chore: cleaned up some dead code, comments, etc

Reviewed-on: #233

.gitignore

@@ -26,3 +26,6 @@ Cargo.lock
 *.pdb
 
 .harmony_generated
+
+# Useful to create ignore folders for temp files and notes
+ignore

Cargo.lock

@@ -1828,6 +1828,40 @@ dependencies = [
  "url",
 ]
 
+[[package]]
+name = "example-k8s-drain-node"
+version = "0.1.0"
+dependencies = [
+ "assert_cmd",
+ "cidr",
+ "env_logger",
+ "harmony",
+ "harmony_cli",
+ "harmony_macros",
+ "harmony_types",
+ "inquire 0.7.5",
+ "log",
+ "tokio",
+ "url",
+]
+
+[[package]]
+name = "example-k8s-write-file-on-node"
+version = "0.1.0"
+dependencies = [
+ "assert_cmd",
+ "cidr",
+ "env_logger",
+ "harmony",
+ "harmony_cli",
+ "harmony_macros",
+ "harmony_types",
+ "inquire 0.7.5",
+ "log",
+ "tokio",
+ "url",
+]
+
 [[package]]
 name = "example-kube-rs"
 version = "0.1.0"
@@ -3638,26 +3672,6 @@ dependencies = [
  "thiserror 1.0.69",
 ]
 
-[[package]]
-name = "json-prompt"
-version = "0.1.0"
-dependencies = [
- "brocade",
- "cidr",
- "env_logger",
- "harmony",
- "harmony_cli",
- "harmony_macros",
- "harmony_secret",
- "harmony_secret_derive",
- "harmony_types",
- "log",
- "schemars 0.8.22",
- "serde",
- "tokio",
- "url",
-]
-
 [[package]]
 name = "jsonpath-rust"
 version = "0.7.5"

Cargo.toml

@@ -52,6 +52,7 @@ kube = { version = "1.1.0", features = [
   "jsonpatch",
 ] }
 k8s-openapi = { version = "0.25", features = ["v1_30"] }
+# TODO replace with https://github.com/bourumir-wyngs/serde-saphyr as serde_yaml is deprecated https://github.com/sebastienrousseau/serde_yml
 serde_yaml = "0.9"
 serde-value = "0.7"
 http = "1.2"

README.md

@@ -1,4 +1,6 @@
-# Harmony : Open-source infrastructure orchestration that treats your platform like first-class code
+# Harmony
+
+Open-source infrastructure orchestration that treats your platform like first-class code.
 
 In other words, Harmony is a **next-generation platform engineering framework**.
 
@@ -20,9 +22,7 @@ All in **one strongly-typed Rust codebase**.
 
 From a **developer laptop** to a **global production cluster**, a single **source of truth** drives the **full software lifecycle.**
 
----
-
-## 1 · The Harmony Philosophy
+## The Harmony Philosophy
 
 Infrastructure is essential, but it shouldn’t be your core business. Harmony is built on three guiding principles that make modern platforms reliable, repeatable, and easy to reason about.
 
@@ -34,9 +34,18 @@ Infrastructure is essential, but it shouldn’t be your core business. Harmony i
 
 These principles surface as simple, ergonomic Rust APIs that let teams focus on their product while trusting the platform underneath.
 
----
+## Where to Start
 
-## 2 · Quick Start
+We have a comprehensive set of documentation right here in the repository.
+
+| I want to...      | Start Here                                                         |
+| ----------------- | ------------------------------------------------------------------ |
+| Get Started       | [Getting Started Guide](./docs/guides/getting-started.md)          |
+| See an Example    | [Use Case: Deploy a Rust Web App](./docs/use-cases/rust-webapp.md) |
+| Explore           | [Documentation Hub](./docs/README.md)                              |
+| See Core Concepts | [Core Concepts Explained](./docs/concepts.md)                      |
+
+## Quick Look: Deploy a Rust Webapp
 
 The snippet below spins up a complete **production-grade Rust + Leptos Webapp** with monitoring. Swap it for your own scores to deploy anything from microservices to machine-learning pipelines.
 
