op_score =
+                            prometheus_operator_helm_chart_score(sender.namespace.clone());
+                        let result = op_score.interpret(&Inventory::empty(), self).await;
+
+                        return match result {
+                            Ok(outcome) => match outcome.status {
+                                InterpretStatus::SUCCESS => Ok(PreparationOutcome::Success {
+                                    details: "installed prometheus operator".into(),
+                                }),
+                                InterpretStatus::NOOP => Ok(PreparationOutcome::Noop),
+                                _ => Err(PreparationError::new(
+                                    "failed to install prometheus operator (unknown error)".into(),
+                                )),
+                            },
+                            Err(err) => Err(PreparationError::new(err.to_string())),
+                        };
+                    }
+                    K8sSource::Kubeconfig => {
+                        debug!("unable to install prometheus operator, contact cluster admin");
+                        return Ok(PreparationOutcome::Noop);
+                    }
+                }
+            } else {
+                warn!("Unable to detect k8s_state. Skipping Prometheus Operator install.");
+                return Ok(PreparationOutcome::Noop);
+            }
+        }
+
+        debug!("Prometheus operator is already present, skipping install");
+
+        Ok(PreparationOutcome::Success {
+            details: "prometheus operator present in cluster".into(),
+        })
+    }
 }
 
 #[derive(Clone, Debug)]
@@ -263,26 +391,25 @@ impl Topology for K8sAnywhereTopology {
         "K8sAnywhereTopology"
     }
 
-    async fn ensure_ready(&self) -> Result<Outcome, InterpretError> {
+    async fn ensure_ready(&self) -> Result<PreparationOutcome, PreparationError> {
         let k8s_state = self
             .k8s_state
             .get_or_try_init(|| self.try_get_or_install_k8s_client())
             .await?;
 
-        let k8s_state: &K8sState = k8s_state.as_ref().ok_or(InterpretError::new(
-            "No K8s client could be found or installed".to_string(),
+        let k8s_state: &K8sState = k8s_state.as_ref().ok_or(PreparationError::new(
+            "no K8s client could be found or installed".to_string(),
         ))?;
 
-        self.ensure_k8s_tenant_manager()
+        self.ensure_k8s_tenant_manager(k8s_state)
             .await
-            .map_err(|e| InterpretError::new(e))?;
+            .map_err(PreparationError::new)?;
 
         match self.is_helm_available() {
-            Ok(()) => Ok(Outcome::success(format!(
-                "{} + helm available",
-                k8s_state.message.clone()
-            ))),
-            Err(e) => Err(InterpretError::new(format!("helm unavailable: {}", e))),
+            Ok(()) => Ok(PreparationOutcome::Success {
+                details: format!("{} + helm available", k8s_state.message.clone()),
+            }),
+            Err(e) => Err(PreparationError::new(format!("helm unavailable: {}", e))),
         }
     }
 }

harmony/src/domain/topology/localhost.rs

@@ -1,9 +1,7 @@
 use async_trait::async_trait;
 use derive_new::new;
 
-use crate::interpret::{InterpretError, Outcome};
-
-use super::{HelmCommand, Topology};
+use super::{HelmCommand, PreparationError, PreparationOutcome, Topology};
 
 #[derive(new)]
 pub struct LocalhostTopology;
@@ -14,10 +12,10 @@ impl Topology for LocalhostTopology {
         "LocalHostTopology"
     }
 
-    async fn ensure_ready(&self) -> Result<Outcome, InterpretError> {
-        Ok(Outcome::success(
-            "Localhost is Chuck Norris, always ready.".to_string(),
-        ))
+    async fn ensure_ready(&self) -> Result<PreparationOutcome, PreparationError> {
+        Ok(PreparationOutcome::Success {
+            details: "Localhost is Chuck Norris, always ready.".into(),
+        })
     }
 }
 

harmony/src/domain/topology/mod.rs

@@ -6,6 +6,7 @@ mod k8s_anywhere;
 mod localhost;
 pub mod oberservability;
 pub mod tenant;
+use derive_new::new;
 pub use k8s_anywhere::*;
 pub use localhost::*;
 pub mod k8s;
@@ -26,10 +27,13 @@ pub use tftp::*;
 mod helm_command;
 pub use helm_command::*;
 
+use super::{
+    executors::ExecutorError,
+    instrumentation::{self, HarmonyEvent},
+};
+use std::error::Error;
 use std::net::IpAddr;
 
-use super::interpret::{InterpretError, Outcome};
-
 /// Represents a logical view of an infrastructure environment providing specific capabilities.
 ///
 /// A Topology acts as a self-contained "package" responsible for managing access
@@ -57,9 +61,128 @@ pub trait Topology: Send + Sync {
     ///     *   **Internal Orchestration:** For complex topologies, this method might manage dependencies on other sub-topologies, ensuring *their* `ensure_ready` is called first. Using nested `Maestros` to run setup `Scores` against these sub-topologies is the recommended pattern for non-trivial bootstrapping, allowing reuse of Harmony's core orchestration logic.
     ///
     /// # Returns
-    /// - `Ok(Outcome)`: Indicates the topology is now ready. The `Outcome` status might be `SUCCESS` if actions were taken, or `NOOP` if it was already ready. The message should provide context.
-    /// - `Err(TopologyError)`: Indicates the topology could not reach a ready state due to configuration issues, discovery failures, bootstrap errors, or unsupported environments.
-    async fn ensure_ready(&self) -> Result<Outcome, InterpretError>;
+    /// - `Ok(PreparationOutcome)`: Indicates the topology is now ready. The `Outcome` status might be `SUCCESS` if actions were taken, or `NOOP` if it was already ready. The message should provide context.
+    /// - `Err(PreparationError)`: Indicates the topology could not reach a ready state due to configuration issues, discovery failures, bootstrap errors, or unsupported environments.
+    async fn ensure_ready(&self) -> Result<PreparationOutcome, PreparationError>;
+}
+
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub enum PreparationOutcome {
+    Success { details: String },
+    Noop,
+}
+
+#[derive(Debug, Clone, new)]
+pub struct PreparationError {
+    msg: String,
+}
+
+impl std::fmt::Display for PreparationError {
+    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+        f.write_str(&self.msg)
+    }
+}
+
+impl Error for PreparationError {}
+
+impl From<ExecutorError> for PreparationError {
+    fn from(value: ExecutorError) -> Self {
+        Self {
+            msg: format!("InterpretError : {value}"),
+        }
+    }
+}
+
+impl From<kube::Error> for PreparationError {
+    fn from(value: kube::Error) -> Self {
+        Self {
+            msg: format!("PreparationError : {value}"),
+        }
+    }
+}
+
+impl From<String> for PreparationError {
+    fn from(value: String) -> Self {
+        Self {
+            msg: format!("PreparationError : {value}"),
+        }
+    }
+}
+
+#[derive(Clone, Debug, PartialEq)]
+pub enum TopologyStatus {
+    Queued,
+    Preparing,
+    Success,
+    Noop,
+    Error,
+}
+
+pub struct TopologyState {
+    pub topology: String,
+    pub status: TopologyStatus,
+}
+
+impl TopologyState {
+    pub fn new(topology: String) -> Self {
+        let instance = Self {
+            topology,
+            status: TopologyStatus::Queued,
+        };
+
+        instrumentation::instrument(HarmonyEvent::TopologyStateChanged {
+            topology: instance.topology.clone(),
+            status: instance.status.clone(),
+            message: None,
+        })
+        .unwrap();
+
+        instance
+    }
+
+    pub fn prepare(&mut self) {
+        self.status = TopologyStatus::Preparing;
+
+        instrumentation::instrument(HarmonyEvent::TopologyStateChanged {
+            topology: self.topology.clone(),
+            status: self.status.clone(),
+            message: None,
+        })
+        .unwrap();
+    }
+
+    pub fn success(&mut self, message: String) {
+        self.status = TopologyStatus::Success;
+
+        instrumentation::instrument(HarmonyEvent::TopologyStateChanged {
+            topology: self.topology.clone(),
+            status: self.status.clone(),
+            message: Some(message),
+        })
+        .unwrap();
+    }
+
+    pub fn noop(&mut self) {
+        self.status = TopologyStatus::Noop;
+
+        instrumentation::instrument(HarmonyEvent::TopologyStateChanged {
+            topology: self.topology.clone(),
+            status: self.status.clone(),
+            message: None,
+        })
+        .unwrap();
+    }
+
+    pub fn error(&mut self, message: String) {
+        self.status = TopologyStatus::Error;
+
+        instrumentation::instrument(HarmonyEvent::TopologyStateChanged {
+            topology: self.topology.clone(),
+            status: self.status.clone(),
+            message: Some(message),
+        })
+        .unwrap();
+    }
 }
 
 #[derive(Debug)]
@@ -88,7 +211,7 @@ impl Serialize for Url {
     {
         match self {
             Url::LocalFolder(path) => serializer.serialize_str(path),
-            Url::Url(url) => serializer.serialize_str(&url.as_str()),
+            Url::Url(url) => serializer.serialize_str(url.as_str()),
         }
     }
 }

harmony/src/domain/topology/oberservability/monitoring.rs

@@ -1,3 +1,5 @@
+use std::any::Any;
+
 use async_trait::async_trait;
 use log::debug;
 
@@ -43,7 +45,7 @@ impl<S: AlertSender + Installable<T>, T: Topology> Interpret<T> for AlertingInte
     }
 
     fn get_name(&self) -> InterpretName {
-        todo!()
+        InterpretName::Alerting
     }
 
     fn get_version(&self) -> Version {
@@ -62,7 +64,9 @@ impl<S: AlertSender + Installable<T>, T: Topology> Interpret<T> for AlertingInte
 #[async_trait]
 pub trait AlertReceiver<S: AlertSender>: std::fmt::Debug + Send + Sync {
     async fn install(&self, sender: &S) -> Result<Outcome, InterpretError>;
+    fn name(&self) -> String;
     fn clone_box(&self) -> Box<dyn AlertReceiver<S>>;
+    fn as_any(&self) -> &dyn Any;
 }
 
 #[async_trait]
@@ -72,6 +76,6 @@ pub trait AlertRule<S: AlertSender>: std::fmt::Debug + Send + Sync {
 }
 
 #[async_trait]
-pub trait ScrapeTarger<S: AlertSender> {
+pub trait ScrapeTarget<S: AlertSender> {
     async fn install(&self, sender: &S) -> Result<(), InterpretError>;
 }

harmony/src/domain/topology/router.rs

@@ -27,11 +27,11 @@ pub struct UnmanagedRouter {
 
 impl Router for UnmanagedRouter {
     fn get_gateway(&self) -> IpAddress {
-        self.gateway.clone()
+        self.gateway
     }
 
     fn get_cidr(&self) -> Ipv4Cidr {
-        self.cidr.clone()
+        self.cidr
     }
 
     fn get_host(&self) -> LogicalHost {

harmony/src/domain/topology/tenant/k8s.rs

@@ -15,36 +15,38 @@ use k8s_openapi::{
     apimachinery::pkg::util::intstr::IntOrString,
 };
 use kube::Resource;
-use log::{debug, info, warn};
+use log::debug;
 use serde::de::DeserializeOwned;
 use serde_json::json;
 use tokio::sync::OnceCell;
 
-use super::{TenantConfig, TenantManager};
+use super::{TenantConfig, TenantManager, network_policy::NetworkPolicyStrategy};
 
-#[derive(Clone, Debug)]
+#[derive(Debug)]
 pub struct K8sTenantManager {
     k8s_client: Arc<K8sClient>,
     k8s_tenant_config: Arc<OnceCell<TenantConfig>>,
+    network_policy_strategy: Box<dyn NetworkPolicyStrategy>,
 }
 
 impl K8sTenantManager {
-    pub fn new(client: Arc<K8sClient>) -> Self {
+    pub fn new(
+        client: Arc<K8sClient>,
+        network_policy_strategy: Box<dyn NetworkPolicyStrategy>,
+    ) -> Self {
         Self {
             k8s_client: client,
             k8s_tenant_config: Arc::new(OnceCell::new()),
+            network_policy_strategy,
         }
     }
-}
 
-impl K8sTenantManager {
     fn get_namespace_name(&self, config: &TenantConfig) -> String {
         config.name.clone()
     }
 
     fn ensure_constraints(&self, _namespace: &Namespace) -> Result<(), ExecutorError> {
-        warn!("Validate that when tenant already exists (by id) that name has not changed");
-        warn!("Make sure other Tenant constraints are respected by this k8s implementation");
+        // TODO: Ensure constraints are applied to namespace (https://git.nationtech.io/NationTech/harmony/issues/98)
         Ok(())
     }
 
@@ -219,24 +221,6 @@ impl K8sTenantManager {
                   }
                 ]
               },
-              {
-                "to": [
-                  {
-                "ipBlock": {
-                    "cidr": "10.43.0.1/32",
-                    }
-                  }
-                ]
-              },
-              {
-                "to": [
-                  {
-                "ipBlock": {
-                    "cidr": "172.23.0.0/16",
-                    }
-                  }
-                ]
-              },
               {
                 "to": [
                   {
@@ -304,19 +288,19 @@ impl K8sTenantManager {
                 let ports: Option<Vec<NetworkPolicyPort>> =
                     c.1.as_ref().map(|spec| match &spec.data {
                         super::PortSpecData::SinglePort(port) => vec![NetworkPolicyPort {
-                            port: Some(IntOrString::Int(port.clone().into())),
+                            port: Some(IntOrString::Int((*port).into())),
                             ..Default::default()
                         }],
                         super::PortSpecData::PortRange(start, end) => vec![NetworkPolicyPort {
-                            port: Some(IntOrString::Int(start.clone().into())),
-                            end_port: Some(end.clone().into()),
+                            port: Some(IntOrString::Int((*start).into())),
+                            end_port: Some((*end).into()),
                             protocol: None, // Not currently supported by Harmony
                         }],
 
                         super::PortSpecData::ListOfPorts(items) => items
                             .iter()
                             .map(|i| NetworkPolicyPort {
-                                port: Some(IntOrString::Int(i.clone().into())),
+                                port: Some(IntOrString::Int((*i).into())),
                                 ..Default::default()
                             })
                             .collect(),
@@ -361,19 +345,19 @@ impl K8sTenantManager {
                 let ports: Option<Vec<NetworkPolicyPort>> =
                     c.1.as_ref().map(|spec| match &spec.data {
                         super::PortSpecData::SinglePort(port) => vec![NetworkPolicyPort {
-                            port: Some(IntOrString::Int(port.clone().into())),
+                            port: Some(IntOrString::Int((*port).into())),
                             ..Default::default()
                         }],
                         super::PortSpecData::PortRange(start, end) => vec![NetworkPolicyPort {
-                            port: Some(IntOrString::Int(start.clone().into())),
-                            end_port: Some(end.clone().into()),
+                            port: Some(IntOrString::Int((*start).into())),
+                            end_port: Some((*end).into()),
                             protocol: None, // Not currently supported by Harmony
                         }],
 
                         super::PortSpecData::ListOfPorts(items) => items
                             .iter()
                             .map(|i| NetworkPolicyPort {
-                                port: Some(IntOrString::Int(i.clone().into())),
+                                port: Some(IntOrString::Int((*i).into())),
                                 ..Default::default()
                             })
                             .collect(),
@@ -406,12 +390,27 @@ impl K8sTenantManager {
     }
 }
 
+impl Clone for K8sTenantManager {
+    fn clone(&self) -> Self {
+        Self {
+            k8s_client: self.k8s_client.clone(),
+            k8s_tenant_config: self.k8s_tenant_config.clone(),
+            network_policy_strategy: self.network_policy_strategy.clone_box(),
+        }
+    }
+}
+
 #[async_trait]
 impl TenantManager for K8sTenantManager {
     async fn provision_tenant(&self, config: &TenantConfig) -> Result<(), ExecutorError> {
         let namespace = self.build_namespace(config)?;
         let resource_quota = self.build_resource_quota(config)?;
+
         let network_policy = self.build_network_policy(config)?;
+        let network_policy = self
+            .network_policy_strategy
+            .adjust_policy(network_policy, config);
+
         let resource_limit_range = self.build_limit_range(config)?;
 
         self.ensure_constraints(&namespace)?;
@@ -428,13 +427,14 @@ impl TenantManager for K8sTenantManager {
         debug!("Creating network_policy for tenant {}", config.name);
         self.apply_resource(network_policy, config).await?;
 
-        info!(
+        debug!(
             "Success provisionning K8s tenant id {} name {}",
             config.id, config.name
         );
         self.store_config(config);
         Ok(())
     }
+
     async fn get_tenant_config(&self) -> Option<TenantConfig> {
         self.k8s_tenant_config.get().cloned()
     }

harmony/src/domain/topology/tenant/mod.rs

@@ -1,11 +1,11 @@
 pub mod k8s;
 mod manager;
-use std::str::FromStr;
-
-pub use manager::*;
-use serde::{Deserialize, Serialize};
+pub mod network_policy;
 
 use crate::data::Id;
+pub use manager::*;
+use serde::{Deserialize, Serialize};
+use std::str::FromStr;
 
 #[derive(Debug, Clone, PartialEq, Serialize, Deserialize)] // Assuming serde for Scores
 pub struct TenantConfig {

harmony/src/domain/topology/tenant/network_policy.rs

@@ -0,0 +1,120 @@
+use k8s_openapi::api::networking::v1::{
+    IPBlock, NetworkPolicy, NetworkPolicyEgressRule, NetworkPolicyPeer, NetworkPolicySpec,
+};
+
+use super::TenantConfig;
+
+pub trait NetworkPolicyStrategy: Send + Sync + std::fmt::Debug {
+    fn clone_box(&self) -> Box<dyn NetworkPolicyStrategy>;
+
+    fn adjust_policy(&self, policy: NetworkPolicy, config: &TenantConfig) -> NetworkPolicy;
+}
+
+#[derive(Clone, Debug)]
+pub struct NoopNetworkPolicyStrategy {}
+
+impl NoopNetworkPolicyStrategy {
+    pub fn new() -> Self {
+        Self {}
+    }
+}
+
+impl Default for NoopNetworkPolicyStrategy {
+    fn default() -> Self {
+        Self::new()
+    }
+}
+
+impl NetworkPolicyStrategy for NoopNetworkPolicyStrategy {
+    fn clone_box(&self) -> Box<dyn NetworkPolicyStrategy> {
+        Box::new(self.clone())
+    }
+
+    fn adjust_policy(&self, policy: NetworkPolicy, _config: &TenantConfig) -> NetworkPolicy {
+        policy
+    }
+}
+
+#[derive(Clone, Debug)]
+pub struct K3dNetworkPolicyStrategy {}
+
+impl K3dNetworkPolicyStrategy {
+    pub fn new() -> Self {
+        Self {}
+    }
+}
+
+impl Default for K3dNetworkPolicyStrategy {
+    fn default() -> Self {
+        Self::new()
+    }
+}
+
+impl NetworkPolicyStrategy for K3dNetworkPolicyStrategy {
+    fn clone_box(&self) -> Box<dyn NetworkPolicyStrategy> {
+        Box::new(self.clone())
+    }
+
+    fn adjust_policy(&self, policy: NetworkPolicy, _config: &TenantConfig) -> NetworkPolicy {
+        let mut egress = policy
+            .spec
+            .clone()
+            .unwrap_or_default()
+            .egress
+            .clone()
+            .unwrap_or_default();
+        egress.push(NetworkPolicyEgressRule {
+            to: Some(vec![NetworkPolicyPeer {
+                ip_block: Some(IPBlock {
+                    cidr: "172.18.0.0/16".into(), // TODO: query the IP range https://git.nationtech.io/NationTech/harmony/issues/108
+                    ..Default::default()
+                }),
+                ..Default::default()
+            }]),
+            ..Default::default()
+        });
+
+        NetworkPolicy {
+            spec: Some(NetworkPolicySpec {
+                egress: Some(egress),
+                ..policy.spec.unwrap_or_default()
+            }),
+            ..policy
+        }
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use k8s_openapi::api::networking::v1::{
+        IPBlock, NetworkPolicy, NetworkPolicyEgressRule, NetworkPolicyPeer, NetworkPolicySpec,
+    };
+
+    use super::{K3dNetworkPolicyStrategy, NetworkPolicyStrategy};
+
+    #[test]
+    pub fn should_add_ip_block_for_k3d_harmony_server() {
+        let strategy = K3dNetworkPolicyStrategy::new();
+
+        let policy =
+            strategy.adjust_policy(NetworkPolicy::default(), &super::TenantConfig::default());
+
+        let expected_policy = NetworkPolicy {
+            spec: Some(NetworkPolicySpec {
+                egress: Some(vec![NetworkPolicyEgressRule {
+                    to: Some(vec![NetworkPolicyPeer {
+                        ip_block: Some(IPBlock {
+                            cidr: "172.18.0.0/16".into(),
+                            ..Default::default()
+                        }),
+                        ..Default::default()
+                    }]),
+                    ..Default::default()
+                }]),
+                ..Default::default()
+            }),
+            ..Default::default()
+        };
+        assert_eq!(expected_policy, policy);
+    }
+}

harmony/src/infra/opnsense/dns.rs

@@ -60,7 +60,7 @@ impl DnsServer for OPNSenseFirewall {
     }
 
     fn get_ip(&self) -> IpAddress {
-        OPNSenseFirewall::get_ip(&self)
+        OPNSenseFirewall::get_ip(self)
     }
 
     fn get_host(&self) -> LogicalHost {

harmony/src/infra/opnsense/http.rs

@@ -48,7 +48,7 @@ impl HttpServer for OPNSenseFirewall {
     async fn ensure_initialized(&self) -> Result<(), ExecutorError> {
         let mut config = self.opnsense_config.write().await;
         let caddy = config.caddy();
-        if let None = caddy.get_full_config() {
+        if caddy.get_full_config().is_none() {
             info!("Http config not available in opnsense config, installing package");
             config.install_package("os-caddy").await.map_err(|e| {
                 ExecutorError::UnexpectedError(format!(

harmony/src/infra/opnsense/load_balancer.rs

@@ -121,10 +121,12 @@ pub(crate) fn haproxy_xml_config_to_harmony_loadbalancer(
 
             LoadBalancerService {
                 backend_servers,
-                listening_port: frontend.bind.parse().expect(&format!(
+                listening_port: frontend.bind.parse().unwrap_or_else(|_| {
+                    panic!(
                         "HAProxy frontend address should be a valid SocketAddr, got {}",
                         frontend.bind
-                )),
+                    )
+                }),
                 health_check,
             }
         })
@@ -167,28 +169,28 @@ pub(crate) fn get_health_check_for_backend(
         None => return None,
     };
 
