wip: vllm example

Reviewed-on: #248

Cargo.lock

@@ -7001,6 +7001,18 @@ version = "0.9.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "0b928f33d975fc6ad9f86c8f283853ad26bdd5b10b7f1542aa2fa15e2289105a"
 
+[[package]]
+name = "vllm"
+version = "0.1.0"
+dependencies = [
+ "env_logger",
+ "harmony",
+ "harmony_cli",
+ "k8s-openapi",
+ "log",
+ "tokio",
+]
+
 [[package]]
 name = "wait-timeout"
 version = "0.2.1"

Cargo.toml

@@ -18,7 +18,7 @@ members = [
   "adr/agent_discovery/mdns",
    "brocade",
    "harmony_agent",
-   "harmony_agent/deploy", "harmony_node_readiness", "harmony-k8s",
+   "harmony_agent/deploy", "harmony_node_readiness", "harmony-k8s", "examples/vllm",
 ]
 
 [workspace.package]

adr/020-monitoring-alerting-architecture.md

@@ -1,318 +0,0 @@
-# Architecture Decision Record: Monitoring and Alerting Architecture
-
-Initial Author: Willem Rolleman, Jean-Gabriel Carrier
-
-Initial Date: March 9, 2026
-
-Last Updated Date: March 9, 2026
-
-## Status
-
-Accepted
-
-Supersedes: [ADR-010](010-monitoring-and-alerting.md)
-
-## Context
-
-Harmony needs a unified approach to monitoring and alerting across different infrastructure targets:
-
-1. **Cluster-level monitoring**: Administrators managing entire Kubernetes/OKD clusters need to define cluster-wide alerts, receivers, and scrape targets.
-
-2. **Tenant-level monitoring**: Multi-tenant clusters where teams are confined to namespaces need monitoring scoped to their resources.
-
-3. **Application-level monitoring**: Developers deploying applications want zero-config monitoring that "just works" for their services.
-
-The monitoring landscape is fragmented:
-- **OKD/OpenShift**: Built-in Prometheus with AlertmanagerConfig CRDs
-- **KubePrometheus**: Helm-based stack with PrometheusRule CRDs
-- **RHOB (Red Hat Observability)**: Operator-based with MonitoringStack CRDs
-- **Standalone Prometheus**: Raw Prometheus deployments
-
-Each system has different CRDs, different installation methods, and different configuration APIs.
-
-## Decision
-
-We implement a **trait-based architecture with compile-time capability verification** that provides:
-
-1. **Type-safe abstractions** via parameterized traits: `AlertReceiver<S>`, `AlertRule<S>`, `ScrapeTarget<S>`
-2. **Compile-time topology compatibility** via the `Observability<S>` capability bound
-3. **Three levels of abstraction**: Cluster, Tenant, and Application monitoring
-4. **Pre-built alert rules** as functions that return typed structs
-
-### Core Traits
-
-```rust
-// domain/topology/monitoring.rs
-
-/// Marker trait for systems that send alerts (Prometheus, etc.)
-pub trait AlertSender: Send + Sync + std::fmt::Debug {
-    fn name(&self) -> String;
-}
-
-/// Defines how a receiver (Discord, Slack, etc.) builds its configuration
-/// for a specific sender type
-pub trait AlertReceiver<S: AlertSender>: std::fmt::Debug + Send + Sync {
-    fn build(&self) -> Result<ReceiverInstallPlan, InterpretError>;
-    fn name(&self) -> String;
-    fn clone_box(&self) -> Box<dyn AlertReceiver<S>>;
-}
-
-/// Defines how an alert rule builds its PrometheusRule configuration
-pub trait AlertRule<S: AlertSender>: std::fmt::Debug + Send + Sync {
-    fn build_rule(&self) -> Result<serde_json::Value, InterpretError>;
-    fn name(&self) -> String;
-    fn clone_box(&self) -> Box<dyn AlertRule<S>>;
-}
-
-/// Capability that topologies implement to support monitoring
-pub trait Observability<S: AlertSender> {
-    async fn install_alert_sender(&self, sender: &S, inventory: &Inventory) 
-        -> Result<PreparationOutcome, PreparationError>;
-    async fn install_receivers(&self, sender: &S, inventory: &Inventory, 
-        receivers: Option<Vec<Box<dyn AlertReceiver<S>>>>) -> Result<...>;
-    async fn install_rules(&self, sender: &S, inventory: &Inventory,
-        rules: Option<Vec<Box<dyn AlertRule<S>>>>) -> Result<...>;
-    async fn add_scrape_targets(&self, sender: &S, inventory: &Inventory,
-        scrape_targets: Option<Vec<Box<dyn ScrapeTarget<S>>>>) -> Result<...>;
-    async fn ensure_monitoring_installed(&self, sender: &S, inventory: &Inventory) 
-        -> Result<...>;
-}
-```
-
-### Alert Sender Types
-
-Each monitoring stack is a distinct `AlertSender`:
-
-| Sender | Module | Use Case |
-|--------|--------|----------|
-| `OpenshiftClusterAlertSender` | `monitoring/okd/` | OKD/OpenShift built-in monitoring |
-| `KubePrometheus` | `monitoring/kube_prometheus/` | Helm-deployed kube-prometheus-stack |
-| `Prometheus` | `monitoring/prometheus/` | Standalone Prometheus via Helm |
-| `RedHatClusterObservability` | `monitoring/red_hat_cluster_observability/` | RHOB operator |
-| `Grafana` | `monitoring/grafana/` | Grafana-managed alerting |
-
-### Three Levels of Monitoring
-
-#### 1. Cluster-Level Monitoring
-
-For cluster administrators. Full control over monitoring infrastructure.
-
-```rust
-// examples/okd_cluster_alerts/src/main.rs
-OpenshiftClusterAlertScore {
-    sender: OpenshiftClusterAlertSender,
-    receivers: vec![Box::new(DiscordReceiver { ... })],
-    rules: vec![Box::new(alert_rules)],
-    scrape_targets: Some(vec![Box::new(external_exporters)]),
-}
-```
-
-**Characteristics:**
-- Cluster-scoped CRDs and resources
-- Can add external scrape targets (outside cluster)
-- Manages Alertmanager configuration
-- Requires cluster-admin privileges
-
-#### 2. Tenant-Level Monitoring
-
-For teams confined to namespaces. The topology determines tenant context.
-
-```rust
-// The topology's Observability impl handles namespace scoping
-impl Observability<KubePrometheus> for K8sAnywhereTopology {
-    async fn install_rules(&self, sender: &KubePrometheus, ...) {
-        // Topology knows if it's tenant-scoped
-        let namespace = self.get_tenant_config().await
-            .map(|t| t.name)
-            .unwrap_or("default");
-        // Install rules in tenant namespace
-    }
-}
-```
-
-**Characteristics:**
-- Namespace-scoped resources
-- Cannot modify cluster-level monitoring config
-- May have restricted receiver types
-- Runtime validation of permissions (cannot be fully compile-time)
-
-#### 3. Application-Level Monitoring
-
-For developers. Zero-config, opinionated monitoring.
-
-```rust
-// modules/application/features/monitoring.rs
-pub struct Monitoring {
-    pub application: Arc<dyn Application>,
-    pub alert_receiver: Vec<Box<dyn AlertReceiver<Prometheus>>>,
-}
-
-impl<T: Topology + Observability<Prometheus> + TenantManager + ...> 
-    ApplicationFeature<T> for Monitoring 
-{
-    async fn ensure_installed(&self, topology: &T) -> Result<...> {
-        // Auto-creates ServiceMonitor
-        // Auto-installs Ntfy for notifications
-        // Handles tenant namespace automatically
-        // Wires up sensible defaults
-    }
-}
-```
-
-**Characteristics:**
-- Automatic ServiceMonitor creation
-- Opinionated notification channel (Ntfy)
-- Tenant-aware via topology
-- Minimal configuration required
-
-## Rationale
-
-### Why Generic Traits Instead of Unified Types?
-
-Each monitoring stack (OKD, KubePrometheus, RHOB) has fundamentally different CRDs:
-
-```rust
-// OKD uses AlertmanagerConfig with different structure
-AlertmanagerConfig { spec: { receivers: [...] } }
-
-// RHOB uses secret references for webhook URLs
-MonitoringStack { spec: { alertmanagerConfig: { discordConfigs: [{ apiURL: { key: "..." } }] } } }
-
-// KubePrometheus uses Alertmanager CRD with different field names
-Alertmanager { spec: { config: { receivers: [...] } } }
-```
-
-A unified type would either:
-1. Be a lowest-common-denominator (loses stack-specific features)
-2. Be a complex union type (hard to use, easy to misconfigure)
-
-Generic traits let each stack express its configuration naturally while providing a consistent interface.
-
-### Why Compile-Time Capability Bounds?
-
-```rust
-impl<T: Topology + Observability<OpenshiftClusterAlertSender>> Score<T> 
-    for OpenshiftClusterAlertScore { ... }
-```
-
-This fails at compile time if you try to use `OpenshiftClusterAlertScore` with a topology that doesn't support OKD monitoring. This prevents the "config-is-valid-but-platform-is-wrong" errors that Harmony was designed to eliminate.
-
-### Why Not a MonitoringStack Abstraction (V2 Approach)?
-
-The V2 approach proposed a unified `MonitoringStack` that hides sender selection:
-
-```rust
-// V2 approach - rejected
-MonitoringStack::new(MonitoringApiVersion::V2CRD)
-    .add_alert_channel(discord)
-```
-
-**Problems:**
-1. Hides which sender you're using, losing compile-time guarantees
-2. "Version selection" actually chooses between fundamentally different systems
-3. Would need to handle all stack-specific features through a generic interface
-
-The current approach is explicit: you choose `OpenshiftClusterAlertSender` and the compiler verifies compatibility.
-
-### Why Runtime Validation for Tenants?
-
-Tenant confinement is determined at runtime by the topology and K8s RBAC. We cannot know at compile time whether a user has cluster-admin or namespace-only access.
-
-Options considered:
-1. **Compile-time tenant markers** - Would require modeling entire RBAC hierarchy in types. Over-engineering.
-2. **Runtime validation** - Current approach. Fails with clear K8s permission errors if insufficient access.
-3. **No tenant support** - Would exclude a major use case.
-
-Runtime validation is the pragmatic choice. The failure mode is clear (K8s API error) and occurs early in execution.
-
-> Note : we will eventually have compile time validation for such things. Rust macros are powerful and we could discover the actual capabilities we're dealing with, similar to sqlx approach in query! macros.
-
-## Consequences
-
-### Pros
-
-1. **Type Safety**: Invalid configurations are caught at compile time
-2. **Extensibility**: Adding a new monitoring stack requires implementing traits, not modifying core code
-3. **Clear Separation**: Cluster/Tenant/Application levels have distinct entry points
-4. **Reusable Rules**: Pre-built alert rules as functions (`high_pvc_fill_rate_over_two_days()`)
-5. **CRD Accuracy**: Type definitions match actual Kubernetes CRDs exactly
-
-### Cons
-
-1. **Implementation Explosion**: `DiscordReceiver` implements `AlertReceiver<S>` for each sender type (3+ implementations)
-2. **Learning Curve**: Understanding the trait hierarchy takes time
-3. **clone_box Boilerplate**: Required for trait object cloning (3 lines per impl)
-
-### Mitigations
-
-- Implementation explosion is contained: each receiver type has O(senders) implementations, but receivers are rare compared to rules
-- Learning curve is documented with examples at each level
-- clone_box boilerplate is minimal and copy-paste
-
-## Alternatives Considered
-
-### Unified MonitoringStack Type
-
-See "Why Not a MonitoringStack Abstraction" above. Rejected for losing compile-time safety.
-
-### Helm-Only Approach
-
-Use `HelmScore` directly for each monitoring deployment. Rejected because:
-- No type safety for alert rules
-- Cannot compose with application features
-- No tenant awareness
-
-### Separate Modules Per Use Case
-
-Have `cluster_monitoring/`, `tenant_monitoring/`, `app_monitoring/` as separate modules. Rejected because:
-- Massive code duplication
-- No shared abstraction for receivers/rules
-- Adding a feature requires three implementations
-
-## Implementation Notes
-
-### Module Structure
-
-```
-modules/monitoring/
-├── mod.rs                     # Public exports
-├── alert_channel/             # Receivers (Discord, Webhook)
-├── alert_rule/                # Rules and pre-built alerts
-│   ├── prometheus_alert_rule.rs
-│   └── alerts/                # Library of pre-built rules
-│       ├── k8s/               # K8s-specific (pvc, pod, memory)
-│       └── infra/             # Infrastructure (opnsense, dell)
-├── okd/                       # OpenshiftClusterAlertSender
-├── kube_prometheus/           # KubePrometheus
-├── prometheus/                # Prometheus
-├── red_hat_cluster_observability/  # RHOB
-├── grafana/                   # Grafana
-├── application_monitoring/    # Application-level scores
-└── scrape_target/             # External scrape targets
-```
-
-### Adding a New Alert Sender
-
-1. Create sender type: `pub struct MySender; impl AlertSender for MySender { ... }`
-2. Implement `Observability<MySender>` for topologies that support it
-3. Create CRD types in `crd/` subdirectory
-4. Implement `AlertReceiver<MySender>` for existing receivers
-5. Implement `AlertRule<MySender>` for `AlertManagerRuleGroup`
-
-### Adding a New Alert Rule
-
-```rust
-pub fn my_custom_alert() -> PrometheusAlertRule {
-    PrometheusAlertRule::new("MyAlert", "up == 0")
-        .for_duration("5m")
-        .label("severity", "critical")
-        .annotation("summary", "Service is down")
-}
-```
-
-No trait implementation needed - `AlertManagerRuleGroup` already handles conversion.
-
-## Related ADRs
-
-- [ADR-013](013-monitoring-notifications.md): Notification channel selection (ntfy)
-- [ADR-011](011-multi-tenant-cluster.md): Multi-tenant cluster architecture

adr/020-monitoring-alerting-architecture/monitoring_v2/Cargo.toml

@@ -1,21 +0,0 @@
-[package]
-name = "example-monitoring-v2"
-edition = "2024"
-version.workspace = true
-readme.workspace = true
-license.workspace = true
-
-[dependencies]
-harmony = { path = "../../harmony" }
-harmony_cli = { path = "../../harmony_cli" }
-harmony-k8s = { path = "../../harmony-k8s" }
-harmony_types = { path = "../../harmony_types" }
-kube = { workspace = true }
-schemars = "0.8"
-serde = { workspace = true, features = ["derive"] }
-serde_json = { workspace = true }
-serde_yaml = { workspace = true }
-url = { workspace = true }
-log = { workspace = true }
-async-trait = { workspace = true }
-k8s-openapi = { workspace = true }

adr/020-monitoring-alerting-architecture/monitoring_v2/README.md

@@ -1,91 +0,0 @@
-# Monitoring v2 - Improved Architecture
-
-This example demonstrates the improved monitoring architecture that addresses the "WTF/minute" issues in the original design.
-
-## Key Improvements
-
-### 1. **Single AlertChannel Trait with Generic Sender**
-
-The original design required 9-12 implementations for each alert channel (Discord, Webhook, etc.) - one for each sender type. The new design uses a single trait with generic sender parameterization:
-
-pub trait AlertChannel<Sender: AlertSender> {
-    async fn install_config(&self, sender: &Sender) -> Result<Outcome, InterpretError>;
-    fn name(&self) -> String;
-    fn as_any(&self) -> &dyn std::any::Any;
-}
-
-**Benefits:**
-- One Discord implementation works with all sender types
-- Type safety at compile time
-- No runtime dispatch overhead
-
-### 2. **MonitoringStack Abstraction**
-
-Instead of manually selecting CRDPrometheus vs KubePrometheus vs RHOBObservability, you now have a unified MonitoringStack that handles versioning:
-
-let monitoring_stack = MonitoringStack::new(MonitoringApiVersion::V2CRD)
-    .set_namespace("monitoring")
-    .add_alert_channel(discord_receiver)
-    .set_scrape_targets(vec![...]);
-
-**Benefits:**
-- Single source of truth for monitoring configuration
-- Easy to switch between monitoring versions
-- Automatic version-specific configuration
-
-### 3. **TenantMonitoringScore - True Composition**
-
-The original monitoring_with_tenant example just put tenant and monitoring as separate items in a vec. The new design truly composes them:
-
-let tenant_score = TenantMonitoringScore::new("test-tenant", monitoring_stack);
-
-This creates a single score that:
-- Has tenant context
-- Has monitoring configuration
-- Automatically installs monitoring scoped to tenant namespace
-
-**Benefits:**
-- No more "two separate things" confusion
-- Automatic tenant namespace scoping
-- Clear ownership: tenant owns its monitoring
-
-### 4. **Versioned Monitoring APIs**
-
-Clear versioning makes it obvious which monitoring stack you're using:
-
-pub enum MonitoringApiVersion {
-    V1Helm,    // Old Helm charts
-    V2CRD,     // Current CRDs
-    V3RHOB,    // RHOB (future)
-}
-
-**Benefits:**
-- No guessing which API version you're using
-- Easy to migrate between versions
-- Backward compatibility path
-
-## Comparison
-
-### Original Design (monitoring_with_tenant)
-- Manual selection of each component
-- Manual installation of both components
-- Need to remember to pass both to harmony_cli::run
-- Monitoring not scoped to tenant automatically
-
-### New Design (monitoring_v2)
-- Single composed score
-- One score does it all
-
-## Usage
-
-cd examples/monitoring_v2
-cargo run
-
-## Migration Path
-
-To migrate from the old design to the new:
-
-1. Replace individual alert channel implementations with AlertChannel<Sender>
-2. Use MonitoringStack instead of manual *Prometheus selection
-3. Use TenantMonitoringScore instead of separate TenantScore + monitoring scores
-4. Select monitoring version via MonitoringApiVersion

adr/020-monitoring-alerting-architecture/monitoring_v2/src/lib.rs

@@ -1,343 +0,0 @@
-use std::collections::HashMap;
-use std::sync::{Arc, Mutex};
-
-
-use log::debug;
-use serde::{Deserialize, Serialize};
-use serde_yaml::{Mapping, Value};
-
-use harmony::data::Version;
-use harmony::interpret::{Interpret, InterpretError, InterpretName, InterpretStatus, Outcome};
-use harmony::inventory::Inventory;
-use harmony::score::Score;
-use harmony::topology::{Topology, tenant::TenantManager};
-
-use harmony_k8s::K8sClient;
-use harmony_types::k8s_name::K8sName;
-use harmony_types::net::Url;
-
-pub trait AlertSender: Send + Sync + std::fmt::Debug {
-    fn name(&self) -> String;
-    fn namespace(&self) -> String;
-}
-
-#[derive(Debug)]
-pub struct CRDPrometheus {
-    pub namespace: String,
-    pub client: Arc<K8sClient>,
-}
-
-impl AlertSender for CRDPrometheus {
-    fn name(&self) -> String {
-        "CRDPrometheus".to_string()
-    }
-
-    fn namespace(&self) -> String {
-        self.namespace.clone()
-    }
-}
-
-#[derive(Debug)]
-pub struct RHOBObservability {
-    pub namespace: String,
-    pub client: Arc<K8sClient>,
-}
-
-impl AlertSender for RHOBObservability {
-    fn name(&self) -> String {
-        "RHOBObservability".to_string()
-    }
-
-    fn namespace(&self) -> String {
-        self.namespace.clone()
-    }
-}
-
-#[derive(Debug)]
-pub struct KubePrometheus {
-    pub config: Arc<Mutex<KubePrometheusConfig>>,
-}
-
-impl Default for KubePrometheus {
-    fn default() -> Self {
-        Self::new()
-    }
-}
-
-impl KubePrometheus {
-    pub fn new() -> Self {
-        Self {
-            config: Arc::new(Mutex::new(KubePrometheusConfig::new())),
-        }
-    }
-}
-
-impl AlertSender for KubePrometheus {
-    fn name(&self) -> String {
-        "KubePrometheus".to_string()
-    }
-
-    fn namespace(&self) -> String {
-        self.config.lock().unwrap().namespace.clone().unwrap_or_else(|| "monitoring".to_string())
-    }
-}
-
-#[derive(Debug, Clone, Serialize, Deserialize)]
-pub struct KubePrometheusConfig {
-    pub namespace: Option<String>,
-    #[serde(skip)]
-    pub alert_receiver_configs: Vec<AlertManagerChannelConfig>,
-}
-
-impl KubePrometheusConfig {
-    pub fn new() -> Self {
-        Self {
-            namespace: None,
-            alert_receiver_configs: Vec::new(),
-        }
-    }
-}
-
-#[derive(Debug, Clone, Serialize, Deserialize)]
-pub struct AlertManagerChannelConfig {
-    pub channel_receiver: serde_yaml::Value,
-    pub channel_route: serde_yaml::Value,
-}
-
-impl Default for AlertManagerChannelConfig {
-    fn default() -> Self {
-        Self {
-            channel_receiver: serde_yaml::Value::Mapping(Default::default()),
-            channel_route: serde_yaml::Value::Mapping(Default::default()),
-        }
-    }
-}
-
-#[derive(Debug, Clone, Serialize, Deserialize)]
-pub struct ScrapeTargetConfig {
-    pub service_name: String,
-    pub port: String,
-    pub path: String,
-}
-
-#[derive(Debug, Clone, Serialize, Deserialize)]
-pub enum MonitoringApiVersion {
-    V1Helm,
-    V2CRD,
-    V3RHOB,
-}
-
-#[derive(Debug, Clone)]
-pub struct MonitoringStack {
-    pub version: MonitoringApiVersion,
-    pub namespace: String,
-    pub alert_channels: Vec<Arc<dyn AlertSender>>,
-    pub scrape_targets: Vec<ScrapeTargetConfig>,
-}
-
-impl MonitoringStack {
-    pub fn new(version: MonitoringApiVersion) -> Self {
-        Self {
-            version,
-            namespace: "monitoring".to_string(),
-            alert_channels: Vec::new(),
-            scrape_targets: Vec::new(),
-        }
-    }
-
-    pub fn set_namespace(mut self, namespace: &str) -> Self {
-        self.namespace = namespace.to_string();
-        self
-    }
-
-    pub fn add_alert_channel(mut self, channel: impl AlertSender + 'static) -> Self {
-        self.alert_channels.push(Arc::new(channel));
-        self
-    }
-
-    pub fn set_scrape_targets(mut self, targets: Vec<(&str, &str, String)>) -> Self {
-        self.scrape_targets = targets
-            .into_iter()
-            .map(|(name, port, path)| ScrapeTargetConfig {
-                service_name: name.to_string(),
-                port: port.to_string(),
-                path,
-            })
-            .collect();
-        self
-    }
-}
-
-pub trait AlertChannel<Sender: AlertSender> {
-    fn install_config(&self, sender: &Sender);
-    fn name(&self) -> String;
-}
-
-#[derive(Debug, Clone)]
-pub struct DiscordWebhook {
-    pub name: K8sName,
-    pub url: Url,
-    pub selectors: Vec<HashMap<String, String>>,
-}
-
-impl DiscordWebhook {
-    fn get_config(&self) -> AlertManagerChannelConfig {
-        let mut route = Mapping::new();
-        route.insert(
-            Value::String("receiver".to_string()),
-            Value::String(self.name.to_string()),
-        );
-        route.insert(
-            Value::String("matchers".to_string()),
-            Value::Sequence(vec![Value::String("alertname!=Watchdog".to_string())]),
-        );
-
-        let mut receiver = Mapping::new();
-        receiver.insert(
-            Value::String("name".to_string()),
-            Value::String(self.name.to_string()),
-        );
-
-        let mut discord_config = Mapping::new();
-        discord_config.insert(
-            Value::String("webhook_url".to_string()),
-            Value::String(self.url.to_string()),
-        );
-
-        receiver.insert(
-            Value::String("discord_configs".to_string()),
-            Value::Sequence(vec![Value::Mapping(discord_config)]),
-        );
-
-        AlertManagerChannelConfig {
-            channel_receiver: Value::Mapping(receiver),
-            channel_route: Value::Mapping(route),
-        }
-    }
-}
-
-impl AlertChannel<CRDPrometheus> for DiscordWebhook {
-    fn install_config(&self, sender: &CRDPrometheus) {
-        debug!("Installing Discord webhook for CRDPrometheus in namespace: {}", sender.namespace());
-        debug!("Config: {:?}", self.get_config());
-        debug!("Installed!");
-    }
-
-    fn name(&self) -> String {
-        "discord-webhook".to_string()
-    }
-}
-
-impl AlertChannel<RHOBObservability> for DiscordWebhook {
-    fn install_config(&self, sender: &RHOBObservability) {
-        debug!("Installing Discord webhook for RHOBObservability in namespace: {}", sender.namespace());
-        debug!("Config: {:?}", self.get_config());
-        debug!("Installed!");
-    }
-
-    fn name(&self) -> String {
-        "webhook-receiver".to_string()
-    }
-}
-
-impl AlertChannel<KubePrometheus> for DiscordWebhook {
-    fn install_config(&self, sender: &KubePrometheus) {
-        debug!("Installing Discord webhook for KubePrometheus in namespace: {}", sender.namespace());
-        let config = sender.config.lock().unwrap();
-        let ns = config.namespace.clone().unwrap_or_else(|| "monitoring".to_string());
-        debug!("Namespace: {}", ns);
-        let mut config = sender.config.lock().unwrap();
-        config.alert_receiver_configs.push(self.get_config());
-        debug!("Installed!");
-    }
-
-    fn name(&self) -> String {
-        "discord-webhook".to_string()
-    }
-}
-
-fn default_monitoring_stack() -> MonitoringStack {
-    MonitoringStack::new(MonitoringApiVersion::V2CRD)
-}
-
-#[derive(Debug, Clone, Serialize, Deserialize)]
-pub struct TenantMonitoringScore {
-    pub tenant_id: harmony_types::id::Id,
-    pub tenant_name: String,
-    #[serde(skip)]
-    #[serde(default = "default_monitoring_stack")]
-    pub monitoring_stack: MonitoringStack,
-}
-
-impl TenantMonitoringScore {
-    pub fn new(tenant_name: &str, monitoring_stack: MonitoringStack) -> Self {
-        Self {
-            tenant_id: harmony_types::id::Id::default(),
-            tenant_name: tenant_name.to_string(),
-            monitoring_stack,
-        }
-    }
-}
-
-impl<T: Topology + TenantManager> Score<T> for TenantMonitoringScore {
-    fn create_interpret(&self) -> Box<dyn Interpret<T>> {
-        Box::new(TenantMonitoringInterpret {
-            score: self.clone(),
-        })
-    }
-
-    fn name(&self) -> String {
-        format!("{} monitoring [TenantMonitoringScore]", self.tenant_name)
-    }
-}
-
-#[derive(Debug)]
-pub struct TenantMonitoringInterpret {
-    pub score: TenantMonitoringScore,
-}
-
-#[async_trait::async_trait]
-impl<T: Topology + TenantManager> Interpret<T> for TenantMonitoringInterpret {
-    async fn execute(
-        &self,
-        _inventory: &Inventory,
-        topology: &T,
-    ) -> Result<Outcome, InterpretError> {
-        let tenant_config = topology.get_tenant_config().await.unwrap();
-        let tenant_ns = tenant_config.name.clone();
-
-        match self.score.monitoring_stack.version {
-            MonitoringApiVersion::V1Helm => {
-                debug!("Installing Helm monitoring for tenant {}", tenant_ns);
-            }
-            MonitoringApiVersion::V2CRD => {
-                debug!("Installing CRD monitoring for tenant {}", tenant_ns);
-            }
-            MonitoringApiVersion::V3RHOB => {
-                debug!("Installing RHOB monitoring for tenant {}", tenant_ns);
-            }
-        }
-
-        Ok(Outcome::success(format!(
-            "Installed monitoring stack for tenant {} with version {:?}",
-            self.score.tenant_name,
-            self.score.monitoring_stack.version
-        )))
-    }
-
-    fn get_name(&self) -> InterpretName {
-        InterpretName::Custom("TenantMonitoringInterpret")
-    }
-
-    fn get_version(&self) -> Version {
-        Version::from("1.0.0").unwrap()
-    }
-
-    fn get_status(&self) -> InterpretStatus {
-        InterpretStatus::SUCCESS
-    }
-
-    fn get_children(&self) -> Vec<harmony_types::id::Id> {
-        Vec::new()
-    }
-}

docs/README.md

@@ -31,16 +31,3 @@ Ready to build your own components? These guides show you how.
 - [**Writing a Score**](./guides/writing-a-score.md): Learn how to create your own `Score` and `Interpret` logic to define a new desired state.
 - [**Writing a Topology**](./guides/writing-a-topology.md): Learn how to model a new environment (like AWS, GCP, or custom hardware) as a `Topology`.
 - [**Adding Capabilities**](./guides/adding-capabilities.md): See how to add a `Capability` to your custom `Topology`.
-- [**Coding Guide**](./coding-guide.md): Conventions and best practices for writing Harmony code.
-
-## 5. Module Documentation
-
-Deep dives into specific Harmony modules and features.
-
-- [**Monitoring and Alerting**](./monitoring.md): Comprehensive guide to cluster, tenant, and application-level monitoring with support for OKD, KubePrometheus, RHOB, and more.
-
-## 6. Architecture Decision Records
-
-Important architectural decisions are documented in the `adr/` directory:
-
-- [Full ADR Index](../adr/)