@@ -94,63 +103,33 @@ async fn main() {
 }
 ```
 
-Run it:
+To run this:
 
-```bash
-cargo run
-```
+- Clone the repository: `git clone https://git.nationtech.io/nationtech/harmony`
+- Install dependencies: `cargo build --release`
+- Run the example: `cargo run --example try_rust_webapp`
 
-Harmony analyses the code, shows an execution plan in a TUI, and applies it once you confirm. Same code, same binary—every environment.
+## Documentation
 
----
+All documentation is in the `/docs` directory.
 
-## 3 · Core Concepts
+- [Documentation Hub](./docs/README.md): The main entry point for all documentation.
+- [Core Concepts](./docs/concepts.md): A detailed look at Score, Topology, Capability, Inventory, and Interpret.
+- [Component Catalogs](./docs/catalogs/README.md): Discover all available Scores, Topologies, and Capabilities.
+- [Developer Guide](./docs/guides/developer-guide.md): Learn how to write your own Scores and Topologies.
 
-| Term             | One-liner                                                                                            |
-| ---------------- | ---------------------------------------------------------------------------------------------------- |
-| **Score<T>**     | Declarative description of the desired state (e.g., `LAMPScore`).                                    |
-| **Interpret<T>** | Imperative logic that realises a `Score` on a specific environment.                                  |
-| **Topology**     | An environment (local k3d, AWS, bare-metal) exposing verified _Capabilities_ (Kubernetes, DNS, …).   |
-| **Maestro**      | Orchestrator that compiles Scores + Topology, ensuring all capabilities line up **at compile-time**. |
-| **Inventory**    | Optional catalogue of physical assets for bare-metal and edge deployments.                           |
+## Architectural Decision Records
 
-A visual overview is in the diagram below.
+- [ADR-001 · Why Rust](adr/001-rust.md)
+- [ADR-003 · Infrastructure Abstractions](adr/003-infrastructure-abstractions.md)
+- [ADR-006 · Secret Management](adr/006-secret-management.md)
+- [ADR-011 · Multi-Tenant Cluster](adr/011-multi-tenant-cluster.md)
 
-[Harmony Core Architecture](docs/diagrams/Harmony_Core_Architecture.drawio.svg)
+## Contribute
 
----
+Discussions and roadmap live in [Issues](https://git.nationtech.io/nationtech/harmony/-/issues). PRs, ideas, and feedback are welcome!
 
-## 4 · Install
-
-Prerequisites:
-
-- Rust
-- Docker (if you deploy locally)
-- `kubectl` / `helm` for Kubernetes-based topologies
-
-```bash
-git clone https://git.nationtech.io/nationtech/harmony
-cd harmony
-cargo build --release          # builds the CLI, TUI and libraries
-```
-
----
-
-## 5 · Learning More
-
-- **Architectural Decision Records** – dive into the rationale
-  - [ADR-001 · Why Rust](adr/001-rust.md)
-  - [ADR-003 · Infrastructure Abstractions](adr/003-infrastructure-abstractions.md)
-  - [ADR-006 · Secret Management](adr/006-secret-management.md)
-  - [ADR-011 · Multi-Tenant Cluster](adr/011-multi-tenant-cluster.md)
-
-- **Extending Harmony** – write new Scores / Interprets, add hardware like OPNsense firewalls, or embed Harmony in your own tooling (`/docs`).
-
-- **Community** – discussions and roadmap live in [GitLab issues](https://git.nationtech.io/nationtech/harmony/-/issues). PRs, ideas, and feedback are welcome!
-
----
-
-## 6 · License
+## License
 
 Harmony is released under the **GNU AGPL v3**.
 

adr/019-Nats-credentials-management.md

@@ -1,86 +0,0 @@
-Initial Date: 2025-02-06
-
-## Status
-
-Proposed
-
-## Context 
-
-The Harmony Agent requires a persistent connection to the NATS Supercluster to perform Key-Value (KV) operations (Read/Write/Watch).
-
-Service Requirements: The agent must authenticate with sufficient privileges to manage KV buckets and interact with the JetStream API.
-
-Infrastructure: NATS is deployed as a multi-site Supercluster. Authentication must be consistent across sites to allow for agent failover and data replication.
-
-https://docs.nats.io/running-a-nats-service/configuration/securing_nats/auth_intro
-
-Technical Constraint: In NATS, JetStream functionality is not global by default; it must be explicitly enabled and capped at the Account level to allow KV bucket creation and persistence.
-
-## Issues
-
-1. The "System Account" Trap
-
-    The Hole: Using the system account for the Harmony Agent.
-
-    The Risk: The NATS System Account is for server heartbeat and monitoring. It cannot (and should not) own JetStream KV buckets.
-
-2. Multi-Site Authorization Sync
-
-    The Hole: Defining users in local nats.conf files via Helm.
-
-    The Risk: If an agent at Site-2 fails over to Site-3, but Site-3’s local configuration doesn't have the testUser credentials, the agent will be locked out during an outage.
-
-3. KV Replication Factor
-
-    The Hole: Not specifying the Replicas count for the KV bucket.
-
-    The Risk: If you create a KV bucket with the default (1 replica), it only exists at the site where it was created. If that site goes down, the data is lost despite having a Supercluster.
-
-4. Subject-Level Permissions
-
-    The Hole: Only granting TEST.* permissions.
-
-    The Risk: NATS KV uses internal subjects (e.g., $KV.<bucket_name>.>). Without access to these, the agent will get an "Authorization Violation" even if it's logged in.
-
-
-## Proposed Solution
-
-To enable reliable, secure communication between the Harmony Agent and the NATS Supercluster, we will implement Account-isolated JetStream using NKey Authentication (or mTLS).
-1. Dedicated Account Architecture
-
-We will move away from the "Global/Default" account. A dedicated HARMONY account will be defined identically across all sites in the Supercluster. This ensures that the metadata for the KV bucket can replicate across the gateways.
-
-    System Account: Reserved for NATS internal health and Supercluster routing.
-
-    Harmony Account: Dedicated to Harmony Agent data, with JetStream explicitly enabled.
-
-2. Authentication: Use harmony secret store mounted into nats container
-
-    Take advantage of currently implemented solution
-
-3. JetStream & KV Configuration
-
-To ensure the KV bucket is available across the Supercluster, the following configuration must be applied:
-
-    Replication Factor (R=3): KV buckets will be created with a replication factor of 3 to ensure data persists across Site-1, Site-2, and Site-3.
-
-    Permissions: The agent will be granted scoped access to:
-
-        $KV.HARMONY.> (Data operations)
-
-        $JS.API.CONSUMER.> and $JS.API.STREAM.> (Management operations)
-
-## Consequence of Decision
-Pros
-
-    Resilience: Agents can fail over to any site in the Supercluster and find their credentials and data.
-
-    Security: By using a dedicated account, the Harmony Agent cannot see or interfere with NATS system traffic.
-
-    Scalability: We can add Site-4 or Site-5 simply by copying the HARMONY account definition.
-
-Cons / Risks
-
-    Configuration Drift: If one site's ConfigMap is updated without the others, authentication will fail during a site failover.
-
-    Complexity: Requires a "Management" step to ensure the account exists on all NATS instances before the agent attempts to connect.

adr/019-Network-bond-setup.md

@@ -0,0 +1,65 @@
+# Architecture Decision Record: Network Bonding Configuration via External Automation
+
+Initial Author: Jean-Gabriel Gill-Couture & Sylvain Tremblay
+
+Initial Date: 2026-02-13
+
+Last Updated Date: 2026-02-13
+
+## Status
+
+Accepted
+
+## Context
+
+We need to configure LACP bonds on 10GbE interfaces across all worker nodes in the OpenShift cluster. A significant challenge is that interface names (e.g., `enp1s0f0` vs `ens1f0`) vary across different hardware nodes.
+
+The standard OpenShift mechanism (MachineConfig) applies identical configurations to all nodes in a MachineConfigPool. Since the interface names differ, a single static MachineConfig cannot target specific physical devices across the entire cluster without complex workarounds.
+
+## Decision
+
+We will use the existing "Harmony" automation tool to generate and apply host-specific NetworkManager configuration files directly to the nodes.
+
+1.  Harmony will generate the specific `.nmconnection` files for the bond and slaves based on its inventory of interface names.
+2.  Files will be pushed to `/etc/NetworkManager/system-connections/` on each node.
+3.  Configuration will be applied via `nmcli` reload or a node reboot.
+
+## Rationale
+
+*   **Inventory Awareness:** Harmony already possesses the specific interface mapping data for each host.
+*   **Persistence:** Fedora CoreOS/SCOS allows writing to `/etc`, and these files persist across reboots and OS upgrades (rpm-ostree updates).
+*   **Avoids Complexity:** This approach avoids the operational overhead of creating unique MachineConfigPools for every single host or hardware variant.
+*   **Safety:** Unlike wildcard matching, this ensures explicit interface selection, preventing accidental bonding of reserved interfaces (e.g., future separation of Ceph storage traffic).
+
+## Consequences
+
+**Pros:**
+*   Precise, per-host configuration without polluting the Kubernetes API with hundreds of MachineConfigs.
+*   Standard Linux networking behavior; easy to debug locally.
+*   Prevents accidental interface capture (unlike wildcards).
+
+**Cons:**
+*   **Loss of Declarative K8s State:** The network config is not managed by the Machine Config Operator (MCO).
+*   **Node Replacement Friction:** Newly provisioned nodes (replacements) will boot with default config. Harmony must be run against new nodes manually or via a hook before they can fully join the cluster workload.
+
+## Alternatives considered
+
+1.  **Wildcard Matching in NetworkManager (e.g., `interface-name=enp*`):**
+    *   *Pros:* Single MachineConfig for the whole cluster.
+    *   *Cons:* Rejected because it is too broad. It risks capturing interfaces intended for other purposes (e.g., splitting storage and cluster networks later).
+
+2.  **"Kitchen Sink" Configuration:**
+    *   *Pros:* Single file listing every possible interface name as a slave.
+    *   *Cons:* "Dirty" configuration; results in many inactive connections on every host; brittle if new naming schemes appear.
+
+3.  **Per-Host MachineConfig:**
+    *   *Pros:* Fully declarative within OpenShift.
+    *   *Cons:* Requires a unique `MachineConfigPool` per host, which is an anti-pattern and unmaintainable at scale.
+
+4.  **On-boot Generation Script:**
+    *   *Pros:* Dynamic detection.
+    *   *Cons:* Increases boot complexity; harder to debug if the script fails during startup.
+
+## Additional Notes
+
+While `/etc` is writable and persistent on CoreOS, this configuration falls outside the "Day 1" Ignition process. Operational runbooks must be updated to ensure Harmony runs on any node replacement events.

brocade/examples/main.rs

@@ -1,7 +1,7 @@
 use std::net::{IpAddr, Ipv4Addr};
 
 use brocade::{BrocadeOptions, ssh};
-use harmony_secret::Secret;
+use harmony_secret::{Secret, SecretManager};
 use harmony_types::switch::PortLocation;
 use schemars::JsonSchema;
 use serde::{Deserialize, Serialize};
@@ -21,17 +21,15 @@ async fn main() {
     // let ip = IpAddr::V4(Ipv4Addr::new(192, 168, 4, 11)); // brocade @ st
     let switch_addresses = vec![ip];
 
-    // let config = SecretManager::get_or_prompt::<BrocadeSwitchAuth>()
-    //     .await
-    //     .unwrap();
+    let config = SecretManager::get_or_prompt::<BrocadeSwitchAuth>()
+        .await
+        .unwrap();
 
     let brocade = brocade::init(
         &switch_addresses,
-        // &config.username,
-        // &config.password,
-        "admin",
-        "password",
-        BrocadeOptions {
+        &config.username,
+        &config.password,
+        &BrocadeOptions {
             dry_run: true,
             ssh: ssh::SshOptions {
                 port: 2222,

brocade/src/lib.rs

@@ -144,7 +144,7 @@ pub async fn init(
     ip_addresses: &[IpAddr],
     username: &str,
     password: &str,
-    options: BrocadeOptions,
+    options: &BrocadeOptions,
 ) -> Result<Box<dyn BrocadeClient + Send + Sync>, Error> {
     let shell = BrocadeShell::init(ip_addresses, username, password, options).await?;
 

brocade/src/shell.rs

@@ -28,7 +28,7 @@ impl BrocadeShell {
         ip_addresses: &[IpAddr],
         username: &str,
         password: &str,
-        options: BrocadeOptions,
+        options: &BrocadeOptions,
     ) -> Result<Self, Error> {
         let ip = ip_addresses
             .first()

brocade/src/ssh.rs

@@ -70,7 +70,7 @@ pub async fn try_init_client(
     username: &str,
     password: &str,
     ip: &std::net::IpAddr,
-    base_options: BrocadeOptions,
+    base_options: &BrocadeOptions,
 ) -> Result<BrocadeOptions, Error> {
     let mut default = SshOptions::default();
     default.port = base_options.ssh.port;

docs/README.md

@@ -1 +1,33 @@
-Not much here yet, see the `adr` folder for now. More to come in time!
+# Harmony Documentation Hub
+
+Welcome to the Harmony documentation. This is the main entry point for learning everything from core concepts to building your own Score, Topologies, and Capabilities.
+
+## 1. Getting Started
+
+If you're new to Harmony, start here:
+
+- [**Getting Started Guide**](./guides/getting-started.md): A step-by-step tutorial that takes you from an empty project to deploying your first application.
+- [**Core Concepts**](./concepts.md): A high-level overview of the key concepts in Harmony: `Score`, `Topology`, `Capability`, `Inventory`, `Interpret`, ...
+
+## 2. Use Cases & Examples
+
+See how to use Harmony to solve real-world problems.
+
+- [**OKD on Bare Metal**](./use-cases/okd-on-bare-metal.md): A detailed walkthrough of bootstrapping a high-availability OKD cluster from physical hardware.
+- [**Deploy a Rust Web App**](./use-cases/deploy-rust-webapp.md): A quick guide to deploying a monitored, containerized web application to a Kubernetes cluster.
+
+## 3. Component Catalogs
+
+Discover existing, reusable components you can use in your Harmony projects.
+
+- [**Scores Catalog**](./catalogs/scores.md): A categorized list of all available `Scores` (the "what").
+- [**Topologies Catalog**](./catalogs/topologies.md): A list of all available `Topologies` (the "where").
+- [**Capabilities Catalog**](./catalogs/capabilities.md): A list of all available `Capabilities` (the "how").
+
+## 4. Developer Guides
+
+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`.

docs/catalogs/README.md

@@ -0,0 +1,7 @@
+# Component Catalogs
+
+This section is the "dictionary" for Harmony. It lists all the reusable components available out-of-the-box.
+
+- [**Scores Catalog**](./scores.md): Discover all available `Scores` (the "what").
+- [**Topologies Catalog**](./topologies.md): A list of all available `Topologies` (the "where").
+- [**Capabilities Catalog**](./capabilities.md): A list of all available `Capabilities` (the "how").

docs/catalogs/capabilities.md

@@ -0,0 +1,40 @@
+# Capabilities Catalog
+
+A `Capability` is a specific feature or API that a `Topology` offers. `Interpret` logic uses these capabilities to execute a `Score`.
+
+This list is primarily for developers **writing new Topologies or Scores**. As a user, you just need to know that the `Topology` you pick (like `K8sAnywhereTopology`) provides the capabilities your `Scores` (like `ApplicationScore`) need.
+
+<!--toc:start-->
+
+- [Capabilities Catalog](#capabilities-catalog)
+  - [Kubernetes & Application](#kubernetes-application)
+  - [Monitoring & Observability](#monitoring-observability)
+  - [Networking (Core Services)](#networking-core-services)
+  - [Networking (Hardware & Host)](#networking-hardware-host)
+
+<!--toc:end-->
+
+## Kubernetes & Application
+
+- **K8sClient**: Provides an authenticated client to interact with a Kubernetes API (create/read/update/delete resources).
+- **HelmCommand**: Provides the ability to execute Helm commands (install, upgrade, template).
+- **TenantManager**: Provides methods for managing tenants in a multi-tenant cluster.
+- **Ingress**: Provides an interface for managing ingress controllers and resources.
+
+## Monitoring & Observability
+
+- **Grafana**: Provides an API for configuring Grafana (datasources, dashboards).
+- **Monitoring**: A general capability for configuring monitoring (e.g., creating Prometheus rules).
+
+## Networking (Core Services)
+
+- **DnsServer**: Provides an interface for creating and managing DNS records.
+- **LoadBalancer**: Provides an interface for configuring a load balancer (e.g., OPNsense, MetalLB).
+- **DhcpServer**: Provides an interface for managing DHCP leases and host bindings.
+- **TftpServer**: Provides an interface for managing files on a TFTP server (e.g., iPXE boot files).
+
+## Networking (Hardware & Host)
+
+- **Router**: Provides an interface for configuring routing rules, typically on a firewall like OPNsense.
+- **Switch**: Provides an interface for configuring a physical network switch (e.g., managing VLANs and port channels).
+- **NetworkManager**: Provides an interface for configuring host-level networking (e.g., creating bonds and bridges on a node).

docs/catalogs/scores.md

@@ -0,0 +1,102 @@
+# Scores Catalog
+
+A `Score` is a declarative description of a desired state. Find the Score you need and add it to your `harmony!` block's `scores` array.
+
+<!--toc:start-->
+
+- [Scores Catalog](#scores-catalog)
+  - [Application Deployment](#application-deployment)
+  - [OKD / Kubernetes Cluster Setup](#okd-kubernetes-cluster-setup)
+  - [Cluster Services & Management](#cluster-services-management)
+  - [Monitoring & Alerting](#monitoring-alerting)
+  - [Infrastructure & Networking (Bare Metal)](#infrastructure-networking-bare-metal)
+  - [Infrastructure & Networking (Cluster)](#infrastructure-networking-cluster)
+  - [Tenant Management](#tenant-management)
+  - [Utility](#utility)
+
+<!--toc:end-->
+
+## Application Deployment
+
+Scores for deploying and managing end-user applications.
+
+- **ApplicationScore**: The primary score for deploying a web application. Describes the application, its framework, and the features it requires (e.g., monitoring, CI/CD).
+- **HelmChartScore**: Deploys a generic Helm chart to a Kubernetes cluster.
+- **ArgoHelmScore**: Deploys an application using an ArgoCD Helm chart.
+- **LAMPScore**: A specialized score for deploying a classic LAMP (Linux, Apache, MySQL, PHP) stack.
+
+## OKD / Kubernetes Cluster Setup
+
+This collection of Scores is used to provision an entire OKD cluster from bare metal. They are typically used in order.
+
+- **OKDSetup01InventoryScore**: Discovers and catalogs the physical hardware.
+- **OKDSetup02BootstrapScore**: Configures the bootstrap node, renders iPXE files, and kicks off the SCOS installation.
+- **OKDSetup03ControlPlaneScore**: Renders iPXE configurations for the control plane nodes.
+- **OKDSetupPersistNetworkBondScore**: Configures network bonds on the nodes and port channels on the switches.
+- **OKDSetup04WorkersScore**: Renders iPXE configurations for the worker nodes.
+- **OKDSetup06InstallationReportScore**: Runs post-installation checks and generates a report.
+- **OKDUpgradeScore**: Manages the upgrade process for an existing OKD cluster.
+
+## Cluster Services & Management