-    let haproxy_health_check = match haproxy
+    let haproxy_health_check = haproxy
         .healthchecks
         .healthchecks
         .iter()
-        .find(|h| &h.uuid == health_check_uuid)
-    {
-        Some(health_check) => health_check,
-        None => return None,
-    };
+        .find(|h| &h.uuid == health_check_uuid)?;
 
     let binding = haproxy_health_check.health_check_type.to_uppercase();
     let uppercase = binding.as_str();
     match uppercase {
         "TCP" => {
             if let Some(checkport) = haproxy_health_check.checkport.content.as_ref() {
-                if checkport.len() > 0 {
-                    return Some(HealthCheck::TCP(Some(checkport.parse().expect(&format!(
+                if !checkport.is_empty() {
+                    return Some(HealthCheck::TCP(Some(checkport.parse().unwrap_or_else(
+                        |_| {
+                            panic!(
                                 "HAProxy check port should be a valid port number, got {checkport}"
-                    )))));
+                            )
+                        },
+                    ))));
                 }
             }
-            return Some(HealthCheck::TCP(None));
+            Some(HealthCheck::TCP(None))
         }
         "HTTP" => {
             let path: String = haproxy_health_check
@@ -355,16 +357,13 @@ mod tests {
 
         // Create an HAProxy instance with servers
         let mut haproxy = HAProxy::default();
-        let mut server = HAProxyServer::default();
-        server.uuid = "server1".to_string();
-        server.address = "192.168.1.1".to_string();
-        server.port = 80;
-
+        let server = HAProxyServer {
+            uuid: "server1".to_string(),
+            address: "192.168.1.1".to_string(),
+            port: 80,
+            ..Default::default()
+        };
         haproxy.servers.servers.push(server);
-        let mut server = HAProxyServer::default();
-        server.uuid = "server3".to_string();
-        server.address = "192.168.1.3".to_string();
-        server.port = 8080;
 
         // Call the function
         let result = get_servers_for_backend(&backend, &haproxy);
@@ -384,10 +383,12 @@ mod tests {
         let backend = HAProxyBackend::default();
         // Create an HAProxy instance with servers
         let mut haproxy = HAProxy::default();
-        let mut server = HAProxyServer::default();
-        server.uuid = "server1".to_string();
-        server.address = "192.168.1.1".to_string();
-        server.port = 80;
+        let server = HAProxyServer {
+            uuid: "server1".to_string(),
+            address: "192.168.1.1".to_string(),
+            port: 80,
+            ..Default::default()
+        };
         haproxy.servers.servers.push(server);
         // Call the function
         let result = get_servers_for_backend(&backend, &haproxy);
@@ -402,10 +403,12 @@ mod tests {
         backend.linked_servers.content = Some("server4,server5".to_string());
         // Create an HAProxy instance with servers
         let mut haproxy = HAProxy::default();
-        let mut server = HAProxyServer::default();
-        server.uuid = "server1".to_string();
-        server.address = "192.168.1.1".to_string();
-        server.port = 80;
+        let server = HAProxyServer {
+            uuid: "server1".to_string(),
+            address: "192.168.1.1".to_string(),
+            port: 80,
+            ..Default::default()
+        };
         haproxy.servers.servers.push(server);
         // Call the function
         let result = get_servers_for_backend(&backend, &haproxy);
@@ -416,20 +419,28 @@ mod tests {
     #[test]
     fn test_get_servers_for_backend_multiple_linked_servers() {
         // Create a backend with multiple linked servers
+        #[allow(clippy::field_reassign_with_default)]
         let mut backend = HAProxyBackend::default();
         backend.linked_servers.content = Some("server1,server2".to_string());
+        //
         // Create an HAProxy instance with matching servers
         let mut haproxy = HAProxy::default();
-        let mut server = HAProxyServer::default();
-        server.uuid = "server1".to_string();
-        server.address = "some-hostname.test.mcd".to_string();
-        server.port = 80;
+        let server = HAProxyServer {
+            uuid: "server1".to_string(),
+            address: "some-hostname.test.mcd".to_string(),
+            port: 80,
+            ..Default::default()
+        };
         haproxy.servers.servers.push(server);
-        let mut server = HAProxyServer::default();
-        server.uuid = "server2".to_string();
-        server.address = "192.168.1.2".to_string();
-        server.port = 8080;
+
+        let server = HAProxyServer {
+            uuid: "server2".to_string(),
+            address: "192.168.1.2".to_string(),
+            port: 8080,
+            ..Default::default()
+        };
         haproxy.servers.servers.push(server);
+
         // Call the function
         let result = get_servers_for_backend(&backend, &haproxy);
         // Check the result

harmony/src/infra/opnsense/tftp.rs

@@ -58,7 +58,7 @@ impl TftpServer for OPNSenseFirewall {
     async fn ensure_initialized(&self) -> Result<(), ExecutorError> {
         let mut config = self.opnsense_config.write().await;
         let tftp = config.tftp();
-        if let None = tftp.get_full_config() {
+        if tftp.get_full_config().is_none() {
             info!("Tftp config not available in opnsense config, installing package");
             config.install_package("os-tftp").await.map_err(|e| {
                 ExecutorError::UnexpectedError(format!(

harmony/src/modules/application/feature.rs

@@ -13,7 +13,7 @@ pub trait ApplicationFeature<T: Topology>:
     fn name(&self) -> String;
 }
 
-trait ApplicationFeatureClone<T: Topology> {
+pub trait ApplicationFeatureClone<T: Topology> {
     fn clone_box(&self) -> Box<dyn ApplicationFeature<T>>;
 }
 
@@ -27,7 +27,7 @@ where
 }
 
 impl<T: Topology> Serialize for Box<dyn ApplicationFeature<T>> {
-    fn serialize<S>(&self, serializer: S) -> Result<S::Ok, S::Error>
+    fn serialize<S>(&self, _serializer: S) -> Result<S::Ok, S::Error>
     where
         S: serde::Serializer,
     {

harmony/src/modules/application/features/argo_types.rs

@@ -184,12 +184,11 @@ impl ArgoApplication {
     pub fn to_yaml(&self) -> serde_yaml::Value {
         let name = &self.name;
         let namespace = if let Some(ns) = self.namespace.as_ref() {
-            &ns
+            ns
         } else {
             "argocd"
         };
         let project = &self.project;
-        let source = &self.source;
 
         let yaml_str = format!(
             r#"
@@ -228,7 +227,7 @@ spec:
             serde_yaml::to_value(&self.source).expect("couldn't serialize source to value");
         let sync_policy = serde_yaml::to_value(&self.sync_policy)
             .expect("couldn't serialize sync_policy to value");
-        let revision_history_limit = serde_yaml::to_value(&self.revision_history_limit)
+        let revision_history_limit = serde_yaml::to_value(self.revision_history_limit)
             .expect("couldn't serialize revision_history_limit to value");
 
         spec.insert(

harmony/src/modules/application/features/continuous_delivery.rs

@@ -1,7 +1,7 @@
 use std::{io::Write, process::Command, sync::Arc};
 
 use async_trait::async_trait;
-use log::{debug, error};
+use log::info;
 use serde_yaml::Value;
 use tempfile::NamedTempFile;
 
@@ -10,7 +10,7 @@ use crate::{
     data::Version,
     inventory::Inventory,
     modules::application::{
-        Application, ApplicationFeature, HelmPackage, OCICompliant,
+        ApplicationFeature, HelmPackage, OCICompliant,
         features::{ArgoApplication, ArgoHelmScore},
     },
     score::Score,
@@ -56,14 +56,11 @@ impl<A: OCICompliant + HelmPackage> ContinuousDelivery<A> {
         chart_url: String,
         image_name: String,
     ) -> Result<(), String> {
-        error!(
-            "FIXME This works only with local k3d installations, which is fine only for current demo purposes. We assume usage of K8sAnywhereTopology"
-        );
-
-        error!("TODO hardcoded k3d bin path is wrong");
+        // TODO: This works only with local k3d installations, which is fine only for current demo purposes. We assume usage of K8sAnywhereTopology"
+        // https://git.nationtech.io/NationTech/harmony/issues/106
         let k3d_bin_path = (*HARMONY_DATA_DIR).join("k3d").join("k3d");
         // --- 1. Import the container image into the k3d cluster ---
-        debug!(
+        info!(
             "Importing image '{}' into k3d cluster 'harmony'",
             image_name
         );
@@ -80,7 +77,7 @@ impl<A: OCICompliant + HelmPackage> ContinuousDelivery<A> {
         }
 
         // --- 2. Get the kubeconfig for the k3d cluster and write it to a temp file ---
-        debug!("Retrieving kubeconfig for k3d cluster 'harmony'");
+        info!("Retrieving kubeconfig for k3d cluster 'harmony'");
         let kubeconfig_output = Command::new(&k3d_bin_path)
             .args(["kubeconfig", "get", "harmony"])
             .output()
@@ -101,7 +98,7 @@ impl<A: OCICompliant + HelmPackage> ContinuousDelivery<A> {
         let kubeconfig_path = temp_kubeconfig.path().to_str().unwrap();
 
         // --- 3. Install or upgrade the Helm chart in the cluster ---
-        debug!(
+        info!(
             "Deploying Helm chart '{}' to namespace '{}'",
             chart_url, app_name
         );
@@ -131,7 +128,7 @@ impl<A: OCICompliant + HelmPackage> ContinuousDelivery<A> {
             ));
         }
 
-        debug!("Successfully deployed '{}' to local k3d cluster.", app_name);
+        info!("Successfully deployed '{}' to local k3d cluster.", app_name);
         Ok(())
     }
 }
@@ -151,14 +148,12 @@ impl<
         // Or ask for it when unknown
 
         let helm_chart = self.application.build_push_helm_package(&image).await?;
-        debug!("Pushed new helm chart {helm_chart}");
 
-        error!("TODO Make building image configurable/skippable if image already exists (prompt)");
+        // TODO: Make building image configurable/skippable if image already exists (prompt)")
+        // https://git.nationtech.io/NationTech/harmony/issues/104
         let image = self.application.build_push_oci_image().await?;
-        debug!("Pushed new docker image {image}");
 
-        debug!("Installing ContinuousDelivery feature");
-        // TODO this is a temporary hack for demo purposes, the deployment target should be driven
+        // TODO: this is a temporary hack for demo purposes, the deployment target should be driven
         // by the topology only and we should not have to know how to perform tasks like this for
         // which the topology should be responsible.
         //
@@ -171,17 +166,20 @@ impl<
         // access it. This forces every Topology to understand the concept of targets though... So
         // instead I'll create a new Capability which is MultiTargetTopology and we'll see how it
         // goes. It still does not feel right though.
+        //
+        // https://git.nationtech.io/NationTech/harmony/issues/106
         match topology.current_target() {
             DeploymentTarget::LocalDev => {
+                info!("Deploying {} locally...", self.application.name());
                 self.deploy_to_local_k3d(self.application.name(), helm_chart, image)
                     .await?;
             }
             target => {
-                debug!("Deploying to target {target:?}");
+                info!("Deploying {} to target {target:?}", self.application.name());
                 let score = ArgoHelmScore {
-                    namespace: "harmonydemo-staging".to_string(),
-                    openshift: false,
-                    domain: "argo.harmonydemo.apps.st.mcd".to_string(),
+                    namespace: "harmony-example-rust-webapp".to_string(),
+                    openshift: true,
+                    domain: "argo.harmonydemo.apps.ncd0.harmony.mcd".to_string(),
                     argo_apps: vec![ArgoApplication::from(CDApplicationConfig {
                         // helm pull oci://hub.nationtech.io/harmony/harmony-example-rust-webapp-chart --version 0.1.0
                         version: Version::from("0.1.0").unwrap(),
@@ -189,12 +187,11 @@ impl<
                         helm_chart_name: "harmony-example-rust-webapp-chart".to_string(),
                         values_overrides: None,
                         name: "harmony-demo-rust-webapp".to_string(),
-                        namespace: "harmonydemo-staging".to_string(),
+                        namespace: "harmony-example-rust-webapp".to_string(),
                     })],
                 };
                 score
-                    .create_interpret()
-                    .execute(&Inventory::empty(), topology)
+                    .interpret(&Inventory::empty(), topology)
                     .await
                     .unwrap();
             }

harmony/src/modules/application/features/helm_argocd_score.rs

@@ -1,5 +1,4 @@
 use async_trait::async_trait;
-use log::error;
 use non_blank_string_rs::NonBlankString;
 use serde::Serialize;
 use std::str::FromStr;
@@ -50,20 +49,21 @@ impl<T: Topology + K8sclient + HelmCommand> Interpret<T> for ArgoInterpret {
         inventory: &Inventory,
         topology: &T,
     ) -> Result<Outcome, InterpretError> {
-        error!("Uncomment below, only disabled for debugging");
-        self.score
-            .create_interpret()
-            .execute(inventory, topology)
-            .await?;
+        self.score.interpret(inventory, topology).await?;
 
         let k8s_client = topology.k8s_client().await?;
         k8s_client
             .apply_yaml_many(&self.argo_apps.iter().map(|a| a.to_yaml()).collect(), None)
             .await
             .unwrap();
+
         Ok(Outcome::success(format!(
-            "Successfully installed ArgoCD and {} Applications",
-            self.argo_apps.len()
+            "ArgoCD installed with {} {}",
+            self.argo_apps.len(),
+            match self.argo_apps.len() {
+                1 => "application",
+                _ => "applications",
+            }
         )))
     }
 
@@ -986,7 +986,7 @@ commitServer:
     );
 
     HelmChartScore {
-        namespace: Some(NonBlankString::from_str(&namespace).unwrap()),
+        namespace: Some(NonBlankString::from_str(namespace).unwrap()),
         release_name: NonBlankString::from_str("argo-cd").unwrap(),
         chart_name: NonBlankString::from_str("argo/argo-cd").unwrap(),
         chart_version: Some(NonBlankString::from_str("8.1.2").unwrap()),

harmony/src/modules/application/features/monitoring.rs

@@ -1,51 +1,67 @@
 use std::sync::Arc;
 
-use async_trait::async_trait;
-use base64::{Engine as _, engine::general_purpose};
-use log::{debug, info};
+use crate::modules::application::{Application, ApplicationFeature};
+use crate::modules::monitoring::application_monitoring::application_monitoring_score::ApplicationMonitoringScore;
+use crate::modules::monitoring::kube_prometheus::crd::crd_alertmanager_config::CRDPrometheus;
 
+use crate::topology::MultiTargetTopology;
 use crate::{
     inventory::Inventory,
-    modules::{
-        application::{ApplicationFeature, OCICompliant},
-        monitoring::{
-            alert_channel::webhook_receiver::WebhookReceiver,
-            kube_prometheus::{
-                helm_prometheus_alert_score::HelmPrometheusAlertingScore,
-                types::{NamespaceSelector, ServiceMonitor},
-            },
-            ntfy::ntfy::NtfyScore,
-        },
+    modules::monitoring::{
+        alert_channel::webhook_receiver::WebhookReceiver, ntfy::ntfy::NtfyScore,
     },
     score::Score,
     topology::{HelmCommand, K8sclient, Topology, Url, tenant::TenantManager},
 };
+use crate::{
+    modules::prometheus::prometheus::PrometheusApplicationMonitoring,
+    topology::oberservability::monitoring::AlertReceiver,
+};
+use async_trait::async_trait;
+use base64::{Engine as _, engine::general_purpose};
+use log::{debug, info};
 
 #[derive(Debug, Clone)]
 pub struct Monitoring {
-    pub application: Arc<dyn OCICompliant>,
+    pub application: Arc<dyn Application>,
+    pub alert_receiver: Vec<Box<dyn AlertReceiver<CRDPrometheus>>>,
 }
 
 #[async_trait]
-impl<T: Topology + HelmCommand + K8sclient + 'static + TenantManager> ApplicationFeature<T>
-    for Monitoring
+impl<
+    T: Topology
+        + HelmCommand
+        + 'static
+        + TenantManager
+        + K8sclient
+        + MultiTargetTopology
+        + std::fmt::Debug
+        + PrometheusApplicationMonitoring<CRDPrometheus>,
+> ApplicationFeature<T> for Monitoring
 {
     async fn ensure_installed(&self, topology: &T) -> Result<(), String> {
         info!("Ensuring monitoring is available for application");
-
-        let ntfy = NtfyScore {
-            // namespace: topology
-            //     .get_tenant_config()
-            //     .await
-            //     .expect("couldn't get tenant config")
-            //     .name,
-            namespace: self.application.name(),
-            host: "localhost".to_string(),
-        };
-        ntfy.create_interpret()
-            .execute(&Inventory::empty(), topology)
+        let namespace = topology
+            .get_tenant_config()
             .await
-            .expect("couldn't create interpret for ntfy");
+            .map(|ns| ns.name.clone())
+            .unwrap_or_else(|| self.application.name());
+
+        let mut alerting_score = ApplicationMonitoringScore {
+            sender: CRDPrometheus {
+                namespace: namespace.clone(),
+                client: topology.k8s_client().await.unwrap(),
+            },
+            application: self.application.clone(),
+            receivers: self.alert_receiver.clone(),
+        };
+        let ntfy = NtfyScore {
+            namespace: namespace.clone(),
+            host: "ntfy.harmonydemo.apps.ncd0.harmony.mcd".to_string(),
+        };
+        ntfy.interpret(&Inventory::empty(), topology)
+            .await
+            .map_err(|e| e.to_string())?;
 
         let ntfy_default_auth_username = "harmony";
         let ntfy_default_auth_password = "harmony";
@@ -70,7 +86,7 @@ impl<T: Topology + HelmCommand + K8sclient + 'static + TenantManager> Applicatio
                 url::Url::parse(
                     format!(
                         "http://ntfy.{}.svc.cluster.local/rust-web-app?auth={ntfy_default_auth_param}",
-                        self.application.name()
+                        namespace.clone()
                     )
                     .as_str(),
                 )
@@ -78,31 +94,11 @@ impl<T: Topology + HelmCommand + K8sclient + 'static + TenantManager> Applicatio
             ),
         };
 
-        let mut service_monitor = ServiceMonitor::default();
-        service_monitor.namespace_selector = Some(NamespaceSelector {
-            any: true,
-            match_names: vec![],
-        });
-
-        service_monitor.name = "rust-webapp".to_string();
-
-        // let alerting_score = ApplicationPrometheusMonitoringScore {
-        //     receivers: vec![Box::new(ntfy_receiver)],
-        //     rules: vec![],
-        //     service_monitors: vec![service_monitor],
-        // };
-
-        let alerting_score = HelmPrometheusAlertingScore {
-            receivers: vec![Box::new(ntfy_receiver)],
-            rules: vec![],
-            service_monitors: vec![service_monitor],
-        };
-
+        alerting_score.receivers.push(Box::new(ntfy_receiver));
         alerting_score
-            .create_interpret()
-            .execute(&Inventory::empty(), topology)
+            .interpret(&Inventory::empty(), topology)
             .await
-            .unwrap();
+            .map_err(|e| e.to_string())?;
         Ok(())
     }
     fn name(&self) -> String {

harmony/src/modules/application/mod.rs

@@ -10,14 +10,23 @@ pub use oci::*;
 pub use rust::*;
 
 use async_trait::async_trait;
+use serde::Serialize;
 
 use crate::{
     data::{Id, Version},
+    instrumentation::{self, HarmonyEvent},
     interpret::{Interpret, InterpretError, InterpretName, InterpretStatus, Outcome},
     inventory::Inventory,
     topology::Topology,
 };
 