docs/monitoring.md

@@ -1,443 +0,0 @@
-# Monitoring and Alerting in Harmony
-
-Harmony provides a unified, type-safe approach to monitoring and alerting across Kubernetes, OpenShift, and bare-metal infrastructure. This guide explains the architecture and how to use it at different levels of abstraction.
-
-## Overview
-
-Harmony's monitoring module supports three distinct use cases:
-
-| Level | Who Uses It | What It Provides |
-|-------|-------------|------------------|
-| **Cluster** | Cluster administrators | Full control over monitoring stack, cluster-wide alerts, external scrape targets |
-| **Tenant** | Platform teams | Namespace-scoped monitoring in multi-tenant environments |
-| **Application** | Application developers | Zero-config monitoring that "just works" |
-
-Each level builds on the same underlying abstractions, ensuring consistency while providing appropriate complexity for each audience.
-
-## Core Concepts
-
-### AlertSender
-
-An `AlertSender` represents the system that evaluates alert rules and sends notifications. Harmony supports multiple monitoring stacks:
-
-| Sender | Description | Use When |
-|--------|-------------|----------|
-| `OpenshiftClusterAlertSender` | OKD/OpenShift built-in monitoring | Running on OKD/OpenShift |
-| `KubePrometheus` | kube-prometheus-stack via Helm | Standard Kubernetes, need full stack |
-| `Prometheus` | Standalone Prometheus | Custom Prometheus deployment |
-| `RedHatClusterObservability` | RHOB operator | Red Hat managed clusters |
-| `Grafana` | Grafana-managed alerting | Grafana as primary alerting layer |
-
-### AlertReceiver
-
-An `AlertReceiver` defines where alerts are sent (Discord, Slack, email, webhook, etc.). Receivers are parameterized by sender type because each monitoring stack has different configuration formats.
-
-```rust
-pub trait AlertReceiver<S: AlertSender> {
-    fn build(&self) -> Result<ReceiverInstallPlan, InterpretError>;
-    fn name(&self) -> String;
-}
-```
-
-Built-in receivers:
-- `DiscordReceiver` - Discord webhooks
-- `WebhookReceiver` - Generic HTTP webhooks
-
-### AlertRule
-
-An `AlertRule` defines a Prometheus alert expression. Rules are also parameterized by sender to handle different CRD formats.
-
-```rust
-pub trait AlertRule<S: AlertSender> {
-    fn build_rule(&self) -> Result<serde_json::Value, InterpretError>;
-    fn name(&self) -> String;
-}
-```
-
-### Observability Capability
-
-Topologies implement `Observability<S>` to indicate they support a specific alert sender:
-
-```rust
-impl Observability<OpenshiftClusterAlertSender> for K8sAnywhereTopology {
-    async fn install_receivers(&self, sender, inventory, receivers) { ... }
-    async fn install_rules(&self, sender, inventory, rules) { ... }
-    // ...
-}
-```
-
-This provides **compile-time verification**: if you try to use `OpenshiftClusterAlertScore` with a topology that doesn't implement `Observability<OpenshiftClusterAlertSender>`, the code won't compile.
-
----
-
-## Level 1: Cluster Monitoring
-
-Cluster monitoring is for administrators who need full control over the monitoring infrastructure. This includes:
-- Installing/managing the monitoring stack
-- Configuring cluster-wide alert receivers
-- Defining cluster-level alert rules
-- Adding external scrape targets (e.g., bare-metal servers, firewalls)
-
-### Example: OKD Cluster Alerts
-
-```rust
-use harmony::{
-    modules::monitoring::{
-        alert_channel::discord_alert_channel::DiscordReceiver,
-        alert_rule::{alerts::k8s::pvc::high_pvc_fill_rate_over_two_days, prometheus_alert_rule::AlertManagerRuleGroup},
-        okd::openshift_cluster_alerting_score::OpenshiftClusterAlertScore,
-        scrape_target::prometheus_node_exporter::PrometheusNodeExporter,
-    },
-    topology::{K8sAnywhereTopology, monitoring::{AlertMatcher, AlertRoute, MatchOp}},
-};
-
-let severity_matcher = AlertMatcher {
-    label: "severity".to_string(),
-    operator: MatchOp::Eq,
-    value: "critical".to_string(),
-};
-
-let rule_group = AlertManagerRuleGroup::new(
-    "cluster-rules",
-    vec![high_pvc_fill_rate_over_two_days()],
-);
-
-let external_exporter = PrometheusNodeExporter {
-    job_name: "firewall".to_string(),
-    metrics_path: "/metrics".to_string(),
-    listen_address: ip!("192.168.1.1"),
-    port: 9100,
-    ..Default::default()
-};
-
-harmony_cli::run(
-    Inventory::autoload(),
-    K8sAnywhereTopology::from_env(),
-    vec![Box::new(OpenshiftClusterAlertScore {
-        sender: OpenshiftClusterAlertSender,
-        receivers: vec![Box::new(DiscordReceiver {
-            name: "critical-alerts".to_string(),
-            url: hurl!("https://discord.com/api/webhooks/..."),
-            route: AlertRoute {
-                matchers: vec![severity_matcher],
-                ..AlertRoute::default("critical-alerts".to_string())
-            },
-        })],
-        rules: vec![Box::new(rule_group)],
-        scrape_targets: Some(vec![Box::new(external_exporter)]),
-    })],
-    None,
-).await?;
-```
-
-### What This Does
-
-1. **Enables cluster monitoring** - Activates OKD's built-in Prometheus
-2. **Enables user workload monitoring** - Allows namespace-scoped rules
-3. **Configures Alertmanager** - Adds Discord receiver with route matching
-4. **Deploys alert rules** - Creates `AlertingRule` CRD with PVC fill rate alert
-5. **Adds external scrape target** - Configures Prometheus to scrape the firewall
-
-### Compile-Time Safety
-
-The `OpenshiftClusterAlertScore` requires:
-
-```rust
-impl<T: Topology + Observability<OpenshiftClusterAlertSender>> Score<T>
-    for OpenshiftClusterAlertScore
-```
-
-If `K8sAnywhereTopology` didn't implement `Observability<OpenshiftClusterAlertSender>`, this code would fail to compile. You cannot accidentally deploy OKD alerts to a cluster that doesn't support them.
-
----
-
-## Level 2: Tenant Monitoring
-
-In multi-tenant clusters, teams are often confined to specific namespaces. Tenant monitoring adapts to this constraint:
-
-- Resources are deployed in the tenant's namespace
-- Cannot modify cluster-level monitoring configuration
-- The topology determines namespace context at runtime
-
-### How It Works
-
-The topology's `Observability` implementation handles tenant scoping:
-
-```rust
-impl Observability<KubePrometheus> for K8sAnywhereTopology {
-    async fn install_rules(&self, sender, inventory, rules) {
-        // Topology knows if it's tenant-scoped
-        let namespace = self.get_tenant_config().await
-            .map(|t| t.name)
-            .unwrap_or_else(|| "monitoring".to_string());
-        
-        // Rules are installed in the appropriate namespace
-        for rule in rules.unwrap_or_default() {
-            let score = KubePrometheusRuleScore {
-                sender: sender.clone(),
-                rule,
-                namespace: namespace.clone(), // Tenant namespace
-            };
-            score.create_interpret().execute(inventory, self).await?;
-        }
-    }
-}
-```
-
-### Tenant vs Cluster Resources
-
-| Resource | Cluster-Level | Tenant-Level |
-|----------|---------------|--------------|
-| Alertmanager config | Global receivers | Namespaced receivers (where supported) |
-| PrometheusRules | Cluster-wide alerts | Namespace alerts only |
-| ServiceMonitors | Any namespace | Own namespace only |
-| External scrape targets | Can add | Cannot add (cluster config) |
-
-### Runtime Validation
-
-Tenant constraints are validated at runtime via Kubernetes RBAC. If a tenant-scoped deployment attempts cluster-level operations, it fails with a clear permission error from the Kubernetes API.
-
-This cannot be fully compile-time because tenant context is determined by who's running the code and what permissions they have—information only available at runtime.
-
----
-
-## Level 3: Application Monitoring
-
-Application monitoring provides zero-config, opinionated monitoring for developers. Just add the `Monitoring` feature to your application and it works.
-
-### Example
-
-```rust
-use harmony::modules::{
-    application::{Application, ApplicationFeature},
-    monitoring::alert_channel::webhook_receiver::WebhookReceiver,
-};
-
-// Define your application
-let my_app = MyApplication::new();
-
-// Add monitoring as a feature
-let monitoring = Monitoring {
-    application: Arc::new(my_app),
-    alert_receiver: vec![], // Uses defaults
-};
-
-// Install with the application
-my_app.add_feature(monitoring);
-```
-
-### What Application Monitoring Provides
-
-1. **Automatic ServiceMonitor** - Creates a ServiceMonitor for your application's pods
-2. **Ntfy Notification Channel** - Auto-installs and configures Ntfy for push notifications
-3. **Tenant Awareness** - Automatically scopes to the correct namespace
-4. **Sensible Defaults** - Pre-configured alert routes and receivers
-
-### Under the Hood
-
-```rust
-impl<T: Topology + Observability<Prometheus> + TenantManager> 
-    ApplicationFeature<T> for Monitoring 
-{
-    async fn ensure_installed(&self, topology: &T) -> Result<...> {
-        // 1. Get tenant namespace (or use app name)
-        let namespace = topology.get_tenant_config().await
-            .map(|ns| ns.name.clone())
-            .unwrap_or_else(|| self.application.name());
-
-        // 2. Create ServiceMonitor for the app
-        let app_service_monitor = ServiceMonitor {
-            metadata: ObjectMeta {
-                name: Some(self.application.name()),
-                namespace: Some(namespace.clone()),
-                ..Default::default()
-            },
-            spec: ServiceMonitorSpec::default(),
-        };
-
-        // 3. Install Ntfy for notifications
-        let ntfy = NtfyScore { namespace, host };
-        ntfy.interpret(&Inventory::empty(), topology).await?;
-
-        // 4. Wire up webhook receiver to Ntfy
-        let ntfy_receiver = WebhookReceiver { ... };
-        
-        // 5. Execute monitoring score
-        alerting_score.interpret(&Inventory::empty(), topology).await?;
-    }
-}
-```
-
----
-
-## Pre-Built Alert Rules
-
-Harmony provides a library of common alert rules in `modules/monitoring/alert_rule/alerts/`:
-
-### Kubernetes Alerts (`alerts/k8s/`)
-
-```rust
-use harmony::modules::monitoring::alert_rule::alerts::k8s::{
-    pod::pod_failed,
-    pvc::high_pvc_fill_rate_over_two_days,
-    memory_usage::alert_high_memory_usage,
-};
-
-let rules = AlertManagerRuleGroup::new("k8s-rules", vec![
-    pod_failed(),
-    high_pvc_fill_rate_over_two_days(),
-    alert_high_memory_usage(),
-]);
-```
-
-Available rules:
-- `pod_failed()` - Pod in failed state
-- `alert_container_restarting()` - Container restart loop
-- `alert_pod_not_ready()` - Pod not ready for extended period
-- `high_pvc_fill_rate_over_two_days()` - PVC will fill within 2 days
-- `alert_high_memory_usage()` - Memory usage above threshold
-- `alert_high_cpu_usage()` - CPU usage above threshold
-
-### Infrastructure Alerts (`alerts/infra/`)
-
-```rust
-use harmony::modules::monitoring::alert_rule::alerts::infra::opnsense::high_http_error_rate;
-
-let rules = AlertManagerRuleGroup::new("infra-rules", vec![
-    high_http_error_rate(),
-]);
-```
-
-### Creating Custom Rules
-
-```rust
-use harmony::modules::monitoring::alert_rule::prometheus_alert_rule::PrometheusAlertRule;
-
-pub fn my_custom_alert() -> PrometheusAlertRule {
-    PrometheusAlertRule::new("MyServiceDown", "up{job=\"my-service\"} == 0")
-        .for_duration("5m")
-        .label("severity", "critical")
-        .annotation("summary", "My service is down")
-        .annotation("description", "The my-service job has been down for more than 5 minutes")
-}
-```
-
----
-
-## Alert Receivers
-
-### Discord Webhook
-
-```rust
-use harmony::modules::monitoring::alert_channel::discord_alert_channel::DiscordReceiver;
-use harmony::topology::monitoring::{AlertRoute, AlertMatcher, MatchOp};
-
-let discord = DiscordReceiver {
-    name: "ops-alerts".to_string(),
-    url: hurl!("https://discord.com/api/webhooks/123456/abcdef"),
-    route: AlertRoute {
-        receiver: "ops-alerts".to_string(),
-        matchers: vec![AlertMatcher {
-            label: "severity".to_string(),
-            operator: MatchOp::Eq,
-            value: "critical".to_string(),
-        }],
-        group_by: vec!["alertname".to_string()],
-        repeat_interval: Some("30m".to_string()),
-        continue_matching: false,
-        children: vec![],
-    },
-};
-```
-
-### Generic Webhook
-
-```rust
-use harmony::modules::monitoring::alert_channel::webhook_receiver::WebhookReceiver;
-
-let webhook = WebhookReceiver {
-    name: "custom-webhook".to_string(),
-    url: hurl!("https://api.example.com/alerts"),
-    route: AlertRoute::default("custom-webhook".to_string()),
-};
-```
-
----
-
-## Adding a New Monitoring Stack
-
-To add support for a new monitoring stack:
-
-1. **Create the sender type** in `modules/monitoring/my_sender/mod.rs`:
-   ```rust
-   #[derive(Debug, Clone)]
-   pub struct MySender;
-   
-   impl AlertSender for MySender {
-       fn name(&self) -> String { "MySender".to_string() }
-   }
-   ```
-
-2. **Define CRD types** in `modules/monitoring/my_sender/crd/`:
-   ```rust
-   #[derive(CustomResource, Debug, Serialize, Deserialize, Clone)]
-   #[kube(group = "monitoring.example.com", version = "v1", kind = "MyAlertRule")]
-   pub struct MyAlertRuleSpec { ... }
-   ```
-
-3. **Implement Observability** in `domain/topology/k8s_anywhere/observability/my_sender.rs`:
-   ```rust
-   impl Observability<MySender> for K8sAnywhereTopology {
-       async fn install_receivers(&self, sender, inventory, receivers) { ... }
-       async fn install_rules(&self, sender, inventory, rules) { ... }
-       // ...
-   }
-   ```
-
-4. **Implement receiver conversions** for existing receivers:
-   ```rust
-   impl AlertReceiver<MySender> for DiscordReceiver {
-       fn build(&self) -> Result<ReceiverInstallPlan, InterpretError> {
-           // Convert DiscordReceiver to MySender's format
-       }
-   }
-   ```
-
-5. **Create score types**:
-   ```rust
-   pub struct MySenderAlertScore {
-       pub sender: MySender,
-       pub receivers: Vec<Box<dyn AlertReceiver<MySender>>>,
-       pub rules: Vec<Box<dyn AlertRule<MySender>>>,
-   }
-   ```
-
----
-
-## Architecture Principles
-
-### Type Safety Over Flexibility
-
-Each monitoring stack has distinct CRDs and configuration formats. Rather than a unified "MonitoringStack" type that loses stack-specific features, we use generic traits that provide type safety while allowing each stack to express its unique configuration.
-
-### Compile-Time Capability Verification
-
-The `Observability<S>` bound ensures you can't deploy OKD alerts to a KubePrometheus cluster. The compiler catches platform mismatches before deployment.
-
-### Explicit Over Implicit
-
-Monitoring stacks are chosen explicitly (`OpenshiftClusterAlertSender` vs `KubePrometheus`). There's no "auto-detection" that could lead to surprising behavior.
-
-### Three Levels, One Foundation
-
-Cluster, tenant, and application monitoring all use the same traits (`AlertSender`, `AlertReceiver`, `AlertRule`). The difference is in how scores are constructed and how topologies interpret them.
-
----
-
-## Related Documentation
-
-- [ADR-020: Monitoring and Alerting Architecture](../adr/020-monitoring-alerting-architecture.md)
-- [ADR-013: Monitoring Notifications (ntfy)](../adr/013-monitoring-notifications.md)
-- [ADR-011: Multi-Tenant Cluster Architecture](../adr/011-multi-tenant-cluster.md)
-- [Coding Guide](coding-guide.md)
-- [Core Concepts](concepts.md)

examples/application_monitoring_with_tenant/src/main.rs

@@ -7,7 +7,7 @@ use harmony::{
         monitoring::alert_channel::webhook_receiver::WebhookReceiver,
         tenant::TenantScore,
     },
-    topology::{K8sAnywhereTopology, monitoring::AlertRoute, tenant::TenantConfig},
+    topology::{K8sAnywhereTopology, tenant::TenantConfig},
 };
 use harmony_types::id::Id;
 use harmony_types::net::Url;
@@ -33,14 +33,9 @@ async fn main() {
         service_port: 3000,
     });
 
-    let receiver_name = "sample-webhook-receiver".to_string();
-
     let webhook_receiver = WebhookReceiver {
-        name: receiver_name.clone(),
+        name: "sample-webhook-receiver".to_string(),
         url: Url::Url(url::Url::parse("https://webhook-doesnt-exist.com").unwrap()),
-        route: AlertRoute {
-            ..AlertRoute::default(receiver_name)
-        },
     };
 
     let app = ApplicationScore {

examples/monitoring/src/main.rs

@@ -1,45 +1,37 @@
-use std::{
+use std::collections::HashMap;
-    collections::HashMap,
-    sync::{Arc, Mutex},
-};
 
 use harmony::{
     inventory::Inventory,
-    modules::monitoring::{
+    modules::{
-        alert_channel::discord_alert_channel::DiscordReceiver,
+        monitoring::{
-        alert_rule::{
+            alert_channel::discord_alert_channel::DiscordWebhook,
-            alerts::{
+            alert_rule::prometheus_alert_rule::AlertManagerRuleGroup,
-                infra::dell_server::{
-                    alert_global_storage_status_critical,
-                    alert_global_storage_status_non_recoverable,
-                    global_storage_status_degraded_non_critical,
-                },
-                k8s::pvc::high_pvc_fill_rate_over_two_days,
-            },
-            prometheus_alert_rule::AlertManagerRuleGroup,
-        },
             kube_prometheus::{
-            helm::config::KubePrometheusConfig,
+                helm_prometheus_alert_score::HelmPrometheusAlertingScore,
-            kube_prometheus_alerting_score::KubePrometheusAlertingScore,
                 types::{
                     HTTPScheme, MatchExpression, Operator, Selector, ServiceMonitor,
                     ServiceMonitorEndpoint,
                 },
             },
         },
-    topology::{K8sAnywhereTopology, monitoring::AlertRoute},
+        prometheus::alerts::{
+            infra::dell_server::{
+                alert_global_storage_status_critical, alert_global_storage_status_non_recoverable,
+                global_storage_status_degraded_non_critical,
+            },
+            k8s::pvc::high_pvc_fill_rate_over_two_days,
+        },
+    },
+    topology::K8sAnywhereTopology,
 };
 use harmony_types::{k8s_name::K8sName, net::Url};
 
 #[tokio::main]
 async fn main() {
-    let receiver_name = "test-discord".to_string();
+    let discord_receiver = DiscordWebhook {
-    let discord_receiver = DiscordReceiver {
+        name: K8sName("test-discord".to_string()),
-        name: receiver_name.clone(),
         url: Url::Url(url::Url::parse("https://discord.doesnt.exist.com").unwrap()),
-        route: AlertRoute {
+        selectors: vec![],
-            ..AlertRoute::default(receiver_name)
-        },
     };
 
     let high_pvc_fill_rate_over_two_days_alert = high_pvc_fill_rate_over_two_days();
@@ -78,15 +70,10 @@ async fn main() {
         endpoints: vec![service_monitor_endpoint],
         ..Default::default()
     };
-
+    let alerting_score = HelmPrometheusAlertingScore {
-    let config = Arc::new(Mutex::new(KubePrometheusConfig::new()));
-
-    let alerting_score = KubePrometheusAlertingScore {
         receivers: vec![Box::new(discord_receiver)],
         rules: vec![Box::new(additional_rules), Box::new(additional_rules2)],
         service_monitors: vec![service_monitor],
-        scrape_targets: None,
-        config,
     };
 
     harmony_cli::run(

examples/monitoring_with_tenant/src/main.rs

@@ -1,32 +1,24 @@
-use std::{
+use std::{collections::HashMap, str::FromStr};
-    collections::HashMap,
-    str::FromStr,
-    sync::{Arc, Mutex},
-};
 
 use harmony::{
     inventory::Inventory,
     modules::{
         monitoring::{
-            alert_channel::discord_alert_channel::DiscordReceiver,
+            alert_channel::discord_alert_channel::DiscordWebhook,
-            alert_rule::{
+            alert_rule::prometheus_alert_rule::AlertManagerRuleGroup,
-                alerts::k8s::pvc::high_pvc_fill_rate_over_two_days,
-                prometheus_alert_rule::AlertManagerRuleGroup,
-            },
             kube_prometheus::{
-                helm::config::KubePrometheusConfig,
+                helm_prometheus_alert_score::HelmPrometheusAlertingScore,
-                kube_prometheus_alerting_score::KubePrometheusAlertingScore,
                 types::{
                     HTTPScheme, MatchExpression, Operator, Selector, ServiceMonitor,
                     ServiceMonitorEndpoint,
                 },
             },
         },
+        prometheus::alerts::k8s::pvc::high_pvc_fill_rate_over_two_days,
         tenant::TenantScore,
     },
     topology::{
         K8sAnywhereTopology,
-        monitoring::AlertRoute,
         tenant::{ResourceLimits, TenantConfig, TenantNetworkPolicy},
     },
 };
@@ -50,13 +42,10 @@ async fn main() {
         },
     };
 
-    let receiver_name = "test-discord".to_string();
+    let discord_receiver = DiscordWebhook {
-    let discord_receiver = DiscordReceiver {
+        name: K8sName("test-discord".to_string()),
-        name: receiver_name.clone(),
         url: Url::Url(url::Url::parse("https://discord.doesnt.exist.com").unwrap()),
-        route: AlertRoute {
+        selectors: vec![],
-            ..AlertRoute::default(receiver_name)
-        },
     };
 
     let high_pvc_fill_rate_over_two_days_alert = high_pvc_fill_rate_over_two_days();
@@ -85,14 +74,10 @@ async fn main() {
         ..Default::default()
     };
 
-    let config = Arc::new(Mutex::new(KubePrometheusConfig::new()));
+    let alerting_score = HelmPrometheusAlertingScore {
-
-    let alerting_score = KubePrometheusAlertingScore {
         receivers: vec![Box::new(discord_receiver)],
         rules: vec![Box::new(additional_rules)],
         service_monitors: vec![service_monitor],
-        scrape_targets: None,
-        config,
     };
 
     harmony_cli::run(

examples/multisite_postgres/src/main.rs

@@ -14,7 +14,6 @@ async fn main() {
             ..Default::default() // Use harmony defaults, they are based on CNPG's default values :
                                  // "default" namespace, 1 instance, 1Gi storage
         },
-        hostname: "postgrestest.sto1.nationtech.io".to_string(),
     };
 
     harmony_cli::run(

examples/okd_cluster_alerts/src/main.rs

@@ -1,64 +1,35 @@
+use std::collections::HashMap;
+
 use harmony::{
     inventory::Inventory,
     modules::monitoring::{
-        alert_channel::discord_alert_channel::DiscordReceiver,
+        alert_channel::discord_alert_channel::DiscordWebhook,
-        alert_rule::{
+        okd::cluster_monitoring::OpenshiftClusterAlertScore,
-            alerts::{
-                infra::opnsense::high_http_error_rate, k8s::pvc::high_pvc_fill_rate_over_two_days,
-            },
-            prometheus_alert_rule::AlertManagerRuleGroup,
-        },
-        okd::openshift_cluster_alerting_score::OpenshiftClusterAlertScore,
-        scrape_target::prometheus_node_exporter::PrometheusNodeExporter,
-    },
-    topology::{
-        K8sAnywhereTopology,
-        monitoring::{AlertMatcher, AlertRoute, MatchOp},
     },
+    topology::K8sAnywhereTopology,
 };
-
+use harmony_macros::hurl;
-use harmony_macros::{hurl, ip};
+use harmony_types::k8s_name::K8sName;
 
 #[tokio::main]
 async fn main() {
-    let platform_matcher = AlertMatcher {
+    let mut sel = HashMap::new();
-        label: "prometheus".to_string(),
+    sel.insert(
-        operator: MatchOp::Eq,
+        "openshift_io_alert_source".to_string(),
-        value: "openshift-monitoring/k8s".to_string(),
+        "platform".to_string(),
-    };
+    );
-    let severity = AlertMatcher {
+    let mut sel2 = HashMap::new();
-        label: "severity".to_string(),
+    sel2.insert("openshift_io_alert_source".to_string(), "".to_string());
-        operator: MatchOp::Eq,
+    let selectors = vec![sel, sel2];
-        value: "critical".to_string(),
-    };
-
-    let high_http_error_rate = high_http_error_rate();
-
-    let additional_rules = AlertManagerRuleGroup::new("test-rule", vec![high_http_error_rate]);
-
-    let scrape_target = PrometheusNodeExporter {
-        job_name: "firewall".to_string(),
-        metrics_path: "/metrics".to_string(),
-        listen_address: ip!("192.168.1.1"),
-        port: 9100,
-        ..Default::default()
-    };
-
     harmony_cli::run(
         Inventory::autoload(),
         K8sAnywhereTopology::from_env(),
         vec![Box::new(OpenshiftClusterAlertScore {
-            receivers: vec![Box::new(DiscordReceiver {
+            receivers: vec![Box::new(DiscordWebhook {
-                name: "crit-wills-discord-channel-example".to_string(),
+                name: K8sName("wills-discord-webhook-example".to_string()),
-                url: hurl!("https://test.io"),
+                url: hurl!("https://something.io"),
-                route: AlertRoute {
+                selectors: selectors,
-                    matchers: vec![severity],
-                    ..AlertRoute::default("crit-wills-discord-channel-example".to_string())
-                },
             })],
-            sender: harmony::modules::monitoring::okd::OpenshiftClusterAlertSender,
-            rules: vec![Box::new(additional_rules)],
-            scrape_targets: Some(vec![Box::new(scrape_target)]),
         })],
         None,
     )

examples/okd_installation/src/main.rs

@@ -6,7 +6,10 @@ use harmony::{
     data::{FileContent, FilePath},
     modules::{
         inventory::HarmonyDiscoveryStrategy,
-        okd::{installation::OKDInstallationPipeline, ipxe::OKDIpxeScore},
+        okd::{
+            installation::OKDInstallationPipeline, ipxe::OKDIpxeScore,
+            load_balancer::OKDLoadBalancerScore,
+        },
     },
     score::Score,
     topology::HAClusterTopology,
@@ -32,6 +35,7 @@ async fn main() {
     scores
         .append(&mut OKDInstallationPipeline::get_all_scores(HarmonyDiscoveryStrategy::MDNS).await);
 
+    scores.push(Box::new(OKDLoadBalancerScore::new(&topology)));
     harmony_cli::run(inventory, topology, scores, None)
         .await
         .unwrap();

examples/public_postgres/src/main.rs

@@ -15,7 +15,6 @@ async fn main() {
             ..Default::default() // Use harmony defaults, they are based on CNPG's default values :
                                  // 1 instance, 1Gi storage
         },
-        hostname: "postgrestest.sto1.nationtech.io".to_string(),
     };
 
     let test_connection = PostgreSQLConnectionScore {

examples/rhob_application_monitoring/src/main.rs

@@ -6,9 +6,9 @@ use harmony::{
         application::{
             ApplicationScore, RustWebFramework, RustWebapp, features::rhob_monitoring::Monitoring,
         },
-        monitoring::alert_channel::discord_alert_channel::DiscordReceiver,
+        monitoring::alert_channel::discord_alert_channel::DiscordWebhook,
     },
-    topology::{K8sAnywhereTopology, monitoring::AlertRoute},
+    topology::K8sAnywhereTopology,
 };
 use harmony_types::{k8s_name::K8sName, net::Url};
 
@@ -22,21 +22,18 @@ async fn main() {
         service_port: 3000,
     });
 
-    let receiver_name = "test-discord".to_string();
+    let discord_receiver = DiscordWebhook {
-    let discord_receiver = DiscordReceiver {
+        name: K8sName("test-discord".to_string()),
-        name: receiver_name.clone(),
         url: Url::Url(url::Url::parse("https://discord.doesnt.exist.com").unwrap()),
-        route: AlertRoute {
+        selectors: vec![],
-            ..AlertRoute::default(receiver_name)
-        },
     };
 
     let app = ApplicationScore {
         features: vec![
-            // Box::new(Monitoring {
+            Box::new(Monitoring {
-            //     application: application.clone(),
+                application: application.clone(),
-            //     alert_receiver: vec![Box::new(discord_receiver)],
+                alert_receiver: vec![Box::new(discord_receiver)],
-            // }),
+            }),
             // TODO add backups, multisite ha, etc
         ],
         application,

examples/rust/src/main.rs

@@ -8,13 +8,13 @@ use harmony::{
             features::{Monitoring, PackagingDeployment},
         },
         monitoring::alert_channel::{
-            discord_alert_channel::DiscordReceiver, webhook_receiver::WebhookReceiver,
+            discord_alert_channel::DiscordWebhook, webhook_receiver::WebhookReceiver,
         },
     },
-    topology::{K8sAnywhereTopology, monitoring::AlertRoute},
+    topology::K8sAnywhereTopology,
 };
 use harmony_macros::hurl;
-use harmony_types::{k8s_name::K8sName, net::Url};
+use harmony_types::k8s_name::K8sName;
 
 #[tokio::main]
 async fn main() {
@@ -26,23 +26,15 @@ async fn main() {
         service_port: 3000,
     });
 
-    let receiver_name = "test-discord".to_string();
+    let discord_receiver = DiscordWebhook {
-    let discord_receiver = DiscordReceiver {
+        name: K8sName("test-discord".to_string()),
-        name: receiver_name.clone(),
+        url: hurl!("https://discord.doesnt.exist.com"),
-        url: Url::Url(url::Url::parse("https://discord.doesnt.exist.com").unwrap()),
+        selectors: vec![],
-        route: AlertRoute {
-            ..AlertRoute::default(receiver_name)
-        },
     };
 
-    let receiver_name = "sample-webhook-receiver".to_string();
-
     let webhook_receiver = WebhookReceiver {
-        name: receiver_name.clone(),
+        name: "sample-webhook-receiver".to_string(),
         url: hurl!("https://webhook-doesnt-exist.com"),
-        route: AlertRoute {
-            ..AlertRoute::default(receiver_name)
-        },
     };
 
     let app = ApplicationScore {
@@ -50,10 +42,10 @@ async fn main() {
             Box::new(PackagingDeployment {
                 application: application.clone(),
             }),
-            // Box::new(Monitoring {
+            Box::new(Monitoring {
-            //     application: application.clone(),
+                application: application.clone(),
-            //     alert_receiver: vec![Box::new(discord_receiver), Box::new(webhook_receiver)],
+                alert_receiver: vec![Box::new(discord_receiver), Box::new(webhook_receiver)],
-            // }),
+            }),
             // TODO add backups, multisite ha, etc
         ],
         application,

examples/try_rust_webapp/src/main.rs

@@ -1,9 +1,12 @@
 use harmony::{
     inventory::Inventory,
-    modules::application::{
+    modules::{
+        application::{
             ApplicationScore, RustWebFramework, RustWebapp,
             features::{Monitoring, PackagingDeployment},
         },
+        monitoring::alert_channel::discord_alert_channel::DiscordWebhook,
+    },
     topology::K8sAnywhereTopology,
 };
 use harmony_macros::hurl;
@@ -27,14 +30,14 @@ async fn main() {
             Box::new(PackagingDeployment {
                 application: application.clone(),
             }),
-            // Box::new(Monitoring {
+            Box::new(Monitoring {
-            //     application: application.clone(),
+                application: application.clone(),
-            //     alert_receiver: vec![Box::new(DiscordWebhook {
+                alert_receiver: vec![Box::new(DiscordWebhook {
-            //         name: K8sName("test-discord".to_string()),
+                    name: K8sName("test-discord".to_string()),
-            //         url: hurl!("https://discord.doesnt.exist.com"),
+                    url: hurl!("https://discord.doesnt.exist.com"),
-            //         selectors: vec![],
+                    selectors: vec![],
-            //     })],
+                })],
-            // }),
+            }),
         ],
         application,
     };

examples/tui/src/main.rs

@@ -44,6 +44,7 @@ fn build_large_score() -> LoadBalancerScore {
         ],
         listening_port: SocketAddr::V4(SocketAddrV4::new(ipv4!("192.168.0.0"), 49387)),
         health_check: Some(HealthCheck::HTTP(
+            Some(1993),
             "/some_long_ass_path_to_see_how_it_is_displayed_but_it_has_to_be_even_longer"
                 .to_string(),
             HttpMethod::GET,

examples/vllm/Cargo.toml

@@ -0,0 +1,15 @@
+[package]
+name = "vllm"
+edition = "2024"
+version.workspace = true
+readme.workspace = true
+license.workspace = true
+publish = false
+
+[dependencies]
+harmony = { path = "../../harmony" }
+harmony_cli = { path = "../../harmony_cli" }
+k8s-openapi = { workspace = true }
+tokio = { workspace = true }
+log = { workspace = true }
+env_logger = { workspace = true }