+
+Scores for installing and managing services _inside_ a Kubernetes cluster.
+
+- **K3DInstallationScore**: Installs and configes a local K3D (k3s-in-docker) cluster. Used by `K8sAnywhereTopology`.
+- **CertManagerHelmScore**: Deploys the `cert-manager` Helm chart.
+- **ClusterIssuerScore**: Configures a `ClusterIssuer` for `cert-manager`, (e.g., for Let's Encrypt).
+- **K8sNamespaceScore**: Ensures a Kubernetes namespace exists.
+- **K8sDeploymentScore**: Deploys a generic `Deployment` resource to Kubernetes.
+- **K8sIngressScore**: Configures an `Ingress` resource for a service.
+
+## Monitoring & Alerting
+
+Scores for configuring observability, dashboards, and alerts.
+
+- **ApplicationMonitoringScore**: A generic score to set up monitoring for an application.
+- **ApplicationRHOBMonitoringScore**: A specialized score for setting up monitoring via the Red Hat Observability stack.
+- **HelmPrometheusAlertingScore**: Configures Prometheus alerts via a Helm chart.
+- **K8sPrometheusCRDAlertingScore**: Configures Prometheus alerts using the `PrometheusRule` CRD.
+- **PrometheusAlertScore**: A generic score for creating a Prometheus alert.
+- **RHOBAlertingScore**: Configures alerts specifically for the Red Hat Observability stack.
+- **NtfyScore**: Configures alerts to be sent to a `ntfy.sh` server.
+
+## Infrastructure & Networking (Bare Metal)
+
+Low-level scores for managing physical hardware and network services.
+
+- **DhcpScore**: Configures a DHCP server.
+- **OKDDhcpScore**: A specialized DHCP configuration for the OKD bootstrap process.
+- **OKDBootstrapDhcpScore**: Configures DHCP specifically for the bootstrap node.
+- **DhcpHostBindingScore**: Creates a specific MAC-to-IP binding in the DHCP server.
+- **DnsScore**: Configures a DNS server.
+- **OKDDnsScore**: A specialized DNS configuration for the OKD cluster (e.g., `api.*`, `*.apps.*`).
+- **StaticFilesHttpScore**: Serves a directory of static files (e.g., a documentation site) over HTTP.
+- **TftpScore**: Configures a TFTP server, typically for serving iPXE boot files.
+- **IPxeMacBootFileScore**: Assigns a specific iPXE boot file to a MAC address in the TFTP server.
+- **OKDIpxeScore**: A specialized score for generating the iPXE boot scripts for OKD.
+- **OPNsenseShellCommandScore**: Executes a shell command on an OPNsense firewall.
+
+## Infrastructure & Networking (Cluster)
+
+Network services that run inside the cluster or as part of the topology.
+
+- **LoadBalancerScore**: Configures a general-purpose load balancer.
+- **OKDLoadBalancerScore**: Configures the high-availability load balancers for the OKD API and ingress.
+- **OKDBootstrapLoadBalancerScore**: Configures the load balancer specifically for the bootstrap-time API endpoint.
+- **K8sIngressScore**: Configures an Ingress controller or resource.
+- [HighAvailabilityHostNetworkScore](../../harmony/src/modules/okd/host_network.rs): Configures network bonds on a host and the corresponding port-channels on the switch stack for high-availability.
+
+## Tenant Management
+
+Scores for managing multi-tenancy within a cluster.
+
+- **TenantScore**: Creates a new tenant (e.g., a namespace, quotas, network policies).
+- **TenantCredentialScore**: Generates and provisions credentials for a new tenant.
+
+## Utility
+
+Helper scores for discovery and inspection.
+
+- **LaunchDiscoverInventoryAgentScore**: Launches the agent responsible for the `OKDSetup01InventoryScore`.
+- **DiscoverHostForRoleScore**: A utility score to find a host matching a specific role in the inventory.
+- **InspectInventoryScore**: Dumps the discovered inventory for inspection.

docs/catalogs/topologies.md

@@ -0,0 +1,59 @@
+# Topologies Catalog
+
+A `Topology` is the logical representation of your infrastructure and its `Capabilities`. You select a `Topology` in your Harmony project to define _where_ your `Scores` will be applied.
+
+<!--toc:start-->
+
+- [Topologies Catalog](#topologies-catalog)
+  - [HAClusterTopology](#haclustertopology)
+  - [K8sAnywhereTopology](#k8sanywheretopology)
+
+<!--toc:end-->
+
+### HAClusterTopology
+
+- **`HAClusterTopology::autoload()`**
+
+This `Topology` represents a high-availability, bare-metal cluster. It is designed for production-grade deployments like OKD.
+
+It models an environment consisting of:
+
+- At least 3 cluster nodes (for control plane/workers)
+- 2 redundant firewalls (e.g., OPNsense)
+- 2 redundant network switches
+
+**Provided Capabilities:**
+This topology provides a rich set of capabilities required for bare-metal provisioning and cluster management, including:
+
+- `K8sClient` (once the cluster is bootstrapped)
+- `DnsServer`
+- `LoadBalancer`
+- `DhcpServer`
+- `TftpServer`
+- `Router` (via the firewalls)
+- `Switch`
+- `NetworkManager` (for host-level network config)
+
+---
+
+### K8sAnywhereTopology
+
+- **`K8sAnywhereTopology::from_env()`**
+
+This `Topology` is designed for development and application deployment. It provides a simple, abstract way to deploy to _any_ Kubernetes cluster.
+
+**How it works:**
+
+1. By default (`from_env()` with no env vars), it automatically provisions a **local K3D (k3s-in-docker) cluster** on your machine. This is perfect for local development and testing.
+2. If you provide a `KUBECONFIG` environment variable, it will instead connect to that **existing Kubernetes cluster** (e.g., your staging or production OKD cluster).
+
+This allows you to use the _exact same code_ to deploy your application locally as you do to deploy it to production.
+
+**Provided Capabilities:**
+
+- `K8sClient`
+- `HelmCommand`
+- `TenantManager`
+- `Ingress`
+- `Monitoring`
+- ...and more.

docs/concepts.md

@@ -0,0 +1,40 @@
+# Core Concepts
+
+Harmony's design is based on a few key concepts. Understanding them is the key to unlocking the framework's power.
+
+### 1. Score
+
+- **What it is:** A **Score** is a declarative description of a desired state. It's a "resource" that defines _what_ you want to achieve, not _how_ to do it.
+- **Example:** `ApplicationScore` declares "I want this web application to be running and monitored."
+
+### 2. Topology
+
+- **What it is:** A **Topology** is the logical representation of your infrastructure and its abilities. It's the "where" your Scores will be applied.
+- **Key Job:** A Topology's most important job is to expose which `Capabilities` it supports.
+- **Example:** `HAClusterTopology` represents a bare-metal cluster and exposes `Capabilities` like `NetworkManager` and `Switch`. `K8sAnywhereTopology` represents a Kubernetes cluster and exposes the `K8sClient` `Capability`.
+
+### 3. Capability
+
+- **What it is:** A **Capability** is a specific feature or API that a `Topology` offers. It's the "how" a `Topology` can fulfill a `Score`'s request.
+- **Example:** The `K8sClient` capability offers a way to interact with a Kubernetes API. The `Switch` capability offers a way to configure a physical network switch.
+
+### 4. Interpret
+
+- **What it is:** An **Interpret** is the execution logic that makes a `Score` a reality. It's the "glue" that connects the _desired state_ (`Score`) to the _environment's abilities_ (`Topology`'s `Capabilities`).
+- **How it works:** When you apply a `Score`, Harmony finds the matching `Interpret` for your `Topology`. This `Interpret` then uses the `Capabilities` provided by the `Topology` to execute the necessary steps.
+
+### 5. Inventory
+
+- **What it is:** An **Inventory** is the physical material (the "what") used in a cluster. This is most relevant for bare-metal or on-premise topologies.
+- **Example:** A list of nodes with their roles (control plane, worker), CPU, RAM, and network interfaces. For the `K8sAnywhereTopology`, the inventory might be empty or autoloaded, as the infrastructure is more abstract.
+
+---
+
+### How They Work Together (The Compile-Time Check)
+
+1. You **write a `Score`** (e.g., `ApplicationScore`).
+2. Your `Score`'s `Interpret` logic requires certain **`Capabilities`** (e.g., `K8sClient` and `Ingress`).
+3. You choose a **`Topology`** to run it on (e.g., `HAClusterTopology`).
+4. **At compile-time**, Harmony checks: "Does `HAClusterTopology` provide the `K8sClient` and `Ingress` capabilities that `ApplicationScore` needs?"
+   - **If Yes:** Your code compiles. You can be confident it will run.
+   - **If No:** The compiler gives you an error. You've just prevented a "config-is-valid-but-platform-is-wrong" runtime error before you even deployed.

docs/guides/getting-started.md

@@ -0,0 +1,42 @@
+# Getting Started Guide
+
+Welcome to Harmony! This guide will walk you through installing the Harmony framework, setting up a new project, and deploying your first application.
+
+We will build and deploy the "Rust Web App" example, which automatically:
+
+1. Provisions a local K3D (Kubernetes in Docker) cluster.
+2. Deploys a sample Rust web application.
+3. Sets up monitoring for the application.
+
+## Prerequisites
+
+Before you begin, you'll need a few tools installed on your system:
+
+- **Rust & Cargo:** [Install Rust](https://www.rust-lang.org/tools/install)
+- **Docker:** [Install Docker](https://docs.docker.com/get-docker/) (Required for the K3D local cluster)
+- **kubectl:** [Install kubectl](https://kubernetes.io/docs/tasks/tools/install-kubectl/) (For inspecting the cluster)
+
+## 1. Install Harmony
+
+First, clone the Harmony repository and build the project. This gives you the `harmony` CLI and all the core libraries.
+
+```bash
+# Clone the main repository
+git clone https://git.nationtech.io/nationtech/harmony
+cd harmony
+
+# Build the project (this may take a few minutes)
+cargo build --release
+```
+
+...
+
+## Next Steps
+
+Congratulations, you've just deployed an application using true infrastructure-as-code!
+
+From here, you can:
+
+- [Explore the Catalogs](../catalogs/README.md): See what other [Scores](../catalogs/scores.md) and [Topologies](../catalogs/topologies.md) are available.
+- [Read the Use Cases](../use-cases/README.md): Check out the [OKD on Bare Metal](./use-cases/okd-on-bare-metal.md) guide for a more advanced scenario.
+- [Write your own Score](../guides/writing-a-score.md): Dive into the [Developer Guide](./guides/developer-guide.md) to start building your own components.

examples/brocade_switch/src/main.rs

@@ -1,22 +1,28 @@
 use std::str::FromStr;
 
-use async_trait::async_trait;
 use brocade::{BrocadeOptions, PortOperatingMode};
 use harmony::{
-    data::Version,
-    infra::brocade::BrocadeSwitchClient,
-    interpret::{Interpret, InterpretError, InterpretName, InterpretStatus, Outcome},
+    infra::brocade::BrocadeSwitchConfig,
     inventory::Inventory,
-    score::Score,
-    topology::{
-        HostNetworkConfig, PortConfig, PreparationError, PreparationOutcome, Switch, SwitchClient,
-        SwitchError, Topology,
-    },
+    modules::brocade::{BrocadeSwitchAuth, BrocadeSwitchScore, SwitchTopology},
 };
 use harmony_macros::ip;
-use harmony_types::{id::Id, net::MacAddress, switch::PortLocation};
-use log::{debug, info};
-use serde::Serialize;
+use harmony_types::{id::Id, switch::PortLocation};
+
+fn get_switch_config() -> BrocadeSwitchConfig {
+    let mut options = BrocadeOptions::default();
+    options.ssh.port = 2222;
+    let auth = BrocadeSwitchAuth {
+        username: "admin".to_string(),
+        password: "password".to_string(),
+    };
+
+    BrocadeSwitchConfig {
+        ips: vec![ip!("127.0.0.1")],
+        auth,
+        options,
+    }
+}
 
 #[tokio::main]
 async fn main() {
@@ -32,126 +38,13 @@ async fn main() {
             (PortLocation(1, 0, 18), PortOperatingMode::Trunk),
         ],
     };
+
     harmony_cli::run(
         Inventory::autoload(),
-        SwitchTopology::new().await,
+        SwitchTopology::new(get_switch_config()).await,
         vec![Box::new(switch_score)],
         None,
     )
     .await
     .unwrap();
 }
-
-#[derive(Clone, Debug, Serialize)]
-struct BrocadeSwitchScore {
-    port_channels_to_clear: Vec<Id>,
-    ports_to_configure: Vec<PortConfig>,
-}
-
-impl<T: Topology + Switch> Score<T> for BrocadeSwitchScore {
-    fn name(&self) -> String {
-        "BrocadeSwitchScore".to_string()
-    }
-
-    #[doc(hidden)]
-    fn create_interpret(&self) -> Box<dyn Interpret<T>> {
-        Box::new(BrocadeSwitchInterpret {
-            score: self.clone(),
-        })
-    }
-}
-
-#[derive(Debug)]
-struct BrocadeSwitchInterpret {
-    score: BrocadeSwitchScore,
-}
-
-#[async_trait]
-impl<T: Topology + Switch> Interpret<T> for BrocadeSwitchInterpret {
-    async fn execute(
-        &self,
-        _inventory: &Inventory,
-        topology: &T,
-    ) -> Result<Outcome, InterpretError> {
-        info!("Applying switch configuration {:?}", self.score);
-        debug!(
-            "Clearing port channel {:?}",
-            self.score.port_channels_to_clear
-        );
-        topology
-            .clear_port_channel(&self.score.port_channels_to_clear)
-            .await
-            .map_err(|e| InterpretError::new(e.to_string()))?;
-        debug!("Configuring interfaces {:?}", self.score.ports_to_configure);
-        topology
-            .configure_interface(&self.score.ports_to_configure)
-            .await
-            .map_err(|e| InterpretError::new(e.to_string()))?;
-        Ok(Outcome::success("switch configured".to_string()))
-    }
-    fn get_name(&self) -> InterpretName {
-        InterpretName::Custom("BrocadeSwitchInterpret")
-    }
-    fn get_version(&self) -> Version {
-        todo!()
-    }
-    fn get_status(&self) -> InterpretStatus {
-        todo!()
-    }
-    fn get_children(&self) -> Vec<Id> {
-        todo!()
-    }
-}
-
-struct SwitchTopology {
-    client: Box<dyn SwitchClient>,
-}
-
-#[async_trait]
-impl Topology for SwitchTopology {
-    fn name(&self) -> &str {
-        "SwitchTopology"
-    }
-
-    async fn ensure_ready(&self) -> Result<PreparationOutcome, PreparationError> {
-        Ok(PreparationOutcome::Noop)
-    }
-}
-
-impl SwitchTopology {
-    async fn new() -> Self {
-        let mut options = BrocadeOptions::default();
-        options.ssh.port = 2222;
-        let client =
-            BrocadeSwitchClient::init(&vec![ip!("127.0.0.1")], &"admin", &"password", options)
-                .await
-                .expect("Failed to connect to switch");
-
-        let client = Box::new(client);
-        Self { client }
-    }
-}
-
-#[async_trait]
-impl Switch for SwitchTopology {
-    async fn setup_switch(&self) -> Result<(), SwitchError> {
-        todo!()
-    }
-
-    async fn get_port_for_mac_address(
-        &self,
-        _mac_address: &MacAddress,
-    ) -> Result<Option<PortLocation>, SwitchError> {
-        todo!()
-    }
-
-    async fn configure_port_channel(&self, _config: &HostNetworkConfig) -> Result<(), SwitchError> {
-        todo!()
-    }
-    async fn clear_port_channel(&self, ids: &Vec<Id>) -> Result<(), SwitchError> {
-        self.client.clear_port_channel(ids).await
-    }
-    async fn configure_interface(&self, ports: &Vec<PortConfig>) -> Result<(), SwitchError> {
-        self.client.configure_interface(ports).await
-    }
-}

examples/k8s_drain_node/Cargo.toml

@@ -0,0 +1,20 @@
+[package]
+name = "example-k8s-drain-node"
+edition = "2024"
+version.workspace = true
+readme.workspace = true
+license.workspace = true
+publish = false
+
+[dependencies]
+harmony = { path = "../../harmony" }
+harmony_cli = { path = "../../harmony_cli" }
+harmony_types = { path = "../../harmony_types" }
+cidr.workspace = true
+tokio.workspace = true
+harmony_macros = { path = "../../harmony_macros" }
+log.workspace = true
+env_logger.workspace = true
+url.workspace = true
+assert_cmd = "2.0.16"
+inquire.workspace = true

examples/k8s_drain_node/src/main.rs

@@ -0,0 +1,61 @@
+use std::time::Duration;
+
+use harmony::topology::k8s::{DrainOptions, K8sClient};
+use log::{info, trace};
+
+#[tokio::main]
+async fn main() {
+    env_logger::init();
+    let k8s = K8sClient::try_default().await.unwrap();
+    let nodes = k8s.get_nodes(None).await.unwrap();
+    trace!("Got nodes : {nodes:#?}");
+    let node_names = nodes
+        .iter()
+        .map(|n| n.metadata.name.as_ref().unwrap())
+        .collect::<Vec<&String>>();
+
+    info!("Got nodes : {:?}", node_names);
+
+    let node_name = inquire::Select::new("What node do you want to operate on?", node_names)
+        .prompt()
+        .unwrap();
+
+    let drain = inquire::Confirm::new("Do you wish to drain the node now ?")
+        .prompt()
+        .unwrap();
+
+    if drain {
+        let mut options = DrainOptions::default_ignore_daemonset_delete_emptydir_data();
+        options.timeout = Duration::from_secs(1);
+        k8s.drain_node(&node_name, &options).await.unwrap();
+
+        info!("Node {node_name} successfully drained");
+    }
+
+    let uncordon =
+        inquire::Confirm::new("Do you wish to uncordon node to resume scheduling workloads now?")
+            .prompt()
+            .unwrap();
+
+    if uncordon {
+        info!("Uncordoning node {node_name}");
+        k8s.uncordon_node(node_name).await.unwrap();
+        info!("Node {node_name} uncordoned");
+    }
+
+    let reboot = inquire::Confirm::new("Do you wish to reboot node now?")
+        .prompt()
+        .unwrap();
+
+    if reboot {
+        k8s.reboot_node(
+            &node_name,
+            &DrainOptions::default_ignore_daemonset_delete_emptydir_data(),
+            Duration::from_secs(3600),
+        )
+        .await
+        .unwrap();
+    }
+
+    info!("All done playing with nodes, happy harmonizing!");
+}

examples/k8s_write_file_on_node/Cargo.toml

@@ -0,0 +1,20 @@
+[package]
+name = "example-k8s-write-file-on-node"
+edition = "2024"
+version.workspace = true
+readme.workspace = true
+license.workspace = true
+publish = false
+
+[dependencies]
+harmony = { path = "../../harmony" }
+harmony_cli = { path = "../../harmony_cli" }
+harmony_types = { path = "../../harmony_types" }
+cidr.workspace = true
+tokio.workspace = true
+harmony_macros = { path = "../../harmony_macros" }
+log.workspace = true
+env_logger.workspace = true
+url.workspace = true
+assert_cmd = "2.0.16"
+inquire.workspace = true

examples/k8s_write_file_on_node/src/main.rs

@@ -0,0 +1,45 @@
+use harmony::topology::k8s::{DrainOptions, K8sClient, NodeFile};
+use log::{info, trace};
+
+#[tokio::main]
+async fn main() {
+    env_logger::init();
+    let k8s = K8sClient::try_default().await.unwrap();
+    let nodes = k8s.get_nodes(None).await.unwrap();
+    trace!("Got nodes : {nodes:#?}");
+    let node_names = nodes
+        .iter()
+        .map(|n| n.metadata.name.as_ref().unwrap())
+        .collect::<Vec<&String>>();
+
+    info!("Got nodes : {:?}", node_names);
+
+    let node = inquire::Select::new("What node do you want to write file to?", node_names)
+        .prompt()
+        .unwrap();
+
+    let path = inquire::Text::new("File path on node").prompt().unwrap();
+    let content = inquire::Text::new("File content").prompt().unwrap();
+
+    let node_file = NodeFile {
+        path: path,
+        content: content,
+        mode: 0o600,
+    };
+
+    k8s.write_files_to_node(&node, &vec![node_file.clone()])
+        .await
+        .unwrap();
+
+    let cmd = inquire::Text::new("Command to run on node")
+        .prompt()
+        .unwrap();
+    k8s.run_privileged_command_on_node(&node, &cmd)