+#[derive(Clone, Debug)]
+pub enum ApplicationFeatureStatus {
+    Installing,
+    Installed,
+    Failed { details: String },
+}
+
 pub trait Application: std::fmt::Debug + Send + Sync {
     fn name(&self) -> String;
 }
@@ -46,20 +55,41 @@ impl<A: Application, T: Topology + std::fmt::Debug> Interpret<T> for Application
                 .join(", ")
         );
         for feature in self.features.iter() {
-            debug!(
-                "Installing feature {} for application {app_name}",
-                feature.name()
-            );
+            instrumentation::instrument(HarmonyEvent::ApplicationFeatureStateChanged {
+                topology: topology.name().into(),
+                application: self.application.name(),
+                feature: feature.name(),
+                status: ApplicationFeatureStatus::Installing,
+            })
+            .unwrap();
+
             let _ = match feature.ensure_installed(topology).await {
-                Ok(()) => (),
+                Ok(()) => {
+                    instrumentation::instrument(HarmonyEvent::ApplicationFeatureStateChanged {
+                        topology: topology.name().into(),
+                        application: self.application.name(),
+                        feature: feature.name(),
+                        status: ApplicationFeatureStatus::Installed,
+                    })
+                    .unwrap();
+                }
                 Err(msg) => {
+                    instrumentation::instrument(HarmonyEvent::ApplicationFeatureStateChanged {
+                        topology: topology.name().into(),
+                        application: self.application.name(),
+                        feature: feature.name(),
+                        status: ApplicationFeatureStatus::Failed {
+                            details: msg.clone(),
+                        },
+                    })
+                    .unwrap();
                     return Err(InterpretError::new(format!(
                         "Application Interpret failed to install feature : {msg}"
                     )));
                 }
             };
         }
-        Ok(Outcome::success("successfully created app".to_string()))
+        Ok(Outcome::success("Application created".to_string()))
     }
 
     fn get_name(&self) -> InterpretName {
@@ -78,3 +108,12 @@ impl<A: Application, T: Topology + std::fmt::Debug> Interpret<T> for Application
         todo!()
     }
 }
+
+impl Serialize for dyn Application {
+    fn serialize<S>(&self, _serializer: S) -> Result<S::Ok, S::Error>
+    where
+        S: serde::Serializer,
+    {
+        todo!()
+    }
+}

harmony/src/modules/application/rust.rs

@@ -1,5 +1,5 @@
 use std::fs;
-use std::path::PathBuf;
+use std::path::{Path, PathBuf};
 use std::process;
 use std::sync::Arc;
 
@@ -10,7 +10,7 @@ use dockerfile_builder::Dockerfile;
 use dockerfile_builder::instruction::{CMD, COPY, ENV, EXPOSE, FROM, RUN, USER, WORKDIR};
 use dockerfile_builder::instruction_builder::CopyBuilder;
 use futures_util::StreamExt;
-use log::{debug, error, log_enabled};
+use log::{debug, info, log_enabled};
 use serde::Serialize;
 use tar::Archive;
 
@@ -46,7 +46,7 @@ where
     }
 
     fn name(&self) -> String {
-        format!("Application: {}", self.application.name())
+        format!("{} [ApplicationScore]", self.application.name())
     }
 }
 
@@ -73,19 +73,19 @@ impl Application for RustWebapp {
 #[async_trait]
 impl HelmPackage for RustWebapp {
     async fn build_push_helm_package(&self, image_url: &str) -> Result<String, String> {
-        debug!("Starting Helm chart build and push for '{}'", self.name);
+        info!("Starting Helm chart build and push for '{}'", self.name);
 
         // 1. Create the Helm chart files on disk.
         let chart_dir = self
             .create_helm_chart_files(image_url)
             .map_err(|e| format!("Failed to create Helm chart files: {}", e))?;
-        debug!("Successfully created Helm chart files in {:?}", chart_dir);
+        info!("Successfully created Helm chart files in {:?}", chart_dir);
 
         // 2. Package the chart into a .tgz archive.
         let packaged_chart_path = self
             .package_helm_chart(&chart_dir)
             .map_err(|e| format!("Failed to package Helm chart: {}", e))?;
-        debug!(
+        info!(
             "Successfully packaged Helm chart: {}",
             packaged_chart_path.to_string_lossy()
         );
@@ -94,7 +94,7 @@ impl HelmPackage for RustWebapp {
         let oci_chart_url = self
             .push_helm_chart(&packaged_chart_path)
             .map_err(|e| format!("Failed to push Helm chart: {}", e))?;
-        debug!("Successfully pushed Helm chart to: {}", oci_chart_url);
+        info!("Successfully pushed Helm chart to: {}", oci_chart_url);
 
         Ok(oci_chart_url)
     }
@@ -107,20 +107,20 @@ impl OCICompliant for RustWebapp {
     async fn build_push_oci_image(&self) -> Result<String, String> {
         // This function orchestrates the build and push process.
         // It's async to match the trait definition, though the underlying docker commands are blocking.
-        debug!("Starting OCI image build and push for '{}'", self.name);
+        info!("Starting OCI image build and push for '{}'", self.name);
 
         // 1. Build the image by calling the synchronous helper function.
         let image_tag = self.image_name();
         self.build_docker_image(&image_tag)
             .await
             .map_err(|e| format!("Failed to build Docker image: {}", e))?;
-        debug!("Successfully built Docker image: {}", image_tag);
+        info!("Successfully built Docker image: {}", image_tag);
 
         // 2. Push the image to the registry.
         self.push_docker_image(&image_tag)
             .await
             .map_err(|e| format!("Failed to push Docker image: {}", e))?;
-        debug!("Successfully pushed Docker image to: {}", image_tag);
+        info!("Successfully pushed Docker image to: {}", image_tag);
 
         Ok(image_tag)
     }
@@ -174,7 +174,7 @@ impl RustWebapp {
             .platform("linux/x86_64");
 
         let mut temp_tar_builder = tar::Builder::new(Vec::new());
-        let _ = temp_tar_builder
+        temp_tar_builder
             .append_dir_all("", self.project_root.clone())
             .unwrap();
         let archive = temp_tar_builder
@@ -195,7 +195,7 @@ impl RustWebapp {
         );
 
         while let Some(msg) = image_build_stream.next().await {
-            println!("Message: {msg:?}");
+            debug!("Message: {msg:?}");
         }
 
         Ok(image_name.to_string())
@@ -219,7 +219,7 @@ impl RustWebapp {
         );
 
         while let Some(msg) = push_image_stream.next().await {
-            println!("Message: {msg:?}");
+            debug!("Message: {msg:?}");
         }
 
         Ok(image_tag.to_string())
@@ -288,9 +288,8 @@ impl RustWebapp {
                         .unwrap(),
                 );
                 // Copy the compiled binary from the builder stage.
-                error!(
-                    "FIXME Should not be using score name here, instead should use name from Cargo.toml"
-                );
+                // TODO: Should not be using score name here, instead should use name from Cargo.toml
+                // https://git.nationtech.io/NationTech/harmony/issues/105
                 let binary_path_in_builder = format!("/app/target/release/{}", self.name);
                 let binary_path_in_final = format!("/home/appuser/{}", self.name);
                 dockerfile.push(
@@ -328,9 +327,8 @@ impl RustWebapp {
                 ));
 
                 // Copy only the compiled binary from the builder stage.
-                error!(
-                    "FIXME Should not be using score name here, instead should use name from Cargo.toml"
-                );
+                // TODO: Should not be using score name here, instead should use name from Cargo.toml
+                // https://git.nationtech.io/NationTech/harmony/issues/105
                 let binary_path_in_builder = format!("/app/target/release/{}", self.name);
                 let binary_path_in_final = format!("/usr/local/bin/{}", self.name);
                 dockerfile.push(
@@ -530,10 +528,7 @@ spec:
     }
 
     /// Packages a Helm chart directory into a .tgz file.
-    fn package_helm_chart(
-        &self,
-        chart_dir: &PathBuf,
-    ) -> Result<PathBuf, Box<dyn std::error::Error>> {
+    fn package_helm_chart(&self, chart_dir: &Path) -> Result<PathBuf, Box<dyn std::error::Error>> {
         let chart_dirname = chart_dir.file_name().expect("Should find a chart dirname");
         debug!(
             "Launching `helm package {}` cli with CWD {}",
@@ -546,14 +541,13 @@ spec:
         );
         let output = process::Command::new("helm")
             .args(["package", chart_dirname.to_str().unwrap()])
-            .current_dir(&self.project_root.join(".harmony_generated").join("helm")) // Run package from the parent dir
+            .current_dir(self.project_root.join(".harmony_generated").join("helm")) // Run package from the parent dir
             .output()?;
 
         self.check_output(&output, "Failed to package Helm chart")?;
 
         // Helm prints the path of the created chart to stdout.
         let tgz_name = String::from_utf8(output.stdout)?
-            .trim()
             .split_whitespace()
             .last()
             .unwrap_or_default()
@@ -573,7 +567,7 @@ spec:
     /// Pushes a packaged Helm chart to an OCI registry.
     fn push_helm_chart(
         &self,
-        packaged_chart_path: &PathBuf,
+        packaged_chart_path: &Path,
     ) -> Result<String, Box<dyn std::error::Error>> {
         // The chart name is the file stem of the .tgz file
         let chart_file_name = packaged_chart_path.file_stem().unwrap().to_str().unwrap();

harmony/src/modules/cert_manager/helm.rs

@@ -41,6 +41,6 @@ impl<T: Topology + HelmCommand> Score<T> for CertManagerHelmScore {
     }
 
     fn name(&self) -> String {
-        format!("CertManagerHelmScore")
+        "CertManagerHelmScore".to_string()
     }
 }

harmony/src/modules/dhcp.rs

@@ -111,7 +111,7 @@ impl DhcpInterpret {
 
         let boot_filename_outcome = match &self.score.boot_filename {
             Some(boot_filename) => {
-                dhcp_server.set_boot_filename(&boot_filename).await?;
+                dhcp_server.set_boot_filename(boot_filename).await?;
                 Outcome::new(
                     InterpretStatus::SUCCESS,
                     format!("Dhcp Interpret Set boot filename to {boot_filename}"),
@@ -122,7 +122,7 @@ impl DhcpInterpret {
 
         let filename_outcome = match &self.score.filename {
             Some(filename) => {
-                dhcp_server.set_filename(&filename).await?;
+                dhcp_server.set_filename(filename).await?;
                 Outcome::new(
                     InterpretStatus::SUCCESS,
                     format!("Dhcp Interpret Set filename to {filename}"),
@@ -133,7 +133,7 @@ impl DhcpInterpret {
 
         let filename64_outcome = match &self.score.filename64 {
             Some(filename64) => {
-                dhcp_server.set_filename64(&filename64).await?;
+                dhcp_server.set_filename64(filename64).await?;
                 Outcome::new(
                     InterpretStatus::SUCCESS,
                     format!("Dhcp Interpret Set filename64 to {filename64}"),
@@ -144,7 +144,7 @@ impl DhcpInterpret {
 
         let filenameipxe_outcome = match &self.score.filenameipxe {
             Some(filenameipxe) => {
-                dhcp_server.set_filenameipxe(&filenameipxe).await?;
+                dhcp_server.set_filenameipxe(filenameipxe).await?;
                 Outcome::new(
                     InterpretStatus::SUCCESS,
                     format!("Dhcp Interpret Set filenameipxe to {filenameipxe}"),
@@ -209,7 +209,7 @@ impl<T: DhcpServer> Interpret<T> for DhcpInterpret {
 
         Ok(Outcome::new(
             InterpretStatus::SUCCESS,
-            format!("Dhcp Interpret execution successful"),
+            "Dhcp Interpret execution successful".to_string(),
         ))
     }
 }

harmony/src/modules/dns.rs

@@ -112,7 +112,7 @@ impl<T: Topology + DnsServer> Interpret<T> for DnsInterpret {
 
         Ok(Outcome::new(
             InterpretStatus::SUCCESS,
-            format!("Dns Interpret execution successful"),
+            "Dns Interpret execution successful".to_string(),
         ))
     }
 }

harmony/src/modules/helm/chart.rs

@@ -55,7 +55,7 @@ impl<T: Topology + HelmCommand> Score<T> for HelmChartScore {
     }
 
     fn name(&self) -> String {
-        format!("{} {} HelmChartScore", self.release_name, self.chart_name)
+        format!("{} [HelmChartScore]", self.release_name)
     }
 }
 
@@ -90,14 +90,10 @@ impl HelmChartInterpret {
         );
 
         match add_output.status.success() {
-            true => {
-                return Ok(());
-            }
-            false => {
-                return Err(InterpretError::new(format!(
+            true => Ok(()),
+            false => Err(InterpretError::new(format!(
                 "Failed to add helm repository!\n{full_output}"
-                )));
-            }
+            ))),
         }
     }
 }
@@ -212,7 +208,7 @@ impl<T: Topology + HelmCommand> Interpret<T> for HelmChartInterpret {
         }
 
         let res = helm_executor.install_or_upgrade(
-            &ns,
+            ns,
             &self.score.release_name,
             &self.score.chart_name,
             self.score.chart_version.as_ref(),
@@ -229,24 +225,27 @@ impl<T: Topology + HelmCommand> Interpret<T> for HelmChartInterpret {
         match status {
             helm_wrapper_rs::HelmDeployStatus::Deployed => Ok(Outcome::new(
                 InterpretStatus::SUCCESS,
-                "Helm Chart deployed".to_string(),
+                format!("Helm Chart {} deployed", self.score.release_name),
             )),
             helm_wrapper_rs::HelmDeployStatus::PendingInstall => Ok(Outcome::new(
                 InterpretStatus::RUNNING,
-                "Helm Chart Pending install".to_string(),
+                format!("Helm Chart {} pending install...", self.score.release_name),
             )),
             helm_wrapper_rs::HelmDeployStatus::PendingUpgrade => Ok(Outcome::new(
                 InterpretStatus::RUNNING,
-                "Helm Chart pending upgrade".to_string(),
-            )),
-            helm_wrapper_rs::HelmDeployStatus::Failed => Err(InterpretError::new(
-                "Failed to install helm chart".to_string(),
+                format!("Helm Chart {} pending upgrade...", self.score.release_name),
             )),
+            helm_wrapper_rs::HelmDeployStatus::Failed => Err(InterpretError::new(format!(
+                "Helm Chart {} installation failed",
+                self.score.release_name
+            ))),
         }
     }
+
     fn get_name(&self) -> InterpretName {
-        todo!()
+        InterpretName::HelmChart
     }
+
     fn get_version(&self) -> Version {
         todo!()
     }

harmony/src/modules/helm/command.rs

@@ -77,14 +77,11 @@ impl HelmCommandExecutor {
             )?;
         }
 
-        let out = match self.clone().run_command(
+        let out = self.clone().run_command(
             self.chart
                 .clone()
                 .helm_args(self.globals.chart_home.clone().unwrap()),
-        ) {
-            Ok(out) => out,
-            Err(e) => return Err(e),
-        };
+        )?;
 
         // TODO: don't use unwrap here
         let s = String::from_utf8(out.stdout).unwrap();
@@ -98,14 +95,11 @@ impl HelmCommandExecutor {
     }
 
     pub fn version(self) -> Result<String, std::io::Error> {
-        let out = match self.run_command(vec![
+        let out = self.run_command(vec![
             "version".to_string(),
             "-c".to_string(),
             "--short".to_string(),
-        ]) {
-            Ok(out) => out,
-            Err(e) => return Err(e),
-        };
+        ])?;
 
         // TODO: don't use unwrap
         Ok(String::from_utf8(out.stdout).unwrap())
@@ -129,15 +123,11 @@ impl HelmCommandExecutor {
             None => PathBuf::from(TempDir::new()?.path()),
         };
 
-        match self.chart.values_inline {
-            Some(yaml_str) => {
-                let tf: TempFile;
-                tf = temp_file::with_contents(yaml_str.as_bytes());
+        if let Some(yaml_str) = self.chart.values_inline {
+            let tf: TempFile = temp_file::with_contents(yaml_str.as_bytes());
             self.chart
                 .additional_values_files
                 .push(PathBuf::from(tf.path()));
-            }
-            None => (),
         };
 
         self.env.insert(
@@ -180,9 +170,9 @@ impl HelmChart {
         match self.repo {
             Some(r) => {
                 if r.starts_with("oci://") {
-                    args.push(String::from(
+                    args.push(
                         r.trim_end_matches("/").to_string() + "/" + self.name.clone().as_str(),
-                    ));
+                    );
                 } else {
                     args.push("--repo".to_string());
                     args.push(r.to_string());
@@ -193,13 +183,10 @@ impl HelmChart {
             None => args.push(self.name),
         };
 
-        match self.version {
-            Some(v) => {
+        if let Some(v) = self.version {
             args.push("--version".to_string());
             args.push(v.to_string());
         }
-            None => (),
-        }
 
         args
     }
@@ -362,7 +349,7 @@ impl<T: Topology + K8sclient + HelmCommand> Interpret<T> for HelmChartInterpretV
     }
 
     fn get_name(&self) -> InterpretName {
-        todo!()
+        InterpretName::HelmCommand
     }
     fn get_version(&self) -> Version {
         todo!()

harmony/src/modules/k3d/install.rs

@@ -1,13 +1,12 @@
 use std::path::PathBuf;
 
 use async_trait::async_trait;
-use log::{debug, info};
+use log::debug;
 use serde::Serialize;
 
 use crate::{
     config::HARMONY_DATA_DIR,
     data::{Id, Version},
-    instrumentation::{self, HarmonyEvent},
     interpret::{Interpret, InterpretError, InterpretName, InterpretStatus, Outcome},
     inventory::Inventory,
     score::Score,
@@ -30,14 +29,14 @@ impl Default for K3DInstallationScore {
 }
 
 impl<T: Topology> Score<T> for K3DInstallationScore {
-    fn create_interpret(&self) -> Box<dyn crate::interpret::Interpret<T>> {
+    fn create_interpret(&self) -> Box<dyn Interpret<T>> {
         Box::new(K3dInstallationInterpret {
             score: self.clone(),
         })
     }
 
     fn name(&self) -> String {
-        todo!()
+        "K3dInstallationScore".into()
     }
 }
 
@@ -51,20 +50,14 @@ impl<T: Topology> Interpret<T> for K3dInstallationInterpret {
     async fn execute(
         &self,
         _inventory: &Inventory,
-        topology: &T,
+        _topology: &T,
     ) -> Result<Outcome, InterpretError> {
-        instrumentation::instrument(HarmonyEvent::InterpretExecutionStarted {
-            topology: topology.name().into(),
-            interpret: "k3d-installation".into(),
-            message: "installing k3d...".into(),
-        })
-        .unwrap();
-
         let k3d = k3d_rs::K3d::new(
             self.score.installation_path.clone(),
             Some(self.score.cluster_name.clone()),
         );
-        let outcome = match k3d.ensure_installed().await {
+
+        match k3d.ensure_installed().await {
             Ok(_client) => {
                 let msg = format!("k3d cluster '{}' installed ", self.score.cluster_name);
                 debug!("{msg}");
@@ -73,16 +66,7 @@ impl<T: Topology> Interpret<T> for K3dInstallationInterpret {
             Err(msg) => Err(InterpretError::new(format!(
                 "failed to ensure k3d is installed : {msg}"
             ))),
-        };
-
-        instrumentation::instrument(HarmonyEvent::InterpretExecutionFinished {
-            topology: topology.name().into(),
-            interpret: "k3d-installation".into(),
-            outcome: outcome.clone(),
-        })
-        .unwrap();
-
-        outcome
+        }
     }
     fn get_name(&self) -> InterpretName {
         InterpretName::K3dInstallation

harmony/src/modules/k8s/resource.rs

@@ -89,7 +89,7 @@ where
         ))
     }
     fn get_name(&self) -> InterpretName {
-        todo!()
+        InterpretName::K8sResource
     }
     fn get_version(&self) -> Version {
         todo!()

harmony/src/modules/lamp.rs

@@ -128,13 +128,12 @@ impl<T: Topology + K8sclient + HelmCommand> Interpret<T> for LAMPInterpret {
 
         info!("Deploying score {deployment_score:#?}");
 
-        deployment_score
-            .create_interpret()
-            .execute(inventory, topology)
-            .await?;
+        deployment_score.interpret(inventory, topology).await?;
 
         info!("LAMP deployment_score {deployment_score:?}");
 
+        let ingress_path = ingress_path!("/");
+
         let lamp_ingress = K8sIngressScore {
             name: fqdn!("lamp-ingress"),
             host: fqdn!("test"),
@@ -144,17 +143,14 @@ impl<T: Topology + K8sclient + HelmCommand> Interpret<T> for LAMPInterpret {
                     .as_str()
             ),
             port: 8080,
-            path: Some(ingress_path!("/")),
+            path: Some(ingress_path),
             path_type: None,
             namespace: self
                 .get_namespace()
                 .map(|nbs| fqdn!(nbs.to_string().as_str())),
         };
 
-        lamp_ingress
-            .create_interpret()
-            .execute(inventory, topology)
-            .await?;
+        lamp_ingress.interpret(inventory, topology).await?;
 
         info!("LAMP lamp_ingress {lamp_ingress:?}");
 