examples/vllm/src/main.rs

@@ -0,0 +1,523 @@
+//! vLLM Deployment Example for Qwen3.5-27B-FP8 on NVIDIA RTX 5090
+//!
+//! This example deploys vLLM serving Qwen3.5-27B with FP8 quantization,
+//! optimized for single RTX 5090 (32GB VRAM) with tool calling support.
+//!
+//! # Architecture & Memory Constraints
+//!
+//! **Model Details:**
+//! - Parameters: 27B (dense, not sparse/MoE)
+//! - Quantization: FP8 (8-bit weights)
+//! - Model size: ~27-28GB in memory
+//! - Native context: 262,144 tokens (will NOT fit in 32GB VRAM)
+//!
+//! **VRAM Budget for RTX 5090 (32GB):**
+//! - Model weights (FP8): ~27GB
+//! - Framework overhead: ~1-2GB
+//! - KV cache: ~2-3GB (for 16k context)
+//! - CUDA context: ~500MB
+//! - Temporary buffers: ~500MB
+//! - **Total: ~31-33GB** (tight fit, leaves minimal headroom)
+//!
+//! # OpenShift/OKD Requirements
+//!
+//! **SCC (Security Context Constraint) Setup:**
+//!
+//! The official vLLM container runs as root and writes to `/root/.cache/huggingface`.
+//! On OpenShift/OKD with the default restricted SCC, containers run as arbitrary UIDs
+//! and cannot write to `/root`. For testing, grant the `anyuid` SCC:
+//!
+//! ```bash
+//! # As cluster admin, grant anyuid SCC to the namespace's service account:
+//! oc adm policy add-scc-to-user anyuid -z default -n vllm-qwen
+//! ```
+//!
+//! This allows pods in the `vllm-qwen` namespace to run as root (UID 0).
+//! For production, consider building a custom vLLM image that runs as non-root.
+//!
+//! # Critical Configuration Notes
+//!
+//! 1. **GPU_MEMORY_UTILIZATION=1.0**: Maximum GPU memory allocation.
+//!    NEVER decrease this for dense models - CPU offloading destroys performance
+//!    (100-1000x slower) for models where every parameter is used during inference.
+//!
+//! 2. **MAX_MODEL_LEN=16384**: Conservative context length that fits in available VRAM.
+//!    Agentic workflows with long tool call histories will need careful context management.
+//!
+//! 3. **--language-model-only**: Skips loading the vision encoder, saving ~1-2GB VRAM.
+//!    Essential for fitting the model in 32GB VRAM.
+//!
+//! 4. **PVC Size**: 50Gi for HuggingFace cache. Qwen3.5-27B-FP8 is ~30GB.
+//!
+//! # Performance Expectations
+//!
+//! - Single token latency: ~50-100ms (no CPU offloading)
+//! - With CPU offloading: ~5-50 seconds per token (unusable for real-time inference)
+//! - Throughput: ~10-20 tokens/second (single stream, no batching)
+//!
+//! # Next Steps for Production
+//!
+//! To increase context length:
+//! 1. Monitor GPU memory: `kubectl exec -it deployment/qwen3-5-27b -- nvidia-smi dmon -s u`
+//! 2. If stable, increase MAX_MODEL_LEN (try 32768, then 65536)
+//! 3. If OOM: revert to lower value
+//!
+//! For full 262k context, consider:
+//! - Multi-GPU setup with tensor parallelism (--tensor-parallel-size 8)
+//! - Or use a smaller model (Qwen3.5-7B-FP8)
+
+use std::collections::BTreeMap;
+
+use harmony::{
+    inventory::Inventory,
+    modules::{
+        k8s::resource::K8sResourceScore,
+        okd::{
+            crd::route::{RoutePort, RouteSpec, RouteTargetReference, TLSConfig},
+            route::OKDRouteScore,
+        },
+    },
+    score::Score,
+    topology::{K8sAnywhereTopology, TlsRouter},
+};
+use k8s_openapi::{
+    api::{
+        apps::v1::{Deployment, DeploymentSpec, DeploymentStrategy},
+        core::v1::{
+            Container, ContainerPort, EmptyDirVolumeSource, EnvVar, EnvVarSource,
+            HTTPGetAction, PersistentVolumeClaim, PersistentVolumeClaimSpec,
+            PersistentVolumeClaimVolumeSource, PodSpec, PodTemplateSpec, Probe,
+            ResourceRequirements, Secret, SecretKeySelector, SecretVolumeSource, Service,
+            ServicePort, ServiceSpec, Volume, VolumeMount, VolumeResourceRequirements,
+        },
+    },
+    apimachinery::pkg::{
+        api::resource::Quantity,
+        apis::meta::v1::{LabelSelector, ObjectMeta},
+        util::intstr::IntOrString,
+    },
+    ByteString,
+};
+use log::info;
+
+const NAMESPACE: &str = "vllm-qwen";
+const MODEL_NAME: &str = "Qwen/Qwen3.5-27B-FP8";
+const DEPLOYMENT_NAME: &str = "qwen3-5-27b";
+const SERVICE_NAME: &str = DEPLOYMENT_NAME;
+const ROUTE_NAME: &str = DEPLOYMENT_NAME;
+const PVC_NAME: &str = "huggingface-cache";
+const SECRET_NAME: &str = "hf-token-secret";
+
+const VLLM_IMAGE: &str = "vllm/vllm-openai:latest";
+const SERVICE_PORT: u16 = 8000;
+const TARGET_PORT: u16 = 8000;
+
+/// Maximum context length for the model (in tokens).
+///
+/// **Impact on VRAM:**
+/// - Qwen3.5-27B uses per-token KV cache storage for the context window
+/// - Larger context = more KV cache memory required
+/// - Approximate KV cache per token: ~32KB for FP8 (very rough estimate)
+/// - 16k tokens ≈ 0.5-1GB KV cache
+/// - 262k tokens ≈ 8-16GB KV cache (native context length - will NOT fit in 32GB VRAM)
+///
+/// **Performance Impact:**
+/// - Context length directly impacts memory for storing conversation history
+/// - Agentic workflows with long tool call histories benefit from more context
+/// - If context > available VRAM, vLLM will OOM and fail to start
+///
+/// **Recommendations for RTX 5090 (32GB):**
+/// - Start with 16384 (conservative, should work)
+/// - If no OOM, try 32768 (better for agentic workflows)
+/// - Monitor GPU memory with `nvidia-smi` during operation
+const MAX_MODEL_LEN: i64 = 16384;
+
+/// Fraction of GPU memory to allocate for the model (0.0 to 1.0).
+///
+/// **CRITICAL WARNING: This is a dense model!**
+/// Qwen3.5-27B-FP8 is NOT a sparse/mixture-of-experts model. All 27B parameters
+/// are active during inference. CPU offloading will DESTROY performance.
+///
+/// **What this parameter controls:**
+/// - Controls how much of GPU memory vLLM pre-allocates for:
+///   1. Model weights (~27GB for FP8 quantization)
+///   2. KV cache for context window
+///   3. Activation buffers for inference
+///   4. Runtime overhead
+///
+/// **VRAM Allocation Example:**
+/// - GPU: 32GB RTX 5090
+/// - GPU_MEMORY_UTILIZATION: 0.95
+/// - vLLM will try to use: 32GB * 0.95 = 30.4GB
+/// - Model weights: ~27-28GB
+/// - Remaining for KV cache + runtime: ~2-3GB
+///
+/// **If set too LOW (e.g., 0.7):**
+/// - vLLM restricts itself to 32GB * 0.7 = 22.4GB
+/// - Model weights alone need ~27GB
+/// - vLLM will OFFLOAD model weights to CPU memory
+/// - Performance: **100-1000x slower** (single token generation can take seconds instead of milliseconds)
+/// - This is catastrophic for a dense model where every layer needs all parameters
+///
+/// **If set too HIGH (e.g., 0.99):**
+/// - vLLM tries to allocate nearly all GPU memory
+/// - Risk: CUDA OOM if any other process needs GPU memory
+/// - Risk: KV cache allocation fails during inference
+/// - System instability
+///
+/// **Current Setting: 0.95**
+/// - Leaves 5% buffer (1.6GB) for CUDA overhead, system processes
+/// - Maximum allocation for model + KV cache: ~30.4GB
+/// - Should leave enough headroom for:
+///   - CUDA context: ~500MB
+///   - Temporary buffers: ~500MB
+///   - Safety margin: ~600MB
+///
+/// **How to tune:**
+/// 1. Start with 0.95 (current setting)
+/// 2. Monitor with `nvidia-smi dmon -s u` during operation
+/// 3. If OOM during inference: reduce MAX_MODEL_LEN first
+/// 4. If stable: try increasing MAX_MODEL_LEN before increasing this
+/// 5. Only increase this if you're certain no other GPU processes run
+///
+/// **NEVER decrease this for dense models!** 
+/// If model doesn't fit, use a smaller model or quantization, not CPU offloading.
+const GPU_MEMORY_UTILIZATION : f32 = 1.0;
+
+#[tokio::main]
+async fn main() -> Result<(), Box<dyn std::error::Error>> {
+    env_logger::init();
+
+    info!("Deploying vLLM with Qwen3.5-27B-FP8 model");
+    info!("Configuration:");
+    info!("  Model: {}", MODEL_NAME);
+    info!("  Max context length: {} tokens", MAX_MODEL_LEN);
+    info!("  GPU memory utilization: {}", GPU_MEMORY_UTILIZATION);
+    info!("  Language model only: true");
+    info!("  Tool calling enabled: true");
+
+    let topology = K8sAnywhereTopology::from_env();
+    let domain = topology
+        .get_internal_domain()
+        .await
+        .ok()
+        .flatten()
+        .unwrap_or_else(|| "cluster.local".to_string());
+
+    let host = format!("{}-{}.apps.{}", SERVICE_NAME, NAMESPACE, domain);
+    info!("Creating route with host: {}", host);
+
+    let scores: Vec<Box<dyn Score<K8sAnywhereTopology>>> = vec![
+        create_namespace(),
+        create_pvc(),
+        create_secret(),
+        create_deployment(),
+        create_service(),
+        create_route(&host),
+    ];
+
+    harmony_cli::run(Inventory::autoload(), topology, scores, None)
+        .await
+        .map_err(|e| format!("Failed to deploy: {}", e))?;
+
+    info!("Successfully deployed vLLM with Qwen3.5-27B-FP8");
+    info!("Access the API at: http://{}.apps.<cluster-domain>", SERVICE_NAME);
+
+    Ok(())
+}
+
+fn create_namespace() -> Box<dyn Score<K8sAnywhereTopology>> {
+    use k8s_openapi::api::core::v1::Namespace;
+
+    let namespace = Namespace {
+        metadata: ObjectMeta {
+            name: Some(NAMESPACE.to_string()),
+            ..Default::default()
+        },
+        spec: None,
+        status: None,
+    };
+
+    Box::new(K8sResourceScore::single(namespace, None))
+}
+
+fn create_pvc() -> Box<dyn Score<K8sAnywhereTopology>> {
+    let pvc = PersistentVolumeClaim {
+        metadata: ObjectMeta {
+            name: Some(PVC_NAME.to_string()),
+            namespace: Some(NAMESPACE.to_string()),
+            ..Default::default()
+        },
+        spec: Some(PersistentVolumeClaimSpec {
+            access_modes: Some(vec!["ReadWriteOnce".to_string()]),
+            resources: Some(VolumeResourceRequirements {
+                requests: Some(BTreeMap::from([(
+                    "storage".to_string(),
+                    Quantity("50Gi".to_string()),
+                )])),
+                limits: None,
+            }),
+            ..Default::default()
+        }),
+        status: None,
+    };
+
+    Box::new(K8sResourceScore::single(
+        pvc,
+        Some(NAMESPACE.to_string()),
+    ))
+}
+
+fn create_secret() -> Box<dyn Score<K8sAnywhereTopology>> {
+    let mut data = BTreeMap::new();
+    data.insert(
+        "token".to_string(),
+        ByteString("".to_string().into_bytes()),
+    );
+
+    let secret = Secret {
+        metadata: ObjectMeta {
+            name: Some(SECRET_NAME.to_string()),
+            namespace: Some(NAMESPACE.to_string()),
+            ..Default::default()
+        },
+        data: Some(data),
+        immutable: Some(false),
+        type_: Some("Opaque".to_string()),
+        string_data: None,
+    };
+
+    Box::new(K8sResourceScore::single(
+        secret,
+        Some(NAMESPACE.to_string()),
+    ))
+}
+
+fn create_deployment() -> Box<dyn Score<K8sAnywhereTopology>> {
+    let deployment = Deployment {
+        metadata: ObjectMeta {
+            name: Some(DEPLOYMENT_NAME.to_string()),
+            namespace: Some(NAMESPACE.to_string()),
+            labels: Some(BTreeMap::from([(
+                "app".to_string(),
+                DEPLOYMENT_NAME.to_string(),
+            )])),
+            ..Default::default()
+        },
+        spec: Some(DeploymentSpec {
+            replicas: Some(1),
+            selector: LabelSelector {
+                match_labels: Some(BTreeMap::from([(
+                    "app".to_string(),
+                    DEPLOYMENT_NAME.to_string(),
+                )])),
+                ..Default::default()
+            },
+            strategy: Some(DeploymentStrategy {
+                type_: Some("Recreate".to_string()),
+                ..Default::default()
+            }),
+            template: PodTemplateSpec {
+                metadata: Some(ObjectMeta {
+                    labels: Some(BTreeMap::from([(
+                        "app".to_string(),
+                        DEPLOYMENT_NAME.to_string(),
+                    )])),
+                    ..Default::default()
+                }),
+                spec: Some(PodSpec {
+                    node_selector: Some(BTreeMap::from([(
+                        "nvidia.com/gpu.product".to_string(),
+                        "NVIDIA-GeForce-RTX-5090".to_string(),
+                    )])),
+                    volumes: Some(vec![
+                        Volume {
+                            name: "cache-volume".to_string(),
+                            persistent_volume_claim: Some(PersistentVolumeClaimVolumeSource {
+                                claim_name: PVC_NAME.to_string(),
+                                read_only: Some(false),
+                            }),
+                            ..Default::default()
+                        },
+                        Volume {
+                            name: "shm".to_string(),
+                            empty_dir: Some(EmptyDirVolumeSource {
+                                medium: Some("Memory".to_string()),
+                                size_limit: Some(Quantity("4Gi".to_string())),
+                            }),
+                            ..Default::default()
+                        },
+                        Volume {
+                            name: "hf-token".to_string(),
+                            secret: Some(SecretVolumeSource {
+                                secret_name: Some(SECRET_NAME.to_string()),
+                                optional: Some(true),
+                                ..Default::default()
+                            }),
+                            ..Default::default()
+                        },
+                    ]),
+                    containers: vec![Container {
+                        name: DEPLOYMENT_NAME.to_string(),
+                        image: Some(VLLM_IMAGE.to_string()),
+                        command: Some(vec!["/bin/sh".to_string(), "-c".to_string()]),
+                        args: Some(vec![build_vllm_command()]),
+                        env: Some(vec![
+                            EnvVar {
+                                name: "HF_TOKEN".to_string(),
+                                value_from: Some(EnvVarSource {
+                                    secret_key_ref: Some(SecretKeySelector {
+                                        key: "token".to_string(),
+                                        name: SECRET_NAME.to_string(),
+                                        optional: Some(true),
+                                    }),
+                                    ..Default::default()
+                                }),
+                                value: None,
+                            },
+                            EnvVar {
+                                name: "VLLM_WORKER_MULTIPROC_METHOD".to_string(),
+                                value: Some("spawn".to_string()),
+                                value_from: None,
+                            },
+                        ]),
+                        ports: Some(vec![ContainerPort {
+                            container_port: SERVICE_PORT as i32,
+                            protocol: Some("TCP".to_string()),
+                            ..Default::default()
+                        }]),
+                        resources: Some(ResourceRequirements {
+                            limits: Some(BTreeMap::from([
+                                ("cpu".to_string(), Quantity("10".to_string())),
+                                ("memory".to_string(), Quantity("30Gi".to_string())),
+                                ("nvidia.com/gpu".to_string(), Quantity("1".to_string())),
+                            ])),
+                            requests: Some(BTreeMap::from([
+                                ("cpu".to_string(), Quantity("2".to_string())),
+                                ("memory".to_string(), Quantity("10Gi".to_string())),
+                                ("nvidia.com/gpu".to_string(), Quantity("1".to_string())),
+                            ])),
+                            claims: None,
+                        }),
+                        volume_mounts: Some(vec![
+                            VolumeMount {
+                                name: "cache-volume".to_string(),
+                                mount_path: "/root/.cache/huggingface".to_string(),
+                                read_only: Some(false),
+                                ..Default::default()
+                            },
+                            VolumeMount {
+                                name: "shm".to_string(),
+                                mount_path: "/dev/shm".to_string(),
+                                ..Default::default()
+                            },
+                            VolumeMount {
+                                name: "hf-token".to_string(),
+                                mount_path: "/etc/secrets/hf-token".to_string(),
+                                read_only: Some(true),
+                                ..Default::default()
+                            },
+                        ]),
+                        liveness_probe: Some(Probe {
+                            http_get: Some(HTTPGetAction {
+                                path: Some("/health".to_string()),
+                                port: IntOrString::Int(SERVICE_PORT as i32),
+                                ..Default::default()
+                            }),
+                            initial_delay_seconds: Some(300),
+                            period_seconds: Some(30),
+                            ..Default::default()
+                        }),
+                        readiness_probe: Some(Probe {
+                            http_get: Some(HTTPGetAction {
+                                path: Some("/health".to_string()),
+                                port: IntOrString::Int(SERVICE_PORT as i32),
+                                ..Default::default()
+                            }),
+                            initial_delay_seconds: Some(120),
+                            period_seconds: Some(10),
+                            ..Default::default()
+                        }),
+                        ..Default::default()
+                    }],
+                    ..Default::default()
+                }),
+            },
+            ..Default::default()
+        }),
+        status: None,
+    };
+
+    Box::new(K8sResourceScore::single(
+        deployment,
+        Some(NAMESPACE.to_string()),
+    ))
+}
+
+fn build_vllm_command() -> String {
+    format!(
+        "vllm serve {} \
+         --port {} \
+         --max-model-len {} \
+         --gpu-memory-utilization {} \
+         --reasoning-parser qwen3 \
+         --enable-auto-tool-choice \
+         --tool-call-parser qwen3_coder \
+         --language-model-only",
+        MODEL_NAME, SERVICE_PORT, MAX_MODEL_LEN, GPU_MEMORY_UTILIZATION
+    )
+}
+
+fn create_service() -> Box<dyn Score<K8sAnywhereTopology>> {
+    let service = Service {
+        metadata: ObjectMeta {
+            name: Some(SERVICE_NAME.to_string()),
+            namespace: Some(NAMESPACE.to_string()),
+            ..Default::default()
+        },
+        spec: Some(ServiceSpec {
+            ports: Some(vec![ServicePort {
+                name: Some("http".to_string()),
+                port: SERVICE_PORT as i32,
+                protocol: Some("TCP".to_string()),
+                target_port: Some(IntOrString::Int(TARGET_PORT as i32)),
+                ..Default::default()
+            }]),
+            selector: Some(BTreeMap::from([(
+                "app".to_string(),
+                DEPLOYMENT_NAME.to_string(),
+            )])),
+            type_: Some("ClusterIP".to_string()),
+            ..Default::default()
+        }),
+        status: None,
+    };
+
+    Box::new(K8sResourceScore::single(
+        service,
+        Some(NAMESPACE.to_string()),
+    ))
+}
+
+fn create_route(host: &str) -> Box<dyn Score<K8sAnywhereTopology>> {
+    let route_spec = RouteSpec {
+        to: RouteTargetReference {
+            kind: "Service".to_string(),
+            name: SERVICE_NAME.to_string(),
+            weight: Some(100),
+        },
+        host: Some(host.to_string()),
+        port: Some(RoutePort {
+            target_port: SERVICE_PORT as u16,
+        }),
+        tls: Some(TLSConfig {
+            termination: "edge".to_string(),
+            insecure_edge_termination_policy: Some("Redirect".to_string()),
+            ..Default::default()
+        }),
+        wildcard_policy: None,
+        ..Default::default()
+    };
+
+    Box::new(OKDRouteScore::new(ROUTE_NAME, NAMESPACE, route_spec))
+}

harmony/src/domain/topology/k8s_anywhere/k8s_anywhere.rs

@@ -1,4 +1,4 @@
-use std::{collections::BTreeMap, process::Command, sync::Arc};
+use std::{collections::BTreeMap, process::Command, sync::Arc, time::Duration};
 
 use async_trait::async_trait;
 use base64::{Engine, engine::general_purpose};
@@ -8,7 +8,7 @@ use k8s_openapi::api::{
     core::v1::{Pod, Secret},
     rbac::v1::{ClusterRoleBinding, RoleRef, Subject},
 };
-use kube::api::{GroupVersionKind, ObjectMeta};
+use kube::api::{DynamicObject, GroupVersionKind, ObjectMeta};
 use log::{debug, info, trace, warn};
 use serde::Serialize;
 use tokio::sync::OnceCell;
@@ -29,7 +29,28 @@ use crate::{
             score_cert_management::CertificateManagementScore,
         },
         k3d::K3DInstallationScore,
+        k8s::ingress::{K8sIngressScore, PathType},
+        monitoring::{
+            grafana::{grafana::Grafana, helm::helm_grafana::grafana_helm_chart_score},
+            kube_prometheus::crd::{
+                crd_alertmanager_config::CRDPrometheus,
+                crd_grafana::{
+                    Grafana as GrafanaCRD, GrafanaCom, GrafanaDashboard,
+                    GrafanaDashboardDatasource, GrafanaDashboardSpec, GrafanaDatasource,
+                    GrafanaDatasourceConfig, GrafanaDatasourceJsonData,
+                    GrafanaDatasourceSecureJsonData, GrafanaDatasourceSpec, GrafanaSpec,
+                },
+                crd_prometheuses::LabelSelector,
+                prometheus_operator::prometheus_operator_helm_chart_score,
+                rhob_alertmanager_config::RHOBObservability,
+                service_monitor::ServiceMonitor,
+            },
+        },
         okd::{crd::ingresses_config::Ingress as IngressResource, route::OKDTlsPassthroughScore},
+        prometheus::{
+            k8s_prometheus_alerting_score::K8sPrometheusCRDAlertingScore,
+            prometheus::PrometheusMonitoring, rhob_alerting_score::RHOBAlertingScore,
+        },
     },
     score::Score,
     topology::{TlsRoute, TlsRouter, ingress::Ingress},
@@ -38,6 +59,7 @@ use crate::{
 use super::super::{
     DeploymentTarget, HelmCommand, K8sclient, MultiTargetTopology, PreparationError,
     PreparationOutcome, Topology,
+    oberservability::monitoring::AlertReceiver,
     tenant::{
         TenantConfig, TenantManager,
         k8s::K8sTenantManager,
@@ -87,6 +109,13 @@ impl K8sclient for K8sAnywhereTopology {
 
 #[async_trait]
 impl TlsRouter for K8sAnywhereTopology {
+    async fn get_public_domain(&self) -> Result<String, String> {
+        match &self.config.public_domain {
+            Some(public_domain) => Ok(public_domain.to_string()),
+            None => Err("Public domain not available".to_string()),
+        }
+    }
+
     async fn get_internal_domain(&self) -> Result<Option<String>, String> {
         match self.get_k8s_distribution().await.map_err(|e| {
             format!(
@@ -144,6 +173,216 @@ impl TlsRouter for K8sAnywhereTopology {
     }
 }
 
+#[async_trait]
+impl Grafana for K8sAnywhereTopology {
+    async fn ensure_grafana_operator(
+        &self,
+        inventory: &Inventory,
+    ) -> Result<PreparationOutcome, PreparationError> {
+        debug!("ensure grafana operator");
+        let client = self.k8s_client().await.unwrap();
+        let grafana_gvk = GroupVersionKind {
+            group: "grafana.integreatly.org".to_string(),
+            version: "v1beta1".to_string(),
+            kind: "Grafana".to_string(),
+        };
+        let name = "grafanas.grafana.integreatly.org";
+        let ns = "grafana";
+
+        let grafana_crd = client
+            .get_resource_json_value(name, Some(ns), &grafana_gvk)
+            .await;
+        match grafana_crd {
+            Ok(_) => {
+                return Ok(PreparationOutcome::Success {
+                    details: "Found grafana CRDs in cluster".to_string(),
+                });
+            }
+
+            Err(_) => {
+                return self
+                    .install_grafana_operator(inventory, Some("grafana"))
+                    .await;
+            }
+        };
+    }
+    async fn install_grafana(&self) -> Result<PreparationOutcome, PreparationError> {
+        let ns = "grafana";
+
+        let mut label = BTreeMap::new();
+
+        label.insert("dashboards".to_string(), "grafana".to_string());
+
+        let label_selector = LabelSelector {
+            match_labels: label.clone(),
+            match_expressions: vec![],
+        };
+
+        let client = self.k8s_client().await?;
+
+        let grafana = self.build_grafana(ns, &label);
+
+        client.apply(&grafana, Some(ns)).await?;
+        //TODO change this to a ensure ready or something better than just a timeout
+        client
+            .wait_until_deployment_ready(
+                "grafana-grafana-deployment",
+                Some("grafana"),
+                Some(Duration::from_secs(30)),
+            )
+            .await?;
+
+        let sa_name = "grafana-grafana-sa";
+        let token_secret_name = "grafana-sa-token-secret";
+
+        let sa_token_secret = self.build_sa_token_secret(token_secret_name, sa_name, ns);
+
+        client.apply(&sa_token_secret, Some(ns)).await?;
+        let secret_gvk = GroupVersionKind {
+            group: "".to_string(),
+            version: "v1".to_string(),
+            kind: "Secret".to_string(),
+        };
+
+        let secret = client
+            .get_resource_json_value(token_secret_name, Some(ns), &secret_gvk)
+            .await?;
+
+        let token = format!(
+            "Bearer {}",
+            self.extract_and_normalize_token(&secret).unwrap()
+        );
+
+        debug!("creating grafana clusterrole binding");
+
+        let clusterrolebinding =
+            self.build_cluster_rolebinding(sa_name, "cluster-monitoring-view", ns);
+
+        client.apply(&clusterrolebinding, Some(ns)).await?;
+
+        debug!("creating grafana datasource crd");
+
+        let thanos_url = format!(
+            "https://{}",
+            self.get_domain("thanos-querier-openshift-monitoring")
+                .await
+                .unwrap()
+        );
+
+        let thanos_openshift_datasource = self.build_grafana_datasource(
+            "thanos-openshift-monitoring",
+            ns,
+            &label_selector,
+            &thanos_url,
+            &token,
+        );
+
+        client.apply(&thanos_openshift_datasource, Some(ns)).await?;
+
+        debug!("creating grafana dashboard crd");
+        let dashboard = self.build_grafana_dashboard(ns, &label_selector);
+
+        client.apply(&dashboard, Some(ns)).await?;
+        debug!("creating grafana ingress");
+        let grafana_ingress = self.build_grafana_ingress(ns).await;
+
+        grafana_ingress
+            .interpret(&Inventory::empty(), self)
+            .await
+            .map_err(|e| PreparationError::new(e.to_string()))?;
+
+        Ok(PreparationOutcome::Success {
+            details: "Installed grafana composants".to_string(),
+        })
+    }
+}
+
+#[async_trait]
+impl PrometheusMonitoring<CRDPrometheus> for K8sAnywhereTopology {
+    async fn install_prometheus(
+        &self,
+        sender: &CRDPrometheus,
+        _inventory: &Inventory,
+        _receivers: Option<Vec<Box<dyn AlertReceiver<CRDPrometheus>>>>,
+    ) -> Result<PreparationOutcome, PreparationError> {
+        let client = self.k8s_client().await?;
+
+        for monitor in sender.service_monitor.iter() {
+            client
+                .apply(monitor, Some(&sender.namespace))
+                .await
+                .map_err(|e| PreparationError::new(e.to_string()))?;
+        }
+        Ok(PreparationOutcome::Success {
+            details: "successfuly installed prometheus components".to_string(),
+        })
+    }
+
+    async fn ensure_prometheus_operator(
+        &self,
+        sender: &CRDPrometheus,
+        _inventory: &Inventory,
+    ) -> Result<PreparationOutcome, PreparationError> {
+        let po_result = self.ensure_prometheus_operator(sender).await?;
+
+        match po_result {
+            PreparationOutcome::Success { details: _ } => {
+                debug!("Detected prometheus crds operator present in cluster.");
+                return Ok(po_result);
+            }
+            PreparationOutcome::Noop => {
+                debug!("Skipping Prometheus CR installation due to missing operator.");
+                return Ok(po_result);
+            }
+        }
+    }
+}
+
+#[async_trait]
+impl PrometheusMonitoring<RHOBObservability> for K8sAnywhereTopology {
+    async fn install_prometheus(
+        &self,
+        sender: &RHOBObservability,
+        inventory: &Inventory,
+        receivers: Option<Vec<Box<dyn AlertReceiver<RHOBObservability>>>>,
+    ) -> Result<PreparationOutcome, PreparationError> {
+        let po_result = self.ensure_cluster_observability_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_cluster_observability_operator_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())),
+        }
+    }
+
+    async fn ensure_prometheus_operator(
+        &self,
+        sender: &RHOBObservability,
+        inventory: &Inventory,
+    ) -> Result<PreparationOutcome, PreparationError> {
+        todo!()
+    }
+}
+
 impl Serialize for K8sAnywhereTopology {
     fn serialize<S>(&self, _serializer: S) -> Result<S::Ok, S::Error>
     where
@@ -348,6 +587,23 @@ impl K8sAnywhereTopology {
         }
     }
 
+    fn extract_and_normalize_token(&self, secret: &DynamicObject) -> Option<String> {
+        let token_b64 = secret
+            .data
+            .get("token")
+            .or_else(|| secret.data.get("data").and_then(|d| d.get("token")))
+            .and_then(|v| v.as_str())?;
+
+        let bytes = general_purpose::STANDARD.decode(token_b64).ok()?;
+
+        let s = String::from_utf8(bytes).ok()?;
+
+        let cleaned = s
+            .trim_matches(|c: char| c.is_whitespace() || c == '\0')
+            .to_string();
+        Some(cleaned)
+    }
+
     pub async fn get_k8s_distribution(&self) -> Result<KubernetesDistribution, PreparationError> {
         self.k8s_client()
             .await?
@@ -407,6 +663,141 @@ impl K8sAnywhereTopology {
         }
     }
 
+    fn build_grafana_datasource(
+        &self,
+        name: &str,
+        ns: &str,
+        label_selector: &LabelSelector,
+        url: &str,
+        token: &str,
+    ) -> GrafanaDatasource {
+        let mut json_data = BTreeMap::new();
+        json_data.insert("timeInterval".to_string(), "5s".to_string());
+
+        GrafanaDatasource {
+            metadata: ObjectMeta {
+                name: Some(name.to_string()),
+                namespace: Some(ns.to_string()),
+                ..Default::default()
+            },
+            spec: GrafanaDatasourceSpec {
+                instance_selector: label_selector.clone(),
+                allow_cross_namespace_import: Some(true),
+                values_from: None,
+                datasource: GrafanaDatasourceConfig {
+                    access: "proxy".to_string(),
+                    name: name.to_string(),
+                    r#type: "prometheus".to_string(),
+                    url: url.to_string(),
+                    database: None,
+                    json_data: Some(GrafanaDatasourceJsonData {
+                        time_interval: Some("60s".to_string()),
+                        http_header_name1: Some("Authorization".to_string()),
+                        tls_skip_verify: Some(true),
+                        oauth_pass_thru: Some(true),
+                    }),
+                    secure_json_data: Some(GrafanaDatasourceSecureJsonData {
+                        http_header_value1: Some(format!("Bearer {token}")),
+                    }),
+                    is_default: Some(false),
+                    editable: Some(true),
+                },
+            },
+        }
+    }
+
+    fn build_grafana_dashboard(
+        &self,
+        ns: &str,
+        label_selector: &LabelSelector,
+    ) -> GrafanaDashboard {
+        let graf_dashboard = GrafanaDashboard {
+            metadata: ObjectMeta {
+                name: Some(format!("grafana-dashboard-{}", ns)),
+                namespace: Some(ns.to_string()),
+                ..Default::default()
+            },
+            spec: GrafanaDashboardSpec {
+                resync_period: Some("30s".to_string()),
+                instance_selector: label_selector.clone(),
+                datasources: Some(vec![GrafanaDashboardDatasource {
+                    input_name: "DS_PROMETHEUS".to_string(),
+                    datasource_name: "thanos-openshift-monitoring".to_string(),
+                }]),
+                json: None,
+                grafana_com: Some(GrafanaCom {
+                    id: 17406,
+                    revision: None,
+                }),
+            },
+        };
+        graf_dashboard
+    }
+
+    fn build_grafana(&self, ns: &str, labels: &BTreeMap<String, String>) -> GrafanaCRD {
+        let grafana = GrafanaCRD {
+            metadata: ObjectMeta {
+                name: Some(format!("grafana-{}", ns)),
+                namespace: Some(ns.to_string()),
+                labels: Some(labels.clone()),
+                ..Default::default()
+            },
+            spec: GrafanaSpec {
+                config: None,
+                admin_user: None,
+                admin_password: None,
+                ingress: None,
+                persistence: None,
+                resources: None,
+            },
+        };
+        grafana
+    }
+
+    async fn build_grafana_ingress(&self, ns: &str) -> K8sIngressScore {
+        let domain = self.get_domain(&format!("grafana-{}", ns)).await.unwrap();
+        let name = format!("{}-grafana", ns);
+        let backend_service = format!("grafana-{}-service", ns);
+
+        K8sIngressScore {
+            name: fqdn::fqdn!(&name),
+            host: fqdn::fqdn!(&domain),
+            backend_service: fqdn::fqdn!(&backend_service),
+            port: 3000,
+            path: Some("/".to_string()),
+            path_type: Some(PathType::Prefix),
+            namespace: Some(fqdn::fqdn!(&ns)),
+            ingress_class_name: Some("openshift-default".to_string()),
+        }
+    }
+
+    async fn get_cluster_observability_operator_prometheus_application_score(
+        &self,
+        sender: RHOBObservability,
+        receivers: Option<Vec<Box<dyn AlertReceiver<RHOBObservability>>>>,
+    ) -> RHOBAlertingScore {
+        RHOBAlertingScore {
+            sender,
+            receivers: receivers.unwrap_or_default(),
+            service_monitors: vec![],
+            prometheus_rules: vec![],
+        }
+    }
+
+    async fn get_k8s_prometheus_application_score(
+        &self,
+        sender: CRDPrometheus,
+        receivers: Option<Vec<Box<dyn AlertReceiver<CRDPrometheus>>>>,
+        service_monitors: Option<Vec<ServiceMonitor>>,
+    ) -> K8sPrometheusCRDAlertingScore {
+        return K8sPrometheusCRDAlertingScore {
+            sender,
+            receivers: receivers.unwrap_or_default(),
+            service_monitors: service_monitors.unwrap_or_default(),
+            prometheus_rules: vec![],
+        };
+    }
+
     async fn openshift_ingress_operator_available(&self) -> Result<(), PreparationError> {
         let client = self.k8s_client().await?;
         let gvk = GroupVersionKind {
@@ -572,6 +963,137 @@ impl K8sAnywhereTopology {
             )),
         }
     }
+
+    async fn ensure_cluster_observability_operator(
+        &self,
+        sender: &RHOBObservability,
+    ) -> Result<PreparationOutcome, PreparationError> {
+        let status = Command::new("sh")
+            .args(["-c", "kubectl get crd -A | grep -i rhobs"])
+            .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 => {
+                        warn!(
+                            "Installing observability operator is not supported on LocalK3d source"
+                        );
+                        return Ok(PreparationOutcome::Noop);
+                        debug!("installing cluster observability operator");
+                        todo!();
+                        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 cluster observability operator".into(),
+                                }),
+                                InterpretStatus::NOOP => Ok(PreparationOutcome::Noop),
+                                _ => Err(PreparationError::new(
+                                    "failed to install cluster observability operator (unknown error)".into(),
+                                )),
+                            },
+                            Err(err) => Err(PreparationError::new(err.to_string())),
+                        };
+                    }
+                    K8sSource::Kubeconfig => {
+                        debug!(
+                            "unable to install cluster observability operator, contact cluster admin"
+                        );
+                        return Ok(PreparationOutcome::Noop);
+                    }
+                }
+            } else {
+                warn!(
+                    "Unable to detect k8s_state. Skipping Cluster Observability Operator install."
+                );
+                return Ok(PreparationOutcome::Noop);
+            }
+        }
+
+        debug!("Cluster Observability Operator is already present, skipping install");
+
+        Ok(PreparationOutcome::Success {
+            details: "cluster observability operator present in cluster".into(),
+        })
+    }
+
+    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(),
+        })
+    }
+
+    async fn install_grafana_operator(
+        &self,
+        inventory: &Inventory,
+        ns: Option<&str>,
+    ) -> Result<PreparationOutcome, PreparationError> {
+        let namespace = ns.unwrap_or("grafana");
+        info!("installing grafana operator in ns {namespace}");
+        let tenant = self.get_k8s_tenant_manager()?.get_tenant_config().await;
+        let mut namespace_scope = false;
+        if tenant.is_some() {
+            namespace_scope = true;
+        }
+        let _grafana_operator_score = grafana_helm_chart_score(namespace, namespace_scope)
+            .interpret(inventory, self)
+            .await
+            .map_err(|e| PreparationError::new(e.to_string()));
+        Ok(PreparationOutcome::Success {
+            details: format!(
+                "Successfully installed grafana operator in ns {}",
+                ns.unwrap()
+            ),
+        })
+    }
 }
 