+        .await
+        .unwrap();
+
+    info!(
+        "File {} mode {} written in node {node}",
+        node_file.path, node_file.mode
+    );
+}

examples/monitoring/src/main.rs

@@ -1,37 +1,45 @@
-use std::collections::HashMap;
+use std::{
+    collections::HashMap,
+    sync::{Arc, Mutex},
+};
 
 use harmony::{
     inventory::Inventory,
-    modules::{
-        monitoring::{
-            alert_channel::discord_alert_channel::DiscordWebhook,
-            alert_rule::prometheus_alert_rule::AlertManagerRuleGroup,
-            kube_prometheus::{
-                helm_prometheus_alert_score::HelmPrometheusAlertingScore,
-                types::{
-                    HTTPScheme, MatchExpression, Operator, Selector, ServiceMonitor,
-                    ServiceMonitorEndpoint,
+    modules::monitoring::{
+        alert_channel::discord_alert_channel::DiscordReceiver,
+        alert_rule::{
+            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,
             },
+            prometheus_alert_rule::AlertManagerRuleGroup,
         },
-        prometheus::alerts::{
-            infra::dell_server::{
-                alert_global_storage_status_critical, alert_global_storage_status_non_recoverable,
-                global_storage_status_degraded_non_critical,
+        kube_prometheus::{
+            helm::config::KubePrometheusConfig,
+            kube_prometheus_alerting_score::KubePrometheusAlertingScore,
+            types::{
+                HTTPScheme, MatchExpression, Operator, Selector, ServiceMonitor,
+                ServiceMonitorEndpoint,
             },
-            k8s::pvc::high_pvc_fill_rate_over_two_days,
         },
     },
-    topology::K8sAnywhereTopology,
+    topology::{K8sAnywhereTopology, monitoring::AlertRoute},
 };
 use harmony_types::{k8s_name::K8sName, net::Url};
 
 #[tokio::main]
 async fn main() {
-    let discord_receiver = DiscordWebhook {
-        name: K8sName("test-discord".to_string()),
+    let receiver_name = "test-discord".to_string();
+    let discord_receiver = DiscordReceiver {
+        name: receiver_name.clone(),
         url: Url::Url(url::Url::parse("https://discord.doesnt.exist.com").unwrap()),
-        selectors: vec![],
+        route: AlertRoute {
+            ..AlertRoute::default(receiver_name)
+        },
     };
 
     let high_pvc_fill_rate_over_two_days_alert = high_pvc_fill_rate_over_two_days();
@@ -70,10 +78,15 @@ 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

@@ -1,24 +1,32 @@
-use std::{collections::HashMap, str::FromStr};
+use std::{
+    collections::HashMap,
+    str::FromStr,
+    sync::{Arc, Mutex},
+};
 
 use harmony::{
     inventory::Inventory,
     modules::{
         monitoring::{
-            alert_channel::discord_alert_channel::DiscordWebhook,
-            alert_rule::prometheus_alert_rule::AlertManagerRuleGroup,
+            alert_channel::discord_alert_channel::DiscordReceiver,
+            alert_rule::{
+                alerts::k8s::pvc::high_pvc_fill_rate_over_two_days,
+                prometheus_alert_rule::AlertManagerRuleGroup,
+            },
             kube_prometheus::{
-                helm_prometheus_alert_score::HelmPrometheusAlertingScore,
+                helm::config::KubePrometheusConfig,
+                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},
     },
 };
@@ -42,10 +50,13 @@ async fn main() {
         },
     };
 
-    let discord_receiver = DiscordWebhook {
-        name: K8sName("test-discord".to_string()),
+    let receiver_name = "test-discord".to_string();
+    let discord_receiver = DiscordReceiver {
+        name: receiver_name.clone(),
         url: Url::Url(url::Url::parse("https://discord.doesnt.exist.com").unwrap()),
-        selectors: vec![],
+        route: AlertRoute {
+            ..AlertRoute::default(receiver_name)
+        },
     };
 
     let high_pvc_fill_rate_over_two_days_alert = high_pvc_fill_rate_over_two_days();
@@ -74,10 +85,14 @@ async fn main() {
         ..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)],
         service_monitors: vec![service_monitor],
+        scrape_targets: None,
+        config,
     };
 
     harmony_cli::run(

examples/nats-supercluster/src/main.rs

@@ -215,7 +215,7 @@ fn site(
             dns_name: format!("{cluster_name}-gw.{domain}"),
             supercluster_ca_secret_name: "nats-supercluster-ca-bundle",
             tls_cert_name: "nats-gateway",
-            jetstream_enabled: "false",
+            jetstream_enabled: "true",
         },
     }
 }

examples/okd_cluster_alerts/src/main.rs

@@ -1,35 +1,64 @@
-use std::collections::HashMap;
-
 use harmony::{
     inventory::Inventory,
     modules::monitoring::{
-        alert_channel::discord_alert_channel::DiscordWebhook,
-        okd::cluster_monitoring::OpenshiftClusterAlertScore,
+        alert_channel::discord_alert_channel::DiscordReceiver,
+        alert_rule::{
+            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_types::k8s_name::K8sName;
+
+use harmony_macros::{hurl, ip};
 
 #[tokio::main]
 async fn main() {
-    let mut sel = HashMap::new();
-    sel.insert(
-        "openshift_io_alert_source".to_string(),
-        "platform".to_string(),
-    );
-    let mut sel2 = HashMap::new();
-    sel2.insert("openshift_io_alert_source".to_string(), "".to_string());
-    let selectors = vec![sel, sel2];
+    let platform_matcher = AlertMatcher {
+        label: "prometheus".to_string(),
+        operator: MatchOp::Eq,
+        value: "openshift-monitoring/k8s".to_string(),
+    };
+    let severity = AlertMatcher {
+        label: "severity".to_string(),
+        operator: MatchOp::Eq,
+        value: "critical".to_string(),
+    };
+
+    let high_http_error_rate = high_http_error_rate();
+
+    let additional_rules = AlertManagerRuleGroup::new("", vec![high_http_error_rate]);
+
+    let scrape_target = PrometheusNodeExporter {
+        job_name: "firewall".to_string(),
+        metrics_path: "/metrics".to_string(),
+        listen_address: ip!("127.0.0.1"),
+        port: 9100,
+        ..Default::default()
+    };
+
     harmony_cli::run(
         Inventory::autoload(),
         K8sAnywhereTopology::from_env(),
         vec![Box::new(OpenshiftClusterAlertScore {
-            receivers: vec![Box::new(DiscordWebhook {
-                name: K8sName("wills-discord-webhook-example".to_string()),
-                url: hurl!("https://something.io"),
-                selectors: selectors,
+            receivers: vec![Box::new(DiscordReceiver {
+                name: "crit-wills-discord-channel-example".to_string(),
+                url: hurl!("https://test.io"),
+                route: AlertRoute {
+                    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/topology.rs

@@ -2,8 +2,12 @@ use brocade::BrocadeOptions;
 use cidr::Ipv4Cidr;
 use harmony::{
     hardware::{Location, SwitchGroup},
-    infra::{brocade::BrocadeSwitchClient, opnsense::OPNSenseManagementInterface},
+    infra::{
+        brocade::{BrocadeSwitchClient, BrocadeSwitchConfig},
+        opnsense::OPNSenseManagementInterface,
+    },
     inventory::Inventory,
+    modules::brocade::BrocadeSwitchAuth,
     topology::{HAClusterTopology, LogicalHost, UnmanagedRouter},
 };
 use harmony_macros::{ip, ipv4};
@@ -36,12 +40,11 @@ pub async fn get_topology() -> HAClusterTopology {
         dry_run: *harmony::config::DRY_RUN,
         ..Default::default()
     };
-    let switch_client = BrocadeSwitchClient::init(
-        &switches,
-        &switch_auth.username,
-        &switch_auth.password,
-        brocade_options,
-    )
+    let switch_client = BrocadeSwitchClient::init(BrocadeSwitchConfig {
+        ips: switches,
+        auth: switch_auth,
+        options: brocade_options,
+    })
     .await
     .expect("Failed to connect to switch");
 
@@ -103,9 +106,3 @@ pub fn get_inventory() -> Inventory {
         control_plane_host: vec![],
     }
 }
-
-#[derive(Secret, Serialize, Deserialize, JsonSchema, Debug)]
-pub struct BrocadeSwitchAuth {
-    pub username: String,
-    pub password: String,
-}

examples/okd_pxe/src/topology.rs

@@ -3,14 +3,16 @@ use cidr::Ipv4Cidr;
 use harmony::{
     config::secret::OPNSenseFirewallCredentials,
     hardware::{Location, SwitchGroup},
-    infra::{brocade::BrocadeSwitchClient, opnsense::OPNSenseManagementInterface},
+    infra::{
+        brocade::{BrocadeSwitchClient, BrocadeSwitchConfig},
+        opnsense::OPNSenseManagementInterface,
+    },
     inventory::Inventory,
+    modules::brocade::BrocadeSwitchAuth,
     topology::{HAClusterTopology, LogicalHost, UnmanagedRouter},
 };
 use harmony_macros::{ip, ipv4};
-use harmony_secret::{Secret, SecretManager};
-use schemars::JsonSchema;
-use serde::{Deserialize, Serialize};
+use harmony_secret::SecretManager;
 use std::{
     net::IpAddr,
     sync::{Arc, OnceLock},
@@ -31,12 +33,11 @@ pub async fn get_topology() -> HAClusterTopology {
         dry_run: *harmony::config::DRY_RUN,
         ..Default::default()
     };
-    let switch_client = BrocadeSwitchClient::init(
-        &switches,
-        &switch_auth.username,
-        &switch_auth.password,
-        brocade_options,
-    )
+    let switch_client = BrocadeSwitchClient::init(BrocadeSwitchConfig {
+        ips: switches,
+        auth: switch_auth,
+        options: brocade_options,
+    })
     .await
     .expect("Failed to connect to switch");
 
@@ -98,9 +99,3 @@ pub fn get_inventory() -> Inventory {
         control_plane_host: vec![],
     }
 }
-
-#[derive(Secret, Serialize, Deserialize, JsonSchema, Debug)]
-pub struct BrocadeSwitchAuth {
-    pub username: String,
-    pub password: String,
-}

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::DiscordWebhook,
+        monitoring::alert_channel::discord_alert_channel::DiscordReceiver,
     },
-    topology::K8sAnywhereTopology,
+    topology::{K8sAnywhereTopology, monitoring::AlertRoute},
 };
 use harmony_types::{k8s_name::K8sName, net::Url};
 
@@ -22,18 +22,21 @@ async fn main() {
         service_port: 3000,
     });
 
-    let discord_receiver = DiscordWebhook {
-        name: K8sName("test-discord".to_string()),
+    let receiver_name = "test-discord".to_string();
+    let discord_receiver = DiscordReceiver {
+        name: receiver_name.clone(),
         url: Url::Url(url::Url::parse("https://discord.doesnt.exist.com").unwrap()),
-        selectors: vec![],
+        route: AlertRoute {
+            ..AlertRoute::default(receiver_name)
+        },
     };
 
     let app = ApplicationScore {
         features: vec![
-            Box::new(Monitoring {
-                application: application.clone(),
-                alert_receiver: vec![Box::new(discord_receiver)],
-            }),
+            // Box::new(Monitoring {
+            //     application: application.clone(),
+            //     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::DiscordWebhook, webhook_receiver::WebhookReceiver,
+            discord_alert_channel::DiscordReceiver, webhook_receiver::WebhookReceiver,
         },
     },
-    topology::K8sAnywhereTopology,
+    topology::{K8sAnywhereTopology, monitoring::AlertRoute},
 };
 use harmony_macros::hurl;
-use harmony_types::k8s_name::K8sName;
+use harmony_types::{k8s_name::K8sName, net::Url};
 
 #[tokio::main]
 async fn main() {
@@ -26,10 +26,13 @@ async fn main() {
         service_port: 3000,
     });
 
-    let discord_receiver = DiscordWebhook {
-        name: K8sName("test-discord".to_string()),
-        url: hurl!("https://discord.doesnt.exist.com"),
-        selectors: vec![],
+    let receiver_name = "test-discord".to_string();
+    let discord_receiver = DiscordReceiver {
+        name: receiver_name.clone(),
+        url: Url::Url(url::Url::parse("https://discord.doesnt.exist.com").unwrap()),
+        route: AlertRoute {
+            ..AlertRoute::default(receiver_name)
+        },
     };
 
     let webhook_receiver = WebhookReceiver {
@@ -42,10 +45,10 @@ async fn main() {
             Box::new(PackagingDeployment {
                 application: application.clone(),
             }),
-            Box::new(Monitoring {
-                application: application.clone(),
-                alert_receiver: vec![Box::new(discord_receiver), Box::new(webhook_receiver)],
-            }),
+            // Box::new(Monitoring {
+            //     application: application.clone(),
+            //     alert_receiver: vec![Box::new(discord_receiver), Box::new(webhook_receiver)],
+            // }),
             // TODO add backups, multisite ha, etc
         ],
         application,

examples/try_rust_webapp/Cargo.toml

@@ -5,6 +5,10 @@ version.workspace = true
 readme.workspace = true
 license.workspace = true
 
+[[example]]
+name = "try_rust_webapp"
+path = "src/main.rs"
+
 [dependencies]
 harmony = { path = "../../harmony" }
 harmony_cli = { path = "../../harmony_cli" }

examples/try_rust_webapp/src/main.rs

@@ -1,11 +1,8 @@
 use harmony::{
     inventory::Inventory,
-    modules::{
-        application::{
-            ApplicationScore, RustWebFramework, RustWebapp,
-            features::{Monitoring, PackagingDeployment},
-        },
-        monitoring::alert_channel::discord_alert_channel::DiscordWebhook,
+    modules::application::{
+        ApplicationScore, RustWebFramework, RustWebapp,
+        features::{Monitoring, PackagingDeployment},
     },
     topology::K8sAnywhereTopology,
 };
@@ -30,14 +27,14 @@ async fn main() {
             Box::new(PackagingDeployment {
                 application: application.clone(),
             }),
-            Box::new(Monitoring {
-                application: application.clone(),
-                alert_receiver: vec![Box::new(DiscordWebhook {
-                    name: K8sName("test-discord".to_string()),
-                    url: hurl!("https://discord.doesnt.exist.com"),
-                    selectors: vec![],
-                })],
-            }),
+            // Box::new(Monitoring {
+            //     application: application.clone(),
+            //     alert_receiver: vec![Box::new(DiscordWebhook {
+            //         name: K8sName("test-discord".to_string()),
+            //         url: hurl!("https://discord.doesnt.exist.com"),
+            //         selectors: vec![],
+            //     })],
+            // }),
         ],
         application,
     };

harmony/src/domain/hardware/mod.rs

@@ -108,11 +108,18 @@ impl PhysicalHost {
             };
 
             let storage_summary = if drive_count > 1 {
+                let drive_sizes = self
+                    .storage
+                    .iter()
+                    .map(|d| format_storage(d.size_bytes))
+                    .collect::<Vec<_>>()
+                    .join(", ");
+
                 format!(
-                    "{} Storage ({}x {})",
+                    "{} Storage ({} Disks [{}])",
                     format_storage(total_storage_bytes),
                     drive_count,
-                    first_drive_model
+                    drive_sizes
                 )
             } else {
                 format!(

harmony/src/domain/topology/ha_cluster.rs

@@ -1,5 +1,4 @@
 use async_trait::async_trait;
-use brocade::PortOperatingMode;
 use harmony_macros::ip;
 use harmony_types::{
     id::Id,
@@ -9,9 +8,9 @@ use harmony_types::{
 use log::debug;
 use log::info;
 
+use crate::topology::PxeOptions;
 use crate::{data::FileContent, executors::ExecutorError, topology::node_exporter::NodeExporter};
 use crate::{infra::network_manager::OpenShiftNmStateNetworkManager, topology::PortConfig};
-use crate::{modules::inventory::HarmonyDiscoveryStrategy, topology::PxeOptions};
 
 use super::{
     DHCPStaticEntry, DhcpServer, DnsRecord, DnsRecordType, DnsServer, Firewall, HostNetworkConfig,
@@ -301,10 +300,10 @@ impl Switch for HAClusterTopology {
         Ok(())
     }
 
-    async fn clear_port_channel(&self, ids: &Vec<Id>) -> Result<(), SwitchError> {
+    async fn clear_port_channel(&self, _ids: &Vec<Id>) -> Result<(), SwitchError> {
         todo!()
     }
-    async fn configure_interface(&self, ports: &Vec<PortConfig>) -> Result<(), SwitchError> {
+    async fn configure_interface(&self, _ports: &Vec<PortConfig>) -> Result<(), SwitchError> {
         todo!()
     }
 }
@@ -322,7 +321,15 @@ impl NetworkManager for HAClusterTopology {
         self.network_manager().await.configure_bond(config).await
     }
 
-    //TODO add snmp here
+    async fn configure_bond_on_primary_interface(
+        &self,
+        config: &HostNetworkConfig,
+    ) -> Result<(), NetworkError> {
+        self.network_manager()
+            .await
+            .configure_bond_on_primary_interface(config)
+            .await
+    }
 }
 
 #[async_trait]
@@ -562,10 +569,10 @@ impl SwitchClient for DummyInfra {
     ) -> Result<u8, SwitchError> {
         unimplemented!("{}", UNIMPLEMENTED_DUMMY_INFRA)
     }
-    async fn clear_port_channel(&self, ids: &Vec<Id>) -> Result<(), SwitchError> {
+    async fn clear_port_channel(&self, _ids: &Vec<Id>) -> Result<(), SwitchError> {
         todo!()
     }
-    async fn configure_interface(&self, ports: &Vec<PortConfig>) -> Result<(), SwitchError> {
+    async fn configure_interface(&self, _ports: &Vec<PortConfig>) -> Result<(), SwitchError> {
         todo!()
     }
 }

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

@@ -0,0 +1,133 @@
+//! Resource Bundle Pattern Implementation
+//!
+//! This module implements the Resource Bundle pattern for managing groups of
+//! Kubernetes resources that form a logical unit of work.
+//!
+//! ## Purpose
+//!
+//! The ResourceBundle pattern addresses the need to manage ephemeral privileged
+//! pods along with their platform-specific security requirements (e.g., OpenShift
+//! Security Context Constraints).
+//!
+//! ## Use Cases
+//!
+//! - Writing files to node filesystems (e.g., NetworkManager configurations for
+//!   network bonding as described in ADR-019)
+//! - Running privileged commands on nodes (e.g., reboots, system configuration)
+//!
+//! ## Benefits
+//!
+//! - **Separation of Concerns**: Client code doesn't need to know about
+//!   platform-specific RBAC requirements
+//! - **Atomic Operations**: Resources are applied and deleted as a unit
+//! - **Clean Abstractions**: Privileged operations are encapsulated in bundles
+//!   rather than scattered throughout client methods
+//!
+//! ## Example
+//!
+//! ```rust,no_run
+//! use harmony::topology::k8s::{K8sClient, helper};
+//! use harmony::topology::KubernetesDistribution;
+//!
+//! async fn write_network_config(client: &K8sClient, node: &str) {
+//!     // Create a bundle with platform-specific RBAC
+//!     let bundle = helper::build_privileged_bundle(
+//!         helper::PrivilegedPodConfig {
+//!             name: "network-config".to_string(),
+//!             namespace: "default".to_string(),
+//!             node_name: node.to_string(),
+//!             // ... other config
+//!             ..Default::default()
+//!         },
+//!         &KubernetesDistribution::OpenshiftFamily,
+//!     );
+//!     
+//!     // Apply all resources (RBAC + Pod) atomically
+//!     bundle.apply(client).await.unwrap();
+//!     
+//!     // ... wait for completion ...
+//!     
+//!     // Cleanup all resources
+//!     bundle.delete(client).await.unwrap();
+//! }
+//! ```
+