@@ -164,7 +160,7 @@ impl<T: Topology + K8sclient + HelmCommand> Interpret<T> for LAMPInterpret {
     }
 
     fn get_name(&self) -> InterpretName {
-        todo!()
+        InterpretName::Lamp
     }
 
     fn get_version(&self) -> Version {
@@ -213,7 +209,7 @@ impl LAMPInterpret {
             repository: None,
         };
 
-        score.create_interpret().execute(inventory, topology).await
+        score.interpret(inventory, topology).await
     }
     fn build_dockerfile(&self, score: &LAMPScore) -> Result<PathBuf, Box<dyn std::error::Error>> {
         let mut dockerfile = Dockerfile::new();

harmony/src/modules/mod.rs

@@ -14,5 +14,6 @@ pub mod monitoring;
 pub mod okd;
 pub mod opnsense;
 pub mod prometheus;
+pub mod storage;
 pub mod tenant;
 pub mod tftp;

harmony/src/modules/monitoring/alert_channel/discord_alert_channel.rs

@@ -1,7 +1,16 @@
+use std::any::Any;
+use std::collections::BTreeMap;
+
 use async_trait::async_trait;
+use k8s_openapi::api::core::v1::Secret;
+use kube::api::ObjectMeta;
 use serde::Serialize;
+use serde_json::json;
 use serde_yaml::{Mapping, Value};
 
+use crate::modules::monitoring::kube_prometheus::crd::crd_alertmanager_config::{
+    AlertmanagerConfig, AlertmanagerConfigSpec, CRDPrometheus,
+};
 use crate::{
     interpret::{InterpretError, Outcome},
     modules::monitoring::{
@@ -20,14 +29,98 @@ pub struct DiscordWebhook {
     pub url: Url,
 }
 
+#[async_trait]
+impl AlertReceiver<CRDPrometheus> for DiscordWebhook {
+    async fn install(&self, sender: &CRDPrometheus) -> Result<Outcome, InterpretError> {
+        let ns = sender.namespace.clone();
+        let secret_name = format!("{}-secret", self.name.clone());
+        let webhook_key = format!("{}", self.url.clone());
+
+        let mut string_data = BTreeMap::new();
+        string_data.insert("webhook-url".to_string(), webhook_key.clone());
+
+        let secret = Secret {
+            metadata: kube::core::ObjectMeta {
+                name: Some(secret_name.clone()),
+                ..Default::default()
+            },
+            string_data: Some(string_data),
+            type_: Some("Opaque".to_string()),
+            ..Default::default()
+        };
+
+        let _ = sender.client.apply(&secret, Some(&ns)).await;
+
+        let spec = AlertmanagerConfigSpec {
+            data: json!({
+                "route": {
+                    "receiver": self.name,
+                },
+                "receivers": [
+                    {
+                        "name": self.name,
+                        "discordConfigs": [
+                            {
+                            "apiURL": {
+                                "name": secret_name,
+                                "key":  "webhook-url",
+                            },
+                            "title": "{{ template \"discord.default.title\" . }}",
+                            "message": "{{ template \"discord.default.message\" . }}"
+                            }
+                        ]
+                    }
+                ]
+            }),
+        };
+
+        let alertmanager_configs = AlertmanagerConfig {
+            metadata: ObjectMeta {
+                name: Some(self.name.clone()),
+                labels: Some(std::collections::BTreeMap::from([(
+                    "alertmanagerConfig".to_string(),
+                    "enabled".to_string(),
+                )])),
+                namespace: Some(ns),
+                ..Default::default()
+            },
+            spec,
+        };
+
+        sender
+            .client
+            .apply(&alertmanager_configs, Some(&sender.namespace))
+            .await?;
+        Ok(Outcome::success(format!(
+            "installed crd-alertmanagerconfigs for {}",
+            self.name
+        )))
+    }
+    fn name(&self) -> String {
+        "discord-webhook".to_string()
+    }
+    fn clone_box(&self) -> Box<dyn AlertReceiver<CRDPrometheus>> {
+        Box::new(self.clone())
+    }
+    fn as_any(&self) -> &dyn Any {
+        self
+    }
+}
+
 #[async_trait]
 impl AlertReceiver<Prometheus> for DiscordWebhook {
     async fn install(&self, sender: &Prometheus) -> Result<Outcome, InterpretError> {
         sender.install_receiver(self).await
     }
+    fn name(&self) -> String {
+        "discord-webhook".to_string()
+    }
     fn clone_box(&self) -> Box<dyn AlertReceiver<Prometheus>> {
         Box::new(self.clone())
     }
+    fn as_any(&self) -> &dyn Any {
+        self
+    }
 }
 
 #[async_trait]
@@ -48,6 +141,12 @@ impl AlertReceiver<KubePrometheus> for DiscordWebhook {
     fn clone_box(&self) -> Box<dyn AlertReceiver<KubePrometheus>> {
         Box::new(self.clone())
     }
+    fn name(&self) -> String {
+        "discord-webhook".to_string()
+    }
+    fn as_any(&self) -> &dyn Any {
+        self
+    }
 }
 
 #[async_trait]

harmony/src/modules/monitoring/alert_channel/webhook_receiver.rs

@@ -1,11 +1,19 @@
+use std::any::Any;
+
 use async_trait::async_trait;
+use kube::api::ObjectMeta;
+use log::debug;
 use serde::Serialize;
+use serde_json::json;
 use serde_yaml::{Mapping, Value};
 
 use crate::{
     interpret::{InterpretError, Outcome},
     modules::monitoring::{
         kube_prometheus::{
+            crd::crd_alertmanager_config::{
+                AlertmanagerConfig, AlertmanagerConfigSpec, CRDPrometheus,
+            },
             prometheus::{KubePrometheus, KubePrometheusReceiver},
             types::{AlertChannelConfig, AlertManagerChannelConfig},
         },
@@ -20,14 +28,81 @@ pub struct WebhookReceiver {
     pub url: Url,
 }
 
+#[async_trait]
+impl AlertReceiver<CRDPrometheus> for WebhookReceiver {
+    async fn install(&self, sender: &CRDPrometheus) -> Result<Outcome, InterpretError> {
+        let spec = AlertmanagerConfigSpec {
+            data: json!({
+                "route": {
+                    "receiver": self.name,
+                },
+                "receivers": [
+                    {
+                        "name": self.name,
+                        "webhookConfigs": [
+                            {
+                            "url": self.url,
+                            }
+                        ]
+                    }
+                ]
+            }),
+        };
+
+        let alertmanager_configs = AlertmanagerConfig {
+            metadata: ObjectMeta {
+                name: Some(self.name.clone()),
+                labels: Some(std::collections::BTreeMap::from([(
+                    "alertmanagerConfig".to_string(),
+                    "enabled".to_string(),
+                )])),
+                namespace: Some(sender.namespace.clone()),
+                ..Default::default()
+            },
+            spec,
+        };
+        debug!(
+            "alert manager configs: \n{:#?}",
+            alertmanager_configs.clone()
+        );
+
+        sender
+            .client
+            .apply(&alertmanager_configs, Some(&sender.namespace))
+            .await?;
+        Ok(Outcome::success(format!(
+            "installed crd-alertmanagerconfigs for {}",
+            self.name
+        )))
+    }
+
+    fn name(&self) -> String {
+        "webhook-receiver".to_string()
+    }
+
+    fn clone_box(&self) -> Box<dyn AlertReceiver<CRDPrometheus>> {
+        Box::new(self.clone())
+    }
+
+    fn as_any(&self) -> &dyn Any {
+        self
+    }
+}
+
 #[async_trait]
 impl AlertReceiver<Prometheus> for WebhookReceiver {
     async fn install(&self, sender: &Prometheus) -> Result<Outcome, InterpretError> {
         sender.install_receiver(self).await
     }
+    fn name(&self) -> String {
+        "webhook-receiver".to_string()
+    }
     fn clone_box(&self) -> Box<dyn AlertReceiver<Prometheus>> {
         Box::new(self.clone())
     }
+    fn as_any(&self) -> &dyn Any {
+        self
+    }
 }
 
 #[async_trait]
@@ -44,9 +119,15 @@ impl AlertReceiver<KubePrometheus> for WebhookReceiver {
     async fn install(&self, sender: &KubePrometheus) -> Result<Outcome, InterpretError> {
         sender.install_receiver(self).await
     }
+    fn name(&self) -> String {
+        "webhook-receiver".to_string()
+    }
     fn clone_box(&self) -> Box<dyn AlertReceiver<KubePrometheus>> {
         Box::new(self.clone())
     }
+    fn as_any(&self) -> &dyn Any {
+        self
+    }
 }
 
 #[async_trait]

harmony/src/modules/monitoring/alert_rule/prometheus_alert_rule.rs

@@ -18,7 +18,7 @@ use crate::{
 #[async_trait]
 impl AlertRule<KubePrometheus> for AlertManagerRuleGroup {
     async fn install(&self, sender: &KubePrometheus) -> Result<Outcome, InterpretError> {
-        sender.install_rule(&self).await
+        sender.install_rule(self).await
     }
     fn clone_box(&self) -> Box<dyn AlertRule<KubePrometheus>> {
         Box::new(self.clone())
@@ -28,7 +28,7 @@ impl AlertRule<KubePrometheus> for AlertManagerRuleGroup {
 #[async_trait]
 impl AlertRule<Prometheus> for AlertManagerRuleGroup {
     async fn install(&self, sender: &Prometheus) -> Result<Outcome, InterpretError> {
-        sender.install_rule(&self).await
+        sender.install_rule(self).await
     }
     fn clone_box(&self) -> Box<dyn AlertRule<Prometheus>> {
         Box::new(self.clone())

harmony/src/modules/monitoring/application_monitoring/application_monitoring_score.rs

@@ -0,0 +1,91 @@
+use std::sync::Arc;
+
+use async_trait::async_trait;
+use serde::Serialize;
+
+use crate::{
+    data::{Id, Version},
+    interpret::{Interpret, InterpretError, InterpretName, InterpretStatus, Outcome},
+    inventory::Inventory,
+    modules::{
+        application::Application,
+        monitoring::kube_prometheus::crd::crd_alertmanager_config::CRDPrometheus,
+        prometheus::prometheus::PrometheusApplicationMonitoring,
+    },
+    score::Score,
+    topology::{PreparationOutcome, Topology, oberservability::monitoring::AlertReceiver},
+};
+
+#[derive(Debug, Clone, Serialize)]
+pub struct ApplicationMonitoringScore {
+    pub sender: CRDPrometheus,
+    pub application: Arc<dyn Application>,
+    pub receivers: Vec<Box<dyn AlertReceiver<CRDPrometheus>>>,
+}
+
+impl<T: Topology + PrometheusApplicationMonitoring<CRDPrometheus>> Score<T>
+    for ApplicationMonitoringScore
+{
+    fn create_interpret(&self) -> Box<dyn Interpret<T>> {
+        Box::new(ApplicationMonitoringInterpret {
+            score: self.clone(),
+        })
+    }
+
+    fn name(&self) -> String {
+        format!(
+            "{} monitoring [ApplicationMonitoringScore]",
+            self.application.name()
+        )
+    }
+}
+
+#[derive(Debug)]
+pub struct ApplicationMonitoringInterpret {
+    score: ApplicationMonitoringScore,
+}
+
+#[async_trait]
+impl<T: Topology + PrometheusApplicationMonitoring<CRDPrometheus>> Interpret<T>
+    for ApplicationMonitoringInterpret
+{
+    async fn execute(
+        &self,
+        inventory: &Inventory,
+        topology: &T,
+    ) -> Result<Outcome, InterpretError> {
+        let result = topology
+            .install_prometheus(
+                &self.score.sender,
+                inventory,
+                Some(self.score.receivers.clone()),
+            )
+            .await;
+
+        match result {
+            Ok(outcome) => match outcome {
+                PreparationOutcome::Success { details: _ } => {
+                    Ok(Outcome::success("Prometheus installed".into()))
+                }
+                PreparationOutcome::Noop => Ok(Outcome::noop()),
+            },
+            Err(err) => Err(InterpretError::from(err)),
+        }
+    }
+
+    fn get_name(&self) -> InterpretName {
+        InterpretName::ApplicationMonitoring
+    }
+
+    fn get_version(&self) -> Version {
+        todo!()
+    }
+
+    fn get_status(&self) -> InterpretStatus {
+        todo!()
+    }
+
+    fn get_children(&self) -> Vec<Id> {
+        todo!()
+    }
+}

harmony/src/modules/monitoring/application_monitoring/k8s_application_monitoring_score.rs

@@ -1,44 +0,0 @@
-use std::sync::{Arc, Mutex};
-
-use serde::Serialize;
-
-use crate::{
-    modules::monitoring::{
-        kube_prometheus::types::ServiceMonitor,
-        prometheus::{prometheus::Prometheus, prometheus_config::PrometheusConfig},
-    },
-    score::Score,
-    topology::{
-        HelmCommand, Topology,
-        oberservability::monitoring::{AlertReceiver, AlertRule, AlertingInterpret},
-        tenant::TenantManager,
-    },
-};
-
-#[derive(Clone, Debug, Serialize)]
-pub struct ApplicationPrometheusMonitoringScore {
-    pub receivers: Vec<Box<dyn AlertReceiver<Prometheus>>>,
-    pub rules: Vec<Box<dyn AlertRule<Prometheus>>>,
-    pub service_monitors: Vec<ServiceMonitor>,
-}
-
-impl<T: Topology + HelmCommand + TenantManager> Score<T> for ApplicationPrometheusMonitoringScore {
-    fn create_interpret(&self) -> Box<dyn crate::interpret::Interpret<T>> {
-        let mut prom_config = PrometheusConfig::new();
-        prom_config.alert_manager = true;
-
-        let config = Arc::new(Mutex::new(prom_config));
-        config
-            .try_lock()
-            .expect("couldn't lock config")
-            .additional_service_monitors = self.service_monitors.clone();
-        Box::new(AlertingInterpret {
-            sender: Prometheus::new(),
-            receivers: self.receivers.clone(),
-            rules: self.rules.clone(),
-        })
-    }
-    fn name(&self) -> String {
-        "ApplicationPrometheusMonitoringScore".to_string()
-    }
-}

harmony/src/modules/monitoring/application_monitoring/mod.rs

@@ -1 +1 @@
-pub mod k8s_application_monitoring_score;
+pub mod application_monitoring_score;

harmony/src/modules/monitoring/grafana/helm/helm_grafana.rs

@@ -4,15 +4,14 @@ use std::str::FromStr;
 use crate::modules::helm::chart::HelmChartScore;
 
 pub fn grafana_helm_chart_score(ns: &str) -> HelmChartScore {
-    let values = format!(
-        r#"
+    let values = r#"
 rbac:
   namespaced: true
 sidecar:
   dashboards:
     enabled: true
         "#
-    );
+    .to_string();
 
     HelmChartScore {
         namespace: Some(NonBlankString::from_str(ns).unwrap()),

harmony/src/modules/monitoring/kube_prometheus/crd/crd_alertmanager_config.rs

@@ -0,0 +1,50 @@
+use std::sync::Arc;
+
+use kube::CustomResource;
+use schemars::JsonSchema;
+use serde::{Deserialize, Serialize};
+
+use crate::topology::{
+    k8s::K8sClient,
+    oberservability::monitoring::{AlertReceiver, AlertSender},
+};
+
+#[derive(CustomResource, Serialize, Deserialize, Debug, Clone, JsonSchema)]
+#[kube(
+    group = "monitoring.coreos.com",
+    version = "v1alpha1",
+    kind = "AlertmanagerConfig",
+    plural = "alertmanagerconfigs",
+    namespaced
+)]
+pub struct AlertmanagerConfigSpec {
+    #[serde(flatten)]
+    pub data: serde_json::Value,
+}
+
+#[derive(Debug, Clone, Serialize)]
+pub struct CRDPrometheus {
+    pub namespace: String,
+    pub client: Arc<K8sClient>,
+}
+
+impl AlertSender for CRDPrometheus {
+    fn name(&self) -> String {
+        "CRDAlertManager".to_string()
+    }
+}
+
+impl Clone for Box<dyn AlertReceiver<CRDPrometheus>> {
+    fn clone(&self) -> Self {
+        self.clone_box()
+    }
+}
+
+impl Serialize for Box<dyn AlertReceiver<CRDPrometheus>> {
+    fn serialize<S>(&self, _serializer: S) -> Result<S::Ok, S::Error>
+    where
+        S: serde::Serializer,
+    {
+        todo!()
+    }
+}

harmony/src/modules/monitoring/kube_prometheus/crd/crd_alertmanagers.rs

@@ -0,0 +1,52 @@
+use kube::CustomResource;
+use schemars::JsonSchema;
+use serde::{Deserialize, Serialize};
+
+use super::crd_prometheuses::LabelSelector;
+
+/// Rust CRD for `Alertmanager` from Prometheus Operator
+#[derive(CustomResource, Serialize, Deserialize, Debug, Clone, JsonSchema)]
+#[kube(
+    group = "monitoring.coreos.com",
+    version = "v1",
+    kind = "Alertmanager",
+    plural = "alertmanagers",
+    namespaced
+)]
+#[serde(rename_all = "camelCase")]
+pub struct AlertmanagerSpec {
+    /// Number of replicas for HA
+    pub replicas: i32,
+
+    /// Selectors for AlertmanagerConfig CRDs
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub alertmanager_config_selector: Option<LabelSelector>,
+
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub alertmanager_config_namespace_selector: Option<LabelSelector>,
+
+    /// Optional pod template metadata (annotations, labels)
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub pod_metadata: Option<LabelSelector>,
+
+    /// Optional topology spread settings
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub version: Option<String>,
+}
+
+impl Default for AlertmanagerSpec {
+    fn default() -> Self {
+        AlertmanagerSpec {
+            replicas: 1,
+
+            // Match all AlertmanagerConfigs in the same namespace
+            alertmanager_config_namespace_selector: None,
+
+            // Empty selector matches all AlertmanagerConfigs in that namespace
+            alertmanager_config_selector: Some(LabelSelector::default()),
+
+            pod_metadata: None,
+            version: None,
+        }
+    }
+}

harmony/src/modules/monitoring/kube_prometheus/crd/crd_default_rules.rs

@@ -0,0 +1,25 @@
+use crate::modules::prometheus::alerts::k8s::{
+    deployment::alert_deployment_unavailable,
+    pod::{alert_container_restarting, alert_pod_not_ready, pod_failed},
+    pvc::high_pvc_fill_rate_over_two_days,
+    service::alert_service_down,
+};
+
+use super::crd_prometheus_rules::Rule;
+
+pub fn build_default_application_rules() -> Vec<Rule> {
+    let pod_failed: Rule = pod_failed().into();
+    let container_restarting: Rule = alert_container_restarting().into();
+    let pod_not_ready: Rule = alert_pod_not_ready().into();
+    let service_down: Rule = alert_service_down().into();
+    let deployment_unavailable: Rule = alert_deployment_unavailable().into();
+    let high_pvc_fill_rate: Rule = high_pvc_fill_rate_over_two_days().into();
+    vec![
+        pod_failed,
+        container_restarting,
+        pod_not_ready,
+        service_down,
+        deployment_unavailable,
+        high_pvc_fill_rate,
+    ]
+}