 #[derive(Clone, Debug)]
@@ -609,6 +1131,7 @@ pub struct K8sAnywhereConfig {
     ///
     /// If the context name is not found, it will fail to initialize.
     pub k8s_context: Option<String>,
+    public_domain: Option<String>,
 }
 
 impl K8sAnywhereConfig {
@@ -636,6 +1159,7 @@ impl K8sAnywhereConfig {
 
         let mut kubeconfig: Option<String> = None;
         let mut k8s_context: Option<String> = None;
+        let mut public_domain: Option<String> = None;
 
         for part in env_var_value.split(',') {
             let kv: Vec<&str> = part.splitn(2, '=').collect();
@@ -643,6 +1167,7 @@ impl K8sAnywhereConfig {
                 match kv[0].trim() {
                     "kubeconfig" => kubeconfig = Some(kv[1].trim().to_string()),
                     "context" => k8s_context = Some(kv[1].trim().to_string()),
+                    "public_domain" => public_domain = Some(kv[1].trim().to_string()),
                     _ => {}
                 }
             }
@@ -660,6 +1185,7 @@ impl K8sAnywhereConfig {
         K8sAnywhereConfig {
             kubeconfig,
             k8s_context,
+            public_domain,
             use_system_kubeconfig,
             autoinstall: false,
             use_local_k3d: false,
@@ -702,6 +1228,7 @@ impl K8sAnywhereConfig {
             use_local_k3d: std::env::var("HARMONY_USE_LOCAL_K3D")
                 .map_or_else(|_| true, |v| v.parse().ok().unwrap_or(true)),
             k8s_context: std::env::var("HARMONY_K8S_CONTEXT").ok(),
+            public_domain: std::env::var("HARMONY_PUBLIC_DOMAIN").ok(),
         }
     }
 }

harmony/src/domain/topology/k8s_anywhere/mod.rs

@@ -1,5 +1,4 @@
 mod k8s_anywhere;
 pub mod nats;
-pub mod observability;
 mod postgres;
 pub use k8s_anywhere::*;

harmony/src/domain/topology/k8s_anywhere/observability/grafana.rs

@@ -1,147 +0,0 @@
-use async_trait::async_trait;
-
-use crate::{
-    inventory::Inventory,
-    modules::monitoring::grafana::{
-        grafana::Grafana,
-        k8s::{
-            score_ensure_grafana_ready::GrafanaK8sEnsureReadyScore,
-            score_grafana_alert_receiver::GrafanaK8sReceiverScore,
-            score_grafana_datasource::GrafanaK8sDatasourceScore,
-            score_grafana_rule::GrafanaK8sRuleScore, score_install_grafana::GrafanaK8sInstallScore,
-        },
-    },
-    score::Score,
-    topology::{
-        K8sAnywhereTopology, PreparationError, PreparationOutcome,
-        monitoring::{AlertReceiver, AlertRule, Observability, ScrapeTarget},
-    },
-};
-
-#[async_trait]
-impl Observability<Grafana> for K8sAnywhereTopology {
-    async fn install_alert_sender(
-        &self,
-        sender: &Grafana,
-        inventory: &Inventory,
-    ) -> Result<PreparationOutcome, PreparationError> {
-        let score = GrafanaK8sInstallScore {
-            sender: sender.clone(),
-        };
-
-        score
-            .create_interpret()
-            .execute(inventory, self)
-            .await
-            .map_err(|e| PreparationError::new(format!("Grafana not installed {}", e)))?;
-        Ok(PreparationOutcome::Success {
-            details: "Successfully installed grafana alert sender".to_string(),
-        })
-    }
-
-    async fn install_receivers(
-        &self,
-        sender: &Grafana,
-        inventory: &Inventory,
-        receivers: Option<Vec<Box<dyn AlertReceiver<Grafana>>>>,
-    ) -> Result<PreparationOutcome, PreparationError> {
-        let receivers = match receivers {
-            Some(r) if !r.is_empty() => r,
-            _ => return Ok(PreparationOutcome::Noop),
-        };
-
-        for receiver in receivers {
-            let score = GrafanaK8sReceiverScore {
-                receiver,
-                sender: sender.clone(),
-            };
-
-            score
-                .create_interpret()
-                .execute(inventory, self)
-                .await
-                .map_err(|e| PreparationError::new(format!("Failed to install receiver: {}", e)))?;
-        }
-
-        Ok(PreparationOutcome::Success {
-            details: "All alert receivers installed successfully".to_string(),
-        })
-    }
-
-    async fn install_rules(
-        &self,
-        sender: &Grafana,
-        inventory: &Inventory,
-        rules: Option<Vec<Box<dyn AlertRule<Grafana>>>>,
-    ) -> Result<PreparationOutcome, PreparationError> {
-        let rules = match rules {
-            Some(r) if !r.is_empty() => r,
-            _ => return Ok(PreparationOutcome::Noop),
-        };
-
-        for rule in rules {
-            let score = GrafanaK8sRuleScore {
-                sender: sender.clone(),
-                rule,
-            };
-
-            score
-                .create_interpret()
-                .execute(inventory, self)
-                .await
-                .map_err(|e| PreparationError::new(format!("Failed to install rule: {}", e)))?;
-        }
-
-        Ok(PreparationOutcome::Success {
-            details: "All alert rules installed successfully".to_string(),
-        })
-    }
-
-    async fn add_scrape_targets(
-        &self,
-        sender: &Grafana,
-        inventory: &Inventory,
-        scrape_targets: Option<Vec<Box<dyn ScrapeTarget<Grafana>>>>,
-    ) -> Result<PreparationOutcome, PreparationError> {
-        let scrape_targets = match scrape_targets {
-            Some(r) if !r.is_empty() => r,
-            _ => return Ok(PreparationOutcome::Noop),
-        };
-
-        for scrape_target in scrape_targets {
-            let score = GrafanaK8sDatasourceScore {
-                scrape_target,
-                sender: sender.clone(),
-            };
-
-            score
-                .create_interpret()
-                .execute(inventory, self)
-                .await
-                .map_err(|e| PreparationError::new(format!("Failed to add DataSource: {}", e)))?;
-        }
-
-        Ok(PreparationOutcome::Success {
-            details: "All datasources installed successfully".to_string(),
-        })
-    }
-
-    async fn ensure_monitoring_installed(
-        &self,
-        sender: &Grafana,
-        inventory: &Inventory,
-    ) -> Result<PreparationOutcome, PreparationError> {
-        let score = GrafanaK8sEnsureReadyScore {
-            sender: sender.clone(),
-        };
-
-        score
-            .create_interpret()
-            .execute(inventory, self)
-            .await
-            .map_err(|e| PreparationError::new(format!("Grafana not ready {}", e)))?;
-        Ok(PreparationOutcome::Success {
-            details: "Grafana Ready".to_string(),
-        })
-    }
-}

harmony/src/domain/topology/k8s_anywhere/observability/kube_prometheus.rs

@@ -1,142 +0,0 @@
-use async_trait::async_trait;
-
-use crate::{
-    inventory::Inventory,
-    modules::monitoring::kube_prometheus::{
-        KubePrometheus, helm::kube_prometheus_helm_chart::kube_prometheus_helm_chart_score,
-        score_kube_prometheus_alert_receivers::KubePrometheusReceiverScore,
-        score_kube_prometheus_ensure_ready::KubePrometheusEnsureReadyScore,
-        score_kube_prometheus_rule::KubePrometheusRuleScore,
-        score_kube_prometheus_scrape_target::KubePrometheusScrapeTargetScore,
-    },
-    score::Score,
-    topology::{
-        K8sAnywhereTopology, PreparationError, PreparationOutcome,
-        monitoring::{AlertReceiver, AlertRule, Observability, ScrapeTarget},
-    },
-};
-
-#[async_trait]
-impl Observability<KubePrometheus> for K8sAnywhereTopology {
-    async fn install_alert_sender(
-        &self,
-        sender: &KubePrometheus,
-        inventory: &Inventory,
-    ) -> Result<PreparationOutcome, PreparationError> {
-        kube_prometheus_helm_chart_score(sender.config.clone())
-            .create_interpret()
-            .execute(inventory, self)
-            .await
-            .map_err(|e| PreparationError::new(e.to_string()))?;
-
-        Ok(PreparationOutcome::Success {
-            details: "Successfully installed kubeprometheus alert sender".to_string(),
-        })
-    }
-
-    async fn install_receivers(
-        &self,
-        sender: &KubePrometheus,
-        inventory: &Inventory,
-        receivers: Option<Vec<Box<dyn AlertReceiver<KubePrometheus>>>>,
-    ) -> Result<PreparationOutcome, PreparationError> {
-        let receivers = match receivers {
-            Some(r) if !r.is_empty() => r,
-            _ => return Ok(PreparationOutcome::Noop),
-        };
-
-        for receiver in receivers {
-            let score = KubePrometheusReceiverScore {
-                receiver,
-                sender: sender.clone(),
-            };
-
-            score
-                .create_interpret()
-                .execute(inventory, self)
-                .await
-                .map_err(|e| PreparationError::new(format!("Failed to install receiver: {}", e)))?;
-        }
-
-        Ok(PreparationOutcome::Success {
-            details: "All alert receivers installed successfully".to_string(),
-        })
-    }
-
-    async fn install_rules(
-        &self,
-        sender: &KubePrometheus,
-        inventory: &Inventory,
-        rules: Option<Vec<Box<dyn AlertRule<KubePrometheus>>>>,
-    ) -> Result<PreparationOutcome, PreparationError> {
-        let rules = match rules {
-            Some(r) if !r.is_empty() => r,
-            _ => return Ok(PreparationOutcome::Noop),
-        };
-
-        for rule in rules {
-            let score = KubePrometheusRuleScore {
-                sender: sender.clone(),
-                rule,
-            };
-
-            score
-                .create_interpret()
-                .execute(inventory, self)
-                .await
-                .map_err(|e| PreparationError::new(format!("Failed to install rule: {}", e)))?;
-        }
-
-        Ok(PreparationOutcome::Success {
-            details: "All alert rules installed successfully".to_string(),
-        })
-    }
-
-    async fn add_scrape_targets(
-        &self,
-        sender: &KubePrometheus,
-        inventory: &Inventory,
-        scrape_targets: Option<Vec<Box<dyn ScrapeTarget<KubePrometheus>>>>,
-    ) -> Result<PreparationOutcome, PreparationError> {
-        let scrape_targets = match scrape_targets {
-            Some(r) if !r.is_empty() => r,
-            _ => return Ok(PreparationOutcome::Noop),
-        };
-
-        for scrape_target in scrape_targets {
-            let score = KubePrometheusScrapeTargetScore {
-                scrape_target,
-                sender: sender.clone(),
-            };
-
-            score
-                .create_interpret()
-                .execute(inventory, self)
-                .await
-                .map_err(|e| PreparationError::new(format!("Failed to install rule: {}", e)))?;
-        }
-
-        Ok(PreparationOutcome::Success {
-            details: "All scrap targets installed successfully".to_string(),
-        })
-    }
-
-    async fn ensure_monitoring_installed(
-        &self,
-        sender: &KubePrometheus,
-        inventory: &Inventory,
-    ) -> Result<PreparationOutcome, PreparationError> {
-        let score = KubePrometheusEnsureReadyScore {
-            sender: sender.clone(),
-        };
-
-        score
-            .create_interpret()
-            .execute(inventory, self)
-            .await
-            .map_err(|e| PreparationError::new(format!("KubePrometheus not ready {}", e)))?;
-        Ok(PreparationOutcome::Success {
-            details: "KubePrometheus Ready".to_string(),
-        })
-    }
-}

harmony/src/domain/topology/k8s_anywhere/observability/mod.rs

@@ -1,5 +0,0 @@
-pub mod grafana;
-pub mod kube_prometheus;
-pub mod openshift_monitoring;
-pub mod prometheus;
-pub mod redhat_cluster_observability;

harmony/src/domain/topology/k8s_anywhere/observability/openshift_monitoring.rs

@@ -1,142 +0,0 @@
-use async_trait::async_trait;
-use log::info;
-
-use crate::score::Score;
-use crate::{
-    inventory::Inventory,
-    modules::monitoring::okd::{
-        OpenshiftClusterAlertSender,
-        score_enable_cluster_monitoring::OpenshiftEnableClusterMonitoringScore,
-        score_openshift_alert_rule::OpenshiftAlertRuleScore,
-        score_openshift_receiver::OpenshiftReceiverScore,
-        score_openshift_scrape_target::OpenshiftScrapeTargetScore,
-        score_user_workload::OpenshiftUserWorkloadMonitoring,
-        score_verify_user_workload_monitoring::VerifyUserWorkload,
-    },
-    topology::{
-        K8sAnywhereTopology, PreparationError, PreparationOutcome,
-        monitoring::{AlertReceiver, AlertRule, Observability, ScrapeTarget},
-    },
-};
-
-#[async_trait]
-impl Observability<OpenshiftClusterAlertSender> for K8sAnywhereTopology {
-    async fn install_alert_sender(
-        &self,
-        _sender: &OpenshiftClusterAlertSender,
-        inventory: &Inventory,
-    ) -> Result<PreparationOutcome, PreparationError> {
-        info!("enabling cluster monitoring");
-        let cluster_monitoring_score = OpenshiftEnableClusterMonitoringScore {};
-        cluster_monitoring_score
-            .create_interpret()
-            .execute(inventory, self)
-            .await
-            .map_err(|e| PreparationError { msg: e.to_string() })?;
-
-        info!("enabling user workload monitoring");
-        let user_workload_score = OpenshiftUserWorkloadMonitoring {};
-        user_workload_score
-            .create_interpret()
-            .execute(inventory, self)
-            .await
-            .map_err(|e| PreparationError { msg: e.to_string() })?;
-
-        Ok(PreparationOutcome::Success {
-            details: "Successfully configured cluster monitoring".to_string(),
-        })
-    }
-
-    async fn install_receivers(
-        &self,
-        _sender: &OpenshiftClusterAlertSender,
-        inventory: &Inventory,
-        receivers: Option<Vec<Box<dyn AlertReceiver<OpenshiftClusterAlertSender>>>>,
-    ) -> Result<PreparationOutcome, PreparationError> {
-        if let Some(receivers) = receivers {
-            for receiver in receivers {
-                info!("Installing receiver {}", receiver.name());
-                let receiver_score = OpenshiftReceiverScore { receiver };
-                receiver_score
-                    .create_interpret()
-                    .execute(inventory, self)
-                    .await
-                    .map_err(|e| PreparationError { msg: e.to_string() })?;
-            }
-            Ok(PreparationOutcome::Success {
-                details: "Successfully installed receivers for OpenshiftClusterMonitoring"
-                    .to_string(),
-            })
-        } else {
-            Ok(PreparationOutcome::Noop)
-        }
-    }
-
-    async fn install_rules(
-        &self,
-        _sender: &OpenshiftClusterAlertSender,
-        inventory: &Inventory,
-        rules: Option<Vec<Box<dyn AlertRule<OpenshiftClusterAlertSender>>>>,
-    ) -> Result<PreparationOutcome, PreparationError> {
-        if let Some(rules) = rules {
-            for rule in rules {
-                info!("Installing rule ");
-                let rule_score = OpenshiftAlertRuleScore { rule: rule };
-                rule_score
-                    .create_interpret()
-                    .execute(inventory, self)
-                    .await
-                    .map_err(|e| PreparationError { msg: e.to_string() })?;
-            }
-            Ok(PreparationOutcome::Success {
-                details: "Successfully installed rules for OpenshiftClusterMonitoring".to_string(),
-            })
-        } else {
-            Ok(PreparationOutcome::Noop)
-        }
-    }
-
-    async fn add_scrape_targets(
-        &self,
-        _sender: &OpenshiftClusterAlertSender,
-        inventory: &Inventory,
-        scrape_targets: Option<Vec<Box<dyn ScrapeTarget<OpenshiftClusterAlertSender>>>>,
-    ) -> Result<PreparationOutcome, PreparationError> {
-        if let Some(scrape_targets) = scrape_targets {
-            for scrape_target in scrape_targets {
-                info!("Installing scrape target");
-                let scrape_target_score = OpenshiftScrapeTargetScore {
-                    scrape_target: scrape_target,
-                };
-                scrape_target_score
-                    .create_interpret()
-                    .execute(inventory, self)
-                    .await
-                    .map_err(|e| PreparationError { msg: e.to_string() })?;
-            }
-            Ok(PreparationOutcome::Success {
-                details: "Successfully added scrape targets for OpenshiftClusterMonitoring"
-                    .to_string(),
-            })
-        } else {
-            Ok(PreparationOutcome::Noop)
-        }
-    }
-
-    async fn ensure_monitoring_installed(
-        &self,
-        _sender: &OpenshiftClusterAlertSender,
-        inventory: &Inventory,
-    ) -> Result<PreparationOutcome, PreparationError> {
-        let verify_monitoring_score = VerifyUserWorkload {};
-        info!("Verifying user workload and cluster monitoring installed");
-        verify_monitoring_score
-            .create_interpret()
-            .execute(inventory, self)
-            .await
-            .map_err(|e| PreparationError { msg: e.to_string() })?;
-        Ok(PreparationOutcome::Success {
-            details: "OpenshiftClusterMonitoring ready".to_string(),
-        })
-    }
-}

harmony/src/domain/topology/k8s_anywhere/observability/prometheus.rs

@@ -1,147 +0,0 @@
-use async_trait::async_trait;
-
-use crate::{
-    inventory::Inventory,
-    modules::monitoring::prometheus::{
-        Prometheus, score_prometheus_alert_receivers::PrometheusReceiverScore,
-        score_prometheus_ensure_ready::PrometheusEnsureReadyScore,
-        score_prometheus_install::PrometheusInstallScore,
-        score_prometheus_rule::PrometheusRuleScore,
-        score_prometheus_scrape_target::PrometheusScrapeTargetScore,
-    },
-    score::Score,
-    topology::{
-        K8sAnywhereTopology, PreparationError, PreparationOutcome,
-        monitoring::{AlertReceiver, AlertRule, Observability, ScrapeTarget},
-    },
-};
-
-#[async_trait]
-impl Observability<Prometheus> for K8sAnywhereTopology {
-    async fn install_alert_sender(
-        &self,
-        sender: &Prometheus,
-        inventory: &Inventory,
-    ) -> Result<PreparationOutcome, PreparationError> {
-        let score = PrometheusInstallScore {
-            sender: sender.clone(),
-        };
-
-        score
-            .create_interpret()
-            .execute(inventory, self)
-            .await
-            .map_err(|e| PreparationError::new(format!("Prometheus not installed {}", e)))?;
-
-        Ok(PreparationOutcome::Success {
-            details: "Successfully installed kubeprometheus alert sender".to_string(),
-        })
-    }
-
-    async fn install_receivers(
-        &self,
-        sender: &Prometheus,
-        inventory: &Inventory,
-        receivers: Option<Vec<Box<dyn AlertReceiver<Prometheus>>>>,
-    ) -> Result<PreparationOutcome, PreparationError> {
-        let receivers = match receivers {
-            Some(r) if !r.is_empty() => r,
-            _ => return Ok(PreparationOutcome::Noop),
-        };
-
-        for receiver in receivers {
-            let score = PrometheusReceiverScore {
-                receiver,
-                sender: sender.clone(),
-            };
-
-            score
-                .create_interpret()
-                .execute(inventory, self)
-                .await
-                .map_err(|e| PreparationError::new(format!("Failed to install receiver: {}", e)))?;
-        }
-
-        Ok(PreparationOutcome::Success {
-            details: "All alert receivers installed successfully".to_string(),
-        })
-    }
-
-    async fn install_rules(
-        &self,
-        sender: &Prometheus,
-        inventory: &Inventory,
-        rules: Option<Vec<Box<dyn AlertRule<Prometheus>>>>,
-    ) -> Result<PreparationOutcome, PreparationError> {
-        let rules = match rules {
-            Some(r) if !r.is_empty() => r,
-            _ => return Ok(PreparationOutcome::Noop),
-        };
-
-        for rule in rules {
-            let score = PrometheusRuleScore {
-                sender: sender.clone(),
-                rule,
-            };
-
-            score
-                .create_interpret()
-                .execute(inventory, self)
-                .await
-                .map_err(|e| PreparationError::new(format!("Failed to install rule: {}", e)))?;
-        }
-
-        Ok(PreparationOutcome::Success {
-            details: "All alert rules installed successfully".to_string(),
-        })
-    }
-
-    async fn add_scrape_targets(
-        &self,
-        sender: &Prometheus,
-        inventory: &Inventory,
-        scrape_targets: Option<Vec<Box<dyn ScrapeTarget<Prometheus>>>>,
-    ) -> Result<PreparationOutcome, PreparationError> {
-        let scrape_targets = match scrape_targets {
-            Some(r) if !r.is_empty() => r,
-            _ => return Ok(PreparationOutcome::Noop),
-        };
-
-        for scrape_target in scrape_targets {
-            let score = PrometheusScrapeTargetScore {
-                scrape_target,
-                sender: sender.clone(),
-            };
-
-            score
-                .create_interpret()
-                .execute(inventory, self)
-                .await
-                .map_err(|e| PreparationError::new(format!("Failed to install rule: {}", e)))?;
-        }
-
-        Ok(PreparationOutcome::Success {
-            details: "All scrap targets installed successfully".to_string(),
-        })
-    }
-
-    async fn ensure_monitoring_installed(
-        &self,
-        sender: &Prometheus,
-        inventory: &Inventory,
-    ) -> Result<PreparationOutcome, PreparationError> {
-        let score = PrometheusEnsureReadyScore {
-            sender: sender.clone(),
-        };
-
-        score
-            .create_interpret()
-            .execute(inventory, self)
-            .await
-            .map_err(|e| PreparationError::new(format!("Prometheus not ready {}", e)))?;
-
-        Ok(PreparationOutcome::Success {
-            details: "Prometheus Ready".to_string(),
-        })
-    }
-}

harmony/src/domain/topology/k8s_anywhere/observability/redhat_cluster_observability.rs

@@ -1,116 +0,0 @@
-use crate::{
-    modules::monitoring::red_hat_cluster_observability::{
-        score_alert_receiver::RedHatClusterObservabilityReceiverScore,
-        score_coo_monitoring_stack::RedHatClusterObservabilityMonitoringStackScore,
-    },
-    score::Score,
-};
-use async_trait::async_trait;
-use log::info;
-
-use crate::{
-    inventory::Inventory,
-    modules::monitoring::red_hat_cluster_observability::{
-        RedHatClusterObservability,
-        score_redhat_cluster_observability_operator::RedHatClusterObservabilityOperatorScore,
-    },
-    topology::{
-        K8sAnywhereTopology, PreparationError, PreparationOutcome,
-        monitoring::{AlertReceiver, AlertRule, Observability, ScrapeTarget},
-    },
-};
-
-#[async_trait]
-impl Observability<RedHatClusterObservability> for K8sAnywhereTopology {
-    async fn install_alert_sender(
-        &self,
-        sender: &RedHatClusterObservability,
-        inventory: &Inventory,
-    ) -> Result<PreparationOutcome, PreparationError> {
-        info!("Verifying Redhat Cluster Observability Operator");
-
-        let coo_score = RedHatClusterObservabilityOperatorScore::default();
-
-        coo_score
-            .create_interpret()
-            .execute(inventory, self)
-            .await
-            .map_err(|e| PreparationError::new(e.to_string()))?;
-
-        info!(
-            "Installing Cluster Observability Operator Monitoring Stack in ns {}",
-            sender.namespace.clone()
-        );
-
-        let coo_monitoring_stack_score = RedHatClusterObservabilityMonitoringStackScore {
-            namespace: sender.namespace.clone(),
-            resource_selector: sender.resource_selector.clone(),
-        };
-
-        coo_monitoring_stack_score
-            .create_interpret()
-            .execute(inventory, self)
-            .await
-            .map_err(|e| PreparationError::new(e.to_string()))?;
-
-        Ok(PreparationOutcome::Success {
-            details: "Successfully installed RedHatClusterObservability Operator".to_string(),
-        })
-    }
-
-    async fn install_receivers(
-        &self,
-        sender: &RedHatClusterObservability,
-        inventory: &Inventory,
-        receivers: Option<Vec<Box<dyn AlertReceiver<RedHatClusterObservability>>>>,
-    ) -> Result<PreparationOutcome, PreparationError> {
-        let receivers = match receivers {
-            Some(r) if !r.is_empty() => r,
-            _ => return Ok(PreparationOutcome::Noop),
-        };
-
-        for receiver in receivers {
-            info!("Installing receiver {}", receiver.name());
-
-            let receiver_score = RedHatClusterObservabilityReceiverScore {
-                receiver,
-                sender: sender.clone(),
-            };
-            receiver_score
-                .create_interpret()
-                .execute(inventory, self)
-                .await
-                .map_err(|e| PreparationError::new(e.to_string()))?;
-        }
-
-        Ok(PreparationOutcome::Success {
-            details: "Successfully installed receivers for OpenshiftClusterMonitoring".to_string(),
-        })
-    }
-
-    async fn install_rules(
-        &self,
-        _sender: &RedHatClusterObservability,
-        _inventory: &Inventory,
-        _rules: Option<Vec<Box<dyn AlertRule<RedHatClusterObservability>>>>,
-    ) -> Result<PreparationOutcome, PreparationError> {
-        todo!()
-    }
-
-    async fn add_scrape_targets(
-        &self,
-        _sender: &RedHatClusterObservability,
-        _inventory: &Inventory,
-        _scrape_targets: Option<Vec<Box<dyn ScrapeTarget<RedHatClusterObservability>>>>,
-    ) -> Result<PreparationOutcome, PreparationError> {
-        todo!()
-    }
-
-    async fn ensure_monitoring_installed(
-        &self,
-        _sender: &RedHatClusterObservability,
-        _inventory: &Inventory,
-    ) -> Result<PreparationOutcome, PreparationError> {
-        todo!()
-    }
-}

harmony/src/domain/topology/load_balancer.rs

@@ -106,6 +106,7 @@ pub enum SSL {
 
 #[derive(Debug, Clone, PartialEq, Serialize)]
 pub enum HealthCheck {
-    HTTP(String, HttpMethod, HttpStatusCode, SSL),
+    /// HTTP(None, "/healthz/ready", HttpMethod::GET, HttpStatusCode::Success2xx, SSL::Disabled)
+    HTTP(Option<u16>, String, HttpMethod, HttpStatusCode, SSL),
     TCP(Option<u16>),
 }

harmony/src/domain/topology/mod.rs

@@ -2,7 +2,6 @@ pub mod decentralized;
 mod failover;
 mod ha_cluster;
 pub mod ingress;
-pub mod monitoring;
 pub mod node_exporter;
 pub mod opnsense;
 pub use failover::*;
@@ -12,6 +11,7 @@ mod http;
 pub mod installable;
 mod k8s_anywhere;
 mod localhost;
+pub mod oberservability;
 pub mod tenant;
 use derive_new::new;
 pub use k8s_anywhere::*;

harmony/src/domain/topology/monitoring.rs

@@ -1,256 +0,0 @@
-use std::{
-    any::Any,
-    collections::{BTreeMap, HashMap},
-    net::IpAddr,
-};
-
-use async_trait::async_trait;
-use kube::api::DynamicObject;
-use log::{debug, info};
-use serde::{Deserialize, Serialize};
-
-use crate::{
-    data::Version,
-    interpret::{Interpret, InterpretError, InterpretName, InterpretStatus, Outcome},
-    inventory::Inventory,
-    topology::{PreparationError, PreparationOutcome, Topology, installable::Installable},
-};
-use harmony_types::id::Id;
-
-/// Defines the application that sends the alerts to a receivers
-/// for example prometheus
-#[async_trait]
-pub trait AlertSender: Send + Sync + std::fmt::Debug {
-    fn name(&self) -> String;
-}
-
-/// Trait which defines how an alert sender is impleneted for a specific topology
-#[async_trait]
-pub trait Observability<S: AlertSender> {
-    async fn install_alert_sender(
-        &self,
-        sender: &S,
-        inventory: &Inventory,
-    ) -> Result<PreparationOutcome, PreparationError>;
-
-    async fn install_receivers(
-        &self,
-        sender: &S,
-        inventory: &Inventory,
-        receivers: Option<Vec<Box<dyn AlertReceiver<S>>>>,
-    ) -> Result<PreparationOutcome, PreparationError>;
-
-    async fn install_rules(
-        &self,
-        sender: &S,
-        inventory: &Inventory,
-        rules: Option<Vec<Box<dyn AlertRule<S>>>>,
-    ) -> Result<PreparationOutcome, PreparationError>;
-
-    async fn add_scrape_targets(
-        &self,
-        sender: &S,
-        inventory: &Inventory,
-        scrape_targets: Option<Vec<Box<dyn ScrapeTarget<S>>>>,
-    ) -> Result<PreparationOutcome, PreparationError>;
-
-    async fn ensure_monitoring_installed(
-        &self,
-        sender: &S,
-        inventory: &Inventory,
-    ) -> Result<PreparationOutcome, PreparationError>;
-}
-
-/// Defines the entity that receives the alerts from a sender. For example Discord, Slack, etc
-///
-pub trait AlertReceiver<S: AlertSender>: std::fmt::Debug + Send + Sync {
-    fn build(&self) -> Result<ReceiverInstallPlan, InterpretError>;
-    fn name(&self) -> String;
-    fn clone_box(&self) -> Box<dyn AlertReceiver<S>>;
-}
-
-/// Defines a generic rule that can be applied to a sender, such as aprometheus alert rule
-pub trait AlertRule<S: AlertSender>: std::fmt::Debug + Send + Sync {
-    fn build_rule(&self) -> Result<serde_json::Value, InterpretError>;
-    fn name(&self) -> String;
-    fn clone_box(&self) -> Box<dyn AlertRule<S>>;
-}
-
-/// A generic scrape target that can be added to a sender to scrape metrics from, for example a
-/// server outside of the cluster
-pub trait ScrapeTarget<S: AlertSender>: std::fmt::Debug + Send + Sync {
-    fn build_scrape_target(&self) -> Result<ExternalScrapeTarget, InterpretError>;
-    fn name(&self) -> String;
-    fn clone_box(&self) -> Box<dyn ScrapeTarget<S>>;
-}
-
-#[derive(Debug, Clone, Serialize, Deserialize)]
-pub struct ExternalScrapeTarget {
-    pub ip: IpAddr,
-    pub port: i32,
-    pub interval: Option<String>,
-    pub path: Option<String>,
-    pub labels: Option<BTreeMap<String, String>>,
-}
-
-/// Alerting interpret to install an alert sender on a given topology
-#[derive(Debug)]
-pub struct AlertingInterpret<S: AlertSender> {
-    pub sender: S,
-    pub receivers: Vec<Box<dyn AlertReceiver<S>>>,
-    pub rules: Vec<Box<dyn AlertRule<S>>>,
-    pub scrape_targets: Option<Vec<Box<dyn ScrapeTarget<S>>>>,
-}
-
-#[async_trait]
-impl<S: AlertSender, T: Topology + Observability<S>> Interpret<T> for AlertingInterpret<S> {
-    async fn execute(
-        &self,
-        inventory: &Inventory,
-        topology: &T,
-    ) -> Result<Outcome, InterpretError> {
-        info!("Configuring alert sender {}", self.sender.name());
-        topology
-            .install_alert_sender(&self.sender, inventory)
-            .await?;
-
-        info!("Installing receivers");
-        topology
-            .install_receivers(&self.sender, inventory, Some(self.receivers.clone()))
-            .await?;
-
-        info!("Installing rules");
-        topology
-            .install_rules(&self.sender, inventory, Some(self.rules.clone()))
-            .await?;
-
-        info!("Adding extra scrape targets");
-        topology
-            .add_scrape_targets(&self.sender, inventory, self.scrape_targets.clone())
-            .await?;
-
-        info!("Ensuring alert sender {} is ready", self.sender.name());
-        topology
-            .ensure_monitoring_installed(&self.sender, inventory)
-            .await?;
-
-        Ok(Outcome::success(format!(
-            "successfully installed alert sender {}",
-            self.sender.name()
-        )))
-    }
-
-    fn get_name(&self) -> InterpretName {
-        InterpretName::Alerting
-    }
-
-    fn get_version(&self) -> Version {
-        todo!()
-    }
-
-    fn get_status(&self) -> InterpretStatus {
-        todo!()
-    }
-
-    fn get_children(&self) -> Vec<Id> {
-        todo!()
-    }
-}
-
-impl<S: AlertSender> Clone for Box<dyn AlertReceiver<S>> {
-    fn clone(&self) -> Self {
-        self.clone_box()
-    }
-}
-
-impl<S: AlertSender> Clone for Box<dyn AlertRule<S>> {
-    fn clone(&self) -> Self {
-        self.clone_box()
-    }
-}
-
-impl<S: AlertSender> Clone for Box<dyn ScrapeTarget<S>> {
-    fn clone(&self) -> Self {
-        self.clone_box()
-    }
-}
-
-pub struct ReceiverInstallPlan {
-    pub install_operation: Option<Vec<InstallOperation>>,
-    pub route: Option<AlertRoute>,
-    pub receiver: Option<serde_yaml::Value>,
-}
-
-impl Default for ReceiverInstallPlan {
-    fn default() -> Self {
-        Self {
-            install_operation: None,
-            route: None,
-            receiver: None,
-        }
-    }
-}
-
-pub enum InstallOperation {
-    CreateSecret {
-        name: String,
-        data: BTreeMap<String, String>,
-    },
-}
-
-///Generic routing that can map to various alert sender backends
-#[derive(Debug, Clone, Serialize)]
-pub struct AlertRoute {
-    pub receiver: String,
-    #[serde(skip_serializing_if = "Vec::is_empty")]
-    pub matchers: Vec<AlertMatcher>,
-    #[serde(skip_serializing_if = "Vec::is_empty")]
-    pub group_by: Vec<String>,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub repeat_interval: Option<String>,
-    #[serde(rename = "continue")]
-    pub continue_matching: bool,
-    #[serde(skip_serializing_if = "Vec::is_empty")]
-    pub children: Vec<AlertRoute>,
-}
-
-impl AlertRoute {
-    pub fn default(name: String) -> Self {
-        Self {
-            receiver: name,
-            matchers: vec![],
-            group_by: vec![],
-            repeat_interval: Some("30s".to_string()),
-            continue_matching: true,
-            children: vec![],
-        }
-    }
-}
-
-#[derive(Debug, Clone, Serialize)]
-pub struct AlertMatcher {
-    pub label: String,
-    pub operator: MatchOp,
-    pub value: String,
-}
-
-#[derive(Debug, Clone)]
-pub enum MatchOp {
-    Eq,
-    NotEq,
-    Regex,
-}
-
-impl Serialize for MatchOp {
-    fn serialize<S>(&self, serializer: S) -> Result<S::Ok, S::Error>
-    where
-        S: serde::Serializer,
-    {
-        let op = match self {
-            MatchOp::Eq => "=",
-            MatchOp::NotEq => "!=",
-            MatchOp::Regex => "=~",
-        };
-        serializer.serialize_str(op)
-    }
-}

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

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

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

@@ -0,0 +1,101 @@
+use std::{any::Any, collections::HashMap};
+
+use async_trait::async_trait;
+use kube::api::DynamicObject;
+use log::debug;
+
+use crate::{
+    data::Version,
+    interpret::{Interpret, InterpretError, InterpretName, InterpretStatus, Outcome},
+    inventory::Inventory,
+    topology::{Topology, installable::Installable},
+};
+use harmony_types::id::Id;
+
+#[async_trait]
+pub trait AlertSender: Send + Sync + std::fmt::Debug {
+    fn name(&self) -> String;
+}
+
+#[derive(Debug)]
+pub struct AlertingInterpret<S: AlertSender> {
+    pub sender: S,
+    pub receivers: Vec<Box<dyn AlertReceiver<S>>>,
+    pub rules: Vec<Box<dyn AlertRule<S>>>,
+    pub scrape_targets: Option<Vec<Box<dyn ScrapeTarget<S>>>>,
+}
+
+#[async_trait]
+impl<S: AlertSender + Installable<T>, T: Topology> Interpret<T> for AlertingInterpret<S> {
+    async fn execute(
+        &self,
+        inventory: &Inventory,
+        topology: &T,
+    ) -> Result<Outcome, InterpretError> {
+        debug!("hit sender configure for AlertingInterpret");
+        self.sender.configure(inventory, topology).await?;
+        for receiver in self.receivers.iter() {
+            receiver.install(&self.sender).await?;
+        }
+        for rule in self.rules.iter() {
+            debug!("installing rule: {:#?}", rule);
+            rule.install(&self.sender).await?;
+        }
+        if let Some(targets) = &self.scrape_targets {
+            for target in targets.iter() {
+                debug!("installing scrape_target: {:#?}", target);
+                target.install(&self.sender).await?;
+            }
+        }
+        self.sender.ensure_installed(inventory, topology).await?;
+        Ok(Outcome::success(format!(
+            "successfully installed alert sender {}",
+            self.sender.name()
+        )))
+    }
+
+    fn get_name(&self) -> InterpretName {
+        InterpretName::Alerting
+    }
+
+    fn get_version(&self) -> Version {
+        todo!()
+    }
+
+    fn get_status(&self) -> InterpretStatus {
+        todo!()
+    }
+
+    fn get_children(&self) -> Vec<Id> {
+        todo!()
+    }
+}
+
+#[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;
+    fn as_alertmanager_receiver(&self) -> Result<AlertManagerReceiver, String>;
+}
+
+#[derive(Debug)]
+pub struct AlertManagerReceiver {
+    pub receiver_config: serde_json::Value,
+    // FIXME we should not leak k8s here. DynamicObject is k8s specific
+    pub additional_ressources: Vec<DynamicObject>,
+    pub route_config: serde_json::Value,
+}
+
+#[async_trait]
+pub trait AlertRule<S: AlertSender>: std::fmt::Debug + Send + Sync {
+    async fn install(&self, sender: &S) -> Result<Outcome, InterpretError>;
+    fn clone_box(&self) -> Box<dyn AlertRule<S>>;
+}
+
+#[async_trait]
+pub trait ScrapeTarget<S: AlertSender>: std::fmt::Debug + Send + Sync {
+    async fn install(&self, sender: &S) -> Result<Outcome, InterpretError>;
+    fn clone_box(&self) -> Box<dyn ScrapeTarget<S>>;
+}

harmony/src/domain/topology/router.rs

@@ -122,4 +122,6 @@ pub trait TlsRouter: Send + Sync {
 
     /// Returns the port that this router exposes externally.
     async fn get_router_port(&self) -> u16;
+
+    async fn get_public_domain(&self) -> Result<String, String>;
 }

harmony/src/infra/opnsense/load_balancer.rs

@@ -216,7 +216,15 @@ pub(crate) fn get_health_check_for_backend(
                     SSL::Other(other.to_string())
                 }
             };
-            Some(HealthCheck::HTTP(path, method, status_code, ssl))
+
+            let port = haproxy_health_check
+                .checkport
+                .content_string()
+                .parse::<u16>()
+                .ok();
+            debug!("Found haproxy healthcheck port {port:?}");
+
+            Some(HealthCheck::HTTP(port, path, method, status_code, ssl))
         }
         _ => panic!("Received unsupported health check type {}", uppercase),
     }
@@ -251,7 +259,7 @@ pub(crate) fn harmony_load_balancer_service_to_haproxy_xml(
     // frontend points to backend
     let healthcheck = if let Some(health_check) = &service.health_check {
         match health_check {
-            HealthCheck::HTTP(path, http_method, _http_status_code, ssl) => {
+            HealthCheck::HTTP(port, path, http_method, _http_status_code, ssl) => {
                 let ssl: MaybeString = match ssl {
                     SSL::SSL => "ssl".into(),
                     SSL::SNI => "sslni".into(),
@@ -259,14 +267,21 @@ pub(crate) fn harmony_load_balancer_service_to_haproxy_xml(
                     SSL::Default => "".into(),
                     SSL::Other(other) => other.as_str().into(),
                 };
+                let path_without_query = path.split_once('?').map_or(path.as_str(), |(p, _)| p);
+                let (port, port_name) = match port {
+                    Some(port) => (Some(port.to_string()), port.to_string()),
+                    None => (None, "serverport".to_string()),
+                };
+
                 let haproxy_check = HAProxyHealthCheck {
-                    name: format!("HTTP_{http_method}_{path}"),
+                    name: format!("HTTP_{http_method}_{path_without_query}_{port_name}"),
                     uuid: Uuid::new_v4().to_string(),
-                    http_method: http_method.to_string().into(),
+                    http_method: http_method.to_string().to_lowercase().into(),
                     health_check_type: "http".to_string(),
                     http_uri: path.clone().into(),
                     interval: "2s".to_string(),
                     ssl,
+                    checkport: MaybeString::from(port.map(|p| p.to_string())),
                     ..Default::default()
                 };
 
