feat(tools): docker autoinstall checks with docker info now and calls rootless setup helper after install

.dockerignore

@@ -1,6 +1,2 @@
 target/
-Dockerfile
-.git
-data
-target
-demos
+Dockerfile

.gitea/workflows/check.yml

@@ -15,4 +15,4 @@ jobs:
         uses: actions/checkout@v4
 
       - name: Run check script
-        run: bash build/check.sh
+        run: bash check.sh

.gitignore

@@ -24,11 +24,3 @@ Cargo.lock
 
 # MSVC Windows builds of rustc generate these, which store debugging information
 *.pdb
-
-.harmony_generated
-
-# Useful to create ignore folders for temp files and notes
-ignore
-
-# Generated book
-book

.sqlx/query-24f719d57144ecf4daa55f0aa5836c165872d70164401c0388e8d625f1b72d7b.json

@@ -1,26 +0,0 @@
-{
-  "db_name": "SQLite",
-  "query": "SELECT host_id, installation_device FROM host_role_mapping WHERE role = ?",
-  "describe": {
-    "columns": [
-      {
-        "name": "host_id",
-        "ordinal": 0,
-        "type_info": "Text"
-      },
-      {
-        "name": "installation_device",
-        "ordinal": 1,
-        "type_info": "Text"
-      }
-    ],
-    "parameters": {
-      "Right": 1
-    },
-    "nullable": [
-      false,
-      true
-    ]
-  },
-  "hash": "24f719d57144ecf4daa55f0aa5836c165872d70164401c0388e8d625f1b72d7b"
-}

.sqlx/query-2ea29df2326f7c84bd4100ad510a3fd4878dc2e217dc83f9bf45a402dfd62a91.json

@@ -0,0 +1,20 @@
+{
+  "db_name": "SQLite",
+  "query": "SELECT host_id FROM host_role_mapping WHERE role = ?",
+  "describe": {
+    "columns": [
+      {
+        "name": "host_id",
+        "ordinal": 0,
+        "type_info": "Text"
+      }
+    ],
+    "parameters": {
+      "Right": 1
+    },
+    "nullable": [
+      false
+    ]
+  },
+  "hash": "2ea29df2326f7c84bd4100ad510a3fd4878dc2e217dc83f9bf45a402dfd62a91"
+}

.sqlx/query-df7a7c9cfdd0972e2e0ce7ea444ba8bc9d708a4fb89d5593a0be2bbebde62aff.json

@@ -1,12 +1,12 @@
 {
   "db_name": "SQLite",
-  "query": "\n        INSERT INTO host_role_mapping (host_id, role, installation_device)\n        VALUES (?, ?, ?)\n        ",
+  "query": "\n        INSERT INTO host_role_mapping (host_id, role)\n        VALUES (?, ?)\n        ",
   "describe": {
     "columns": [],
     "parameters": {
-      "Right": 3
+      "Right": 2
     },
     "nullable": []
   },
-  "hash": "6fcc29cfdbdf3b2cee94a4844e227f09b245dd8f079832a9a7b774151cb03af6"
+  "hash": "df7a7c9cfdd0972e2e0ce7ea444ba8bc9d708a4fb89d5593a0be2bbebde62aff"
 }

Cargo.toml

@@ -1,28 +1,22 @@
 [workspace]
 resolver = "2"
 members = [
-  "examples/*",
   "private_repos/*",
+  "examples/*",
   "harmony",
   "harmony_types",
   "harmony_macros",
   "harmony_tui",
-  "harmony_execution",
   "opnsense-config",
   "opnsense-config-xml",
   "harmony_cli",
-  "k3d",
+  "harmony_tools",
   "harmony_composer",
   "harmony_inventory_agent",
   "harmony_secret_derive",
   "harmony_secret",
-  "harmony_config_derive",
-  "harmony_config",
+  "adr/agent_discovery/mdns",
   "brocade",
-  "harmony_agent",
-  "harmony_agent/deploy",
-  "harmony_node_readiness",
-  "harmony-k8s",
 ]
 
 [workspace.package]
@@ -41,8 +35,6 @@ tokio = { version = "1.40", features = [
   "macros",
   "rt-multi-thread",
 ] }
-tokio-retry = "0.3.0"
-tokio-util = "0.7.15"
 cidr = { features = ["serde"], version = "0.2" }
 russh = "0.45"
 russh-keys = "0.45"
@@ -57,7 +49,6 @@ kube = { version = "1.1.0", features = [
   "jsonpatch",
 ] }
 k8s-openapi = { version = "0.25", features = ["v1_30"] }
-# TODO replace with https://github.com/bourumir-wyngs/serde-saphyr as serde_yaml is deprecated https://github.com/sebastienrousseau/serde_yml
 serde_yaml = "0.9"
 serde-value = "0.7"
 http = "1.2"

README.md

@@ -1,121 +1,90 @@
-# Harmony
-
-**Infrastructure orchestration that treats your platform like first-class code.**
-
-Harmony is an open-source framework that brings the rigor of software engineering to infrastructure management. Write Rust code to define what you want, and Harmony handles the rest — from local development to production clusters.
+# Harmony : Open-source infrastructure orchestration that treats your platform like first-class code
 
 _By [NationTech](https://nationtech.io)_
 
-[![Build](https://git.nationtech.io/NationTech/harmony/actions/workflows/check.yml/badge.svg)](https://git.nationtech.io/NationTech/harmony)
+[![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)
 
----
+### Unify
 
-## The Problem Harmony Solves
+- **Project Scaffolding**
+- **Infrastructure Provisioning**
+- **Application Deployment**
+- **Day-2 operations**
 
-Modern infrastructure is messy. Your Kubernetes cluster needs monitoring. Your bare-metal servers need provisioning. Your applications need deployments. Each comes with its own tooling, its own configuration format, and its own failure modes.
+All in **one strongly-typed Rust codebase**.
 
-**What if you could describe your entire platform in one consistent language?**
+### Deploy anywhere
 
-That's Harmony. It unifies project scaffolding, infrastructure provisioning, application deployment, and day-2 operations into a single strongly-typed Rust codebase.
+From a **developer laptop** to a **global production cluster**, a single **source of truth** drives the **full software lifecycle.**
 
 ---
 
-## Three Principles That Make the Difference
+## 1 · The Harmony Philosophy
 
-| Principle | What It Means |
-|-----------|---------------|
-| **Infrastructure as Resilient Code** | Stop fighting with YAML and bash. Write type-safe Rust that you can test, version, and refactor like any other code. |
-| **Prove It Works Before You Deploy** | Harmony verifies at _compile time_ that your application can actually run on your target infrastructure. No more "the config looks right but it doesn't work" surprises. |
-| **One Unified Model** | Software and infrastructure are one system. Deploy from laptop to production cluster without switching contexts or tools. |
+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.
+
+| 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.
 
 ---
 
-## How It Works: The Core Concepts
+## 2 · Quick Start
 
-Harmony is built around three concepts that work together:
-
-### Score — "What You Want"
-
-A `Score` is a declarative description of desired state. Think of it as a "recipe" that says _what_ you want without specifying _how_ to get there.
-
-```rust
-// "I want a PostgreSQL cluster running with default settings"
-let postgres = PostgreSQLScore {
-    config: PostgreSQLConfig {
-        cluster_name: "harmony-postgres-example".to_string(),
-        namespace: "harmony-postgres-example".to_string(),
-        ..Default::default()
-    },
-};
-```
-
-### Topology — "Where It Goes"
-
-A `Topology` represents your infrastructure environment and its capabilities. It answers the question: "What can this environment actually do?"
-
-```rust
-// Deploy to a local K3D cluster, or any Kubernetes cluster via environment variables
-K8sAnywhereTopology::from_env()
-```
-
-### Interpret — "How It Happens"
-
-An `Interpret` is the execution logic that connects your `Score` to your `Topology`. It translates "what you want" into "what the infrastructure does."
-
-**The Compile-Time Check:** Before your code ever runs, Harmony verifies that your `Score` is compatible with your `Topology`. If your application needs a feature your infrastructure doesn't provide, you get a compile error — not a runtime failure.
-
----
-
-## What You Can Deploy
-
-Harmony ships with ready-made Scores for:
-
-**Data Services**
-- PostgreSQL clusters (via CloudNativePG operator)
-- Multi-site PostgreSQL with failover
-
-**Kubernetes**
-- Namespaces, Deployments, Ingress
-- Helm charts
-- cert-manager for TLS
-- Monitoring (Prometheus, alerting, ntfy)
-
-**Bare Metal / Infrastructure**
-- OKD clusters from scratch
-- OPNsense firewalls
-- Network services (DNS, DHCP, TFTP)
-- Brocade switch configuration
-
-**And more:** Application deployment, tenant management, load balancing, and more.
-
----
-
-## Quick Start: Deploy a PostgreSQL Cluster
-
-This example provisions a local Kubernetes cluster (K3D) and deploys a PostgreSQL cluster on it — no external infrastructure required.
+The snippet below spins up a complete **production-grade Rust + Leptos Webapp** with monitoring. Swap it for your own scores to deploy anything from microservices to machine-learning pipelines.
 
 ```rust
 use harmony::{
     inventory::Inventory,
-    modules::postgresql::{PostgreSQLScore, capability::PostgreSQLConfig},
+    modules::{
+        application::{
+            ApplicationScore, RustWebFramework, RustWebapp,
+            features::{PackagingDeployment, rhob_monitoring::Monitoring},
+        },
+        monitoring::alert_channel::discord_alert_channel::DiscordWebhook,
+    },
     topology::K8sAnywhereTopology,
 };
+use harmony_macros::hurl;
+use std::{path::PathBuf, sync::Arc};
 
 #[tokio::main]
 async fn main() {
-    let postgres = PostgreSQLScore {
-        config: PostgreSQLConfig {
-            cluster_name: "harmony-postgres-example".to_string(),
-            namespace: "harmony-postgres-example".to_string(),
-            ..Default::default()
-        },
+    let application = Arc::new(RustWebapp {
+        name: "harmony-example-leptos".to_string(),
+        project_root: PathBuf::from(".."), // <== Your project root, usually .. if you use the standard `/harmony` folder
+        framework: Some(RustWebFramework::Leptos),
+        service_port: 8080,
+    });
+
+    // Define your Application deployment and the features you want
+    let app = ApplicationScore {
+        features: vec![
+            Box::new(PackagingDeployment {
+                application: application.clone(),
+            }),
+            Box::new(Monitoring {
+                application: application.clone(),
+                alert_receiver: vec![
+                    Box::new(DiscordWebhook {
+                        name: "test-discord".to_string(),
+                        url: hurl!("https://discord.doesnt.exist.com"), // <== Get your discord webhook url
+                    }),
+                ],
+            }),
+        ],
+        application,
     };
 
     harmony_cli::run(
         Inventory::autoload(),
-        K8sAnywhereTopology::from_env(),
-        vec![Box::new(postgres)],
+        K8sAnywhereTopology::from_env(), // <== Deploy to local automatically provisioned local k3d by default or connect to any kubernetes cluster
+        vec![Box::new(app)],
         None,
     )
     .await
@@ -123,128 +92,70 @@ async fn main() {
 }
 ```
 
