demo: describe the storyline of the talk

Reviewed-on: #125

.cargo/config.toml

@@ -0,0 +1,5 @@
+[target.x86_64-pc-windows-msvc]
+rustflags = ["-C", "link-arg=/STACK:8000000"]
+
+[target.x86_64-pc-windows-gnu]
+rustflags = ["-C", "link-arg=-Wl,--stack,8000000"]

.dockerignore

@@ -0,0 +1,2 @@
+target/
+Dockerfile

.gitea/workflows/check.yml

@@ -0,0 +1,18 @@
+name: Run Check Script
+on:
+  push:
+    branches:
+      - master
+  pull_request:
+
+jobs:
+  check:
+    runs-on: docker
+    container:
+      image: hub.nationtech.io/harmony/harmony_composer:latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Run check script
+        run: bash check.sh

.gitea/workflows/harmony_composer.yaml

@@ -0,0 +1,95 @@
+name: Compile and package harmony_composer
+on:
+  push:
+    branches:
+      - master
+
+jobs:
+  package_harmony_composer:
+    container:
+      image: hub.nationtech.io/harmony/harmony_composer:latest
+    runs-on: dind
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Build for Linux x86_64
+        run: cargo build --release --bin harmony_composer --target x86_64-unknown-linux-gnu
+
+      - name: Build for Windows x86_64 GNU
+        run: cargo build --release --bin harmony_composer --target x86_64-pc-windows-gnu
+
+      - name: Setup log into hub.nationtech.io
+        uses: docker/login-action@v3
+        with:
+          registry: hub.nationtech.io
+          username: ${{ secrets.HUB_BOT_USER }}
+          password: ${{ secrets.HUB_BOT_PASSWORD }}
+
+      # TODO: build ARM images and MacOS binaries (or other targets) too
+
+      - name: Update snapshot-latest tag
+        run: |
+          git config user.name "Gitea CI"
+          git config user.email "ci@nationtech.io"
+          git tag -f snapshot-latest
+          git push origin snapshot-latest --force
+
+      - name: Install jq
+        run: apt install -y jq # The current image includes apt lists so we don't have to apt update and rm /var/lib/apt... every time. But if the image is optimized it won't work anymore
+
+      - name: Create or update release
+        run: |
+          # First, check if release exists and delete it if it does
+          RELEASE_ID=$(curl -s -X GET \
+            -H "Authorization: token ${{ secrets.GITEATOKEN }}" \
+            "https://git.nationtech.io/api/v1/repos/nationtech/harmony/releases/tags/snapshot-latest" \
+            | jq -r '.id // empty')
+
+          if [ -n "$RELEASE_ID" ]; then
+            # Delete existing release
+            curl -X DELETE \
+              -H "Authorization: token ${{ secrets.GITEATOKEN }}" \
+              "https://git.nationtech.io/api/v1/repos/nationtech/harmony/releases/$RELEASE_ID"
+          fi
+
+          # Create new release
+          RESPONSE=$(curl -X POST \
+            -H "Authorization: token ${{ secrets.GITEATOKEN }}" \
+            -H "Content-Type: application/json" \
+            -d '{
+              "tag_name": "snapshot-latest",
+              "name": "Latest Snapshot",
+              "body": "Automated snapshot build from master branch",
+              "draft": false,
+              "prerelease": true
+            }' \
+            "https://git.nationtech.io/api/v1/repos/nationtech/harmony/releases")
+
+          echo "RELEASE_ID=$(echo $RESPONSE | jq -r '.id')" >> $GITHUB_ENV
+
+      - name: Upload Linux binary
+        run: |
+          curl -X POST \
+            -H "Authorization: token ${{ secrets.GITEATOKEN }}" \
+            -H "Content-Type: application/octet-stream" \
+            --data-binary "@target/x86_64-unknown-linux-gnu/release/harmony_composer" \
+            "https://git.nationtech.io/api/v1/repos/nationtech/harmony/releases/${{ env.RELEASE_ID }}/assets?name=harmony_composer"
+
+      - name: Upload Windows binary
+        run: |
+          curl -X POST \
+            -H "Authorization: token ${{ secrets.GITEATOKEN }}" \
+            -H "Content-Type: application/octet-stream" \
+            --data-binary "@target/x86_64-pc-windows-gnu/release/harmony_composer.exe" \
+            "https://git.nationtech.io/api/v1/repos/nationtech/harmony/releases/${{ env.RELEASE_ID }}/assets?name=harmony_composer.exe"
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Build and push
+        uses: docker/build-push-action@v6
+        with:
+          context: .
+          push: true
+          tags: hub.nationtech.io/harmony/harmony_composer:latest

.gitignore

@@ -1,3 +1,25 @@
-target
-private_repos
-log/
+### General ###
+private_repos/
+
+### Harmony ###
+harmony.log
+
+### Helm ###
+# Chart dependencies
+**/charts/*.tgz
+
+### Rust ###
+# Generated by Cargo
+# will have compiled files and executables
+debug/
+target/
+
+# Remove Cargo.lock from gitignore if creating an executable, leave it for libraries
+# More information here https://doc.rust-lang.org/cargo/guide/cargo-toml-vs-cargo-lock.html
+Cargo.lock
+
+# These are backup files generated by rustfmt
+**/*.rs.bk
+
+# MSVC Windows builds of rustc generate these, which store debugging information
+*.pdb

.sqlx/query-934035c7ca6e064815393e4e049a7934b0a7fac04a4fe4b2a354f0443d630990.json

@@ -0,0 +1,32 @@
+{
+  "db_name": "SQLite",
+  "query": "SELECT id, version_id, data as \"data: Json<PhysicalHost>\" FROM physical_hosts WHERE id = ? ORDER BY version_id DESC LIMIT 1",
+  "describe": {
+    "columns": [
+      {
+        "name": "id",
+        "ordinal": 0,
+        "type_info": "Text"
+      },
+      {
+        "name": "version_id",
+        "ordinal": 1,
+        "type_info": "Text"
+      },
+      {
+        "name": "data: Json<PhysicalHost>",
+        "ordinal": 2,
+        "type_info": "Null"
+      }
+    ],
+    "parameters": {
+      "Right": 1
+    },
+    "nullable": [
+      false,
+      false,
+      false
+    ]
+  },
+  "hash": "934035c7ca6e064815393e4e049a7934b0a7fac04a4fe4b2a354f0443d630990"
+}

.sqlx/query-f10f615ee42129ffa293e46f2f893d65a237d31d24b74a29c6a8d8420d255ab8.json

@@ -0,0 +1,12 @@
+{
+  "db_name": "SQLite",
+  "query": "INSERT INTO physical_hosts (id, version_id, data) VALUES (?, ?, ?)",
+  "describe": {
+    "columns": [],
+    "parameters": {
+      "Right": 3
+    },
+    "nullable": []
+  },
+  "hash": "f10f615ee42129ffa293e46f2f893d65a237d31d24b74a29c6a8d8420d255ab8"
+}

CONTRIBUTING.md

@@ -0,0 +1,36 @@
+# Contributing to the Harmony project
+
+## Write small P-R
+
+Aim for the smallest piece of work that is mergeable.
+
+Mergeable means that :
+
+- it does not break the build
+- it moves the codebase one step forward
+
+P-Rs can be many things, they do not have to be complete features.
+
+### What a P-R **should** be
+
+- Introduce a new trait : This will be the place to discuss the new trait addition, its design and implementation
+- A new implementation of a trait : a new concrete implementation of the LoadBalancer trait
+- A new CI check : something that improves quality, robustness, ci performance
+- Documentation improvements
+- Refactoring
+- Bugfix
+
+### What a P-R **should not** be
+
+- Large. Anything over 200 lines (excluding generated lines) should have a very good reason to be this large.
+- A mix of refactoring, bug fixes and new features.
+- Introducing multiple new features or ideas at once.
+- Multiple new implementations of a trait/functionnality at once
+
+The general idea is to keep P-Rs small and single purpose.
+
+## Commit message formatting
+
+We follow conventional commits guidelines.
+
+https://www.conventionalcommits.org/en/v1.0.0/

Cargo.toml

@@ -11,6 +11,10 @@ members = [
   "opnsense-config-xml",
   "harmony_cli",
   "k3d",
+  "harmony_composer",
+  "harmony_inventory_agent",
+  "harmony_secret_derive",
+  "harmony_secret", "adr/agent_discovery/mdns",
 ]
 
 [workspace.package]
@@ -19,27 +23,48 @@ readme = "README.md"
 license = "GNU AGPL v3"
 
 [workspace.dependencies]
-log = "0.4.22"
-env_logger = "0.11.5"
-derive-new = "0.7.0"
-async-trait = "0.1.82"
-tokio = { version = "1.40.0", features = ["io-std", "fs", "macros", "rt-multi-thread"] }
-cidr = "0.2.3"
-russh = "0.45.0"
-russh-keys = "0.45.0"
-rand = "0.8.5"
-url = "2.5.4"
-kube = "0.98.0"
-k8s-openapi = { version = "0.24.0", features = ["v1_30"] }
-serde_yaml = "0.9.34"
-serde-value = "0.7.0"
-http = "1.2.0"
-inquire = "0.7.5"
-
-[workspace.dependencies.uuid]
-version = "1.11.0"
-features = [
-  "v4",                # Lets you generate random UUIDs
-  "fast-rng",          # Use a faster (but still sufficiently random) RNG
-  "macro-diagnostics", # Enable better diagnostics for compile-time UUIDs
-]
+log = { version = "0.4", features = ["kv"] }
+env_logger = "0.11"
+derive-new = "0.7"
+async-trait = "0.1"
+tokio = { version = "1.40", features = [
+  "io-std",
+  "fs",
+  "macros",
+  "rt-multi-thread",
+] }
+cidr = { features = ["serde"], version = "0.2" }
+russh = "0.45"
+russh-keys = "0.45"
+rand = "0.9"
+url = "2.5"
+kube = { version = "1.1.0", features = [
+  "config",
+  "client",
+  "runtime",
+  "rustls-tls",
+  "ws",
+  "jsonpatch",
+] }
+k8s-openapi = { version = "0.25", features = ["v1_30"] }
+serde_yaml = "0.9"
+serde-value = "0.7"
+http = "1.2"
+inquire = "0.7"
+convert_case = "0.8"
+chrono = "0.4"
+similar = "2"
+uuid = { version = "1.11", features = ["v4", "fast-rng", "macro-diagnostics"] }
+pretty_assertions = "1.4.1"
+tempfile = "3.20.0"
+bollard = "0.19.1"
+base64 = "0.22.1"
+tar = "0.4.44"
+lazy_static = "1.5.0"
+directories = "6.0.0"
+thiserror = "2.0.14"
+serde = { version = "1.0.209", features = ["derive", "rc"] }
+serde_json = "1.0.127"
+askama = "0.14"
+sqlx = { version = "0.8", features = ["runtime-tokio", "sqlite" ] }
+reqwest = { version = "0.12", features = ["blocking", "stream", "rustls-tls", "http2", "json"], default-features = false }

Dockerfile

@@ -0,0 +1,26 @@
+FROM docker.io/rust:1.89.0 AS build
+
+WORKDIR /app
+
+COPY . .
+
+RUN cargo build --release --bin harmony_composer
+
+FROM docker.io/rust:1.89.0
+
+WORKDIR /app
+
+RUN rustup target add x86_64-pc-windows-gnu
+RUN rustup target add x86_64-unknown-linux-gnu
+RUN rustup component add rustfmt
+RUN rustup component add clippy
+
+RUN apt update
+
+# TODO: Consider adding more supported targets
+# nodejs for checkout action, docker for building containers, mingw for cross-compiling for windows
+RUN apt install -y nodejs docker.io mingw-w64
+
+COPY --from=build /app/target/release/harmony_composer .
+
+ENTRYPOINT ["/app/harmony_composer"]

README.md

@@ -1,33 +1,150 @@
-# Harmony : Open Infrastructure Orchestration
+# Harmony : Open-source infrastructure orchestration that treats your platform like first-class code
 
-## Quick demo
+_By [NationTech](https://nationtech.io)_
 
-`cargo run -p example-tui`
+[![Build](https://git.nationtech.io/NationTech/harmony/actions/workflows/check.yml/badge.svg)](https://git.nationtech.io/nationtech/harmony)
+[![License](https://img.shields.io/badge/license-AGPLv3-blue?style=flat-square)](LICENSE)
 
-This will launch Harmony's minimalist terminal ui which embeds a few demo scores.
+### Unify
 
-Usage instructions will be displayed at the bottom of the TUI.
+- **Project Scaffolding**
+- **Infrastructure Provisioning**
+- **Application Deployment**
+- **Day-2 operations**
 
-`cargo run --bin example-cli -- --help`
+All in **one strongly-typed Rust codebase**.
 
-This is the harmony CLI, a minimal implementation
+### Deploy anywhere
 
-The current help text:
+From a **developer laptop** to a **global production cluster**, a single **source of truth** drives the **full software lifecycle.**
 
-````
-Usage: example-cli [OPTIONS]
+---
 
-Options:
-  -y, --yes              Run score(s) or not
-  -f, --filter <FILTER>  Filter query
-  -i, --interactive      Run interactive TUI or not
-  -a, --all              Run all or nth, defaults to all
-  -n, --number <NUMBER>  Run nth matching, zero indexed [default: 0]
-  -l, --list             list scores, will also be affected by run filter
-  -h, --help             Print help
-  -V, --version          Print version```
+## 1 · The Harmony Philosophy
 
-## Core architecture
+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.
 
-![Harmony Core Architecture](docs/diagrams/Harmony_Core_Architecture.drawio.svg)
-````
+| Principle                              | What it means for you                                                                                                                                                                |
+| -------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| **Infrastructure as Resilient Code**   | Replace sprawling YAML and bash scripts with type-safe Rust. Test, refactor, and version your platform just like application code.                                                   |
+| **Prove It Works — Before You Deploy** | Harmony uses the compiler to verify that your application’s needs match the target environment’s capabilities at **compile-time**, eliminating an entire class of runtime outages.   |
+| **One Unified Model**                  | Software and infrastructure are a single system. Harmony models them together, enabling deep automation—from bare-metal servers to Kubernetes workloads—with zero context switching. |
+
+These principles surface as simple, ergonomic Rust APIs that let teams focus on their product while trusting the platform underneath.
+
+---
+
+## 2 · Quick Start
+
+The snippet below spins up a complete **production-grade LAMP stack** with monitoring. Swap it for your own scores to deploy anything from microservices to machine-learning pipelines.
+
+```rust
+use harmony::{
+    data::Version,
+    inventory::Inventory,
+    maestro::Maestro,
+    modules::{
+        lamp::{LAMPConfig, LAMPScore},
+        monitoring::monitoring_alerting::MonitoringAlertingStackScore,
+    },
+    topology::{K8sAnywhereTopology, Url},
+};
+
+#[tokio::main]
+async fn main() {
+    // 1. Describe what you want
+    let lamp_stack = LAMPScore {
+        name: "harmony-lamp-demo".into(),
+        domain: Url::Url(url::Url::parse("https://lampdemo.example.com").unwrap()),
+        php_version: Version::from("8.3.0").unwrap(),
+        config: LAMPConfig {
+            project_root: "./php".into(),
+            database_size: "4Gi".into(),
+            ..Default::default()
+        },
+    };
+
+    // 2. Enhance with extra scores (monitoring, CI/CD, …)
+    let mut monitoring = MonitoringAlertingStackScore::new();
+    monitoring.namespace = Some(lamp_stack.config.namespace.clone());
+
+    // 3. Run your scores on the desired topology & inventory
+    harmony_cli::run(
+        Inventory::autoload(),                // auto-detect hardware / kube-config
+        K8sAnywhereTopology::from_env(),      // local k3d, CI, staging, prod…
+        vec![
+          Box::new(lamp_stack),
+          Box::new(monitoring)
+        ],
+        None
+    ).await.unwrap();
+}
+```
+
+Run it:
+
+```bash
+cargo run
+```
+
+Harmony analyses the code, shows an execution plan in a TUI, and applies it once you confirm. Same code, same binary—every environment.
+
+---
+
+## 3 · Core Concepts
+
+| 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.                           |
+
+A visual overview is in the diagram below.
+
+[Harmony Core Architecture](docs/diagrams/Harmony_Core_Architecture.drawio.svg)
+
+---
+
+## 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
+
+Harmony is released under the **GNU AGPL v3**.
+
+> We choose a strong copyleft license to ensure the project—and every improvement to it—remains open and benefits the entire community. Fork it, enhance it, even out-innovate us; just keep it open.
+
+See [LICENSE](LICENSE) for the full text.
+
+---
+
+_Made with ❤️ & 🦀 by the NationTech and the Harmony community_

adr/000-ADR-Template.md

@@ -1,6 +1,6 @@
 # Architecture Decision Record: \<Title\>
 
-Name: \<Name\>
+Initial Author: \<Name\>
 
 Initial Date: \<Date\>
 

adr/009-helm-and-kustomize-handling.md

@@ -1,6 +1,6 @@
 # Architecture Decision Record: Helm and Kustomize Handling
 
-Name: Taha Hawa
+Initial Author: Taha Hawa
 
 Initial Date: 2025-04-15
 

adr/010-monitoring-alerting/architecture.rs

@@ -0,0 +1,73 @@
+pub trait MonitoringSystem {}
+
+// 1. Modified AlertReceiver trait:
+//    - Removed the problematic `clone` method.
+//    - Added `box_clone` which returns a Box<dyn AlertReceiver>.
+pub trait AlertReceiver {
+    type M: MonitoringSystem;
+    fn install(&self, sender: &Self::M) -> Result<(), String>;
+    // This method allows concrete types to clone themselves into a Box<dyn AlertReceiver>
+    fn box_clone(&self) -> Box<dyn AlertReceiver<M = Self::M>>;
+}
+#[derive(Clone)]
+struct Prometheus{}
+impl MonitoringSystem for Prometheus {}
+
+#[derive(Clone)] // Keep derive(Clone) for DiscordWebhook itself
+struct DiscordWebhook{}
+
+impl AlertReceiver for DiscordWebhook {
+    type M = Prometheus;
+    fn install(&self, sender: &Self::M) -> Result<(), String> {
+        // Placeholder for actual installation logic
+        println!("DiscordWebhook installed for Prometheus monitoring.");
+        Ok(())
+    }
+    // 2. Implement `box_clone` for DiscordWebhook:
+    //    This uses the derived `Clone` for DiscordWebhook to create a new boxed instance.
+    fn box_clone(&self) -> Box<dyn AlertReceiver<M = Self::M>> {
+        Box::new(self.clone())
+    }
+}
+
+// 3. Implement `std::clone::Clone` for `Box<dyn AlertReceiver<M= M>>`:
+//    This allows `Box<dyn AlertReceiver>` to be cloned.
+//    The `+ 'static` lifetime bound is often necessary for trait objects stored in collections,
+//    ensuring they live long enough.
+impl<M: MonitoringSystem + 'static> Clone for Box<dyn AlertReceiver<M= M>> {
+    fn clone(&self) -> Self {
+        self.box_clone() // Call the custom `box_clone` method
+    }
+}
+
+// MonitoringConfig can now derive Clone because its `receivers` field
+// (Vec<Box<dyn AlertReceiver<M = M>>>) is now cloneable.
+#[derive(Clone)]
+struct MonitoringConfig <M: MonitoringSystem + 'static>{
+    receivers: Vec<Box<dyn AlertReceiver<M = M>>>
+}
+
+// Example usage to demonstrate compilation and functionality
+fn main() {
+    let prometheus_instance = Prometheus{};
+    let discord_webhook_instance = DiscordWebhook{};
+
+    let mut config = MonitoringConfig {
+        receivers: Vec::new()
+    };
+
+    // Create a boxed alert receiver
+    let boxed_receiver: Box<dyn AlertReceiver<M = Prometheus>> = Box::new(discord_webhook_instance);
+    config.receivers.push(boxed_receiver);
+
+    // Clone the config, which will now correctly clone the boxed receiver
+    let cloned_config = config.clone();
+
+    println!("Original config has {} receivers.", config.receivers.len());
+    println!("Cloned config has {} receivers.", cloned_config.receivers.len());
+
+    // Example of using the installed receiver
+    if let Some(receiver) = config.receivers.get(0) {
+        let _ = receiver.install(&prometheus_instance);
+    }
+}

adr/010-monitoring-and-alerting.md

@@ -1,7 +1,7 @@
 # Architecture Decision Record: Monitoring and Alerting
 
-Proposed by: Willem Rolleman
-Date: April 28 2025
+Initial Author : Willem Rolleman
+Date : April 28 2025
 