+use kube::{Error, Resource, ResourceExt, api::DynamicObject};
+use serde::Serialize;
+use serde_json;
+
+use crate::domain::topology::k8s::K8sClient;
+
+/// A ResourceBundle represents a logical unit of work consisting of multiple
+/// Kubernetes resources that should be applied or deleted together.
+///
+/// This pattern is useful for managing ephemeral privileged pods along with
+/// their required RBAC bindings (e.g., OpenShift SCC bindings).
+#[derive(Debug)]
+pub struct ResourceBundle {
+    pub resources: Vec<DynamicObject>,
+}
+
+impl ResourceBundle {
+    pub fn new() -> Self {
+        Self {
+            resources: Vec::new(),
+        }
+    }
+
+    /// Add a Kubernetes resource to this bundle.
+    /// The resource is converted to a DynamicObject for generic handling.
+    pub fn add<K>(&mut self, resource: K)
+    where
+        K: Resource + Serialize,
+        <K as Resource>::DynamicType: Default,
+    {
+        // Convert the typed resource to JSON, then to DynamicObject
+        let json = serde_json::to_value(&resource).expect("Failed to serialize resource");
+        let mut obj: DynamicObject =
+            serde_json::from_value(json).expect("Failed to convert to DynamicObject");
+
+        // Ensure type metadata is set
+        if obj.types.is_none() {
+            let api_version = Default::default();
+            let kind = Default::default();
+            let gvk = K::api_version(&api_version);
+            let kind = K::kind(&kind);
+            obj.types = Some(kube::api::TypeMeta {
+                api_version: gvk.to_string(),
+                kind: kind.to_string(),
+            });
+        }
+
+        self.resources.push(obj);
+    }
+
+    /// Apply all resources in this bundle to the cluster.
+    /// Resources are applied in the order they were added.
+    pub async fn apply(&self, client: &K8sClient) -> Result<(), Error> {
+        for res in &self.resources {
+            let namespace = res.namespace();
+            client
+                .apply_dynamic(res, namespace.as_deref(), true)
+                .await?;
+        }
+        Ok(())
+    }
+
+    /// Delete all resources in this bundle from the cluster.
+    /// Resources are deleted in reverse order to respect dependencies.
+    pub async fn delete(&self, client: &K8sClient) -> Result<(), Error> {
+        // FIXME delete all in parallel and retry using kube::client::retry::RetryPolicy
+        for res in self.resources.iter().rev() {
+            let api = client.get_api_for_dynamic_object(res, res.namespace().as_deref())?;
+            let name = res.name_any();
+            // FIXME this swallows all errors. Swallowing a 404 is ok but other errors must be
+            // handled properly (such as retrying). A normal error case is when we delete a
+            // resource bundle with dependencies between various resources. Such as a pod with a
+            // dependency on a ClusterRoleBinding. Trying to delete the ClusterRoleBinding first
+            // is expected to fail
+            let _ = api.delete(&name, &kube::api::DeleteParams::default()).await;
+        }
+        Ok(())
+    }
+}

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

@@ -0,0 +1 @@
+pub const PRIVILEGED_POD_IMAGE: &str = "hub.nationtech.io/redhat/ubi10:latest";

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

@@ -0,0 +1,601 @@
+use std::collections::BTreeMap;
+use std::time::Duration;
+
+use crate::topology::KubernetesDistribution;
+
+use super::bundle::ResourceBundle;
+use super::config::PRIVILEGED_POD_IMAGE;
+use k8s_openapi::api::core::v1::{
+    Container, HostPathVolumeSource, Pod, PodSpec, SecurityContext, Volume, VolumeMount,
+};
+use k8s_openapi::api::rbac::v1::{ClusterRoleBinding, RoleRef, Subject};
+use k8s_openapi::apimachinery::pkg::apis::meta::v1::ObjectMeta;
+use kube::error::DiscoveryError;
+use log::{debug, error, info, warn};
+
+#[derive(Debug)]
+pub struct PrivilegedPodConfig {
+    pub name: String,
+    pub namespace: String,
+    pub node_name: String,
+    pub container_name: String,
+    pub command: Vec<String>,
+    pub volumes: Vec<Volume>,
+    pub volume_mounts: Vec<VolumeMount>,
+    pub host_pid: bool,
+    pub host_network: bool,
+}
+
+impl Default for PrivilegedPodConfig {
+    fn default() -> Self {
+        Self {
+            name: "privileged-pod".to_string(),
+            namespace: "harmony".to_string(),
+            node_name: "".to_string(),
+            container_name: "privileged-container".to_string(),
+            command: vec![],
+            volumes: vec![],
+            volume_mounts: vec![],
+            host_pid: false,
+            host_network: false,
+        }
+    }
+}
+
+pub fn build_privileged_pod(
+    config: PrivilegedPodConfig,
+    k8s_distribution: &KubernetesDistribution,
+) -> Pod {
+    let annotations = match k8s_distribution {
+        KubernetesDistribution::OpenshiftFamily => Some(BTreeMap::from([
+            ("openshift.io/scc".to_string(), "privileged".to_string()),
+            (
+                "openshift.io/required-scc".to_string(),
+                "privileged".to_string(),
+            ),
+        ])),
+        _ => None,
+    };
+
+    Pod {
+        metadata: ObjectMeta {
+            name: Some(config.name),
+            namespace: Some(config.namespace),
+            annotations,
+            ..Default::default()
+        },
+        spec: Some(PodSpec {
+            node_name: Some(config.node_name),
+            restart_policy: Some("Never".to_string()),
+            host_pid: Some(config.host_pid),
+            host_network: Some(config.host_network),
+            containers: vec![Container {
+                name: config.container_name,
+                image: Some(PRIVILEGED_POD_IMAGE.to_string()),
+                command: Some(config.command),
+                security_context: Some(SecurityContext {
+                    privileged: Some(true),
+                    ..Default::default()
+                }),
+                volume_mounts: Some(config.volume_mounts),
+                ..Default::default()
+            }],
+            volumes: Some(config.volumes),
+            ..Default::default()
+        }),
+        ..Default::default()
+    }
+}
+
+pub fn host_root_volume() -> (Volume, VolumeMount) {
+    (
+        Volume {
+            name: "host".to_string(),
+            host_path: Some(HostPathVolumeSource {
+                path: "/".to_string(),
+                ..Default::default()
+            }),
+            ..Default::default()
+        },
+        VolumeMount {
+            name: "host".to_string(),
+            mount_path: "/host".to_string(),
+            ..Default::default()
+        },
+    )
+}
+
+/// Build a ResourceBundle containing a privileged pod and any required RBAC.
+///
+/// This function implements the Resource Bundle pattern to encapsulate platform-specific
+/// security requirements for running privileged operations on nodes.
+///
+/// # Platform-Specific Behavior
+///
+/// - **OpenShift**: Creates a ClusterRoleBinding to grant the default ServiceAccount
+///   access to the `system:openshift:scc:privileged` ClusterRole, which allows the pod
+///   to use the privileged Security Context Constraint (SCC).
+/// - **Standard Kubernetes/K3s**: Only creates the Pod resource, as these distributions
+///   use standard PodSecurityPolicy or don't enforce additional security constraints.
+///
+/// # Arguments
+///
+/// * `config` - Configuration for the privileged pod (name, namespace, command, etc.)
+/// * `k8s_distribution` - The detected Kubernetes distribution to determine RBAC requirements
+///
+/// # Returns
+///
+/// A `ResourceBundle` containing 1-2 resources:
+/// - ClusterRoleBinding (OpenShift only)
+/// - Pod (all distributions)
+///
+/// # Example
+///
+/// ```rust,no_run
+/// # use harmony::topology::k8s::helper::{build_privileged_bundle, PrivilegedPodConfig};
+/// # use harmony::topology::KubernetesDistribution;
+/// let bundle = build_privileged_bundle(
+///     PrivilegedPodConfig {
+///         name: "network-setup".to_string(),
+///         namespace: "default".to_string(),
+///         node_name: "worker-01".to_string(),
+///         container_name: "setup".to_string(),
+///         command: vec!["nmcli".to_string(), "connection".to_string(), "reload".to_string()],
+///         ..Default::default()
+///     },
+///     &KubernetesDistribution::OpenshiftFamily,
+/// );
+/// // Bundle now contains ClusterRoleBinding + Pod
+/// ```
+pub fn build_privileged_bundle(
+    config: PrivilegedPodConfig,
+    k8s_distribution: &KubernetesDistribution,
+) -> ResourceBundle {
+    debug!(
+        "Building privileged bundle for config {config:#?} on distribution {k8s_distribution:?}"
+    );
+    let mut bundle = ResourceBundle::new();
+    let pod_name = config.name.clone();
+    let namespace = config.namespace.clone();
+
+    // 1. On OpenShift, create RBAC binding to privileged SCC
+    if let KubernetesDistribution::OpenshiftFamily = k8s_distribution {
+        // The default ServiceAccount needs to be bound to the privileged SCC
+        // via the system:openshift:scc:privileged ClusterRole
+        let crb = ClusterRoleBinding {
+            metadata: ObjectMeta {
+                name: Some(format!("{}-scc-binding", pod_name)),
+                ..Default::default()
+            },
+            role_ref: RoleRef {
+                api_group: "rbac.authorization.k8s.io".to_string(),
+                kind: "ClusterRole".to_string(),
+                name: "system:openshift:scc:privileged".to_string(),
+            },
+            subjects: Some(vec![Subject {
+                kind: "ServiceAccount".to_string(),
+                name: "default".to_string(),
+                namespace: Some(namespace.clone()),
+                api_group: None,
+                ..Default::default()
+            }]),
+        };
+        bundle.add(crb);
+    }
+
+    // 2. Build the privileged pod
+    let pod = build_privileged_pod(config, k8s_distribution);
+    bundle.add(pod);
+
+    bundle
+}
+
+/// Action to take when a drain operation times out.
+pub enum DrainTimeoutAction {
+    /// Accept the partial drain and continue
+    Accept,
+    /// Retry the drain for another timeout period
+    Retry,
+    /// Abort the drain operation
+    Abort,
+}
+
+/// Prompts the user to confirm acceptance of a partial drain.
+///
+/// Returns `Ok(true)` if the user confirms acceptance, `Ok(false)` if the user
+/// chooses to retry or abort, and `Err` if the prompt system fails entirely.
+pub fn prompt_drain_timeout_action(
+    node_name: &str,
+    pending_count: usize,
+    timeout_duration: Duration,
+) -> Result<DrainTimeoutAction, kube::Error> {
+    let prompt_msg = format!(
+        "Drain operation timed out on node '{}' with {} pod(s) remaining. What would you like to do?",
+        node_name, pending_count
+    );
+
+    loop {
+        let choices = vec![
+            "Accept drain failure (requires confirmation)".to_string(),
+            format!("Retry drain for another {:?}", timeout_duration),
+            "Abort operation".to_string(),
+        ];
+
+        let selection = inquire::Select::new(&prompt_msg, choices)
+            .with_help_message("Use arrow keys to navigate, Enter to select")
+            .prompt()
+            .map_err(|e| {
+                kube::Error::Discovery(DiscoveryError::MissingResource(format!(
+                    "Prompt failed: {}",
+                    e
+                )))
+            })?;
+
+        if selection.starts_with("Accept") {
+            // Require typed confirmation - retry until correct or user cancels
+            let required_confirmation = format!("yes-accept-drain:{}={}", node_name, pending_count);
+
+            let confirmation_prompt = format!(
+                "To accept this partial drain, type exactly: {}",
+                required_confirmation
+            );
+
+            match inquire::Text::new(&confirmation_prompt)
+                .with_help_message(&format!(
+                    "This action acknowledges {} pods will remain on the node",
+                    pending_count
+                ))
+                .prompt()
+            {
+                Ok(input) if input == required_confirmation => {
+                    warn!(
+                        "User accepted partial drain of node '{}' with {} pods remaining (confirmation: {})",
+                        node_name, pending_count, required_confirmation
+                    );
+                    return Ok(DrainTimeoutAction::Accept);
+                }
+                Ok(input) => {
+                    warn!(
+                        "Confirmation failed. Expected '{}', got '{}'. Please try again.",
+                        required_confirmation, input
+                    );
+                }
+                Err(e) => {
+                    // User cancelled (Ctrl+C) or prompt system failed
+                    error!("Confirmation prompt cancelled or failed: {}", e);
+                    return Ok(DrainTimeoutAction::Abort);
+                }
+            }
+        } else if selection.starts_with("Retry") {
+            info!(
+                "User chose to retry drain operation for another {:?}",
+                timeout_duration
+            );
+            return Ok(DrainTimeoutAction::Retry);
+        } else {
+            error!("Drain operation aborted by user");
+            return Ok(DrainTimeoutAction::Abort);
+        }
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use pretty_assertions::assert_eq;
+
+    #[test]
+    fn test_host_root_volume() {
+        let (volume, mount) = host_root_volume();
+
+        assert_eq!(volume.name, "host");
+        assert_eq!(volume.host_path.as_ref().unwrap().path, "/");
+
+        assert_eq!(mount.name, "host");
+        assert_eq!(mount.mount_path, "/host");
+    }
+
+    #[test]
+    fn test_build_privileged_pod_minimal() {
+        let pod = build_privileged_pod(
+            PrivilegedPodConfig {
+                name: "minimal-pod".to_string(),
+                namespace: "kube-system".to_string(),
+                node_name: "node-123".to_string(),
+                container_name: "debug-container".to_string(),
+                command: vec!["sleep".to_string(), "3600".to_string()],
+                ..Default::default()
+            },
+            &KubernetesDistribution::Default,
+        );
+
+        assert_eq!(pod.metadata.name, Some("minimal-pod".to_string()));
+        assert_eq!(pod.metadata.namespace, Some("kube-system".to_string()));
+
+        let spec = pod.spec.as_ref().expect("Pod spec should be present");
+        assert_eq!(spec.node_name, Some("node-123".to_string()));
+        assert_eq!(spec.restart_policy, Some("Never".to_string()));
+        assert_eq!(spec.host_pid, Some(false));
+        assert_eq!(spec.host_network, Some(false));
+
+        assert_eq!(spec.containers.len(), 1);
+        let container = &spec.containers[0];
+        assert_eq!(container.name, "debug-container");
+        assert_eq!(container.image, Some(PRIVILEGED_POD_IMAGE.to_string()));
+        assert_eq!(
+            container.command,
+            Some(vec!["sleep".to_string(), "3600".to_string()])
+        );
+
+        // Security context check
+        let sec_ctx = container
+            .security_context
+            .as_ref()
+            .expect("Security context missing");
+        assert_eq!(sec_ctx.privileged, Some(true));
+    }
+
+    #[test]
+    fn test_build_privileged_pod_with_volumes_and_host_access() {
+        let (host_vol, host_mount) = host_root_volume();
+
+        let pod = build_privileged_pod(
+            PrivilegedPodConfig {
+                name: "full-pod".to_string(),
+                namespace: "default".to_string(),
+                node_name: "node-1".to_string(),
+                container_name: "runner".to_string(),
+                command: vec!["/bin/sh".to_string()],
+                volumes: vec![host_vol.clone()],
+                volume_mounts: vec![host_mount.clone()],
+                host_pid: true,
+                host_network: true,
+            },
+            &KubernetesDistribution::Default,
+        );
+
+        let spec = pod.spec.as_ref().expect("Pod spec should be present");
+        assert_eq!(spec.host_pid, Some(true));
+        assert_eq!(spec.host_network, Some(true));
+
+        // Check volumes in Spec
+        let volumes = spec.volumes.as_ref().expect("Volumes should be present");
+        assert_eq!(volumes.len(), 1);
+        assert_eq!(volumes[0].name, "host");
+
+        // Check mounts in Container
+        let container = &spec.containers[0];
+        let mounts = container
+            .volume_mounts
+            .as_ref()
+            .expect("Mounts should be present");
+        assert_eq!(mounts.len(), 1);
+        assert_eq!(mounts[0].name, "host");
+        assert_eq!(mounts[0].mount_path, "/host");
+    }
+
+    #[test]
+    fn test_build_privileged_pod_structure_correctness() {
+        // This test validates that the construction logic puts things in the right places
+        // effectively validating the "template".
+
+        let custom_vol = Volume {
+            name: "custom-vol".to_string(),
+            ..Default::default()
+        };
+        let custom_mount = VolumeMount {
+            name: "custom-vol".to_string(),
+            mount_path: "/custom".to_string(),
+            ..Default::default()
+        };
+
+        let pod = build_privileged_pod(
+            PrivilegedPodConfig {
+                name: "structure-test".to_string(),
+                namespace: "test-ns".to_string(),
+                node_name: "test-node".to_string(),
+                container_name: "test-container".to_string(),
+                command: vec!["cmd".to_string()],
+                volumes: vec![custom_vol],
+                volume_mounts: vec![custom_mount],
+                ..Default::default()
+            },
+            &KubernetesDistribution::Default,
+        );
+
+        // Validate structure depth
+        let spec = pod.spec.as_ref().unwrap();
+
+        // 1. Spec level fields
+        assert!(spec.node_name.is_some());
+        assert!(spec.volumes.is_some());
+
+        // 2. Container level fields
+        let container = &spec.containers[0];
+        assert!(container.security_context.is_some());
+        assert!(container.volume_mounts.is_some());
+
+        // 3. Nested fields
+        assert!(
+            container
+                .security_context
+                .as_ref()
+                .unwrap()
+                .privileged
+                .unwrap()
+        );
+        assert_eq!(spec.volumes.as_ref().unwrap()[0].name, "custom-vol");
+        assert_eq!(
+            container.volume_mounts.as_ref().unwrap()[0].mount_path,
+            "/custom"
+        );
+    }
+
+    #[test]
+    fn test_build_privileged_bundle_default_distribution() {
+        let bundle = build_privileged_bundle(
+            PrivilegedPodConfig {
+                name: "test-bundle".to_string(),
+                namespace: "test-ns".to_string(),
+                node_name: "node-1".to_string(),
+                container_name: "test-container".to_string(),
+                command: vec!["echo".to_string(), "hello".to_string()],
+                ..Default::default()