harmony/src/modules/monitoring/kube_prometheus/crd/crd_grafana.rs

@@ -0,0 +1,153 @@
+use std::collections::BTreeMap;
+
+use kube::CustomResource;
+use schemars::JsonSchema;
+use serde::{Deserialize, Serialize};
+
+use super::crd_prometheuses::LabelSelector;
+
+#[derive(CustomResource, Serialize, Deserialize, Debug, Clone, JsonSchema)]
+#[kube(
+    group = "grafana.integreatly.org",
+    version = "v1beta1",
+    kind = "Grafana",
+    plural = "grafanas",
+    namespaced
+)]
+#[serde(rename_all = "camelCase")]
+pub struct GrafanaSpec {
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub config: Option<GrafanaConfig>,
+
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub admin_user: Option<String>,
+
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub admin_password: Option<String>,
+
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub ingress: Option<GrafanaIngress>,
+
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub persistence: Option<GrafanaPersistence>,
+
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub resources: Option<ResourceRequirements>,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, JsonSchema)]
+#[serde(rename_all = "camelCase")]
+pub struct GrafanaConfig {
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub log: Option<GrafanaLogConfig>,
+
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub security: Option<GrafanaSecurityConfig>,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, JsonSchema)]
+#[serde(rename_all = "camelCase")]
+pub struct GrafanaLogConfig {
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub mode: Option<String>,
+
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub level: Option<String>,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, JsonSchema)]
+#[serde(rename_all = "camelCase")]
+pub struct GrafanaSecurityConfig {
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub admin_user: Option<String>,
+
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub admin_password: Option<String>,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, JsonSchema)]
+#[serde(rename_all = "camelCase")]
+pub struct GrafanaIngress {
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub enabled: Option<bool>,
+
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub hosts: Option<Vec<String>>,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, JsonSchema)]
+#[serde(rename_all = "camelCase")]
+pub struct GrafanaPersistence {
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub enabled: Option<bool>,
+
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub storage_class_name: Option<String>,
+
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub size: Option<String>,
+}
+
+// ------------------------------------------------------------------------------------------------
+
+#[derive(CustomResource, Serialize, Deserialize, Debug, Clone, JsonSchema)]
+#[kube(
+    group = "grafana.integreatly.org",
+    version = "v1beta1",
+    kind = "GrafanaDashboard",
+    plural = "grafanadashboards",
+    namespaced
+)]
+#[serde(rename_all = "camelCase")]
+pub struct GrafanaDashboardSpec {
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub resync_period: Option<String>,
+
+    pub instance_selector: LabelSelector,
+
+    pub json: String,
+}
+
+// ------------------------------------------------------------------------------------------------
+
+#[derive(CustomResource, Serialize, Deserialize, Debug, Clone, JsonSchema)]
+#[kube(
+    group = "grafana.integreatly.org",
+    version = "v1beta1",
+    kind = "GrafanaDatasource",
+    plural = "grafanadatasources",
+    namespaced
+)]
+#[serde(rename_all = "camelCase")]
+pub struct GrafanaDatasourceSpec {
+    pub instance_selector: LabelSelector,
+
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub allow_cross_namespace_import: Option<bool>,
+
+    pub datasource: GrafanaDatasourceConfig,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, JsonSchema)]
+#[serde(rename_all = "camelCase")]
+pub struct GrafanaDatasourceConfig {
+    pub access: String,
+    pub database: Option<String>,
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub json_data: Option<BTreeMap<String, String>>,
+    pub name: String,
+    pub r#type: String,
+    pub url: String,
+}
+
+// ------------------------------------------------------------------------------------------------
+
+#[derive(Serialize, Deserialize, Debug, Clone, JsonSchema, Default)]
+#[serde(rename_all = "camelCase")]
+pub struct ResourceRequirements {
+    #[serde(default, skip_serializing_if = "BTreeMap::is_empty")]
+    pub limits: BTreeMap<String, String>,
+
+    #[serde(default, skip_serializing_if = "BTreeMap::is_empty")]
+    pub requests: BTreeMap<String, String>,
+}

harmony/src/modules/monitoring/kube_prometheus/crd/crd_prometheus_rules.rs

@@ -0,0 +1,57 @@
+use std::collections::BTreeMap;
+
+use kube::CustomResource;
+use schemars::JsonSchema;
+use serde::{Deserialize, Serialize};
+
+use crate::modules::monitoring::alert_rule::prometheus_alert_rule::PrometheusAlertRule;
+
+#[derive(CustomResource, Debug, Serialize, Deserialize, Clone, JsonSchema)]
+#[kube(
+    group = "monitoring.coreos.com",
+    version = "v1",
+    kind = "PrometheusRule",
+    plural = "prometheusrules",
+    namespaced
+)]
+#[serde(rename_all = "camelCase")]
+pub struct PrometheusRuleSpec {
+    pub groups: Vec<RuleGroup>,
+}
+
+#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema)]
+pub struct RuleGroup {
+    pub name: String,
+    pub rules: Vec<Rule>,
+}
+
+#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema)]
+#[serde(rename_all = "camelCase")]
+pub struct Rule {
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub alert: Option<String>,
+
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub expr: Option<String>,
+
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub for_: Option<String>,
+
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub labels: Option<std::collections::BTreeMap<String, String>>,
+
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub annotations: Option<std::collections::BTreeMap<String, String>>,
+}
+
+impl From<PrometheusAlertRule> for Rule {
+    fn from(value: PrometheusAlertRule) -> Self {
+        Rule {
+            alert: Some(value.alert),
+            expr: Some(value.expr),
+            for_: value.r#for,
+            labels: Some(value.labels.into_iter().collect::<BTreeMap<_, _>>()),
+            annotations: Some(value.annotations.into_iter().collect::<BTreeMap<_, _>>()),
+        }
+    }
+}

harmony/src/modules/monitoring/kube_prometheus/crd/crd_prometheuses.rs

@@ -0,0 +1,118 @@
+use std::collections::BTreeMap;
+
+use kube::CustomResource;
+use schemars::JsonSchema;
+use serde::{Deserialize, Serialize};
+
+use crate::modules::monitoring::kube_prometheus::types::Operator;
+
+#[derive(CustomResource, Serialize, Deserialize, Debug, Clone, JsonSchema)]
+#[kube(
+    group = "monitoring.coreos.com",
+    version = "v1",
+    kind = "Prometheus",
+    plural = "prometheuses",
+    namespaced
+)]
+#[serde(rename_all = "camelCase")]
+pub struct PrometheusSpec {
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub alerting: Option<PrometheusSpecAlerting>,
+
+    pub service_account_name: String,
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub service_monitor_namespace_selector: Option<LabelSelector>,
+
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub service_monitor_selector: Option<LabelSelector>,
+
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub service_discovery_role: Option<String>,
+
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub pod_monitor_selector: Option<LabelSelector>,
+
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub rule_selector: Option<LabelSelector>,
+
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub rule_namespace_selector: Option<LabelSelector>,
+}
+
+#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema, Default)]
+#[serde(rename_all = "camelCase")]
+pub struct NamespaceSelector {
+    #[serde(default, skip_serializing_if = "Vec::is_empty")]
+    pub match_names: Vec<String>,
+}
+
+/// Contains alerting configuration, specifically Alertmanager endpoints.
+#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema, Default)]
+pub struct PrometheusSpecAlerting {
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub alertmanagers: Option<Vec<AlertmanagerEndpoints>>,
+}
+
+/// Represents an Alertmanager endpoint configuration used by Prometheus.
+#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema, Default)]
+pub struct AlertmanagerEndpoints {
+    /// Name of the Alertmanager Service.
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub name: Option<String>,
+
+    /// Namespace of the Alertmanager Service.
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub namespace: Option<String>,
+
+    /// Port to access on the Alertmanager Service (e.g. "web").
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub port: Option<String>,
+
+    /// Scheme to use for connecting (e.g. "http").
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub scheme: Option<String>,
+    // Other fields like `tls_config`, `path_prefix`, etc., can be added if needed.
+}
+
+#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema, Default)]
+#[serde(rename_all = "camelCase")]
+pub struct LabelSelector {
+    #[serde(default, skip_serializing_if = "BTreeMap::is_empty")]
+    pub match_labels: BTreeMap<String, String>,
+
+    #[serde(default, skip_serializing_if = "Vec::is_empty")]
+    pub match_expressions: Vec<LabelSelectorRequirement>,
+}
+
+#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema)]
+#[serde(rename_all = "camelCase")]
+pub struct LabelSelectorRequirement {
+    pub key: String,
+    pub operator: Operator,
+    #[serde(default, skip_serializing_if = "Vec::is_empty")]
+    pub values: Vec<String>,
+}
+
+impl Default for PrometheusSpec {
+    fn default() -> Self {
+        PrometheusSpec {
+            alerting: None,
+
+            service_account_name: "prometheus".into(),
+
+            // null means "only my namespace"
+            service_monitor_namespace_selector: None,
+
+            // empty selector means match all ServiceMonitors in that namespace
+            service_monitor_selector: Some(LabelSelector::default()),
+
+            service_discovery_role: Some("Endpoints".into()),
+
+            pod_monitor_selector: None,
+
+            rule_selector: None,
+
+            rule_namespace_selector: Some(LabelSelector::default()),
+        }
+    }
+}

harmony/src/modules/monitoring/kube_prometheus/crd/grafana_default_dashboard.rs

@@ -0,0 +1,203 @@
+pub fn build_default_dashboard(namespace: &str) -> String {
+    let dashboard = format!(
+        r#"{{
+  "annotations": {{
+    "list": []
+  }},
+  "editable": true,
+  "gnetId": null,
+  "graphTooltip": 0,
+  "id": null,
+  "iteration": 171105,
+  "panels": [
+    {{
+      "datasource": "$datasource",
+      "fieldConfig": {{
+        "defaults": {{
+          "unit": "short"
+        }},
+        "overrides": []
+      }},
+      "gridPos": {{
+        "h": 6,
+        "w": 6,
+        "x": 0,
+        "y": 0
+      }},
+      "id": 1,
+      "options": {{
+        "reduceOptions": {{
+          "calcs": ["lastNotNull"],
+          "fields": "",
+          "values": false
+        }}
+      }},
+      "pluginVersion": "9.0.0",
+      "targets": [
+        {{
+          "expr": "sum(kube_pod_status_phase{{namespace=\"{namespace}\",  phase=\"Running\"}})",
+          "legendFormat": "",
+          "refId": "A"
+        }}
+      ],
+      "title": "Pods in Namespace",
+      "type": "stat"
+    }},
+    {{
+      "datasource": "$datasource",
+      "fieldConfig": {{
+        "defaults": {{
+          "unit": "short"
+        }},
+        "overrides": []
+      }},
+      "gridPos": {{
+        "h": 6,
+        "w": 6,
+        "x": 6,
+        "y": 0
+      }},
+      "id": 2,
+      "options": {{
+        "reduceOptions": {{
+          "calcs": ["lastNotNull"],
+          "fields": "",
+          "values": false
+        }}
+      }},
+      "pluginVersion": "9.0.0",
+      "targets": [
+        {{
+          "expr": "sum(kube_pod_status_phase{{phase=\"Failed\", namespace=\"{namespace}\"}})",
+          "legendFormat": "",
+          "refId": "A"
+        }}
+      ],
+      "title": "Pods in Failed State",
+      "type": "stat"
+    }},
+    {{
+      "datasource": "$datasource",
+      "fieldConfig": {{
+        "defaults": {{
+          "unit": "percentunit"
+        }},
+        "overrides": []
+      }},
+      "gridPos": {{
+        "h": 6,
+        "w": 12,
+        "x": 0,
+        "y": 6
+      }},
+      "id": 3,
+      "options": {{
+        "reduceOptions": {{
+          "calcs": ["lastNotNull"],
+          "fields": "",
+          "values": false
+        }}
+      }},
+      "pluginVersion": "9.0.0",
+      "targets": [
+        {{
+          "expr": "sum(kube_deployment_status_replicas_available{{namespace=\"{namespace}\"}}) / sum(kube_deployment_spec_replicas{{namespace=\"{namespace}\"}})",
+          "legendFormat": "",
+          "refId": "A"
+        }}
+      ],
+      "title": "Deployment Health (Available / Desired)",
+      "type": "stat"
+    }},
+    {{
+      "datasource": "$datasource",
+      "fieldConfig": {{
+        "defaults": {{
+          "unit": "short"
+        }},
+        "overrides": []
+      }},
+      "gridPos": {{
+        "h": 6,
+        "w": 12,
+        "x": 0,
+        "y": 12
+      }},
+      "id": 4,
+      "options": {{
+        "reduceOptions": {{
+          "calcs": ["lastNotNull"],
+          "fields": "",
+          "values": false
+        }}
+      }},
+      "pluginVersion": "9.0.0",
+      "targets": [
+        {{
+          "expr": "sum by(pod) (rate(kube_pod_container_status_restarts_total{{namespace=\"{namespace}\"}}[5m]))",
+          "legendFormat": "{{{{pod}}}}",
+          "refId": "A"
+        }}
+      ],
+      "title": "Container Restarts (per pod)",
+      "type": "timeseries"
+    }},
+    {{
+      "datasource": "$datasource",
+      "fieldConfig": {{
+        "defaults": {{
+          "unit": "short"
+        }},
+        "overrides": []
+      }},
+      "gridPos": {{
+        "h": 6,
+        "w": 12,
+        "x": 0,
+        "y": 18
+      }},
+      "id": 5,
+      "options": {{
+        "reduceOptions": {{
+          "calcs": ["lastNotNull"],
+          "fields": "",
+          "values": false
+        }}
+      }},
+      "pluginVersion": "9.0.0",
+      "targets": [
+        {{
+          "expr": "sum(ALERTS{{alertstate=\"firing\", namespace=\"{namespace}\"}}) or vector(0)",
+          "legendFormat": "",
+          "refId": "A"
+        }}
+      ],
+      "title": "Firing Alerts in Namespace",
+      "type": "stat"
+    }}
+  ],
+  "schemaVersion": 36,
+  "templating": {{
+    "list": [
+      {{
+        "name": "datasource",
+        "type": "datasource",
+        "pluginId": "prometheus",
+        "label": "Prometheus",
+        "query": "prometheus",
+        "refresh": 1,
+        "hide": 0,
+        "current": {{
+          "selected": true,
+          "text": "Prometheus",
+          "value": "Prometheus"
+        }}
+      }}
+    ]
+  }},
+  "title": "Tenant Namespace Overview",
+  "version": 1
+}}"#
+    );
+    dashboard
+}

harmony/src/modules/monitoring/kube_prometheus/crd/grafana_operator.rs

@@ -0,0 +1,20 @@
+use std::str::FromStr;
+
+use non_blank_string_rs::NonBlankString;
+
+use crate::modules::helm::chart::HelmChartScore;
+
+pub fn grafana_operator_helm_chart_score(ns: String) -> HelmChartScore {
+    HelmChartScore {
+        namespace: Some(NonBlankString::from_str(&ns).unwrap()),
+        release_name: NonBlankString::from_str("grafana_operator").unwrap(),
+        chart_name: NonBlankString::from_str("oci://ghcr.io/grafana/helm-charts/grafana-operator")
+            .unwrap(),
+        chart_version: None,
+        values_overrides: None,
+        values_yaml: None,
+        create_namespace: true,
+        install_only: true,
+        repository: None,
+    }
+}

harmony/src/modules/monitoring/kube_prometheus/crd/mod.rs

@@ -0,0 +1,11 @@
+pub mod crd_alertmanager_config;
+pub mod crd_alertmanagers;
+pub mod crd_default_rules;
+pub mod crd_grafana;
+pub mod crd_prometheus_rules;
+pub mod crd_prometheuses;
+pub mod grafana_default_dashboard;
+pub mod grafana_operator;
+pub mod prometheus_operator;
+pub mod role;
+pub mod service_monitor;

harmony/src/modules/monitoring/kube_prometheus/crd/prometheus_operator.rs

@@ -0,0 +1,22 @@
+use std::str::FromStr;
+
+use non_blank_string_rs::NonBlankString;
+
+use crate::modules::helm::chart::HelmChartScore;
+
+pub fn prometheus_operator_helm_chart_score(ns: String) -> HelmChartScore {
+    HelmChartScore {
+        namespace: Some(NonBlankString::from_str(&ns).unwrap()),
+        release_name: NonBlankString::from_str("prometheus-operator").unwrap(),
+        chart_name: NonBlankString::from_str(
+            "oci://hub.nationtech.io/harmony/nt-prometheus-operator",
+        )
+        .unwrap(),
+        chart_version: None,
+        values_overrides: None,
+        values_yaml: None,
+        create_namespace: true,
+        install_only: true,
+        repository: None,
+    }
+}

harmony/src/modules/monitoring/kube_prometheus/crd/role.rs

@@ -0,0 +1,62 @@
+use k8s_openapi::api::{
+    core::v1::ServiceAccount,
+    rbac::v1::{PolicyRule, Role, RoleBinding, RoleRef, Subject},
+};
+use kube::api::ObjectMeta;
+
+pub fn build_prom_role(role_name: String, namespace: String) -> Role {
+    Role {
+        metadata: ObjectMeta {
+            name: Some(role_name),
+            namespace: Some(namespace),
+            ..Default::default()
+        },
+        rules: Some(vec![PolicyRule {
+            api_groups: Some(vec!["".into()]), // core API group
+            resources: Some(vec!["services".into(), "endpoints".into(), "pods".into()]),
+            verbs: vec!["get".into(), "list".into(), "watch".into()],
+            ..Default::default()
+        }]),
+    }
+}
+
+pub fn build_prom_rolebinding(
+    role_name: String,
+    namespace: String,
+    service_account_name: String,
+) -> RoleBinding {
+    RoleBinding {
+        metadata: ObjectMeta {
+            name: Some(format!("{}-rolebinding", role_name)),
+            namespace: Some(namespace.clone()),
+            ..Default::default()
+        },
+        role_ref: RoleRef {
+            api_group: "rbac.authorization.k8s.io".into(),
+            kind: "Role".into(),
+            name: role_name,
+        },
+        subjects: Some(vec![Subject {
+            kind: "ServiceAccount".into(),
+            name: service_account_name,
+            namespace: Some(namespace.clone()),
+            ..Default::default()
+        }]),
+    }
+}
+
+pub fn build_prom_service_account(
+    service_account_name: String,
+    namespace: String,
+) -> ServiceAccount {
+    ServiceAccount {
+        automount_service_account_token: None,
+        image_pull_secrets: None,
+        metadata: ObjectMeta {
+            name: Some(service_account_name),
+            namespace: Some(namespace),
+            ..Default::default()
+        },
+        secrets: None,
+    }
+}

harmony/src/modules/monitoring/kube_prometheus/crd/service_monitor.rs

@@ -0,0 +1,87 @@
+use std::collections::HashMap;
+
+use kube::CustomResource;
+use schemars::JsonSchema;
+use serde::{Deserialize, Serialize};
+
+use crate::modules::monitoring::kube_prometheus::types::{
+    HTTPScheme, MatchExpression, NamespaceSelector, Operator, Selector,
+    ServiceMonitor as KubeServiceMonitor, ServiceMonitorEndpoint,
+};
+
+/// This is the top-level struct for the ServiceMonitor Custom Resource.
+/// The `#[derive(CustomResource)]` macro handles all the boilerplate for you,
+/// including the `impl Resource`.
+#[derive(CustomResource, Serialize, Deserialize, Debug, Clone, JsonSchema)]
+#[kube(
+    group = "monitoring.coreos.com",
+    version = "v1",
+    kind = "ServiceMonitor",
+    plural = "servicemonitors",
+    namespaced
+)]
+#[serde(rename_all = "camelCase")]
+pub struct ServiceMonitorSpec {
+    /// A label selector to select services to monitor.
+    pub selector: Selector,
+
+    /// A list of endpoints on the selected services to be monitored.
+    pub endpoints: Vec<ServiceMonitorEndpoint>,
+
+    /// Selector to select which namespaces the Kubernetes Endpoints objects
+    /// are discovered from.
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub namespace_selector: Option<NamespaceSelector>,
+
+    /// The label to use to retrieve the job name from.
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub job_label: Option<String>,
+
+    /// Pod-based target labels to transfer from the Kubernetes Pod onto the target.
+    #[serde(default, skip_serializing_if = "Vec::is_empty")]
+    pub pod_target_labels: Vec<String>,
+
+    /// TargetLabels transfers labels on the Kubernetes Service object to the target.
+    #[serde(default, skip_serializing_if = "Vec::is_empty")]
+    pub target_labels: Vec<String>,
+}
+
+impl Default for ServiceMonitorSpec {
+    fn default() -> Self {
+        let labels = HashMap::new();
+        Self {
+            selector: Selector {
+                match_labels: { labels },
+                match_expressions: vec![MatchExpression {
+                    key: "app.kubernetes.io/name".into(),
+                    operator: Operator::Exists,
+                    values: vec![],
+                }],
+            },
+            endpoints: vec![ServiceMonitorEndpoint {
+                port: Some("http".to_string()),
+                path: Some("/metrics".into()),
+                interval: Some("30s".into()),
+                scheme: Some(HTTPScheme::HTTP),
+                ..Default::default()
+            }],
+            namespace_selector: None, // only the same namespace
+            job_label: Some("app".into()),
+            pod_target_labels: vec![],
+            target_labels: vec![],
+        }
+    }
+}
+
+impl From<KubeServiceMonitor> for ServiceMonitorSpec {
+    fn from(value: KubeServiceMonitor) -> Self {
+        Self {
+            selector: value.selector,
+            endpoints: value.endpoints,
+            namespace_selector: value.namespace_selector,
+            job_label: value.job_label,
+            pod_target_labels: value.pod_target_labels,
+            target_labels: value.target_labels,
+        }
+    }
+}

harmony/src/modules/monitoring/kube_prometheus/helm/config.rs

@@ -27,6 +27,12 @@ pub struct KubePrometheusConfig {
     pub alert_rules: Vec<AlertManagerAdditionalPromRules>,
     pub additional_service_monitors: Vec<ServiceMonitor>,
 }
+impl Default for KubePrometheusConfig {
+    fn default() -> Self {
+        Self::new()
+    }
+}
+
 impl KubePrometheusConfig {
     pub fn new() -> Self {
         Self {
@@ -35,7 +41,7 @@ impl KubePrometheusConfig {
             windows_monitoring: false,
             alert_manager: true,
             grafana: true,
-            node_exporter: false,
+            node_exporter: true,
             prometheus: true,
             kubernetes_service_monitors: true,
             kubernetes_api_server: true,

harmony/src/modules/monitoring/kube_prometheus/helm/kube_prometheus_helm_chart.rs