 ## Status
 

adr/011-multi-tenant-cluster.md

@@ -0,0 +1,161 @@
+# Architecture Decision Record: Multi-Tenancy Strategy for Harmony Managed Clusters
+
+Initial Author: Jean-Gabriel Gill-Couture
+
+Initial Date: 2025-05-26
+
+## Status
+
+Proposed
+
+## Context
+
+Harmony manages production OKD/Kubernetes clusters that serve multiple clients with varying trust levels and operational requirements. We need a multi-tenancy strategy that provides:
+
+1. **Strong isolation** between client workloads while maintaining operational simplicity
+2. **Controlled API access** allowing clients self-service capabilities within defined boundaries
+3. **Security-first approach** protecting both the cluster infrastructure and tenant data
+4. **Harmony-native implementation** using our Score/Interpret pattern for automated tenant provisioning
+5. **Scalable management** supporting both small trusted clients and larger enterprise customers
+
+The official Kubernetes multi-tenancy documentation identifies two primary models: namespace-based isolation and virtual control planes per tenant. Given Harmony's focus on operational simplicity, provider-agnostic abstractions (ADR-003), and hexagonal architecture (ADR-002), we must choose an approach that balances security, usability, and maintainability.
+
+Our clients represent a hybrid tenancy model:
+- **Customer multi-tenancy**: Each client operates independently with no cross-tenant trust
+- **Team multi-tenancy**: Individual clients may have multiple team members requiring coordinated access
+- **API access requirement**: Unlike pure SaaS scenarios, clients need controlled Kubernetes API access for self-service operations
+
+The official kubernetes documentation on multi tenancy heavily inspired this ADR : https://kubernetes.io/docs/concepts/security/multi-tenancy/
+
+## Decision
+
+Implement **namespace-based multi-tenancy** with the following architecture:
+
+### 1. Network Security Model
+- **Private cluster access**: Kubernetes API and OpenShift console accessible only via WireGuard VPN
+- **No public exposure**: Control plane endpoints remain internal to prevent unauthorized access attempts
+- **VPN-based authentication**: Initial access control through WireGuard client certificates
+
+### 2. Tenant Isolation Strategy
+- **Dedicated namespace per tenant**: Each client receives an isolated namespace with access limited only to the required resources and operations
+- **Complete network isolation**: NetworkPolicies prevent cross-namespace communication while allowing full egress to public internet
+- **Resource governance**: ResourceQuotas and LimitRanges enforce CPU, memory, and storage consumption limits
+- **Storage access control**: Clients can create PersistentVolumeClaims but cannot directly manipulate PersistentVolumes or access other tenants' storage
+
+### 3. Access Control Framework
+- **Principle of Least Privilege**: RBAC grants only necessary permissions within tenant namespace scope
+- **Namespace-scoped**: Clients can create/modify/delete resources within their namespace
+- **Cluster-level restrictions**: No access to cluster-wide resources, other namespaces, or sensitive cluster operations
+- **Whitelisted operations**: Controlled self-service capabilities for ingress, secrets, configmaps, and workload management
+
+### 4. Identity Management Evolution
+- **Phase 1**: Manual provisioning of VPN access and Kubernetes ServiceAccounts/Users
+- **Phase 2**: Migration to Keycloak-based identity management (aligning with ADR-006) for centralized authentication and lifecycle management
+
+### 5. Harmony Integration
+- **TenantScore implementation**: Declarative tenant provisioning using Harmony's Score/Interpret pattern
+- **Topology abstraction**: Tenant configuration abstracted from underlying Kubernetes implementation details
+- **Automated deployment**: Complete tenant setup automated through Harmony's orchestration capabilities
+
+## Rationale
+
+### Network Security Through VPN Access
+- **Defense in depth**: VPN requirement adds critical security layer preventing unauthorized cluster access
+- **Simplified firewall rules**: No need for complex public endpoint protections or rate limiting
+- **Audit capability**: VPN access provides clear audit trail of cluster connections
+- **Aligns with enterprise practices**: Most enterprise customers already use VPN infrastructure
+
+### Namespace Isolation vs Virtual Control Planes
+Following Kubernetes official guidance, namespace isolation provides:
+- **Lower resource overhead**: Virtual control planes require dedicated etcd, API server, and controller manager per tenant
+- **Operational simplicity**: Single control plane to maintain, upgrade, and monitor
+- **Cross-tenant service integration**: Enables future controlled cross-tenant communication if required
+- **Proven stability**: Namespace-based isolation is well-tested and widely deployed
+- **Cost efficiency**: Significantly lower infrastructure costs compared to dedicated control planes
+
+### Hybrid Tenancy Model Suitability
+Our approach addresses both customer and team multi-tenancy requirements:
+- **Customer isolation**: Strong network and RBAC boundaries prevent cross-tenant interference
+- **Team collaboration**: Multiple team members can share namespace access through group-based RBAC
+- **Self-service balance**: Controlled API access enables client autonomy without compromising security
+
+### Harmony Architecture Alignment
+- **Provider agnostic**: TenantScore abstracts multi-tenancy concepts, enabling future support for other Kubernetes distributions
+- **Hexagonal architecture**: Tenant management becomes an infrastructure capability accessed through well-defined ports
+- **Declarative automation**: Tenant lifecycle fully managed through Harmony's Score execution model
+
+## Consequences
+
+### Positive Consequences
+- **Strong security posture**: VPN + namespace isolation provides robust tenant separation
+- **Operational efficiency**: Single cluster management with automated tenant provisioning
+- **Client autonomy**: Self-service capabilities reduce operational support burden
+- **Scalable architecture**: Can support hundreds of tenants per cluster without architectural changes
+- **Future flexibility**: Foundation supports evolution to more sophisticated multi-tenancy models
+- **Cost optimization**: Shared infrastructure maximizes resource utilization
+
+### Negative Consequences
+- **VPN operational overhead**: Requires VPN infrastructure management
+- **Manual provisioning complexity**: Phase 1 manual user management creates administrative burden
+- **Network policy dependency**: Requires CNI with NetworkPolicy support (OVN-Kubernetes provides this and is the OKD/Openshift default)
+- **Cluster-wide resource limitations**: Some advanced Kubernetes features require cluster-wide access
+- **Single point of failure**: Cluster outage affects all tenants simultaneously
+
+### Migration Challenges
+- **Legacy client integration**: Existing clients may need VPN client setup and credential migration
+- **Monitoring complexity**: Per-tenant observability requires careful metric and log segmentation
+- **Backup considerations**: Tenant data backup must respect isolation boundaries
+
+## Alternatives Considered
+
+### Alternative 1: Virtual Control Plane Per Tenant
+**Pros**: Complete control plane isolation, full Kubernetes API access per tenant
+**Cons**: 3-5x higher resource usage, complex cross-tenant networking, operational complexity scales linearly with tenants
+
+**Rejected**: Resource overhead incompatible with cost-effective multi-tenancy goals
+
+### Alternative 2: Dedicated Clusters Per Tenant
+**Pros**: Maximum isolation, independent upgrade cycles, simplified security model
+**Cons**: Exponential operational complexity, prohibitive costs, resource waste
+
+**Rejected**: Operational overhead makes this approach unsustainable for multiple clients
+
+### Alternative 3: Public API with Advanced Authentication
+**Pros**: No VPN requirement, potentially simpler client access
+**Cons**: Larger attack surface, complex rate limiting and DDoS protection, increased security monitoring requirements
+
+**Rejected**: Risk/benefit analysis favors VPN-based access control
+
+### Alternative 4: Service Mesh Based Isolation
+**Pros**: Fine-grained traffic control, encryption, advanced observability
+**Cons**: Significant operational complexity, performance overhead, steep learning curve
+
+**Rejected**: Complexity overhead outweighs benefits for current requirements; remains option for future enhancement
+
+## Additional Notes
+
+### Implementation Roadmap
+1. **Phase 1**: Implement VPN access and manual tenant provisioning
+2. **Phase 2**: Deploy TenantScore automation for namespace, RBAC, and NetworkPolicy management
+4. **Phase 3**: Work on privilege escalation from pods, audit for weaknesses, enforce security policies on pod runtimes
+3. **Phase 4**: Integrate Keycloak for centralized identity management
+4. **Phase 5**: Add advanced monitoring and per-tenant observability
+
+### TenantScore Structure Preview
+```rust
+pub struct TenantScore {
+    pub tenant_config: TenantConfig,
+    pub resource_quotas: ResourceQuotaConfig,
+    pub network_isolation: NetworkIsolationPolicy,
+    pub storage_access: StorageAccessConfig,
+    pub rbac_config: RBACConfig,
+}
+```
+
+### Future Enhancements
+- **Cross-tenant service mesh**: For approved inter-tenant communication
+- **Advanced monitoring**: Per-tenant Prometheus/Grafana instances
+- **Backup automation**: Tenant-scoped backup policies
+- **Cost allocation**: Detailed per-tenant resource usage tracking
+
+This ADR establishes the foundation for secure, scalable multi-tenancy in Harmony-managed clusters while maintaining operational simplicity and cost effectiveness. A follow-up ADR will detail the Tenant abstraction and user management mechanisms within the Harmony framework.

adr/011-tenant/NetworkPolicy.yaml

@@ -0,0 +1,41 @@
+apiVersion: networking.k8s.io/v1
+kind: NetworkPolicy
+metadata:
+  name: tenant-isolation-policy
+  namespace: testtenant
+spec:
+  podSelector: {}  # Selects all pods in the namespace
+  policyTypes:
+  - Ingress
+  - Egress
+  ingress:
+  - from:
+    - podSelector: {}  # Allow from all pods in the same namespace
+  egress:
+  - to:
+    - podSelector: {}  # Allow to all pods in the same namespace
+  - to:
+    - podSelector: {}
+      namespaceSelector: 
+        matchLabels:
+          kubernetes.io/metadata.name: openshift-dns # Target the openshift-dns namespace
+    # Note, only opening port 53 is not enough, will have to dig deeper into this one eventually
+    # ports:
+    # - protocol: UDP
+    #   port: 53
+    # - protocol: TCP
+    #   port: 53
+  # Allow egress to public internet only
+  - to:
+    - ipBlock:
+        cidr: 0.0.0.0/0
+        except:
+        - 10.0.0.0/8      # RFC1918
+        - 172.16.0.0/12   # RFC1918
+        - 192.168.0.0/16  # RFC1918
+        - 169.254.0.0/16  # Link-local
+        - 127.0.0.0/8     # Loopback
+        - 224.0.0.0/4     # Multicast
+        - 240.0.0.0/4     # Reserved
+        - 100.64.0.0/10   # Carrier-grade NAT
+        - 0.0.0.0/8       # Reserved

adr/011-tenant/TestDeployment.yaml

@@ -0,0 +1,95 @@
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: testtenant
+---
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: testtenant2
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: test-web
+  namespace: testtenant
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: test-web
+  template:
+    metadata:
+      labels:
+        app: test-web
+    spec:
+      containers:
+      - name: nginx
+        image: nginxinc/nginx-unprivileged
+        ports:
+        - containerPort: 80
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: test-web
+  namespace: testtenant
+spec:
+  selector:
+    app: test-web
+  ports:
+  - port: 80
+    targetPort: 8080
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: test-client
+  namespace: testtenant
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: test-client
+  template:
+    metadata:
+      labels:
+        app: test-client
+    spec:
+      containers:
+      - name: curl
+        image: curlimages/curl:latest
+        command: ["/bin/sh", "-c", "sleep 3600"]
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: test-web
+  namespace: testtenant2
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: test-web
+  template:
+    metadata:
+      labels:
+        app: test-web
+    spec:
+      containers:
+      - name: nginx
+        image: nginxinc/nginx-unprivileged
+        ports:
+        - containerPort: 80
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: test-web
+  namespace: testtenant2
+spec:
+  selector:
+    app: test-web
+  ports:
+  - port: 80
+    targetPort: 8080

adr/012-project-delivery-automation.md

@@ -0,0 +1,63 @@
+# Architecture Decision Record: \<Title\>
+
+Initial Author: Jean-Gabriel Gill-Couture
+
+Initial Date: 2025-06-04
+
+Last Updated Date: 2025-06-04
+
+## Status
+
+Proposed
+
+## Context
+
+As Harmony's goal is to make software delivery easier, we must provide an easy way for developers to express their app's semantics and dependencies with great abstractions, in a similar fashion to what the score.dev project is doing.
+
+Thus, we started working on ways to package common types of applications such as LAMP, which we started working on with `LAMPScore`.
+
+Now is time for the next step : we want to pave the way towards complete lifecycle automation. To do this, we will start with a way to execute Harmony's modules easily from anywhere, starting with locally and in CI environments.
+
+## Decision
+
+To achieve easy, portable execution of Harmony, we will follow this architecture :
+
+- Host a basic harmony release that is compiled with the CLI by our gitea/github server
+    - This binary will do the following : check if there is a `harmony` folder in the current path
+    - If yes
+        - Check if cargo is available locally and compile the harmony binary, or compile the harmony binary using a rust docker container, if neither cargo or a container runtime is available, output a message explaining the situation
+        - Run the newly compiled binary. (Ideally using pid handoff like exec does but some research around this should be done. I think handing off the process is to help with OS interaction such as terminal apps, signals, exit codes, process handling, etc but there might be some side effects)
+    - If not
+        - Suggest initializing a project by auto detecting what the project looks like
+        - When the project type cannot be auto detected, provide links to Harmony's documentation on how to set up a project, a link to the examples folder, and a ask the user if he wants to initialize an empty Harmony project in the current folder
+            - harmony/Cargo.toml with dependencies set
+            - harmony/src/main.rs with an example LAMPScore setup and ready to run
+- This same binary can be used in a CI environment to run the target project's Harmony module. By default, we provide these opinionated steps :
+    1. **An empty check step.** The purpose of this step is to run all tests and checks against the codebase. For complex projects this could involve a very complex pipeline of test environments setup and execution but this is out of scope for now. This is not handled by harmony. For projects with automatic setup, we can fill this step with something like `cargo fmt --check; cargo test; cargo build` but Harmony is not directly involved in the execution of this step.
+    2. **Package and publish.** Once all checks have passed, the production ready container is built and pushed to a registry. This is done by Harmony.
+    3. **Deploy to staging automatically.** 
+    4. **Run a sanity check on staging.** As Harmony is responsible for deploying, Harmony should have all the knowledge of how to perform a sanity check on the staging environment. This will, most of the time, be a simple verification of the kubernetes health of all deployed components, and a poke on the public endpoint when there is one.
+    5. **Deploy to production automatically.** Many projects will require manual approval here, this can be easily set up in the CI afterwards, but our opinion is that 
+    6. **Run a sanity check on production.** Same check as staging, but on production.
+
+*Note on providing a base pipeline :* Having a complete pipeline set up automatically will encourage development teams to build upon these by adding tests where they belong. The goal here is to provide an opiniated solution that works for most small and large projects. Of course, many orgnizations will need to add steps such as deploying to sandbox environments, requiring more advanced approvals, more complex publication and coordination with other projects. But this here encompasses the basics required to build and deploy software reliably at any scale.
+
+### Environment setup
+
+TBD : For now, environments (tenants) will be set up and configured manually. Harmony will rely on the kubeconfig provided in the environment where it is running to deploy in the namespace.
+
+For the CD tool such as Argo or Flux they will be activated by default by Harmony when using application level Scores such as LAMPScore in a similar way that the container is automatically built. Then, CI deployment steps will be notifying the CD tool using its API of the new release to deploy.
+
+## Rationale
+
+Reasoning behind the decision
+
+## Consequences
+
+Pros/Cons of chosen solution
+
+## Alternatives considered
+
+Pros/Cons of various proposed solutions considered
+
+## Additional Notes

adr/013-monitoring-notifications.md

@@ -0,0 +1,78 @@
+# Architecture Decision Record: Monitoring Notifications
+
+Initial Author: Taha Hawa
+
+Initial Date: 2025-06-26
+
+Last Updated Date: 2025-06-26
+
+## Status
+
+Proposed
+
+## Context
+
+We need to send notifications (typically from AlertManager/Prometheus) and we need to receive said notifications on mobile devices for sure in some way, whether it's push messages, SMS, phone call, email, etc or all of the above.
+
+## Decision
+
+We should go with https://ntfy.sh except host it ourselves.
+
+`ntfy` is an open source solution written in Go that has the features we need.
+
+## Rationale
+
+`ntfy` has pretty much everything we need (push notifications, email forwarding, receives via webhook), and nothing/not much we don't. Good fit, lightweight.
+
+## Consequences
+
+Pros:
+
+- topics, with ACLs
+- lightweight
+- reliable
+- easy to configure
+- mobile app
+  - the mobile app can listen via websocket, poll, or receive via Firebase/GCM on Android, or similar on iOS.
+- Forward to email
+- Text-to-Speech phone call messages using Twilio integration
+- Operates based on simple HTTP requests/Webhooks, easily usable via AlertManager
+
+Cons:
+
+- No SMS pushes
+- SQLite DB, makes it harder to HA/scale
+
+## Alternatives considered
+
+[AWS SNS](https://aws.amazon.com/sns/):
+Pros:
+
+- highly reliable
+- no hosting needed
+
+Cons:
+
+- no control, not self hosted
+- costs (per usage)
+
+[Apprise](https://github.com/caronc/apprise):
+Pros:
+
+- Way more ways of sending notifications
+- Can use ntfy as one of the backends/ways of sending
+
+Cons:
+
+- Way too overkill for what we need in terms of features
+
+[Gotify](https://github.com/gotify/server):
+Pros:
+
+- simple, lightweight, golang, etc
+
+Cons:
+
+- Pushes topics are per-user
+
+## Additional Notes

adr/agent_discovery/mdns/Cargo.toml

@@ -0,0 +1,17 @@
+[package]
+name = "mdns"
+edition = "2024"
+version.workspace = true
+readme.workspace = true
+license.workspace = true
+
+[dependencies]
+mdns-sd = "0.14"
+tokio = { version = "1", features = ["full"] }
+futures = "0.3"
+dmidecode = "0.2" # For getting the motherboard ID on the agent
+log.workspace=true
+env_logger.workspace=true
+clap = { version = "4.5.46", features = ["derive"] }
+get_if_addrs = "0.5.3"
+local-ip-address = "0.6.5"

adr/agent_discovery/mdns/src/advertise.rs

@@ -0,0 +1,60 @@
+// harmony-agent/src/main.rs
+
+use log::info;
+use mdns_sd::{ServiceDaemon, ServiceInfo};
+use std::collections::HashMap;
+
+use crate::SERVICE_TYPE;
+
+// The service we are advertising.
+const SERVICE_PORT: u16 = 43210; // A port for the service. It needs one, even if unused.
+
+pub async fn advertise() {
+    info!("Starting Harmony Agent...");
+
+    // Get a unique ID for this machine.
+    let motherboard_id = "some motherboard id";
+    let instance_name = format!("harmony-agent-{}", motherboard_id);
+    info!("This agent's instance name: {}", instance_name);
+    info!("Advertising with ID: {}", motherboard_id);
+
+    // Create a new mDNS daemon.
+    let mdns = ServiceDaemon::new().expect("Failed to create mDNS daemon");
+
+    // Create a TXT record HashMap to hold our metadata.
+    let mut properties = HashMap::new();
+    properties.insert("id".to_string(), motherboard_id.to_string());
+    properties.insert("version".to_string(), "1.0".to_string());
+
+    // Create the service information.
+    // The instance name should be unique on the network.
+    let local_ip = local_ip_address::local_ip().unwrap();
+    let service_info = ServiceInfo::new(
+        SERVICE_TYPE,
+        &instance_name,
+        "harmony-host.local.", // A hostname for the service
+        local_ip,
+        // "0.0.0.0",
+        SERVICE_PORT,
+        Some(properties),
+    )
+    .expect("Failed to create service info");
+
+    // Register our service with the daemon.
+    mdns.register(service_info)
+        .expect("Failed to register service");
+
+    info!(
+        "Service '{}' registered and now being advertised.",
+        instance_name
+    );
+    info!("Agent is running. Press Ctrl+C to exit.");
+
+    for iface in get_if_addrs::get_if_addrs().unwrap() {
+        println!("{:#?}", iface);
+    }
+
+    // Keep the agent running indefinitely.
+    tokio::signal::ctrl_c().await.unwrap();
+    info!("Shutting down agent.");
+}