+            },
+            &KubernetesDistribution::Default,
+        );
+
+        // For Default distribution, only the Pod should be in the bundle
+        assert_eq!(bundle.resources.len(), 1);
+
+        let pod_obj = &bundle.resources[0];
+        assert_eq!(pod_obj.metadata.name.as_deref(), Some("test-bundle"));
+        assert_eq!(pod_obj.metadata.namespace.as_deref(), Some("test-ns"));
+    }
+
+    #[test]
+    fn test_build_privileged_bundle_openshift_distribution() {
+        let bundle = build_privileged_bundle(
+            PrivilegedPodConfig {
+                name: "test-bundle-ocp".to_string(),
+                namespace: "test-ns".to_string(),
+                node_name: "node-1".to_string(),
+                container_name: "test-container".to_string(),
+                command: vec!["echo".to_string(), "hello".to_string()],
+                ..Default::default()
+            },
+            &KubernetesDistribution::OpenshiftFamily,
+        );
+
+        // For OpenShift, both ClusterRoleBinding and Pod should be in the bundle
+        assert_eq!(bundle.resources.len(), 2);
+
+        // First resource should be the ClusterRoleBinding
+        let crb_obj = &bundle.resources[0];
+        assert_eq!(
+            crb_obj.metadata.name.as_deref(),
+            Some("test-bundle-ocp-scc-binding")
+        );
+
+        // Verify it's targeting the privileged SCC
+        if let Some(role_ref) = crb_obj.data.get("roleRef") {
+            assert_eq!(
+                role_ref.get("name").and_then(|v| v.as_str()),
+                Some("system:openshift:scc:privileged")
+            );
+        }
+
+        // Second resource should be the Pod
+        let pod_obj = &bundle.resources[1];
+        assert_eq!(pod_obj.metadata.name.as_deref(), Some("test-bundle-ocp"));
+        assert_eq!(pod_obj.metadata.namespace.as_deref(), Some("test-ns"));
+    }
+
+    #[test]
+    fn test_build_privileged_bundle_k3s_distribution() {
+        let bundle = build_privileged_bundle(
+            PrivilegedPodConfig {
+                name: "test-bundle-k3s".to_string(),
+                namespace: "test-ns".to_string(),
+                node_name: "node-1".to_string(),
+                container_name: "test-container".to_string(),
+                command: vec!["echo".to_string(), "hello".to_string()],
+                ..Default::default()
+            },
+            &KubernetesDistribution::K3sFamily,
+        );
+
+        // For K3s, only the Pod should be in the bundle (no special SCC)
+        assert_eq!(bundle.resources.len(), 1);
+
+        let pod_obj = &bundle.resources[0];
+        assert_eq!(pod_obj.metadata.name.as_deref(), Some("test-bundle-k3s"));
+    }
+
+    #[test]
+    fn test_pod_yaml_rendering_expected() {
+        let pod = build_privileged_pod(
+            PrivilegedPodConfig {
+                name: "pod_name".to_string(),
+                namespace: "pod_namespace".to_string(),
+                node_name: "node name".to_string(),
+                container_name: "container name".to_string(),
+                command: vec!["command".to_string(), "argument".to_string()],
+                host_pid: true,
+                host_network: true,
+                ..Default::default()
+            },
+            &KubernetesDistribution::Default,
+        );
+
+        assert_eq!(
+            &serde_yaml::to_string(&pod).unwrap(),
+            "apiVersion: v1
+kind: Pod
+metadata:
+  name: pod_name
+  namespace: pod_namespace
+spec:
+  containers:
+  - command:
+    - command
+    - argument
+    image: hub.nationtech.io/redhat/ubi10:latest
+    name: container name
+    securityContext:
+      privileged: true
+    volumeMounts: []
+  hostNetwork: true
+  hostPID: true
+  nodeName: node name
+  restartPolicy: Never
+  volumes: []
+"
+        );
+    }
+
+    #[test]
+    fn test_pod_yaml_rendering_openshift() {
+        let pod = build_privileged_pod(
+            PrivilegedPodConfig {
+                name: "pod_name".to_string(),
+                namespace: "pod_namespace".to_string(),
+                node_name: "node name".to_string(),
+                container_name: "container name".to_string(),
+                command: vec!["command".to_string(), "argument".to_string()],
+                host_pid: true,
+                host_network: true,
+                ..Default::default()
+            },
+            &KubernetesDistribution::OpenshiftFamily,
+        );
+
+        assert_eq!(
+            &serde_yaml::to_string(&pod).unwrap(),
+            "apiVersion: v1
+kind: Pod
+metadata:
+  annotations:
+    openshift.io/required-scc: privileged
+    openshift.io/scc: privileged
+  name: pod_name
+  namespace: pod_namespace
+spec:
+  containers:
+  - command:
+    - command
+    - argument
+    image: hub.nationtech.io/redhat/ubi10:latest
+    name: container name
+    securityContext:
+      privileged: true
+    volumeMounts: []
+  hostNetwork: true
+  hostPID: true
+  nodeName: node name
+  restartPolicy: Never
+  volumes: []
+"
+        );
+    }
+}

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

@@ -1,19 +1,12 @@
-use std::{collections::BTreeMap, process::Command, sync::Arc, time::Duration};
+use std::{collections::BTreeMap, process::Command, sync::Arc};
 
 use async_trait::async_trait;
-use base64::{Engine, engine::general_purpose};
 use harmony_types::rfc1123::Rfc1123Name;
-use k8s_openapi::{
-    ByteString,
-    api::{
-        core::v1::{Pod, Secret},
-        rbac::v1::{ClusterRoleBinding, RoleRef, Subject},
-    },
-};
-use kube::{
-    api::{DynamicObject, GroupVersionKind, ObjectMeta},
-    runtime::conditions,
+use k8s_openapi::api::{
+    core::v1::{Pod, Secret},
+    rbac::v1::{ClusterRoleBinding, RoleRef, Subject},
 };
+use kube::api::{GroupVersionKind, ObjectMeta};
 use log::{debug, info, trace, warn};
 use serde::Serialize;
 use tokio::sync::OnceCell;
@@ -34,32 +27,7 @@ use crate::{
             score_cert_management::CertificateManagementScore,
         },
         k3d::K3DInstallationScore,
-        k8s::{
-            ingress::{K8sIngressScore, PathType},
-            resource::K8sResourceScore,
-        },
-        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,
-            },
-        },
-        nats::capability::NatsCluster,
         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},
@@ -69,7 +37,6 @@ use super::super::{
     DeploymentTarget, HelmCommand, K8sclient, MultiTargetTopology, PreparationError,
     PreparationOutcome, Topology,
     k8s::K8sClient,
-    oberservability::monitoring::AlertReceiver,
     tenant::{
         TenantConfig, TenantManager,
         k8s::K8sTenantManager,
@@ -103,7 +70,6 @@ enum K8sSource {
 pub struct K8sAnywhereTopology {
     k8s_state: Arc<OnceCell<Option<K8sState>>>,
     tenant_manager: Arc<OnceCell<K8sTenantManager>>,
-    k8s_distribution: Arc<OnceCell<KubernetesDistribution>>,
     config: Arc<K8sAnywhereConfig>,
 }
 
@@ -184,216 +150,6 @@ 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
@@ -554,7 +310,6 @@ impl K8sAnywhereTopology {
         Self {
             k8s_state: Arc::new(OnceCell::new()),
             tenant_manager: Arc::new(OnceCell::new()),
-            k8s_distribution: Arc::new(OnceCell::new()),
             config: Arc::new(K8sAnywhereConfig::from_env()),
         }
     }
@@ -563,7 +318,6 @@ impl K8sAnywhereTopology {
         Self {
             k8s_state: Arc::new(OnceCell::new()),
             tenant_manager: Arc::new(OnceCell::new()),
-            k8s_distribution: Arc::new(OnceCell::new()),
             config: Arc::new(config),
         }
     }
@@ -600,56 +354,14 @@ impl K8sAnywhereTopology {
         }
     }
 
-    pub async fn get_k8s_distribution(&self) -> Result<&KubernetesDistribution, PreparationError> {
-        self.k8s_distribution
-            .get_or_try_init(async || {
-                debug!("Trying to detect k8s distribution");
-                let client = self.k8s_client().await.unwrap();
-
-                let discovery = client.discovery().await.map_err(|e| {
-                    PreparationError::new(format!("Could not discover API groups: {}", e))
-                })?;
-
-                let version = client.get_apiserver_version().await.map_err(|e| {
-                    PreparationError::new(format!("Could not get server version: {}", e))
-                })?;
-
-                // OpenShift / OKD
-                if discovery
-                    .groups()
-                    .any(|g| g.name() == "project.openshift.io")
-                {
-                    info!("Found KubernetesDistribution OpenshiftFamily");
-                    return Ok(KubernetesDistribution::OpenshiftFamily);
-                }
-
-                // K3d / K3s
-                if version.git_version.contains("k3s") {
-                    info!("Found KubernetesDistribution K3sFamily");
-                    return Ok(KubernetesDistribution::K3sFamily);
-                }
-
-                info!("Could not identify KubernetesDistribution, using Default");
-                return Ok(KubernetesDistribution::Default);
-            })
+    pub async fn get_k8s_distribution(&self) -> Result<KubernetesDistribution, PreparationError> {
+        self.k8s_client()
+            .await?
+            .get_k8s_distribution()
             .await
-    }
-
-    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)
+            .map_err(|e| {
+                PreparationError::new(format!("Failed to get k8s distribution from client : {e}"))
+            })
     }
 
     pub fn build_cluster_rolebinding(
@@ -701,141 +413,6 @@ 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 {
@@ -1001,137 +578,6 @@ 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)]

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

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

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

@@ -0,0 +1,147 @@
+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

@@ -0,0 +1,142 @@
+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

@@ -0,0 +1,5 @@
+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

@@ -0,0 +1,142 @@
+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

@@ -0,0 +1,147 @@
+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

@@ -0,0 +1,114 @@
+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> {
+        if let Some(receivers) = receivers {
+            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(),
+            })
+        } else {
+            Ok(PreparationOutcome::Noop)
+        }
+    }
+
+    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

@@ -1,7 +1,6 @@
 use std::{net::SocketAddr, str::FromStr};
 
 use async_trait::async_trait;
-use log::debug;
 use serde::Serialize;
 
 use super::LogicalHost;

harmony/src/domain/topology/mod.rs

@@ -2,6 +2,7 @@ pub mod decentralized;
 mod failover;
 mod ha_cluster;
 pub mod ingress;
+pub mod monitoring;
 pub mod node_exporter;
 pub mod opnsense;
 pub use failover::*;
@@ -11,7 +12,6 @@ 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

@@ -0,0 +1,234 @@
+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_route(&self) -> Result<serde_yaml::Value, InterpretError>;
+    fn build_receiver(&self) -> Result<serde_yaml::Value, 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()
+    }
+}
+
+///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/network.rs

@@ -188,6 +188,10 @@ impl FromStr for DnsRecordType {
 pub trait NetworkManager: Debug + Send + Sync {
     async fn ensure_network_manager_installed(&self) -> Result<(), NetworkError>;
     async fn configure_bond(&self, config: &HostNetworkConfig) -> Result<(), NetworkError>;
+    async fn configure_bond_on_primary_interface(
+        &self,
+        config: &HostNetworkConfig,
+    ) -> Result<(), NetworkError>;
 }
 
 #[derive(Debug, Clone, new)]

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

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

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

@@ -1,101 +0,0 @@
-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/infra/brocade.rs

@@ -5,9 +5,20 @@ use harmony_types::{
     net::{IpAddress, MacAddress},
     switch::{PortDeclaration, PortLocation},
 };
+use log::info;
 use option_ext::OptionExt;
 
-use crate::topology::{PortConfig, SwitchClient, SwitchError};
+use crate::{
+    modules::brocade::BrocadeSwitchAuth,
+    topology::{PortConfig, SwitchClient, SwitchError},
+};
+
+#[derive(Debug, Clone)]
+pub struct BrocadeSwitchConfig {
+    pub ips: Vec<IpAddress>,
+    pub auth: BrocadeSwitchAuth,
+    pub options: BrocadeOptions,
+}
 
 #[derive(Debug)]
 pub struct BrocadeSwitchClient {
@@ -15,13 +26,11 @@ pub struct BrocadeSwitchClient {
 }
 
 impl BrocadeSwitchClient {
-    pub async fn init(
-        ip_addresses: &[IpAddress],
-        username: &str,
-        password: &str,
-        options: BrocadeOptions,
-    ) -> Result<Self, brocade::Error> {
-        let brocade = brocade::init(ip_addresses, username, password, options).await?;
+    pub async fn init(config: BrocadeSwitchConfig) -> Result<Self, brocade::Error> {
+        let auth = &config.auth;
+        let options = &config.options;
+
+        let brocade = brocade::init(&config.ips, &auth.username, &auth.password, options).await?;
         Ok(Self { brocade })
     }
 }
@@ -52,13 +61,18 @@ impl SwitchClient for BrocadeSwitchClient {
                         || link.remote_port.contains(&interface.port_location)
                 })
             })
-            .map(|interface| (interface.name.clone(), PortOperatingMode::Access))
+            .map(|interface| (interface.name.clone(), PortOperatingMode::Trunk))
             .collect();
 
         if interfaces.is_empty() {
             return Ok(());
         }
 
+        info!("About to configure interfaces {interfaces:?}");
+        // inquire::Confirm::new("Do you wish to configures interfaces now?")
+        //     .prompt()
+        //     .map_err(|e| SwitchError::new(e.to_string()))?;
+
         self.brocade
             .configure_interfaces(&interfaces)
             .await
@@ -208,8 +222,8 @@ mod tests {
         //TODO not sure about this
         let configured_interfaces = brocade.configured_interfaces.lock().unwrap();
         assert_that!(*configured_interfaces).contains_exactly(vec![
-            (first_interface.name.clone(), PortOperatingMode::Access),
-            (second_interface.name.clone(), PortOperatingMode::Access),
+            (first_interface.name.clone(), PortOperatingMode::Trunk),
+            (second_interface.name.clone(), PortOperatingMode::Trunk),
         ]);
     }
 

harmony/src/infra/network_manager.rs

@@ -3,6 +3,7 @@ use std::{
     sync::Arc,
 };
 
+use askama::Template;
 use async_trait::async_trait;
 use harmony_types::id::Id;
 use k8s_openapi::api::core::v1::Node;
@@ -10,13 +11,71 @@ use kube::{
     ResourceExt,
     api::{ObjectList, ObjectMeta},
 };
-use log::{debug, info};
+use log::{debug, info, warn};
 
 use crate::{
     modules::okd::crd::nmstate,
-    topology::{HostNetworkConfig, NetworkError, NetworkManager, k8s::K8sClient},
+    topology::{
+        HostNetworkConfig, NetworkError, NetworkManager,
+        k8s::{DrainOptions, K8sClient, NodeFile},
+    },
 };
 
+/// NetworkManager bond configuration template
+#[derive(Template)]
+#[template(
+    source = r#"[connection]
+id={{ bond_name }}
+uuid={{ bond_uuid }}
+type=bond
+autoconnect-slaves=1
+interface-name={{ bond_name }}
+
+[bond]
+lacp_rate=fast
+mode=802.3ad
+xmit_hash_policy=layer2
+
+[ipv4]
+method=auto
+
+[ipv6]
+addr-gen-mode=default
+method=auto
+
+[proxy]
+"#,
+    ext = "txt"
+)]
+struct BondConfigTemplate {
+    bond_name: String,
+    bond_uuid: String,
+}
+
+/// NetworkManager bond slave configuration template
+#[derive(Template)]
+#[template(
+    source = r#"[connection]
+id={{ slave_id }}
+uuid={{ slave_uuid }}
+type=ethernet
+interface-name={{ interface_name }}
+master={{ bond_name }}
+slave-type=bond
+
+[ethernet]
+
+[bond-port]
+"#,
+    ext = "txt"
+)]
+struct BondSlaveConfigTemplate {
+    slave_id: String,
+    slave_uuid: String,
+    interface_name: String,
+    bond_name: String,
+}
+
 /// TODO document properly the non-intuitive behavior or "roll forward only" of nmstate in general
 /// It is documented in nmstate official doc, but worth mentionning here :
 ///
@@ -87,6 +146,117 @@ impl NetworkManager for OpenShiftNmStateNetworkManager {
         Ok(())
     }
 
+    /// Configures bonding on the primary network interface of a node.
+    ///
+    /// Changing the *primary* network interface (making it a bond
+    /// slave) will disrupt node connectivity mid-change, so the
+    /// procedure is:
+    ///
+    ///   1. Generate NetworkManager .nmconnection files
+    ///   2. Drain the node (includes cordon)
+    ///   3. Write configuration files to `/etc/NetworkManager/system-connections/`
+    ///   4. Attempt to reload NetworkManager (optional, best-effort)
+    ///   5. Reboot the node with full verification (drain, boot_id check, uncordon)
+    ///
+    /// The reboot procedure includes:
+    /// - Recording boot_id before reboot
+    /// - Fire-and-forget reboot command
+    /// - Waiting for NotReady status
+    /// - Waiting for Ready status
+    /// - Verifying boot_id changed
+    /// - Uncordoning the node
+    ///
+    /// See ADR-019 for context and rationale.
+    async fn configure_bond_on_primary_interface(
+        &self,
+        config: &HostNetworkConfig,
+    ) -> Result<(), NetworkError> {
+        use std::time::Duration;
+
+        let node_name = self.get_node_name_for_id(&config.host_id).await?;
+        let hostname = self.get_hostname(&config.host_id).await?;
+
+        info!(
+            "Configuring bond on primary interface for host '{}' (node '{}')",
+            config.host_id, node_name
+        );
+
+        // 1. Generate .nmconnection files
+        let files = self.generate_nmconnection_files(&hostname, config)?;
+        debug!(
+            "Generated {} NetworkManager configuration files",
+            files.len()
+        );
+
+        // 2. Write configuration files to the node (before draining)
+        // We do this while the node is still running for faster operation
+        info!(
+            "Writing NetworkManager configuration files to node '{}'...",
+            node_name
+        );
+        self.k8s_client
+            .write_files_to_node(&node_name, &files)
+            .await
+            .map_err(|e| {
+                NetworkError::new(format!(
+                    "Failed to write configuration files to node '{}': {}",
+                    node_name, e
+                ))
+            })?;
+
+        // 3. Reload NetworkManager configuration (best-effort)
+        // This won't activate the bond yet since the primary interface would lose connectivity,
+        // but it validates the configuration files are correct
+        info!(
+            "Reloading NetworkManager configuration on node '{}'...",
+            node_name
+        );
+        match self
+            .k8s_client
+            .run_privileged_command_on_node(&node_name, "chroot /host nmcli connection reload")
+            .await
+        {
+            Ok(output) => {
+                debug!("NetworkManager reload output: {}", output.trim());
+            }