@@ -305,7 +320,10 @@ pub(crate) fn harmony_load_balancer_service_to_haproxy_xml(
     let mut backend = HAProxyBackend {
         uuid: Uuid::new_v4().to_string(),
         enabled: 1,
-        name: format!("backend_{}", service.listening_port),
+        name: format!(
+            "backend_{}",
+            service.listening_port.to_string().replace(':', "_")
+        ),
         algorithm: "roundrobin".to_string(),
         random_draws: Some(2),
         stickiness_expire: "30m".to_string(),
@@ -337,10 +355,22 @@ pub(crate) fn harmony_load_balancer_service_to_haproxy_xml(
     let frontend = Frontend {
         uuid: uuid::Uuid::new_v4().to_string(),
         enabled: 1,
-        name: format!("frontend_{}", service.listening_port),
+        name: format!(
+            "frontend_{}",
+            service.listening_port.to_string().replace(':', "_")
+        ),
         bind: service.listening_port.to_string(),
         mode: "tcp".to_string(), // TODO do not depend on health check here
         default_backend: Some(backend.uuid.clone()),
+        stickiness_expire: "30m".to_string().into(),
+        stickiness_size: "50k".to_string().into(),
+        stickiness_conn_rate_period: "10s".to_string().into(),
+        stickiness_sess_rate_period: "10s".to_string().into(),
+        stickiness_http_req_rate_period: "10s".to_string().into(),
+        stickiness_http_err_rate_period: "10s".to_string().into(),
+        stickiness_bytes_in_rate_period: "1m".to_string().into(),
+        stickiness_bytes_out_rate_period: "1m".to_string().into(),
+        ssl_hsts_max_age: 15768000,
         ..Default::default()
     };
     info!("HAPRoxy frontend and backend mode currently hardcoded to tcp");

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

@@ -2,15 +2,13 @@ use crate::modules::application::{
     Application, ApplicationFeature, InstallationError, InstallationOutcome,
 };
 use crate::modules::monitoring::application_monitoring::application_monitoring_score::ApplicationMonitoringScore;
+use crate::modules::monitoring::grafana::grafana::Grafana;
+use crate::modules::monitoring::kube_prometheus::crd::crd_alertmanager_config::CRDPrometheus;
 use crate::modules::monitoring::kube_prometheus::crd::service_monitor::{
     ServiceMonitor, ServiceMonitorSpec,
 };
-use crate::modules::monitoring::prometheus::Prometheus;
-use crate::modules::monitoring::prometheus::helm::prometheus_config::PrometheusConfig;
 use crate::topology::MultiTargetTopology;
 use crate::topology::ingress::Ingress;
-use crate::topology::monitoring::Observability;
-use crate::topology::monitoring::{AlertReceiver, AlertRoute};
 use crate::{
     inventory::Inventory,
     modules::monitoring::{
@@ -19,6 +17,10 @@ use crate::{
     score::Score,
     topology::{HelmCommand, K8sclient, Topology, tenant::TenantManager},
 };
+use crate::{
+    modules::prometheus::prometheus::PrometheusMonitoring,
+    topology::oberservability::monitoring::AlertReceiver,
+};
 use async_trait::async_trait;
 use base64::{Engine as _, engine::general_purpose};
 use harmony_secret::SecretManager;
@@ -28,13 +30,12 @@ use kube::api::ObjectMeta;
 use log::{debug, info};
 use schemars::JsonSchema;
 use serde::{Deserialize, Serialize};
-use std::sync::{Arc, Mutex};
+use std::sync::Arc;
 
-//TODO test this
 #[derive(Debug, Clone)]
 pub struct Monitoring {
     pub application: Arc<dyn Application>,
-    pub alert_receiver: Vec<Box<dyn AlertReceiver<Prometheus>>>,
+    pub alert_receiver: Vec<Box<dyn AlertReceiver<CRDPrometheus>>>,
 }
 
 #[async_trait]
@@ -45,7 +46,8 @@ impl<
         + TenantManager
         + K8sclient
         + MultiTargetTopology
-        + Observability<Prometheus>
+        + PrometheusMonitoring<CRDPrometheus>
+        + Grafana
         + Ingress
         + std::fmt::Debug,
 > ApplicationFeature<T> for Monitoring
@@ -72,15 +74,17 @@ impl<
         };
 
         let mut alerting_score = ApplicationMonitoringScore {
-            sender: Prometheus {
+            sender: CRDPrometheus {
-                config: Arc::new(Mutex::new(PrometheusConfig::new())),
+                namespace: namespace.clone(),
+                client: topology.k8s_client().await.unwrap(),
+                service_monitor: vec![app_service_monitor],
             },
             application: self.application.clone(),
             receivers: self.alert_receiver.clone(),
         };
         let ntfy = NtfyScore {
             namespace: namespace.clone(),
-            host: domain.clone(),
+            host: domain,
         };
         ntfy.interpret(&Inventory::empty(), topology)
             .await
@@ -101,28 +105,20 @@ impl<
 
         debug!("ntfy_default_auth_param: {ntfy_default_auth_param}");
 
-        debug!("ntfy_default_auth_param: {ntfy_default_auth_param}");
         let ntfy_receiver = WebhookReceiver {
             name: "ntfy-webhook".to_string(),
             url: Url::Url(
                 url::Url::parse(
                     format!(
-                        "http://{domain}/{}?auth={ntfy_default_auth_param}",
+                        "http://ntfy.{}.svc.cluster.local/rust-web-app?auth={ntfy_default_auth_param}",
-                        __self.application.name()
+                        namespace.clone()
                     )
                     .as_str(),
                 )
                 .unwrap(),
             ),
-            route: AlertRoute {
-                ..AlertRoute::default("ntfy-webhook".to_string())
-            },
         };
-        debug!(
+
-            "ntfy webhook receiver \n{:#?}\nntfy topic: {}",
-            ntfy_receiver.clone(),
-            self.application.name()
-        );
         alerting_score.receivers.push(Box::new(ntfy_receiver));
         alerting_score
             .interpret(&Inventory::empty(), topology)

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

@@ -3,13 +3,11 @@ use std::sync::Arc;
 use crate::modules::application::{
     Application, ApplicationFeature, InstallationError, InstallationOutcome,
 };
+use crate::modules::monitoring::application_monitoring::rhobs_application_monitoring_score::ApplicationRHOBMonitoringScore;
 
-use crate::modules::monitoring::red_hat_cluster_observability::RedHatClusterObservability;
+use crate::modules::monitoring::kube_prometheus::crd::rhob_alertmanager_config::RHOBObservability;
-use crate::modules::monitoring::red_hat_cluster_observability::redhat_cluster_observability::RedHatClusterObservabilityScore;
 use crate::topology::MultiTargetTopology;
 use crate::topology::ingress::Ingress;
-use crate::topology::monitoring::Observability;
-use crate::topology::monitoring::{AlertReceiver, AlertRoute};
 use crate::{
     inventory::Inventory,
     modules::monitoring::{
@@ -18,6 +16,10 @@ use crate::{
     score::Score,
     topology::{HelmCommand, K8sclient, Topology, tenant::TenantManager},
 };
+use crate::{
+    modules::prometheus::prometheus::PrometheusMonitoring,
+    topology::oberservability::monitoring::AlertReceiver,
+};
 use async_trait::async_trait;
 use base64::{Engine as _, engine::general_purpose};
 use harmony_types::net::Url;
@@ -26,10 +28,9 @@ use log::{debug, info};
 #[derive(Debug, Clone)]
 pub struct Monitoring {
     pub application: Arc<dyn Application>,
-    pub alert_receiver: Vec<Box<dyn AlertReceiver<RedHatClusterObservability>>>,
+    pub alert_receiver: Vec<Box<dyn AlertReceiver<RHOBObservability>>>,
 }
 
-///TODO TEST this
 #[async_trait]
 impl<
     T: Topology
@@ -40,7 +41,7 @@ impl<
         + MultiTargetTopology
         + Ingress
         + std::fmt::Debug
-        + Observability<RedHatClusterObservability>,
+        + PrometheusMonitoring<RHOBObservability>,
 > ApplicationFeature<T> for Monitoring
 {
     async fn ensure_installed(
@@ -54,14 +55,13 @@ impl<
             .map(|ns| ns.name.clone())
             .unwrap_or_else(|| self.application.name());
 
-        let mut alerting_score = RedHatClusterObservabilityScore {
+        let mut alerting_score = ApplicationRHOBMonitoringScore {
-            sender: RedHatClusterObservability {
+            sender: RHOBObservability {
                 namespace: namespace.clone(),
-                resource_selector: todo!(),
+                client: topology.k8s_client().await.unwrap(),
             },
+            application: self.application.clone(),
             receivers: self.alert_receiver.clone(),
-            rules: vec![],
-            scrape_targets: None,
         };
         let domain = topology
             .get_domain("ntfy")
@@ -97,15 +97,12 @@ impl<
                 url::Url::parse(
                     format!(
                         "http://{domain}/{}?auth={ntfy_default_auth_param}",
-                        __self.application.name()
+                        self.application.name()
                     )
                     .as_str(),
                 )
                 .unwrap(),
             ),
-            route: AlertRoute {
-                ..AlertRoute::default("ntfy-webhook".to_string())
-            },
         };
         debug!(
             "ntfy webhook receiver \n{:#?}\nntfy topic: {}",

harmony/src/modules/application/rust.rs

@@ -1,6 +1,5 @@
 use std::fs::{self};
-use std::path::{Path, PathBuf};
+use std::path::PathBuf;
-use std::process;
 use std::sync::Arc;
 
 use async_trait::async_trait;
@@ -65,6 +64,7 @@ pub struct RustWebapp {
     ///
     /// This is the place to put the public host name if this is a public facing webapp.
     pub dns: String,
+    pub version: String,
 }
 
 impl Application for RustWebapp {
@@ -465,6 +465,7 @@ impl RustWebapp {
 
         let app_name = &self.name;
         let service_port = self.service_port;
+        let version = &self.version;
         // Create Chart.yaml
         let chart_yaml = format!(
             r#"
@@ -472,7 +473,7 @@ apiVersion: v2
 name: {chart_name}
 description: A Helm chart for the {app_name} web application.
 type: application
-version: 0.2.1
+version: {version}
 appVersion: "{image_tag}"
 "#,
         );

harmony/src/modules/k8s/resource.rs

@@ -1,4 +1,5 @@
 use async_trait::async_trait;
+use k8s_openapi::ResourceScope;
 use kube::Resource;
 use log::info;
 use serde::{Serialize, de::DeserializeOwned};
@@ -28,7 +29,7 @@ impl<K: Resource + std::fmt::Debug> K8sResourceScore<K> {
 }
 
 impl<
-    K: Resource
+    K: Resource<Scope: ResourceScope>
         + std::fmt::Debug
         + Sync
         + DeserializeOwned
@@ -60,7 +61,7 @@ pub struct K8sResourceInterpret<K: Resource + std::fmt::Debug + Sync + Send> {
 
 #[async_trait]
 impl<
-    K: Resource
+    K: Resource<Scope: ResourceScope>
         + Clone
         + std::fmt::Debug
         + DeserializeOwned

harmony/src/modules/mod.rs

@@ -20,6 +20,7 @@ pub mod okd;
 pub mod openbao;
 pub mod opnsense;
 pub mod postgresql;
+pub mod prometheus;
 pub mod storage;
 pub mod tenant;
 pub mod tftp;

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

@@ -1,38 +1,99 @@
-use crate::modules::monitoring::kube_prometheus::KubePrometheus;
+use std::any::Any;
-use crate::modules::monitoring::okd::OpenshiftClusterAlertSender;
+use std::collections::{BTreeMap, HashMap};
-use crate::modules::monitoring::red_hat_cluster_observability::RedHatClusterObservability;
+
-use crate::topology::monitoring::{AlertRoute, InstallOperation, ReceiverInstallPlan};
+use async_trait::async_trait;
-use crate::{interpret::InterpretError, topology::monitoring::AlertReceiver};
+use harmony_types::k8s_name::K8sName;
-use harmony_types::net::Url;
+use k8s_openapi::api::core::v1::Secret;
+use kube::Resource;
+use kube::api::{DynamicObject, ObjectMeta};
+use log::{debug, trace};
 use serde::Serialize;
 use serde_json::json;
-use std::collections::BTreeMap;
+use serde_yaml::{Mapping, Value};
+
+use crate::infra::kube::kube_resource_to_dynamic;
+use crate::modules::monitoring::kube_prometheus::crd::crd_alertmanager_config::{
+    AlertmanagerConfig, AlertmanagerConfigSpec, CRDPrometheus,
+};
+use crate::modules::monitoring::kube_prometheus::crd::rhob_alertmanager_config::RHOBObservability;
+use crate::modules::monitoring::okd::OpenshiftClusterAlertSender;
+use crate::topology::oberservability::monitoring::AlertManagerReceiver;
+use crate::{
+    interpret::{InterpretError, Outcome},
+    modules::monitoring::{
+        kube_prometheus::{
+            prometheus::{KubePrometheus, KubePrometheusReceiver},
+            types::{AlertChannelConfig, AlertManagerChannelConfig},
+        },
+        prometheus::prometheus::{Prometheus, PrometheusReceiver},
+    },
+    topology::oberservability::monitoring::AlertReceiver,
+};
+use harmony_types::net::Url;
 
 #[derive(Debug, Clone, Serialize)]
-pub struct DiscordReceiver {
+pub struct DiscordWebhook {
-    pub name: String,
+    pub name: K8sName,
     pub url: Url,
-    pub route: AlertRoute,
+    pub selectors: Vec<HashMap<String, String>>,
 }
 
-impl AlertReceiver<OpenshiftClusterAlertSender> for DiscordReceiver {
+impl DiscordWebhook {
-    fn build(&self) -> Result<ReceiverInstallPlan, InterpretError> {
+    fn get_receiver_config(&self) -> Result<AlertManagerReceiver, String> {
-        let receiver_block = serde_yaml::to_value(json!({
+        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 mut matchers: Vec<String> = Vec::new();
+        for selector in &self.selectors {
+            trace!("selector: {:#?}", selector);
+            for (k, v) in selector {
+                matchers.push(format!("{} = {}", k, v));
+            }
+        }
+
+        Ok(AlertManagerReceiver {
+            additional_ressources: vec![kube_resource_to_dynamic(&secret)?],
+
+            receiver_config: json!({
                 "name": self.name,
-            "discord_configs": [{
+                "discord_configs": [
-                "webhook_url": format!("{}", self.url),
+                    {
+                    "webhook_url": self.url.clone(),
                     "title": "{{ template \"discord.default.title\" . }}",
                     "message": "{{ template \"discord.default.message\" . }}"
-            }]
+                    }
-        }))
+                ]
-        .map_err(|e| InterpretError::new(e.to_string()))?;
+            }),
+            route_config: json!({
+                "receiver": self.name,
+                "matchers": matchers,
 
-        Ok(ReceiverInstallPlan {
+            }),
-            install_operation: None,
-            route: Some(self.route.clone()),
-            receiver: Some(receiver_block),
         })
     }
+}
+
+#[async_trait]
+impl AlertReceiver<OpenshiftClusterAlertSender> for DiscordWebhook {
+    async fn install(
+        &self,
+        sender: &OpenshiftClusterAlertSender,
+    ) -> Result<Outcome, InterpretError> {
+        todo!()
+    }
 
     fn name(&self) -> String {
         self.name.clone().to_string()
@@ -41,77 +102,309 @@ impl AlertReceiver<OpenshiftClusterAlertSender> for DiscordReceiver {
     fn clone_box(&self) -> Box<dyn AlertReceiver<OpenshiftClusterAlertSender>> {
         Box::new(self.clone())
     }
+
+    fn as_any(&self) -> &dyn Any {
+        todo!()
+    }
+
+    fn as_alertmanager_receiver(&self) -> Result<AlertManagerReceiver, String> {
+        self.get_receiver_config()
+    }
 }
 
-impl AlertReceiver<RedHatClusterObservability> for DiscordReceiver {
+#[async_trait]
-    fn build(&self) -> Result<ReceiverInstallPlan, InterpretError> {
+impl AlertReceiver<RHOBObservability> for DiscordWebhook {
+    fn as_alertmanager_receiver(&self) -> Result<AlertManagerReceiver, String> {
+        todo!()
+    }
+
+    async fn install(&self, sender: &RHOBObservability) -> Result<Outcome, InterpretError> {
+        let ns = sender.namespace.clone();
+
+        let config = self.get_receiver_config()?;
+        for resource in config.additional_ressources.iter() {
+            todo!("can I apply a dynamicresource");
+            // sender.client.apply(resource, Some(&ns)).await;
+        }
+
+        let spec = crate::modules::monitoring::kube_prometheus::crd::rhob_alertmanager_config::AlertmanagerConfigSpec {
+            data: json!({
+                "route": {
+                    "receiver": self.name,
+                },
+                "receivers": [
+                    config.receiver_config
+                ]
+            }),
+        };
+
+        let alertmanager_configs = crate::modules::monitoring::kube_prometheus::crd::rhob_alertmanager_config::AlertmanagerConfig {
+            metadata: ObjectMeta {
+                name: Some(self.name.clone().to_string()),
+                labels: Some(std::collections::BTreeMap::from([(
+                    "alertmanagerConfig".to_string(),
+                    "enabled".to_string(),
+                )])),
+                namespace: Some(sender.namespace.clone()),
+                ..Default::default()
+            },
+            spec,
+        };
+        debug!(
+            "alertmanager_configs yaml:\n{:#?}",
+            serde_yaml::to_string(&alertmanager_configs)
+        );
+        debug!(
+            "alert manager configs: \n{:#?}",
+            alertmanager_configs.clone()
+        );
+
+        sender
+            .client
+            .apply(&alertmanager_configs, Some(&sender.namespace))
+            .await?;
+        Ok(Outcome::success(format!(
+            "installed rhob-alertmanagerconfigs for {}",
+            self.name
+        )))
+    }
+
+    fn name(&self) -> String {
+        "webhook-receiver".to_string()
+    }
+
+    fn clone_box(&self) -> Box<dyn AlertReceiver<RHOBObservability>> {
+        Box::new(self.clone())
+    }
+
+    fn as_any(&self) -> &dyn Any {
+        self
+    }
+}
+
+#[async_trait]
+impl AlertReceiver<CRDPrometheus> for DiscordWebhook {
+    fn as_alertmanager_receiver(&self) -> Result<AlertManagerReceiver, String> {
+        todo!()
+    }
+    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 receiver_config = json!({
+        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",
-                        "name": format!("{}-secret", self.name)
                             },
                             "title": "{{ template \"discord.default.title\" . }}",
                             "message": "{{ template \"discord.default.message\" . }}"
                             }
                         ]
-        });
-
-        Ok(ReceiverInstallPlan {
-            install_operation: Some(vec![InstallOperation::CreateSecret {
-                name: secret_name,
-                data: string_data,
-            }]),
-            route: Some(self.route.clone()),
-            receiver: Some(
-                serde_yaml::to_value(receiver_config)
-                    .map_err(|e| InterpretError::new(e.to_string()))
-                    .expect("failed to build yaml value"),
-            ),
-        })
                     }
+                ]
+            }),
+        };
 
+        let alertmanager_configs = AlertmanagerConfig {
+            metadata: ObjectMeta {
+                name: Some(self.name.clone().to_string()),
+                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 {
-        self.name.clone()
+        "discord-webhook".to_string()
     }
-
+    fn clone_box(&self) -> Box<dyn AlertReceiver<CRDPrometheus>> {
-    fn clone_box(&self) -> Box<dyn AlertReceiver<RedHatClusterObservability>> {
         Box::new(self.clone())
     }
+    fn as_any(&self) -> &dyn Any {
+        self
+    }
 }
 
-impl AlertReceiver<KubePrometheus> for DiscordReceiver {
+#[async_trait]
-    fn build(&self) -> Result<ReceiverInstallPlan, InterpretError> {
+impl AlertReceiver<Prometheus> for DiscordWebhook {
-        let receiver_block = serde_yaml::to_value(json!({
+    fn as_alertmanager_receiver(&self) -> Result<AlertManagerReceiver, String> {
-            "name": self.name,
+        todo!()
-            "discord_configs": [{
+    }
-                "webhook_url": format!("{}", self.url),
+    async fn install(&self, sender: &Prometheus) -> Result<Outcome, InterpretError> {
-                "title": "{{ template \"discord.default.title\" . }}",
+        sender.install_receiver(self).await
-                "message": "{{ template \"discord.default.message\" . }}"
-            }]
-        }))
-        .map_err(|e| InterpretError::new(e.to_string()))?;
-
-        Ok(ReceiverInstallPlan {
-            install_operation: None,
-            route: Some(self.route.clone()),
-            receiver: Some(receiver_block),
-        })
     }
-
     fn name(&self) -> String {
-        self.name.clone()
+        "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]
+impl PrometheusReceiver for DiscordWebhook {
+    fn name(&self) -> String {
+        self.name.clone().to_string()
+    }
+    async fn configure_receiver(&self) -> AlertManagerChannelConfig {
+        self.get_config().await
+    }
+}
+
+#[async_trait]
+impl AlertReceiver<KubePrometheus> for DiscordWebhook {
+    fn as_alertmanager_receiver(&self) -> Result<AlertManagerReceiver, String> {
+        todo!()
+    }
+    async fn install(&self, sender: &KubePrometheus) -> Result<Outcome, InterpretError> {
+        sender.install_receiver(self).await
+    }
     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]
+impl KubePrometheusReceiver for DiscordWebhook {
+    fn name(&self) -> String {
+        self.name.clone().to_string()
+    }
+    async fn configure_receiver(&self) -> AlertManagerChannelConfig {
+        self.get_config().await
+    }
+}
+
+#[async_trait]
+impl AlertChannelConfig for DiscordWebhook {
+    async fn get_config(&self) -> AlertManagerChannelConfig {
+        let channel_global_config = None;
+        let channel_receiver = self.alert_channel_receiver().await;
+        let channel_route = self.alert_channel_route().await;
+
+        AlertManagerChannelConfig {
+            channel_global_config,
+            channel_receiver,
+            channel_route,
+        }
+    }
+}
+
+impl DiscordWebhook {
+    async fn alert_channel_route(&self) -> serde_yaml::Value {
+        let mut route = Mapping::new();
+        route.insert(
+            Value::String("receiver".to_string()),
+            Value::String(self.name.clone().to_string()),
+        );
+        route.insert(
+            Value::String("matchers".to_string()),
+            Value::Sequence(vec![Value::String("alertname!=Watchdog".to_string())]),
+        );
+        route.insert(Value::String("continue".to_string()), Value::Bool(true));
+        Value::Mapping(route)
+    }
+
+    async fn alert_channel_receiver(&self) -> serde_yaml::Value {
+        let mut receiver = Mapping::new();
+        receiver.insert(
+            Value::String("name".to_string()),
+            Value::String(self.name.clone().to_string()),
+        );
+
+        let mut discord_config = Mapping::new();
+        discord_config.insert(
+            Value::String("webhook_url".to_string()),
+            Value::String(self.url.to_string()),
+        );
+
+        receiver.insert(
+            Value::String("discord_configs".to_string()),
+            Value::Sequence(vec![Value::Mapping(discord_config)]),
+        );
+
+        Value::Mapping(receiver)
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[tokio::test]
+    async fn discord_serialize_should_match() {
+        let discord_receiver = DiscordWebhook {
+            name: K8sName("test-discord".to_string()),
+            url: Url::Url(url::Url::parse("https://discord.i.dont.exist.com").unwrap()),
+            selectors: vec![],
+        };
+
+        let discord_receiver_receiver =
+            serde_yaml::to_string(&discord_receiver.alert_channel_receiver().await).unwrap();
+        println!("receiver \n{:#}", discord_receiver_receiver);
+        let discord_receiver_receiver_yaml = r#"name: test-discord
+discord_configs:
+- webhook_url: https://discord.i.dont.exist.com/
+"#
+        .to_string();
+
+        let discord_receiver_route =
+            serde_yaml::to_string(&discord_receiver.alert_channel_route().await).unwrap();
+        println!("route \n{:#}", discord_receiver_route);
+        let discord_receiver_route_yaml = r#"receiver: test-discord
+matchers:
+- alertname!=Watchdog
+continue: true
+"#
+        .to_string();
+
+        assert_eq!(discord_receiver_receiver, discord_receiver_receiver_yaml);
+        assert_eq!(discord_receiver_route, discord_receiver_route_yaml);
+    }
 }

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

@@ -1,13 +1,25 @@
+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,
+    interpret::{InterpretError, Outcome},
     modules::monitoring::{
-        kube_prometheus::KubePrometheus, okd::OpenshiftClusterAlertSender, prometheus::Prometheus,
+        kube_prometheus::{
-        red_hat_cluster_observability::RedHatClusterObservability,
+            crd::{
+                crd_alertmanager_config::CRDPrometheus, rhob_alertmanager_config::RHOBObservability,
             },
-    topology::monitoring::{AlertReceiver, AlertRoute, ReceiverInstallPlan},
+            prometheus::{KubePrometheus, KubePrometheusReceiver},
+            types::{AlertChannelConfig, AlertManagerChannelConfig},
+        },
+        prometheus::prometheus::{Prometheus, PrometheusReceiver},
+    },
+    topology::oberservability::monitoring::{AlertManagerReceiver, AlertReceiver},
 };
 use harmony_types::net::Url;
 
@@ -15,12 +27,21 @@ use harmony_types::net::Url;
 pub struct WebhookReceiver {
     pub name: String,
     pub url: Url,
-    pub route: AlertRoute,
 }
 
-impl WebhookReceiver {
+#[async_trait]
-    fn build_receiver(&self) -> serde_json::Value {
+impl AlertReceiver<RHOBObservability> for WebhookReceiver {
-        json!({
+    fn as_alertmanager_receiver(&self) -> Result<AlertManagerReceiver, String> {
+        todo!()
+    }
+    async fn install(&self, sender: &RHOBObservability) -> Result<Outcome, InterpretError> {
+        let spec = crate::modules::monitoring::kube_prometheus::crd::rhob_alertmanager_config::AlertmanagerConfigSpec {
+            data: json!({
+                "route": {
+                    "receiver": self.name,
+                },
+                "receivers": [
+                    {
                         "name": self.name,
                         "webhookConfigs": [
                             {
@@ -31,99 +52,256 @@ impl WebhookReceiver {
                                     }
                                 }
                             }
-        ]})
+                        ]
+                    }
+                ]
+            }),
+        };
+
+        let alertmanager_configs = crate::modules::monitoring::kube_prometheus::crd::rhob_alertmanager_config::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 rhob-alertmanagerconfigs for {}",
+            self.name
+        )))
     }
 
-    fn build_route(&self) -> serde_json::Value {
-        json!({
-            "name": self.name})
-    }
-}
-
-impl AlertReceiver<OpenshiftClusterAlertSender> for WebhookReceiver {
     fn name(&self) -> String {
-        self.name.clone()
+        "webhook-receiver".to_string()
     }
 
-    fn clone_box(&self) -> Box<dyn AlertReceiver<OpenshiftClusterAlertSender>> {
+    fn clone_box(&self) -> Box<dyn AlertReceiver<RHOBObservability>> {
         Box::new(self.clone())
     }
 
-    fn build(&self) -> Result<crate::topology::monitoring::ReceiverInstallPlan, InterpretError> {
+    fn as_any(&self) -> &dyn Any {
-        let receiver = self.build_receiver();
+        self
-        let receiver =
-            serde_yaml::to_value(receiver).map_err(|e| InterpretError::new(e.to_string()))?;
-
-        Ok(ReceiverInstallPlan {
-            install_operation: None,
-            route: Some(self.route.clone()),
-            receiver: Some(receiver),
-        })
     }
 }
 
-impl AlertReceiver<RedHatClusterObservability> for WebhookReceiver {
+#[async_trait]
-    fn name(&self) -> String {
+impl AlertReceiver<CRDPrometheus> for WebhookReceiver {
-        self.name.clone()
+    fn as_alertmanager_receiver(&self) -> Result<AlertManagerReceiver, String> {
+        todo!()
+    }
+    async fn install(&self, sender: &CRDPrometheus) -> Result<Outcome, InterpretError> {
+        let spec = crate::modules::monitoring::kube_prometheus::crd::crd_alertmanager_config::AlertmanagerConfigSpec {
+            data: json!({
+                "route": {
+                    "receiver": self.name,
+                },
+                "receivers": [
+                    {
+                        "name": self.name,
+                        "webhookConfigs": [
+                            {
+                            "url": self.url,
+                            }
+                        ]
+                    }
+                ]
+            }),
+        };
+
+        let alertmanager_configs = crate::modules::monitoring::kube_prometheus::crd::crd_alertmanager_config::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 clone_box(&self) -> Box<dyn AlertReceiver<RedHatClusterObservability>> {
+    fn name(&self) -> String {
+        "webhook-receiver".to_string()
+    }
+
+    fn clone_box(&self) -> Box<dyn AlertReceiver<CRDPrometheus>> {
         Box::new(self.clone())
     }
 
-    fn build(&self) -> Result<crate::topology::monitoring::ReceiverInstallPlan, InterpretError> {
+    fn as_any(&self) -> &dyn Any {
-        let receiver = self.build_receiver();
+        self
-        let receiver =
-            serde_yaml::to_value(receiver).map_err(|e| InterpretError::new(e.to_string()))?;
-
-        Ok(ReceiverInstallPlan {
-            install_operation: None,
-            route: Some(self.route.clone()),
-            receiver: Some(receiver),
-        })
-    }
-}
-
-impl AlertReceiver<KubePrometheus> for WebhookReceiver {
-    fn name(&self) -> String {
-        self.name.clone()
-    }
-
-    fn clone_box(&self) -> Box<dyn AlertReceiver<KubePrometheus>> {
-        Box::new(self.clone())
-    }
-
-    fn build(&self) -> Result<crate::topology::monitoring::ReceiverInstallPlan, InterpretError> {
-        let receiver = self.build_receiver();
-        let receiver =
-            serde_yaml::to_value(receiver).map_err(|e| InterpretError::new(e.to_string()))?;
-
-        Ok(ReceiverInstallPlan {
-            install_operation: None,
-            route: Some(self.route.clone()),
-            receiver: Some(receiver),
-        })
     }
 }
 