adr/agent_discovery/mdns/src/discover.rs

@@ -0,0 +1,110 @@
+use log::debug;
+use mdns_sd::{ServiceDaemon, ServiceEvent};
+
+use crate::SERVICE_TYPE;
+
+pub async fn discover() {
+    println!("Starting Harmony Master and browsing for agents...");
+
+    // Create a new mDNS daemon.
+    let mdns = ServiceDaemon::new().expect("Failed to create mDNS daemon");
+
+    // Start browsing for the service type.
+    // The receiver will be a stream of events.
+    let receiver = mdns.browse(SERVICE_TYPE).expect("Failed to browse");
+
+    println!(
+        "Listening for mDNS events for '{}'. Press Ctrl+C to exit.",
+        SERVICE_TYPE
+    );
+
+    std::thread::spawn(move || {
+        while let Ok(event) = receiver.recv() {
+            match event {
+                ServiceEvent::ServiceData(resolved) => {
+                    println!("Resolved a new service: {}", resolved.fullname);
+                }
+                other_event => {
+                    println!("Received other event: {:?}", &other_event);
+                }
+            }
+        }
+    });
+
+    // Gracefully shutdown the daemon.
+    std::thread::sleep(std::time::Duration::from_secs(1000000));
+    mdns.shutdown().unwrap();
+
+    // Process events as they come in.
+    // while let Ok(event) = receiver.recv_async().await {
+    //     debug!("Received event {event:?}");
+    //     // match event {
+    //     //     ServiceEvent::ServiceFound(svc_type, fullname) => {
+    //     //         println!("\n--- Agent Discovered ---");
+    //     //         println!("  Service Name: {}", fullname());
+    //     //         // You can now resolve this service to get its IP, port, and TXT records
+    //     //         // The resolve operation is a separate network call.
+    //     //         let receiver = mdns.browse(info.get_fullname()).unwrap();
+    //     //         if let Ok(resolve_event) = receiver.recv_timeout(Duration::from_secs(2)) {
+    //     //              if let ServiceEvent::ServiceResolved(info) = resolve_event {
+    //     //                 let ip = info.get_addresses().iter().next().unwrap();
+    //     //                 let port = info.get_port();
+    //     //                 let motherboard_id = info.get_property("id").map_or("N/A", |v| v.val_str());
+    //     //
+    //     //                 println!("  IP: {}:{}", ip, port);
+    //     //                 println!("  Motherboard ID: {}", motherboard_id);
+    //     //                 println!("------------------------");
+    //     //
+    //     //                 // TODO: Add this agent to your central list of discovered hosts.
+    //     //              }
+    //     //         } else {
+    //     //             println!("Could not resolve service '{}' in time.", info.get_fullname());
+    //     //         }
+    //     //     }
+    //     //     ServiceEvent::ServiceRemoved(info) => {
+    //     //         println!("\n--- Agent Removed ---");
+    //     //         println!("  Service Name: {}", info.get_fullname());
+    //     //         println!("---------------------");
+    //     //         // TODO: Remove this agent from your list.
+    //     //     }
+    //     //     _ => {
+    //     //         // We don't care about other event types for this example
+    //     //     }
+    //     // }
+    // }
+}
+
+async fn discover_example() {
+    use mdns_sd::{ServiceDaemon, ServiceEvent};
+
+    // Create a daemon
+    let mdns = ServiceDaemon::new().expect("Failed to create daemon");
+
+    // Use recently added `ServiceEvent::ServiceData`.
+    mdns.use_service_data(true)
+        .expect("Failed to use ServiceData");
+
+    // Browse for a service type.
+    let service_type = "_mdns-sd-my-test._udp.local.";
+    let receiver = mdns.browse(service_type).expect("Failed to browse");
+
+    // Receive the browse events in sync or async. Here is
+    // an example of using a thread. Users can call `receiver.recv_async().await`
+    // if running in async environment.
+    std::thread::spawn(move || {
+        while let Ok(event) = receiver.recv() {
+            match event {
+                ServiceEvent::ServiceData(resolved) => {
+                    println!("Resolved a new service: {}", resolved.fullname);
+                }
+                other_event => {
+                    println!("Received other event: {:?}", &other_event);
+                }
+            }
+        }
+    });
+
+    // Gracefully shutdown the daemon.
+    std::thread::sleep(std::time::Duration::from_secs(1));
+    mdns.shutdown().unwrap();
+}

adr/agent_discovery/mdns/src/main.rs

@@ -0,0 +1,31 @@
+use clap::{Parser, ValueEnum};
+
+mod advertise;
+mod discover;
+
+#[derive(Parser, Debug)]
+#[command(version, about, long_about = None)]
+struct Args {
+    #[arg(value_enum)]
+    profile: Profiles,
+}
+
+#[derive(Copy, Clone, Debug, PartialEq, Eq, PartialOrd, Ord, ValueEnum)]
+enum Profiles {
+    Advertise,
+    Discover,
+}
+
+// The service type we are looking for.
+const SERVICE_TYPE: &str = "_harmony._tcp.local.";
+
+#[tokio::main]
+async fn main() {
+    env_logger::init();
+    let args = Args::parse();
+
+    match args.profile {
+        Profiles::Advertise => advertise::advertise().await,
+        Profiles::Discover => discover::discover().await,
+    }
+}

check.sh

@@ -1,5 +1,8 @@
 #!/bin/sh
 set -e
+
+rustc --version
 cargo check --all-targets --all-features --keep-going
 cargo fmt --check
+cargo clippy
 cargo test

data/pxe/okd/README.md

@@ -0,0 +1,8 @@
+Here lies all the data files required for an OKD cluster PXE boot setup.
+
+This inclues ISO files, binary boot files, ipxe, etc.
+
+TODO as of august 2025 :
+
+- `harmony_inventory_agent` should be downloaded from official releases, this embedded version is practical for now though
+- The cluster ssh key should be generated and handled by harmony with the private key saved in a secret store

data/pxe/okd/http_files/.gitattributes

@@ -0,0 +1,9 @@
+harmony_inventory_agent filter=lfs diff=lfs merge=lfs -text
+os filter=lfs diff=lfs merge=lfs -text
+os/centos-stream-9 filter=lfs diff=lfs merge=lfs -text
+os/centos-stream-9/images filter=lfs diff=lfs merge=lfs -text
+os/centos-stream-9/initrd.img filter=lfs diff=lfs merge=lfs -text
+os/centos-stream-9/vmlinuz filter=lfs diff=lfs merge=lfs -text
+os/centos-stream-9/images/efiboot.img filter=lfs diff=lfs merge=lfs -text
+os/centos-stream-9/images/install.img filter=lfs diff=lfs merge=lfs -text
+os/centos-stream-9/images/pxeboot filter=lfs diff=lfs merge=lfs -text

data/pxe/okd/http_files/cluster_ssh_key.pub

@@ -0,0 +1 @@
+ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIBx6bDylvC68cVpjKfEFtLQJ/dOFi6PVS2vsIOqPDJIc jeangab@liliane2

data/watchguard/pxe-http-files/.gitattributes

@@ -0,0 +1 @@
+slitaz/* filter=lfs diff=lfs merge=lfs -text

data/watchguard/pxe-http-files/boot.ipxe

@@ -0,0 +1,6 @@
+#!ipxe
+
+set base-url http://192.168.33.1:8080
+set hostfile ${base-url}/byMAC/01-${mac:hexhyp}.ipxe
+
+chain ${hostfile} || chain ${base-url}/default.ipxe

data/watchguard/pxe-http-files/byMAC/01-c4-62-37-01-bc-68.ipxe

@@ -0,0 +1,35 @@
+#!ipxe
+menu PXE Boot Menu - [${mac}]
+item okdinstallation  Install OKD
+item slitaz  Boot to Slitaz - old linux for debugging
+choose selected
+
+goto ${selected}
+
+:local
+exit
+
+#################################
+# okdinstallation
+#################################
+:okdinstallation
+set base-url http://192.168.33.1:8080
+set kernel-image fcos/fedora-coreos-39.20231101.3.0-live-kernel-x86_64
+set live-rootfs fcos/fedora-coreos-39.20231101.3.0-live-rootfs.x86_64.img
+set live-initramfs fcos/fedora-coreos-39.20231101.3.0-live-initramfs.x86_64.img
+set install-disk /dev/nvme0n1
+set ignition-file ncd0/master.ign
+
+kernel ${base-url}/${kernel-image} initrd=main coreos.live.rootfs_url=${base-url}/${live-rootfs} coreos.inst.install_dev=${install-disk} coreos.inst.ignition_url=${base-url}/${ignition-file}  ip=enp1s0:dhcp
+initrd --name main ${base-url}/${live-initramfs}
+boot
+
+#################################
+# slitaz
+#################################
+:slitaz
+set server_ip 192.168.33.1:8080
+set base_url http://${server_ip}/slitaz
+kernel ${base_url}/vmlinuz-2.6.37-slitaz rw root=/dev/null vga=788 initrd=rootfs.gz
+initrd ${base_url}/rootfs.gz
+boot

data/watchguard/pxe-http-files/byMAC/01-c4-62-37-02-60-fa.ipxe

@@ -0,0 +1,35 @@
+#!ipxe
+menu PXE Boot Menu - [${mac}]
+item okdinstallation  Install OKD
+item slitaz  Boot to Slitaz - old linux for debugging
+choose selected
+
+goto ${selected}
+
+:local
+exit
+
+#################################
+# okdinstallation
+#################################
+:okdinstallation
+set base-url http://192.168.33.1:8080
+set kernel-image fcos/fedora-coreos-39.20231101.3.0-live-kernel-x86_64
+set live-rootfs fcos/fedora-coreos-39.20231101.3.0-live-rootfs.x86_64.img
+set live-initramfs fcos/fedora-coreos-39.20231101.3.0-live-initramfs.x86_64.img
+set install-disk /dev/nvme0n1
+set ignition-file ncd0/master.ign
+
+kernel ${base-url}/${kernel-image} initrd=main coreos.live.rootfs_url=${base-url}/${live-rootfs} coreos.inst.install_dev=${install-disk} coreos.inst.ignition_url=${base-url}/${ignition-file}  ip=enp1s0:dhcp
+initrd --name main ${base-url}/${live-initramfs}
+boot
+
+#################################
+# slitaz
+#################################
+:slitaz
+set server_ip 192.168.33.1:8080
+set base_url http://${server_ip}/slitaz
+kernel ${base_url}/vmlinuz-2.6.37-slitaz rw root=/dev/null vga=788 initrd=rootfs.gz
+initrd ${base_url}/rootfs.gz
+boot

data/watchguard/pxe-http-files/byMAC/01-c4-62-37-02-61-0f.ipxe

@@ -0,0 +1,35 @@
+#!ipxe
+menu PXE Boot Menu - [${mac}]
+item okdinstallation  Install OKD
+item slitaz  Slitaz - an old linux image for debugging
+choose selected
+
+goto ${selected}
+
+:local
+exit
+
+#################################
+# okdinstallation
+#################################
+:okdinstallation
+set base-url http://192.168.33.1:8080
+set kernel-image fcos/fedora-coreos-39.20231101.3.0-live-kernel-x86_64
+set live-rootfs fcos/fedora-coreos-39.20231101.3.0-live-rootfs.x86_64.img
+set live-initramfs fcos/fedora-coreos-39.20231101.3.0-live-initramfs.x86_64.img
+set install-disk /dev/sda
+set ignition-file ncd0/worker.ign
+
+kernel ${base-url}/${kernel-image} initrd=main coreos.live.rootfs_url=${base-url}/${live-rootfs} coreos.inst.install_dev=${install-disk} coreos.inst.ignition_url=${base-url}/${ignition-file}  ip=enp1s0:dhcp
+initrd --name main ${base-url}/${live-initramfs}
+boot
+
+#################################
+# slitaz
+#################################
+:slitaz
+set server_ip 192.168.33.1:8080
+set base_url http://${server_ip}/slitaz
+kernel ${base_url}/vmlinuz-2.6.37-slitaz rw root=/dev/null vga=788 initrd=rootfs.gz
+initrd ${base_url}/rootfs.gz
+boot

data/watchguard/pxe-http-files/byMAC/01-c4-62-37-02-61-1a.ipxe

@@ -0,0 +1,35 @@
+#!ipxe
+menu PXE Boot Menu - [${mac}]
+item okdinstallation  Install OKD
+item slitaz  Boot to Slitaz - old linux for debugging
+choose selected
+
+goto ${selected}
+
+:local
+exit
+
+#################################
+# okdinstallation
+#################################
+:okdinstallation
+set base-url http://192.168.33.1:8080
+set kernel-image fcos/fedora-coreos-39.20231101.3.0-live-kernel-x86_64
+set live-rootfs fcos/fedora-coreos-39.20231101.3.0-live-rootfs.x86_64.img
+set live-initramfs fcos/fedora-coreos-39.20231101.3.0-live-initramfs.x86_64.img
+set install-disk /dev/nvme0n1
+set ignition-file ncd0/master.ign
+
+kernel ${base-url}/${kernel-image} initrd=main coreos.live.rootfs_url=${base-url}/${live-rootfs} coreos.inst.install_dev=${install-disk} coreos.inst.ignition_url=${base-url}/${ignition-file}  ip=enp1s0:dhcp
+initrd --name main ${base-url}/${live-initramfs}
+boot
+
+#################################
+# slitaz
+#################################
+:slitaz
+set server_ip 192.168.33.1:8080
+set base_url http://${server_ip}/slitaz
+kernel ${base_url}/vmlinuz-2.6.37-slitaz rw root=/dev/null vga=788 initrd=rootfs.gz
+initrd ${base_url}/rootfs.gz
+boot

data/watchguard/pxe-http-files/byMAC/01-c4-62-37-02-61-26.ipxe

@@ -0,0 +1,35 @@
+#!ipxe
+menu PXE Boot Menu - [${mac}]
+item okdinstallation  Install OKD
+item slitaz  Slitaz - an old linux image for debugging
+choose selected
+
+goto ${selected}
+
+:local
+exit
+
+#################################
+# okdinstallation
+#################################
+:okdinstallation
+set base-url http://192.168.33.1:8080
+set kernel-image fcos/fedora-coreos-39.20231101.3.0-live-kernel-x86_64
+set live-rootfs fcos/fedora-coreos-39.20231101.3.0-live-rootfs.x86_64.img
+set live-initramfs fcos/fedora-coreos-39.20231101.3.0-live-initramfs.x86_64.img
+set install-disk /dev/sda
+set ignition-file ncd0/worker.ign
+
+kernel ${base-url}/${kernel-image} initrd=main coreos.live.rootfs_url=${base-url}/${live-rootfs} coreos.inst.install_dev=${install-disk} coreos.inst.ignition_url=${base-url}/${ignition-file}  ip=enp1s0:dhcp
+initrd --name main ${base-url}/${live-initramfs}
+boot
+
+#################################
+# slitaz
+#################################
+:slitaz
+set server_ip 192.168.33.1:8080
+set base_url http://${server_ip}/slitaz
+kernel ${base_url}/vmlinuz-2.6.37-slitaz rw root=/dev/null vga=788 initrd=rootfs.gz
+initrd ${base_url}/rootfs.gz
+boot

data/watchguard/pxe-http-files/byMAC/01-c4-62-37-02-61-70.ipxe

@@ -0,0 +1,37 @@
+#!ipxe
+menu PXE Boot Menu - [${mac}]
+item okdinstallation  Install OKD
+item slitaz  Slitaz - an old linux image for debugging
+choose selected
+
+goto ${selected}
+
+:local
+exit
+# This is the bootstrap node
+# it will become wk2
+
+#################################
+# okdinstallation
+#################################
+:okdinstallation
+set base-url http://192.168.33.1:8080
+set kernel-image fcos/fedora-coreos-39.20231101.3.0-live-kernel-x86_64
+set live-rootfs fcos/fedora-coreos-39.20231101.3.0-live-rootfs.x86_64.img
+set live-initramfs fcos/fedora-coreos-39.20231101.3.0-live-initramfs.x86_64.img
+set install-disk /dev/sda
+set ignition-file ncd0/worker.ign
+
+kernel ${base-url}/${kernel-image} initrd=main coreos.live.rootfs_url=${base-url}/${live-rootfs} coreos.inst.install_dev=${install-disk} coreos.inst.ignition_url=${base-url}/${ignition-file}  ip=enp1s0:dhcp
+initrd --name main ${base-url}/${live-initramfs}
+boot
+
+#################################
+# slitaz
+#################################
+:slitaz
+set server_ip 192.168.33.1:8080
+set base_url http://${server_ip}/slitaz
+kernel ${base_url}/vmlinuz-2.6.37-slitaz rw root=/dev/null vga=788 initrd=rootfs.gz
+initrd ${base_url}/rootfs.gz
+boot

data/watchguard/pxe-http-files/default.ipxe

@@ -0,0 +1,71 @@
+#!ipxe
+menu PXE Boot Menu - [${mac}]
+item local  Boot from Hard Disk
+item slitaz Boot slitaz live environment [tux|root:root]
+#item ubuntu-server Ubuntu 24.04.1 live server
+#item ubuntu-desktop Ubuntu 24.04.1 desktop
+#item systemrescue System Rescue 11.03
+item memtest memtest
+#choose --default local --timeout 5000 selected
+choose selected
+
+goto ${selected}
+
+:local
+exit
+
+#################################
+# slitaz
+#################################
+:slitaz
+set server_ip 192.168.33.1:8080
+set base_url http://${server_ip}/slitaz
+kernel ${base_url}/vmlinuz-2.6.37-slitaz rw root=/dev/null vga=788 initrd=rootfs.gz
+initrd ${base_url}/rootfs.gz
+boot
+
+#################################
+# Ubuntu Server
+#################################
+:ubuntu-server
+set server_ip 192.168.33.1:8080
+set base_url http://${server_ip}/ubuntu/live-server-24.04.1
+
+kernel ${base_url}/vmlinuz ip=dhcp url=${base_url}/ubuntu-24.04.1-live-server-amd64.iso autoinstall ds=nocloud
+initrd ${base_url}/initrd
+boot
+
+#################################
+# Ubuntu Desktop
+#################################
+:ubuntu-desktop
+set server_ip 192.168.33.1:8080
+set base_url http://${server_ip}/ubuntu/desktop-24.04.1
+
+kernel ${base_url}/vmlinuz ip=dhcp url=${base_url}/ubuntu-24.04.1-desktop-amd64.iso autoinstall ds=nocloud
+initrd ${base_url}/initrd
+boot
+
+#################################
+# System Rescue
+#################################
+:systemrescue
+set base-url http://192.168.33.1:8080/systemrescue
+
+kernel ${base-url}/vmlinuz initrd=sysresccd.img boot=systemrescue docache
+initrd ${base-url}/sysresccd.img
+boot
+
+#################################
+# MemTest86 (BIOS/UEFI)
+#################################
+:memtest
+iseq ${platform} efi && goto memtest_efi || goto memtest_bios
+
+:memtest_efi
+kernel http://192.168.33.1:8080/memtest/memtest64.efi
+boot
+
+:memtest_bios
+kernel http://192.168.33.1:8080/memtest/memtest64.bin
+boot