@@ -12,8 +12,8 @@ use crate::modules::{
     helm::chart::HelmChartScore,
     monitoring::kube_prometheus::types::{
         AlertGroup, AlertManager, AlertManagerAdditionalPromRules, AlertManagerConfig,
-        AlertManagerRoute, AlertManagerSpec, AlertManagerValues, ConfigReloader, Limits,
-        PrometheusConfig, Requests, Resources,
+        AlertManagerConfigSelector, AlertManagerRoute, AlertManagerSpec, AlertManagerValues,
+        ConfigReloader, Limits, PrometheusConfig, Requests, Resources,
     },
 };
 
@@ -35,7 +35,7 @@ pub fn kube_prometheus_helm_chart_score(
     let kube_proxy = config.kube_proxy.to_string();
     let kube_state_metrics = config.kube_state_metrics.to_string();
     let node_exporter = config.node_exporter.to_string();
-    let prometheus_operator = config.prometheus_operator.to_string();
+    let _prometheus_operator = config.prometheus_operator.to_string();
     let prometheus = config.prometheus.to_string();
     let resource_limit = Resources {
         limits: Limits {
@@ -64,7 +64,7 @@ pub fn kube_prometheus_helm_chart_score(
             indent_lines(&yaml, indent_level + 2)
         )
     }
-    let resource_section = resource_block(&resource_limit, 2);
+    let _resource_section = resource_block(&resource_limit, 2);
 
     let mut values = format!(
         r#"
@@ -332,6 +332,11 @@ prometheusOperator:
             .push(receiver.channel_receiver.clone());
     }
 
+    let mut labels = BTreeMap::new();
+    labels.insert("alertmanagerConfig".to_string(), "enabled".to_string());
+    let alert_manager_config_selector = AlertManagerConfigSelector {
+        match_labels: labels,
+    };
     let alert_manager_values = AlertManagerValues {
         alertmanager: AlertManager {
             enabled: config.alert_manager,
@@ -347,6 +352,8 @@ prometheusOperator:
                         cpu: "100m".to_string(),
                     },
                 },
+                alert_manager_config_selector,
+                replicas: 2,
             },
             init_config_reloader: ConfigReloader {
                 resources: Resources {

harmony/src/modules/monitoring/kube_prometheus/mod.rs

@@ -1,3 +1,4 @@
+pub mod crd;
 pub mod helm;
 pub mod helm_prometheus_alert_score;
 pub mod prometheus;

harmony/src/modules/monitoring/kube_prometheus/prometheus.rs

@@ -55,6 +55,12 @@ pub struct KubePrometheus {
     pub config: Arc<Mutex<KubePrometheusConfig>>,
 }
 
+impl Default for KubePrometheus {
+    fn default() -> Self {
+        Self::new()
+    }
+}
+
 impl KubePrometheus {
     pub fn new() -> Self {
         Self {
@@ -113,8 +119,7 @@ impl KubePrometheus {
         topology: &T,
     ) -> Result<Outcome, InterpretError> {
         kube_prometheus_helm_chart_score(self.config.clone())
-            .create_interpret()
-            .execute(inventory, topology)
+            .interpret(inventory, topology)
             .await
     }
 }

harmony/src/modules/monitoring/kube_prometheus/types.rs

@@ -1,7 +1,8 @@
 use std::collections::{BTreeMap, HashMap};
 
 use async_trait::async_trait;
-use serde::Serialize;
+use schemars::JsonSchema;
+use serde::{Deserialize, Serialize};
 use serde_yaml::{Mapping, Sequence, Value};
 
 use crate::modules::monitoring::alert_rule::prometheus_alert_rule::AlertManagerRuleGroup;
@@ -55,6 +56,14 @@ pub struct AlertManagerChannelConfig {
 #[serde(rename_all = "camelCase")]
 pub struct AlertManagerSpec {
     pub(crate) resources: Resources,
+    pub replicas: u32,
+    pub alert_manager_config_selector: AlertManagerConfigSelector,
+}
+
+#[derive(Debug, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct AlertManagerConfigSelector {
+    pub match_labels: BTreeMap<String, String>,
 }
 
 #[derive(Debug, Clone, Serialize)]
@@ -86,7 +95,7 @@ pub struct AlertGroup {
     pub groups: Vec<AlertManagerRuleGroup>,
 }
 
-#[derive(Debug, Clone, Serialize)]
+#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema)]
 pub enum HTTPScheme {
     #[serde(rename = "http")]
     HTTP,
@@ -94,7 +103,7 @@ pub enum HTTPScheme {
     HTTPS,
 }
 
-#[derive(Debug, Clone, Serialize)]
+#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema)]
 pub enum Operator {
     In,
     NotIn,
@@ -139,74 +148,83 @@ pub struct ServiceMonitorTLSConfig {
     pub server_name: Option<String>,
 }
 
-#[derive(Debug, Clone, Serialize)]
+#[derive(Serialize, Deserialize, Debug, Clone, JsonSchema, Default)]
 #[serde(rename_all = "camelCase")]
 pub struct ServiceMonitorEndpoint {
-    // ## Name of the endpoint's service port
-    // ## Mutually exclusive with targetPort
+    /// Name of the service port this endpoint refers to.
     pub port: Option<String>,
 
-    // ## Name or number of the endpoint's target port
-    // ## Mutually exclusive with port
-    pub target_port: Option<String>,
-
-    // ## File containing bearer token to be used when scraping targets
-    // ##
-    pub bearer_token_file: Option<String>,
-
-    // ## Interval at which metrics should be scraped
-    // ##
+    /// Interval at which metrics should be scraped.
+    #[serde(default, skip_serializing_if = "Option::is_none")]
     pub interval: Option<String>,
 
-    // ## HTTP path to scrape for metrics
-    // ##
-    pub path: String,
+    /// The HTTP path to scrape for metrics.
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub path: Option<String>,
 
-    // ## HTTP scheme to use for scraping
-    // ##
-    pub scheme: HTTPScheme,
+    /// HTTP scheme to use for scraping.
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub scheme: Option<HTTPScheme>,
 
-    // ## TLS configuration to use when scraping the endpoint
-    // ##
-    pub tls_config: Option<ServiceMonitorTLSConfig>,
+    /// Relabelings to apply to samples before scraping.
+    #[serde(default, skip_serializing_if = "Vec::is_empty")]
+    pub relabelings: Vec<RelabelConfig>,
 
-    // ## MetricRelabelConfigs to apply to samples after scraping, but before ingestion.
-    // ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/main/Documentation/api-reference/api.md#relabelconfig
-    // ##
-    // # - action: keep
-    // #   regex: 'kube_(daemonset|deployment|pod|namespace|node|statefulset).+'
-    // #   sourceLabels: [__name__]
-    pub metric_relabelings: Vec<Mapping>,
-
-    // ## RelabelConfigs to apply to samples before scraping
-    // ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/main/Documentation/api-reference/api.md#relabelconfig
-    // ##
-    // # - sourceLabels: [__meta_kubernetes_pod_node_name]
-    // #   separator: ;
-    // #   regex: ^(.*)$
-    // #   targetLabel: nodename
-    // #   replacement: $1
-    // #   action: replace
-    pub relabelings: Vec<Mapping>,
+    /// MetricRelabelings to apply to samples after scraping, but before ingestion.
+    #[serde(default, skip_serializing_if = "Vec::is_empty")]
+    pub metric_relabelings: Vec<RelabelConfig>,
 }
 
-#[derive(Debug, Clone, Serialize)]
+#[derive(Serialize, Deserialize, Debug, Clone, JsonSchema)]
+#[serde(rename_all = "camelCase")]
+pub struct RelabelConfig {
+    /// The action to perform based on the regex matching.
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub action: Option<String>,
+
+    /// A list of labels from which to extract values.
+    #[serde(default, skip_serializing_if = "Vec::is_empty")]
+    pub source_labels: Vec<String>,
+
+    /// Separator to be used when concatenating source_labels.
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub separator: Option<String>,
+
+    /// The label to which the resulting value is written.
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub target_label: Option<String>,
+
+    /// A regular expression to match against the concatenated source label values.
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub regex: Option<String>,
+
+    /// The replacement value to use.
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub replacement: Option<String>,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, JsonSchema)]
 #[serde(rename_all = "camelCase")]
 pub struct MatchExpression {
     pub key: String,
-    pub operator: Operator,
+    pub operator: Operator, // "In", "NotIn", "Exists", "DoesNotExist"
+    #[serde(default, skip_serializing_if = "Vec::is_empty")]
     pub values: Vec<String>,
 }
 
-#[derive(Debug, Clone, Serialize)]
+#[derive(Serialize, Deserialize, Debug, Clone, JsonSchema, Default)]
 #[serde(rename_all = "camelCase")]
 pub struct Selector {
-    //   # label selector for services
+    /// A map of key-value pairs to match.
+    #[serde(default, skip_serializing_if = "HashMap::is_empty")]
     pub match_labels: HashMap<String, String>,
+
+    /// A list of label selector requirements.
+    #[serde(default, skip_serializing_if = "Vec::is_empty")]
     pub match_expressions: Vec<MatchExpression>,
 }
 
-#[derive(Debug, Clone, Serialize)]
+#[derive(Debug, Clone, Serialize, Deserialize)]
 #[serde(rename_all = "camelCase")]
 pub struct ServiceMonitor {
     pub name: String,
@@ -250,10 +268,15 @@ pub struct ServiceMonitor {
     pub fallback_scrape_protocol: Option<String>,
 }
 
-#[derive(Debug, Serialize, Clone)]
+#[derive(Serialize, Deserialize, Debug, Clone, JsonSchema, Default)]
 #[serde(rename_all = "camelCase")]
 pub struct NamespaceSelector {
+    /// Select all namespaces.
+    #[serde(default, skip_serializing_if = "std::ops::Not::not")]
     pub any: bool,
+
+    /// List of namespace names to select from.
+    #[serde(default, skip_serializing_if = "Vec::is_empty")]
     pub match_names: Vec<String>,
 }
 
@@ -275,19 +298,3 @@ impl Default for ServiceMonitor {
         }
     }
 }
-
-impl Default for ServiceMonitorEndpoint {
-    fn default() -> Self {
-        Self {
-            port: Some("80".to_string()),
-            target_port: Default::default(),
-            bearer_token_file: Default::default(),
-            interval: Default::default(),
-            path: "/metrics".to_string(),
-            scheme: HTTPScheme::HTTP,
-            tls_config: Default::default(),
-            metric_relabelings: Default::default(),
-            relabelings: Default::default(),
-        }
-    }
-}

harmony/src/modules/monitoring/ntfy/helm/ntfy_helm_chart.rs

@@ -1,9 +1,25 @@
 use non_blank_string_rs::NonBlankString;
 use std::str::FromStr;
 
-use crate::modules::helm::chart::{HelmChartScore, HelmRepository};
+use crate::{modules::helm::chart::HelmChartScore, topology::DeploymentTarget};
+
+pub fn ntfy_helm_chart_score(
+    namespace: String,
+    host: String,
+    target: DeploymentTarget,
+) -> HelmChartScore {
+    // TODO not actually the correct logic, this should be fixed by using an ingresss which is the
+    // correct k8s standard.
+    //
+    // Another option is to delegate to the topology the ingress technology it wants to use Route,
+    // Ingress or other
+    let route_enabled = match target {
+        DeploymentTarget::LocalDev => false,
+        DeploymentTarget::Staging => true,
+        DeploymentTarget::Production => true,
+    };
+    let ingress_enabled = !route_enabled;
 
-pub fn ntfy_helm_chart_score(namespace: String, host: String) -> HelmChartScore {
     let values = format!(
         r#"
 replicaCount: 1
@@ -25,23 +41,14 @@ serviceAccount:
 
 service:
   type: ClusterIP
-  port: 80
+  port: 8080
 
 ingress:
-  enabled: true
-#  annotations:
-    # kubernetes.io/ingress.class: nginx
-    # kubernetes.io/tls-acme: "true"
-  hosts:
-    - host: {host}
-      paths:
-        - path: /
-          pathType: ImplementationSpecific
-  tls: []
-  #  - secretName: chart-example-tls
-  #    hosts:
-  #      - chart-example.local
+  enabled: {ingress_enabled}
 
+route:
+  enabled: {route_enabled}
+  host: {host}
 
 autoscaling:
   enabled: false
@@ -49,7 +56,7 @@ autoscaling:
 config:
   enabled: true
   data:
-#    base-url: "https://ntfy.something.com"
+    base-url: "https://{host}"
     auth-file: "/var/cache/ntfy/user.db"
     auth-default-access: "deny-all"
     cache-file: "/var/cache/ntfy/cache.db"
@@ -58,6 +65,8 @@ config:
     # web-root: "disable"
     enable-signup: false
     enable-login: "true"
+    enable-metrics: "true"
+    listen-http: ":8080"
 
 persistence:
   enabled: true
@@ -68,16 +77,12 @@ persistence:
     HelmChartScore {
         namespace: Some(NonBlankString::from_str(&namespace).unwrap()),
         release_name: NonBlankString::from_str("ntfy").unwrap(),
-        chart_name: NonBlankString::from_str("sarab97/ntfy").unwrap(),
-        chart_version: Some(NonBlankString::from_str("0.1.7").unwrap()),
+        chart_name: NonBlankString::from_str("oci://hub.nationtech.io/harmony/ntfy").unwrap(),
+        chart_version: Some(NonBlankString::from_str("0.1.7-nationtech.1").unwrap()),
         values_overrides: None,
         values_yaml: Some(values.to_string()),
         create_namespace: true,
         install_only: false,
-        repository: Some(HelmRepository::new(
-            "sarab97".to_string(),
-            url::Url::parse("https://charts.sarabsingh.com").unwrap(),
-            true,
-        )),
+        repository: None,
     }
 }

harmony/src/modules/monitoring/ntfy/mod.rs

@@ -1,2 +1,3 @@
 pub mod helm;
+#[allow(clippy::module_inception)]
 pub mod ntfy;

harmony/src/modules/monitoring/ntfy/ntfy.rs

@@ -1,7 +1,7 @@
 use std::sync::Arc;
 
 use async_trait::async_trait;
-use log::debug;
+use log::info;
 use serde::Serialize;
 use strum::{Display, EnumString};
 
@@ -11,7 +11,7 @@ use crate::{
     inventory::Inventory,
     modules::monitoring::ntfy::helm::ntfy_helm_chart::ntfy_helm_chart_score,
     score::Score,
-    topology::{HelmCommand, K8sclient, Topology, k8s::K8sClient},
+    topology::{HelmCommand, K8sclient, MultiTargetTopology, Topology, k8s::K8sClient},
 };
 
 #[derive(Debug, Clone, Serialize)]
@@ -20,7 +20,7 @@ pub struct NtfyScore {
     pub host: String,
 }
 
-impl<T: Topology + HelmCommand + K8sclient> Score<T> for NtfyScore {
+impl<T: Topology + HelmCommand + K8sclient + MultiTargetTopology> Score<T> for NtfyScore {
     fn create_interpret(&self) -> Box<dyn Interpret<T>> {
         Box::new(NtfyInterpret {
             score: self.clone(),
@@ -28,7 +28,7 @@ impl<T: Topology + HelmCommand + K8sclient> Score<T> for NtfyScore {
     }
 
     fn name(&self) -> String {
-        format!("Ntfy")
+        "alert receiver [NtfyScore]".into()
     }
 }
 
@@ -39,31 +39,21 @@ pub struct NtfyInterpret {
 
 #[derive(Debug, EnumString, Display)]
 enum NtfyAccessMode {
-    #[strum(serialize = "read-write", serialize = "rw", to_string = "read-write")]
+    #[strum(serialize = "read-write", serialize = "rw")]
     ReadWrite,
-    #[strum(
-        serialize = "read-only",
-        serialize = "ro",
-        serialize = "read",
-        to_string = "read-only"
-    )]
+    #[strum(serialize = "read-only", serialize = "ro", serialize = "read")]
     ReadOnly,
-    #[strum(
-        serialize = "write-only",
-        serialize = "wo",
-        serialize = "write",
-        to_string = "write-only"
-    )]
+    #[strum(serialize = "write-only", serialize = "wo", serialize = "write")]
     WriteOnly,
-    #[strum(serialize = "none", to_string = "deny")]
+    #[strum(serialize = "deny", serialize = "none")]
     Deny,
 }
 
 #[derive(Debug, EnumString, Display)]
 enum NtfyRole {
-    #[strum(serialize = "user", to_string = "user")]
+    #[strum(serialize = "user")]
     User,
-    #[strum(serialize = "admin", to_string = "admin")]
+    #[strum(serialize = "admin")]
     Admin,
 }
 
@@ -87,7 +77,7 @@ impl NtfyInterpret {
                 vec![
                     "sh",
                     "-c",
-                    format!("NTFY_PASSWORD={password} ntfy user add --role={role} {username}")
+                    format!("NTFY_PASSWORD={password} ntfy user add --role={role} --ignore-exists {username}")
                         .as_str(),
                 ],
             )
@@ -95,69 +85,52 @@ impl NtfyInterpret {
 
         Ok(())
     }
-
-    async fn set_access(
-        &self,
-        k8s_client: Arc<K8sClient>,
-        username: &str,
-        topic: &str,
-        mode: NtfyAccessMode,
-    ) -> Result<(), String> {
-        k8s_client
-            .exec_app(
-                "ntfy".to_string(),
-                Some(&self.score.namespace),
-                vec![
-                    "sh",
-                    "-c",
-                    format!("ntfy access {username} {topic} {mode}").as_str(),
-                ],
-            )
-            .await?;
-
-        Ok(())
-    }
 }
 
 /// We need a ntfy interpret to wrap the HelmChartScore in order to run the score, and then bootstrap the config inside ntfy
 #[async_trait]
-impl<T: Topology + HelmCommand + K8sclient> Interpret<T> for NtfyInterpret {
+impl<T: Topology + HelmCommand + K8sclient + MultiTargetTopology> Interpret<T> for NtfyInterpret {
     async fn execute(
         &self,
         inventory: &Inventory,
         topology: &T,
     ) -> Result<Outcome, InterpretError> {
-        ntfy_helm_chart_score(self.score.namespace.clone(), self.score.host.clone())
-            .create_interpret()
-            .execute(inventory, topology)
+        ntfy_helm_chart_score(
+            self.score.namespace.clone(),
+            self.score.host.clone(),
+            topology.current_target(),
+        )
+        .interpret(inventory, topology)
         .await?;
 
-        debug!("installed ntfy helm chart");
+        info!("installed ntfy helm chart");
         let client = topology
             .k8s_client()
             .await
             .expect("couldn't get k8s client");
 
+        info!("deploying ntfy...");
         client
             .wait_until_deployment_ready(
                 "ntfy".to_string(),
-                Some(&self.score.namespace.as_str()),
+                Some(self.score.namespace.as_str()),
                 None,
             )
             .await?;
-        debug!("created k8s client");
+        info!("ntfy deployed");
 
+        info!("adding user harmony");
         self.add_user(client, "harmony", "harmony", Some(NtfyRole::Admin))
             .await?;
+        info!("user added");
 
-        debug!("exec into pod done");
-
-        Ok(Outcome::success("installed ntfy".to_string()))
+        Ok(Outcome::success("Ntfy installed".to_string()))
     }
 
     fn get_name(&self) -> InterpretName {
-        todo!()
+        InterpretName::Ntfy
     }
+
     fn get_version(&self) -> Version {
         todo!()
     }

harmony/src/modules/monitoring/prometheus/mod.rs

@@ -1,3 +1,4 @@
 pub mod helm;
+#[allow(clippy::module_inception)]
 pub mod prometheus;
 pub mod prometheus_config;

harmony/src/modules/monitoring/prometheus/prometheus.rs

@@ -37,6 +37,12 @@ impl AlertSender for Prometheus {
     }
 }
 
+impl Default for Prometheus {
+    fn default() -> Self {
+        Self::new()
+    }
+}
+
 impl Prometheus {
     pub fn new() -> Self {
         Self {
@@ -94,8 +100,7 @@ impl Prometheus {
         topology: &T,
     ) -> Result<Outcome, InterpretError> {
         prometheus_helm_chart_score(self.config.clone())
-            .create_interpret()
-            .execute(inventory, topology)
+            .interpret(inventory, topology)
             .await
     }
     pub async fn install_grafana<T: Topology + HelmCommand + Send + Sync>(
@@ -110,13 +115,12 @@ impl Prometheus {
 
         if let Some(ns) = namespace.as_deref() {
             grafana_helm_chart_score(ns)
-                .create_interpret()
-                .execute(inventory, topology)
+                .interpret(inventory, topology)
                 .await
         } else {
-            Err(InterpretError::new(format!(
-                "could not install grafana, missing namespace",
-            )))
+            Err(InterpretError::new(
+                "could not install grafana, missing namespace".to_string(),
+            ))
         }
     }
 }

harmony/src/modules/monitoring/prometheus/prometheus_config.rs

@@ -16,6 +16,12 @@ pub struct PrometheusConfig {
     pub additional_service_monitors: Vec<ServiceMonitor>,
 }
 