-### What this actually does
-
-When you compile and run this program:
-
-1. **Compiles** the Harmony Score into an executable
-2. **Connects** to `K8sAnywhereTopology` — which auto-provisions a local K3D cluster if none exists
-3. **Installs** the CloudNativePG operator into the cluster (one-time setup)
-4. **Creates** a PostgreSQL cluster with 1 instance and 1 GiB of storage
-5. **Exposes** the PostgreSQL instance as a Kubernetes Service
-
-### Prerequisites
-
-- [Rust](https://rust-lang.org/tools/install) (edition 2024)
-- [Docker](https://docs.docker.com/get-docker/) (for the local K3D cluster)
-- [kubectl](https://kubernetes.io/docs/tasks/tools/install-kubectl/) (optional, for inspecting the cluster)
-
-### Run it
+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
-# Clone the repository
 git clone https://git.nationtech.io/nationtech/harmony
 cd harmony
-
-# Build the project
-cargo build --release
-
-# Run the example
-cargo run -p example-postgresql
-```
-
-Harmony will print its progress as it sets up the cluster and deploys PostgreSQL. When complete, you can inspect the deployment:
-
-```bash
-kubectl get pods -n harmony-postgres-example
-kubectl get secret -n harmony-postgres-example harmony-postgres-example-db-user -o jsonpath='{.data.password}' | base64 -d
-```
-
-To connect to the database, forward the port:
-```bash
-kubectl port-forward -n harmony-postgres-example svc/harmony-postgres-example-rw 5432:5432
-psql -h localhost -p 5432 -U postgres
-```
-
-To clean up, delete the K3D cluster:
-```bash
-k3d cluster delete harmony-postgres-example
+cargo build --release          # builds the CLI, TUI and libraries
 ```
 
 ---
 
-## Environment Variables
+## 5 · Learning More
 
-`K8sAnywhereTopology::from_env()` reads the following environment variables to determine where and how to connect:
+- **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)
 
-| Variable | Default | Description |
-|----------|---------|-------------|
-| `KUBECONFIG` | `~/.kube/config` | Path to your kubeconfig file |
-| `HARMONY_AUTOINSTALL` | `true` | Auto-provision a local K3D cluster if none found |
-| `HARMONY_USE_LOCAL_K3D` | `true` | Always prefer local K3D over remote clusters |
-| `HARMONY_PROFILE` | `dev` | Deployment profile: `dev`, `staging`, or `prod` |
-| `HARMONY_K8S_CONTEXT` | _none_ | Use a specific kubeconfig context |
-| `HARMONY_PUBLIC_DOMAIN` | _none_ | Public domain for ingress endpoints |
+- **Extending Harmony** – write new Scores / Interprets, add hardware like OPNsense firewalls, or embed Harmony in your own tooling (`/docs`).
 
-To connect to an existing Kubernetes cluster instead of provisioning K3D:
-
-```bash
-# Point to your kubeconfig
-export KUBECONFIG=/path/to/your/kubeconfig
-export HARMONY_USE_LOCAL_K3D=false
-export HARMONY_AUTOINSTALL=false
-
-# Then run
-cargo run -p example-postgresql
-```
+- **Community** – discussions and roadmap live in [GitLab issues](https://git.nationtech.io/nationtech/harmony/-/issues). PRs, ideas, and feedback are welcome!
 
 ---
 
-## Documentation
-
-| I want to... | Start here |
-|--------------|------------|
-| Understand the core concepts | [Core Concepts](./docs/concepts.md) |
-| Deploy my first application | [Getting Started Guide](./docs/guides/getting-started.md) |
-| Explore available components | [Scores Catalog](./docs/catalogs/scores.md) · [Topologies Catalog](./docs/catalogs/topologies.md) |
-| See a complete bare-metal deployment | [OKD on Bare Metal](./docs/use-cases/okd-on-bare-metal.md) |
-| Build my own Score or Topology | [Developer Guide](./docs/guides/developer-guide.md) |
-
----
-
-## Why Rust?
-
-We chose Rust for the same reason you might: **reliability through type safety**.
-
-Infrastructure code runs in production. It needs to be correct. Rust's ownership model and type system let us build a framework where:
-
-- Invalid configurations fail at compile time, not at 3 AM
-- Refactoring infrastructure is as safe as refactoring application code
-- The compiler verifies that your platform can actually fulfill your requirements
-
-See [ADR-001 · Why Rust](./adr/001-rust.md) for our full rationale.
-
----
-
-## Architecture Decisions
-
-Harmony's design is documented through Architecture Decision Records (ADRs):
-
-- [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)
-
----
-
-## License
+## 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.
+> 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 NationTech and the Harmony community_
+_Made with ❤️ & 🦀 by the NationTech and the Harmony community_

adr/006-secret-management.md

@@ -2,7 +2,7 @@
 
 ## Status
 
-Rejected : See ADR 020 ./020-interactive-configuration-crate.md
+Proposed
 
 ### TODO [#3](https://git.nationtech.io/NationTech/harmony/issues/3):
 

book.toml

@@ -1,9 +0,0 @@
-[book]
-title = "Harmony"
-description = "Infrastructure orchestration that treats your platform like first-class code"
-src = "docs"
-build-dir = "book"
-authors = ["NationTech"]
-
-[output.html]
-mathjax-support = false

brocade/Cargo.toml

@@ -16,4 +16,3 @@ env_logger.workspace = true
 regex = "1.11.3"
 harmony_secret = { path = "../harmony_secret" }
 serde.workspace = true
-schemars = "0.8"

brocade/examples/main.rs

@@ -3,10 +3,9 @@ use std::net::{IpAddr, Ipv4Addr};
 use brocade::{BrocadeOptions, ssh};
 use harmony_secret::{Secret, SecretManager};
 use harmony_types::switch::PortLocation;
-use schemars::JsonSchema;
 use serde::{Deserialize, Serialize};
 
-#[derive(Secret, Clone, Debug, JsonSchema, Serialize, Deserialize)]
+#[derive(Secret, Clone, Debug, Serialize, Deserialize)]
 struct BrocadeSwitchAuth {
     username: String,
     password: String,
@@ -21,15 +20,17 @@ async fn main() {
     // let ip = IpAddr::V4(Ipv4Addr::new(192, 168, 4, 11)); // brocade @ st
     let switch_addresses = vec![ip];
 
-    let config = SecretManager::get_or_prompt::<BrocadeSwitchAuth>()
-        .await
-        .unwrap();
+    // let config = SecretManager::get_or_prompt::<BrocadeSwitchAuth>()
+    //     .await
+    //     .unwrap();
 
     let brocade = brocade::init(
         &switch_addresses,
-        &config.username,
-        &config.password,
-        &BrocadeOptions {
+        // &config.username,
+        // &config.password,
+        "admin",
+        "password",
+        BrocadeOptions {
             dry_run: true,
             ssh: ssh::SshOptions {
                 port: 2222,

brocade/src/fast_iron.rs

@@ -1,7 +1,8 @@
 use super::BrocadeClient;
 use crate::{
     BrocadeInfo, Error, ExecutionMode, InterSwitchLink, InterfaceInfo, MacAddressEntry,
-    PortChannelId, PortOperatingMode, parse_brocade_mac_address, shell::BrocadeShell,
+    PortChannelId, PortOperatingMode, SecurityLevel, parse_brocade_mac_address,
+    shell::BrocadeShell,
 };
 
 use async_trait::async_trait;

brocade/src/lib.rs

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

brocade/src/network_operating_system.rs

@@ -8,7 +8,7 @@ use regex::Regex;
 use crate::{
     BrocadeClient, BrocadeInfo, Error, ExecutionMode, InterSwitchLink, InterfaceInfo,
     InterfaceStatus, InterfaceType, MacAddressEntry, PortChannelId, PortOperatingMode,
-    parse_brocade_mac_address, shell::BrocadeShell,
+    SecurityLevel, parse_brocade_mac_address, shell::BrocadeShell,
 };
 
 #[derive(Debug)]

brocade/src/shell.rs

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

brocade/src/ssh.rs

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

build/book.sh

@@ -1,11 +0,0 @@
-#!/bin/sh
-set -e
-
-cd "$(dirname "$0")/.."
-
-cargo install mdbook --locked
-mdbook build
-
-test -f book/index.html || (echo "ERROR: book/index.html not found" && exit 1)
-test -f book/concepts.html || (echo "ERROR: book/concepts.html not found" && exit 1)
-test -f book/guides/getting-started.html || (echo "ERROR: book/guides/getting-started.html not found" && exit 1)

build/ci.sh

@@ -1,16 +0,0 @@
-#!/bin/sh
-set -e
-
-cd "$(dirname "$0")/.."
-
-BRANCH="${1:-main}"
-
-echo "=== Running CI for branch: $BRANCH ==="
-
-echo "--- Checking code ---"
-./build/check.sh
-
-echo "--- Building book ---"
-./build/book.sh
-
-echo "=== CI passed ==="

check.sh

@@ -1,8 +1,6 @@
 #!/bin/sh
 set -e
 
-cd "$(dirname "$0")/.."
-
 rustc --version
 cargo check --all-targets --all-features --keep-going
 cargo fmt --check

docs/README.md

@@ -1,37 +1 @@
-# Harmony Documentation Hub
-
-Welcome to the Harmony documentation. This is the main entry point for learning everything from core concepts to building your own Score, Topologies, and Capabilities.
-
-## 1. Getting Started
-
-If you're new to Harmony, start here:
-
-- [**Getting Started Guide**](./guides/getting-started.md): A step-by-step tutorial that takes you from an empty project to deploying your first application.
-- [**Core Concepts**](./concepts.md): A high-level overview of the key concepts in Harmony: `Score`, `Topology`, `Capability`, `Inventory`, `Interpret`, ...
-
-## 2. Use Cases & Examples
-
-See how to use Harmony to solve real-world problems.
-
-- [**PostgreSQL on Local K3D**](./use-cases/postgresql-on-local-k3d.md): Deploy a production-grade PostgreSQL cluster on a local K3D cluster. The fastest way to get started.
-- [**OKD on Bare Metal**](./use-cases/okd-on-bare-metal.md): A detailed walkthrough of bootstrapping a high-availability OKD cluster from physical hardware.
-
-## 3. Component Catalogs
-
-Discover existing, reusable components you can use in your Harmony projects.
-
-- [**Scores Catalog**](./catalogs/scores.md): A categorized list of all available `Scores` (the "what").
-- [**Topologies Catalog**](./catalogs/topologies.md): A list of all available `Topologies` (the "where").
-- [**Capabilities Catalog**](./catalogs/capabilities.md): A list of all available `Capabilities` (the "how").