data/watchguard/pxe-http-files/paul

@@ -1 +0,0 @@
-hey i am paul

demos/cncf-k8s-quebec-meetup-september-2025/storyline.md

@@ -0,0 +1,132 @@
+# Harmony, Orchestrateur d'infrastructure open-source
+
+**Target Duration:** 25 minutes\
+**Tone:** Friendly, expert-to-expert, inspiring.
+
+---
+
+#### **Slide 1: Title Slide**
+
+- **Visual:** Clean and simple. Your company logo (NationTech) and the Harmony logo.
+
+---
+
+#### **Slide 2: The YAML Labyrinth**
+
+**Goal:** Get every head in the room nodding in agreement. Start with their world, not yours.
+
+- **Visual:**
+  - Option A: "The Pull Request from Hell". A screenshot of a GitHub pull request for a seemingly minor change that touches dozens of YAML files across multiple directories. A sea of red and green diffs that is visually overwhelming.
+  - Option B: A complex flowchart connecting dozens of logos: Terraform, Ansible, K8s, Helm, etc.
+- **Narration:**\
+  [...ADD SOMETHING FOR INTRODUCTION...]\
+  "We love the power that tools like Kubernetes and the CNCF landscape have given us. But let's be honest... when did our infrastructure code start looking like _this_?"\
+  "We have GitOps, which is great. But it often means we're managing this fragile cathedral of YAML, Helm charts, and brittle scripts. We spend more time debugging indentation and tracing variables than we do building truly resilient systems."
+
+---
+
+#### **Slide 3: The Real Cost: Cognitive Fatigue**
+
+- **Visual:** "The Jenga Tower of Tools". A tall, precarious Jenga tower where each block is the logo of a different tool (Terraform, K8s, Helm, Ansible, Prometheus, ArgoCD, etc.). One block near the bottom is being nervously pulled out.
+- **Narration:**
+  "The real cost isn't just complexity; it's _cognitive fatigue_. The constant need to choose, learn, integrate, and operate a dozen different tools, each with its own syntax and failure modes. It's the nagging fear that a tiny typo in a config file could bring everything down. Click-ops isn't the answer, but the current state of IaC feels like we've traded one problem for another."
+
+---
+
+#### **Slide 4: The Broken Promise of "Code"**
+
+**Goal:** Introduce the core idea before introducing the product. This makes the solution feel inevitable.
+
+- **(Initial Visual):** A two-panel slide.
+  - **Left Panel Title: "The Plan"** - A terminal showing a green, successful `terraform plan` output.
+  - **Right Panel Title: "The Reality"** - The _next_ screen in the terminal, showing the `terraform apply` failing with a cascade of red error text.
+- **Narration:**
+  "We call our discipline **Infrastructure as Code**. And we've all been here. Our 'compiler' is a `terraform plan` that says everything looks perfect. We get the green light."
+  (Pause for a beat)
+  "And then we `apply`, and reality hits. It fails halfway through, at runtime, when it's most expensive and painful to fix."
+
+**(Click to transition the slide)**
+
+- **(New Visual):** The entire slide is replaced by a clean screenshot of a code editor (like VS Code) showing Harmony's Rust DSL. A red squiggly line is under a config line. The error message is clear in the "Problems" panel: `error: Incompatible deployment. Production target 'gcp-prod-cluster' requires a StorageClass with 'snapshots' capability, but 'standard-sc' does not provide it.`
+- **Narration (continued):**
+  "In software development, we solved these problems years ago. We don't accept 'it compiled, but crashed on startup'. We have real tools, type systems, compilers, test frameworks, and IDEs that catch our mistakes before they ever reach production. **So, what if we could treat our entire infrastructure... like a modern, compiled application?**"
+  "What if your infrastructure code could get compile-time checks, straight into the editor... instead of runtime panics and failures at 3 AM in production?"
+
+---
+
+#### **Slide 5: Introducing Harmony**
+
+**Goal:** Introduce Harmony as the answer to the "What If?" question.
+
+- **Visual:** The Harmony logo, large and centered.
+- **Tagline:** `Infrastructure in type-safe Rust. No YAML required.`
+- **Narration:**
+  "This is Harmony. It's an open-source orchestrator that lets you define your entire stack — from a dev laptop to a multi-site bare-metal cluster—in a single, type-safe Rust codebase."
+
+---
+
+#### **Slide 6: Before & After**
+
+- **Visual:** A side-by-side comparison. Left side: A screen full of complex, nested YAML. Right side: 10-15 lines of clean, readable Harmony Rust DSL that accomplishes the same thing.
+- **Narration:**
+  "This is the difference. On the left, the fragile world of strings and templates. On the right, a portable, verifiable program that describes your apps, your infra, and your operations. We unify scaffolding, provisioning, and Day-2 ops, all verified by the Rust compiler. But enough slides... let's see it in action."
+
+---
+
+#### **Slide 7: Live Demo: Zero to Monitored App**
+
+**Goal:** Show, don't just tell. Make it look effortless. This is where you build the "dream."
+
+- **Visual:** Your terminal/IDE, ready to go.
+- **Narration Guide:**
+  "Okay, for this demo, we're going to take a standard web app from GitHub. Nothing special about it."
+  _(Show the repo)_
+  "Now, let's bring it into Harmony. This is the entire definition we need to describe the application and its needs."
+  _(Show the Rust DSL)_
+  "First, let's run it locally on k3d. The exact same definition for dev as for prod."
+  _(Deploy locally, show it works)_
+  "Cool. But a real app needs monitoring. In Harmony, that's just adding a feature to our code."
+  _(Uncomment one line: `.with_feature(Monitoring)` and redeploy)_
+  "And just like that, we have a fully configured Prometheus and Grafana stack, scraping our app. No YAML, no extra config."
+  "Finally, let's push this to our production staging cluster. We just change the target and specify our multi-site Ceph storage."
+  _(Deploy to the remote cluster)_
+  "And there it is. We've gone from a simple web app to a monitored, enterprise-grade service in minutes."
+
+---
+
+#### **Slide 8: Live Demo: Embracing Chaos**
+
+**Goal:** Prove the "predictable" and "resilient" claims in the most dramatic way possible.
+
+- **Visual:** A slide showing a map or diagram of your distributed infrastructure (the different data centers). Then switch back to your terminal.
+- **Narration Guide:**
+  "This is great when things are sunny. But production is chaos. So... let's break things. On purpose."
+  "First, a network failure." _(Kill a switch/link, show app is still up)_
+  "Now, let's power off a storage server." _(Force off a server, show Ceph healing and the app is unaffected)_
+  "How about a control plane node?" _(Force off a k8s control plane, show the cluster is still running)_
+  "Okay, for the grand finale. What if we have a cascading failure? I'm going to kill _another_ storage server. This should cause a total failure in this data center."
+  _(Force off the second server, narrate what's happening)_
+  "And there it is... Ceph has lost quorum in this site... and Harmony has automatically failed everything over to our other datacenter. The app is still running."
+
+---
+
+#### **Slide 9: The New Reality**
+
+**Goal:** Summarize the dream and tell the audience what you want them to do.
+
+- **Visual:** The clean, simple Harmony Rust DSL code from Slide 6. A summary of what was just accomplished is listed next to it: `✓ GitHub to Prod in minutes`, `✓ Type-Safe Validation`, `✓ Built-in Monitoring`, `✓ Automated Multi-Site Failover`.
+- **Narration:**
+  "So, in just a few minutes, we went from a simple web app to a multi-site, monitored, and chaos-proof production deployment. We did it with a small amount of code that is easy to read, easy to verify, and completely portable. This is our vision: to offload the complexity, eliminate cognitive fatigue, and make infrastructure simple, predictable, and even fun again."
+
+---
+
+#### **Slide 10: Join Us**
+
+- **Visual:** A clean, final slide with QR codes and links.
+  - GitHub Repo (`github.com/nation-tech/harmony`)
+  - Website (`harmony.sh` or similar)
+  - Your contact info (`jg@nation.tech` / LinkedIn / Twitter)
+- **Narration:**
+  "Harmony is open-source, AGPLv3. We believe this is the future, but we're just getting started. We know this crowd has great infrastructure minds out there, and we need your feedback. Please, check out the project on GitHub. Star it if you like what you see. Tell us what's missing. Let's build this future together. Thank you."
+
+**(Open for Q&A)**

docs/README.md

@@ -0,0 +1 @@
+Not much here yet, see the `adr` folder for now. More to come in time!

docs/cyborg-metaphor.md

@@ -0,0 +1,13 @@
+## Conceptual metaphor : The Cyborg and the Central Nervous System
+
+At the heart of Harmony lies a core belief: in modern, decentralized systems, **software and infrastructure are not separate entities.** They are a single, symbiotic organism—a cyborg.
+
+The software is the electronics, the "mind"; the infrastructure is the biological host, the "body". They live or die, thrive or sink together.
+
+Traditional approaches attempt to manage this complex organism with fragmented tools: static YAML for configuration, brittle scripts for automation, and separate Infrastructure as Code (IaC) for provisioning. This creates a disjointed system that struggles to scale or heal itself, making it inadequate for the demands of fully automated, enterprise-grade clusters.
+
+Harmony's goal is to provide the **central nervous system for this cyborg**. We aim to achieve the full automation of complex, decentralized clouds by managing this integrated entity holistically.
+
+To achieve this, a tool must be both robust and powerful. It must manage the entire lifecycle—deployment, upgrades, failure recovery, and decommissioning—with precision. This requires full control over application packaging and a deep, intrinsic integration between the software and the infrastructure it inhabits.
+
+This is why Harmony uses a powerful, living language like Rust. It replaces static, lifeless configuration files with a dynamic, breathing codebase. It allows us to express the complex relationships and behaviors of a modern distributed system, enabling the creation of truly automated, resilient, and powerful platforms that can thrive.

docs/pxe_test/README.md

@@ -0,0 +1,108 @@
+# OPNsense PXE Lab Environment
+
+This project contains a script to automatically set up a virtual lab environment for testing PXE boot services managed by an OPNsense firewall.
+
+## Overview
+
+The `pxe_vm_lab_setup.sh` script will create the following resources using libvirt/KVM:
+
+1.  **A Virtual Network**: An isolated network named `harmonylan` (`virbr1`) for the lab.
+2.  **Two Virtual Machines**:
+    *   `opnsense-pxe`: A firewall VM that will act as the gateway and PXE server.
+    *   `pxe-node-1`: A client VM configured to boot from the network.
+
+## Prerequisites
+
+Ensure you have the following software installed on your Arch Linux host:
+
+*   `libvirt`
+*   `qemu`
+*   `virt-install` (from the `virt-install` package)
+*   `curl`
+*   `bzip2`
+
+## Usage
+
+### 1. Create the Environment
+
+Run the `up` command to download the necessary images and create the network and VMs.
+
+```bash
+sudo ./pxe_vm_lab_setup.sh up
+```
+
+### 2. Install and Configure OPNsense
+
+The OPNsense VM is created but the OS needs to be installed manually via the console.
+
+1.  **Connect to the VM console**:
+    ```bash
+    sudo virsh console opnsense-pxe
+    ```
+
+2.  **Log in as the installer**:
+    *   Username: `installer`
+    *   Password: `opnsense`
+
+3.  **Follow the on-screen installation wizard**. When prompted to assign network interfaces (`WAN` and `LAN`):
+    *   Find the MAC address for the `harmonylan` interface by running this command in another terminal:
+        ```bash
+        virsh domiflist opnsense-pxe
+        # Example output:
+        # Interface   Type      Source       Model    MAC
+        # ---------------------------------------------------------
+        # vnet18      network   default      virtio   52:54:00:b5:c4:6d
+        # vnet19      network   harmonylan   virtio   52:54:00:21:f9:ba
+        ```
+    *   Assign the interface connected to `harmonylan` (e.g., `vtnet1` with MAC `52:54:00:21:f9:ba`) as your **LAN**.
+    *   Assign the other interface as your **WAN**.
+
+4.  After the installation is complete, **shut down** the VM from the console menu.
+
+5.  **Detach the installation media** by editing the VM's configuration:
+    ```bash
+    sudo virsh edit opnsense-pxe
+    ```
+    Find and **delete** the entire `<disk>` block corresponding to the `.img` file (the one with `<target ... bus='usb'/>`).
+
+6.  **Start the VM** to boot into the newly installed system:
+    ```bash
+    sudo virsh start opnsense-pxe
+    ```
+
+### 3. Connect to OPNsense from Your Host
+
+To configure OPNsense, you need to connect your host to the `harmonylan` network.
+
+1.  By default, OPNsense configures its LAN interface with the IP `192.168.1.1`.
+2.  Assign a compatible IP address to your host's `virbr1` bridge interface:
+    ```bash
+    sudo ip addr add 192.168.1.5/24 dev virbr1
+    ```
+3.  You can now access the OPNsense VM from your host:
+    *   **SSH**: `ssh root@192.168.1.1` (password: `opnsense`)
+    *   **Web UI**: `https://192.168.1.1`
+
+### 4. Configure PXE Services with Harmony
+
+With connectivity established, you can now use Harmony to configure the OPNsense firewall for PXE booting. Point your Harmony OPNsense scores to the firewall using these details:
+
+*   **Hostname/IP**: `192.168.1.1`
+*   **Credentials**: `root` / `opnsense`
+
+### 5. Boot the PXE Client
+
+Once your Harmony configuration has been applied and OPNsense is serving DHCP/TFTP, start the client VM. It will automatically attempt to boot from the network.
+
+```bash
+sudo virsh start pxe-node-1
+sudo virsh console pxe-node-1
+```
+
+## Cleanup
+
+To destroy all VMs and networks created by the script, run the `clean` command:
+
+```bash
+sudo ./pxe_vm_lab_setup.sh clean
+```

docs/pxe_test/pxe_vm_lab_setup.sh

@@ -0,0 +1,191 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# --- Configuration ---
+LAB_DIR="/var/lib/harmony_pxe_test"
+IMG_DIR="${LAB_DIR}/images"
+STATE_DIR="${LAB_DIR}/state"
+VM_OPN="opnsense-pxe"
+VM_PXE="pxe-node-1"
+NET_HARMONYLAN="harmonylan"
+
+# Network settings for the isolated LAN
+VLAN_CIDR="192.168.150.0/24"
+VLAN_GW="192.168.150.1"
+VLAN_MASK="255.255.255.0"
+
+# VM Specifications
+RAM_OPN="2048"
+VCPUS_OPN="2"
+DISK_OPN_GB="10"
+OS_VARIANT_OPN="freebsd14.0" # Updated to a more recent FreeBSD variant
+
+RAM_PXE="4096"
+VCPUS_PXE="2"
+DISK_PXE_GB="40"
+OS_VARIANT_LINUX="centos-stream9"
+
+OPN_IMG_URL="https://mirror.ams1.nl.leaseweb.net/opnsense/releases/25.7/OPNsense-25.7-serial-amd64.img.bz2"
+OPN_IMG_PATH="${IMG_DIR}/OPNsense-25.7-serial-amd64.img"
+CENTOS_ISO_URL="https://mirror.stream.centos.org/9-stream/BaseOS/x86_64/os/images/boot.iso"
+CENTOS_ISO_PATH="${IMG_DIR}/CentOS-Stream-9-latest-boot.iso"
+
+CONNECT_URI="qemu:///system"
+
+download_if_missing() {
+  local url="$1"
+  local dest="$2"
+  if [[ ! -f "$dest" ]]; then
+    echo "Downloading $url to $dest"
+    mkdir -p "$(dirname "$dest")"
+    local tmp
+    tmp="$(mktemp)"
+    curl -L --progress-bar "$url" -o "$tmp"
+    case "$url" in
+      *.bz2) bunzip2 -c "$tmp" > "$dest" && rm -f "$tmp" ;;
+      *) mv "$tmp" "$dest" ;;
+    esac
+  else
+    echo "Already present: $dest"
+  fi
+}
+
+# Ensures a libvirt network is defined and active
+ensure_network() {
+  local net_name="$1"
+  local net_xml_path="$2"
+  if virsh --connect "${CONNECT_URI}" net-info "${net_name}" >/dev/null 2>&1; then
+    echo "Network ${net_name} already exists."
+  else
+    echo "Defining network ${net_name} from ${net_xml_path}"
+    virsh --connect "${CONNECT_URI}" net-define "${net_xml_path}"
+  fi
+
+  if ! virsh --connect "${CONNECT_URI}" net-info "${net_name}" | grep "Active: *yes"; then
+    echo "Starting network ${net_name}..."
+    virsh --connect "${CONNECT_URI}" net-start "${net_name}"
+    virsh --connect "${CONNECT_URI}" net-autostart "${net_name}"
+  fi
+}
+
+# Destroys a VM completely
+destroy_vm() {
+  local vm_name="$1"
+  if virsh --connect "${CONNECT_URI}" dominfo "$vm_name" >/dev/null 2>&1; then
+    echo "Destroying and undefining VM: ${vm_name}"
+    virsh --connect "${CONNECT_URI}" destroy "$vm_name" || true
+    virsh --connect "${CONNECT_URI}" undefine "$vm_name" --nvram
+  fi
+}
+
+# Destroys a libvirt network
+destroy_network() {
+  local net_name="$1"
+  if virsh --connect "${CONNECT_URI}" net-info "$net_name" >/dev/null 2>&1; then
+    echo "Destroying and undefining network: ${net_name}"
+    virsh --connect "${CONNECT_URI}" net-destroy "$net_name" || true
+    virsh --connect "${CONNECT_URI}" net-undefine "$net_name"
+  fi
+}
+
+# --- Main Logic ---
+create_lab_environment() {
+  # Create network definition files
+  cat > "${STATE_DIR}/default.xml" <<EOF
+<network>
+  <name>default</name>
+  <forward mode='nat'/>
+  <bridge name='virbr0' stp='on' delay='0'/>
+  <ip address='192.168.122.1' netmask='255.255.255.0'>
+    <dhcp>
+      <range start='192.168.122.100' end='192.168.122.200'/>
+    </dhcp>
+  </ip>
+</network>
+EOF
+
+  cat > "${STATE_DIR}/${NET_HARMONYLAN}.xml" <<EOF
+<network>
+  <name>${NET_HARMONYLAN}</name>
+  <bridge name='virbr1' stp='on' delay='0'/>
+</network>
+EOF
+
+  # Ensure both networks exist and are active
+  ensure_network "default" "${STATE_DIR}/default.xml"
+  ensure_network "${NET_HARMONYLAN}" "${STATE_DIR}/${NET_HARMONYLAN}.xml"
+
+  # --- Create OPNsense VM (MODIFIED SECTION) ---
+  local disk_opn="${IMG_DIR}/${VM_OPN}.qcow2"
+  if [[ ! -f "$disk_opn" ]]; then
+    qemu-img create -f qcow2 "$disk_opn" "${DISK_OPN_GB}G"
+  fi
+
+  echo "Creating OPNsense VM using serial image..."
+  virt-install \
+    --connect "${CONNECT_URI}" \
+    --name "${VM_OPN}" \
+    --ram "${RAM_OPN}" \
+    --vcpus "${VCPUS_OPN}" \
+    --cpu host-passthrough \
+    --os-variant "${OS_VARIANT_OPN}" \
+    --graphics none \
+    --noautoconsole \
+    --disk path="${disk_opn}",device=disk,bus=virtio,boot.order=1 \
+    --disk path="${OPN_IMG_PATH}",device=disk,bus=usb,readonly=on,boot.order=2 \
+    --network network=default,model=virtio \
+    --network network="${NET_HARMONYLAN}",model=virtio \
+    --boot uefi,menu=on
+
+  echo "OPNsense VM created. Connect with: sudo virsh console ${VM_OPN}"
+  echo "The VM will boot from the serial installation image."
+  echo "Login with user 'installer' and password 'opnsense' to start the installation."
+  echo "Install onto the VirtIO disk (vtbd0)."
+  echo "After installation, shutdown the VM, then run 'sudo virsh edit ${VM_OPN}' and remove the USB disk block to boot from the installed system."
+
+  # --- Create PXE Client VM ---
+  local disk_pxe="${IMG_DIR}/${VM_PXE}.qcow2"
+  if [[ ! -f "$disk_pxe" ]]; then
+    qemu-img create -f qcow2 "$disk_pxe" "${DISK_PXE_GB}G"
+  fi
+
+  echo "Creating PXE client VM..."
+  virt-install \
+    --connect "${CONNECT_URI}" \
+    --name "${VM_PXE}" \
+    --ram "${RAM_PXE}" \
+    --vcpus "${VCPUS_PXE}" \
+    --cpu host-passthrough \
+    --os-variant "${OS_VARIANT_LINUX}" \
+    --graphics none \
+    --noautoconsole \
+    --disk path="${disk_pxe}",format=qcow2,bus=virtio \
+    --network network="${NET_HARMONYLAN}",model=virtio \
+    --pxe \
+    --boot uefi,menu=on
+
+  echo "PXE VM created. It will attempt to netboot on ${NET_HARMONYLAN}."
+}
+
+# --- Script Entrypoint ---
+case "${1:-}" in
+  up)
+    mkdir -p "${IMG_DIR}" "${STATE_DIR}"
+    download_if_missing "$OPN_IMG_URL" "$OPN_IMG_PATH"
+    download_if_missing "$CENTOS_ISO_URL" "$CENTOS_ISO_PATH"
+    create_lab_environment
+    echo "Lab setup complete. Use 'sudo virsh list --all' to see VMs."
+    ;;
+  clean)
+    destroy_vm "${VM_PXE}"
+    destroy_vm "${VM_OPN}"
+    destroy_network "${NET_HARMONYLAN}"
+    # Optionally destroy the default network if you want a full reset
+    # destroy_network "default"
+    echo "Cleanup complete."
+    ;;
+  *)
+    echo "Usage: sudo $0 {up|clean}"
+    exit 1
+    ;;
+esac

examples/application_monitoring_with_tenant/Cargo.toml

@@ -0,0 +1,15 @@
+[package]
+name = "example-application-monitoring-with-tenant"
+edition = "2024"
+version.workspace = true
+readme.workspace = true
+license.workspace = true
+
+[dependencies]
+env_logger.workspace = true
+harmony = { path = "../../harmony" }
+harmony_cli = { path = "../../harmony_cli" }
+harmony_types = { path = "../../harmony_types" }
+logging = "0.1.0"
+tokio.workspace = true
+url.workspace = true

examples/application_monitoring_with_tenant/src/main.rs

@@ -0,0 +1,56 @@
+use std::{path::PathBuf, str::FromStr, sync::Arc};
+
+use harmony::{
+    inventory::Inventory,
+    modules::{
+        application::{ApplicationScore, RustWebFramework, RustWebapp, features::Monitoring},
+        monitoring::alert_channel::webhook_receiver::WebhookReceiver,
+        tenant::TenantScore,
+    },
+    topology::{K8sAnywhereTopology, tenant::TenantConfig},
+};
+use harmony_types::id::Id;
+use harmony_types::net::Url;
+
+#[tokio::main]
+async fn main() {
+    //TODO there is a bug where the application is deployed into the namespace matching the
+    //application name and the tenant is created in the namesapce matching the tenant name
+    //in order for the application to be deployed in the tenant namespace the application.name and
+    //the TenantConfig.name must match
+    let tenant = TenantScore {
+        config: TenantConfig {
+            id: Id::from_str("test-tenant-id").unwrap(),
+            name: "example-monitoring".to_string(),
+            ..Default::default()
+        },
+    };
+    let application = Arc::new(RustWebapp {
+        name: "example-monitoring".to_string(),
+        domain: Url::Url(url::Url::parse("https://rustapp.harmony.example.com").unwrap()),
+        project_root: PathBuf::from("./examples/rust/webapp"),
+        framework: Some(RustWebFramework::Leptos),
+    });
+
+    let webhook_receiver = WebhookReceiver {
+        name: "sample-webhook-receiver".to_string(),
+        url: Url::Url(url::Url::parse("https://webhook-doesnt-exist.com").unwrap()),
+    };
+
+    let app = ApplicationScore {
+        features: vec![Box::new(Monitoring {
+            alert_receiver: vec![Box::new(webhook_receiver)],
+            application: application.clone(),
+        })],
+        application,
+    };
+
+    harmony_cli::run(
+        Inventory::autoload(),
+        K8sAnywhereTopology::from_env(),
+        vec![Box::new(tenant), Box::new(app)],
+        None,
+    )
+    .await
+    .unwrap();
+}

examples/cli/src/main.rs

@@ -1,20 +1,27 @@
 use harmony::{
     inventory::Inventory,
-    maestro::Maestro,
-    modules::dummy::{ErrorScore, PanicScore, SuccessScore},
+    modules::{
+        dummy::{ErrorScore, PanicScore, SuccessScore},
+        inventory::DiscoverInventoryAgentScore,
+    },
     topology::LocalhostTopology,
 };
 