+            Err(e) => {
+                warn!(
+                    "Failed to reload NetworkManager configuration: {}. Proceeding with reboot.",
+                    e
+                );
+                // Don't fail here - reboot will pick up the config anyway
+            }
+        }
+
+        // 4. Reboot the node with full verification
+        // The reboot_node function handles: drain, boot_id capture, reboot, NotReady wait,
+        // Ready wait, boot_id verification, and uncordon
+        // 60 minutes timeout for bare-metal environments (drain can take 20-30 mins)
+        let reboot_timeout = Duration::from_secs(3600);
+        info!(
+            "Rebooting node '{}' to apply network configuration (timeout: {:?})...",
+            node_name, reboot_timeout
+        );
+
+        self.k8s_client
+            .reboot_node(
+                &node_name,
+                &DrainOptions::default_ignore_daemonset_delete_emptydir_data(),
+                reboot_timeout,
+            )
+            .await
+            .map_err(|e| {
+                NetworkError::new(format!("Failed to reboot node '{}': {}", node_name, e))
+            })?;
+
+        info!(
+            "Successfully configured bond on primary interface for host '{}' (node '{}')",
+            config.host_id, node_name
+        );
+
+        Ok(())
+    }
+
     async fn configure_bond(&self, config: &HostNetworkConfig) -> Result<(), NetworkError> {
         let hostname = self.get_hostname(&config.host_id).await.map_err(|e| {
             NetworkError::new(format!(
@@ -208,14 +378,14 @@ impl OpenShiftNmStateNetworkManager {
         }
     }
 
-    async fn get_hostname(&self, host_id: &Id) -> Result<String, String> {
+    async fn get_node_for_id(&self, host_id: &Id) -> Result<Node, String> {
         let nodes: ObjectList<Node> = self
             .k8s_client
             .list_resources(None, None)
             .await
             .map_err(|e| format!("Failed to list nodes: {e}"))?;
 
-        let Some(node) = nodes.iter().find(|n| {
+        let Some(node) = nodes.into_iter().find(|n| {
             n.status
                 .as_ref()
                 .and_then(|s| s.node_info.as_ref())
@@ -225,6 +395,20 @@ impl OpenShiftNmStateNetworkManager {
             return Err(format!("No node found for host '{host_id}'"));
         };
 
+        Ok(node)
+    }
+
+    async fn get_node_name_for_id(&self, host_id: &Id) -> Result<String, String> {
+        let node = self.get_node_for_id(host_id).await?;
+
+        node.metadata.name.ok_or(format!(
+            "A node should always have a name, node for host_id {host_id} has no name"
+        ))
+    }
+
+    async fn get_hostname(&self, host_id: &Id) -> Result<String, String> {
+        let node = self.get_node_for_id(host_id).await?;
+
         node.labels()
             .get("kubernetes.io/hostname")
             .ok_or(format!(
@@ -261,4 +445,82 @@ impl OpenShiftNmStateNetworkManager {
         let next_id = (0..).find(|id| !used_ids.contains(id)).unwrap();
         Ok(format!("bond{next_id}"))
     }
+
+    /// Generates NetworkManager .nmconnection files for bonding configuration.
+    ///
+    /// Creates:
+    /// - One bond master configuration file (bond0.nmconnection)
+    /// - One slave configuration file per interface (bond0-<iface>.nmconnection)
+    ///
+    /// All files are placed in `/etc/NetworkManager/system-connections/` with
+    /// mode 0o600 (required by NetworkManager).
+    fn generate_nmconnection_files(
+        &self,
+        hostname: &str,
+        config: &HostNetworkConfig,
+    ) -> Result<Vec<NodeFile>, NetworkError> {
+        let mut files = Vec::new();
+        let bond_name = "bond0";
+        let bond_uuid = uuid::Uuid::new_v4().to_string();
+
+        // Generate bond master configuration
+        let bond_template = BondConfigTemplate {
+            bond_name: bond_name.to_string(),
+            bond_uuid: bond_uuid.clone(),
+        };
+
+        let bond_content = bond_template.render().map_err(|e| {
+            NetworkError::new(format!(
+                "Failed to render bond configuration template: {}",
+                e
+            ))
+        })?;
+
+        files.push(NodeFile {
+            path: format!(
+                "/etc/NetworkManager/system-connections/{}.nmconnection",
+                bond_name
+            ),
+            content: bond_content,
+            mode: 0o600,
+        });
+
+        // Generate slave configurations for each interface
+        for switch_port in &config.switch_ports {
+            let interface_name = &switch_port.interface.name;
+            let slave_id = format!("{}-{}", bond_name, interface_name);
+            let slave_uuid = uuid::Uuid::new_v4().to_string();
+
+            let slave_template = BondSlaveConfigTemplate {
+                slave_id: slave_id.clone(),
+                slave_uuid,
+                interface_name: interface_name.clone(),
+                bond_name: bond_name.to_string(),
+            };
+
+            let slave_content = slave_template.render().map_err(|e| {
+                NetworkError::new(format!(
+                    "Failed to render slave configuration template for interface '{}': {}",
+                    interface_name, e
+                ))
+            })?;
+
+            files.push(NodeFile {
+                path: format!(
+                    "/etc/NetworkManager/system-connections/{}.nmconnection",
+                    slave_id
+                ),
+                content: slave_content,
+                mode: 0o600,
+            });
+        }
+
+        debug!(
+            "Generated {} NetworkManager configuration files for host '{}'",
+            files.len(),
+            hostname
+        );
+
+        Ok(files)
+    }
 }

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

@@ -2,13 +2,15 @@ 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::AlertReceiver;
+use crate::topology::monitoring::Observability;
 use crate::{
     inventory::Inventory,
     modules::monitoring::{
@@ -17,10 +19,6 @@ 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;
@@ -30,12 +28,12 @@ use kube::api::ObjectMeta;
 use log::{debug, info};
 use schemars::JsonSchema;
 use serde::{Deserialize, Serialize};
-use std::sync::Arc;
+use std::sync::{Arc, Mutex};
 
 #[derive(Debug, Clone)]
 pub struct Monitoring {
     pub application: Arc<dyn Application>,
-    pub alert_receiver: Vec<Box<dyn AlertReceiver<CRDPrometheus>>>,
+    pub alert_receiver: Vec<Box<dyn AlertReceiver<Prometheus>>>,
 }
 
 #[async_trait]
@@ -46,8 +44,7 @@ impl<
         + TenantManager
         + K8sclient
         + MultiTargetTopology
-        + PrometheusMonitoring<CRDPrometheus>
-        + Grafana
+        + Observability<Prometheus>
         + Ingress
         + std::fmt::Debug,
 > ApplicationFeature<T> for Monitoring
@@ -74,10 +71,8 @@ impl<
         };
 
         let mut alerting_score = ApplicationMonitoringScore {
-            sender: CRDPrometheus {
-                namespace: namespace.clone(),
-                client: topology.k8s_client().await.unwrap(),
-                service_monitor: vec![app_service_monitor],
+            sender: Prometheus {
+                config: Arc::new(Mutex::new(PrometheusConfig::new())),
             },
             application: self.application.clone(),
             receivers: self.alert_receiver.clone(),
@@ -119,11 +114,12 @@ impl<
             ),
         };
 
-        alerting_score.receivers.push(Box::new(ntfy_receiver));
-        alerting_score
-            .interpret(&Inventory::empty(), topology)
-            .await
-            .map_err(|e| e.to_string())?;
+        todo!();
+        // alerting_score.receivers.push(Box::new(ntfy_receiver));
+        // alerting_score
+        //     .interpret(&Inventory::empty(), topology)
+        //     .await
+        //     .map_err(|e| e.to_string())?;
 
         Ok(InstallationOutcome::success())
     }

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

@@ -3,11 +3,13 @@ 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::kube_prometheus::crd::rhob_alertmanager_config::RHOBObservability;
+use crate::modules::monitoring::red_hat_cluster_observability::RedHatClusterObservability;
+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::AlertReceiver;
+use crate::topology::monitoring::Observability;
 use crate::{
     inventory::Inventory,
     modules::monitoring::{
@@ -16,10 +18,6 @@ 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;
@@ -28,9 +26,10 @@ use log::{debug, info};
 #[derive(Debug, Clone)]
 pub struct Monitoring {
     pub application: Arc<dyn Application>,
-    pub alert_receiver: Vec<Box<dyn AlertReceiver<RHOBObservability>>>,
+    pub alert_receiver: Vec<Box<dyn AlertReceiver<RedHatClusterObservability>>>,
 }
 
+///TODO TEST this
 #[async_trait]
 impl<
     T: Topology
@@ -41,7 +40,7 @@ impl<
         + MultiTargetTopology
         + Ingress
         + std::fmt::Debug
-        + PrometheusMonitoring<RHOBObservability>,
+        + Observability<RedHatClusterObservability>,
 > ApplicationFeature<T> for Monitoring
 {
     async fn ensure_installed(
@@ -55,13 +54,14 @@ impl<
             .map(|ns| ns.name.clone())
             .unwrap_or_else(|| self.application.name());
 
-        let mut alerting_score = ApplicationRHOBMonitoringScore {
-            sender: RHOBObservability {
+        let mut alerting_score = RedHatClusterObservabilityScore {
+            sender: RedHatClusterObservability {
                 namespace: namespace.clone(),
-                client: topology.k8s_client().await.unwrap(),
+                resource_selector: todo!(),
             },
-            application: self.application.clone(),
             receivers: self.alert_receiver.clone(),
+            rules: vec![],
+            scrape_targets: None,
         };
         let domain = topology
             .get_domain("ntfy")

harmony/src/modules/brocade/brocade.rs

@@ -0,0 +1,138 @@
+use async_trait::async_trait;
+use brocade::{BrocadeOptions, PortOperatingMode};
+
+use crate::{
+    data::Version,
+    infra::brocade::{BrocadeSwitchClient, BrocadeSwitchConfig},
+    interpret::{Interpret, InterpretError, InterpretName, InterpretStatus, Outcome},
+    inventory::Inventory,
+    score::Score,
+    topology::{
+        HostNetworkConfig, PortConfig, PreparationError, PreparationOutcome, Switch, SwitchClient,
+        SwitchError, Topology,
+    },
+};
+use harmony_macros::ip;
+use harmony_types::{id::Id, net::MacAddress, switch::PortLocation};
+use log::{debug, info};
+use serde::Serialize;
+
+#[derive(Clone, Debug, Serialize)]
+pub struct BrocadeSwitchScore {
+    pub port_channels_to_clear: Vec<Id>,
+    pub ports_to_configure: Vec<PortConfig>,
+}
+
+impl<T: Topology + Switch> Score<T> for BrocadeSwitchScore {
+    fn name(&self) -> String {
+        "BrocadeSwitchScore".to_string()
+    }
+
+    #[doc(hidden)]
+    fn create_interpret(&self) -> Box<dyn Interpret<T>> {
+        Box::new(BrocadeSwitchInterpret {
+            score: self.clone(),
+        })
+    }
+}
+
+#[derive(Debug)]
+pub struct BrocadeSwitchInterpret {
+    score: BrocadeSwitchScore,
+}
+
+#[async_trait]
+impl<T: Topology + Switch> Interpret<T> for BrocadeSwitchInterpret {
+    async fn execute(
+        &self,
+        _inventory: &Inventory,
+        topology: &T,
+    ) -> Result<Outcome, InterpretError> {
+        info!("Applying switch configuration {:?}", self.score);
+        debug!(
+            "Clearing port channel {:?}",
+            self.score.port_channels_to_clear
+        );
+        topology
+            .clear_port_channel(&self.score.port_channels_to_clear)
+            .await
+            .map_err(|e| InterpretError::new(e.to_string()))?;
+        debug!("Configuring interfaces {:?}", self.score.ports_to_configure);
+        topology
+            .configure_interface(&self.score.ports_to_configure)
+            .await
+            .map_err(|e| InterpretError::new(e.to_string()))?;
+        Ok(Outcome::success("switch configured".to_string()))
+    }
+    fn get_name(&self) -> InterpretName {
+        InterpretName::Custom("BrocadeSwitchInterpret")
+    }
+    fn get_version(&self) -> Version {
+        todo!()
+    }
+    fn get_status(&self) -> InterpretStatus {
+        todo!()
+    }
+    fn get_children(&self) -> Vec<Id> {
+        todo!()
+    }
+}
+
+/*
+pub struct BrocadeSwitchConfig {
+    pub ips: Vec<harmony_types::net::IpAddress>,
+    pub username: String,
+    pub password: String,
+    pub options: BrocadeOptions,
+}
+*/
+
+pub struct SwitchTopology {
+    client: Box<dyn SwitchClient>,
+}
+
+#[async_trait]
+impl Topology for SwitchTopology {
+    fn name(&self) -> &str {
+        "SwitchTopology"
+    }
+
+    async fn ensure_ready(&self) -> Result<PreparationOutcome, PreparationError> {
+        Ok(PreparationOutcome::Noop)
+    }
+}
+
+impl SwitchTopology {
+    pub async fn new(config: BrocadeSwitchConfig) -> Self {
+        let client = BrocadeSwitchClient::init(config)
+            .await
+            .expect("Failed to connect to switch");
+
+        let client = Box::new(client);
+        Self { client }
+    }
+}
+
+#[async_trait]
+impl Switch for SwitchTopology {
+    async fn setup_switch(&self) -> Result<(), SwitchError> {
+        todo!()
+    }
+
+    async fn get_port_for_mac_address(
+        &self,
+        _mac_address: &MacAddress,
+    ) -> Result<Option<PortLocation>, SwitchError> {
+        todo!()
+    }
+
+    async fn configure_port_channel(&self, _config: &HostNetworkConfig) -> Result<(), SwitchError> {
+        todo!()
+    }
+    async fn clear_port_channel(&self, ids: &Vec<Id>) -> Result<(), SwitchError> {
+        self.client.clear_port_channel(ids).await
+    }
+    async fn configure_interface(&self, ports: &Vec<PortConfig>) -> Result<(), SwitchError> {
+        self.client.configure_interface(ports).await
+    }
+}

harmony/src/modules/brocade/brocade_snmp.rs

@@ -39,16 +39,16 @@ pub struct BrocadeEnableSnmpInterpret {
 }
 
 #[derive(Secret, Clone, Debug, JsonSchema, Serialize, Deserialize)]
-struct BrocadeSwitchAuth {
-    username: String,
-    password: String,
+pub struct BrocadeSwitchAuth {
+    pub username: String,
+    pub password: String,
 }
 
 #[derive(Secret, Clone, Debug, JsonSchema, Serialize, Deserialize)]
-struct BrocadeSnmpAuth {
-    username: String,
-    auth_password: String,
-    des_password: String,
+pub struct BrocadeSnmpAuth {
+    pub username: String,
+    pub auth_password: String,
+    pub des_password: String,
 }
 
 #[async_trait]
@@ -72,7 +72,7 @@ impl<T: Topology> Interpret<T> for BrocadeEnableSnmpInterpret {
             &switch_addresses,
             &config.username,
             &config.password,
-            BrocadeOptions {
+            &BrocadeOptions {
                 dry_run: self.score.dry_run,
                 ..Default::default()
             },

harmony/src/modules/brocade/mod.rs

@@ -0,0 +1,5 @@
+pub mod brocade;
+pub use brocade::*;
+
+pub mod brocade_snmp;
+pub use brocade_snmp::*;

harmony/src/modules/inventory/discovery.rs

@@ -82,17 +82,40 @@ impl<T: Topology> Interpret<T> for DiscoverHostForRoleInterpret {
                         self.score.role,
                         choice.summary()
                     );
-                    let disk_names: Vec<String> =
-                        choice.storage.iter().map(|s| s.name.clone()).collect();
+                    let mut disk_choices: Vec<(String, String)> = vec![];
+
+                    for s in choice.storage.iter() {
+                        let size_gb: f64 = s.size_bytes as f64 / 1_000_000_000.0;
+                        let (size, unit) = if size_gb >= 1000.0 {
+                            (size_gb / 1000.0, "TB")
+                        } else {
+                            (size_gb, "GB")
+                        };
+                        let drive_type = if s.rotational { "rotational" } else { "SSD" };
+                        let smart_str = s.smart_status.as_deref().unwrap_or("N/A");
+                        let display = format!(
+                            "{} : [{}] - {:.0} {} ({}) - {} - Smart: {}",
+                            s.name, s.model, size, unit, drive_type, s.interface_type, smart_str
+                        );
+                        disk_choices.push((display, s.name.clone()));
+                    }
+
+                    let display_refs: Vec<&str> =
+                        disk_choices.iter().map(|(d, _)| d.as_str()).collect();
 
                     let disk_choice = inquire::Select::new(
                         &format!("Select the disk to use on host {}:", choice.summary()),
-                        disk_names,
+                        display_refs,
                     )
                     .prompt();
 
                     match disk_choice {
-                        Ok(disk_name) => {
+                        Ok(selected_display) => {
+                            let disk_name = disk_choices
+                                .iter()
+                                .find(|(d, _)| d.as_str() == selected_display)
+                                .map(|(_, name)| name.clone())
+                                .unwrap();
                             info!("Selected disk {} for node {}", disk_name, choice.summary());
                             host_repo
                                 .save_role_mapping(&self.score.role, &choice, &disk_name)

harmony/src/modules/k8s/resource.rs

@@ -9,7 +9,7 @@ use crate::{
     interpret::{Interpret, InterpretError, InterpretName, InterpretStatus, Outcome},
     inventory::Inventory,
     score::Score,
-    topology::{K8sclient, Topology},
+    topology::{K8sclient, Topology, k8s::ApplyStrategy},
 };
 use harmony_types::id::Id;
 
@@ -29,7 +29,7 @@ impl<K: Resource + std::fmt::Debug> K8sResourceScore<K> {
 }
 
 impl<
-    K: Resource<Scope = NamespaceResourceScope>
+    K: Resource
         + std::fmt::Debug
         + Sync
         + DeserializeOwned
@@ -42,6 +42,7 @@ impl<
 > Score<T> for K8sResourceScore<K>
 where
     <K as kube::Resource>::DynamicType: Default,
+    <K as kube::Resource>::Scope: ApplyStrategy<K>,
 {
     fn create_interpret(&self) -> Box<dyn Interpret<T>> {
         Box::new(K8sResourceInterpret {
@@ -61,7 +62,7 @@ pub struct K8sResourceInterpret<K: Resource + std::fmt::Debug + Sync + Send> {
 
 #[async_trait]
 impl<
-    K: Resource<Scope = NamespaceResourceScope>
+    K: Resource
         + Clone
         + std::fmt::Debug
         + DeserializeOwned
@@ -73,6 +74,7 @@ impl<
 > Interpret<T> for K8sResourceInterpret<K>
 where
     <K as kube::Resource>::DynamicType: Default,
+    <K as kube::Resource>::Scope: ApplyStrategy<K>,
 {
     async fn execute(
         &self,

harmony/src/modules/mod.rs

@@ -18,7 +18,6 @@ pub mod network;
 pub mod okd;
 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

@@ -1,98 +1,54 @@
-use std::any::Any;
-use std::collections::{BTreeMap, HashMap};
+use std::collections::BTreeMap;
 
-use async_trait::async_trait;
-use harmony_types::k8s_name::K8sName;
+use crate::modules::monitoring::kube_prometheus::KubePrometheus;
+use crate::modules::monitoring::okd::OpenshiftClusterAlertSender;
+use crate::modules::monitoring::red_hat_cluster_observability::RedHatClusterObservability;
+use crate::topology::monitoring::{AlertRoute, MatchOp};