-
-## 4. Developer Guides
-
-Ready to build your own components? These guides show you how.
-
-- [**Writing a Score**](./guides/writing-a-score.md): Learn how to create your own `Score` and `Interpret` logic to define a new desired state.
-- [**Writing a Topology**](./guides/writing-a-topology.md): Learn how to model a new environment (like AWS, GCP, or custom hardware) as a `Topology`.
-- [**Adding Capabilities**](./guides/adding-capabilities.md): See how to add a `Capability` to your custom `Topology`.
-
-## 5. Architecture Decision Records
-
-Harmony's design is documented through Architecture Decision Records (ADRs). See the [ADR Overview](./adr/README.md) for a complete index of all decisions.
+Not much here yet, see the `adr` folder for now. More to come in time!

docs/SUMMARY.md

@@ -1,53 +0,0 @@
-# Summary
-
-[Harmony Documentation](./README.md)
-
-- [Core Concepts](./concepts.md)
-- [Getting Started Guide](./guides/getting-started.md)
-
-## Use Cases
-
-- [PostgreSQL on Local K3D](./use-cases/postgresql-on-local-k3d.md)
-- [OKD on Bare Metal](./use-cases/okd-on-bare-metal.md)
-
-## Component Catalogs
-
-- [Scores Catalog](./catalogs/scores.md)
-- [Topologies Catalog](./catalogs/topologies.md)
-- [Capabilities Catalog](./catalogs/capabilities.md)
-
-## Developer Guides
-
-- [Developer Guide](./guides/developer-guide.md)
-- [Writing a Score](./guides/writing-a-score.md)
-- [Writing a Topology](./guides/writing-a-topology.md)
-- [Adding Capabilities](./guides/adding-capabilities.md)
-
-## Configuration
-
-- [Configuration](./concepts/configuration.md)
-
-## Architecture Decision Records
-
-- [ADR Overview](./adr/README.md)
-   - [000 · ADR Template](./adr/000-ADR-Template.md)
-   - [001 · Why Rust](./adr/001-rust.md)
-   - [002 · Hexagonal Architecture](./adr/002-hexagonal-architecture.md)
-   - [003 · Infrastructure Abstractions](./adr/003-infrastructure-abstractions.md)
-   - [004 · iPXE](./adr/004-ipxe.md)
-   - [005 · Interactive Project](./adr/005-interactive-project.md)
-   - [006 · Secret Management](./adr/006-secret-management.md)
-   - [007 · Default Runtime](./adr/007-default-runtime.md)
-   - [008 · Score Display Formatting](./adr/008-score-display-formatting.md)
-   - [009 · Helm and Kustomize Handling](./adr/009-helm-and-kustomize-handling.md)
-   - [010 · Monitoring and Alerting](./adr/010-monitoring-and-alerting.md)
-   - [011 · Multi-Tenant Cluster](./adr/011-multi-tenant-cluster.md)
-   - [012 · Project Delivery Automation](./adr/012-project-delivery-automation.md)
-   - [013 · Monitoring Notifications](./adr/013-monitoring-notifications.md)
-   - [015 · Higher Order Topologies](./adr/015-higher-order-topologies.md)
-   - [016 · Harmony Agent and Global Mesh](./adr/016-Harmony-Agent-And-Global-Mesh-For-Decentralized-Workload-Management.md)
-   - [017-1 · NATS Clusters Interconnection](./adr/017-1-Nats-Clusters-Interconnection-Topology.md)
-   - [018 · Template Hydration for Workload Deployment](./adr/018-Template-Hydration-For-Workload-Deployment.md)
-   - [019 · Network Bond Setup](./adr/019-Network-bond-setup.md)
-   - [020 · Interactive Configuration Crate](./adr/020-interactive-configuration-crate.md)
-   - [020-1 · Zitadel + OpenBao Secure Config Store](./adr/020-1-zitadel-openbao-secure-config-store.md)

docs/adr/017-1-Nats-Clusters-Interconnection-Topology.md

@@ -1,189 +0,0 @@
-### 1. ADR 017-1: NATS Cluster Interconnection & Trust Topology
-
-# Architecture Decision Record: NATS Cluster Interconnection & Trust Topology
-
-**Status:** Proposed
-**Date:** 2026-01-12
-**Precedes:** [017-Staleness-Detection-for-Failover.md]
-
-## Context
-
-In ADR 017, we defined the failover mechanisms for the Harmony mesh. However, for a Primary (Site A) and a Replica (Site B) to communicate securely—or for the Global Mesh to function across disparate locations—we must establish a robust Transport Layer Security (TLS) strategy.
-
-Our primary deployment platform is OKD (Kubernetes). While OKD provides an internal `service-ca`, it is designed primarily for intra-cluster service-to-service communication. It lacks the flexibility required for:
-1.  **Public/External Gateway Identities:** NATS Gateways need to identify themselves via public DNS names or external IPs, not just internal `.svc` cluster domains.
-2.  **Cross-Cluster Trust:** We need a mechanism to allow Cluster A to trust Cluster B without sharing a single private root key.
-
-## Decision
-
-We will implement an **"Islands of Trust"** topology using **cert-manager** on OKD.
-
-### 1. Per-Cluster Certificate Authorities (CA)
-
-* We explicitly **reject** the use of a single "Supercluster CA" shared across all sites.
-    * Instead, every Harmony Cluster (Site A, Site B, etc.) will generate its own unique Self-Signed Root CA managed by `cert-manager` inside that cluster.
-*   **Lifecycle:** Root CAs will have a long duration (e.g., 10 years) to minimize rotation friction, while Leaf Certificates (NATS servers) will remain short-lived (e.g., 90 days) and rotate automatically.
-
-> Note : The decision to have a single CA for various workloads managed by Harmony on each deployment, or to have multiple CA for each service that requires interconnection is not made yet. This ADR leans towards one CA per service. This allows for maximum flexibility. But the direction might change and no clear decision has been made yet. The alternative of establishing that each cluster/harmony deployment has a single identity could make mTLS very simple between tenants.
-
-### 2. Trust Federation via Bundle Exchange
-
-To enable secure communication (mTLS) between clusters (e.g., for NATS Gateways or Leaf Nodes):
-
-*   **No Private Keys are shared.**
-*   We will aggregate the **Public CA Certificates** of all trusted clusters into a shared `ca-bundle.pem`.
-*   This bundle is distributed to the NATS configuration of every node.
-*   **Verification Logic:** When Site A connects to Site B, Site A verifies Site B's certificate against the bundle. Since Site B's CA public key is in the bundle, the connection is accepted.
-
-### 3. Tooling
-
-* We will use **cert-manager** (deployed via Operator on OKD) rather than OKD's built-in `service-ca`. This provides us with standard CRDs (`Issuer`, `Certificate`) to manage the lifecycle, rotation, and complex SANs (Subject Alternative Names) required for external connectivity.
-* Harmony will manage installation, configuration and bundle creation across all sites
-
-## Rationale
-
-**Security Blast Radius (The "Key Leak" Scenario)**
-If we used a single global CA and the private key for Site A was compromised (e.g., physical theft of a server from a basement), the attacker could impersonate *any* site in the global mesh.
-By using Per-Cluster CAs:
-*   If Site A is compromised, only Site A's identity is stolen.
-*   We can "evict" Site A from the mesh simply by removing Site A's Public CA from the `ca-bundle.pem` on the remaining healthy clusters and reloading. The attacker can no longer authenticate.
-
-**Decentralized Autonomy**
-This aligns with the "Humane Computing" vision. A local cluster owns its identity. It does not depend on a central authority to issue its certificates. It can function in isolation (offline) indefinitely without needing to "phone home" to renew credentials.
-
-## Consequences
-
-**Positive**
-*   **High Security:** Compromise of one node does not compromise the global mesh.
-*   **Flexibility:** Easier to integrate with third-party clusters or partners by simply adding their public CA to the bundle.
-*   **Standardization:** `cert-manager` is the industry standard, making the configuration portable to non-OKD K8s clusters if needed.
-
-**Negative**
-*   **Configuration Complexity:** We must manage a mechanism to distribute the `ca-bundle.pem` containing public keys to all sites. This should be automated (e.g., via a Harmony Agent) to ensure timely updates and revocation.
-*   **Revocation Latency:** Revoking a compromised cluster requires updating and reloading the bundle on all other clusters. This is slower than OCSP/CRL but acceptable for infrastructure-level trust if automation is in place.
-
----
-
-# 2. Concrete overview of the process, how it can be implemented manually across multiple OKD clusters
-
-All of this will be automated via Harmony, but to understand correctly the process it is outlined in details here :
-
-## 1. Deploying and Configuring cert-manager on OKD
-
-While OKD has a built-in `service-ca` controller, it is "opinionated" and primarily signs certs for internal services (like `my-svc.my-namespace.svc`). It is **not suitable** for the Harmony Global Mesh because you cannot easily control the Subject Alternative Names (SANs) for external routes (e.g., `nats.site-a.nationtech.io`), nor can you easily export its CA to other clusters.
-
-**The Solution:** Use the **cert-manager Operator for Red Hat OpenShift**.
-
-### Step 1: Install the Operator
-1.  Log in to the OKD Web Console.
-2.  Navigate to **Operators** -> **OperatorHub**.
-3.  Search for **"cert-manager"**.
-4.  Choose the **"cert-manager Operator for Red Hat OpenShift"** (Red Hat provided) or the community version.
-5.  Click **Install**. Use the default settings (Namespace: `cert-manager-operator`).
-
-### Step 2: Create the "Island" CA (The Issuer)
-Once installed, you define your cluster's unique identity. Apply this YAML to your NATS namespace.
-
-```yaml
-# filepath: k8s/01-issuer.yaml
-apiVersion: cert-manager.io/v1
-kind: Issuer
-metadata:
-  name: harmony-selfsigned-issuer
-  namespace: harmony-nats
-spec:
-  selfSigned: {}
----
-# This generates the unique Root CA for THIS specific cluster
-apiVersion: cert-manager.io/v1