 #[tokio::main]
 async fn main() {
-    let inventory = Inventory::autoload();
-    let topology = LocalhostTopology::new();
-    let mut maestro = Maestro::initialize(inventory, topology).await.unwrap();
-
-    maestro.register_all(vec![
-        Box::new(SuccessScore {}),
-        Box::new(ErrorScore {}),
-        Box::new(PanicScore {}),
-    ]);
-    harmony_cli::init(maestro, None).await.unwrap();
+    harmony_cli::run(
+        Inventory::autoload(),
+        LocalhostTopology::new(),
+        vec![
+            Box::new(SuccessScore {}),
+            Box::new(ErrorScore {}),
+            Box::new(PanicScore {}),
+            Box::new(DiscoverInventoryAgentScore {
+                discovery_timeout: Some(10),
+            }),
+        ],
+        None,
+    )
+    .await
+    .unwrap();
 }

examples/kube-rs/Cargo.toml

@@ -14,8 +14,8 @@ harmony_macros = { path = "../../harmony_macros" }
 log = { workspace = true }
 env_logger = { workspace = true }
 url = { workspace = true }
-kube = "0.98.0"
-k8s-openapi = { version = "0.24.0", features = [ "v1_30" ] }
+kube = "1.1.0"
+k8s-openapi = { version = "0.25.0", features = ["v1_30"] }
 http = "1.2.0"
 serde_yaml = "0.9.34"
 inquire.workspace = true

examples/kube-rs/src/main.rs

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

examples/lamp/Cargo.toml

@@ -8,7 +8,7 @@ publish = false
 
 [dependencies]
 harmony = { path = "../../harmony" }
-harmony_tui = { path = "../../harmony_tui" }
+harmony_cli = { path = "../../harmony_cli" }
 harmony_types = { path = "../../harmony_types" }
 cidr = { workspace = true }
 tokio = { workspace = true }

examples/lamp/php/index.php

@@ -1,3 +1,85 @@
 <?php
-print_r("Hello this is from PHP")
+
+ini_set('display_errors', 1);
+error_reporting(E_ALL);
+
+$host = getenv('MYSQL_HOST') ?: '';
+$user = getenv('MYSQL_USER') ?: 'root';
+$pass = getenv('MYSQL_PASSWORD') ?: '';
+$db   = 'testfill';
+$charset = 'utf8mb4';
+
+$dsn = "mysql:host=$host;charset=$charset";
+$options = [
+    PDO::ATTR_ERRMODE => PDO::ERRMODE_EXCEPTION,
+    PDO::ATTR_DEFAULT_FETCH_MODE => PDO::FETCH_ASSOC,
+];
+
+try {
+    $pdo = new PDO($dsn, $user, $pass, $options);
+    $pdo->exec("CREATE DATABASE IF NOT EXISTS `$db`");
+    $pdo->exec("USE `$db`");
+    $pdo->exec("
+        CREATE TABLE IF NOT EXISTS filler (
+            id INT AUTO_INCREMENT PRIMARY KEY,
+            data LONGBLOB
+        )
+    ");
+} catch (\PDOException $e) {
+    die("❌ DB connection failed: " . $e->getMessage());
+}
+
+function getDbStats($pdo, $db) {
+    $stmt = $pdo->query("
+        SELECT 
+            ROUND(SUM(data_length + index_length) / 1024 / 1024 / 1024, 2) AS total_size_gb,
+            SUM(table_rows) AS total_rows
+        FROM information_schema.tables
+        WHERE table_schema = '$db'
+    ");
+    $result = $stmt->fetch();
+    $sizeGb = $result['total_size_gb'] ?? '0';
+    $rows = $result['total_rows'] ?? '0';
+    $avgMb = ($rows > 0) ? round(($sizeGb * 1024) / $rows, 2) : 0;
+    return [$sizeGb, $rows, $avgMb];
+}
+
+list($dbSize, $rowCount, $avgRowMb) = getDbStats($pdo, $db);
+
+$message = '';
+
+if ($_SERVER['REQUEST_METHOD'] === 'POST' && isset($_POST['fill'])) {
+    $iterations = 1024;
+    $data = str_repeat(random_bytes(1024), 1024); // 1MB
+    $stmt = $pdo->prepare("INSERT INTO filler (data) VALUES (:data)");
+
+    for ($i = 0; $i < $iterations; $i++) {
+        $stmt->execute([':data' => $data]);
+    }
+
+    list($dbSize, $rowCount, $avgRowMb) = getDbStats($pdo, $db);
+
+    $message = "<p style='color: green;'>✅ 1GB inserted into MariaDB successfully.</p>";
+}
 ?>
+
+<!DOCTYPE html>
+<html>
+<head>
+    <title>MariaDB Filler</title>
+</head>
+<body>
+    <h1>MariaDB Storage Filler</h1>
+    <?= $message ?>
+    <ul>
+        <li><strong>📦 MariaDB Used Size:</strong> <?= $dbSize ?> GB</li>
+        <li><strong>📊 Total Rows:</strong> <?= $rowCount ?></li>
+        <li><strong>📐 Average Row Size:</strong> <?= $avgRowMb ?> MB</li>
+    </ul>
+
+    <form method="post">
+        <button name="fill" value="1" type="submit">Insert 1GB into DB</button>
+    </form>
+</body>
+</html>
+

examples/lamp/src/main.rs

@@ -1,35 +1,55 @@
 use harmony::{
     data::Version,
     inventory::Inventory,
-    maestro::Maestro,
-    modules::lamp::{LAMPConfig, LAMPProfile, LAMPScore},
-    topology::{K8sAnywhereTopology, Url},
+    modules::lamp::{LAMPConfig, LAMPScore},
+    topology::K8sAnywhereTopology,
 };
-use std::collections::HashMap;
+use harmony_types::net::Url;
 
 #[tokio::main]
 async fn main() {
-    // let _ = env_logger::Builder::from_default_env().filter_level(log::LevelFilter::Info).try_init();
+    // This here is the whole configuration to
+    // - setup a local K3D cluster
+    // - Build a docker image with the PHP project builtin and production grade settings
+    // - Deploy a mariadb database using a production grade helm chart
+    // - Deploy the new container using a kubernetes deployment
+    // - Configure networking between the PHP container and the database
+    // - Provision a public route and an SSL certificate automatically on production environments
+    //
+    // Enjoy :)
     let lamp_stack = LAMPScore {
         name: "harmony-lamp-demo".to_string(),
         domain: Url::Url(url::Url::parse("https://lampdemo.harmony.nationtech.io").unwrap()),
         php_version: Version::from("8.4.4").unwrap(),
+        // This config can be extended as needed for more complicated configurations
         config: LAMPConfig {
             project_root: "./php".into(),
+            database_size: "4Gi".to_string().into(),
             ..Default::default()
         },
-        profiles: HashMap::from([
-            ("dev", LAMPProfile { ssl_enabled: false }),
-            ("prod", LAMPProfile { ssl_enabled: true }),
-        ]),
     };
 
-    let mut maestro = Maestro::<K8sAnywhereTopology>::initialize(
+    //let monitoring = MonitoringAlertingScore {
+    //    alert_receivers: vec![Box::new(DiscordWebhook {
+    //        url: Url::Url(url::Url::parse("https://discord.idonotexist.com").unwrap()),
+    //        // TODO write url macro
+    //        // url: url!("https://discord.idonotexist.com"),
+    //    })],
+    //    alert_rules: vec![],
+    //    scrape_targets: vec![],
+    //};
+
+    // You can choose the type of Topology you want, we suggest starting with the
+    // K8sAnywhereTopology as it is the most automatic one that enables you to easily deploy
+    // locally, to development environment from a CI, to staging, and to production with settings
+    // that automatically adapt to each environment grade.
+    harmony_cli::run(
         Inventory::autoload(),
-        K8sAnywhereTopology::new(),
+        K8sAnywhereTopology::from_env(),
+        vec![Box::new(lamp_stack)],
+        None,
     )
     .await
     .unwrap();
-    maestro.register_all(vec![Box::new(lamp_stack)]);
-    harmony_tui::init(maestro).await.unwrap();
 }
+// That's it, end of the infra as code.

examples/monitoring/Cargo.toml

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

examples/monitoring/src/main.rs

@@ -0,0 +1,86 @@
+use std::collections::HashMap;
+
+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,
+                },
+            },
+        },
+        prometheus::alerts::{
+            infra::dell_server::{
+                alert_global_storage_status_critical, alert_global_storage_status_non_recoverable,
+                global_storage_status_degraded_non_critical,
+            },
+            k8s::pvc::high_pvc_fill_rate_over_two_days,
+        },
+    },
+    topology::K8sAnywhereTopology,
+};
+use harmony_types::net::Url;
+
+#[tokio::main]
+async fn main() {
+    let discord_receiver = DiscordWebhook {
+        name: "test-discord".to_string(),
+        url: Url::Url(url::Url::parse("https://discord.doesnt.exist.com").unwrap()),
+    };
+
+    let high_pvc_fill_rate_over_two_days_alert = high_pvc_fill_rate_over_two_days();
+    let dell_system_storage_degraded = global_storage_status_degraded_non_critical();
+    let alert_global_storage_status_critical = alert_global_storage_status_critical();
+    let alert_global_storage_status_non_recoverable = alert_global_storage_status_non_recoverable();
+
+    let additional_rules =
+        AlertManagerRuleGroup::new("pvc-alerts", vec![high_pvc_fill_rate_over_two_days_alert]);
+    let additional_rules2 = AlertManagerRuleGroup::new(
+        "dell-server-alerts",
+        vec![
+            dell_system_storage_degraded,
+            alert_global_storage_status_critical,
+            alert_global_storage_status_non_recoverable,
+        ],
+    );
+
+    let service_monitor_endpoint = ServiceMonitorEndpoint {
+        port: Some("80".to_string()),
+        path: Some("/metrics".to_string()),
+        scheme: Some(HTTPScheme::HTTP),
+        ..Default::default()
+    };
+
+    let service_monitor = ServiceMonitor {
+        name: "test-service-monitor".to_string(),
+        selector: Selector {
+            match_labels: HashMap::new(),
+            match_expressions: vec![MatchExpression {
+                key: "test".to_string(),
+                operator: Operator::In,
+                values: vec!["test-service".to_string()],
+            }],
+        },
+        endpoints: vec![service_monitor_endpoint],
+        ..Default::default()
+    };
+    let alerting_score = HelmPrometheusAlertingScore {
+        receivers: vec![Box::new(discord_receiver)],
+        rules: vec![Box::new(additional_rules), Box::new(additional_rules2)],
+        service_monitors: vec![service_monitor],
+    };
+
+    harmony_cli::run(
+        Inventory::autoload(),
+        K8sAnywhereTopology::from_env(),
+        vec![Box::new(alerting_score)],
+        None,
+    )
+    .await
+    .unwrap();
+}

examples/monitoring_with_tenant/Cargo.toml

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

examples/monitoring_with_tenant/src/main.rs

@@ -0,0 +1,90 @@
+use std::{collections::HashMap, str::FromStr};
+
+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,
+                },
+            },
+        },
+        prometheus::alerts::k8s::pvc::high_pvc_fill_rate_over_two_days,
+        tenant::TenantScore,
+    },
+    topology::{
+        K8sAnywhereTopology,
+        tenant::{ResourceLimits, TenantConfig, TenantNetworkPolicy},
+    },
+};
+use harmony_types::id::Id;
+use harmony_types::net::Url;
+
+#[tokio::main]
+async fn main() {
+    let tenant = TenantScore {
+        config: TenantConfig {
+            id: Id::from_str("1234").unwrap(),
+            name: "test-tenant".to_string(),
+            resource_limits: ResourceLimits {
+                cpu_request_cores: 6.0,
+                cpu_limit_cores: 4.0,
+                memory_request_gb: 4.0,
+                memory_limit_gb: 4.0,
+                storage_total_gb: 10.0,
+            },
+            network_policy: TenantNetworkPolicy::default(),
+        },
+    };
+
+    let discord_receiver = DiscordWebhook {
+        name: "test-discord".to_string(),
+        url: Url::Url(url::Url::parse("https://discord.doesnt.exist.com").unwrap()),
+    };
+
+    let high_pvc_fill_rate_over_two_days_alert = high_pvc_fill_rate_over_two_days();
+
+    let additional_rules =
+        AlertManagerRuleGroup::new("pvc-alerts", vec![high_pvc_fill_rate_over_two_days_alert]);
+
+    let service_monitor_endpoint = ServiceMonitorEndpoint {
+        port: Some("80".to_string()),
+        path: Some("/metrics".to_string()),
+        scheme: Some(HTTPScheme::HTTP),
+        ..Default::default()
+    };
+
+    let service_monitor = ServiceMonitor {
+        name: "test-service-monitor".to_string(),
+        selector: Selector {
+            match_labels: HashMap::new(),
+            match_expressions: vec![MatchExpression {
+                key: "test".to_string(),
+                operator: Operator::In,
+                values: vec!["test-service".to_string()],
+            }],
+        },
+        endpoints: vec![service_monitor_endpoint],
+        ..Default::default()
+    };
+
+    let alerting_score = HelmPrometheusAlertingScore {
+        receivers: vec![Box::new(discord_receiver)],
+        rules: vec![Box::new(additional_rules)],
+        service_monitors: vec![service_monitor],
+    };
+
+    harmony_cli::run(
+        Inventory::autoload(),
+        K8sAnywhereTopology::from_env(),
+        vec![Box::new(tenant), Box::new(alerting_score)],
+        None,
+    )
+    .await
+    .unwrap();
+}

examples/nanodc/rook-cephcluster/install-rook-cephcluster.sh

@@ -0,0 +1,4 @@
+#!/bin/bash
+
+helm install --create-namespace --namespace rook-ceph rook-ceph-cluster \
+   --set operatorNamespace=rook-ceph rook-release/rook-ceph-cluster -f values.yaml