+use crate::{interpret::InterpretError, topology::monitoring::AlertReceiver};
+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 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 DiscordWebhook {
-    pub name: K8sName,
+pub struct DiscordReceiver {
+    pub name: String,
     pub url: Url,
-    pub selectors: Vec<HashMap<String, String>>,
+    pub route: AlertRoute,
 }
 
-impl DiscordWebhook {
-    fn get_receiver_config(&self) -> Result<AlertManagerReceiver, String> {
-        let secret_name = format!("{}-secret", self.name.clone());
-        let webhook_key = format!("{}", self.url.clone());
+impl AlertReceiver<OpenshiftClusterAlertSender> for DiscordReceiver {
+    fn build_route(&self) -> Result<serde_yaml::Value, InterpretError> {
+        let matchers: Vec<String> = self
+            .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();
 
-        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": [
-                    {
-                    "webhook_url": self.url.clone(),
-                    "title": "{{ template \"discord.default.title\" . }}",
-                    "message": "{{ template \"discord.default.message\" . }}"
-                    }
-                ]
-            }),
-            route_config: json!({
-                "receiver": self.name,
-                "matchers": matchers,
-
-            }),
-        })
+        let route_block = serde_yaml::to_value(json!({
+            "receiver": self.name,
+            "matchers": matchers,
+        }))
+        .unwrap();
+        Ok(route_block)
     }
-}
 
-#[async_trait]
-impl AlertReceiver<OpenshiftClusterAlertSender> for DiscordWebhook {
-    async fn install(
-        &self,
-        sender: &OpenshiftClusterAlertSender,
-    ) -> Result<Outcome, InterpretError> {
-        todo!()
+    fn build_receiver(&self) -> Result<serde_yaml::Value, InterpretError> {
+        let receiver_block = serde_yaml::to_value(json!({
+            "name": self.name,
+            "discord_configs": [{
+                "webhook_url": format!("{}", self.url),
+                "title": "{{ template \"discord.default.title\" . }}",
+                "message": "{{ template \"discord.default.message\" . }}"
+            }]
+        }))
+        .map_err(|e| InterpretError::new(e.to_string()))?;
+        Ok(receiver_block)
     }
 
     fn name(&self) -> String {
@@ -102,93 +58,16 @@ impl AlertReceiver<OpenshiftClusterAlertSender> for DiscordWebhook {
     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()
-    }
 }
 
-#[async_trait]
-impl AlertReceiver<RHOBObservability> for DiscordWebhook {
-    fn as_alertmanager_receiver(&self) -> Result<AlertManagerReceiver, String> {
-        todo!()
+impl AlertReceiver<RedHatClusterObservability> for DiscordReceiver {
+    fn build_route(&self) -> Result<serde_yaml::Value, InterpretError> {
+        serde_yaml::to_value(&self.route).map_err(|e| InterpretError::new(e.to_string()))
     }
 
-    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();
+    fn build_receiver(&self) -> Result<serde_yaml::Value, InterpretError> {
+        //FIXME this secret needs to be applied so that the discord Configs for RedHatCO
+        //CRD AlertmanagerConfigs can access the URL
         let secret_name = format!("{}-secret", self.name.clone());
         let webhook_key = format!("{}", self.url.clone());
 
@@ -205,206 +84,54 @@ impl AlertReceiver<CRDPrometheus> for DiscordWebhook {
             ..Default::default()
         };
 
-        let _ = sender.client.apply(&secret, Some(&ns)).await;
-
-        let spec = AlertmanagerConfigSpec {
-            data: json!({
-                "route": {
-                    "receiver": self.name,
-                },
-                "receivers": [
-                    {
-                        "name": self.name,
-                        "discordConfigs": [
-                            {
-                            "apiURL": {
-                                "name": secret_name,
-                                "key":  "webhook-url",
-                            },
-                            "title": "{{ template \"discord.default.title\" . }}",
-                            "message": "{{ template \"discord.default.message\" . }}"
-                            }
-                        ]
-                    }
-                ]
-            }),
-        };
-
-        let alertmanager_configs = AlertmanagerConfig {
-            metadata: ObjectMeta {
-                name: Some(self.name.clone().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
-        )))
+        let receiver_config = json!({
+            "name": self.name,
+            "discordConfigs": [
+                {
+                    "apiURL": {
+                        "key": "webhook-url",
+                        "name": format!("{}-secret", self.name)
+                    },
+                    "title": "{{ template \"discord.default.title\" . }}",
+                    "message": "{{ template \"discord.default.message\" . }}"
+                }
+            ]
+        });
+        serde_yaml::to_value(receiver_config).map_err(|e| InterpretError::new(e.to_string()))
     }
+
     fn name(&self) -> String {
-        "discord-webhook".to_string()
+        self.name.clone()
     }
-    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
-    }
 }
 
-#[async_trait]
-impl AlertReceiver<Prometheus> for DiscordWebhook {
-    fn as_alertmanager_receiver(&self) -> Result<AlertManagerReceiver, String> {
-        todo!()
+impl AlertReceiver<KubePrometheus> for DiscordReceiver {
+    fn build_route(&self) -> Result<serde_yaml::Value, InterpretError> {
+        serde_yaml::to_value(self.route.clone()).map_err(|e| InterpretError::new(e.to_string()))
     }
-    async fn install(&self, sender: &Prometheus) -> Result<Outcome, InterpretError> {
-        sender.install_receiver(self).await
+
+    fn build_receiver(&self) -> Result<serde_yaml::Value, InterpretError> {
+        let receiver_block = serde_yaml::to_value(json!({
+            "name": self.name,
+            "discord_configs": [{
+                "webhook_url": format!("{}", self.url),
+                "title": "{{ template \"discord.default.title\" . }}",
+                "message": "{{ template \"discord.default.message\" . }}"
+            }]
+        }))
+        .map_err(|e| InterpretError::new(e.to_string()))?;
+        Ok(receiver_block)
     }
+
     fn name(&self) -> String {
-        "discord-webhook".to_string()
+        self.name.clone()
     }
-    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

@@ -1,25 +1,13 @@
-use std::any::Any;
-
-use async_trait::async_trait;
-use kube::api::ObjectMeta;
-use log::debug;
 use serde::Serialize;
 use serde_json::json;
-use serde_yaml::{Mapping, Value};
 
 use crate::{
-    interpret::{InterpretError, Outcome},
+    interpret::InterpretError,
     modules::monitoring::{
-        kube_prometheus::{
-            crd::{
-                crd_alertmanager_config::CRDPrometheus, rhob_alertmanager_config::RHOBObservability,
-            },
-            prometheus::{KubePrometheus, KubePrometheusReceiver},
-            types::{AlertChannelConfig, AlertManagerChannelConfig},
-        },
-        prometheus::prometheus::{Prometheus, PrometheusReceiver},
+        kube_prometheus::KubePrometheus, okd::OpenshiftClusterAlertSender, prometheus::Prometheus,
+        red_hat_cluster_observability::RedHatClusterObservability,
     },
-    topology::oberservability::monitoring::{AlertManagerReceiver, AlertReceiver},
+    topology::monitoring::AlertReceiver,
 };
 use harmony_types::net::Url;
 
@@ -29,279 +17,104 @@ pub struct WebhookReceiver {
     pub url: Url,
 }
 
-#[async_trait]
-impl AlertReceiver<RHOBObservability> for WebhookReceiver {
-    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": [
-                            {
-                            "url": self.url,
-                            "httpConfig": {
-                                "tlsConfig": {
-                                    "insecureSkipVerify": true
-                                    }
-                                }
-                            }
-                        ]
+impl WebhookReceiver {
+    fn build_receiver(&self) -> serde_json::Value {
+        json!({
+        "name": self.name,
+        "webhookConfigs": [
+            {
+            "url": self.url,
+            "httpConfig": {
+                "tlsConfig": {
+                    "insecureSkipVerify": true
                     }
-                ]
-            }),
-        };
-
-        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 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
+    fn build_route(&self) -> serde_json::Value {
+        json!({
+            "name": self.name})
     }
 }
 
-#[async_trait]
-impl AlertReceiver<CRDPrometheus> for WebhookReceiver {
-    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
-        )))
+impl AlertReceiver<OpenshiftClusterAlertSender> for WebhookReceiver {
+    fn build_receiver(&self) -> Result<serde_yaml::Value, InterpretError> {
+        let receiver = self.build_receiver();
+        serde_yaml::to_value(receiver).map_err(|e| InterpretError::new(e.to_string()))
     }
 
-    fn name(&self) -> String {
-        "webhook-receiver".to_string()
+    fn build_route(&self) -> Result<serde_yaml::Value, InterpretError> {
+        let route = self.build_route();
+        serde_yaml::to_value(route).map_err(|e| InterpretError::new(e.to_string()))
     }
 
-    fn clone_box(&self) -> Box<dyn AlertReceiver<CRDPrometheus>> {
-        Box::new(self.clone())
-    }
-
-    fn as_any(&self) -> &dyn Any {
-        self
-    }
-}
-
-#[async_trait]
-impl AlertReceiver<Prometheus> for WebhookReceiver {
-    fn as_alertmanager_receiver(&self) -> Result<AlertManagerReceiver, String> {
-        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 {
-        self
-    }
-}
-
-#[async_trait]
-impl PrometheusReceiver for WebhookReceiver {
     fn name(&self) -> String {
         self.name.clone()
     }
-    async fn configure_receiver(&self) -> AlertManagerChannelConfig {
-        self.get_config().await
+
+    fn clone_box(&self) -> Box<dyn AlertReceiver<OpenshiftClusterAlertSender>> {
+        Box::new(self.clone())
     }
 }
 
-#[async_trait]
-impl AlertReceiver<KubePrometheus> for WebhookReceiver {
-    fn as_alertmanager_receiver(&self) -> Result<AlertManagerReceiver, String> {
-        todo!()
+impl AlertReceiver<RedHatClusterObservability> for WebhookReceiver {
+    fn build_receiver(&self) -> Result<serde_yaml::Value, InterpretError> {
+        let receiver = self.build_receiver();
+        serde_yaml::to_value(receiver).map_err(|e| InterpretError::new(e.to_string()))
     }
-    async fn install(&self, sender: &KubePrometheus) -> Result<Outcome, InterpretError> {
-        sender.install_receiver(self).await
+
+    fn build_route(&self) -> Result<serde_yaml::Value, InterpretError> {
+        let route = self.build_route();
+        serde_yaml::to_value(route).map_err(|e| InterpretError::new(e.to_string()))
     }
+
     fn name(&self) -> String {
-        "webhook-receiver".to_string()
+        self.name.clone()
     }
+
+    fn clone_box(&self) -> Box<dyn AlertReceiver<RedHatClusterObservability>> {
+        Box::new(self.clone())
+    }
+}
+
+impl AlertReceiver<KubePrometheus> for WebhookReceiver {
+    fn build_receiver(&self) -> Result<serde_yaml::Value, InterpretError> {
+        let receiver = self.build_receiver();
+        serde_yaml::to_value(receiver).map_err(|e| InterpretError::new(e.to_string()))
+    }
+
+    fn build_route(&self) -> Result<serde_yaml::Value, InterpretError> {
+        let route = self.build_route();
+        serde_yaml::to_value(route).map_err(|e| InterpretError::new(e.to_string()))
+    }
+
+    fn name(&self) -> String {
+        self.name.clone()
+    }
+
     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 {
+impl AlertReceiver<Prometheus> for WebhookReceiver {
+    fn build_receiver(&self) -> Result<serde_yaml::Value, InterpretError> {
+        let receiver = self.build_receiver();
+        serde_yaml::to_value(receiver).map_err(|e| InterpretError::new(e.to_string()))
+    }
+
+    fn build_route(&self) -> Result<serde_yaml::Value, InterpretError> {
+        let route = self.build_route();
+        serde_yaml::to_value(route).map_err(|e| InterpretError::new(e.to_string()))
+    }
+
     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);
+
+    fn clone_box(&self) -> Box<dyn AlertReceiver<Prometheus>> {
+        Box::new(self.clone())
     }
 }

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

@@ -1 +1,2 @@
 pub mod dell_server;
+pub mod opnsense;

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

@@ -0,0 +1,15 @@
+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 +1,2 @@
+pub mod alerts;
 pub mod prometheus_alert_rule;

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

@@ -1,79 +1,13 @@
-use std::collections::{BTreeMap, HashMap};
+use std::collections::HashMap;
 
-use async_trait::async_trait;
 use serde::Serialize;
 
 use crate::{
-    interpret::{InterpretError, Outcome},
-    modules::monitoring::{
-        kube_prometheus::{
-            prometheus::{KubePrometheus, KubePrometheusRule},
-            types::{AlertGroup, AlertManagerAdditionalPromRules},
-        },
-        prometheus::prometheus::{Prometheus, PrometheusRule},
-    },
-    topology::oberservability::monitoring::AlertRule,
+    interpret::InterpretError,
+    modules::monitoring::{kube_prometheus::KubePrometheus, okd::OpenshiftClusterAlertSender},
+    topology::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 {
@@ -129,3 +63,55 @@ 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

@@ -5,32 +5,26 @@ use serde::Serialize;
 
 use crate::{
     interpret::Interpret,
-    modules::{
-        application::Application,
-        monitoring::{
-            grafana::grafana::Grafana, kube_prometheus::crd::crd_alertmanager_config::CRDPrometheus,
-        },
-        prometheus::prometheus::PrometheusMonitoring,
-    },
+    modules::{application::Application, monitoring::prometheus::Prometheus},
     score::Score,
     topology::{
         K8sclient, Topology,
-        oberservability::monitoring::{AlertReceiver, AlertingInterpret, ScrapeTarget},
+        monitoring::{AlertReceiver, AlertingInterpret, Observability, ScrapeTarget},
     },
 };
 
 #[derive(Debug, Clone, Serialize)]
 pub struct ApplicationMonitoringScore {
-    pub sender: CRDPrometheus,
+    pub sender: Prometheus,
     pub application: Arc<dyn Application>,
-    pub receivers: Vec<Box<dyn AlertReceiver<CRDPrometheus>>>,
+    pub receivers: Vec<Box<dyn AlertReceiver<Prometheus>>>,
 }
 
-impl<T: Topology + PrometheusMonitoring<CRDPrometheus> + K8sclient + Grafana> Score<T>
-    for ApplicationMonitoringScore
-{
+impl<T: Topology + Observability<Prometheus> + K8sclient> 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

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

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

@@ -1,17 +1,48 @@
 use async_trait::async_trait;
-use k8s_openapi::Resource;
+use serde::Serialize;
 
 use crate::{
     inventory::Inventory,
-    topology::{PreparationError, PreparationOutcome},
+    topology::{
+        PreparationError, PreparationOutcome,
+        monitoring::{AlertReceiver, AlertRule, AlertSender, ScrapeTarget},
+    },
 };
 
-#[async_trait]
-pub trait Grafana {
-    async fn ensure_grafana_operator(
-        &self,
-        inventory: &Inventory,
-    ) -> Result<PreparationOutcome, PreparationError>;
-
-    async fn install_grafana(&self) -> Result<PreparationOutcome, PreparationError>;
+#[derive(Debug, Clone, Serialize)]
+pub struct Grafana {
+    pub namespace: String,
+}
+
+impl AlertSender for Grafana {
+    fn name(&self) -> String {
+        "grafana".to_string()
+    }
+}
+
+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

@@ -0,0 +1,32 @@
+use serde::Serialize;
+
+use crate::{
+    modules::monitoring::grafana::grafana::Grafana,
+    score::Score,
+    topology::{
+        HelmCommand, 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

@@ -1,28 +0,0 @@
-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

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

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

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

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

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

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

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

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

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

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

@@ -0,0 +1,7 @@
+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

@@ -0,0 +1,54 @@
+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

@@ -0,0 +1,24 @@
+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

@@ -0,0 +1,83 @@
+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

@@ -0,0 +1,67 @@
+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

@@ -0,0 +1,189 @@
+use serde::Serialize;
+
+use crate::{
+    interpret::Interpret,
+    modules::monitoring::grafana::grafana::Grafana,
+    score::Score,
+    topology::{K8sclient, Topology},
+};
+
+#[derive(Debug, Clone, Serialize)]
+pub struct GrafanaK8sInstallScore {
+    pub sender: Grafana,
+}
+
+impl<T: Topology + K8sclient> Score<T> for GrafanaK8sInstallScore {
+    fn name(&self) -> String {
+        "GrafanaK8sEnsureReadyScore".to_string()
+    }
+
+    fn create_interpret(&self) -> Box<dyn Interpret<T>> {
+        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

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

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

@@ -1,91 +1,17 @@
-use std::sync::Arc;
-
-use async_trait::async_trait;
 use kube::CustomResource;
 use schemars::JsonSchema;
 use serde::{Deserialize, Serialize};
 
-use crate::{
-    interpret::{InterpretError, Outcome},
-    inventory::Inventory,
-    modules::{
-        monitoring::{
-            grafana::grafana::Grafana, kube_prometheus::crd::service_monitor::ServiceMonitor,
-        },
-        prometheus::prometheus::PrometheusMonitoring,
-    },
-    topology::{
-        K8sclient, Topology,
-        installable::Installable,
-        k8s::K8sClient,
-        oberservability::monitoring::{AlertReceiver, AlertSender, ScrapeTarget},
-    },
-};
-
-#[derive(CustomResource, Serialize, Deserialize, Debug, Clone, JsonSchema)]
+#[derive(CustomResource, Serialize, Deserialize, Default, Debug, Clone, JsonSchema)]
 #[kube(
     group = "monitoring.coreos.com",
-    version = "v1alpha1",
+    version = "v1",
     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::prometheus::alerts::k8s::{
+use crate::modules::monitoring::alert_rule::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_prometheus_rules.rs

@@ -6,13 +6,14 @@ use serde::{Deserialize, Serialize};
 
 use crate::modules::monitoring::alert_rule::prometheus_alert_rule::PrometheusAlertRule;
 
-#[derive(CustomResource, Debug, Serialize, Deserialize, Clone, JsonSchema)]
+#[derive(CustomResource, Default, 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

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