-kind: Certificate
-metadata:
-  name: harmony-root-ca
-  namespace: harmony-nats
-spec:
-  isCA: true
-  commonName: "harmony-site-a-ca" # CHANGE THIS per cluster (e.g., site-b-ca)
-  duration: 87600h # 10 years
-  renewBefore: 2160h # 3 months before expiry
-  secretName: harmony-root-ca-secret
-  privateKey:
-    algorithm: ECDSA
-    size: 256
-  issuerRef:
-    name: harmony-selfsigned-issuer
-    kind: Issuer
-    group: cert-manager.io
----
-# This Issuer uses the Root CA generated above to sign NATS certs
-apiVersion: cert-manager.io/v1
-kind: Issuer
-metadata:
-  name: harmony-ca-issuer
-  namespace: harmony-nats
-spec:
-  ca:
-    secretName: harmony-root-ca-secret
-```
-
-### Step 3: Generate the NATS Server Certificate
-This certificate will be used by the NATS server. It includes both internal DNS names (for local clients) and external DNS names (for the global mesh).
-
-```yaml
-# filepath: k8s/02-nats-cert.yaml
-apiVersion: cert-manager.io/v1
-kind: Certificate
-metadata:
-  name: nats-server-cert
-  namespace: harmony-nats
-spec:
-  secretName: nats-server-tls
-  duration: 2160h # 90 days
-  renewBefore: 360h # 15 days
-  issuerRef:
-    name: harmony-ca-issuer
-    kind: Issuer
-  # CRITICAL: Define all names this server can be reached by
-  dnsNames:
-  - "nats"
-  - "nats.harmony-nats.svc"
-  - "nats.harmony-nats.svc.cluster.local"
-  - "*.nats.harmony-nats.svc.cluster.local"
-  - "nats-gateway.site-a.nationtech.io" # External Route for Mesh
-```
-
-## 2. Implementing the "Islands of Trust" (Trust Bundle)
-
-To make Site A and Site B talk, you need to exchange **Public Keys**.
-
-1.  **Extract Public CA from Site A:**
-    ```bash
-    oc get secret harmony-root-ca-secret -n harmony-nats -o jsonpath='{.data.ca\.crt}' | base64 -d > site-a.crt
-    ```
-2.  **Extract Public CA from Site B:**
-    ```bash
-    oc get secret harmony-root-ca-secret -n harmony-nats -o jsonpath='{.data.ca\.crt}' | base64 -d > site-b.crt
-    ```
-3.  **Create the Bundle:**
-    Combine them into one file.
-    ```bash
-    cat site-a.crt site-b.crt > ca-bundle.crt
-    ```
-4.  **Upload Bundle to Both Clusters:**
-    Create a ConfigMap or Secret in *both* clusters containing this combined bundle.
-    ```bash
-    oc create configmap nats-trust-bundle --from-file=ca.crt=ca-bundle.crt -n harmony-nats
-    ```
-5.  **Configure NATS:**
-    Mount this ConfigMap and point NATS to it.
-
-    ```conf
-    # nats.conf snippet
-    tls {
-      cert_file: "/etc/nats-certs/tls.crt"
-      key_file:  "/etc/nats-certs/tls.key"
-      # Point to the bundle containing BOTH Site A and Site B public CAs
-      ca_file:   "/etc/nats-trust/ca.crt"
-    }
-    ```
-
-This setup ensures that Site A can verify Site B's certificate (signed by `harmony-site-b-ca`) because Site B's CA is in Site A's trust store, and vice versa, without ever sharing the private keys that generated them.

docs/adr/018-Template-Hydration-For-Workload-Deployment.md

@@ -1,141 +0,0 @@
-# Architecture Decision Record: Template Hydration for Kubernetes Manifest Generation
-
-Initial Author: Jean-Gabriel Gill-Couture & Sylvain Tremblay
-
-Initial Date: 2025-01-23
-
-Last Updated Date: 2025-01-23
-
-## Status
-
-Implemented
-
-## Context
-
-Harmony's philosophy is built on three guiding principles: Infrastructure as Resilient Code, Prove It Works — Before You Deploy, and One Unified Model. Our goal is to shift validation and verification as left as possible—ideally to compile time—rather than discovering errors at deploy time.
-
-After investigating a few approaches such as compile-checked Askama templates to generate Kubernetes manifests for Helm charts, we found again that this approach suffered from several fundamental limitations:
-
-*   **Late Validation:** Typos in template syntax or field names are only discovered at deployment time, not during compilation. A mistyped `metadata.name` won't surface until Helm attempts to render the template.
-*   **Brittle Maintenance:** Templates are string-based with limited IDE support. Refactoring requires grep-and-replace across YAML-like template files, risking subtle breakage.
-*   **Hard-to-Test Logic:** Testing template output requires mocking the template engine and comparing serialized strings rather than asserting against typed data structures.
-*   **No Type Safety:** There is no guarantee that the generated YAML will be valid Kubernetes resources without runtime validation.
-
-We also faced a strategic choice around Helm: use it as both *templating engine* and *packaging mechanism*, or decouple these concerns. While Helm's ecosystem integration (Harbor, ArgoCD, OCI registry support) is valuable, the Jinja-like templating is at odds with Harmony's "code-first" ethos.
-
-## Decision
-
-We will adopt the **Template Hydration Pattern**—constructing Kubernetes manifests programmatically using strongly-typed `kube-rs` objects, then serializing them to YAML files for packaging into Helm charts.
-
-Specifically:
-
-*   **Write strongly typed `k8s_openapi` Structs:** All Kubernetes resources (Deployment, Service, ConfigMap, etc.) will be constructed using the typed structs generated by `k8s_openapi`.
-*   **Direct Serialization to YAML:** Rather than rendering templates, we use `serde_yaml::to_string()` to serialize typed objects directly into YAML manifests. This way, YAML is only used as a data-transfer format and not a templating/programming language - which it is not.
-*   **Helm as Packaging-Only:** Helm's role is reduced to packaging pre-rendered templates into a tarball and pushing to OCI registries. No template rendering logic resides within Helm.
-*   **Ecosystem Preservation:** The generated Helm charts remain fully compatible with Harbor, ArgoCD, and any Helm-compatible tool—the only difference is that the `templates/` directory contains static YAML files.
-
-The implementation in `backend_app.rs` demonstrates this pattern:
-
-```rust
-let deployment = Deployment {
-    metadata: ObjectMeta {
-        name: Some(self.name.clone()),
-        labels: Some([("app.kubernetes.io/name".to_string(), self.name.clone())].into()),
-        ..Default::default()
-    },
-    spec: Some(DeploymentSpec { /* ... */ }),
-    ..Default::default()
-};
-
-let deployment_yaml = serde_yaml::to_string(&deployment)?;
-fs::write(templates_dir.join("deployment.yaml"), deployment_yaml)?;
-```
-
-## Rationale
-
-**Aligns with "Infrastructure as Resilient Code"**
-
-Harmony's first principle states that infrastructure should be treated like application code. By expressing Kubernetes manifests as Rust structs, we gain:
-
-*   **Refactorability:** Rename a label and the compiler catches all usages.
-*   **IDE Support:** Autocomplete for all Kubernetes API fields; documentation inline.
-*   **Code Navigation:** Jump to definition shows exactly where a value comes from.
-
-**Achieves "Prove It Works — Before You Deploy"**
-
-The compiler now validates that:
-
-*   All required fields are populated (Rust's `Option` type prevents missing fields).
-*   Field types match expectations (ports are integers, not strings).
-*   Enums contain valid values (e.g., `ServiceType::ClusterIP`).
-
-This moves what was runtime validation into compile-time checks, fulfilling the "shift left" promise.
-
-**Enables True Unit Testing**
-
-Developers can now write unit tests that assert directly against typed objects:
-
-```rust
-let deployment = create_deployment(&app);
-assert_eq!(deployment.spec.unwrap().replicas.unwrap(), 3);
-assert_eq!(deployment.metadata.name.unwrap(), "my-app");
-```
-
-No string parsing, no YAML serialization, no fragile assertions against rendered output.
-
-**Preserves Ecosystem Benefits**
-
-By generating standard Helm chart structures, Harmony retains compatibility with:
-
-*   **OCI Registries (Harbor, GHCR):** `helm push` works exactly as before.
-*   **ArgoCD:** Syncs and manages releases using the generated charts.
-*   **Existing Workflows:** Teams already consuming Helm charts see no change.
-
-The Helm tarball becomes a "dumb pipe" for transport, which is arguably its ideal role.
-
-## Consequences
-
-### Positive
-
-*   **Compile-Time Safety:** A broad class of errors (typos, missing fields, type mismatches) is now caught at build time.
-*   **Better Developer Experience:** IDE autocomplete, inline documentation, and refactor support significantly reduce the learning curve for Kubernetes manifests.
-*   **Testability:** Unit tests can validate manifest structure without integration or runtime checks.
-*   **Auditability:** The source-of-truth for manifests is now pure Rust—easier to review in pull requests than template logic scattered across files.
-*   **Future-Extensibility:** CustomResources (CRDs) can be supported via `kopium`-generated Rust types, maintaining the same strong typing.
-
-### Negative
-
-*   **API Schema Drift:** Kubernetes API changes require regenerating `k8s_openapi` types and updating code. A change in a struct field will cause the build to fail—intentionally, but still requiring the pipeline to be updated.
-*   **Verbosity:** Typed construction is more verbose than the equivalent template. Builder patterns or helper functions will be needed to keep code readable.
-*   **Learning Curve:** Contributors must understand both the Kubernetes resource spec *and* the Rust type system, rather than just YAML.
-*   **Debugging Shift:** When debugging generated YAML, you now trace through Rust code rather than template files—more precise but different mental model.
-
-## Alternatives Considered
-
-### 1. Enhance Askama with Compile-Time Validation
-*Pros:* Stay within familiar templating paradigm; minimal code changes.