examples/nanodc/rook-cephcluster/values.yaml

@@ -0,0 +1,721 @@
+# Default values for a single rook-ceph cluster
+# This is a YAML-formatted file.
+# Declare variables to be passed into your templates.
+
+# -- Namespace of the main rook operator
+operatorNamespace: rook-ceph
+
+# -- The metadata.name of the CephCluster CR
+# @default -- The same as the namespace
+clusterName:
+
+# -- Optional override of the target kubernetes version
+kubeVersion:
+
+# -- Cluster ceph.conf override
+configOverride:
+# configOverride: |
+#   [global]
+#   mon_allow_pool_delete = true
+#   osd_pool_default_size = 3
+#   osd_pool_default_min_size = 2
+
+# Installs a debugging toolbox deployment
+toolbox:
+  # -- Enable Ceph debugging pod deployment. See [toolbox](../Troubleshooting/ceph-toolbox.md)
+  enabled: true
+  # -- Toolbox image, defaults to the image used by the Ceph cluster
+  image: #quay.io/ceph/ceph:v19.2.2
+  # -- Toolbox tolerations
+  tolerations: []
+  # -- Toolbox affinity
+  affinity: {}
+  # -- Toolbox container security context
+  containerSecurityContext:
+    runAsNonRoot: true
+    runAsUser: 2016
+    runAsGroup: 2016
+    capabilities:
+      drop: ["ALL"]
+  # -- Toolbox resources
+  resources:
+    limits:
+      memory: "1Gi"
+    requests:
+      cpu: "100m"
+      memory: "128Mi"
+  # -- Set the priority class for the toolbox if desired
+  priorityClassName:
+
+monitoring:
+  # -- Enable Prometheus integration, will also create necessary RBAC rules to allow Operator to create ServiceMonitors.
+  # Monitoring requires Prometheus to be pre-installed
+  enabled: false
+  # -- Whether to disable the metrics reported by Ceph. If false, the prometheus mgr module and Ceph exporter are enabled
+  metricsDisabled: false
+  # -- Whether to create the Prometheus rules for Ceph alerts
+  createPrometheusRules: false
+  # -- The namespace in which to create the prometheus rules, if different from the rook cluster namespace.
+  # If you have multiple rook-ceph clusters in the same k8s cluster, choose the same namespace (ideally, namespace with prometheus
+  # deployed) to set rulesNamespaceOverride for all the clusters. Otherwise, you will get duplicate alerts with multiple alert definitions.
+  rulesNamespaceOverride:
+  # Monitoring settings for external clusters:
+  # externalMgrEndpoints: <list of endpoints>
+  # externalMgrPrometheusPort: <port>
+  # Scrape interval for prometheus
+  # interval: 10s
+  # allow adding custom labels and annotations to the prometheus rule
+  prometheusRule:
+    # -- Labels applied to PrometheusRule
+    labels: {}
+    # -- Annotations applied to PrometheusRule
+    annotations: {}
+
+# -- Create & use PSP resources. Set this to the same value as the rook-ceph chart.
+pspEnable: false
+
+# imagePullSecrets option allow to pull docker images from private docker registry. Option will be passed to all service accounts.
+# imagePullSecrets:
+# - name: my-registry-secret
+
+# All values below are taken from the CephCluster CRD
+# -- Cluster configuration.
+# @default -- See [below](#ceph-cluster-spec)
+cephClusterSpec:
+  # This cluster spec example is for a converged cluster where all the Ceph daemons are running locally,
+  # as in the host-based example (cluster.yaml). For a different configuration such as a
+  # PVC-based cluster (cluster-on-pvc.yaml), external cluster (cluster-external.yaml),
+  # or stretch cluster (cluster-stretched.yaml), replace this entire `cephClusterSpec`
+  # with the specs from those examples.
+
+  # For more details, check https://rook.io/docs/rook/v1.10/CRDs/Cluster/ceph-cluster-crd/
+  cephVersion:
+    # The container image used to launch the Ceph daemon pods (mon, mgr, osd, mds, rgw).
+    # v18 is Reef, v19 is Squid
+    # RECOMMENDATION: In production, use a specific version tag instead of the general v18 flag, which pulls the latest release and could result in different
+    # versions running within the cluster. See tags available at https://hub.docker.com/r/ceph/ceph/tags/.
+    # If you want to be more precise, you can always use a timestamp tag such as quay.io/ceph/ceph:v19.2.2-20250409
+    # This tag might not contain a new Ceph version, just security fixes from the underlying operating system, which will reduce vulnerabilities
+    image: quay.io/ceph/ceph:v19.2.2
+    # Whether to allow unsupported versions of Ceph. Currently Reef and Squid are supported.
+    # Future versions such as Tentacle (v20) would require this to be set to `true`.
+    # Do not set to true in production.
+    allowUnsupported: false
+
+  # The path on the host where configuration files will be persisted. Must be specified. If there are multiple clusters, the directory must be unique for each cluster.
+  # Important: if you reinstall the cluster, make sure you delete this directory from each host or else the mons will fail to start on the new cluster.
+  # In Minikube, the '/data' directory is configured to persist across reboots. Use "/data/rook" in Minikube environment.
+  dataDirHostPath: /var/lib/rook
+
+  # Whether or not upgrade should continue even if a check fails
+  # This means Ceph's status could be degraded and we don't recommend upgrading but you might decide otherwise
+  # Use at your OWN risk
+  # To understand Rook's upgrade process of Ceph, read https://rook.io/docs/rook/v1.10/Upgrade/ceph-upgrade/
+  skipUpgradeChecks: false
+
+  # Whether or not continue if PGs are not clean during an upgrade
+  continueUpgradeAfterChecksEvenIfNotHealthy: false
+
+  # WaitTimeoutForHealthyOSDInMinutes defines the time (in minutes) the operator would wait before an OSD can be stopped for upgrade or restart.
+  # If the timeout exceeds and OSD is not ok to stop, then the operator would skip upgrade for the current OSD and proceed with the next one
+  # if `continueUpgradeAfterChecksEvenIfNotHealthy` is `false`. If `continueUpgradeAfterChecksEvenIfNotHealthy` is `true`, then operator would
+  # continue with the upgrade of an OSD even if its not ok to stop after the timeout. This timeout won't be applied if `skipUpgradeChecks` is `true`.
+  # The default wait timeout is 10 minutes.
+  waitTimeoutForHealthyOSDInMinutes: 10
+
+  # Whether or not requires PGs are clean before an OSD upgrade. If set to `true` OSD upgrade process won't start until PGs are healthy.
+  # This configuration will be ignored if `skipUpgradeChecks` is `true`.
+  # Default is false.
+  upgradeOSDRequiresHealthyPGs: false
+
+  mon:
+    # Set the number of mons to be started. Generally recommended to be 3.
+    # For highest availability, an odd number of mons should be specified.
+    count: 3
+    # The mons should be on unique nodes. For production, at least 3 nodes are recommended for this reason.
+    # Mons should only be allowed on the same node for test environments where data loss is acceptable.
+    allowMultiplePerNode: false
+
+  mgr:
+    # When higher availability of the mgr is needed, increase the count to 2.
+    # In that case, one mgr will be active and one in standby. When Ceph updates which
+    # mgr is active, Rook will update the mgr services to match the active mgr.
+    count: 2
+    allowMultiplePerNode: false
+    modules:
+      # List of modules to optionally enable or disable.
+      # Note the "dashboard" and "monitoring" modules are already configured by other settings in the cluster CR.
+      # - name: rook
+      #   enabled: true
+
+  # enable the ceph dashboard for viewing cluster status
+  dashboard:
+    enabled: true
+    # serve the dashboard under a subpath (useful when you are accessing the dashboard via a reverse proxy)
+    # urlPrefix: /ceph-dashboard
+    # serve the dashboard at the given port.
+    # port: 8443
+    # Serve the dashboard using SSL (if using ingress to expose the dashboard and `ssl: true` you need to set
+    # the corresponding "backend protocol" annotation(s) for your ingress controller of choice)
+    ssl: true
+
+  # Network configuration, see: https://github.com/rook/rook/blob/master/Documentation/CRDs/Cluster/ceph-cluster-crd.md#network-configuration-settings
+  network:
+    connections:
+      # Whether to encrypt the data in transit across the wire to prevent eavesdropping the data on the network.
+      # The default is false. When encryption is enabled, all communication between clients and Ceph daemons, or between Ceph daemons will be encrypted.
+      # When encryption is not enabled, clients still establish a strong initial authentication and data integrity is still validated with a crc check.
+      # IMPORTANT: Encryption requires the 5.11 kernel for the latest nbd and cephfs drivers. Alternatively for testing only,
+      # you can set the "mounter: rbd-nbd" in the rbd storage class, or "mounter: fuse" in the cephfs storage class.
+      # The nbd and fuse drivers are *not* recommended in production since restarting the csi driver pod will disconnect the volumes.
+      encryption:
+        enabled: false
+      # Whether to compress the data in transit across the wire. The default is false.
+      # The kernel requirements above for encryption also apply to compression.
+      compression:
+        enabled: false
+      # Whether to require communication over msgr2. If true, the msgr v1 port (6789) will be disabled
+      # and clients will be required to connect to the Ceph cluster with the v2 port (3300).
+      # Requires a kernel that supports msgr v2 (kernel 5.11 or CentOS 8.4 or newer).
+      requireMsgr2: false
+  #   # enable host networking
+  #   provider: host
+  #   # EXPERIMENTAL: enable the Multus network provider
+  #   provider: multus
+  #   selectors:
+  #     # The selector keys are required to be `public` and `cluster`.
+  #     # Based on the configuration, the operator will do the following:
+  #     #   1. if only the `public` selector key is specified both public_network and cluster_network Ceph settings will listen on that interface
+  #     #   2. if both `public` and `cluster` selector keys are specified the first one will point to 'public_network' flag and the second one to 'cluster_network'
+  #     #
+  #     # In order to work, each selector value must match a NetworkAttachmentDefinition object in Multus
+  #     #
+  #     # public: public-conf --> NetworkAttachmentDefinition object name in Multus
+  #     # cluster: cluster-conf --> NetworkAttachmentDefinition object name in Multus
+  #   # Provide internet protocol version. IPv6, IPv4 or empty string are valid options. Empty string would mean IPv4
+  #   ipFamily: "IPv6"
+  #   # Ceph daemons to listen on both IPv4 and Ipv6 networks
+  #   dualStack: false
+
+  # enable the crash collector for ceph daemon crash collection
+  crashCollector:
+    disable: false
+    # Uncomment daysToRetain to prune ceph crash entries older than the
+    # specified number of days.
+    # daysToRetain: 30
+
+  # enable log collector, daemons will log on files and rotate
+  logCollector:
+    enabled: true
+    periodicity: daily # one of: hourly, daily, weekly, monthly
+    maxLogSize: 500M # SUFFIX may be 'M' or 'G'. Must be at least 1M.
+
+  # automate [data cleanup process](https://github.com/rook/rook/blob/master/Documentation/Storage-Configuration/ceph-teardown.md#delete-the-data-on-hosts) in cluster destruction.
+  cleanupPolicy:
+    # Since cluster cleanup is destructive to data, confirmation is required.
+    # To destroy all Rook data on hosts during uninstall, confirmation must be set to "yes-really-destroy-data".
+    # This value should only be set when the cluster is about to be deleted. After the confirmation is set,
+    # Rook will immediately stop configuring the cluster and only wait for the delete command.
+    # If the empty string is set, Rook will not destroy any data on hosts during uninstall.
+    confirmation: ""
+    # sanitizeDisks represents settings for sanitizing OSD disks on cluster deletion
+    sanitizeDisks:
+      # method indicates if the entire disk should be sanitized or simply ceph's metadata
+      # in both case, re-install is possible
+      # possible choices are 'complete' or 'quick' (default)
+      method: quick
+      # dataSource indicate where to get random bytes from to write on the disk
+      # possible choices are 'zero' (default) or 'random'
+      # using random sources will consume entropy from the system and will take much more time then the zero source
+      dataSource: zero
+      # iteration overwrite N times instead of the default (1)
+      # takes an integer value
+      iteration: 1
+    # allowUninstallWithVolumes defines how the uninstall should be performed
+    # If set to true, cephCluster deletion does not wait for the PVs to be deleted.
+    allowUninstallWithVolumes: false
+
+  # To control where various services will be scheduled by kubernetes, use the placement configuration sections below.
+  # The example under 'all' would have all services scheduled on kubernetes nodes labeled with 'role=storage-node' and
+  # tolerate taints with a key of 'storage-node'.
+  # placement:
+  #   all:
+  #     nodeAffinity:
+  #       requiredDuringSchedulingIgnoredDuringExecution:
+  #         nodeSelectorTerms:
+  #           - matchExpressions:
+  #             - key: role
+  #               operator: In
+  #               values:
+  #               - storage-node
+  #     podAffinity:
+  #     podAntiAffinity:
+  #     topologySpreadConstraints:
+  #     tolerations:
+  #     - key: storage-node
+  #       operator: Exists
+  #   # The above placement information can also be specified for mon, osd, and mgr components
+  #   mon:
+  #   # Monitor deployments may contain an anti-affinity rule for avoiding monitor
+  #   # collocation on the same node. This is a required rule when host network is used
+  #   # or when AllowMultiplePerNode is false. Otherwise this anti-affinity rule is a
+  #   # preferred rule with weight: 50.
+  #   osd:
+  #   mgr:
+  #   cleanup:
+
+  # annotations:
+  #   all:
+  #   mon:
+  #   osd:
+  #   cleanup:
+  #   prepareosd:
+  #   # If no mgr annotations are set, prometheus scrape annotations will be set by default.
+  #   mgr:
+  #   dashboard:
+
+  # labels:
+  #   all:
+  #   mon:
+  #   osd:
+  #   cleanup:
+  #   mgr:
+  #   prepareosd:
+  #   # monitoring is a list of key-value pairs. It is injected into all the monitoring resources created by operator.
+  #   # These labels can be passed as LabelSelector to Prometheus
+  #   monitoring:
+  #   dashboard:
+
+  resources:
+    mgr:
+      limits:
+        memory: "1Gi"
+      requests:
+        cpu: "500m"
+        memory: "512Mi"
+    mon:
+      limits:
+        memory: "2Gi"
+      requests:
+        cpu: "1000m"
+        memory: "1Gi"
+    osd:
+      limits:
+        memory: "4Gi"
+      requests:
+        cpu: "1000m"
+        memory: "4Gi"
+    prepareosd:
+      # limits: It is not recommended to set limits on the OSD prepare job
+      #         since it's a one-time burst for memory that must be allowed to
+      #         complete without an OOM kill.  Note however that if a k8s
+      #         limitRange guardrail is defined external to Rook, the lack of
+      #         a limit here may result in a sync failure, in which case a
+      #         limit should be added.  1200Mi may suffice for up to 15Ti
+      #         OSDs ; for larger devices 2Gi may be required.
+      #         cf. https://github.com/rook/rook/pull/11103
+      requests:
+        cpu: "500m"
+        memory: "50Mi"
+    mgr-sidecar:
+      limits:
+        memory: "100Mi"
+      requests:
+        cpu: "100m"
+        memory: "40Mi"
+    crashcollector:
+      limits:
+        memory: "60Mi"
+      requests:
+        cpu: "100m"
+        memory: "60Mi"
+    logcollector:
+      limits:
+        memory: "1Gi"
+      requests:
+        cpu: "100m"
+        memory: "100Mi"
+    cleanup:
+      limits:
+        memory: "1Gi"
+      requests:
+        cpu: "500m"
+        memory: "100Mi"
+    exporter:
+      limits:
+        memory: "128Mi"
+      requests:
+        cpu: "50m"
+        memory: "50Mi"
+
+  # The option to automatically remove OSDs that are out and are safe to destroy.
+  removeOSDsIfOutAndSafeToRemove: false
+
+  # priority classes to apply to ceph resources
+  priorityClassNames:
+    mon: system-node-critical
+    osd: system-node-critical
+    mgr: system-cluster-critical
+
+  storage: # cluster level storage configuration and selection
+    useAllNodes: true
+    useAllDevices: true
+    # deviceFilter:
+    # config:
+    #   crushRoot: "custom-root" # specify a non-default root label for the CRUSH map
+    #   metadataDevice: "md0" # specify a non-rotational storage so ceph-volume will use it as block db device of bluestore.
+    #   databaseSizeMB: "1024" # uncomment if the disks are smaller than 100 GB
+    #   osdsPerDevice: "1" # this value can be overridden at the node or device level
+    #   encryptedDevice: "true" # the default value for this option is "false"
+    # # Individual nodes and their config can be specified as well, but 'useAllNodes' above must be set to false. Then, only the named
+    # # nodes below will be used as storage resources. Each node's 'name' field should match their 'kubernetes.io/hostname' label.
+    # nodes:
+    #   - name: "172.17.4.201"
+    #     devices: # specific devices to use for storage can be specified for each node
+    #       - name: "sdb"
+    #       - name: "nvme01" # multiple osds can be created on high performance devices
+    #         config:
+    #           osdsPerDevice: "5"
+    #       - name: "/dev/disk/by-id/ata-ST4000DM004-XXXX" # devices can be specified using full udev paths
+    #     config: # configuration can be specified at the node level which overrides the cluster level config
+    #   - name: "172.17.4.301"
+    #     deviceFilter: "^sd."
+
+  # The section for configuring management of daemon disruptions during upgrade or fencing.
+  disruptionManagement:
+    # If true, the operator will create and manage PodDisruptionBudgets for OSD, Mon, RGW, and MDS daemons. OSD PDBs are managed dynamically
+    # via the strategy outlined in the [design](https://github.com/rook/rook/blob/master/design/ceph/ceph-managed-disruptionbudgets.md). The operator will
+    # block eviction of OSDs by default and unblock them safely when drains are detected.
+    managePodBudgets: true
+    # A duration in minutes that determines how long an entire failureDomain like `region/zone/host` will be held in `noout` (in addition to the
+    # default DOWN/OUT interval) when it is draining. This is only relevant when  `managePodBudgets` is `true`. The default value is `30` minutes.
+    osdMaintenanceTimeout: 30
+
+  # Configure the healthcheck and liveness probes for ceph pods.
+  # Valid values for daemons are 'mon', 'osd', 'status'
+  healthCheck:
+    daemonHealth:
+      mon:
+        disabled: false
+        interval: 45s
+      osd:
+        disabled: false
+        interval: 60s
+      status:
+        disabled: false
+        interval: 60s
+    # Change pod liveness probe, it works for all mon, mgr, and osd pods.
+    livenessProbe:
+      mon:
+        disabled: false
+      mgr:
+        disabled: false
+      osd:
+        disabled: false
+
+ingress:
+  # -- Enable an ingress for the ceph-dashboard
+  dashboard:
+    # {}
+    # labels:
+       # external-dns/private: "true"
+     annotations:
+       "route.openshift.io/termination": "passthrough"
+       # external-dns.alpha.kubernetes.io/hostname: dashboard.example.com
+       # nginx.ingress.kubernetes.io/rewrite-target: /ceph-dashboard/$2
+       # If the dashboard has ssl: true the following will make sure the NGINX Ingress controller can expose the dashboard correctly
+       # nginx.ingress.kubernetes.io/backend-protocol: "HTTPS"
+       # nginx.ingress.kubernetes.io/server-snippet: |
+       #   proxy_ssl_verify off;
+     host:
+       name: ceph.apps.ncd0.harmony.mcd
+       path: null # TODO the chart does not allow removing the path, and it causes openshift to fail creating a route, because path is not supported with termination mode passthrough
+       pathType: ImplementationSpecific
+     tls:
+     - {}
+    #   secretName: testsecret-tls
+    # Note: Only one of ingress class annotation or the `ingressClassName:` can be used at a time
+    # to set the ingress class
+    # ingressClassName: openshift-default
+    # labels:
+    #   external-dns/private: "true"
+    # annotations:
+    #   external-dns.alpha.kubernetes.io/hostname: dashboard.example.com
+    #   nginx.ingress.kubernetes.io/rewrite-target: /ceph-dashboard/$2
+    # If the dashboard has ssl: true the following will make sure the NGINX Ingress controller can expose the dashboard correctly
+    #   nginx.ingress.kubernetes.io/backend-protocol: "HTTPS"
+    #   nginx.ingress.kubernetes.io/server-snippet: |
+    #     proxy_ssl_verify off;
+    # host:
+    #   name: dashboard.example.com
+    #   path: "/ceph-dashboard(/|$)(.*)"
+    #   pathType: Prefix
+    # tls:
+    # - hosts:
+    #     - dashboard.example.com
+    #   secretName: testsecret-tls
+    ## Note: Only one of ingress class annotation or the `ingressClassName:` can be used at a time
+    ## to set the ingress class
+    # ingressClassName: nginx
+
+# -- A list of CephBlockPool configurations to deploy
+# @default -- See [below](#ceph-block-pools)
+cephBlockPools:
+  - name: ceph-blockpool
+    # see https://github.com/rook/rook/blob/master/Documentation/CRDs/Block-Storage/ceph-block-pool-crd.md#spec for available configuration
+    spec:
+      failureDomain: host
+      replicated:
+        size: 3
+      # Enables collecting RBD per-image IO statistics by enabling dynamic OSD performance counters. Defaults to false.
+      # For reference: https://docs.ceph.com/docs/latest/mgr/prometheus/#rbd-io-statistics
+      # enableRBDStats: true
+    storageClass:
+      enabled: true
+      name: ceph-block
+      annotations: {}
+      labels: {}
+      isDefault: true
+      reclaimPolicy: Delete
+      allowVolumeExpansion: true
+      volumeBindingMode: "Immediate"
+      mountOptions: []
+      # see https://kubernetes.io/docs/concepts/storage/storage-classes/#allowed-topologies
+      allowedTopologies: []
+      #        - matchLabelExpressions:
+      #            - key: rook-ceph-role
+      #              values:
+      #                - storage-node
+      # see https://github.com/rook/rook/blob/master/Documentation/Storage-Configuration/Block-Storage-RBD/block-storage.md#provision-storage for available configuration
+      parameters:
+        # (optional) mapOptions is a comma-separated list of map options.
+        # For krbd options refer
+        # https://docs.ceph.com/docs/latest/man/8/rbd/#kernel-rbd-krbd-options
+        # For nbd options refer
+        # https://docs.ceph.com/docs/latest/man/8/rbd-nbd/#options
+        # mapOptions: lock_on_read,queue_depth=1024
+
+        # (optional) unmapOptions is a comma-separated list of unmap options.
+        # For krbd options refer
+        # https://docs.ceph.com/docs/latest/man/8/rbd/#kernel-rbd-krbd-options
+        # For nbd options refer
+        # https://docs.ceph.com/docs/latest/man/8/rbd-nbd/#options
+        # unmapOptions: force
+
+        # RBD image format. Defaults to "2".
+        imageFormat: "2"
+
+        # RBD image features, equivalent to OR'd bitfield value: 63
+        # Available for imageFormat: "2". Older releases of CSI RBD
+        # support only the `layering` feature. The Linux kernel (KRBD) supports the
+        # full feature complement as of 5.4
+        imageFeatures: layering
+
+        # These secrets contain Ceph admin credentials.
+        csi.storage.k8s.io/provisioner-secret-name: rook-csi-rbd-provisioner
+        csi.storage.k8s.io/provisioner-secret-namespace: "{{ .Release.Namespace }}"
+        csi.storage.k8s.io/controller-expand-secret-name: rook-csi-rbd-provisioner
+        csi.storage.k8s.io/controller-expand-secret-namespace: "{{ .Release.Namespace }}"
+        csi.storage.k8s.io/node-stage-secret-name: rook-csi-rbd-node
+        csi.storage.k8s.io/node-stage-secret-namespace: "{{ .Release.Namespace }}"
+        # Specify the filesystem type of the volume. If not specified, csi-provisioner
+        # will set default as `ext4`. Note that `xfs` is not recommended due to potential deadlock
+        # in hyperconverged settings where the volume is mounted on the same node as the osds.
+        csi.storage.k8s.io/fstype: ext4
+
+# -- A list of CephFileSystem configurations to deploy
+# @default -- See [below](#ceph-file-systems)
+cephFileSystems:
+  - name: ceph-filesystem
+    # see https://github.com/rook/rook/blob/master/Documentation/CRDs/Shared-Filesystem/ceph-filesystem-crd.md#filesystem-settings for available configuration
+    spec:
+      metadataPool:
+        replicated:
+          size: 3
+      dataPools:
+        - failureDomain: host
+          replicated:
+            size: 3
+          # Optional and highly recommended, 'data0' by default, see https://github.com/rook/rook/blob/master/Documentation/CRDs/Shared-Filesystem/ceph-filesystem-crd.md#pools
+          name: data0
+      metadataServer:
+        activeCount: 1
+        activeStandby: true
+        resources:
+          limits:
+            memory: "4Gi"
+          requests:
+            cpu: "1000m"
+            memory: "4Gi"
+        priorityClassName: system-cluster-critical
+    storageClass:
+      enabled: true
+      isDefault: false
+      name: ceph-filesystem
+      # (Optional) specify a data pool to use, must be the name of one of the data pools above, 'data0' by default
+      pool: data0
+      reclaimPolicy: Delete
+      allowVolumeExpansion: true
+      volumeBindingMode: "Immediate"
+      annotations: {}
+      labels: {}
+      mountOptions: []
+      # see https://github.com/rook/rook/blob/master/Documentation/Storage-Configuration/Shared-Filesystem-CephFS/filesystem-storage.md#provision-storage for available configuration
+      parameters:
+        # The secrets contain Ceph admin credentials.
+        csi.storage.k8s.io/provisioner-secret-name: rook-csi-cephfs-provisioner
+        csi.storage.k8s.io/provisioner-secret-namespace: "{{ .Release.Namespace }}"
+        csi.storage.k8s.io/controller-expand-secret-name: rook-csi-cephfs-provisioner
+        csi.storage.k8s.io/controller-expand-secret-namespace: "{{ .Release.Namespace }}"
+        csi.storage.k8s.io/node-stage-secret-name: rook-csi-cephfs-node
+        csi.storage.k8s.io/node-stage-secret-namespace: "{{ .Release.Namespace }}"
+        # Specify the filesystem type of the volume. If not specified, csi-provisioner
+        # will set default as `ext4`. Note that `xfs` is not recommended due to potential deadlock
+        # in hyperconverged settings where the volume is mounted on the same node as the osds.
+        csi.storage.k8s.io/fstype: ext4
+
+# -- Settings for the filesystem snapshot class
+# @default -- See [CephFS Snapshots](../Storage-Configuration/Ceph-CSI/ceph-csi-snapshot.md#cephfs-snapshots)
+cephFileSystemVolumeSnapshotClass:
+  enabled: false
+  name: ceph-filesystem
+  isDefault: true
+  deletionPolicy: Delete
+  annotations: {}
+  labels: {}
+  # see https://rook.io/docs/rook/v1.10/Storage-Configuration/Ceph-CSI/ceph-csi-snapshot/#cephfs-snapshots for available configuration
+  parameters: {}
+
+# -- Settings for the block pool snapshot class
+# @default -- See [RBD Snapshots](../Storage-Configuration/Ceph-CSI/ceph-csi-snapshot.md#rbd-snapshots)
+cephBlockPoolsVolumeSnapshotClass:
+  enabled: false
+  name: ceph-block
+  isDefault: false
+  deletionPolicy: Delete
+  annotations: {}
+  labels: {}
+  # see https://rook.io/docs/rook/v1.10/Storage-Configuration/Ceph-CSI/ceph-csi-snapshot/#rbd-snapshots for available configuration
+  parameters: {}
+
+# -- A list of CephObjectStore configurations to deploy
+# @default -- See [below](#ceph-object-stores)
+cephObjectStores:
+  - name: ceph-objectstore
+    # see https://github.com/rook/rook/blob/master/Documentation/CRDs/Object-Storage/ceph-object-store-crd.md#object-store-settings for available configuration
+    spec:
+      metadataPool:
+        failureDomain: host
+        replicated:
+          size: 3
+      dataPool:
+        failureDomain: host
+        erasureCoded:
+          dataChunks: 2
+          codingChunks: 1
+        parameters:
+          bulk: "true"
+      preservePoolsOnDelete: true
+      gateway:
+        port: 80
+        resources:
+          limits:
+            memory: "2Gi"
+          requests:
+            cpu: "1000m"
+            memory: "1Gi"
+        # securePort: 443
+        # sslCertificateRef:
+        instances: 1
+        priorityClassName: system-cluster-critical
+        # opsLogSidecar:
+        #   resources:
+        #     limits:
+        #       memory: "100Mi"
+        #     requests:
+        #       cpu: "100m"
+        #       memory: "40Mi"
+    storageClass:
+      enabled: true
+      name: ceph-bucket
+      reclaimPolicy: Delete
+      volumeBindingMode: "Immediate"
+      annotations: {}
+      labels: {}
+      # see https://github.com/rook/rook/blob/master/Documentation/Storage-Configuration/Object-Storage-RGW/ceph-object-bucket-claim.md#storageclass for available configuration
+      parameters:
+        # note: objectStoreNamespace and objectStoreName are configured by the chart
+        region: us-east-1
+    ingress:
+      # Enable an ingress for the ceph-objectstore
+      enabled: true
+      # The ingress port by default will be the object store's "securePort" (if set), or the gateway "port".
+      # To override those defaults, set this ingress port to the desired port.
+      # port: 80
+      # annotations: {}
+      host:
+        name: objectstore.apps.ncd0.harmony.mcd
+        path: /
+        pathType: Prefix
+      # tls:
+      # - hosts:
+      #     - objectstore.example.com
+      #   secretName: ceph-objectstore-tls
+      # ingressClassName: nginx
+## cephECBlockPools are disabled by default, please remove the comments and set desired values to enable it
+## For erasure coded a replicated metadata pool is required.
+## https://rook.io/docs/rook/latest/CRDs/Shared-Filesystem/ceph-filesystem-crd/#erasure-coded
+#cephECBlockPools:
+#  - name: ec-pool
+#    spec:
+#      metadataPool:
+#        replicated:
+#          size: 2
+#      dataPool:
+#        failureDomain: osd
+#        erasureCoded:
+#          dataChunks: 2
+#          codingChunks: 1
+#        deviceClass: hdd
+#
+#    parameters:
+#      # clusterID is the namespace where the rook cluster is running
+#      # If you change this namespace, also change the namespace below where the secret namespaces are defined
+#      clusterID: rook-ceph # namespace:cluster
+#      # (optional) mapOptions is a comma-separated list of map options.
+#      # For krbd options refer
+#      # https://docs.ceph.com/docs/latest/man/8/rbd/#kernel-rbd-krbd-options
+#      # For nbd options refer
+#      # https://docs.ceph.com/docs/latest/man/8/rbd-nbd/#options
+#      # mapOptions: lock_on_read,queue_depth=1024
+#
+#      # (optional) unmapOptions is a comma-separated list of unmap options.
+#      # For krbd options refer
+#      # https://docs.ceph.com/docs/latest/man/8/rbd/#kernel-rbd-krbd-options
+#      # For nbd options refer
+#      # https://docs.ceph.com/docs/latest/man/8/rbd-nbd/#options
+#      # unmapOptions: force
+#
+#      # RBD image format. Defaults to "2".
+#      imageFormat: "2"
+#
+#      # RBD image features, equivalent to OR'd bitfield value: 63
+#      # Available for imageFormat: "2". Older releases of CSI RBD
+#      # support only the `layering` feature. The Linux kernel (KRBD) supports the
+#      # full feature complement as of 5.4
+#      # imageFeatures: layering,fast-diff,object-map,deep-flatten,exclusive-lock
+#      imageFeatures: layering
+#
+#    storageClass:
+#      provisioner: rook-ceph.rbd.csi.ceph.com # csi-provisioner-name
+#      enabled: true
+#      name: rook-ceph-block
+#      isDefault: false
+#      annotations: { }
+#      labels: { }
+#      allowVolumeExpansion: true
+#      reclaimPolicy: Delete
+
+# -- CSI driver name prefix for cephfs, rbd and nfs.
+# @default -- `namespace name where rook-ceph operator is deployed`
+csiDriverNamePrefix:

examples/nanodc/rook-operator/install-rook-operator.sh

@@ -0,0 +1,3 @@
+#!/bin/bash
+helm repo add rook-release https://charts.rook.io/release
+helm install --create-namespace --namespace rook-ceph rook-ceph rook-release/rook-ceph -f values.yaml

examples/nanodc/rook-operator/values.yaml

@@ -0,0 +1,674 @@
+# Default values for rook-ceph-operator
+# This is a YAML-formatted file.
+# Declare variables to be passed into your templates.
+
+image:
+  # -- Image
+  repository: docker.io/rook/ceph
+  # -- Image tag
+  # @default -- `master`
+  tag: v1.17.1
+  # -- Image pull policy
+  pullPolicy: IfNotPresent
+
+crds:
+  # -- Whether the helm chart should create and update the CRDs. If false, the CRDs must be
+  # managed independently with deploy/examples/crds.yaml.
+  # **WARNING** Only set during first deployment. If later disabled the cluster may be DESTROYED.
+  # If the CRDs are deleted in this case, see
+  # [the disaster recovery guide](https://rook.io/docs/rook/latest/Troubleshooting/disaster-recovery/#restoring-crds-after-deletion)
+  # to restore them.
+  enabled: true
+
+# -- Pod resource requests & limits
+resources:
+  limits:
+    memory: 512Mi
+  requests:
+    cpu: 200m
+    memory: 128Mi
+
+# -- Kubernetes [`nodeSelector`](https://kubernetes.io/docs/concepts/configuration/assign-pod-node/#nodeselector) to add to the Deployment.
+nodeSelector: {}
+# Constraint rook-ceph-operator Deployment to nodes with label `disktype: ssd`.
+# For more info, see https://kubernetes.io/docs/concepts/configuration/assign-pod-node/#nodeselector
+#  disktype: ssd
+
+# -- List of Kubernetes [`tolerations`](https://kubernetes.io/docs/concepts/scheduling-eviction/taint-and-toleration/) to add to the Deployment.
+tolerations: []
+
+# -- Delay to use for the `node.kubernetes.io/unreachable` pod failure toleration to override
+# the Kubernetes default of 5 minutes
+unreachableNodeTolerationSeconds: 5
+
+# -- Whether the operator should watch cluster CRD in its own namespace or not
+currentNamespaceOnly: false
+
+# -- Custom pod labels for the operator
+operatorPodLabels: {}
+
+# -- Pod annotations
+annotations: {}
+
+# -- Global log level for the operator.
+# Options: `ERROR`, `WARNING`, `INFO`, `DEBUG`
+logLevel: INFO
+
+# -- If true, create & use RBAC resources
+rbacEnable: true
+
+rbacAggregate:
+  # -- If true, create a ClusterRole aggregated to [user facing roles](https://kubernetes.io/docs/reference/access-authn-authz/rbac/#user-facing-roles) for objectbucketclaims
+  enableOBCs: false
+
+# -- If true, create & use PSP resources
+pspEnable: false
+
+# -- Set the priority class for the rook operator deployment if desired
+priorityClassName:
+
+# -- Set the container security context for the operator
+containerSecurityContext:
+  runAsNonRoot: true
+  runAsUser: 2016
+  runAsGroup: 2016
+  capabilities:
+    drop: ["ALL"]
+# -- If true, loop devices are allowed to be used for osds in test clusters
+allowLoopDevices: false
+
+# Settings for whether to disable the drivers or other daemons if they are not
+# needed
+csi:
+  # -- Enable Ceph CSI RBD driver
+  enableRbdDriver: true
+  # -- Enable Ceph CSI CephFS driver
+  enableCephfsDriver: true
+  # -- Disable the CSI driver.
+  disableCsiDriver: "false"
+
+  # -- Enable host networking for CSI CephFS and RBD nodeplugins. This may be necessary
+  # in some network configurations where the SDN does not provide access to an external cluster or
+  # there is significant drop in read/write performance
+  enableCSIHostNetwork: true
+  # -- Enable Snapshotter in CephFS provisioner pod
+  enableCephfsSnapshotter: true
+  # -- Enable Snapshotter in NFS provisioner pod
+  enableNFSSnapshotter: true
+  # -- Enable Snapshotter in RBD provisioner pod
+  enableRBDSnapshotter: true
+  # -- Enable Host mount for `/etc/selinux` directory for Ceph CSI nodeplugins
+  enablePluginSelinuxHostMount: false
+  # -- Enable Ceph CSI PVC encryption support
+  enableCSIEncryption: false
+
+  # -- Enable volume group snapshot feature. This feature is
+  # enabled by default as long as the necessary CRDs are available in the cluster.
+  enableVolumeGroupSnapshot: true
+  # -- PriorityClassName to be set on csi driver plugin pods
+  pluginPriorityClassName: system-node-critical
+
+  # -- PriorityClassName to be set on csi driver provisioner pods
+  provisionerPriorityClassName: system-cluster-critical
+
+  # -- Policy for modifying a volume's ownership or permissions when the RBD PVC is being mounted.
+  # supported values are documented at https://kubernetes-csi.github.io/docs/support-fsgroup.html
+  rbdFSGroupPolicy: "File"
+
+  # -- Policy for modifying a volume's ownership or permissions when the CephFS PVC is being mounted.
+  # supported values are documented at https://kubernetes-csi.github.io/docs/support-fsgroup.html
+  cephFSFSGroupPolicy: "File"
+
+  # -- Policy for modifying a volume's ownership or permissions when the NFS PVC is being mounted.
+  # supported values are documented at https://kubernetes-csi.github.io/docs/support-fsgroup.html
+  nfsFSGroupPolicy: "File"
+
+  # -- OMAP generator generates the omap mapping between the PV name and the RBD image
+  # which helps CSI to identify the rbd images for CSI operations.
+  # `CSI_ENABLE_OMAP_GENERATOR` needs to be enabled when we are using rbd mirroring feature.
+  # By default OMAP generator is disabled and when enabled, it will be deployed as a
+  # sidecar with CSI provisioner pod, to enable set it to true.
+  enableOMAPGenerator: false
+
+  # -- Set CephFS Kernel mount options to use https://docs.ceph.com/en/latest/man/8/mount.ceph/#options.
+  # Set to "ms_mode=secure" when connections.encrypted is enabled in CephCluster CR
+  cephFSKernelMountOptions:
+
+  # -- Enable adding volume metadata on the CephFS subvolumes and RBD images.
+  # Not all users might be interested in getting volume/snapshot details as metadata on CephFS subvolume and RBD images.
+  # Hence enable metadata is false by default
+  enableMetadata: false
+
+  # -- Set replicas for csi provisioner deployment
+  provisionerReplicas: 2
+
+  # -- Cluster name identifier to set as metadata on the CephFS subvolume and RBD images. This will be useful
+  # in cases like for example, when two container orchestrator clusters (Kubernetes/OCP) are using a single ceph cluster
+  clusterName:
+
+  # -- Set logging level for cephCSI containers maintained by the cephCSI.
+  # Supported values from 0 to 5. 0 for general useful logs, 5 for trace level verbosity.
+  logLevel: 0
+
+  # -- Set logging level for Kubernetes-csi sidecar containers.
+  # Supported values from 0 to 5. 0 for general useful logs (the default), 5 for trace level verbosity.
+  # @default -- `0`
+  sidecarLogLevel:
+
+  # -- CSI driver name prefix for cephfs, rbd and nfs.
+  # @default -- `namespace name where rook-ceph operator is deployed`
+  csiDriverNamePrefix:
+
+  # -- CSI RBD plugin daemonset update strategy, supported values are OnDelete and RollingUpdate
+  # @default -- `RollingUpdate`
+  rbdPluginUpdateStrategy:
+
+  # -- A maxUnavailable parameter of CSI RBD plugin daemonset update strategy.
+  # @default -- `1`
+  rbdPluginUpdateStrategyMaxUnavailable:
+
+  # -- CSI CephFS plugin daemonset update strategy, supported values are OnDelete and RollingUpdate
+  # @default -- `RollingUpdate`
+  cephFSPluginUpdateStrategy:
+
+  # -- A maxUnavailable parameter of CSI cephFS plugin daemonset update strategy.
+  # @default -- `1`
+  cephFSPluginUpdateStrategyMaxUnavailable:
+
+  # -- CSI NFS plugin daemonset update strategy, supported values are OnDelete and RollingUpdate
+  # @default -- `RollingUpdate`
+  nfsPluginUpdateStrategy:
+
+  # -- Set GRPC timeout for csi containers (in seconds). It should be >= 120. If this value is not set or is invalid, it defaults to 150
+  grpcTimeoutInSeconds: 150
+
+  # -- Burst to use while communicating with the kubernetes apiserver.
+  kubeApiBurst:
+
+  # -- QPS to use while communicating with the kubernetes apiserver.
+  kubeApiQPS:
+
+  # -- The volume of the CephCSI RBD plugin DaemonSet
+  csiRBDPluginVolume:
+  #  - name: lib-modules
+  #    hostPath:
+  #      path: /run/booted-system/kernel-modules/lib/modules/
+  #  - name: host-nix
+  #    hostPath:
+  #      path: /nix
+
+  # -- The volume mounts of the CephCSI RBD plugin DaemonSet
+  csiRBDPluginVolumeMount:
+  #  - name: host-nix
+  #    mountPath: /nix
+  #    readOnly: true
+
+  # -- The volume of the CephCSI CephFS plugin DaemonSet
+  csiCephFSPluginVolume:
+  #  - name: lib-modules
+  #    hostPath:
+  #      path: /run/booted-system/kernel-modules/lib/modules/
+  #  - name: host-nix
+  #    hostPath:
+  #      path: /nix
+
+  # -- The volume mounts of the CephCSI CephFS plugin DaemonSet
+  csiCephFSPluginVolumeMount:
+  #  - name: host-nix
+  #    mountPath: /nix
+  #    readOnly: true
+
+  # -- CEPH CSI RBD provisioner resource requirement list
+  # csi-omap-generator resources will be applied only if `enableOMAPGenerator` is set to `true`
+  # @default -- see values.yaml
+  csiRBDProvisionerResource: |
+    - name : csi-provisioner
+      resource:
+        requests:
+          memory: 128Mi
+          cpu: 100m
+        limits:
+          memory: 256Mi
+    - name : csi-resizer
+      resource:
+        requests:
+          memory: 128Mi
+          cpu: 100m
+        limits:
+          memory: 256Mi
+    - name : csi-attacher
+      resource:
+        requests:
+          memory: 128Mi
+          cpu: 100m
+        limits:
+          memory: 256Mi
+    - name : csi-snapshotter
+      resource:
+        requests:
+          memory: 128Mi
+          cpu: 100m
+        limits:
+          memory: 256Mi
+    - name : csi-rbdplugin
+      resource:
+        requests:
+          memory: 512Mi
+        limits:
+          memory: 1Gi
+    - name : csi-omap-generator
+      resource:
+        requests:
+          memory: 512Mi
+          cpu: 250m
+        limits:
+          memory: 1Gi
+    - name : liveness-prometheus
+      resource:
+        requests:
+          memory: 128Mi
+          cpu: 50m
+        limits:
+          memory: 256Mi
+
+  # -- CEPH CSI RBD plugin resource requirement list
+  # @default -- see values.yaml
+  csiRBDPluginResource: |
+    - name : driver-registrar
+      resource:
+        requests:
+          memory: 128Mi
+          cpu: 50m
+        limits:
+          memory: 256Mi
+    - name : csi-rbdplugin
+      resource:
+        requests:
+          memory: 512Mi
+          cpu: 250m
+        limits:
+          memory: 1Gi
+    - name : liveness-prometheus
+      resource:
+        requests:
+          memory: 128Mi
+          cpu: 50m
+        limits:
+          memory: 256Mi
+
+  # -- CEPH CSI CephFS provisioner resource requirement list
+  # @default -- see values.yaml
+  csiCephFSProvisionerResource: |
+    - name : csi-provisioner
+      resource:
+        requests:
+          memory: 128Mi
+          cpu: 100m
+        limits:
+          memory: 256Mi
+    - name : csi-resizer
+      resource:
+        requests:
+          memory: 128Mi
+          cpu: 100m
+        limits:
+          memory: 256Mi
+    - name : csi-attacher
+      resource:
+        requests:
+          memory: 128Mi
+          cpu: 100m
+        limits:
+          memory: 256Mi
+    - name : csi-snapshotter
+      resource:
+        requests:
+          memory: 128Mi
+          cpu: 100m
+        limits:
+          memory: 256Mi
+    - name : csi-cephfsplugin
+      resource:
+        requests:
+          memory: 512Mi
+          cpu: 250m
+        limits:
+          memory: 1Gi
+    - name : liveness-prometheus
+      resource:
+        requests:
+          memory: 128Mi
+          cpu: 50m
+        limits:
+          memory: 256Mi
+
+  # -- CEPH CSI CephFS plugin resource requirement list
+  # @default -- see values.yaml
+  csiCephFSPluginResource: |
+    - name : driver-registrar
+      resource:
+        requests:
+          memory: 128Mi
+          cpu: 50m
+        limits:
+          memory: 256Mi
+    - name : csi-cephfsplugin
+      resource:
+        requests:
+          memory: 512Mi
+          cpu: 250m
+        limits:
+          memory: 1Gi
+    - name : liveness-prometheus
+      resource:
+        requests:
+          memory: 128Mi
+          cpu: 50m
+        limits:
+          memory: 256Mi
+
+  # -- CEPH CSI NFS provisioner resource requirement list
+  # @default -- see values.yaml
+  csiNFSProvisionerResource: |
+    - name : csi-provisioner
+      resource:
+        requests:
+          memory: 128Mi
+          cpu: 100m
+        limits:
+          memory: 256Mi
+    - name : csi-nfsplugin
+      resource:
+        requests:
+          memory: 512Mi
+          cpu: 250m
+        limits:
+          memory: 1Gi
+    - name : csi-attacher
+      resource:
+        requests:
+          memory: 512Mi
+          cpu: 250m
+        limits:
+          memory: 1Gi
+
+  # -- CEPH CSI NFS plugin resource requirement list
+  # @default -- see values.yaml
+  csiNFSPluginResource: |
+    - name : driver-registrar
+      resource:
+        requests:
+          memory: 128Mi
+          cpu: 50m
+        limits:
+          memory: 256Mi
+    - name : csi-nfsplugin
+      resource:
+        requests:
+          memory: 512Mi
+          cpu: 250m
+        limits:
+          memory: 1Gi
+
+  # Set provisionerTolerations and provisionerNodeAffinity for provisioner pod.
+  # The CSI provisioner would be best to start on the same nodes as other ceph daemons.
+
+  # -- Array of tolerations in YAML format which will be added to CSI provisioner deployment
+  provisionerTolerations:
+  #    - key: key
+  #      operator: Exists
+  #      effect: NoSchedule
+
+  # -- The node labels for affinity of the CSI provisioner deployment [^1]
+  provisionerNodeAffinity: #key1=value1,value2; key2=value3
+  # Set pluginTolerations and pluginNodeAffinity for plugin daemonset pods.
+  # The CSI plugins need to be started on all the nodes where the clients need to mount the storage.
+
+  # -- Array of tolerations in YAML format which will be added to CephCSI plugin DaemonSet
+  pluginTolerations:
+  #    - key: key
+  #      operator: Exists
+  #      effect: NoSchedule
+
+  # -- The node labels for affinity of the CephCSI RBD plugin DaemonSet [^1]
+  pluginNodeAffinity: # key1=value1,value2; key2=value3
+
+  # -- Enable Ceph CSI Liveness sidecar deployment
+  enableLiveness: false
+
+  # -- CSI CephFS driver metrics port
+  # @default -- `9081`
+  cephfsLivenessMetricsPort:
+
+  # -- CSI Addons server port
+  # @default -- `9070`
+  csiAddonsPort:
+  # -- CSI Addons server port for the RBD provisioner
+  # @default -- `9070`
+  csiAddonsRBDProvisionerPort:
+  # -- CSI Addons server port for the Ceph FS provisioner
+  # @default -- `9070`
+  csiAddonsCephFSProvisionerPort:
+
+  # -- Enable Ceph Kernel clients on kernel < 4.17. If your kernel does not support quotas for CephFS
+  # you may want to disable this setting. However, this will cause an issue during upgrades
+  # with the FUSE client. See the [upgrade guide](https://rook.io/docs/rook/v1.2/ceph-upgrade.html)
+  forceCephFSKernelClient: true
+
+  # -- Ceph CSI RBD driver metrics port
+  # @default -- `8080`
+  rbdLivenessMetricsPort:
+
+  serviceMonitor:
+    # -- Enable ServiceMonitor for Ceph CSI drivers
+    enabled: false
+    # -- Service monitor scrape interval
+    interval: 10s
+    # -- ServiceMonitor additional labels
+    labels: {}
+    # -- Use a different namespace for the ServiceMonitor
+    namespace:
+
+  # -- Kubelet root directory path (if the Kubelet uses a different path for the `--root-dir` flag)
+  # @default -- `/var/lib/kubelet`
+  kubeletDirPath:
+
+  # -- Duration in seconds that non-leader candidates will wait to force acquire leadership.
+  # @default -- `137s`
+  csiLeaderElectionLeaseDuration:
+
+  # -- Deadline in seconds that the acting leader will retry refreshing leadership before giving up.
+  # @default -- `107s`
+  csiLeaderElectionRenewDeadline:
+
+  # -- Retry period in seconds the LeaderElector clients should wait between tries of actions.
+  # @default -- `26s`
+  csiLeaderElectionRetryPeriod:
+
+  cephcsi:
+    # -- Ceph CSI image repository
+    repository: quay.io/cephcsi/cephcsi
+    # -- Ceph CSI image tag
+    tag: v3.14.0
+
+  registrar:
+    # -- Kubernetes CSI registrar image repository
+    repository: registry.k8s.io/sig-storage/csi-node-driver-registrar
+    # -- Registrar image tag
+    tag: v2.13.0
+
+  provisioner:
+    # -- Kubernetes CSI provisioner image repository
+    repository: registry.k8s.io/sig-storage/csi-provisioner
+    # -- Provisioner image tag
+    tag: v5.1.0
+
+  snapshotter:
+    # -- Kubernetes CSI snapshotter image repository
+    repository: registry.k8s.io/sig-storage/csi-snapshotter
+    # -- Snapshotter image tag
+    tag: v8.2.0
+
+  attacher:
+    # -- Kubernetes CSI Attacher image repository
+    repository: registry.k8s.io/sig-storage/csi-attacher
+    # -- Attacher image tag
+    tag: v4.8.0
+
+  resizer:
+    # -- Kubernetes CSI resizer image repository
+    repository: registry.k8s.io/sig-storage/csi-resizer
+    # -- Resizer image tag
+    tag: v1.13.1
+
+  # -- Image pull policy
+  imagePullPolicy: IfNotPresent
+
+  # -- Labels to add to the CSI CephFS Deployments and DaemonSets Pods
+  cephfsPodLabels: #"key1=value1,key2=value2"
+
+  # -- Labels to add to the CSI NFS Deployments and DaemonSets Pods
+  nfsPodLabels: #"key1=value1,key2=value2"
+
+  # -- Labels to add to the CSI RBD Deployments and DaemonSets Pods
+  rbdPodLabels: #"key1=value1,key2=value2"
+
+  csiAddons:
+    # -- Enable CSIAddons
+    enabled: false
+    # -- CSIAddons sidecar image repository
+    repository: quay.io/csiaddons/k8s-sidecar
+    # -- CSIAddons sidecar image tag
+    tag: v0.12.0
+
+  nfs:
+    # -- Enable the nfs csi driver
+    enabled: false
+
+  topology:
+    # -- Enable topology based provisioning
+    enabled: false
+    # NOTE: the value here serves as an example and needs to be
+    # updated with node labels that define domains of interest
+    # -- domainLabels define which node labels to use as domains
+    # for CSI nodeplugins to advertise their domains
+    domainLabels:
+    # - kubernetes.io/hostname
+    # - topology.kubernetes.io/zone
+    # - topology.rook.io/rack
+
+  # -- Whether to skip any attach operation altogether for CephFS PVCs. See more details
+  # [here](https://kubernetes-csi.github.io/docs/skip-attach.html#skip-attach-with-csi-driver-object).
+  # If cephFSAttachRequired is set to false it skips the volume attachments and makes the creation
+  # of pods using the CephFS PVC fast. **WARNING** It's highly discouraged to use this for
+  # CephFS RWO volumes. Refer to this [issue](https://github.com/kubernetes/kubernetes/issues/103305) for more details.
+  cephFSAttachRequired: true
+  # -- Whether to skip any attach operation altogether for RBD PVCs. See more details
+  # [here](https://kubernetes-csi.github.io/docs/skip-attach.html#skip-attach-with-csi-driver-object).
+  # If set to false it skips the volume attachments and makes the creation of pods using the RBD PVC fast.
+  # **WARNING** It's highly discouraged to use this for RWO volumes as it can cause data corruption.
+  # csi-addons operations like Reclaimspace and PVC Keyrotation will also not be supported if set
+  # to false since we'll have no VolumeAttachments to determine which node the PVC is mounted on.
+  # Refer to this [issue](https://github.com/kubernetes/kubernetes/issues/103305) for more details.
+  rbdAttachRequired: true
+  # -- Whether to skip any attach operation altogether for NFS PVCs. See more details
+  # [here](https://kubernetes-csi.github.io/docs/skip-attach.html#skip-attach-with-csi-driver-object).
+  # If cephFSAttachRequired is set to false it skips the volume attachments and makes the creation
+  # of pods using the NFS PVC fast. **WARNING** It's highly discouraged to use this for
+  # NFS RWO volumes. Refer to this [issue](https://github.com/kubernetes/kubernetes/issues/103305) for more details.
+  nfsAttachRequired: true
+
+# -- Enable discovery daemon
+enableDiscoveryDaemon: false
+# -- Set the discovery daemon device discovery interval (default to 60m)
+discoveryDaemonInterval: 60m
+
+# -- The timeout for ceph commands in seconds
+cephCommandsTimeoutSeconds: "15"
+
+# -- If true, run rook operator on the host network
+useOperatorHostNetwork:
+
+# -- If true, scale down the rook operator.
+# This is useful for administrative actions where the rook operator must be scaled down, while using gitops style tooling
+# to deploy your helm charts.
+scaleDownOperator: false
+
+## Rook Discover configuration
+## toleration: NoSchedule, PreferNoSchedule or NoExecute
+## tolerationKey: Set this to the specific key of the taint to tolerate
+## tolerations: Array of tolerations in YAML format which will be added to agent deployment
+## nodeAffinity: Set to labels of the node to match
+
+discover:
+  # -- Toleration for the discover pods.
+  # Options: `NoSchedule`, `PreferNoSchedule` or `NoExecute`
+  toleration:
+  # -- The specific key of the taint to tolerate
+  tolerationKey:
+  # -- Array of tolerations in YAML format which will be added to discover deployment
+  tolerations:
+  #   - key: key
+  #     operator: Exists
+  #     effect: NoSchedule
+  # -- The node labels for affinity of `discover-agent` [^1]
+  nodeAffinity:
+  #   key1=value1,value2; key2=value3
+  #
+  #   or
+  #
+  #   requiredDuringSchedulingIgnoredDuringExecution:
+  #     nodeSelectorTerms:
+  #       - matchExpressions:
+  #           - key: storage-node
+  #             operator: Exists
+  # -- Labels to add to the discover pods
+  podLabels: # "key1=value1,key2=value2"
+  # -- Add resources to discover daemon pods
+  resources:
+  #   - limits:
+  #       memory: 512Mi
+  #   - requests:
+  #       cpu: 100m
+  #       memory: 128Mi
+
+# -- Custom label to identify node hostname. If not set `kubernetes.io/hostname` will be used
+customHostnameLabel:
+
+# -- Runs Ceph Pods as privileged to be able to write to `hostPaths` in OpenShift with SELinux restrictions.
+hostpathRequiresPrivileged: false
+
+# -- Whether to create all Rook pods to run on the host network, for example in environments where a CNI is not enabled
+enforceHostNetwork: false
+
+# -- Disable automatic orchestration when new devices are discovered.
+disableDeviceHotplug: false
+
+# -- The revision history limit for all pods created by Rook. If blank, the K8s default is 10.
+revisionHistoryLimit:
+
+# -- Blacklist certain disks according to the regex provided.
+discoverDaemonUdev:
+
+# -- imagePullSecrets option allow to pull docker images from private docker registry. Option will be passed to all service accounts.
+imagePullSecrets:
+# - name: my-registry-secret
+
+# -- Whether the OBC provisioner should watch on the operator namespace or not, if not the namespace of the cluster will be used
+enableOBCWatchOperatorNamespace: true
+
+# -- Specify the prefix for the OBC provisioner in place of the cluster namespace
+# @default -- `ceph cluster namespace`
+obcProvisionerNamePrefix:
+
+# -- Many OBC additional config fields may be risky for administrators to allow users control over.
+# The safe and default-allowed fields are 'maxObjects' and 'maxSize'.
+# Other fields should be considered risky. To allow all additional configs, use this value:
+#   "maxObjects,maxSize,bucketMaxObjects,bucketMaxSize,bucketPolicy,bucketLifecycle,bucketOwner"
+# @default -- "maxObjects,maxSize"
+obcAllowAdditionalConfigFields: "maxObjects,maxSize"
+
+monitoring:
+  # -- Enable monitoring. Requires Prometheus to be pre-installed.
+  # Enabling will also create RBAC rules to allow Operator to create ServiceMonitors
+  enabled: false