+#[async_trait]
 impl AlertReceiver<Prometheus> for WebhookReceiver {
-    fn name(&self) -> String {
+    fn as_alertmanager_receiver(&self) -> Result<AlertManagerReceiver, String> {
-        self.name.clone()
+        todo!()
+    }
+    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 {
-    fn build(&self) -> Result<crate::topology::monitoring::ReceiverInstallPlan, InterpretError> {
+        self
-        let receiver = self.build_receiver();
+    }
-        let receiver =
+}
-            serde_yaml::to_value(receiver).map_err(|e| InterpretError::new(e.to_string()))?;
+
-
+#[async_trait]
-        Ok(ReceiverInstallPlan {
+impl PrometheusReceiver for WebhookReceiver {
-            install_operation: None,
+    fn name(&self) -> String {
-            route: Some(self.route.clone()),
+        self.name.clone()
-            receiver: Some(receiver),
+    }
-        })
+    async fn configure_receiver(&self) -> AlertManagerChannelConfig {
+        self.get_config().await
+    }
+}
+
+#[async_trait]
+impl AlertReceiver<KubePrometheus> for WebhookReceiver {
+    fn as_alertmanager_receiver(&self) -> Result<AlertManagerReceiver, String> {
+        todo!()
+    }
+    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]
+impl KubePrometheusReceiver for WebhookReceiver {
+    fn name(&self) -> String {
+        self.name.clone()
+    }
+    async fn configure_receiver(&self) -> AlertManagerChannelConfig {
+        self.get_config().await
+    }
+}
+
+#[async_trait]
+impl AlertChannelConfig for WebhookReceiver {
+    async fn get_config(&self) -> AlertManagerChannelConfig {
+        let channel_global_config = None;
+        let channel_receiver = self.alert_channel_receiver().await;
+        let channel_route = self.alert_channel_route().await;
+
+        AlertManagerChannelConfig {
+            channel_global_config,
+            channel_receiver,
+            channel_route,
+        }
+    }
+}
+
+impl WebhookReceiver {
+    async fn alert_channel_route(&self) -> serde_yaml::Value {
+        let mut route = Mapping::new();
+        route.insert(
+            Value::String("receiver".to_string()),
+            Value::String(self.name.clone()),
+        );
+        route.insert(
+            Value::String("matchers".to_string()),
+            Value::Sequence(vec![Value::String("alertname!=Watchdog".to_string())]),
+        );
+        route.insert(Value::String("continue".to_string()), Value::Bool(true));
+        Value::Mapping(route)
+    }
+
+    async fn alert_channel_receiver(&self) -> serde_yaml::Value {
+        let mut receiver = Mapping::new();
+        receiver.insert(
+            Value::String("name".to_string()),
+            Value::String(self.name.clone()),
+        );
+
+        let mut webhook_config = Mapping::new();
+        webhook_config.insert(
+            Value::String("url".to_string()),
+            Value::String(self.url.to_string()),
+        );
+
+        receiver.insert(
+            Value::String("webhook_configs".to_string()),
+            Value::Sequence(vec![Value::Mapping(webhook_config)]),
+        );
+
+        Value::Mapping(receiver)
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    #[tokio::test]
+    async fn webhook_serialize_should_match() {
+        let webhook_receiver = WebhookReceiver {
+            name: "test-webhook".to_string(),
+            url: Url::Url(url::Url::parse("https://webhook.i.dont.exist.com").unwrap()),
+        };
+
+        let webhook_receiver_receiver =
+            serde_yaml::to_string(&webhook_receiver.alert_channel_receiver().await).unwrap();
+        println!("receiver \n{:#}", webhook_receiver_receiver);
+        let webhook_receiver_receiver_yaml = r#"name: test-webhook
+webhook_configs:
+- url: https://webhook.i.dont.exist.com/
+"#
+        .to_string();
+
+        let webhook_receiver_route =
+            serde_yaml::to_string(&webhook_receiver.alert_channel_route().await).unwrap();
+        println!("route \n{:#}", webhook_receiver_route);
+        let webhook_receiver_route_yaml = r#"receiver: test-webhook
+matchers:
+- alertname!=Watchdog
+continue: true
+"#
+        .to_string();
+
+        assert_eq!(webhook_receiver_receiver, webhook_receiver_receiver_yaml);
+        assert_eq!(webhook_receiver_route, webhook_receiver_route_yaml);
     }
 }

harmony/src/modules/monitoring/alert_rule/alerts/infra/opnsense.rs

@@ -1,15 +0,0 @@
-use crate::modules::monitoring::alert_rule::prometheus_alert_rule::PrometheusAlertRule;
-
-pub fn high_http_error_rate() -> PrometheusAlertRule {
-    let expression = r#"(
-  sum(rate(http_requests_total{status=~"5.."}[5m])) by (job, route, service)
-  /
-  sum(rate(http_requests_total[5m])) by (job, route, service)
-) > 0.05 and sum(rate(http_requests_total[5m])) by (job, route, service) > 10"#;
-
-    PrometheusAlertRule::new("HighApplicationErrorRate", expression)
-        .for_duration("10m")
-        .label("severity", "warning")
-        .annotation("summary", "High HTTP error rate on {{ $labels.job }}")
-        .annotation("description", "Job {{ $labels.job }} (route {{ $labels.route }}) has an error rate > 5% over the last 10m.")
-}

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

@@ -1,2 +1 @@
-pub mod alerts;
 pub mod prometheus_alert_rule;

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

@@ -1,13 +1,79 @@
-use std::collections::HashMap;
+use std::collections::{BTreeMap, HashMap};
 
+use async_trait::async_trait;
 use serde::Serialize;
 
 use crate::{
-    interpret::InterpretError,
+    interpret::{InterpretError, Outcome},
-    modules::monitoring::{kube_prometheus::KubePrometheus, okd::OpenshiftClusterAlertSender},
+    modules::monitoring::{
-    topology::monitoring::AlertRule,
+        kube_prometheus::{
+            prometheus::{KubePrometheus, KubePrometheusRule},
+            types::{AlertGroup, AlertManagerAdditionalPromRules},
+        },
+        prometheus::prometheus::{Prometheus, PrometheusRule},
+    },
+    topology::oberservability::monitoring::AlertRule,
 };
 
+#[async_trait]
+impl AlertRule<KubePrometheus> for AlertManagerRuleGroup {
+    async fn install(&self, sender: &KubePrometheus) -> Result<Outcome, InterpretError> {
+        sender.install_rule(self).await
+    }
+    fn clone_box(&self) -> Box<dyn AlertRule<KubePrometheus>> {
+        Box::new(self.clone())
+    }
+}
+
+#[async_trait]
+impl AlertRule<Prometheus> for AlertManagerRuleGroup {
+    async fn install(&self, sender: &Prometheus) -> Result<Outcome, InterpretError> {
+        sender.install_rule(self).await
+    }
+    fn clone_box(&self) -> Box<dyn AlertRule<Prometheus>> {
+        Box::new(self.clone())
+    }
+}
+
+#[async_trait]
+impl PrometheusRule for AlertManagerRuleGroup {
+    fn name(&self) -> String {
+        self.name.clone()
+    }
+    async fn configure_rule(&self) -> AlertManagerAdditionalPromRules {
+        let mut additional_prom_rules = BTreeMap::new();
+
+        additional_prom_rules.insert(
+            self.name.clone(),
+            AlertGroup {
+                groups: vec![self.clone()],
+            },
+        );
+        AlertManagerAdditionalPromRules {
+            rules: additional_prom_rules,
+        }
+    }
+}
+#[async_trait]
+impl KubePrometheusRule for AlertManagerRuleGroup {
+    fn name(&self) -> String {
+        self.name.clone()
+    }
+    async fn configure_rule(&self) -> AlertManagerAdditionalPromRules {
+        let mut additional_prom_rules = BTreeMap::new();
+
+        additional_prom_rules.insert(
+            self.name.clone(),
+            AlertGroup {
+                groups: vec![self.clone()],
+            },
+        );
+        AlertManagerAdditionalPromRules {
+            rules: additional_prom_rules,
+        }
+    }
+}
+
 impl AlertManagerRuleGroup {
     pub fn new(name: &str, rules: Vec<PrometheusAlertRule>) -> AlertManagerRuleGroup {
         AlertManagerRuleGroup {
@@ -63,55 +129,3 @@ impl PrometheusAlertRule {
         self
     }
 }
-
-impl AlertRule<OpenshiftClusterAlertSender> for AlertManagerRuleGroup {
-    fn build_rule(&self) -> Result<serde_json::Value, InterpretError> {
-        let name = self.name.clone();
-        let mut rules: Vec<crate::modules::monitoring::okd::crd::alerting_rules::Rule> = vec![];
-        for rule in self.rules.clone() {
-            rules.push(rule.into())
-        }
-
-        let rule_groups =
-            vec![crate::modules::monitoring::okd::crd::alerting_rules::RuleGroup { name, rules }];
-
-        Ok(serde_json::to_value(rule_groups).map_err(|e| InterpretError::new(e.to_string()))?)
-    }
-
-    fn name(&self) -> String {
-        self.name.clone()
-    }
-
-    fn clone_box(&self) -> Box<dyn AlertRule<OpenshiftClusterAlertSender>> {
-        Box::new(self.clone())
-    }
-}
-
-impl AlertRule<KubePrometheus> for AlertManagerRuleGroup {
-    fn build_rule(&self) -> Result<serde_json::Value, InterpretError> {
-        let name = self.name.clone();
-        let mut rules: Vec<
-            crate::modules::monitoring::kube_prometheus::crd::crd_prometheus_rules::Rule,
-        > = vec![];
-        for rule in self.rules.clone() {
-            rules.push(rule.into())
-        }
-
-        let rule_groups = vec![
-            crate::modules::monitoring::kube_prometheus::crd::crd_prometheus_rules::RuleGroup {
-                name,
-                rules,
-            },
-        ];
-
-        Ok(serde_json::to_value(rule_groups).map_err(|e| InterpretError::new(e.to_string()))?)
-    }
-
-    fn name(&self) -> String {
-        self.name.clone()
-    }
-
-    fn clone_box(&self) -> Box<dyn AlertRule<KubePrometheus>> {
-        Box::new(self.clone())
-    }
-}

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

@@ -5,26 +5,32 @@ use serde::Serialize;
 
 use crate::{
     interpret::Interpret,
-    modules::{application::Application, monitoring::prometheus::Prometheus},
+    modules::{
+        application::Application,
+        monitoring::{
+            grafana::grafana::Grafana, kube_prometheus::crd::crd_alertmanager_config::CRDPrometheus,
+        },
+        prometheus::prometheus::PrometheusMonitoring,
+    },
     score::Score,
     topology::{
         K8sclient, Topology,
-        monitoring::{AlertReceiver, AlertingInterpret, Observability, ScrapeTarget},
+        oberservability::monitoring::{AlertReceiver, AlertingInterpret, ScrapeTarget},
     },
 };
 
 #[derive(Debug, Clone, Serialize)]
 pub struct ApplicationMonitoringScore {
-    pub sender: Prometheus,
+    pub sender: CRDPrometheus,
     pub application: Arc<dyn Application>,
-    pub receivers: Vec<Box<dyn AlertReceiver<Prometheus>>>,
+    pub receivers: Vec<Box<dyn AlertReceiver<CRDPrometheus>>>,
 }
 
-impl<T: Topology + Observability<Prometheus> + K8sclient> Score<T> for ApplicationMonitoringScore {
+impl<T: Topology + PrometheusMonitoring<CRDPrometheus> + K8sclient + Grafana> Score<T>
+    for ApplicationMonitoringScore
+{
     fn create_interpret(&self) -> Box<dyn Interpret<T>> {
         debug!("creating alerting interpret");
-        //TODO will need to use k8sclient to apply service monitors or find a way to pass
-        //them to the AlertingInterpret potentially via Sender Prometheus
         Box::new(AlertingInterpret {
             sender: self.sender.clone(),
             receivers: self.receivers.clone(),

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

@@ -9,27 +9,28 @@ use crate::{
     inventory::Inventory,
     modules::{
         application::Application,
-        monitoring::red_hat_cluster_observability::RedHatClusterObservability,
+        monitoring::kube_prometheus::crd::{
+            crd_alertmanager_config::CRDPrometheus, rhob_alertmanager_config::RHOBObservability,
+        },
+        prometheus::prometheus::PrometheusMonitoring,
     },
     score::Score,
-    topology::{
+    topology::{PreparationOutcome, Topology, oberservability::monitoring::AlertReceiver},
-        Topology,
-        monitoring::{AlertReceiver, AlertingInterpret, Observability},
-    },
 };
 use harmony_types::id::Id;
+
 #[derive(Debug, Clone, Serialize)]
-pub struct ApplicationRedHatClusterMonitoringScore {
+pub struct ApplicationRHOBMonitoringScore {
-    pub sender: RedHatClusterObservability,
+    pub sender: RHOBObservability,
     pub application: Arc<dyn Application>,
-    pub receivers: Vec<Box<dyn AlertReceiver<RedHatClusterObservability>>>,
+    pub receivers: Vec<Box<dyn AlertReceiver<RHOBObservability>>>,
 }
 
-impl<T: Topology + Observability<RedHatClusterObservability>> Score<T>
+impl<T: Topology + PrometheusMonitoring<RHOBObservability>> Score<T>
-    for ApplicationRedHatClusterMonitoringScore
+    for ApplicationRHOBMonitoringScore
 {
     fn create_interpret(&self) -> Box<dyn Interpret<T>> {
-        Box::new(ApplicationRedHatClusterMonitoringInterpret {
+        Box::new(ApplicationRHOBMonitoringInterpret {
             score: self.clone(),
         })
     }
@@ -43,28 +44,38 @@ impl<T: Topology + Observability<RedHatClusterObservability>> Score<T>
 }
 
 #[derive(Debug)]
-pub struct ApplicationRedHatClusterMonitoringInterpret {
+pub struct ApplicationRHOBMonitoringInterpret {
-    score: ApplicationRedHatClusterMonitoringScore,
+    score: ApplicationRHOBMonitoringScore,
 }
 
 #[async_trait]
-impl<T: Topology + Observability<RedHatClusterObservability>> Interpret<T>
+impl<T: Topology + PrometheusMonitoring<RHOBObservability>> Interpret<T>
-    for ApplicationRedHatClusterMonitoringInterpret
+    for ApplicationRHOBMonitoringInterpret
 {
     async fn execute(
         &self,
         inventory: &Inventory,
         topology: &T,
     ) -> Result<Outcome, InterpretError> {
-        //TODO will need to use k8sclient to apply crd ServiceMonitor or find a way to pass
+        let result = topology
-        //them to the AlertingInterpret potentially via Sender RedHatClusterObservability
+            .install_prometheus(
-        let alerting_interpret = AlertingInterpret {
+                &self.score.sender,
-            sender: self.score.sender.clone(),
+                inventory,
-            receivers: self.score.receivers.clone(),
+                Some(self.score.receivers.clone()),
-            rules: vec![],
+            )
-            scrape_targets: None,
+            .await;
-        };
+
-        alerting_interpret.execute(inventory, topology).await
+        match result {
+            Ok(outcome) => match outcome {
+                PreparationOutcome::Success { details: _ } => {
+                    Ok(Outcome::success("Prometheus installed".into()))
+                }
+                PreparationOutcome::Noop => {
+                    Ok(Outcome::noop("Prometheus installation skipped".into()))
+                }
+            },
+            Err(err) => Err(InterpretError::from(err)),
+        }
     }
 
     fn get_name(&self) -> InterpretName {

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

@@ -1,41 +1,17 @@
-use serde::Serialize;
+use async_trait::async_trait;
+use k8s_openapi::Resource;
 
-use crate::topology::monitoring::{AlertReceiver, AlertRule, AlertSender, ScrapeTarget};
+use crate::{
+    inventory::Inventory,
+    topology::{PreparationError, PreparationOutcome},
+};
 
-#[derive(Debug, Clone, Serialize)]
+#[async_trait]
-pub struct Grafana {
+pub trait Grafana {
-    pub namespace: String,
+    async fn ensure_grafana_operator(
-}
+        &self,
-
+        inventory: &Inventory,
-impl AlertSender for Grafana {
+    ) -> Result<PreparationOutcome, PreparationError>;
-    fn name(&self) -> String {
+
-        "grafana".to_string()
+    async fn install_grafana(&self) -> Result<PreparationOutcome, PreparationError>;
-    }
-}
-
-impl Serialize for Box<dyn AlertReceiver<Grafana>> {
-    fn serialize<S>(&self, _serializer: S) -> Result<S::Ok, S::Error>
-    where
-        S: serde::Serializer,
-    {
-        todo!()
-    }
-}
-
-impl Serialize for Box<dyn AlertRule<Grafana>> {
-    fn serialize<S>(&self, _serializer: S) -> Result<S::Ok, S::Error>
-    where
-        S: serde::Serializer,
-    {
-        todo!()
-    }
-}
-
-impl Serialize for Box<dyn ScrapeTarget<Grafana>> {
-    fn serialize<S>(&self, _serializer: S) -> Result<S::Ok, S::Error>
-    where
-        S: serde::Serializer,
-    {
-        todo!()
-    }
 }

harmony/src/modules/monitoring/grafana/grafana_alerting_score.rs

@@ -1,32 +0,0 @@
-use serde::Serialize;
-
-use crate::{
-    modules::monitoring::grafana::grafana::Grafana,
-    score::Score,
-    topology::{
-        Topology,
-        monitoring::{AlertReceiver, AlertRule, AlertingInterpret, Observability, ScrapeTarget},
-    },
-};
-
-#[derive(Clone, Debug, Serialize)]
-pub struct GrafanaAlertingScore {
-    pub receivers: Vec<Box<dyn AlertReceiver<Grafana>>>,
-    pub rules: Vec<Box<dyn AlertRule<Grafana>>>,
-    pub scrape_targets: Option<Vec<Box<dyn ScrapeTarget<Grafana>>>>,
-    pub sender: Grafana,
-}
-
-impl<T: Topology + Observability<Grafana>> Score<T> for GrafanaAlertingScore {
-    fn create_interpret(&self) -> Box<dyn crate::interpret::Interpret<T>> {
-        Box::new(AlertingInterpret {
-            sender: self.sender.clone(),
-            receivers: self.receivers.clone(),
-            rules: self.rules.clone(),
-            scrape_targets: self.scrape_targets.clone(),
-        })
-    }
-    fn name(&self) -> String {
-        "HelmPrometheusAlertingScore".to_string()
-    }
-}

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

@@ -0,0 +1,28 @@
+use harmony_macros::hurl;
+use non_blank_string_rs::NonBlankString;
+use std::{collections::HashMap, str::FromStr};
+
+use crate::modules::helm::chart::{HelmChartScore, HelmRepository};
+
+pub fn grafana_helm_chart_score(ns: &str, namespace_scope: bool) -> HelmChartScore {
+    let mut values_overrides = HashMap::new();
+    values_overrides.insert(
+        NonBlankString::from_str("namespaceScope").unwrap(),
+        namespace_scope.to_string(),
+    );
+    HelmChartScore {
+        namespace: Some(NonBlankString::from_str(ns).unwrap()),
+        release_name: NonBlankString::from_str("grafana-operator").unwrap(),
+        chart_name: NonBlankString::from_str("grafana/grafana-operator").unwrap(),
+        chart_version: None,
+        values_overrides: Some(values_overrides),
+        values_yaml: None,
+        create_namespace: true,
+        install_only: true,
+        repository: Some(HelmRepository::new(
+            "grafana".to_string(),
+            hurl!("https://grafana.github.io/helm-charts"),
+            true,
+        )),
+    }
+}

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

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

harmony/src/modules/monitoring/grafana/k8s/crd/mod.rs

@@ -1,3 +0,0 @@
-pub mod crd_grafana;
-pub mod grafana_default_dashboard;
-pub mod rhob_grafana;

harmony/src/modules/monitoring/grafana/k8s/helm/mod.rs

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

harmony/src/modules/monitoring/grafana/k8s/mod.rs

@@ -1,7 +0,0 @@
-pub mod crd;
-pub mod helm;
-pub mod score_ensure_grafana_ready;
-pub mod score_grafana_alert_receiver;
-pub mod score_grafana_datasource;
-pub mod score_grafana_rule;
-pub mod score_install_grafana;

harmony/src/modules/monitoring/grafana/k8s/score_ensure_grafana_ready.rs

@@ -1,54 +0,0 @@
-use serde::Serialize;
-
-use crate::{
-    interpret::Interpret,
-    modules::monitoring::grafana::grafana::Grafana,
-    score::Score,
-    topology::{K8sclient, Topology},
-};
-
-#[derive(Debug, Clone, Serialize)]
-pub struct GrafanaK8sEnsureReadyScore {
-    pub sender: Grafana,
-}
-
-impl<T: Topology + K8sclient> Score<T> for GrafanaK8sEnsureReadyScore {
-    fn name(&self) -> String {
-        "GrafanaK8sEnsureReadyScore".to_string()
-    }
-
-    fn create_interpret(&self) -> Box<dyn Interpret<T>> {
-        todo!()
-    }
-}
-//     async fn ensure_ready(
-//         &self,
-//         inventory: &Inventory,
-//     ) -> Result<PreparationOutcome, PreparationError> {
-//         debug!("ensure grafana operator");
-//         let client = self.k8s_client().await.unwrap();
-//         let grafana_gvk = GroupVersionKind {
-//             group: "grafana.integreatly.org".to_string(),
-//             version: "v1beta1".to_string(),
-//             kind: "Grafana".to_string(),
-//         };
-//         let name = "grafanas.grafana.integreatly.org";
-//         let ns = "grafana";
-//
-//         let grafana_crd = client
-//             .get_resource_json_value(name, Some(ns), &grafana_gvk)
-//             .await;
-//         match grafana_crd {
-//             Ok(_) => {
-//                 return Ok(PreparationOutcome::Success {
-//                     details: "Found grafana CRDs in cluster".to_string(),
-//                 });
-//             }
-//
-//             Err(_) => {
-//                 return self
-//                     .install_grafana_operator(inventory, Some("grafana"))
-//                     .await;
-//             }
-//         };
-//     }

harmony/src/modules/monitoring/grafana/k8s/score_grafana_alert_receiver.rs

@@ -1,24 +0,0 @@
-use serde::Serialize;
-
-use crate::{
-    interpret::Interpret,
-    modules::monitoring::grafana::grafana::Grafana,
-    score::Score,
-    topology::{K8sclient, Topology, monitoring::AlertReceiver},
-};
-
-#[derive(Debug, Clone, Serialize)]
-pub struct GrafanaK8sReceiverScore {
-    pub sender: Grafana,
-    pub receiver: Box<dyn AlertReceiver<Grafana>>,
-}
-
-impl<T: Topology + K8sclient> Score<T> for GrafanaK8sReceiverScore {
-    fn name(&self) -> String {
-        "GrafanaK8sReceiverScore".to_string()
-    }
-
-    fn create_interpret(&self) -> Box<dyn Interpret<T>> {
-        todo!()
-    }
-}

harmony/src/modules/monitoring/grafana/k8s/score_grafana_datasource.rs

@@ -1,83 +0,0 @@
-use serde::Serialize;
-
-use crate::{
-    interpret::Interpret,
-    modules::monitoring::grafana::grafana::Grafana,
-    score::Score,
-    topology::{K8sclient, Topology, monitoring::ScrapeTarget},
-};
-
-#[derive(Debug, Clone, Serialize)]
-pub struct GrafanaK8sDatasourceScore {
-    pub sender: Grafana,
-    pub scrape_target: Box<dyn ScrapeTarget<Grafana>>,
-}
-
-impl<T: Topology + K8sclient> Score<T> for GrafanaK8sDatasourceScore {
-    fn name(&self) -> String {
-        "GrafanaK8sDatasourceScore".to_string()
-    }
-
-    fn create_interpret(&self) -> Box<dyn Interpret<T>> {
-        todo!()
-    }
-}
-
-//     fn extract_and_normalize_token(&self, secret: &DynamicObject) -> Option<String> {
-//         let token_b64 = secret
-//             .data
-//             .get("token")
-//             .or_else(|| secret.data.get("data").and_then(|d| d.get("token")))
-//             .and_then(|v| v.as_str())?;
-//
-//         let bytes = general_purpose::STANDARD.decode(token_b64).ok()?;
-//
-//         let s = String::from_utf8(bytes).ok()?;
-//
-//         let cleaned = s
-//             .trim_matches(|c: char| c.is_whitespace() || c == '\0')
-//             .to_string();
-//         Some(cleaned)
-//     }
-//     fn build_grafana_datasource(
-//         &self,
-//         name: &str,
-//         ns: &str,
-//         label_selector: &LabelSelector,
-//         url: &str,
-//         token: &str,
-//     ) -> GrafanaDatasource {
-//         let mut json_data = BTreeMap::new();
-//         json_data.insert("timeInterval".to_string(), "5s".to_string());
-//
-//         GrafanaDatasource {
-//             metadata: ObjectMeta {
-//                 name: Some(name.to_string()),
-//                 namespace: Some(ns.to_string()),
-//                 ..Default::default()
-//             },
-//             spec: GrafanaDatasourceSpec {
-//                 instance_selector: label_selector.clone(),
-//                 allow_cross_namespace_import: Some(true),
-//                 values_from: None,
-//                 datasource: GrafanaDatasourceConfig {
-//                     access: "proxy".to_string(),
-//                     name: name.to_string(),
-//                     rype: "prometheus".to_string(),
-//                     url: url.to_string(),
-//                     database: None,
-//                     json_data: Some(GrafanaDatasourceJsonData {
-//                         time_interval: Some("60s".to_string()),
-//                         http_header_name1: Some("Authorization".to_string()),
-//                         tls_skip_verify: Some(true),
-//                         oauth_pass_thru: Some(true),
-//                     }),
-//                     secure_json_data: Some(GrafanaDatasourceSecureJsonData {
-//                         http_header_value1: Some(format!("Bearer {token}")),
-//                     }),
-//                     is_default: Some(false),
-//                     editable: Some(true),
-//                 },
-//             },
-//         }
-//     }

harmony/src/modules/monitoring/grafana/k8s/score_grafana_rule.rs

@@ -1,67 +0,0 @@
-use serde::Serialize;
-
-use crate::{
-    interpret::Interpret,
-    modules::monitoring::grafana::grafana::Grafana,
-    score::Score,
-    topology::{K8sclient, Topology, monitoring::AlertRule},
-};
-
-#[derive(Debug, Clone, Serialize)]
-pub struct GrafanaK8sRuleScore {
-    pub sender: Grafana,
-    pub rule: Box<dyn AlertRule<Grafana>>,
-}
-
-impl<T: Topology + K8sclient> Score<T> for GrafanaK8sRuleScore {
-    fn name(&self) -> String {
-        "GrafanaK8sRuleScore".to_string()
-    }
-
-    fn create_interpret(&self) -> Box<dyn Interpret<T>> {
-        todo!()
-    }
-}
-
-// kind: Secret
-// apiVersion: v1
-// metadata:
-//   name: credentials
-//   namespace: grafana
-// stringData:
-//   PROMETHEUS_USERNAME: root
-//   PROMETHEUS_PASSWORD: secret
-// type: Opaque
-// ---
-// apiVersion: grafana.integreatly.org/v1beta1
-// kind: GrafanaDatasource
-// metadata:
-//   name: grafanadatasource-sample
-// spec:
-//   valuesFrom:
-//     - targetPath: "basicAuthUser"
-//       valueFrom:
-//         secretKeyRef:
-//           name: "credentials"
-//           key: "PROMETHEUS_USERNAME"
-//     - targetPath: "secureJsonData.basicAuthPassword"
-//       valueFrom:
-//         secretKeyRef:
-//           name: "credentials"
-//           key: "PROMETHEUS_PASSWORD"
-//   instanceSelector:
-//     matchLabels:
-//       dashboards: "grafana"
-//   datasource:
-//     name: prometheus
-//     type: prometheus
-//     access: proxy
-//     basicAuth: true
-//     url: http://prometheus-service:9090
-//     isDefault: true
-//     basicAuthUser: ${PROMETHEUS_USERNAME}
-//     jsonData:
-//       "tlsSkipVerify": true
-//       "timeInterval": "5s"
-//     secureJsonData:
-//       "basicAuthPassword": ${PROMETHEUS_PASSWORD} #

harmony/src/modules/monitoring/grafana/k8s/score_install_grafana.rs

@@ -1,223 +0,0 @@
-use async_trait::async_trait;
-use harmony_types::id::Id;
-use serde::Serialize;
-
-use crate::{
-    data::Version,
-    interpret::{Interpret, InterpretError, InterpretName, InterpretStatus, Outcome},
-    inventory::Inventory,
-    modules::monitoring::grafana::grafana::Grafana,
-    score::Score,
-    topology::{HelmCommand, K8sclient, Topology},
-};
-
-#[derive(Debug, Clone, Serialize)]
-pub struct GrafanaK8sInstallScore {
-    pub sender: Grafana,
-}
-
-impl<T: Topology + K8sclient + HelmCommand> Score<T> for GrafanaK8sInstallScore {
-    fn name(&self) -> String {
-        "GrafanaK8sEnsureReadyScore".to_string()
-    }
-
-    fn create_interpret(&self) -> Box<dyn Interpret<T>> {
-        Box::new(GrafanaK8sInstallInterpret {})
-    }
-}
-
-#[derive(Debug, Clone, Serialize)]
-pub struct GrafanaK8sInstallInterpret {}
-
-#[async_trait]
-impl<T: Topology + K8sclient + HelmCommand> Interpret<T> for GrafanaK8sInstallInterpret {
-    async fn execute(
-        &self,
-        inventory: &Inventory,
-        topology: &T,
-    ) -> Result<Outcome, InterpretError> {
-        todo!()
-    }
-
-    fn get_name(&self) -> InterpretName {
-        InterpretName::Custom("GrafanaK8sInstallInterpret")
-    }
-
-    fn get_version(&self) -> Version {
-        todo!()
-    }
-
-    fn get_status(&self) -> InterpretStatus {
-        todo!()
-    }
-
-    fn get_children(&self) -> Vec<Id> {
-        todo!()
-    }
-}
-// let score = grafana_operator_helm_chart_score(sender.namespace.clone());
-//
-// score
-//     .create_interpret()
-//     .execute(inventory, self)
-//     .await
-//     .map_err(|e| PreparationError::new(e.to_string()))?;
-//
-
-//
-//     fn build_grafana_dashboard(
-//         &self,
-//         ns: &str,
-//         label_selector: &LabelSelector,
-//     ) -> GrafanaDashboard {
-//         let graf_dashboard = GrafanaDashboard {
-//             metadata: ObjectMeta {
-//                 name: Some(format!("grafana-dashboard-{}", ns)),
-//                 namespace: Some(ns.to_string()),
-//                 ..Default::default()
-//             },
-//             spec: GrafanaDashboardSpec {
-//                 resync_period: Some("30s".to_string()),
-//                 instance_selector: label_selector.clone(),
-//                 datasources: Some(vec![GrafanaDashboardDatasource {
-//                     input_name: "DS_PROMETHEUS".to_string(),
-//                     datasource_name: "thanos-openshift-monitoring".to_string(),
-//                 }]),
-//                 json: None,
-//                 grafana_com: Some(GrafanaCom {
-//                     id: 17406,
-//                     revision: None,
-//                 }),
-//             },
-//         };
-//         graf_dashboard
-//     }
-//
-//     fn build_grafana(&self, ns: &str, labels: &BTreeMap<String, String>) -> GrafanaCRD {
-//         let grafana = GrafanaCRD {
-//             metadata: ObjectMeta {
-//                 name: Some(format!("grafana-{}", ns)),
-//                 namespace: Some(ns.to_string()),
-//                 labels: Some(labels.clone()),
-//                 ..Default::default()
-//             },
-//             spec: GrafanaSpec {
-//                 config: None,
-//                 admin_user: None,
-//                 admin_password: None,
-//                 ingress: None,
-//                 persistence: None,
-//                 resources: None,
-//             },
-//         };
-//         grafana
-//     }
-//
-//     async fn build_grafana_ingress(&self, ns: &str) -> K8sIngressScore {
-//         let domain = self.get_domain(&format!("grafana-{}", ns)).await.unwrap();
-//         let name = format!("{}-grafana", ns);
-//         let backend_service = format!("grafana-{}-service", ns);
-//
-//         K8sIngressScore {
-//             name: fqdn::fqdn!(&name),
-//             host: fqdn::fqdn!(&domain),
-//             backend_service: fqdn::fqdn!(&backend_service),
-//             port: 3000,
-//             path: Some("/".to_string()),
-//             path_type: Some(PathType::Prefix),
-//             namespace: Some(fqdn::fqdn!(&ns)),
-//             ingress_class_name: Some("openshift-default".to_string()),
-//         }
-//     }
-// #[async_trait]
-// impl Grafana for K8sAnywhereTopology {
-//     async fn install_grafana(&self) -> Result<PreparationOutcome, PreparationError> {
-//         let ns = "grafana";
-//
-//         let mut label = BTreeMap::new();
-//
-//         label.insert("dashboards".to_string(), "grafana".to_string());
-//
-//         let label_selector = LabelSelector {
-//             match_labels: label.clone(),
-//             match_expressions: vec![],
-//         };
-//
-//         let client = self.k8s_client().await?;
-//
-//         let grafana = self.build_grafana(ns, &label);
-//
-//         client.apply(&grafana, Some(ns)).await?;
-//         //TODO change this to a ensure ready or something better than just a timeout
-//         client
-//             .wait_until_deployment_ready(
-//                 "grafana-grafana-deployment",
-//                 Some("grafana"),
-//                 Some(Duration::from_secs(30)),
-//             )
-//             .await?;
-//
-//         let sa_name = "grafana-grafana-sa";
-//         let token_secret_name = "grafana-sa-token-secret";
-//
-//         let sa_token_secret = self.build_sa_token_secret(token_secret_name, sa_name, ns);
-//
-//         client.apply(&sa_token_secret, Some(ns)).await?;
-//         let secret_gvk = GroupVersionKind {
-//             group: "".to_string(),
-//             version: "v1".to_string(),
-//             kind: "Secret".to_string(),
-//         };
-//
-//         let secret = client
-//             .get_resource_json_value(token_secret_name, Some(ns), &secret_gvk)
-//             .await?;
-//
-//         let token = format!(
-//             "Bearer {}",
-//             self.extract_and_normalize_token(&secret).unwrap()
-//         );
-//
-//         debug!("creating grafana clusterrole binding");
-//
-//         let clusterrolebinding =
-//             self.build_cluster_rolebinding(sa_name, "cluster-monitoring-view", ns);
-//
-//         client.apply(&clusterrolebinding, Some(ns)).await?;
-//
-//         debug!("creating grafana datasource crd");
-//
-//         let thanos_url = format!(
-//             "https://{}",
-//             self.get_domain("thanos-querier-openshift-monitoring")
-//                 .await
-//                 .unwrap()
-//         );
-//
-//         let thanos_openshift_datasource = self.build_grafana_datasource(
-//             "thanos-openshift-monitoring",
-//             ns,
-//             &label_selector,
-//             &thanos_url,
-//             &token,
-//         );
-//
-//         client.apply(&thanos_openshift_datasource, Some(ns)).await?;
-//
-//         debug!("creating grafana dashboard crd");
-//         let dashboard = self.build_grafana_dashboard(ns, &label_selector);
-//
-//         client.apply(&dashboard, Some(ns)).await?;
-//         debug!("creating grafana ingress");
-//         let grafana_ingress = self.build_grafana_ingress(ns).await;
-//
-//         grafana_ingress
-//             .interpret(&Inventory::empty(), self)
-//             .await
-//             .map_err(|e| PreparationError::new(e.to_string()))?;
-//
-//         Ok(PreparationOutcome::Success {
-//             details: "Installed grafana composants".to_string(),
-//         })
-//     }
-// }

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

@@ -1,3 +1,2 @@
 pub mod grafana;
-pub mod grafana_alerting_score;
+pub mod helm;
-pub mod k8s;

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

@@ -1,17 +1,91 @@
+use std::sync::Arc;
+
+use async_trait::async_trait;
 use kube::CustomResource;
 use schemars::JsonSchema;
 use serde::{Deserialize, Serialize};
 
-#[derive(CustomResource, Serialize, Deserialize, Default, Debug, Clone, JsonSchema)]
+use crate::{
+    interpret::InterpretError,
+    inventory::Inventory,
+    modules::{
+        monitoring::{
+            grafana::grafana::Grafana, kube_prometheus::crd::service_monitor::ServiceMonitor,
+        },
+        prometheus::prometheus::PrometheusMonitoring,
+    },
+    topology::{
+        K8sclient, Topology,
+        installable::Installable,
+        oberservability::monitoring::{AlertReceiver, AlertSender, ScrapeTarget},
+    },
+};
+use harmony_k8s::K8sClient;
+
+#[derive(CustomResource, Serialize, Deserialize, Debug, Clone, JsonSchema)]
 #[kube(
     group = "monitoring.coreos.com",
-    version = "v1",
+    version = "v1alpha1",
     kind = "AlertmanagerConfig",
     plural = "alertmanagerconfigs",
-    namespaced,
+    namespaced
-    derive = "Default"
 )]
 pub struct AlertmanagerConfigSpec {
     #[serde(flatten)]
     pub data: serde_json::Value,
 }
+
+#[derive(Debug, Clone, Serialize)]
+pub struct CRDPrometheus {
+    pub namespace: String,
+    pub client: Arc<K8sClient>,
+    pub service_monitor: Vec<ServiceMonitor>,
+}
+
+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 Clone for Box<dyn ScrapeTarget<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!()
+    }
+}
+
+#[async_trait]
+impl<T: Topology + K8sclient + PrometheusMonitoring<CRDPrometheus> + Grafana> Installable<T>
+    for CRDPrometheus
+{
+    async fn configure(&self, inventory: &Inventory, topology: &T) -> Result<(), InterpretError> {
+        topology.ensure_grafana_operator(inventory).await?;
+        topology.ensure_prometheus_operator(self, inventory).await?;
+        Ok(())
+    }
+
+    async fn ensure_installed(
+        &self,
+        inventory: &Inventory,
+        topology: &T,
+    ) -> Result<(), InterpretError> {
+        topology.install_grafana().await?;
+        topology.install_prometheus(&self, inventory, None).await?;
+        Ok(())
+    }
+}

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

@@ -1,4 +1,4 @@
-use crate::modules::monitoring::alert_rule::alerts::k8s::{
+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,

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

@@ -4,7 +4,7 @@ use kube::CustomResource;
 use schemars::JsonSchema;
 use serde::{Deserialize, Serialize};
 
-use crate::modules::monitoring::kube_prometheus::crd::crd_prometheuses::LabelSelector;
+use super::crd_prometheuses::LabelSelector;
 
 #[derive(CustomResource, Serialize, Deserialize, Debug, Clone, JsonSchema)]
 #[kube(

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

@@ -6,14 +6,13 @@ use serde::{Deserialize, Serialize};
 
 use crate::modules::monitoring::alert_rule::prometheus_alert_rule::PrometheusAlertRule;
 
-#[derive(CustomResource, Default, Debug, Serialize, Deserialize, Clone, JsonSchema)]
+#[derive(CustomResource, Debug, Serialize, Deserialize, Clone, JsonSchema)]
 #[kube(
     group = "monitoring.coreos.com",
     version = "v1",
     kind = "PrometheusRule",
     plural = "prometheusrules",
-    namespaced,
+    namespaced
-    derive = "Default"
 )]
 #[serde(rename_all = "camelCase")]
 pub struct PrometheusRuleSpec {

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

@@ -1,18 +1,23 @@
-use std::collections::BTreeMap;
+use std::net::IpAddr;
 
+use async_trait::async_trait;
 use kube::CustomResource;
 use schemars::JsonSchema;
 use serde::{Deserialize, Serialize};
 
-use crate::modules::monitoring::kube_prometheus::crd::crd_prometheuses::LabelSelector;
+use crate::{
+    modules::monitoring::kube_prometheus::crd::{
+        crd_alertmanager_config::CRDPrometheus, crd_prometheuses::LabelSelector,
+    },
+    topology::oberservability::monitoring::ScrapeTarget,
+};
 
-#[derive(CustomResource, Default, Serialize, Deserialize, Debug, Clone, JsonSchema)]
+#[derive(CustomResource, Serialize, Deserialize, Debug, Clone, JsonSchema)]
 #[kube(
     group = "monitoring.coreos.com",
     version = "v1alpha1",
     kind = "ScrapeConfig",
     plural = "scrapeconfigs",
-    derive = "Default",
     namespaced
 )]
 #[serde(rename_all = "camelCase")]
@@ -65,8 +70,8 @@ pub struct ScrapeConfigSpec {
 #[serde(rename_all = "camelCase")]
 pub struct StaticConfig {
     pub targets: Vec<String>,
-    #[serde(skip_serializing_if = "Option::is_none")]
+
-    pub labels: Option<BTreeMap<String, String>>,
+    pub labels: Option<LabelSelector>,
 }
 
 /// Relabeling configuration for target or metric relabeling.