-*Cons:* Rust's type system cannot fully express Kubernetes schema validation without significant macro boilerplate. Errors would still surface at template evaluation time, not compilation.
-
-### 2. Use Helm SDK Programmatically (Go)
-*Pros:* Direct access to Helm's template engine; no YAML serialization step.
-*Cons:* Would introduce a second language (Go) into a Rust codebase, increasing cognitive load and compilation complexity. No improvement in compile-time safety.
-
-### 3. Raw YAML String Templating (Manual)
-*Pros:* Maximum control; no external dependencies.
-*Cons:* Even more error-prone than Askama; no structure validation; string concatenation errors abound.
-
-### 4. Use Kustomize for All Manifests
-*Pros:* Declarative overlays; standard tool.
-*Cons:* Kustomize is itself a layer over YAML templates with its own DSL. It does not provide compile-time type safety and would require externalizing manifest management outside Harmony's codebase.
-
-__Note that this template hydration architecture still allows to override templates with tools like kustomize when required__
-
-## Additional Notes
-
-**Scalability to Future Topologies**
-
-The Template Hydration pattern enables future Harmony architectures to generate manifests dynamically based on topology context. For example, a `CostTopology` might adjust resource requests based on cluster pricing, manipulating the typed `Deployment::spec` directly before serialization.
-
-**Implementation Status**
-
-As of this writing, the pattern is implemented for `BackendApp` deployments (`backend_app.rs`). The next phase is to extend this pattern across all application modules (`webapp.rs`, etc.) and to standardize on this approach for any new implementations.

docs/adr/019-Network-bond-setup.md

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

docs/adr/020-1-zitadel-openbao-secure-config-store.md

@@ -1,233 +0,0 @@
-# ADR 020-1: Zitadel OIDC and OpenBao Integration for the Config Store
-
-Author: Jean-Gabriel Gill-Couture
-
-Date: 2026-03-18
-
-## Status
-
-Proposed
-
-## Context
-
-ADR 020 defines a unified `harmony_config` crate with a `ConfigStore` trait. The default team-oriented backend is OpenBao, which provides encrypted storage, versioned KV, audit logging, and fine-grained access control.
-
-OpenBao requires authentication. The question is how developers authenticate without introducing new credentials to manage.
-
-The goals are:
-
-- **Zero new credentials.** Developers log in with their existing corporate identity (Google Workspace, GitHub, or Microsoft Entra ID / Azure AD).
-- **Headless compatibility.** The flow must work over SSH, inside containers, and in CI — environments with no browser or localhost listener.
-- **Minimal friction.** After a one-time login, authentication should be invisible for weeks of active use.
-- **Centralized offboarding.** Revoking a user in the identity provider must immediately revoke their access to the config store.
-
-## Decision
-
-Developers authenticate to OpenBao through a two-step process: first, they obtain an OIDC token from Zitadel (`sso.nationtech.io`) using the OAuth 2.0 Device Authorization Grant (RFC 8628); then, they exchange that token for a short-lived OpenBao client token via OpenBao's JWT auth method.
-
-### The authentication flow
-
-#### Step 1: Trigger
-
-The `ConfigManager` attempts to resolve a value via the `StoreSource`. The `StoreSource` checks for a cached OpenBao token in `~/.local/share/harmony/session.json`. If the token is missing or expired, authentication begins.
-
-#### Step 2: Device Authorization Request
-
-Harmony sends a `POST` to Zitadel's device authorization endpoint:
-
-```
-POST https://sso.nationtech.io/oauth/v2/device_authorization
-Content-Type: application/x-www-form-urlencoded
-
-client_id=<harmony_client_id>&scope=openid email profile offline_access
-```
-
-Zitadel responds with:
-
-```json
-{
-  "device_code": "dOcbPeysDhT26ZatRh9n7Q",
-  "user_code": "GQWC-FWFK",
-  "verification_uri": "https://sso.nationtech.io/device",
-  "verification_uri_complete": "https://sso.nationtech.io/device?user_code=GQWC-FWFK",
-  "expires_in": 300,
-  "interval": 5
-}
-```
-
-#### Step 3: User prompt
-
-Harmony prints the code and URL to the terminal:
-
-```
-[Harmony] To authenticate, open your browser to:
-          https://sso.nationtech.io/device
-          and enter code: GQWC-FWFK
-
-          Or visit: https://sso.nationtech.io/device?user_code=GQWC-FWFK
-```
-
-If a desktop environment is detected, Harmony also calls `open` / `xdg-open` to launch the browser automatically. The `verification_uri_complete` URL pre-fills the code, so the user only needs to click "Confirm" after logging in.
-
-There is no localhost HTTP listener. The CLI does not need to bind a port or receive a callback. This is what makes the device flow work over SSH, in containers, and through corporate firewalls — unlike the `oc login` approach which spins up a temporary web server to catch a redirect.
-
-#### Step 4: User login
-
-The developer logs in through Zitadel's web UI using one of the configured identity providers:
-
-- **Google Workspace** — for teams using Google as their corporate identity.
-- **GitHub** — for open-source or GitHub-centric teams.
-- **Microsoft Entra ID (Azure AD)** — for enterprise clients, particularly common in Quebec and the broader Canadian public sector.
-
-Zitadel federates the login to the chosen provider. The developer authenticates with their existing corporate credentials. No new password is created.
-
-#### Step 5: Polling
-
-While the user is authenticating in the browser, Harmony polls Zitadel's token endpoint at the interval specified in the device authorization response (typically 5 seconds):
-
-```
-POST https://sso.nationtech.io/oauth/v2/token
-Content-Type: application/x-www-form-urlencoded
-
-grant_type=urn:ietf:params:oauth:grant-type:device_code
-&device_code=dOcbPeysDhT26ZatRh9n7Q
-&client_id=<harmony_client_id>
-```
-
-Before the user completes login, Zitadel responds with `authorization_pending`. Once the user consents, Zitadel returns:
-
-```json
-{
-  "access_token": "...",
-  "token_type": "Bearer",
-  "expires_in": 3600,
-  "refresh_token": "...",
-  "id_token": "eyJhbGciOiJSUzI1NiIs..."
-}
-```
-
-The `scope=offline_access` in the initial request is what causes Zitadel to issue a `refresh_token`.
-
-#### Step 6: OpenBao JWT exchange
-
-Harmony sends the `id_token` (a JWT signed by Zitadel) to OpenBao's JWT auth method:
-
-```
-POST https://secrets.nationtech.io/v1/auth/jwt/login
-Content-Type: application/json
-
-{
-  "role": "harmony-developer",
-  "jwt": "eyJhbGciOiJSUzI1NiIs..."
-}
-```
-
-OpenBao validates the JWT:
-
-1. It fetches Zitadel's public keys from `https://sso.nationtech.io/oauth/v2/keys` (the JWKS endpoint).
-2. It verifies the JWT signature.
-3. It reads the claims (`email`, `groups`, and any custom claims mapped from the upstream identity provider, such as Azure AD tenant or Google Workspace org).
-4. It evaluates the claims against the `bound_claims` and `bound_audiences` configured on the `harmony-developer` role.
-5. If validation passes, OpenBao returns a client token:
-
-```json
-{
-  "auth": {
-    "client_token": "hvs.CAES...",
-    "policies": ["harmony-dev"],
-    "metadata": { "role": "harmony-developer" },
-    "lease_duration": 14400,
-    "renewable": true
-  }
-}
-```
-
-Harmony caches the OpenBao token, the OIDC refresh token, and the token expiry timestamps to `~/.local/share/harmony/session.json` with `0600` file permissions.
-
-### OpenBao storage structure
-
-All configuration and secret state is stored in an OpenBao Versioned KV v2 engine.
-
-Path taxonomy:
-
-```
-harmony/<organization>/<project>/<environment>/<key>
-```
-
-Examples:
-
-```
-harmony/nationtech/my-app/staging/PostgresConfig
-harmony/nationtech/my-app/production/PostgresConfig
-harmony/nationtech/my-app/local-shared/PostgresConfig
-```
-
-The `ConfigClass` (Standard vs. Secret) can influence OpenBao policy structure — for example, `Secret`-class paths could require stricter ACLs or additional audit backends — but the path taxonomy itself does not change. This is an operational concern configured in OpenBao policies, not a structural one enforced by path naming.
-
-### Token lifecycle and silent refresh
-
-The system manages three tokens with different lifetimes:
-
-| Token | TTL | Max TTL | Purpose |
-|---|---|---|---|
-| OpenBao client token | 4 hours | 24 hours | Read/write config store |
-| OIDC ID token | 1 hour | — | Exchange for OpenBao token |
-| OIDC refresh token | 90 days absolute, 30 days inactivity | — | Obtain new ID tokens silently |
-
-The refresh flow, from the developer's perspective:
-
-1. **Same session (< 4 hours since last use).** The cached OpenBao token is still valid. No network call to Zitadel. Fastest path.
-2. **Next day (OpenBao token expired, refresh token valid).** Harmony uses the OIDC `refresh_token` to request a new `id_token` from Zitadel's token endpoint (`grant_type=refresh_token`). It then exchanges the new `id_token` for a fresh OpenBao token. This happens silently. The developer sees no prompt.
-3. **OpenBao token near max TTL (approaching 24 hours of cumulative renewals).** Instead of renewing, Harmony re-authenticates using the refresh token to get a completely fresh OpenBao token. Transparent to the user.
-4. **After 30 days of inactivity.** The OIDC refresh token expires. Harmony falls back to the device flow (Step 2 above) and prompts the user to re-authenticate in the browser. This is the only scenario where a returning developer sees a login prompt.