examples/nanodc/src/main.rs

@@ -1,26 +1,152 @@
-use harmony::{
-    inventory::Inventory,
-    maestro::Maestro,
-    modules::dummy::{ErrorScore, PanicScore, SuccessScore},
-    topology::HAClusterTopology,
+use std::{
+    net::{IpAddr, Ipv4Addr},
+    sync::Arc,
 };
 
+use cidr::Ipv4Cidr;
+use harmony::{
+    hardware::{FirewallGroup, HostCategory, Location, PhysicalHost, SwitchGroup},
+    infra::opnsense::OPNSenseManagementInterface,
+    inventory::Inventory,
+    modules::{
+        http::StaticFilesHttpScore,
+        ipxe::IpxeScore,
+        okd::{
+            bootstrap_dhcp::OKDBootstrapDhcpScore,
+            bootstrap_load_balancer::OKDBootstrapLoadBalancerScore, dhcp::OKDDhcpScore,
+            dns::OKDDnsScore,
+        },
+        tftp::TftpScore,
+    },
+    topology::{LogicalHost, UnmanagedRouter},
+};
+use harmony_macros::{ip, mac_address};
+use harmony_types::net::Url;
+
 #[tokio::main]
 async fn main() {
-    let inventory = Inventory::autoload();
-    let topology = HAClusterTopology::autoload();
-    let mut maestro = Maestro::initialize(inventory, topology).await.unwrap();
+    let firewall = harmony::topology::LogicalHost {
+        ip: ip!("192.168.33.1"),
+        name: String::from("fw0"),
+    };
 
-    maestro.register_all(vec![
-        // ADD scores :
-        // 1. OPNSense setup scores
-        // 2. Bootstrap node setup
-        // 3. Control plane setup
-        // 4. Workers setup
-        // 5. Various tools and apps setup
-        Box::new(SuccessScore {}),
-        Box::new(ErrorScore {}),
-        Box::new(PanicScore {}),
-    ]);
-    harmony_tui::init(maestro).await.unwrap();
+    let opnsense = Arc::new(
+        harmony::infra::opnsense::OPNSenseFirewall::new(firewall, None, "root", "opnsense").await,
+    );
+    let lan_subnet = Ipv4Addr::new(192, 168, 33, 0);
+    let gateway_ipv4 = Ipv4Addr::new(192, 168, 33, 1);
+    let gateway_ip = IpAddr::V4(gateway_ipv4);
+    let topology = harmony::topology::HAClusterTopology {
+        domain_name: "ncd0.harmony.mcd".to_string(), // TODO this must be set manually correctly
+        // when setting up the opnsense firewall
+        router: Arc::new(UnmanagedRouter::new(
+            gateway_ip,
+            Ipv4Cidr::new(lan_subnet, 24).unwrap(),
+        )),
+        load_balancer: opnsense.clone(),
+        firewall: opnsense.clone(),
+        tftp_server: opnsense.clone(),
+        http_server: opnsense.clone(),
+        dhcp_server: opnsense.clone(),
+        dns_server: opnsense.clone(),
+        control_plane: vec![
+            LogicalHost {
+                ip: ip!("192.168.33.20"),
+                name: "cp0".to_string(),
+            },
+            LogicalHost {
+                ip: ip!("192.168.33.21"),
+                name: "cp1".to_string(),
+            },
+            LogicalHost {
+                ip: ip!("192.168.33.22"),
+                name: "cp2".to_string(),
+            },
+        ],
+        bootstrap_host: LogicalHost {
+            ip: ip!("192.168.33.66"),
+            name: "bootstrap".to_string(),
+        },
+        workers: vec![
+            LogicalHost {
+                ip: ip!("192.168.33.30"),
+                name: "wk0".to_string(),
+            },
+            LogicalHost {
+                ip: ip!("192.168.33.31"),
+                name: "wk1".to_string(),
+            },
+            LogicalHost {
+                ip: ip!("192.168.33.32"),
+                name: "wk2".to_string(),
+            },
+        ],
+        switch: vec![],
+    };
+
+    let inventory = Inventory {
+        location: Location::new("I am mobile".to_string(), "earth".to_string()),
+        switch: SwitchGroup::from([]),
+        firewall_mgmt: Box::new(OPNSenseManagementInterface::new()),
+        storage_host: vec![],
+        worker_host: vec![
+            PhysicalHost::empty(HostCategory::Server)
+                .mac_address(mac_address!("C4:62:37:02:61:0F")),
+            PhysicalHost::empty(HostCategory::Server)
+                .mac_address(mac_address!("C4:62:37:02:61:26")),
+            // thisone
+            // Then create the ipxe file
+            // set the dns static leases
+            // bootstrap nodes
+            // start ceph cluster
+            // try installation of lampscore
+            // bingo?
+            PhysicalHost::empty(HostCategory::Server)
+                .mac_address(mac_address!("C4:62:37:02:61:70")),
+        ],
+        control_plane_host: vec![
+            PhysicalHost::empty(HostCategory::Server)
+                .mac_address(mac_address!("C4:62:37:02:60:FA")),
+            PhysicalHost::empty(HostCategory::Server)
+                .mac_address(mac_address!("C4:62:37:02:61:1A")),
+            PhysicalHost::empty(HostCategory::Server)
+                .mac_address(mac_address!("C4:62:37:01:BC:68")),
+        ],
+    };
+
+    // TODO regroup smaller scores in a larger one such as this
+    // let okd_boostrap_preparation();
+
+    let bootstrap_dhcp_score = OKDBootstrapDhcpScore::new(&topology, &inventory);
+    let bootstrap_load_balancer_score = OKDBootstrapLoadBalancerScore::new(&topology);
+    let dhcp_score = OKDDhcpScore::new(&topology, &inventory);
+    let dns_score = OKDDnsScore::new(&topology);
+    let load_balancer_score =
+        harmony::modules::okd::load_balancer::OKDLoadBalancerScore::new(&topology);
+
+    let tftp_score = TftpScore::new(Url::LocalFolder("./data/watchguard/tftpboot".to_string()));
+    let http_score = StaticFilesHttpScore {
+        folder_to_serve: Some(Url::LocalFolder(
+            "./data/watchguard/pxe-http-files".to_string(),
+        )),
+        files: vec![],
+    };
+    let ipxe_score = IpxeScore::new();
+
+    harmony_tui::run(
+        inventory,
+        topology,
+        vec![
+            Box::new(dns_score),
+            Box::new(bootstrap_dhcp_score),
+            Box::new(bootstrap_load_balancer_score),
+            Box::new(load_balancer_score),
+            Box::new(tftp_score),
+            Box::new(http_score),
+            Box::new(ipxe_score),
+            Box::new(dhcp_score),
+        ],
+    )
+    .await
+    .unwrap();
 }

examples/ntfy/Cargo.toml

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

examples/ntfy/src/main.rs

@@ -0,0 +1,18 @@
+use harmony::{
+    inventory::Inventory, modules::monitoring::ntfy::ntfy::NtfyScore, topology::K8sAnywhereTopology,
+};
+
+#[tokio::main]
+async fn main() {
+    harmony_cli::run(
+        Inventory::autoload(),
+        K8sAnywhereTopology::from_env(),
+        vec![Box::new(NtfyScore {
+            namespace: "monitoring".to_string(),
+            host: "localhost".to_string(),
+        })],
+        None,
+    )
+    .await
+    .unwrap();
+}

examples/okd_pxe/Cargo.toml

@@ -0,0 +1,21 @@
+[package]
+name = "example-pxe"
+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" }
+harmony_secret = { path = "../../harmony_secret" }
+harmony_secret_derive = { path = "../../harmony_secret_derive" }
+cidr = { workspace = true }
+tokio = { workspace = true }
+harmony_macros = { path = "../../harmony_macros" }
+log = { workspace = true }
+env_logger = { workspace = true }
+url = { workspace = true }
+serde.workspace = true

examples/okd_pxe/src/main.rs

@@ -0,0 +1,24 @@
+mod topology;
+
+use crate::topology::{get_inventory, get_topology};
+use harmony::modules::okd::ipxe::OkdIpxeScore;
+
+#[tokio::main]
+async fn main() {
+    let inventory = get_inventory();
+    let topology = get_topology().await;
+
+    let kickstart_filename = "inventory.kickstart".to_string();
+    let cluster_pubkey_filename = "cluster_ssh_key.pub".to_string();
+    let harmony_inventory_agent = "harmony_inventory_agent".to_string();
+
+    let ipxe_score = OkdIpxeScore {
+        kickstart_filename,
+        harmony_inventory_agent,
+        cluster_pubkey_filename,
+    };
+
+    harmony_cli::run(inventory, topology, vec![Box::new(ipxe_score)], None)
+        .await
+        .unwrap();
+}

examples/okd_pxe/src/topology.rs

@@ -0,0 +1,77 @@
+use cidr::Ipv4Cidr;
+use harmony::{
+    hardware::{FirewallGroup, HostCategory, Location, PhysicalHost, SwitchGroup},
+    infra::opnsense::OPNSenseManagementInterface,
+    inventory::Inventory,
+    topology::{HAClusterTopology, LogicalHost, UnmanagedRouter},
+};
+use harmony_macros::{ip, ipv4};
+use harmony_secret::{Secret, SecretManager};
+use serde::{Deserialize, Serialize};
+use std::{net::IpAddr, sync::Arc};
+
+#[derive(Secret, Serialize, Deserialize, Debug, PartialEq)]
+struct OPNSenseFirewallConfig {
+    username: String,
+    password: String,
+}
+
+pub async fn get_topology() -> HAClusterTopology {
+    let firewall = harmony::topology::LogicalHost {
+        ip: ip!("192.168.1.1"),
+        name: String::from("opnsense-1"),
+    };
+
+    let config = SecretManager::get::<OPNSenseFirewallConfig>().await;
+    let config = config.unwrap();
+
+    let opnsense = Arc::new(
+        harmony::infra::opnsense::OPNSenseFirewall::new(
+            firewall,
+            None,
+            &config.username,
+            &config.password,
+        )
+        .await,
+    );
+    let lan_subnet = ipv4!("192.168.1.0");
+    let gateway_ipv4 = ipv4!("192.168.1.1");
+    let gateway_ip = IpAddr::V4(gateway_ipv4);
+    harmony::topology::HAClusterTopology {
+        domain_name: "demo.harmony.mcd".to_string(),
+        router: Arc::new(UnmanagedRouter::new(
+            gateway_ip,
+            Ipv4Cidr::new(lan_subnet, 24).unwrap(),
+        )),
+        load_balancer: opnsense.clone(),
+        firewall: opnsense.clone(),
+        tftp_server: opnsense.clone(),
+        http_server: opnsense.clone(),
+        dhcp_server: opnsense.clone(),
+        dns_server: opnsense.clone(),
+        control_plane: vec![LogicalHost {
+            ip: ip!("10.100.8.20"),
+            name: "cp0".to_string(),
+        }],
+        bootstrap_host: LogicalHost {
+            ip: ip!("10.100.8.20"),
+            name: "cp0".to_string(),
+        },
+        workers: vec![],
+        switch: vec![],
+    }
+}
+
+pub fn get_inventory() -> Inventory {
+    Inventory {
+        location: Location::new(
+            "Some virtual machine or maybe a physical machine if you're cool".to_string(),
+            "testopnsense".to_string(),
+        ),
+        switch: SwitchGroup::from([]),
+        firewall_mgmt: Box::new(OPNSenseManagementInterface::new()),
+        storage_host: vec![],
+        worker_host: vec![],
+        control_plane_host: vec![],
+    }
+}