+impl Default for PrometheusConfig {
+    fn default() -> Self {
+        Self::new()
+    }
+}
+
 impl PrometheusConfig {
     pub fn new() -> Self {
         Self {

harmony/src/modules/okd/bootstrap_dhcp.rs

@@ -32,7 +32,7 @@ impl OKDBootstrapDhcpScore {
             logical_host: topology.bootstrap_host.clone(),
             physical_host: inventory
                 .worker_host
-                .get(0)
+                .first()
                 .expect("Should have at least one worker to be used as bootstrap node")
                 .clone(),
         });

harmony/src/modules/okd/upgrade.rs

@@ -6,6 +6,12 @@ pub struct OKDUpgradeScore {
     _target_version: Version,
 }
 
+impl Default for OKDUpgradeScore {
+    fn default() -> Self {
+        Self::new()
+    }
+}
+
 impl OKDUpgradeScore {
     pub fn new() -> Self {
         Self {

harmony/src/modules/prometheus/alerts/k8s/deployment.rs

@@ -0,0 +1,23 @@
+use std::collections::HashMap;
+
+use crate::modules::monitoring::alert_rule::prometheus_alert_rule::PrometheusAlertRule;
+
+pub fn alert_deployment_unavailable() -> PrometheusAlertRule {
+    PrometheusAlertRule {
+        alert: "DeploymentUnavailable".into(),
+        expr: "kube_deployment_status_replicas_unavailable > 0".into(),
+        r#for: Some("2m".into()),
+        labels: HashMap::from([("severity".into(), "warning".into())]),
+        annotations: HashMap::from([
+            (
+                "summary".into(),
+                "Deployment has unavailable replicas".into(),
+            ),
+            (
+                "description".into(),
+                "A deployment in this namespace has unavailable replicas for over 2 minutes."
+                    .into(),
+            ),
+        ]),
+    }
+}

harmony/src/modules/prometheus/alerts/k8s/memory_usage.rs

@@ -0,0 +1,37 @@
+use std::collections::HashMap;
+
+use crate::modules::monitoring::alert_rule::prometheus_alert_rule::PrometheusAlertRule;
+
+pub fn alert_high_memory_usage() -> PrometheusAlertRule {
+    PrometheusAlertRule {
+        alert: "HighMemoryUsage".into(),
+        expr: "container_memory_working_set_bytes{container!=\"\",namespace!=\"\"} > 500000000"
+            .into(),
+        r#for: Some("2m".into()),
+        labels: HashMap::from([("severity".into(), "warning".into())]),
+        annotations: HashMap::from([
+            ("summary".into(), "Pod is using high memory".into()),
+            (
+                "description".into(),
+                "A pod is consuming more than 500Mi of memory.".into(),
+            ),
+        ]),
+    }
+}
+
+pub fn alert_high_cpu_usage() -> PrometheusAlertRule {
+    PrometheusAlertRule {
+        alert: "HighCPUUsage".into(),
+        expr: "rate(container_cpu_usage_seconds_total{container!=\"\",namespace!=\"\"}[1m]) > 0.9"
+            .into(),
+        r#for: Some("1m".into()),
+        labels: HashMap::from([("severity".into(), "warning".into())]),
+        annotations: HashMap::from([
+            ("summary".into(), "Pod is using high CPU".into()),
+            (
+                "description".into(),
+                "A pod is using more than 90% of a core over 1 minute.".into(),
+            ),
+        ]),
+    }
+}

harmony/src/modules/prometheus/alerts/k8s/mod.rs

@@ -1 +1,5 @@
+pub mod deployment;
+pub mod memory_usage;
+pub mod pod;
 pub mod pvc;
+pub mod service;

harmony/src/modules/prometheus/alerts/k8s/pod.rs

@@ -0,0 +1,55 @@
+use std::collections::HashMap;
+
+use crate::modules::monitoring::alert_rule::prometheus_alert_rule::PrometheusAlertRule;
+
+pub fn pod_failed() -> PrometheusAlertRule {
+    PrometheusAlertRule {
+        alert: "PodFailed".into(),
+        expr: "kube_pod_status_phase{phase=\"Failed\"} > 2".into(),
+        r#for: Some("2m".into()),
+        labels: HashMap::from([("severity".into(), "critical".into())]),
+        annotations: HashMap::from([
+            ("summary".into(), "A pod has failed".into()),
+            (
+                "description".into(),
+                "One or more pods are in Failed phase.".into(),
+            ),
+        ]),
+    }
+}
+
+pub fn alert_container_restarting() -> PrometheusAlertRule {
+    PrometheusAlertRule {
+        alert: "ContainerRestarting".into(),
+        expr: "increase(kube_pod_container_status_restarts_total[5m]) > 3".into(),
+        r#for: Some("5m".into()),
+        labels: HashMap::from([("severity".into(), "warning".into())]),
+        annotations: HashMap::from([
+            (
+                "summary".into(),
+                "Container is restarting frequently".into(),
+            ),
+            (
+                "description".into(),
+                "A container in this namespace has restarted more than 3 times in 5 minutes."
+                    .into(),
+            ),
+        ]),
+    }
+}
+
+pub fn alert_pod_not_ready() -> PrometheusAlertRule {
+    PrometheusAlertRule {
+        alert: "PodNotReady".into(),
+        expr: "kube_pod_status_ready{condition=\"true\"} == 0".into(),
+        r#for: Some("2m".into()),
+        labels: HashMap::from([("severity".into(), "warning".into())]),
+        annotations: HashMap::from([
+            ("summary".into(), "Pod is not ready".into()),
+            (
+                "description".into(),
+                "A pod in the namespace is not reporting Ready status.".into(),
+            ),
+        ]),
+    }
+}

harmony/src/modules/prometheus/alerts/k8s/service.rs

@@ -0,0 +1,19 @@
+use std::collections::HashMap;
+
+use crate::modules::monitoring::alert_rule::prometheus_alert_rule::PrometheusAlertRule;
+
+pub fn alert_service_down() -> PrometheusAlertRule {
+    PrometheusAlertRule {
+        alert: "ServiceDown".into(),
+        expr: "up == 0".into(),
+        r#for: Some("1m".into()),
+        labels: HashMap::from([("severity".into(), "critical".into())]),
+        annotations: HashMap::from([
+            ("summary".into(), "Service is down".into()),
+            (
+                "description".into(),
+                "A target service in the namespace is not responding to Prometheus scrapes.".into(),
+            ),
+        ]),
+    }
+}

harmony/src/modules/prometheus/k8s_prometheus_alerting_score.rs

@@ -0,0 +1,570 @@
+use std::fs;
+use std::{collections::BTreeMap, sync::Arc};
+use tempfile::tempdir;
+
+use async_trait::async_trait;
+use kube::api::ObjectMeta;
+use log::{debug, info};
+use serde::Serialize;
+use std::process::Command;
+
+use crate::modules::monitoring::kube_prometheus::crd::crd_alertmanager_config::CRDPrometheus;
+use crate::modules::monitoring::kube_prometheus::crd::crd_default_rules::build_default_application_rules;
+use crate::modules::monitoring::kube_prometheus::crd::crd_grafana::{
+    Grafana, GrafanaDashboard, GrafanaDashboardSpec, GrafanaDatasource, GrafanaDatasourceConfig,
+    GrafanaDatasourceSpec, GrafanaSpec,
+};
+use crate::modules::monitoring::kube_prometheus::crd::crd_prometheus_rules::{
+    PrometheusRule, PrometheusRuleSpec, RuleGroup,
+};
+use crate::modules::monitoring::kube_prometheus::crd::grafana_default_dashboard::build_default_dashboard;
+use crate::modules::monitoring::kube_prometheus::crd::service_monitor::{
+    ServiceMonitor, ServiceMonitorSpec,
+};
+use crate::topology::oberservability::monitoring::AlertReceiver;
+use crate::topology::{K8sclient, Topology, k8s::K8sClient};
+use crate::{
+    data::{Id, Version},
+    interpret::{Interpret, InterpretError, InterpretName, InterpretStatus, Outcome},
+    inventory::Inventory,
+    modules::monitoring::kube_prometheus::crd::{
+        crd_alertmanagers::{Alertmanager, AlertmanagerSpec},
+        crd_prometheuses::{
+            AlertmanagerEndpoints, LabelSelector, Prometheus, PrometheusSpec,
+            PrometheusSpecAlerting,
+        },
+        role::{build_prom_role, build_prom_rolebinding, build_prom_service_account},
+    },
+    score::Score,
+};
+
+use super::prometheus::PrometheusApplicationMonitoring;
+
+#[derive(Clone, Debug, Serialize)]
+pub struct K8sPrometheusCRDAlertingScore {
+    pub sender: CRDPrometheus,
+    pub receivers: Vec<Box<dyn AlertReceiver<CRDPrometheus>>>,
+    pub service_monitors: Vec<ServiceMonitor>,
+    pub prometheus_rules: Vec<RuleGroup>,
+}
+
+impl<T: Topology + K8sclient + PrometheusApplicationMonitoring<CRDPrometheus>> Score<T>
+    for K8sPrometheusCRDAlertingScore
+{
+    fn create_interpret(&self) -> Box<dyn crate::interpret::Interpret<T>> {
+        Box::new(K8sPrometheusCRDAlertingInterpret {
+            sender: self.sender.clone(),
+            receivers: self.receivers.clone(),
+            service_monitors: self.service_monitors.clone(),
+            prometheus_rules: self.prometheus_rules.clone(),
+        })
+    }
+
+    fn name(&self) -> String {
+        "prometheus alerting [CRDAlertingScore]".into()
+    }
+}
+
+#[derive(Clone, Debug)]
+pub struct K8sPrometheusCRDAlertingInterpret {
+    pub sender: CRDPrometheus,
+    pub receivers: Vec<Box<dyn AlertReceiver<CRDPrometheus>>>,
+    pub service_monitors: Vec<ServiceMonitor>,
+    pub prometheus_rules: Vec<RuleGroup>,
+}
+
+#[async_trait]
+impl<T: Topology + K8sclient + PrometheusApplicationMonitoring<CRDPrometheus>> Interpret<T>
+    for K8sPrometheusCRDAlertingInterpret
+{
+    async fn execute(
+        &self,
+        _inventory: &Inventory,
+        topology: &T,
+    ) -> Result<Outcome, InterpretError> {
+        let client = topology.k8s_client().await.unwrap();
+        self.ensure_grafana_operator().await?;
+        self.install_prometheus(&client).await?;
+        self.install_alert_manager(&client).await?;
+        self.install_client_kube_metrics().await?;
+        self.install_grafana(&client).await?;
+        self.install_receivers(&self.sender, &self.receivers)
+            .await?;
+        self.install_rules(&self.prometheus_rules, &client).await?;
+        self.install_monitors(self.service_monitors.clone(), &client)
+            .await?;
+        Ok(Outcome::success(
+            "K8s monitoring components installed".to_string(),
+        ))
+    }
+
+    fn get_name(&self) -> InterpretName {
+        InterpretName::K8sPrometheusCrdAlerting
+    }
+
+    fn get_version(&self) -> Version {
+        todo!()
+    }
+
+    fn get_status(&self) -> InterpretStatus {
+        todo!()
+    }
+
+    fn get_children(&self) -> Vec<Id> {
+        todo!()
+    }
+}
+
+impl K8sPrometheusCRDAlertingInterpret {
+    async fn crd_exists(&self, crd: &str) -> bool {
+        let status = Command::new("sh")
+            .args(["-c", &format!("kubectl get crd -A | grep -i {crd}")])
+            .status()
+            .map_err(|e| InterpretError::new(format!("could not connect to cluster: {}", e)))
+            .unwrap();
+
+        status.success()
+    }
+
+    async fn install_chart(
+        &self,
+        chart_path: String,
+        chart_name: String,
+    ) -> Result<(), InterpretError> {
+        let temp_dir =
+            tempdir().map_err(|e| InterpretError::new(format!("Tempdir error: {}", e)))?;
+        let temp_path = temp_dir.path().to_path_buf();
+        debug!("Using temp directory: {}", temp_path.display());
+        let chart = format!("{}/{}", chart_path, chart_name);
+        let pull_output = Command::new("helm")
+            .args(["pull", &chart, "--destination", temp_path.to_str().unwrap()])
+            .output()
+            .map_err(|e| InterpretError::new(format!("Helm pull error: {}", e)))?;
+
+        if !pull_output.status.success() {
+            return Err(InterpretError::new(format!(
+                "Helm pull failed: {}",
+                String::from_utf8_lossy(&pull_output.stderr)
+            )));
+        }
+
+        let tgz_path = fs::read_dir(&temp_path)
+            .unwrap()
+            .filter_map(|entry| {
+                let entry = entry.ok()?;
+                let path = entry.path();
+                if path.extension()? == "tgz" {
+                    Some(path)
+                } else {
+                    None
+                }
+            })
+            .next()
+            .ok_or_else(|| InterpretError::new("Could not find pulled Helm chart".into()))?;
+
+        debug!("Installing chart from: {}", tgz_path.display());
+
+        let install_output = Command::new("helm")
+            .args([
+                "upgrade",
+                "--install",
+                &chart_name,
+                tgz_path.to_str().unwrap(),
+                "--namespace",
+                &self.sender.namespace.clone(),
+                "--create-namespace",
+                "--wait",
+                "--atomic",
+            ])
+            .output()
+            .map_err(|e| InterpretError::new(format!("Helm install error: {}", e)))?;
+
+        if !install_output.status.success() {
+            return Err(InterpretError::new(format!(
+                "Helm install failed: {}",
+                String::from_utf8_lossy(&install_output.stderr)
+            )));
+        }
+
+        debug!(
+            "Installed chart {}/{} in namespace: {}",
+            &chart_path,
+            &chart_name,
+            self.sender.namespace.clone()
+        );
+        Ok(())
+    }
+
+    async fn ensure_grafana_operator(&self) -> Result<Outcome, InterpretError> {
+        if self.crd_exists("grafanas.grafana.integreatly.org").await {
+            debug!("grafana CRDs already exist — skipping install.");
+            return Ok(Outcome::success("Grafana CRDs already exist".to_string()));
+        }
+
+        let _ = Command::new("helm")
+            .args([
+                "repo",
+                "add",
+                "grafana-operator",
+                "https://grafana.github.io/helm-charts",
+            ])
+            .output()
+            .unwrap();
+
+        let _ = Command::new("helm")
+            .args(["repo", "update"])
+            .output()
+            .unwrap();
+
+        let output = Command::new("helm")
+            .args([
+                "install",
+                "grafana-operator",
+                "grafana-operator/grafana-operator",
+                "--namespace",
+                &self.sender.namespace.clone(),
+                "--create-namespace",
+                "--set",
+                "namespaceScope=true",
+            ])
+            .output()
+            .unwrap();
+
+        if !output.status.success() {
+            return Err(InterpretError::new(format!(
+                "helm install failed:\nstdout: {}\nstderr: {}",
+                String::from_utf8_lossy(&output.stdout),
+                String::from_utf8_lossy(&output.stderr)
+            )));
+        }
+
+        Ok(Outcome::success(format!(
+            "installed grafana operator in ns {}",
+            self.sender.namespace.clone()
+        )))
+    }
+
+    async fn install_prometheus(&self, client: &Arc<K8sClient>) -> Result<Outcome, InterpretError> {
+        debug!(
+            "installing crd-prometheuses in namespace {}",
+            self.sender.namespace.clone()
+        );
+        debug!("building role/rolebinding/serviceaccount for crd-prometheus");
+        let rolename = format!("{}-prom", self.sender.namespace.clone());
+        let sa_name = format!("{}-prom-sa", self.sender.namespace.clone());
+        let role = build_prom_role(rolename.clone(), self.sender.namespace.clone());
+        let rolebinding = build_prom_rolebinding(
+            rolename.clone(),
+            self.sender.namespace.clone(),
+            sa_name.clone(),
+        );
+        let sa = build_prom_service_account(sa_name.clone(), self.sender.namespace.clone());
+        let prom_spec = PrometheusSpec {
+            alerting: Some(PrometheusSpecAlerting {
+                alertmanagers: Some(vec![AlertmanagerEndpoints {
+                    name: Some("alertmanager-operated".into()),
+                    namespace: Some(self.sender.namespace.clone()),
+                    port: Some("web".into()),
+                    scheme: Some("http".into()),
+                }]),
+            }),
+            service_account_name: sa_name.clone(),
+            service_monitor_namespace_selector: Some(LabelSelector {
+                match_labels: BTreeMap::from([(
+                    "kubernetes.io/metadata.name".to_string(),
+                    self.sender.namespace.clone(),
+                )]),
+                match_expressions: vec![],
+            }),
+            service_monitor_selector: Some(LabelSelector {
+                match_labels: BTreeMap::from([("client".to_string(), "prometheus".to_string())]),
+                ..Default::default()
+            }),
+
+            service_discovery_role: Some("Endpoints".into()),
+
+            pod_monitor_selector: Some(LabelSelector {
+                match_labels: BTreeMap::from([("client".to_string(), "prometheus".to_string())]),
+                ..Default::default()
+            }),
+
+            rule_selector: Some(LabelSelector {
+                match_labels: BTreeMap::from([("role".to_string(), "prometheus-rule".to_string())]),
+                ..Default::default()
+            }),
+
+            rule_namespace_selector: Some(LabelSelector {
+                match_labels: BTreeMap::from([(
+                    "kubernetes.io/metadata.name".to_string(),
+                    self.sender.namespace.clone(),
+                )]),
+                match_expressions: vec![],
+            }),
+        };
+        let prom = Prometheus {
+            metadata: ObjectMeta {
+                name: Some(self.sender.namespace.clone()),
+                labels: Some(std::collections::BTreeMap::from([
+                    ("alertmanagerConfig".to_string(), "enabled".to_string()),
+                    ("client".to_string(), "prometheus".to_string()),
+                ])),
+                namespace: Some(self.sender.namespace.clone()),
+                ..Default::default()
+            },
+            spec: prom_spec,
+        };
+        client
+            .apply(&role, Some(&self.sender.namespace.clone()))
+            .await
+            .map_err(|e| InterpretError::new(e.to_string()))?;
+        info!(
+            "installed prometheus role: {:#?} in ns {:#?}",
+            role.metadata.name.unwrap(),
+            role.metadata.namespace.unwrap()
+        );
+        client
+            .apply(&rolebinding, Some(&self.sender.namespace.clone()))
+            .await
+            .map_err(|e| InterpretError::new(e.to_string()))?;
+        info!(
+            "installed prometheus rolebinding: {:#?} in ns {:#?}",
+            rolebinding.metadata.name.unwrap(),
+            rolebinding.metadata.namespace.unwrap()
+        );
+        client
+            .apply(&sa, Some(&self.sender.namespace.clone()))
+            .await
+            .map_err(|e| InterpretError::new(e.to_string()))?;
+        info!(
+            "installed prometheus service account: {:#?} in ns {:#?}",
+            sa.metadata.name.unwrap(),
+            sa.metadata.namespace.unwrap()
+        );
+        client
+            .apply(&prom, Some(&self.sender.namespace.clone()))
+            .await
+            .map_err(|e| InterpretError::new(e.to_string()))?;
+        info!(
+            "installed prometheus: {:#?} in ns {:#?}",
+            &prom.metadata.name.clone().unwrap(),
+            &prom.metadata.namespace.clone().unwrap()
+        );
+
+        Ok(Outcome::success(format!(
+            "successfully deployed crd-prometheus {:#?}",
+            prom
+        )))
+    }
+
+    async fn install_alert_manager(
+        &self,
+        client: &Arc<K8sClient>,
+    ) -> Result<Outcome, InterpretError> {
+        let am = Alertmanager {
+            metadata: ObjectMeta {
+                name: Some(self.sender.namespace.clone()),
+                labels: Some(std::collections::BTreeMap::from([(
+                    "alertmanagerConfig".to_string(),
+                    "enabled".to_string(),
+                )])),
+                namespace: Some(self.sender.namespace.clone()),
+                ..Default::default()
+            },
+            spec: AlertmanagerSpec::default(),
+        };
+        client
+            .apply(&am, Some(&self.sender.namespace.clone()))
+            .await
+            .map_err(|e| InterpretError::new(e.to_string()))?;
+        Ok(Outcome::success(format!(
+            "successfully deployed service monitor {:#?}",
+            am.metadata.name
+        )))
+    }
+    async fn install_monitors(
+        &self,
+        mut monitors: Vec<ServiceMonitor>,
+        client: &Arc<K8sClient>,
+    ) -> Result<Outcome, InterpretError> {
+        let default_service_monitor = ServiceMonitor {
+            metadata: ObjectMeta {
+                name: Some(self.sender.namespace.clone()),
+                labels: Some(std::collections::BTreeMap::from([
+                    ("alertmanagerConfig".to_string(), "enabled".to_string()),
+                    ("client".to_string(), "prometheus".to_string()),
+                    (
+                        "app.kubernetes.io/name".to_string(),
+                        "kube-state-metrics".to_string(),
+                    ),
+                ])),
+                namespace: Some(self.sender.namespace.clone()),
+                ..Default::default()
+            },
+            spec: ServiceMonitorSpec::default(),
+        };
+        monitors.push(default_service_monitor);
+        for monitor in monitors.iter() {
+            client
+                .apply(monitor, Some(&self.sender.namespace.clone()))
+                .await
+                .map_err(|e| InterpretError::new(e.to_string()))?;
+        }
+        Ok(Outcome::success(
+            "succesfully deployed service monitors".to_string(),
+        ))
+    }
+
+    async fn install_rules(
+        &self,
+        #[allow(clippy::ptr_arg)] rules: &Vec<RuleGroup>,
+        client: &Arc<K8sClient>,
+    ) -> Result<Outcome, InterpretError> {
+        let mut prom_rule_spec = PrometheusRuleSpec {
+            groups: rules.clone(),
+        };
+
+        let default_rules_group = RuleGroup {
+            name: "default-rules".to_string(),
+            rules: build_default_application_rules(),
+        };
+
+        prom_rule_spec.groups.push(default_rules_group);
+        let prom_rules = PrometheusRule {
+            metadata: ObjectMeta {
+                name: Some(self.sender.namespace.clone()),
+                labels: Some(std::collections::BTreeMap::from([
+                    ("alertmanagerConfig".to_string(), "enabled".to_string()),
+                    ("role".to_string(), "prometheus-rule".to_string()),
+                ])),
+                namespace: Some(self.sender.namespace.clone()),
+                ..Default::default()
+            },
+            spec: prom_rule_spec,
+        };
+        client
+            .apply(&prom_rules, Some(&self.sender.namespace.clone()))
+            .await
+            .map_err(|e| InterpretError::new(e.to_string()))?;
+        Ok(Outcome::success(format!(
+            "successfully deployed rules {:#?}",
+            prom_rules.metadata.name
+        )))
+    }
+
+    async fn install_client_kube_metrics(&self) -> Result<Outcome, InterpretError> {
+        self.install_chart(
+            "oci://hub.nationtech.io/harmony".to_string(),
+            "nt-kube-metrics".to_string(),
+        )
+        .await?;
+        Ok(Outcome::success(format!(
+            "Installed client kube metrics in ns {}",
+            &self.sender.namespace.clone()
+        )))
+    }
+
+    async fn install_grafana(&self, client: &Arc<K8sClient>) -> Result<Outcome, InterpretError> {
+        let mut label = BTreeMap::new();
+        label.insert("dashboards".to_string(), "grafana".to_string());
+        let labels = LabelSelector {
+            match_labels: label.clone(),
+            match_expressions: vec![],
+        };
+        let mut json_data = BTreeMap::new();
+        json_data.insert("timeInterval".to_string(), "5s".to_string());
+        let namespace = self.sender.namespace.clone();
+
+        let json = build_default_dashboard(&namespace);
+
+        let graf_data_source = GrafanaDatasource {
+            metadata: ObjectMeta {
+                name: Some(format!(
+                    "grafana-datasource-{}",
+                    self.sender.namespace.clone()
+                )),
+                namespace: Some(self.sender.namespace.clone()),
+                ..Default::default()
+            },
+            spec: GrafanaDatasourceSpec {
+                instance_selector: labels.clone(),
+                allow_cross_namespace_import: Some(false),
+                datasource: GrafanaDatasourceConfig {
+                    access: "proxy".to_string(),
+                    database: Some("prometheus".to_string()),
+                    json_data: Some(json_data),
+                    //this is fragile
+                    name: format!("prometheus-{}-0", self.sender.namespace.clone()),
+                    r#type: "prometheus".to_string(),
+                    url: format!(
+                        "http://prometheus-operated.{}.svc.cluster.local:9090",
+                        self.sender.namespace.clone()
+                    ),
+                },
+            },
+        };
+
+        client
+            .apply(&graf_data_source, Some(&self.sender.namespace.clone()))
+            .await
+            .map_err(|e| InterpretError::new(e.to_string()))?;
+
+        let graf_dashboard = GrafanaDashboard {
+            metadata: ObjectMeta {
+                name: Some(format!(
+                    "grafana-dashboard-{}",
+                    self.sender.namespace.clone()
+                )),
+                namespace: Some(self.sender.namespace.clone()),
+                ..Default::default()
+            },
+            spec: GrafanaDashboardSpec {
+                resync_period: Some("30s".to_string()),
+                instance_selector: labels.clone(),
+                json,
+            },
+        };
+
+        client
+            .apply(&graf_dashboard, Some(&self.sender.namespace.clone()))
+            .await
+            .map_err(|e| InterpretError::new(e.to_string()))?;
+
+        let grafana = Grafana {
+            metadata: ObjectMeta {
+                name: Some(format!("grafana-{}", self.sender.namespace.clone())),
+                namespace: Some(self.sender.namespace.clone()),
+                labels: Some(label.clone()),
+                ..Default::default()
+            },
+            spec: GrafanaSpec {
+                config: None,
+                admin_user: None,
+                admin_password: None,
+                ingress: None,
+                persistence: None,
+                resources: None,
+            },
+        };
+        client
+            .apply(&grafana, Some(&self.sender.namespace.clone()))
+            .await
+            .map_err(|e| InterpretError::new(e.to_string()))?;
+        Ok(Outcome::success(format!(
+            "successfully deployed grafana instance {:#?}",
+            grafana.metadata.name
+        )))
+    }
+
+    async fn install_receivers(
+        &self,
+        sender: &CRDPrometheus,
+        receivers: &Vec<Box<dyn AlertReceiver<CRDPrometheus>>>,
+    ) -> Result<Outcome, InterpretError> {
+        for receiver in receivers.iter() {
+            receiver.install(sender).await.map_err(|err| {
+                InterpretError::new(format!("failed to install receiver: {}", err))
+            })?;
+        }
+        Ok(Outcome::success("successfully deployed receivers".into()))
+    }
+}