-5. **User offboarded.** An administrator revokes the user's account or group membership in Zitadel. The next time the refresh token is used, Zitadel rejects it. The device flow also fails because the user can no longer authenticate. Access is terminated without any action needed on the OpenBao side.
-
-OpenBao token renewal uses the `/auth/token/renew-self` endpoint with the `X-Vault-Token` header. Harmony renews proactively at ~75% of the TTL to avoid race conditions.
-
-### OpenBao role configuration
-
-The OpenBao JWT auth role for Harmony developers:
-
-```bash
-bao write auth/jwt/config \
-    oidc_discovery_url="https://sso.nationtech.io" \
-    bound_issuer="https://sso.nationtech.io"
-
-bao write auth/jwt/role/harmony-developer \
-    role_type="jwt" \
-    bound_audiences="<harmony_client_id>" \
-    user_claim="email" \
-    groups_claim="urn:zitadel:iam:org:project:roles" \
-    policies="harmony-dev" \
-    ttl="4h" \
-    max_ttl="24h" \
-    token_type="service"
-```
-
-The `bound_audiences` claim ties the role to the specific Harmony Zitadel application. The `groups_claim` allows mapping Zitadel project roles to OpenBao policies for per-team or per-project access control.
-
-### Self-hosted deployments
-
-For organizations running their own infrastructure, the same architecture applies. The operator deploys Zitadel and OpenBao using Harmony's existing `ZitadelScore` and `OpenbaoScore`. The only configuration needed is three environment variables (or their equivalents in the bootstrap config):
-
-- `HARMONY_SSO_URL` — the Zitadel instance URL.
-- `HARMONY_SECRETS_URL` — the OpenBao instance URL.
-- `HARMONY_SSO_CLIENT_ID` — the Zitadel application client ID.
-
-None of these are secrets. They can be committed to an infrastructure repository or distributed via any convenient channel.
-
-## Consequences
-
-### Positive
-
-- Developers authenticate with existing corporate credentials. No new passwords, no static tokens to distribute.
-- The device flow works in every environment: local terminal, SSH, containers, CI runners, corporate VPNs.
-- Silent token refresh keeps developers authenticated for weeks without any manual intervention.
-- User offboarding is a single action in Zitadel. No OpenBao token rotation or manual revocation required.
-- Azure AD / Microsoft Entra ID support addresses the enterprise and public sector market.
-
-### Negative
-
-- The OAuth state machine (device code polling, token refresh, error handling) adds implementation complexity compared to a static token approach.
-- Developers must have network access to `sso.nationtech.io` and `secrets.nationtech.io` to pull or push configuration state. True offline work falls back to the local file store, which does not sync with the team.
-- The first login per machine requires a browser interaction. Fully headless first-run scenarios (e.g., a fresh CI runner with no pre-seeded tokens) must use `EnvSource` overrides or a service account JWT.

docs/adr/020-interactive-configuration-crate.md

@@ -1,177 +0,0 @@
-# ADR 020: Unified Configuration and Secret Management
-
-Author: Jean-Gabriel Gill-Couture
-
-Date: 2026-03-18
-
-## Status
-
-Proposed
-
-## Context
-
-Harmony's orchestration logic depends on runtime data that falls into two categories:
-
-1. **Secrets** — credentials, tokens, private keys.
-2. **Operational configuration** — deployment targets, host selections, port assignments, reboot decisions, and similar contextual choices.
-
-Both categories share the same fundamental lifecycle: a value must be acquired before execution can proceed, it may come from several backends (environment variable, remote store, interactive prompt), and it must be shareable across a team without polluting the Git repository.
-
-Treating these categories as separate subsystems forces developers to choose between a "config API" and a "secret API" at every call site. The only meaningful difference between the two is how the storage backend handles the data (plaintext vs. encrypted, audited vs. unaudited) and how the CLI displays it (visible vs. masked). That difference belongs in the backend, not in the application code.
-
-Three concrete problems drive this change:
-
-- **Async terminal corruption.** `inquire` prompts assume exclusive terminal ownership. Background tokio tasks emitting log output during a prompt corrupt the terminal state. This is inherent to Harmony's concurrent orchestration model.
-- **Untestable code paths.** Any function containing an inline `inquire` call requires a real TTY to execute. Unit testing is impossible without ignoring the test entirely.
-- **No backend integration.** Inline prompts cannot be answered from a remote store, an environment variable, or a CI pipeline. Every automated deployment that passes through a prompting code path requires a human operator at a terminal.
-
-## Decision
-
-A single workspace crate, `harmony_config`, provides all configuration and secret acquisition for Harmony. It replaces both `harmony_secret` and all inline `inquire` usage.
-
-### Schema in Git, state in the store
-
-The Rust type system serves as the configuration schema. Developers declare what configuration is needed by defining structs:
-
-```rust
-#[derive(Config, Serialize, Deserialize, JsonSchema, InteractiveParse)]
-struct PostgresConfig {
-    pub host: String,
-    pub port: u16,
-    #[config(secret)]
-    pub password: String,
-}
-```
-
-These structs live in Git and evolve with the code. When a branch introduces a new field, Git tracks that schema change. The actual values live in an external store — OpenBao by default. No `.env` files, no JSON config files, no YAML in the repository.
-
-### Data classification
-
-```rust
-/// Tells the storage backend how to handle the data.
-pub enum ConfigClass {
-    /// Plaintext storage is acceptable.
-    Standard,
-    /// Must be encrypted at rest, masked in UI, subject to audit logging.
-    Secret,
-}
-```
-
-Classification is determined at the struct level. A struct with no `#[config(secret)]` fields has `ConfigClass::Standard`. A struct with one or more `#[config(secret)]` fields is elevated to `ConfigClass::Secret`. The struct is always stored as a single cohesive JSON blob; field-level splitting across backends is not a concern of the trait.
-
-The `#[config(secret)]` attribute also instructs the `PromptSource` to mask terminal input for that field during interactive prompting.
-
-### The Config trait
-
-```rust
-pub trait Config: Serialize + DeserializeOwned + JsonSchema + InteractiveParseObj + Sized {
-    /// Stable lookup key. By default, the struct name.
-    const KEY: &'static str;
-
-    /// How the backend should treat this data.
-    const CLASS: ConfigClass;
-}
-```
-
-A `#[derive(Config)]` proc macro generates the implementation. The macro inspects field attributes to determine `CLASS`.
-
-### The ConfigStore trait
-
-```rust
-#[async_trait]
-pub trait ConfigStore: Send + Sync {
-    async fn get(
-        &self,
-        class: ConfigClass,
-        namespace: &str,
-        key: &str,
-    ) -> Result<Option<serde_json::Value>, ConfigError>;
-
-    async fn set(
-        &self,
-        class: ConfigClass,
-        namespace: &str,
-        key: &str,
-        value: &serde_json::Value,
-    ) -> Result<(), ConfigError>;
-}
-```
-
-The `class` parameter is a hint. The store implementation decides what to do with it. An OpenBao store may route `Secret` data to a different path prefix or apply stricter ACLs. A future store could split fields across backends — that is an implementation concern, not a trait concern.
-
-### Resolution chain
-
-The `ConfigManager` tries sources in priority order:
-
-1. **`EnvSource`** — reads `HARMONY_CONFIG_{KEY}` as a JSON string. Override hatch for CI/CD pipelines and containerized environments.
-2. **`StoreSource`** — wraps a `ConfigStore` implementation. For teams, this is the OpenBao backend authenticated via Zitadel OIDC (see ADR 020-1).
-3. **`PromptSource`** — presents an `interactive-parse` prompt on the terminal. Acquires a process-wide async mutex before rendering to prevent log output corruption.
-
-When `PromptSource` obtains a value, the `ConfigManager` persists it back to the `StoreSource` so that subsequent runs — by the same developer or any teammate — resolve without prompting.
-
-Callers that do not include `PromptSource` in their source list never block on a TTY. Test code passes empty source lists and constructs config structs directly.
-
-### Schema versioning
-
-The Rust struct is the schema. When a developer renames a field, removes a field, or changes a type on a branch, the store may still contain data shaped for a previous version of the struct. If another team member who does not yet have that commit runs the code, `serde_json::from_value` will fail on the stale entry.
-
-In the initial implementation, the resolution chain handles this gracefully: a deserialization failure is treated as a cache miss, and the `PromptSource` fires. The prompted value overwrites the stale entry in the store.
-
-This is sufficient for small teams working on short-lived branches. It is not sufficient at scale, where silent re-prompting could mask real configuration drift.
-
-A future iteration will introduce a compile-time schema migration mechanism, similar to how `sqlx` verifies queries against a live database at compile time. The mechanism will:
-
-- Detect schema drift between the Rust struct and the stored JSON.
-- Apply named, ordered migration functions to transform stored data forward.
-- Reject ambiguous migrations at compile time rather than silently corrupting state.
-
-Until that mechanism exists, teams should treat store entries as soft caches: the struct definition is always authoritative, and the store is best-effort.
-
-## Rationale
-