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

@@ -1,9 +1,22 @@
 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 crd_scrape_config;
+pub mod grafana_default_dashboard;
+pub mod grafana_operator;
 pub mod prometheus_operator;
+pub mod rhob_alertmanager_config;
+pub mod rhob_alertmanagers;
+pub mod rhob_cluster_observability_operator;
+pub mod rhob_default_rules;
+pub mod rhob_grafana;
+pub mod rhob_monitoring_stack;
+pub mod rhob_prometheus_rules;
+pub mod rhob_prometheuses;
+pub mod rhob_role;
+pub mod rhob_service_monitor;
 pub mod role;
 pub mod service_monitor;

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

@@ -0,0 +1,48 @@
+use std::sync::Arc;
+
+use kube::CustomResource;
+use schemars::JsonSchema;
+use serde::{Deserialize, Serialize};
+
+use crate::topology::oberservability::monitoring::{AlertReceiver, AlertSender};
+use harmony_k8s::K8sClient;
+
+#[derive(CustomResource, Serialize, Deserialize, Debug, Clone, JsonSchema)]
+#[kube(
+    group = "monitoring.rhobs",
+    version = "v1alpha1",
+    kind = "AlertmanagerConfig",
+    plural = "alertmanagerconfigs",
+    namespaced
+)]
+pub struct AlertmanagerConfigSpec {
+    #[serde(flatten)]
+    pub data: serde_json::Value,
+}
+
+#[derive(Debug, Clone, Serialize)]
+pub struct RHOBObservability {
+    pub namespace: String,
+    pub client: Arc<K8sClient>,
+}
+
+impl AlertSender for RHOBObservability {
+    fn name(&self) -> String {
+        "RHOBAlertManager".to_string()
+    }
+}
+
+impl Clone for Box<dyn AlertReceiver<RHOBObservability>> {
+    fn clone(&self) -> Self {
+        self.clone_box()
+    }
+}
+
+impl Serialize for Box<dyn AlertReceiver<RHOBObservability>> {
+    fn serialize<S>(&self, _serializer: S) -> Result<S::Ok, S::Error>
+    where
+        S: serde::Serializer,
+    {
+        todo!()
+    }
+}

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

@@ -2,7 +2,7 @@ use kube::CustomResource;
 use schemars::JsonSchema;
 use serde::{Deserialize, Serialize};
 
-use crate::modules::monitoring::red_hat_cluster_observability::crd::rhob_prometheuses::LabelSelector;
+use super::crd_prometheuses::LabelSelector;
 
 /// Rust CRD for `Alertmanager` from Prometheus Operator
 #[derive(CustomResource, Serialize, Deserialize, Debug, Clone, JsonSchema)]

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

@@ -0,0 +1,22 @@
+use std::str::FromStr;
+
+use non_blank_string_rs::NonBlankString;
+
+use crate::modules::helm::chart::HelmChartScore;
+//TODO package chart or something for COO okd
+pub fn rhob_cluster_observability_operator() -> HelmChartScore {
+    HelmChartScore {
+        namespace: None,
+        release_name: NonBlankString::from_str("").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/rhob_default_rules.rs

@@ -1,11 +1,11 @@
-use crate::modules::monitoring::{
+use crate::modules::{
-    alert_rule::alerts::k8s::{
+    monitoring::kube_prometheus::crd::rhob_prometheus_rules::Rule,
+    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,
     },
-    red_hat_cluster_observability::crd::rhob_prometheus_rules::Rule,
 };
 
 pub fn build_default_application_rules() -> Vec<Rule> {

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

@@ -4,7 +4,7 @@ use kube::CustomResource;
 use schemars::JsonSchema;
 use serde::{Deserialize, Serialize};
 
-use crate::modules::monitoring::red_hat_cluster_observability::crd::rhob_prometheuses::LabelSelector;
+use crate::modules::monitoring::kube_prometheus::crd::rhob_prometheuses::LabelSelector;
 
 #[derive(CustomResource, Serialize, Deserialize, Debug, Clone, JsonSchema)]
 #[kube(

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

@@ -2,7 +2,7 @@ use kube::CustomResource;
 use schemars::JsonSchema;
 use serde::{Deserialize, Serialize};
 
-use crate::modules::monitoring::red_hat_cluster_observability::crd::rhob_prometheuses::LabelSelector;
+use crate::modules::monitoring::kube_prometheus::crd::rhob_prometheuses::LabelSelector;
 
 /// MonitoringStack CRD for monitoring.rhobs/v1alpha1
 #[derive(CustomResource, Serialize, Deserialize, Debug, Clone, JsonSchema)]
@@ -11,8 +11,7 @@ use crate::modules::monitoring::red_hat_cluster_observability::crd::rhob_prometh
     version = "v1alpha1",
     kind = "MonitoringStack",
     plural = "monitoringstacks",
-    namespaced,
+    namespaced
-    derive = "Default"
 )]
 #[serde(rename_all = "camelCase")]
 pub struct MonitoringStackSpec {

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

@@ -4,6 +4,8 @@ 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.rhobs",
@@ -91,14 +93,6 @@ pub struct LabelSelectorRequirement {
     pub values: Vec<String>,
 }
 
-#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema)]
-pub enum Operator {
-    In,
-    NotIn,
-    Exists,
-    DoesNotExist,
-}
-
 impl Default for PrometheusSpec {
     fn default() -> Self {
         PrometheusSpec {

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

@@ -1,13 +1,20 @@
 use super::config::KubePrometheusConfig;
+use log::debug;
 use non_blank_string_rs::NonBlankString;
+use serde_yaml::{Mapping, Value};
 use std::{
+    collections::BTreeMap,
     str::FromStr,
     sync::{Arc, Mutex},
 };
 
 use crate::modules::{
     helm::chart::HelmChartScore,
-    monitoring::kube_prometheus::types::{Limits, Requests, Resources},
+    monitoring::kube_prometheus::types::{
+        AlertGroup, AlertManager, AlertManagerAdditionalPromRules, AlertManagerConfig,
+        AlertManagerConfigSelector, AlertManagerRoute, AlertManagerSpec, AlertManagerValues,
+        ConfigReloader, Limits, PrometheusConfig, Requests, Resources,
+    },
 };
 
 pub fn kube_prometheus_helm_chart_score(
@@ -59,7 +66,7 @@ pub fn kube_prometheus_helm_chart_score(
     }
     let _resource_section = resource_block(&resource_limit, 2);
 
-    let values = format!(
+    let mut values = format!(
         r#"
 global:
   rbac:
@@ -274,6 +281,131 @@ prometheusOperator:
 "#,
     );
 
+    let prometheus_config =
+        crate::modules::monitoring::kube_prometheus::types::PrometheusConfigValues {
+            prometheus: PrometheusConfig {
+                prometheus: bool::from_str(prometheus.as_str()).expect("couldn't parse bool"),
+                additional_service_monitors: config.additional_service_monitors.clone(),
+            },
+        };
+    let prometheus_config_yaml =
+        serde_yaml::to_string(&prometheus_config).expect("Failed to serialize YAML");
+
+    debug!(
+        "serialized prometheus config: \n {:#}",
+        prometheus_config_yaml
+    );
+    values.push_str(&prometheus_config_yaml);
+
+    // add required null receiver for prometheus alert manager
+    let mut null_receiver = Mapping::new();
+    null_receiver.insert(
+        Value::String("receiver".to_string()),
+        Value::String("null".to_string()),
+    );
+    null_receiver.insert(
+        Value::String("matchers".to_string()),
+        Value::Sequence(vec![Value::String("alertname!=Watchdog".to_string())]),
+    );
+    null_receiver.insert(Value::String("continue".to_string()), Value::Bool(true));
+
+    //add alert channels
+    let mut alert_manager_channel_config = AlertManagerConfig {
+        global: Mapping::new(),
+        route: AlertManagerRoute {
+            routes: vec![Value::Mapping(null_receiver)],
+        },
+        receivers: vec![serde_yaml::from_str("name: 'null'").unwrap()],
+    };
+    for receiver in config.alert_receiver_configs.iter() {
+        if let Some(global) = receiver.channel_global_config.clone() {
+            alert_manager_channel_config
+                .global
+                .insert(global.0, global.1);
+        }
+        alert_manager_channel_config
+            .route
+            .routes
+            .push(receiver.channel_route.clone());
+        alert_manager_channel_config
+            .receivers
+            .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,
+            config: alert_manager_channel_config,
+            alertmanager_spec: AlertManagerSpec {
+                resources: Resources {
+                    limits: Limits {
+                        memory: "100Mi".to_string(),
+                        cpu: "100m".to_string(),
+                    },
+                    requests: Requests {
+                        memory: "100Mi".to_string(),
+                        cpu: "100m".to_string(),
+                    },
+                },
+                alert_manager_config_selector,
+                replicas: 2,
+            },
+            init_config_reloader: ConfigReloader {
+                resources: Resources {
+                    limits: Limits {
+                        memory: "100Mi".to_string(),
+                        cpu: "100m".to_string(),
+                    },
+                    requests: Requests {
+                        memory: "100Mi".to_string(),
+                        cpu: "100m".to_string(),
+                    },
+                },
+            },
+        },
+    };
+
+    let alert_manager_yaml =
+        serde_yaml::to_string(&alert_manager_values).expect("Failed to serialize YAML");
+    debug!("serialized alert manager: \n {:#}", alert_manager_yaml);
+    values.push_str(&alert_manager_yaml);
+
+    //format alert manager additional rules for helm chart
+    let mut merged_rules: BTreeMap<String, AlertGroup> = BTreeMap::new();
+
+    for additional_rule in config.alert_rules.clone() {
+        for (key, group) in additional_rule.rules {
+            merged_rules.insert(key, group);
+        }
+    }
+
+    let merged_rules = AlertManagerAdditionalPromRules {
+        rules: merged_rules,
+    };
+
+    let mut alert_manager_additional_rules = serde_yaml::Mapping::new();
+    let rules_value = serde_yaml::to_value(merged_rules).unwrap();
+
+    alert_manager_additional_rules.insert(
+        serde_yaml::Value::String("additionalPrometheusRulesMap".to_string()),
+        rules_value,
+    );
+
+    let alert_manager_additional_rules_yaml =
+        serde_yaml::to_string(&alert_manager_additional_rules).expect("Failed to serialize YAML");
+    debug!(
+        "alert_rules_yaml:\n{:#}",
+        alert_manager_additional_rules_yaml
+    );
+
+    values.push_str(&alert_manager_additional_rules_yaml);
+    debug!("full values.yaml: \n {:#}", values);
+
     HelmChartScore {
         namespace: Some(NonBlankString::from_str(&config.namespace.clone().unwrap()).unwrap()),
         release_name: NonBlankString::from_str("kube-prometheus").unwrap(),

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

@@ -2,41 +2,36 @@ use std::sync::{Arc, Mutex};
 
 use serde::Serialize;
 
-use super::helm::config::KubePrometheusConfig;
+use super::{helm::config::KubePrometheusConfig, prometheus::KubePrometheus};
 use crate::{
-    modules::monitoring::kube_prometheus::{KubePrometheus, types::ServiceMonitor},
+    modules::monitoring::kube_prometheus::types::ServiceMonitor,
     score::Score,
     topology::{
-        Topology,
+        HelmCommand, Topology,
-        monitoring::{AlertReceiver, AlertRule, AlertingInterpret, Observability, ScrapeTarget},
+        oberservability::monitoring::{AlertReceiver, AlertRule, AlertingInterpret},
+        tenant::TenantManager,
     },
 };
 
-//TODO untested
 #[derive(Clone, Debug, Serialize)]
-pub struct KubePrometheusAlertingScore {
+pub struct HelmPrometheusAlertingScore {
     pub receivers: Vec<Box<dyn AlertReceiver<KubePrometheus>>>,
     pub rules: Vec<Box<dyn AlertRule<KubePrometheus>>>,
-    pub scrape_targets: Option<Vec<Box<dyn ScrapeTarget<KubePrometheus>>>>,
     pub service_monitors: Vec<ServiceMonitor>,
-    pub config: Arc<Mutex<KubePrometheusConfig>>,
 }
 
-impl<T: Topology + Observability<KubePrometheus>> Score<T> for KubePrometheusAlertingScore {
+impl<T: Topology + HelmCommand + TenantManager> Score<T> for HelmPrometheusAlertingScore {
     fn create_interpret(&self) -> Box<dyn crate::interpret::Interpret<T>> {
-        //TODO test that additional service monitor is added
+        let config = Arc::new(Mutex::new(KubePrometheusConfig::new()));
-        self.config
+        config
             .try_lock()
             .expect("couldn't lock config")
             .additional_service_monitors = self.service_monitors.clone();
-
         Box::new(AlertingInterpret {
-            sender: KubePrometheus {
+            sender: KubePrometheus { config },
-                config: self.config.clone(),
-            },
             receivers: self.receivers.clone(),
             rules: self.rules.clone(),
-            scrape_targets: self.scrape_targets.clone(),
+            scrape_targets: None,
         })
     }
     fn name(&self) -> String {

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

@@ -1,71 +1,5 @@
-use std::sync::{Arc, Mutex};
-
-use async_trait::async_trait;
-use serde::Serialize;
-
-use crate::{
-    modules::monitoring::kube_prometheus::helm::config::KubePrometheusConfig,
-    topology::monitoring::{AlertReceiver, AlertRule, AlertSender, ScrapeTarget},
-};
-
 pub mod crd;
 pub mod helm;
-pub mod kube_prometheus_alerting_score;
+pub mod helm_prometheus_alert_score;
-pub mod score_kube_prometheus_alert_receivers;
+pub mod prometheus;
-pub mod score_kube_prometheus_ensure_ready;
-pub mod score_kube_prometheus_rule;
-pub mod score_kube_prometheus_scrape_target;
 pub mod types;
-
-impl Serialize for Box<dyn ScrapeTarget<KubePrometheus>> {
-    fn serialize<S>(&self, _serializer: S) -> Result<S::Ok, S::Error>
-    where
-        S: serde::Serializer,
-    {
-        todo!()
-    }
-}
-
-#[async_trait]
-impl AlertSender for KubePrometheus {
-    fn name(&self) -> String {
-        "HelmKubePrometheus".to_string()
-    }
-}
-
-#[derive(Clone, Debug, Serialize)]
-pub struct KubePrometheus {
-    pub config: Arc<Mutex<KubePrometheusConfig>>,
-}
-
-impl Default for KubePrometheus {
-    fn default() -> Self {
-        Self::new()
-    }
-}
-
-impl KubePrometheus {
-    pub fn new() -> Self {
-        Self {
-            config: Arc::new(Mutex::new(KubePrometheusConfig::new())),
-        }
-    }
-}
-
-impl Serialize for Box<dyn AlertReceiver<KubePrometheus>> {
-    fn serialize<S>(&self, _serializer: S) -> Result<S::Ok, S::Error>
-    where
-        S: serde::Serializer,
-    {
-        todo!()
-    }
-}
-
-impl Serialize for Box<dyn AlertRule<KubePrometheus>> {
-    fn serialize<S>(&self, _serializer: S) -> Result<S::Ok, S::Error>
-    where
-        S: serde::Serializer,
-    {
-        todo!()
-    }
-}

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

@@ -0,0 +1,167 @@
+use std::sync::{Arc, Mutex};
+
+use async_trait::async_trait;
+use log::{debug, error};
+use serde::Serialize;
+
+use crate::{
+    interpret::{InterpretError, Outcome},
+    inventory::Inventory,
+    modules::monitoring::alert_rule::prometheus_alert_rule::AlertManagerRuleGroup,
+    score,
+    topology::{
+        HelmCommand, Topology,
+        installable::Installable,
+        oberservability::monitoring::{AlertReceiver, AlertRule, AlertSender},
+        tenant::TenantManager,
+    },
+};
+
+use score::Score;
+
+use super::{
+    helm::{
+        config::KubePrometheusConfig, kube_prometheus_helm_chart::kube_prometheus_helm_chart_score,
+    },
+    types::{AlertManagerAdditionalPromRules, AlertManagerChannelConfig},
+};
+
+#[async_trait]
+impl AlertSender for KubePrometheus {
+    fn name(&self) -> String {
+        "HelmKubePrometheus".to_string()
+    }
+}
+
+#[async_trait]
+impl<T: Topology + HelmCommand + TenantManager> Installable<T> for KubePrometheus {
+    async fn configure(&self, _inventory: &Inventory, topology: &T) -> Result<(), InterpretError> {
+        self.configure_with_topology(topology).await;
+        Ok(())
+    }
+
+    async fn ensure_installed(
+        &self,
+        inventory: &Inventory,
+        topology: &T,
+    ) -> Result<(), InterpretError> {
+        self.install_prometheus(inventory, topology).await?;
+        Ok(())
+    }
+}
+
+#[derive(Debug)]
+pub struct KubePrometheus {
+    pub config: Arc<Mutex<KubePrometheusConfig>>,
+}
+
+impl Default for KubePrometheus {
+    fn default() -> Self {
+        Self::new()
+    }
+}
+
+impl KubePrometheus {
+    pub fn new() -> Self {
+        Self {
+            config: Arc::new(Mutex::new(KubePrometheusConfig::new())),
+        }
+    }
+
+    pub async fn configure_with_topology<T: TenantManager>(&self, topology: &T) {
+        let ns = topology
+            .get_tenant_config()
+            .await
+            .map(|cfg| cfg.name.clone())
+            .unwrap_or_else(|| "monitoring".to_string());
+        error!("This must be refactored, see comments in pr #74");
+        debug!("NS: {}", ns);
+        self.config.lock().unwrap().namespace = Some(ns);
+    }
+
+    pub async fn install_receiver(
+        &self,
+        prometheus_receiver: &dyn KubePrometheusReceiver,
+    ) -> Result<Outcome, InterpretError> {
+        let prom_receiver = prometheus_receiver.configure_receiver().await;
+        debug!(
+            "adding alert receiver to prometheus config: {:#?}",
+            &prom_receiver
+        );
+        let mut config = self.config.lock().unwrap();
+
+        config.alert_receiver_configs.push(prom_receiver);
+        let prom_receiver_name = prometheus_receiver.name();
+        debug!("installed alert receiver {}", &prom_receiver_name);
+        Ok(Outcome::success(format!(
+            "Sucessfully installed receiver {}",
+            prom_receiver_name
+        )))
+    }
+
+    pub async fn install_rule(
+        &self,
+        prometheus_rule: &AlertManagerRuleGroup,
+    ) -> Result<Outcome, InterpretError> {
+        let prometheus_rule = prometheus_rule.configure_rule().await;
+        let mut config = self.config.lock().unwrap();
+
+        config.alert_rules.push(prometheus_rule.clone());
+        Ok(Outcome::success(format!(
+            "Successfully installed alert rule: {:#?},",
+            prometheus_rule
+        )))
+    }
+
+    pub async fn install_prometheus<T: Topology + HelmCommand + Send + Sync>(
+        &self,
+        inventory: &Inventory,
+        topology: &T,
+    ) -> Result<Outcome, InterpretError> {
+        kube_prometheus_helm_chart_score(self.config.clone())
+            .interpret(inventory, topology)
+            .await
+    }
+}
+
+#[async_trait]
+pub trait KubePrometheusReceiver: Send + Sync + std::fmt::Debug {
+    fn name(&self) -> String;
+    async fn configure_receiver(&self) -> AlertManagerChannelConfig;
+}
+
+impl Serialize for Box<dyn AlertReceiver<KubePrometheus>> {
+    fn serialize<S>(&self, _serializer: S) -> Result<S::Ok, S::Error>
+    where
+        S: serde::Serializer,
+    {
+        todo!()
+    }
+}
+
+impl Clone for Box<dyn AlertReceiver<KubePrometheus>> {
+    fn clone(&self) -> Self {
+        self.clone_box()
+    }
+}
+
+#[async_trait]
+pub trait KubePrometheusRule: Send + Sync + std::fmt::Debug {
+    fn name(&self) -> String;
+    async fn configure_rule(&self) -> AlertManagerAdditionalPromRules;
+}
+
+impl Serialize for Box<dyn AlertRule<KubePrometheus>> {
+    fn serialize<S>(&self, _serializer: S) -> Result<S::Ok, S::Error>
+    where
+        S: serde::Serializer,
+    {
+        todo!()
+    }
+}
+
+impl Clone for Box<dyn AlertRule<KubePrometheus>> {
+    fn clone(&self) -> Self {
+        self.clone_box()
+    }
+}

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

@@ -1,61 +0,0 @@
-use kube::api::ObjectMeta;
-use serde::Serialize;
-
-use crate::{
-    interpret::Interpret,
-    modules::{
-        k8s::resource::K8sResourceScore,
-        monitoring::kube_prometheus::{
-            KubePrometheus,
-            crd::crd_alertmanager_config::{AlertmanagerConfig, AlertmanagerConfigSpec},
-        },
-    },
-    score::Score,
-    topology::{K8sclient, Topology, monitoring::AlertReceiver},
-};
-
-#[derive(Debug, Clone, Serialize)]
-pub struct KubePrometheusReceiverScore {
-    pub sender: KubePrometheus,
-    pub receiver: Box<dyn AlertReceiver<KubePrometheus>>,
-}
-
-impl<T: Topology + K8sclient> Score<T> for KubePrometheusReceiverScore {
-    fn name(&self) -> String {
-        "KubePrometheusReceiverScore".to_string()
-    }
-
-    fn create_interpret(&self) -> Box<dyn Interpret<T>> {
-        let name = self.receiver.name();
-        let namespace = self.sender.config.lock().unwrap().namespace.clone();
-        let install_plan = self.receiver.build().expect("failed to build install plan");
-
-        let route = install_plan.route.expect(&format!(
-            "failed to build route for receveiver {}",
-            name.clone()
-        ));
-
-        let route = serde_yaml::to_value(route).expect("failed to serialize route object to yaml");
-
-        let receiver = install_plan.receiver.expect(&format!(
-            "failed to build receiver path for receiver {}",
-            name.clone()
-        ));
-
-        let data = serde_json::json!({
-        "route": route,
-        "receivers": [receiver]
-        });
-
-        let alertmanager_config = AlertmanagerConfig {
-            metadata: ObjectMeta {
-                name: Some(name),
-                namespace: namespace.clone(),
-                ..Default::default()
-            },
-            spec: AlertmanagerConfigSpec { data: data },
-        };
-
-        K8sResourceScore::single(alertmanager_config, namespace).create_interpret()
-    }
-}

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

@@ -1,80 +0,0 @@
-use async_trait::async_trait;
-use harmony_types::id::Id;
-use serde::Serialize;
-
-use crate::{
-    data::Version,
-    interpret::{Interpret, InterpretError, InterpretName, InterpretStatus, Outcome},
-    inventory::Inventory,
-    modules::monitoring::kube_prometheus::KubePrometheus,
-    score::Score,
-    topology::{K8sclient, Topology},
-};
-
-#[derive(Clone, Debug, Serialize)]
-pub struct KubePrometheusEnsureReadyScore {
-    pub sender: KubePrometheus,
-}
-
-impl<T: Topology + K8sclient> Score<T> for KubePrometheusEnsureReadyScore {
-    fn name(&self) -> String {
-        "KubePrometheusEnsureReadyScore".to_string()
-    }
-
-    fn create_interpret(&self) -> Box<dyn Interpret<T>> {
-        Box::new(KubePrometheusEnsureReadyInterpret {
-            sender: self.sender.clone(),
-        })
-    }
-}
-
-#[derive(Clone, Debug, Serialize)]
-pub struct KubePrometheusEnsureReadyInterpret {
-    pub sender: KubePrometheus,
-}
-
-#[async_trait]
-impl<T: Topology + K8sclient> Interpret<T> for KubePrometheusEnsureReadyInterpret {
-    async fn execute(
-        &self,
-        _inventory: &Inventory,
-        topology: &T,
-    ) -> Result<Outcome, InterpretError> {
-        let client = topology.k8s_client().await?;
-        let namespace = self
-            .sender
-            .config
-            .lock()
-            .unwrap()
-            .namespace
-            .clone()
-            .unwrap_or("default".to_string());
-
-        let prometheus_name = "kube-prometheues-kube-prometheus-operator";
-
-        client
-            .wait_until_deployment_ready(prometheus_name, Some(&namespace), None)
-            .await?;
-
-        Ok(Outcome::success(format!(
-            "deployment: {} ready in ns: {}",
-            prometheus_name, namespace
-        )))
-    }
-
-    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!()
-    }
-}

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

@@ -1,46 +0,0 @@
-use kube::api::ObjectMeta;
-use serde::Serialize;
-
-use crate::{
-    interpret::Interpret,
-    modules::{
-        k8s::resource::K8sResourceScore,
-        monitoring::kube_prometheus::{
-            KubePrometheus,
-            crd::crd_prometheus_rules::{PrometheusRule, PrometheusRuleSpec, RuleGroup},
-        },
-    },
-    score::Score,
-    topology::{K8sclient, Topology, monitoring::AlertRule},
-};
-
-#[derive(Debug, Clone, Serialize)]
-pub struct KubePrometheusRuleScore {
-    pub sender: KubePrometheus,
-    pub rule: Box<dyn AlertRule<KubePrometheus>>,
-}
-
-impl<T: Topology + K8sclient> Score<T> for KubePrometheusRuleScore {
-    fn name(&self) -> String {
-        "KubePrometheusRuleScore".to_string()
-    }
-
-    fn create_interpret(&self) -> Box<dyn Interpret<T>> {
-        let name = self.rule.name();
-        let namespace = self.sender.config.lock().unwrap().namespace.clone();
-        let groups: Vec<RuleGroup> =
-            serde_json::from_value(self.rule.build_rule().expect("failed to build alert rule"))
-                .expect("failed to serialize rule group");
-
-        let prometheus_rule = PrometheusRule {
-            metadata: ObjectMeta {
-                name: Some(name.clone()),
-                namespace: namespace.clone(),
-                ..Default::default()
-            },
-
-            spec: PrometheusRuleSpec { groups },
-        };
-        K8sResourceScore::single(prometheus_rule, namespace).create_interpret()
-    }
-}

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

@@ -1,61 +0,0 @@
-use kube::api::ObjectMeta;
-use serde::Serialize;
-
-use crate::{
-    interpret::Interpret,
-    modules::{
-        k8s::resource::K8sResourceScore,
-        monitoring::kube_prometheus::{
-            KubePrometheus,
-            crd::crd_scrape_config::{ScrapeConfig, ScrapeConfigSpec, StaticConfig},
-        },
-    },
-    score::Score,
-    topology::{K8sclient, Topology, monitoring::ScrapeTarget},
-};
-
-#[derive(Debug, Clone, Serialize)]
-pub struct KubePrometheusScrapeTargetScore {
-    pub sender: KubePrometheus,
-    pub scrape_target: Box<dyn ScrapeTarget<KubePrometheus>>,
-}
-
-impl<T: Topology + K8sclient> Score<T> for KubePrometheusScrapeTargetScore {
-    fn name(&self) -> String {
-        "KubePrometheusScrapeTargetScore".to_string()
-    }
-
-    fn create_interpret(&self) -> Box<dyn Interpret<T>> {
-        let name = self.scrape_target.name();
-        let namespace = self.sender.config.lock().unwrap().namespace.clone();
-
-        let external_target = self
-            .scrape_target
-            .build_scrape_target()
-            .expect("failed to build external scrape target");
-
-        //TODO this may need to modified to include a scrapeConfigSelector label from the
-        //prometheus operator
-        let labels = external_target.labels;
-
-        let scrape_target = ScrapeConfig {
-            metadata: ObjectMeta {
-                name: Some(name.clone()),
-                namespace: namespace.clone(),
-                ..Default::default()
-            },
-            spec: ScrapeConfigSpec {
-                static_configs: Some(vec![StaticConfig {
-                    targets: vec![format!("{}:{}", external_target.ip, external_target.port)],
-                    labels,
-                }]),
-                metrics_path: external_target.path,
-                scrape_interval: external_target.interval,
-                job_name: Some(name),
-                ..Default::default()
-            },
-        };
-
-        K8sResourceScore::single(scrape_target, namespace).create_interpret()
-    }
-}

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

@@ -3,7 +3,7 @@ use std::collections::{BTreeMap, HashMap};
 use async_trait::async_trait;
 use schemars::JsonSchema;
 use serde::{Deserialize, Serialize};
-use serde_yaml::Value;
+use serde_yaml::{Mapping, Sequence, Value};
 
 use crate::modules::monitoring::alert_rule::prometheus_alert_rule::AlertManagerRuleGroup;
 
@@ -12,6 +12,36 @@ pub trait AlertChannelConfig {
     async fn get_config(&self) -> AlertManagerChannelConfig;
 }
 
+#[derive(Debug, Clone, Serialize)]
+pub struct AlertManagerValues {
+    pub alertmanager: AlertManager,
+}
+#[derive(Debug, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct AlertManager {
+    pub enabled: bool,
+    pub config: AlertManagerConfig,
+    pub alertmanager_spec: AlertManagerSpec,
+    pub init_config_reloader: ConfigReloader,
+}
+
+#[derive(Debug, Clone, Serialize)]
+pub struct ConfigReloader {
+    pub resources: Resources,
+}
+
+#[derive(Debug, Clone, Serialize)]
+pub struct AlertManagerConfig {
+    pub global: Mapping,
+    pub route: AlertManagerRoute,
+    pub receivers: Sequence,
+}
+
+#[derive(Debug, Clone, Serialize)]
+pub struct AlertManagerRoute {
+    pub routes: Sequence,
+}
+
 #[derive(Debug, Clone, Serialize)]
 pub struct AlertManagerChannelConfig {
     ///expecting an option that contains two values
@@ -22,6 +52,20 @@ pub struct AlertManagerChannelConfig {
     pub channel_receiver: Value,
 }
 