harmony/src/modules/prometheus/mod.rs

@@ -1 +1,4 @@
 pub mod alerts;
+pub mod k8s_prometheus_alerting_score;
+#[allow(clippy::module_inception)]
+pub mod prometheus;

harmony/src/modules/prometheus/prometheus.rs

@@ -0,0 +1,19 @@
+use async_trait::async_trait;
+
+use crate::{
+    inventory::Inventory,
+    topology::{
+        PreparationError, PreparationOutcome,
+        oberservability::monitoring::{AlertReceiver, AlertSender},
+    },
+};
+
+#[async_trait]
+pub trait PrometheusApplicationMonitoring<S: AlertSender> {
+    async fn install_prometheus(
+        &self,
+        sender: &S,
+        inventory: &Inventory,
+        receivers: Option<Vec<Box<dyn AlertReceiver<S>>>>,
+    ) -> Result<PreparationOutcome, PreparationError>;
+}

harmony/src/modules/storage/ceph/ceph_remove_osd_score.rs

@@ -0,0 +1,419 @@
+use std::{
+    process::Command,
+    sync::Arc,
+    time::{Duration, Instant},
+};
+
+use async_trait::async_trait;
+use log::{info, warn};
+use serde::{Deserialize, Serialize};
+use tokio::time::sleep;
+
+use crate::{
+    data::{Id, Version},
+    interpret::{Interpret, InterpretError, InterpretName, InterpretStatus, Outcome},
+    inventory::Inventory,
+    score::Score,
+    topology::{K8sclient, Topology, k8s::K8sClient},
+};
+
+#[derive(Debug, Clone, Serialize)]
+pub struct CephRemoveOsd {
+    pub osd_deployment_name: String,
+    pub rook_ceph_namespace: String,
+}
+
+impl<T: Topology + K8sclient> Score<T> for CephRemoveOsd {
+    fn name(&self) -> String {
+        format!("CephRemoveOsdScore")
+    }
+
+    #[doc(hidden)]
+    fn create_interpret(&self) -> Box<dyn Interpret<T>> {
+        Box::new(CephRemoveOsdInterpret {
+            score: self.clone(),
+        })
+    }
+}
+
+#[derive(Debug, Clone)]
+pub struct CephRemoveOsdInterpret {
+    score: CephRemoveOsd,
+}
+
+#[async_trait]
+impl<T: Topology + K8sclient> Interpret<T> for CephRemoveOsdInterpret {
+    async fn execute(
+        &self,
+        _inventory: &Inventory,
+        topology: &T,
+    ) -> Result<Outcome, InterpretError> {
+        let client = topology.k8s_client().await.unwrap();
+        self.verify_ceph_toolbox_exists(client.clone()).await?;
+        self.scale_deployment(client.clone()).await?;
+        self.verify_deployment_scaled(client.clone()).await?;
+        self.delete_deployment(client.clone()).await?;
+        self.verify_deployment_deleted(client.clone()).await?;
+        let osd_id_full = self.get_ceph_osd_id().unwrap();
+        self.purge_ceph_osd(client.clone(), &osd_id_full).await?;
+        self.verify_ceph_osd_removal(client.clone(), &osd_id_full)
+            .await?;
+
+        Ok(Outcome::success(format!(
+            "Successfully removed OSD {} from rook-ceph cluster by deleting deployment {}",
+            osd_id_full, self.score.osd_deployment_name
+        )))
+    }
+    fn get_name(&self) -> InterpretName {
+        todo!()
+    }
+
+    fn get_version(&self) -> Version {
+        todo!()
+    }
+
+    fn get_status(&self) -> InterpretStatus {
+        todo!()
+    }
+
+    fn get_children(&self) -> Vec<Id> {
+        todo!()
+    }
+}
+
+impl CephRemoveOsdInterpret {
+    pub fn get_ceph_osd_id(&self) -> Result<String, InterpretError> {
+        let osd_id_numeric = self
+            .score
+            .osd_deployment_name
+            .split('-')
+            .nth(3)
+            .ok_or_else(|| {
+                InterpretError::new(format!(
+                    "Could not parse OSD id from deployment name {}",
+                    self.score.osd_deployment_name
+                ))
+            })?;
+        let osd_id_full = format!("osd.{}", osd_id_numeric);
+
+        info!(
+            "Targeting Ceph OSD: {} (parsed from deployment {})",
+            osd_id_full, self.score.osd_deployment_name
+        );
+
+        Ok(osd_id_full)
+    }
+
+    pub async fn verify_ceph_toolbox_exists(
+        &self,
+        client: Arc<K8sClient>,
+    ) -> Result<Outcome, InterpretError> {
+        let toolbox_dep = "rook-ceph-tools".to_string();
+
+        match client
+            .get_deployment(&toolbox_dep, Some(&self.score.rook_ceph_namespace))
+            .await
+        {
+            Ok(Some(deployment)) => {
+                if let Some(status) = deployment.status {
+                    let ready_count = status.ready_replicas.unwrap_or(0);
+                    if ready_count >= 1 {
+                        return Ok(Outcome::success(format!(
+                            "'{}' is ready with {} replica(s).",
+                            &toolbox_dep, ready_count
+                        )));
+                    } else {
+                        return Err(InterpretError::new(
+                            "ceph-tool-box not ready in cluster".to_string(),
+                        ));
+                    }
+                } else {
+                    Err(InterpretError::new(format!(
+                        "failed to get deployment status {}",
+                        &toolbox_dep
+                    )))
+                }
+            }
+            Ok(None) => Err(InterpretError::new(format!(
+                "Deployment '{}' not found in namespace '{}'.",
+                &toolbox_dep, self.score.rook_ceph_namespace
+            ))),
+            Err(e) => Err(InterpretError::new(format!(
+                "Failed to query for deployment '{}': {}",
+                &toolbox_dep, e
+            ))),
+        }
+    }
+
+    pub async fn scale_deployment(
+        &self,
+        client: Arc<K8sClient>,
+    ) -> Result<Outcome, InterpretError> {
+        info!(
+            "Scaling down OSD deployment: {}",
+            self.score.osd_deployment_name
+        );
+        client
+            .scale_deployment(
+                &self.score.osd_deployment_name,
+                Some(&self.score.rook_ceph_namespace),
+                0,
+            )
+            .await?;
+        Ok(Outcome::success(format!(
+            "Scaled down deployment {}",
+            self.score.osd_deployment_name
+        )))
+    }
+
+    pub async fn verify_deployment_scaled(
+        &self,
+        client: Arc<K8sClient>,
+    ) -> Result<Outcome, InterpretError> {
+        let (timeout, interval, start) = self.build_timer();
+
+        info!("Waiting for OSD deployment to scale down to 0 replicas");
+        loop {
+            let dep = client
+                .get_deployment(
+                    &self.score.osd_deployment_name,
+                    Some(&self.score.rook_ceph_namespace),
+                )
+                .await?;
+
+            if let Some(deployment) = dep {
+                if let Some(status) = deployment.status {
+                    if status.replicas.unwrap_or(1) == 0 && status.ready_replicas.unwrap_or(1) == 0
+                    {
+                        return Ok(Outcome::success(
+                            "Deployment successfully scaled down.".to_string(),
+                        ));
+                    }
+                }
+            }
+
+            if start.elapsed() > timeout {
+                return Err(InterpretError::new(format!(
+                    "Timed out waiting for deployment {} to scale down",
+                    self.score.osd_deployment_name
+                )));
+            }
+            sleep(interval).await;
+        }
+    }
+
+    fn build_timer(&self) -> (Duration, Duration, Instant) {
+        let timeout = Duration::from_secs(120);
+        let interval = Duration::from_secs(5);
+        let start = Instant::now();
+        (timeout, interval, start)
+    }
+    pub async fn delete_deployment(
+        &self,
+        client: Arc<K8sClient>,
+    ) -> Result<Outcome, InterpretError> {
+        info!(
+            "Deleting OSD deployment: {}",
+            self.score.osd_deployment_name
+        );
+        client
+            .delete_deployment(
+                &self.score.osd_deployment_name,
+                Some(&self.score.rook_ceph_namespace),
+            )
+            .await?;
+        Ok(Outcome::success(format!(
+            "deployment {} deleted",
+            self.score.osd_deployment_name
+        )))
+    }
+
+    pub async fn verify_deployment_deleted(
+        &self,
+        client: Arc<K8sClient>,
+    ) -> Result<Outcome, InterpretError> {
+        let (timeout, interval, start) = self.build_timer();
+
+        info!("Waiting for OSD deployment to scale down to 0 replicas");
+        loop {
+            let dep = client
+                .get_deployment(
+                    &self.score.osd_deployment_name,
+                    Some(&self.score.rook_ceph_namespace),
+                )
+                .await?;
+
+            if dep.is_none() {
+                info!(
+                    "Deployment {} successfully deleted.",
+                    self.score.osd_deployment_name
+                );
+                return Ok(Outcome::success(format!(
+                    "Deployment {} deleted.",
+                    self.score.osd_deployment_name
+                )));
+            }
+
+            if start.elapsed() > timeout {
+                return Err(InterpretError::new(format!(
+                    "Timed out waiting for deployment {} to be deleted",
+                    self.score.osd_deployment_name
+                )));
+            }
+            sleep(interval).await;
+        }
+    }
+
+    fn get_osd_tree(&self, json: serde_json::Value) -> Result<CephOsdTree, InterpretError> {
+        let nodes = json.get("nodes").ok_or_else(|| {
+            InterpretError::new("Missing 'nodes' field in ceph osd tree JSON".to_string())
+        })?;
+        let tree: CephOsdTree = CephOsdTree {
+            nodes: serde_json::from_value(nodes.clone()).map_err(|e| {
+                InterpretError::new(format!("Failed to parse ceph osd tree JSON: {}", e))
+            })?,
+        };
+        Ok(tree)
+    }
+
+    pub async fn purge_ceph_osd(
+        &self,
+        client: Arc<K8sClient>,
+        osd_id_full: &str,
+    ) -> Result<Outcome, InterpretError> {
+        info!(
+            "Purging OSD {} from Ceph cluster and removing its auth key",
+            osd_id_full
+        );
+        client
+            .exec_app_capture_output(
+                "rook-ceph-tools".to_string(),
+                "app".to_string(),
+                Some(&self.score.rook_ceph_namespace),
+                vec![
+                    format!("ceph osd purge {osd_id_full} --yes-i-really-mean-it").as_str(),
+                    format!("ceph auth del osd.{osd_id_full}").as_str(),
+                ],
+            )
+            .await?;
+        Ok(Outcome::success(format!(
+            "osd id {} removed from osd tree",
+            osd_id_full
+        )))
+    }
+
+    pub async fn verify_ceph_osd_removal(
+        &self,
+        client: Arc<K8sClient>,
+        osd_id_full: &str,
+    ) -> Result<Outcome, InterpretError> {
+        let (timeout, interval, start) = self.build_timer();
+        info!(
+            "Verifying OSD {} has been removed from the Ceph tree...",
+            osd_id_full
+        );
+        loop {
+            let output = client
+                .exec_app_capture_output(
+                    "rook-ceph-tools".to_string(),
+                    "app".to_string(),
+                    Some(&self.score.rook_ceph_namespace),
+                    vec!["ceph osd tree -f json"],
+                )
+                .await?;
+            let tree =
+                self.get_osd_tree(serde_json::from_str(&output).expect("could not extract json"));
+
+            let osd_found = tree
+                .unwrap()
+                .nodes
+                .iter()
+                .any(|node| node.name == osd_id_full);
+
+            if !osd_found {
+                return Ok(Outcome::success(format!(
+                    "Successfully verified that OSD {} is removed from the Ceph cluster.",
+                    osd_id_full,
+                )));
+            }
+
+            if start.elapsed() > timeout {
+                return Err(InterpretError::new(format!(
+                    "Timed out waiting for OSD {} to be removed from Ceph tree",
+                    osd_id_full
+                )));
+            }
+
+            warn!(
+                "OSD {} still found in Ceph tree, retrying in {:?}...",
+                osd_id_full, interval
+            );
+            sleep(interval).await;
+        }
+    }
+}
+#[derive(Debug, Deserialize, PartialEq)]
+pub struct CephOsdTree {
+    pub nodes: Vec<CephNode>,
+}
+
+#[derive(Debug, Deserialize, PartialEq)]
+pub struct CephNode {
+    pub id: i32,
+    pub name: String,
+    #[serde(rename = "type")]
+    pub node_type: String,
+    pub type_id: Option<i32>,
+    pub children: Option<Vec<i32>>,
+    pub exists: Option<i32>,
+    pub status: Option<String>,
+}
+
+#[cfg(test)]
+mod tests {
+    use serde_json::json;
+
+    use super::*;
+
+    #[test]
+    fn test_get_osd_tree() {
+        let json_data = json!({
+            "nodes": [
+                {"id": 1, "name": "osd.1", "type": "osd", "primary_affinity":"1"},
+                {"id": 2, "name": "osd.2", "type": "osd", "crush_weight": 1.22344}
+            ]
+        });
+        let interpret = CephRemoveOsdInterpret {
+            score: CephRemoveOsd {
+                osd_deployment_name: "osd-1".to_string(),
+                rook_ceph_namespace: "dummy_ns".to_string(),
+            },
+        };
+        let json = interpret.get_osd_tree(json_data).unwrap();
+
+        let expected = CephOsdTree {
+            nodes: vec![
+                CephNode {
+                    id: 1,
+                    name: "osd.1".to_string(),
+                    node_type: "osd".to_string(),
+                    type_id: None,
+                    children: None,
+                    exists: None,
+                    status: None,
+                },
+                CephNode {
+                    id: 2,
+                    name: "osd.2".to_string(),
+                    node_type: "osd".to_string(),
+                    type_id: None,
+                    children: None,
+                    exists: None,
+                    status: None,
+                },
+            ],
+        };
+
+        assert_eq!(json, expected);
+    }
+}

harmony/src/modules/storage/ceph/mod.rs

@@ -0,0 +1 @@
+pub mod ceph_remove_osd_score;

harmony/src/modules/storage/mod.rs

@@ -0,0 +1 @@
+pub mod ceph;

harmony/src/modules/tenant/credentials.rs

@@ -17,7 +17,7 @@ impl<T: Topology + TenantCredentialManager> Score<T> for TenantCredentialScore {
     }
 
     fn name(&self) -> String {
-        todo!()
+        "TenantCredentialScore".into()
     }
 }
 

harmony/src/modules/tenant/mod.rs

@@ -28,7 +28,7 @@ impl<T: Topology + TenantManager> Score<T> for TenantScore {
     }
 
     fn name(&self) -> String {
-        format!("{} TenantScore", self.config.name)
+        format!("{} [TenantScore]", self.config.name)
     }
 }
 
@@ -47,8 +47,8 @@ impl<T: Topology + TenantManager> Interpret<T> for TenantInterpret {
         topology.provision_tenant(&self.tenant_config).await?;
 
         Ok(Outcome::success(format!(
-            "Successfully provisioned tenant {} with id {}",
-            self.tenant_config.name, self.tenant_config.id
+            "Tenant provisioned with id '{}'",
+            self.tenant_config.id
         )))
     }
 

harmony_cli/Cargo.toml

@@ -5,6 +5,10 @@ version.workspace = true
 readme.workspace = true
 license.workspace = true
 
+[features]
+default = ["tui"]
+tui = ["dep:harmony_tui"]
+
 [dependencies]
 assert_cmd = "2.0.17"
 clap = { version = "4.5.35", features = ["derive"] }
@@ -19,7 +23,5 @@ lazy_static = "1.5.0"
 log.workspace = true
 indicatif-log-bridge = "0.2.3"
 
-
-[features]
-default = ["tui"]
-tui = ["dep:harmony_tui"]
+[dev-dependencies]
+harmony = { path = "../harmony", features = ["testing"] }