-**Why merge secrets and config into one crate?** Separate crates with nearly identical trait shapes (`Secret` vs `Config`, `SecretStore` vs `ConfigStore`) force developers to make a classification decision at every call site. A unified crate with a `ConfigClass` discriminator moves that decision to the struct definition, where it belongs.
-
-**Why OpenBao as the default backend?** OpenBao is a fully open-source Vault fork under the Linux Foundation. It runs on-premises with no phone-home requirement — a hard constraint for private cloud and regulated environments. Harmony already deploys OpenBao for clients (`OpenbaoScore`), so no new infrastructure is introduced.
-
-**Why not store values in Git (e.g., encrypted YAML)?** Git-tracked config files create merge conflicts, require re-encryption on team membership changes, and leak metadata (file names, key names) even when values are encrypted. Storing state in OpenBao avoids all of these issues and provides audit logging, access control, and versioned KV out of the box.
-
-**Why keep `PromptSource`?** Removing interactive prompts entirely would break the zero-infrastructure bootstrapping path and eliminate human-confirmation safety gates for destructive operations (interface reconfiguration, node reboot). The problem was never that prompts exist — it is that they were unavoidable and untestable. Making `PromptSource` an explicit, opt-in entry in the source list restores control.
-
-## Consequences
-
-### Positive
-
-- A single API surface for all runtime data acquisition.
-- All currently-ignored tests become runnable without TTY access.
-- Async terminal corruption is eliminated by the process-wide prompt mutex.
-- The bootstrapping path requires no infrastructure for a first run; `PromptSource` alone is sufficient.
-- The team path (OpenBao + Zitadel) reuses infrastructure Harmony already deploys.
-- User offboarding is a single Zitadel action.
-
-### Negative
-
-- Migrating all inline `inquire` and `harmony_secret` call sites is a significant refactoring effort.
-- Until the schema migration mechanism is built, store entries for renamed or removed fields become stale and must be re-prompted.
-- The Zitadel device flow introduces a browser step on first login per machine.
-
-## Implementation Plan
-
-### Phase 1: Trait design and crate restructure
-
-Refactor `harmony_config` to define the final `Config`, `ConfigClass`, and `ConfigStore` traits. Update the derive macro to support `#[config(secret)]` and generate the correct `CLASS` constant. Implement `EnvSource` and `PromptSource` against the new traits. Write comprehensive unit tests using mock stores.
-
-### Phase 2: Absorb `harmony_secret`
-
-Migrate the `OpenbaoSecretStore`, `InfisicalSecretStore`, and `LocalFileSecretStore` implementations from `harmony_secret` into `harmony_config` as `ConfigStore` backends. Update all call sites that use `SecretManager::get`, `SecretManager::get_or_prompt`, or `SecretManager::set` to use `harmony_config` equivalents.
-
-### Phase 3: Migrate inline prompts
-
-Replace all inline `inquire` call sites in the `harmony` crate (`infra/brocade.rs`, `infra/network_manager.rs`, `modules/okd/host_network.rs`, and others) with `harmony_config` structs and `get_or_prompt` calls. Un-ignore the affected tests.
-
-### Phase 4: Zitadel and OpenBao integration
-
-Implement the authentication flow described in ADR 020-1. Wire `StoreSource` to use Zitadel OIDC tokens for OpenBao access. Implement token caching and silent refresh.
-
-### Phase 5: Remove `harmony_secret`
-
-Delete the `harmony_secret` and `harmony_secret_derive` crates from the workspace. All functionality now lives in `harmony_config`.

docs/adr/README.md

@@ -1,63 +0,0 @@
-# Architecture Decision Records
-
-An Architecture Decision Record (ADR) documents a significant architectural decision made during the development of Harmony — along with its context, rationale, and consequences.
-
-## Why We Use ADRs
-
-As a platform engineering framework used by a team, Harmony accumulates technical decisions over time. ADRs help us:
-
-- **Track rationale** — understand _why_ a decision was made, not just _what_ was decided
-- ** onboard new contributors** — the "why" is preserved even when team membership changes
-- **Avoid repeating past mistakes** — previous decisions and their context are searchable
-- **Manage technical debt** — ADRs make it easier to revisit and revise past choices
-
-An ADR captures a decision at a point in time. It is not a specification — it is a record of reasoning.
-
-## ADR Format
-
-Every ADR follows this structure:
-
-| Section | Purpose |
-|---------|---------|
-| **Status** | Proposed / Pending / Accepted / Implemented / Deprecated |
-| **Context** | The problem or background — the "why" behind this decision |
-| **Decision** | The chosen solution or direction |
-| **Rationale** | Reasoning behind the decision |
-| **Consequences** | Both positive and negative outcomes |
-| **Alternatives considered** | Other options that were evaluated |
-| **Additional Notes** | Supplementary context, links, or open questions |
-
-## ADR Index
-
-| Number | Title | Status |
-|--------|-------|--------|
-| [000](./000-ADR-Template.md) | ADR Template | Reference |
-| [001](./001-rust.md) | Why Rust | Accepted |
-| [002](./002-hexagonal-architecture.md) | Hexagonal Architecture | Accepted |
-| [003](./003-infrastructure-abstractions.md) | Infrastructure Abstractions | Accepted |
-| [004](./004-ipxe.md) | iPXE | Accepted |
-| [005](./005-interactive-project.md) | Interactive Project | Proposed |
-| [006](./006-secret-management.md) | Secret Management | Accepted |
-| [007](./007-default-runtime.md) | Default Runtime | Accepted |
-| [008](./008-score-display-formatting.md) | Score Display Formatting | Proposed |
-| [009](./009-helm-and-kustomize-handling.md) | Helm and Kustomize Handling | Accepted |
-| [010](./010-monitoring-and-alerting.md) | Monitoring and Alerting | Accepted |
-| [011](./011-multi-tenant-cluster.md) | Multi-Tenant Cluster | Accepted |
-| [012](./012-project-delivery-automation.md) | Project Delivery Automation | Proposed |
-| [013](./013-monitoring-notifications.md) | Monitoring Notifications | Accepted |
-| [015](./015-higher-order-topologies.md) | Higher Order Topologies | Proposed |
-| [016](./016-Harmony-Agent-And-Global-Mesh-For-Decentralized-Workload-Management.md) | Harmony Agent and Global Mesh | Proposed |
-| [017-1](./017-1-Nats-Clusters-Interconnection-Topology.md) | NATS Clusters Interconnection Topology | Proposed |
-| [018](./018-Template-Hydration-For-Workload-Deployment.md) | Template Hydration for Workload Deployment | Proposed |
-| [019](./019-Network-bond-setup.md) | Network Bond Setup | Proposed |
-| [020-1](./020-1-zitadel-openbao-secure-config-store.md) | Zitadel + OpenBao Secure Config Store | Accepted |
-| [020](./020-interactive-configuration-crate.md) | Interactive Configuration Crate | Proposed |
-
-## Contributing
-
-When making a significant technical change:
-
-1. **Check existing ADRs** — the decision may already be documented
-2. **Create a new ADR** using the [template](./000-ADR-Template.md) if the change warrants architectural discussion
-3. **Set status to Proposed** and open it for team review
-4. Once accepted and implemented, update the status accordingly

docs/catalogs/README.md

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

docs/catalogs/capabilities.md

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

docs/catalogs/scores.md

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

docs/catalogs/topologies.md

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

docs/concepts.md

@@ -1,45 +0,0 @@
-# Core Concepts
-
-Harmony's design is based on a few key concepts. Understanding them is the key to unlocking the framework's power.
-
-### 1. Score
-
-- **What it is:** A **Score** is a declarative description of a desired state. It's a "resource" that defines _what_ you want to achieve, not _how_ to do it.
-- **Example:** `ApplicationScore` declares "I want this web application to be running and monitored."
-
-### 2. Topology
-
-- **What it is:** A **Topology** is the logical representation of your infrastructure and its abilities. It's the "where" your Scores will be applied.
-- **Key Job:** A Topology's most important job is to expose which `Capabilities` it supports.
-- **Example:** `HAClusterTopology` represents a bare-metal cluster and exposes `Capabilities` like `NetworkManager` and `Switch`. `K8sAnywhereTopology` represents a Kubernetes cluster and exposes the `K8sClient` `Capability`.
-
-### 3. Capability
-
-- **What it is:** A **Capability** is a specific feature or API that a `Topology` offers. It's the "how" a `Topology` can fulfill a `Score`'s request.
-- **Example:** The `K8sClient` capability offers a way to interact with a Kubernetes API. The `Switch` capability offers a way to configure a physical network switch.
-
-### 4. Interpret
-
-- **What it is:** An **Interpret** is the execution logic that makes a `Score` a reality. It's the "glue" that connects the _desired state_ (`Score`) to the _environment's abilities_ (`Topology`'s `Capabilities`).
-- **How it works:** When you apply a `Score`, Harmony finds the matching `Interpret` for your `Topology`. This `Interpret` then uses the `Capabilities` provided by the `Topology` to execute the necessary steps.
-
-### 5. Inventory
-
-- **What it is:** An **Inventory** is the physical material (the "what") used in a cluster. This is most relevant for bare-metal or on-premise topologies.
-- **Example:** A list of nodes with their roles (control plane, worker), CPU, RAM, and network interfaces. For the `K8sAnywhereTopology`, the inventory might be empty or autoloaded, as the infrastructure is more abstract.