+#[derive(Debug, Clone, Serialize)]
+#[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)]
 pub struct Resources {
     pub limits: Limits,

harmony/src/modules/monitoring/mod.rs

@@ -6,5 +6,4 @@ pub mod kube_prometheus;
 pub mod ntfy;
 pub mod okd;
 pub mod prometheus;
-pub mod red_hat_cluster_observability;
 pub mod scrape_target;

harmony/src/modules/monitoring/okd/cluster_monitoring.rs

@@ -0,0 +1,270 @@
+use base64::prelude::*;
+
+use async_trait::async_trait;
+use harmony_types::id::Id;
+use kube::api::DynamicObject;
+use log::{debug, info, trace};
+use serde::Serialize;
+
+use crate::{
+    data::Version,
+    interpret::{Interpret, InterpretError, InterpretName, InterpretStatus, Outcome},
+    inventory::Inventory,
+    modules::monitoring::okd::OpenshiftClusterAlertSender,
+    score::Score,
+    topology::{K8sclient, Topology, oberservability::monitoring::AlertReceiver},
+};
+
+impl Clone for Box<dyn AlertReceiver<OpenshiftClusterAlertSender>> {
+    fn clone(&self) -> Self {
+        self.clone_box()
+    }
+}
+
+impl Serialize for Box<dyn AlertReceiver<OpenshiftClusterAlertSender>> {
+    fn serialize<S>(&self, _serializer: S) -> Result<S::Ok, S::Error>
+    where
+        S: serde::Serializer,
+    {
+        todo!()
+    }
+}
+
+#[derive(Debug, Clone, Serialize)]
+pub struct OpenshiftClusterAlertScore {
+    pub receivers: Vec<Box<dyn AlertReceiver<OpenshiftClusterAlertSender>>>,
+}
+
+impl<T: Topology + K8sclient> Score<T> for OpenshiftClusterAlertScore {
+    fn name(&self) -> String {
+        "ClusterAlertScore".to_string()
+    }
+
+    #[doc(hidden)]
+    fn create_interpret(&self) -> Box<dyn Interpret<T>> {
+        Box::new(OpenshiftClusterAlertInterpret {
+            receivers: self.receivers.clone(),
+        })
+    }
+}
+
+#[derive(Debug)]
+pub struct OpenshiftClusterAlertInterpret {
+    receivers: Vec<Box<dyn AlertReceiver<OpenshiftClusterAlertSender>>>,
+}
+
+#[async_trait]
+impl<T: Topology + K8sclient> Interpret<T> for OpenshiftClusterAlertInterpret {
+    async fn execute(
+        &self,
+        _inventory: &Inventory,
+        topology: &T,
+    ) -> Result<Outcome, InterpretError> {
+        let client = topology.k8s_client().await?;
+        let openshift_monitoring_namespace = "openshift-monitoring";
+
+        let mut alertmanager_main_secret: DynamicObject = client
+            .get_secret_json_value("alertmanager-main", Some(openshift_monitoring_namespace))
+            .await?;
+        trace!("Got secret {alertmanager_main_secret:#?}");
+
+        let data: &mut serde_json::Value = &mut alertmanager_main_secret.data;
+        trace!("Alertmanager-main secret data {data:#?}");
+        let data_obj = data
+            .get_mut("data")
+            .ok_or(InterpretError::new(
+                "Missing 'data' field in alertmanager-main secret.".to_string(),
+            ))?
+            .as_object_mut()
+            .ok_or(InterpretError::new(
+                "'data' field in alertmanager-main secret is expected to be an object ."
+                    .to_string(),
+            ))?;
+
+        let config_b64 = data_obj
+            .get("alertmanager.yaml")
+            .ok_or(InterpretError::new(
+                "Missing 'alertmanager.yaml' in alertmanager-main secret data".to_string(),
+            ))?
+            .as_str()
+            .unwrap_or("");
+        trace!("Config base64 {config_b64}");
+
+        let config_bytes = BASE64_STANDARD.decode(config_b64).unwrap_or_default();
+
+        let mut am_config: serde_yaml::Value =
+            serde_yaml::from_str(&String::from_utf8(config_bytes).unwrap_or_default())
+                .unwrap_or_default();
+
+        debug!("Current alertmanager config {am_config:#?}");
+
+        let existing_receivers_sequence = if let Some(receivers) = am_config.get_mut("receivers") {
+            match receivers.as_sequence_mut() {
+                Some(seq) => seq,
+                None => {
+                    return Err(InterpretError::new(format!(
+                        "Expected alertmanager config receivers to be a sequence, got {:?}",
+                        receivers
+                    )));
+                }
+            }
+        } else {
+            &mut serde_yaml::Sequence::default()
+        };
+
+        let mut additional_resources = vec![];
+
+        for custom_receiver in &self.receivers {
+            let name = custom_receiver.name();
+            let alertmanager_receiver = custom_receiver.as_alertmanager_receiver()?;
+
+            let receiver_json_value = alertmanager_receiver.receiver_config;
+
+            let receiver_yaml_string =
+                serde_json::to_string(&receiver_json_value).map_err(|e| {
+                    InterpretError::new(format!("Failed to serialize receiver config: {}", e))
+                })?;
+
+            let receiver_yaml_value: serde_yaml::Value =
+                serde_yaml::from_str(&receiver_yaml_string).map_err(|e| {
+                    InterpretError::new(format!("Failed to parse receiver config as YAML: {}", e))
+                })?;
+
+            if let Some(idx) = existing_receivers_sequence.iter().position(|r| {
+                r.get("name")
+                    .and_then(|n| n.as_str())
+                    .map_or(false, |n| n == name)
+            }) {
+                info!("Replacing existing AlertManager receiver: {}", name);
+                existing_receivers_sequence[idx] = receiver_yaml_value;
+            } else {
+                debug!("Adding new AlertManager receiver: {}", name);
+                existing_receivers_sequence.push(receiver_yaml_value);
+            }
+
+            additional_resources.push(alertmanager_receiver.additional_ressources);
+        }
+
+        let existing_route_mapping = if let Some(route) = am_config.get_mut("route") {
+            match route.as_mapping_mut() {
+                Some(map) => map,
+                None => {
+                    return Err(InterpretError::new(format!(
+                        "Expected alertmanager config route to be a mapping, got {:?}",
+                        route
+                    )));
+                }
+            }
+        } else {
+            &mut serde_yaml::Mapping::default()
+        };
+
+        let existing_route_sequence = if let Some(routes) = existing_route_mapping.get_mut("routes")
+        {
+            match routes.as_sequence_mut() {
+                Some(seq) => seq,
+                None => {
+                    return Err(InterpretError::new(format!(
+                        "Expected alertmanager config routes to be a sequence, got {:?}",
+                        routes
+                    )));
+                }
+            }
+        } else {
+            &mut serde_yaml::Sequence::default()
+        };
+
+        for custom_receiver in &self.receivers {
+            let name = custom_receiver.name();
+            let alertmanager_receiver = custom_receiver.as_alertmanager_receiver()?;
+
+            let route_json_value = alertmanager_receiver.route_config;
+            let route_yaml_string = serde_json::to_string(&route_json_value).map_err(|e| {
+                InterpretError::new(format!("Failed to serialize route config: {}", e))
+            })?;
+
+            let route_yaml_value: serde_yaml::Value = serde_yaml::from_str(&route_yaml_string)
+                .map_err(|e| {
+                    InterpretError::new(format!("Failed to parse route config as YAML: {}", e))
+                })?;
+
+            if let Some(idy) = existing_route_sequence.iter().position(|r| {
+                r.get("receiver")
+                    .and_then(|n| n.as_str())
+                    .map_or(false, |n| n == name)
+            }) {
+                info!("Replacing existing AlertManager receiver: {}", name);
+                existing_route_sequence[idy] = route_yaml_value;
+            } else {
+                debug!("Adding new AlertManager receiver: {}", name);
+                existing_route_sequence.push(route_yaml_value);
+            }
+        }
+        debug!("Current alertmanager config {am_config:#?}");
+        // TODO
+        // - save new version of alertmanager config
+        // - write additional ressources to the cluster
+        let am_config = serde_yaml::to_string(&am_config).map_err(|e| {
+            InterpretError::new(format!(
+                "Failed to serialize new alertmanager config to string : {e}"
+            ))
+        })?;
+
+        let mut am_config_b64 = String::new();
+        BASE64_STANDARD.encode_string(am_config, &mut am_config_b64);
+
+        // TODO put update configmap value and save new value
+        data_obj.insert(
+            "alertmanager.yaml".to_string(),
+            serde_json::Value::String(am_config_b64),
+        );
+
+        // https://kubernetes.io/docs/reference/using-api/server-side-apply/#field-management
+        alertmanager_main_secret.metadata.managed_fields = None;
+
+        trace!("Applying new alertmanager_main_secret {alertmanager_main_secret:#?}");
+        client
+            .apply_dynamic(
+                &alertmanager_main_secret,
+                Some(openshift_monitoring_namespace),
+                true,
+            )
+            .await?;
+
+        let additional_resources = additional_resources.concat();
+        trace!("Applying additional ressources for alert receivers {additional_resources:#?}");
+        client
+            .apply_dynamic_many(
+                &additional_resources,
+                Some(openshift_monitoring_namespace),
+                true,
+            )
+            .await?;
+
+        Ok(Outcome::success(format!(
+            "Successfully configured {} cluster alert receivers: {}",
+            self.receivers.len(),
+            self.receivers
+                .iter()
+                .map(|r| r.name())
+                .collect::<Vec<_>>()
+                .join(", ")
+        )))
+    }
+
+    fn get_name(&self) -> InterpretName {
+        InterpretName::Custom("OpenshiftClusterAlertInterpret")
+    }
+
+    fn get_version(&self) -> Version {
+        todo!()
+    }
+
+    fn get_status(&self) -> InterpretStatus {
+        todo!()
+    }
+
+    fn get_children(&self) -> Vec<Id> {
+        todo!()
+    }
+}

harmony/src/modules/monitoring/okd/crd/alerting_rules.rs

@@ -1,58 +0,0 @@
-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, Default)]
-#[kube(
-    group = "monitoring.openshift.io",
-    version = "v1",
-    kind = "AlertingRule",
-    plural = "alertingrules",
-    namespaced,
-    derive = "Default"
-)]
-#[serde(rename_all = "camelCase")]
-pub struct AlertingRuleSpec {
-    pub groups: serde_json::Value,
-}
-
-#[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/okd/crd/mod.rs

@@ -1,3 +0,0 @@
-pub mod alerting_rules;
-pub mod scrape_target;
-pub mod service_monitor;

harmony/src/modules/monitoring/okd/crd/scrape_target.rs

@@ -1,72 +0,0 @@
-use kube::CustomResource;
-use schemars::JsonSchema;
-use serde::{Deserialize, Serialize};
-use std::collections::BTreeMap;
-
-#[derive(CustomResource, Debug, Serialize, Deserialize, Clone, JsonSchema, Default)]
-#[kube(
-    group = "monitoring.coreos.com",
-    version = "v1alpha1",
-    kind = "ScrapeConfig",
-    plural = "scrapeconfigs",
-    namespaced,
-    derive = "Default"
-)]
-#[serde(rename_all = "camelCase")]
-pub struct ScrapeConfigSpec {
-    #[serde(default, skip_serializing_if = "Option::is_none")]
-    pub job_name: Option<String>,
-
-    #[serde(default, skip_serializing_if = "Option::is_none")]
-    pub metrics_path: Option<String>,
-
-    #[serde(default, skip_serializing_if = "Option::is_none")]
-    pub scrape_interval: Option<String>,
-
-    #[serde(default, skip_serializing_if = "Option::is_none")]
-    pub scrape_timeout: Option<String>,
-
-    #[serde(default, skip_serializing_if = "Option::is_none")]
-    pub scheme: Option<String>,
-
-    #[serde(default, skip_serializing_if = "Option::is_none")]
-    pub static_configs: Option<Vec<StaticConfig>>,
-
-    #[serde(default, skip_serializing_if = "Option::is_none")]
-    pub relabelings: Option<Vec<RelabelConfig>>,
-
-    #[serde(default, skip_serializing_if = "Option::is_none")]
-    pub metric_relabelings: Option<Vec<RelabelConfig>>,
-}
-
-#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema, Default)]
-#[serde(rename_all = "camelCase")]
-pub struct StaticConfig {
-    /// targets: ["host:port"]
-    pub targets: Vec<String>,
-
-    #[serde(default, skip_serializing_if = "Option::is_none")]
-    pub labels: Option<BTreeMap<String, String>>,
-}
-
-#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema, Default)]
-#[serde(rename_all = "camelCase")]
-pub struct RelabelConfig {
-    #[serde(default, skip_serializing_if = "Option::is_none")]
-    pub source_labels: Option<Vec<String>>,
-
-    #[serde(default, skip_serializing_if = "Option::is_none")]
-    pub separator: Option<String>,
-
-    #[serde(default, skip_serializing_if = "Option::is_none")]
-    pub target_label: Option<String>,
-
-    #[serde(default, skip_serializing_if = "Option::is_none")]
-    pub replacement: Option<String>,
-
-    #[serde(default, skip_serializing_if = "Option::is_none")]
-    pub action: Option<String>,
-
-    #[serde(default, skip_serializing_if = "Option::is_none")]
-    pub regex: Option<String>,
-}

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

@@ -1,97 +0,0 @@
-use kube::CustomResource;
-use schemars::JsonSchema;
-use serde::{Deserialize, Serialize};
-use std::collections::BTreeMap;
-
-#[derive(CustomResource, Debug, Serialize, Deserialize, Clone, JsonSchema, Default)]
-#[kube(
-    group = "monitoring.coreos.com",
-    version = "v1",
-    kind = "ServiceMonitor",
-    plural = "servicemonitors",
-    namespaced,
-    derive = "Default"
-)]
-#[serde(rename_all = "camelCase")]
-pub struct ServiceMonitorSpec {
-    /// The label to use to retrieve the job name from.
-    #[serde(default, skip_serializing_if = "Option::is_none")]
-    pub job_label: Option<String>,
-
-    /// TargetLabels transfers labels on the Kubernetes Service onto the target.
-    #[serde(default, skip_serializing_if = "Option::is_none")]
-    pub target_labels: Option<Vec<String>>,
-
-    /// PodTargetLabels transfers labels on the Kubernetes Pod onto the target.
-    #[serde(default, skip_serializing_if = "Option::is_none")]
-    pub pod_target_labels: Option<Vec<String>>,
-
-    /// A list of endpoints allowed as part of this ServiceMonitor.
-    pub endpoints: Vec<Endpoint>,
-
-    /// Selector to select Endpoints objects.
-    pub selector: LabelSelector,
-
-    /// 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>,
-}
-
-#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema, Default)]
-#[serde(rename_all = "camelCase")]
-pub struct Endpoint {
-    /// Name of the service port this endpoint refers to.
-    #[serde(default, skip_serializing_if = "Option::is_none")]
-    pub port: Option<String>,
-
-    /// HTTP path to scrape for metrics.
-    #[serde(default, skip_serializing_if = "Option::is_none")]
-    pub path: Option<String>,
-
-    /// HTTP scheme to use for scraping.
-    #[serde(default, skip_serializing_if = "Option::is_none")]
-    pub scheme: Option<String>,
-
-    /// Interval at which metrics should be scraped.
-    #[serde(default, skip_serializing_if = "Option::is_none")]
-    pub interval: Option<String>,
-
-    /// Timeout after which the scrape is ended.
-    #[serde(default, skip_serializing_if = "Option::is_none")]
-    pub scrape_timeout: Option<String>,
-
-    /// HonorLabels chooses the metric's labels on collisions with target labels.
-    #[serde(default, skip_serializing_if = "Option::is_none")]
-    pub honor_labels: Option<bool>,
-}
-
-#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema, Default)]
-#[serde(rename_all = "camelCase")]
-pub struct LabelSelector {
-    #[serde(default, skip_serializing_if = "Option::is_none")]
-    pub match_labels: Option<BTreeMap<String, String>>,
-
-    #[serde(default, skip_serializing_if = "Option::is_none")]
-    pub match_expressions: Option<Vec<LabelSelectorRequirement>>,
-}
-
-#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema, Default)]
-#[serde(rename_all = "camelCase")]
-pub struct LabelSelectorRequirement {
-    pub key: String,
-    pub operator: String,
-    #[serde(default, skip_serializing_if = "Option::is_none")]
-    pub values: Option<Vec<String>>,
-}
-
-#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema, Default)]
-#[serde(rename_all = "camelCase")]
-pub struct NamespaceSelector {
-    /// Boolean describing whether all namespaces are selected in contrast to a list restricting them.
-    #[serde(default, skip_serializing_if = "Option::is_none")]
-    pub any: Option<bool>,
-
-    /// List of namespace names.
-    #[serde(default, skip_serializing_if = "Option::is_none")]
-    pub match_names: Option<Vec<String>>,
-}

harmony/src/modules/monitoring/okd/enable_user_workload.rs

@@ -0,0 +1,60 @@
+use crate::{
+    data::Version,
+    interpret::{Interpret, InterpretError, InterpretName, InterpretStatus, Outcome},
+    inventory::Inventory,
+    modules::monitoring::okd::config::Config,
+    score::Score,
+    topology::{K8sclient, Topology},
+};
+use async_trait::async_trait;
+use harmony_types::id::Id;
+use serde::Serialize;
+
+#[derive(Clone, Debug, Serialize)]
+pub struct OpenshiftUserWorkloadMonitoring {}
+
+impl<T: Topology + K8sclient> Score<T> for OpenshiftUserWorkloadMonitoring {
+    fn name(&self) -> String {
+        "OpenshiftUserWorkloadMonitoringScore".to_string()
+    }
+
+    fn create_interpret(&self) -> Box<dyn Interpret<T>> {
+        Box::new(OpenshiftUserWorkloadMonitoringInterpret {})
+    }
+}
+
+#[derive(Clone, Debug, Serialize)]
+pub struct OpenshiftUserWorkloadMonitoringInterpret {}
+
+#[async_trait]
+impl<T: Topology + K8sclient> Interpret<T> for OpenshiftUserWorkloadMonitoringInterpret {
+    async fn execute(
+        &self,
+        _inventory: &Inventory,
+        topology: &T,
+    ) -> Result<Outcome, InterpretError> {
+        let client = topology.k8s_client().await.unwrap();
+        Config::create_cluster_monitoring_config_cm(&client).await?;
+        Config::create_user_workload_monitoring_config_cm(&client).await?;
+        Config::verify_user_workload(&client).await?;
+        Ok(Outcome::success(
+            "successfully enabled user-workload-monitoring".to_string(),
+        ))
+    }
+
+    fn get_name(&self) -> InterpretName {
+        InterpretName::Custom("OpenshiftUserWorkloadMonitoring")
+    }
+
+    fn get_version(&self) -> Version {
+        todo!()
+    }
+
+    fn get_status(&self) -> InterpretStatus {
+        todo!()
+    }
+
+    fn get_children(&self) -> Vec<Id> {
+        todo!()
+    }
+}

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

@@ -1,17 +1,10 @@
-use serde::Serialize;
+use crate::topology::oberservability::monitoring::AlertSender;
 
-use crate::topology::monitoring::{AlertReceiver, AlertRule, AlertSender, ScrapeTarget};
+pub mod cluster_monitoring;
+pub(crate) mod config;
+pub mod enable_user_workload;
 
-pub mod crd;
+#[derive(Debug)]
-pub mod openshift_cluster_alerting_score;
-pub mod score_enable_cluster_monitoring;
-pub mod score_openshift_alert_rule;
-pub mod score_openshift_receiver;
-pub mod score_openshift_scrape_target;
-pub mod score_user_workload;
-pub mod score_verify_user_workload_monitoring;
-
-#[derive(Debug, Clone, Serialize)]
 pub struct OpenshiftClusterAlertSender;
 
 impl AlertSender for OpenshiftClusterAlertSender {
@@ -19,30 +12,3 @@ impl AlertSender for OpenshiftClusterAlertSender {
         "OpenshiftClusterAlertSender".to_string()
     }
 }
-
-impl Serialize for Box<dyn AlertReceiver<OpenshiftClusterAlertSender>> {
-    fn serialize<S>(&self, _serializer: S) -> Result<S::Ok, S::Error>
-    where
-        S: serde::Serializer,
-    {
-        todo!()
-    }
-}
-
-impl Serialize for Box<dyn AlertRule<OpenshiftClusterAlertSender>> {
-    fn serialize<S>(&self, _serializer: S) -> Result<S::Ok, S::Error>
-    where
-        S: serde::Serializer,
-    {
-        todo!()
-    }
-}
-
-impl Serialize for Box<dyn ScrapeTarget<OpenshiftClusterAlertSender>> {
-    fn serialize<S>(&self, _serializer: S) -> Result<S::Ok, S::Error>
-    where
-        S: serde::Serializer,
-    {
-        todo!()
-    }
-}

harmony/src/modules/monitoring/okd/openshift_cluster_alerting_score.rs

@@ -1,36 +0,0 @@
-use serde::Serialize;
-
-use crate::{
-    interpret::Interpret,
-    modules::monitoring::okd::OpenshiftClusterAlertSender,
-    score::Score,
-    topology::{
-        Topology,
-        monitoring::{AlertReceiver, AlertRule, AlertingInterpret, Observability, ScrapeTarget},
-    },
-};
-
-#[derive(Debug, Clone, Serialize)]
-pub struct OpenshiftClusterAlertScore {
-    pub sender: OpenshiftClusterAlertSender,
-    pub receivers: Vec<Box<dyn AlertReceiver<OpenshiftClusterAlertSender>>>,
-    pub rules: Vec<Box<dyn AlertRule<OpenshiftClusterAlertSender>>>,
-    pub scrape_targets: Option<Vec<Box<dyn ScrapeTarget<OpenshiftClusterAlertSender>>>>,
-}
-
-impl<T: Topology + Observability<OpenshiftClusterAlertSender>> Score<T>
-    for OpenshiftClusterAlertScore
-{
-    fn name(&self) -> String {
-        "OpenshiftClusterAlertScore".to_string()
-    }
-
-    fn create_interpret(&self) -> Box<dyn Interpret<T>> {
-        Box::new(AlertingInterpret {
-            sender: OpenshiftClusterAlertSender,
-            receivers: self.receivers.clone(),
-            rules: self.rules.clone(),
-            scrape_targets: self.scrape_targets.clone(),
-        })
-    }
-}

harmony/src/modules/monitoring/okd/score_enable_cluster_monitoring.rs

@@ -1,150 +0,0 @@
-use std::{collections::BTreeMap, sync::Arc};
-
-use async_trait::async_trait;
-use harmony_k8s::K8sClient;
-use harmony_types::id::Id;
-use k8s_openapi::api::core::v1::ConfigMap;
-use kube::api::{GroupVersionKind, ObjectMeta};
-use log::debug;
-use serde::Serialize;
-
-use crate::{
-    data::Version,
-    interpret::{Interpret, InterpretError, InterpretName, InterpretStatus, Outcome},
-    inventory::Inventory,
-    modules::k8s::resource::K8sResourceScore,
-    score::Score,
-    topology::{K8sclient, Topology},
-};
-
-#[derive(Clone, Debug, Serialize)]
-pub struct OpenshiftEnableClusterMonitoringScore {}
-
-impl<T: Topology + K8sclient> Score<T> for OpenshiftEnableClusterMonitoringScore {
-    fn name(&self) -> String {
-        "OpenshiftClusterMonitoringScore".to_string()
-    }
-
-    fn create_interpret(&self) -> Box<dyn Interpret<T>> {
-        Box::new(OpenshiftEnableClusterMonitoringInterpret {})
-    }
-}
-
-#[derive(Clone, Debug, Serialize)]
-pub struct OpenshiftEnableClusterMonitoringInterpret {}
-
-#[async_trait]
-impl<T: Topology + K8sclient> Interpret<T> for OpenshiftEnableClusterMonitoringInterpret {
-    async fn execute(
-        &self,
-        inventory: &Inventory,
-        topology: &T,
-    ) -> Result<Outcome, InterpretError> {
-        let namespace = "openshift-monitoring".to_string();
-        let name = "cluster-monitoring-config".to_string();
-        let client = topology.k8s_client().await?;
-        let enabled = self
-            .check_cluster_monitoring_enabled(client, &name, &namespace)
-            .await
-            .map_err(|e| InterpretError::new(e))?;
-
-        debug!("enabled {:#?}", enabled);
-
-        match enabled {
-            true => Ok(Outcome::success(
-                "Openshift Cluster Monitoring already enabled".to_string(),
-            )),
-            false => {
-                let mut data = BTreeMap::new();
-                data.insert(
-                    "config.yaml".to_string(),
-                    r#"
-enableUserWorkload: true
-alertmanagerMain:
-  enableUserAlertmanagerConfig: true
-"#
-                    .to_string(),
-                );
-
-                let cm = ConfigMap {
-                    metadata: ObjectMeta {
-                        name: Some(name),
-                        namespace: Some(namespace.clone()),
-                        ..Default::default()
-                    },
-                    data: Some(data),
-                    ..Default::default()
-                };
-                K8sResourceScore::single(cm, Some(namespace))
-                    .create_interpret()
-                    .execute(inventory, topology)
-                    .await?;
-
-                Ok(Outcome::success(
-                    "Successfully enabled Openshift Cluster Monitoring".to_string(),
-                ))
-            }
-        }
-    }
-
-    fn get_name(&self) -> InterpretName {
-        InterpretName::Custom("OpenshiftEnableClusterMonitoringInterpret")
-    }
-
-    fn get_version(&self) -> Version {
-        todo!()
-    }
-
-    fn get_status(&self) -> InterpretStatus {
-        todo!()
-    }
-
-    fn get_children(&self) -> Vec<Id> {
-        todo!()
-    }
-}
-
-impl OpenshiftEnableClusterMonitoringInterpret {
-    async fn check_cluster_monitoring_enabled(
-        &self,
-        client: Arc<K8sClient>,
-        name: &str,
-        namespace: &str,
-    ) -> Result<bool, String> {
-        let gvk = GroupVersionKind {
-            group: "".to_string(),
-            version: "v1".to_string(),
-            kind: "ConfigMap".to_string(),
-        };
-
-        let cm = match client
-            .get_resource_json_value(name, Some(namespace), &gvk)
-            .await
-        {
-            Ok(obj) => obj,
-            Err(_) => return Ok(false),
-        };
-
-        debug!("{:#?}", cm.data.pointer("/data/config.yaml"));
-        let config_yaml_str = match cm
-            .data
-            .pointer("/data/config.yaml")
-            .and_then(|v| v.as_str())
-        {
-            Some(s) => s,
-            None => return Ok(false),
-        };
-
-        debug!("{:#?}", config_yaml_str);
-        let parsed_config: serde_yaml::Value = serde_yaml::from_str(config_yaml_str)
-            .map_err(|e| format!("Failed to parse nested YAML: {}", e))?;
-
-        let enabled = parsed_config
-            .get("enableUserWorkload")
-            .and_then(|v| v.as_bool())
-            .unwrap_or(false);
-
-        debug!("{:#?}", enabled);
-        Ok(enabled)
-    }
-}

harmony/src/modules/monitoring/okd/score_openshift_alert_rule.rs

@@ -1,42 +0,0 @@
-use kube::api::ObjectMeta;
-use serde::Serialize;
-
-use crate::{
-    interpret::Interpret,
-    modules::{
-        k8s::resource::K8sResourceScore,
-        monitoring::okd::{
-            OpenshiftClusterAlertSender,
-            crd::alerting_rules::{AlertingRule, AlertingRuleSpec},
-        },
-    },
-    score::Score,
-    topology::{K8sclient, Topology, monitoring::AlertRule},
-};
-
-#[derive(Debug, Clone, Serialize)]
-pub struct OpenshiftAlertRuleScore {
-    pub rule: Box<dyn AlertRule<OpenshiftClusterAlertSender>>,
-}
-
-impl<T: Topology + K8sclient> Score<T> for OpenshiftAlertRuleScore {
-    fn name(&self) -> String {
-        "OpenshiftAlertingRuleScore".to_string()
-    }
-
-    fn create_interpret(&self) -> Box<dyn Interpret<T>> {
-        let namespace = "openshift-monitoring".to_string();
-        let alerting_rule = AlertingRule {
-            metadata: ObjectMeta {
-                name: Some(self.rule.name()),
-                namespace: Some(namespace.clone()),
-                ..Default::default()
-            },
-            spec: AlertingRuleSpec {
-                groups: self.rule.build_rule().unwrap(),
-            },
-        };
-
-        K8sResourceScore::single(alerting_rule, Some(namespace)).create_interpret()
-    }
-}

harmony/src/modules/monitoring/okd/score_openshift_receiver.rs

@@ -1,213 +0,0 @@
-use async_trait::async_trait;
-use base64::{Engine as _, prelude::BASE64_STANDARD};
-use harmony_types::id::Id;
-use kube::api::DynamicObject;
-use serde::Serialize;
-
-use crate::{
-    data::Version,
-    interpret::{Interpret, InterpretError, InterpretName, InterpretStatus, Outcome},
-    inventory::Inventory,
-    modules::monitoring::okd::OpenshiftClusterAlertSender,
-    score::Score,
-    topology::{
-        K8sclient, Topology,
-        monitoring::{AlertReceiver, AlertRoute, MatchOp},
-    },
-};
-
-#[derive(Debug, Clone, Serialize)]
-pub struct OpenshiftReceiverScore {
-    pub receiver: Box<dyn AlertReceiver<OpenshiftClusterAlertSender>>,
-}
-
-impl<T: Topology + K8sclient> Score<T> for OpenshiftReceiverScore {
-    fn name(&self) -> String {
-        "OpenshiftAlertReceiverScore".to_string()
-    }
-
-    fn create_interpret(&self) -> Box<dyn Interpret<T>> {
-        Box::new(OpenshiftReceiverInterpret {
-            receiver: self.receiver.clone(),
-        })
-    }
-}
-
-#[derive(Debug)]
-pub struct OpenshiftReceiverInterpret {
-    receiver: Box<dyn AlertReceiver<OpenshiftClusterAlertSender>>,
-}
-
-#[async_trait]
-impl<T: Topology + K8sclient> Interpret<T> for OpenshiftReceiverInterpret {
-    async fn execute(
-        &self,
-        _inventory: &Inventory,
-        topology: &T,
-    ) -> Result<Outcome, InterpretError> {
-        let client = topology.k8s_client().await?;
-        let ns = "openshift-monitoring";
-
-        let mut am_secret: DynamicObject = client
-            .get_secret_json_value("alertmanager-main", Some(ns))
-            .await?;
-
-        let data = am_secret
-            .data
-            .get_mut("data")
-            .ok_or_else(|| {
-                InterpretError::new("Missing 'data' field in alertmanager-main secret".into())
-            })?
-            .as_object_mut()
-            .ok_or_else(|| InterpretError::new("'data' field must be a JSON object".into()))?;
-
-        let config_b64 = data
-            .get("alertmanager.yaml")
-            .and_then(|v| v.as_str())
-            .unwrap_or_default();
-
-        let config_bytes = BASE64_STANDARD.decode(config_b64).unwrap_or_default();
-
-        let mut am_config: serde_yaml::Value = serde_yaml::from_slice(&config_bytes)
-            .unwrap_or_else(|_| serde_yaml::Value::Mapping(serde_yaml::Mapping::new()));
-
-        let name = self.receiver.name();
-        let install_plan = self.receiver.build().expect("failed to build install plan");
-        let receiver = install_plan.receiver.expect("unable to find receiver path");
-
-        let alert_route = install_plan
-            .route
-            .ok_or_else(|| InterpretError::new("missing route".into()))?;
-
-        let route = self.serialize_route(&alert_route);
-
-        let route = serde_yaml::to_value(route).map_err(|e| InterpretError::new(e.to_string()))?;
-
-        if am_config.get("receivers").is_none() {
-            am_config["receivers"] = serde_yaml::Value::Sequence(vec![]);
-        }
-        if am_config.get("route").is_none() {
-            am_config["route"] = serde_yaml::Value::Mapping(serde_yaml::Mapping::new());
-        }
-        if am_config["route"].get("routes").is_none() {
-            am_config["route"]["routes"] = serde_yaml::Value::Sequence(vec![]);
-        }
-
-        {
-            let receivers_seq = am_config["receivers"].as_sequence_mut().unwrap();
-            if let Some(idx) = receivers_seq
-                .iter()
-                .position(|r| r.get("name").and_then(|n| n.as_str()) == Some(&name))
-            {
-                receivers_seq[idx] = receiver;
-            } else {
-                receivers_seq.push(receiver);
-            }
-        }
-
-        {
-            let route_seq = am_config["route"]["routes"].as_sequence_mut().unwrap();
-            if let Some(idx) = route_seq
-                .iter()
-                .position(|r| r.get("receiver").and_then(|n| n.as_str()) == Some(&name))
-            {
-                route_seq[idx] = route;
-            } else {
-                route_seq.push(route);
-            }
-        }
-
-        let yaml_str =
-            serde_yaml::to_string(&am_config).map_err(|e| InterpretError::new(e.to_string()))?;
-
-        let mut yaml_b64 = String::new();
-
-        BASE64_STANDARD.encode_string(yaml_str, &mut yaml_b64);
-        data.insert(
-            "alertmanager.yaml".to_string(),
-            serde_json::Value::String(yaml_b64),
-        );
-        am_secret.metadata.managed_fields = None;
-
-        client.apply_dynamic(&am_secret, Some(ns), true).await?;
-
-        Ok(Outcome::success(format!(
-            "Configured OpenShift cluster alert receiver: {}",
-            name
-        )))
-    }
-
-    fn get_name(&self) -> InterpretName {
-        InterpretName::Custom("OpenshiftAlertReceiverInterpret")
-    }
-
-    fn get_version(&self) -> Version {
-        todo!()
-    }
-
-    fn get_status(&self) -> InterpretStatus {
-        todo!()
-    }
-
-    fn get_children(&self) -> Vec<Id> {
-        todo!()
-    }
-}
-impl OpenshiftReceiverInterpret {
-    fn serialize_route(&self, route: &AlertRoute) -> serde_yaml::Value {
-        // Convert matchers
-        let matchers: Vec<String> = route
-            .matchers
-            .iter()
-            .map(|m| match m.operator {
-                MatchOp::Eq => format!("{} = {}", m.label, m.value),
-                MatchOp::NotEq => format!("{} != {}", m.label, m.value),
-                MatchOp::Regex => format!("{} =~ {}", m.label, m.value),
-            })
-            .collect();
-
-        // Recursively convert children routes
-        let children: Vec<serde_yaml::Value> = route
-            .children
-            .iter()
-            .map(|c| self.serialize_route(c))
-            .collect();
-
-        // Build the YAML object for this route
-        let mut route_map = serde_yaml::Mapping::new();
-        route_map.insert(
-            serde_yaml::Value::String("receiver".to_string()),
-            serde_yaml::Value::String(route.receiver.clone()),
-        );
-        if !matchers.is_empty() {
-            route_map.insert(
-                serde_yaml::Value::String("matchers".to_string()),
-                serde_yaml::to_value(matchers).unwrap(),
-            );
-        }
-        if !route.group_by.is_empty() {
-            route_map.insert(
-                serde_yaml::Value::String("group_by".to_string()),
-                serde_yaml::to_value(route.group_by.clone()).unwrap(),
-            );
-        }
-        if let Some(ref interval) = route.repeat_interval {
-            route_map.insert(
-                serde_yaml::Value::String("repeat_interval".to_string()),
-                serde_yaml::Value::String(interval.clone()),
-            );
-        }
-        route_map.insert(
-            serde_yaml::Value::String("continue".to_string()),
-            serde_yaml::Value::Bool(route.continue_matching),
-        );
-        if !children.is_empty() {
-            route_map.insert(
-                serde_yaml::Value::String("routes".to_string()),
-                serde_yaml::Value::Sequence(children),
-            );
-        }
-
-        serde_yaml::Value::Mapping(route_map)
-    }
-}