-
-### 6. Configuration & Secrets
-
-- **What it is:** Configuration represents the runtime data required to deploy your `Scores`. This includes both non-sensitive state (like cluster hostnames, deployment profiles) and sensitive secrets (like API keys, database passwords).
-- **How it works:** See the [Configuration Concept Guide](./concepts/configuration.md) to understand Harmony's unified approach to managing schema in Git and state in OpenBao.
-
----
-
-### How They Work Together (The Compile-Time Check)
-
-1. You **write a `Score`** (e.g., `ApplicationScore`).
-2. Your `Score`'s `Interpret` logic requires certain **`Capabilities`** (e.g., `K8sClient` and `Ingress`).
-3. You choose a **`Topology`** to run it on (e.g., `HAClusterTopology`).
-4. **At compile-time**, Harmony checks: "Does `HAClusterTopology` provide the `K8sClient` and `Ingress` capabilities that `ApplicationScore` needs?"
-   - **If Yes:** Your code compiles. You can be confident it will run.
-   - **If No:** The compiler gives you an error. You've just prevented a "config-is-valid-but-platform-is-wrong" runtime error before you even deployed.

docs/concepts/configuration.md

@@ -1,107 +0,0 @@
-# Configuration and Secrets
-
-Harmony treats configuration and secrets as a single concern. Developers use one crate, `harmony_config`, to declare, store, and retrieve all runtime data — whether it is a public hostname or a database password.
-
-## The mental model: schema in Git, state in the store
-
-### Schema
-
-In Harmony, the Rust code is the configuration schema. You declare what your module needs by defining a struct:
-
-```rust
-#[derive(Config, Serialize, Deserialize, JsonSchema, InteractiveParse)]
-struct PostgresConfig {
-    pub host: String,
-    pub port: u16,
-    #[config(secret)]
-    pub password: String,
-}
-```
-
-This struct is tracked in Git. When a branch adds a new field, Git tracks that the branch requires a new value. When a branch removes a field, the old value in the store becomes irrelevant. The struct is always authoritative.
-
-### State
-
-The actual values live in a config store — by default, OpenBao. No `.env` files, no JSON, no YAML in the repository.
-
-When you run your code, Harmony reads the struct (schema) and resolves values from the store (state):
-
-- If the store has the value, it is injected seamlessly.
-- If the store does not have it, Harmony prompts you in the terminal. Your answer is pushed back to the store automatically.
-- When a teammate runs the same code, they are not prompted — you already provided the value.
-
-### How branch switching works
-
-Because the schema is just Rust code tracked in Git, branch switching works naturally:
-
-1. You check out `feat/redis`. The code now requires `RedisConfig`.
-2. You run `cargo run`. Harmony detects that `RedisConfig` has no value in the store. It prompts you.
-3. You provide the values. Harmony pushes them to OpenBao.
-4. Your teammate checks out `feat/redis` and runs `cargo run`. No prompt — the values are already in the store.
-5. You switch back to `main`. `RedisConfig` does not exist in that branch's code. The store entry is ignored.
-
-## Secrets vs. standard configuration
-
-From your application code, there is no difference. You always call `harmony_config::get_or_prompt::<T>()`.
-
-The difference is in the struct definition:
-
-```rust
-// Standard config — stored in plaintext, displayed during prompting.
-#[derive(Config)]
-struct ClusterConfig {
-    pub api_url: String,
-    pub namespace: String,
-}
-
-// Contains a secret field — the entire struct is stored encrypted,
-// and the password field is masked during terminal prompting.
-#[derive(Config)]
-struct DatabaseConfig {
-    pub host: String,
-    #[config(secret)]
-    pub password: String,
-}
-```
-
-If a struct contains any `#[config(secret)]` field, Harmony elevates the entire struct to `ConfigClass::Secret`. The storage backend decides what that means in practice — in the case of OpenBao, it may route the data to a path with stricter ACLs or audit policies.
-
-## Authentication and team sharing
-
-Harmony uses Zitadel (hosted at `sso.nationtech.io`) for identity and OpenBao (hosted at `secrets.nationtech.io`) for storage.
-
-**First run on a new machine:**
-
-1. Harmony detects that you are not logged in.
-2. It prints a short code and URL to your terminal, and opens your browser if possible.
-3. You log in with your corporate identity (Google, GitHub, or Microsoft Entra ID / Azure AD).
-4. Harmony receives an OIDC token, exchanges it for an OpenBao token, and caches the session locally.
-
-**Subsequent runs:**
-
-- Harmony silently refreshes your tokens in the background. You do not need to log in again for up to 90 days of active use.
-- If you are inactive for 30 days, or if an administrator revokes your access in Zitadel, you will be prompted to re-authenticate.
-
-**Offboarding:**
-
-Revoking a user in Zitadel immediately invalidates their ability to refresh tokens or obtain new ones. No manual secret rotation is required.
-
-## Resolution chain
-
-When Harmony resolves a config value, it tries sources in order:
-
-1. **Environment variable** (`HARMONY_CONFIG_{KEY}`) — highest priority. Use this in CI/CD to override any value without touching the store.
-2. **Config store** (OpenBao for teams, local file for solo/offline use) — the primary source for shared team state.
-3. **Interactive prompt** — last resort. Prompts the developer and persists the answer back to the store.
-
-## Schema versioning
-
-The Rust struct is the single source of truth for what configuration looks like. If a developer renames or removes a field on a branch, the store may still contain data shaped for the old version of the struct. When another developer who does not have that change runs the code, deserialization will fail.
-
-In the current implementation, this is handled gracefully: a deserialization failure is treated as a miss, and Harmony re-prompts. The new answer overwrites the stale entry.
-
-A compile-time migration mechanism is planned for a future release to handle this more rigorously at scale.
-
-## Offline and local development
-
-If you are working offline or evaluating Harmony without a team OpenBao instance, the `StoreSource` falls back to a local file store at `~/.local/share/harmony/config/`. The developer experience is identical — prompting, caching, and resolution all work the same way. The only difference is that the state is local to your machine and not shared with teammates.

docs/guides/adding-capabilities.md

@@ -1,135 +0,0 @@
-# Adding Capabilities
-
-`Capabilities` are trait methods that a `Topology` exposes to Scores. They are the "how" — the specific APIs and features that let a Score translate intent into infrastructure actions.
-
-## How Capabilities Work
-
-When a Score declares it needs certain Capabilities:
-
-```rust
-impl<T: Topology + K8sclient + HelmCommand> Score<T> for MyScore {
-    // ...
-}
-```
-
-The compiler verifies that the target `Topology` implements both `K8sclient` and `HelmCommand`. If it doesn't, compilation fails. This is the compile-time safety check that prevents invalid configurations from reaching production.
-
-## Built-in Capabilities
-
-Harmony provides a set of standard Capabilities:
-
-| Capability | What it provides |
-|------------|------------------|
-| `K8sclient` | A Kubernetes API client |
-| `HelmCommand` | A configured `helm` CLI invocation |
-| `TlsRouter` | TLS certificate management |
-| `NetworkManager` | Host network configuration |
-| `SwitchClient` | Network switch configuration |
-| `CertificateManagement` | Certificate issuance via cert-manager |
-
-## Implementing a Capability
-
-Capabilities are implemented as trait methods on your Topology:
-
-```rust
-use std::sync::Arc;
-use harmony_k8s::K8sClient;
-use harmony::topology::K8sclient;
-
-pub struct MyTopology {
-    kubeconfig: Option<String>,
-}
-
-#[async_trait]
-impl K8sclient for MyTopology {
-    async fn k8s_client(&self) -> Result<Arc<K8sClient>, String> {
-        let client = match &self.kubeconfig {
-            Some(path) => K8sClient::from_kubeconfig(path).await?,
-            None => K8sClient::try_default().await?,
-        };
-        Ok(Arc::new(client))
-    }
-}
-```
-
-## Adding a Custom Capability
-
-For specialized infrastructure needs, add your own Capability as a trait:
-
-```rust
-use async_trait::async_trait;
-use crate::executors::ExecutorError;
-
-/// A capability for configuring network switches
-#[async_trait]
-pub trait SwitchClient: Send + Sync {
-    async fn configure_port(
-        &self,
-        switch: &str,
-        port: &str,
-        vlan: u16,
-    ) -> Result<(), ExecutorError>;
-
-    async fn configure_port_channel(
-        &self,
-        switch: &str,
-        name: &str,
-        ports: &[&str],
-    ) -> Result<(), ExecutorError>;
-}
-```
-
-Then implement it on your Topology:
-
-```rust
-use harmony_infra::brocade::BrocadeClient;
-
-pub struct MyTopology {
-    switch_client: Arc<dyn SwitchClient>,
-}
-
-impl SwitchClient for MyTopology {
-    async fn configure_port(&self, switch: &str, port: &str, vlan: u16) -> Result<(), ExecutorError> {
-        self.switch_client.configure_port(switch, port, vlan).await
-    }
-
-    async fn configure_port_channel(&self, switch: &str, name: &str, ports: &[&str]) -> Result<(), ExecutorError> {
-        self.switch_client.configure_port_channel(switch, name, ports).await
-    }
-}
-```
-
-Now Scores that need `SwitchClient` can run on `MyTopology`.
-
-## Capability Composition
-
-Topologies often compose multiple Capabilities to support complex Scores:
-
-```rust
-pub struct HAClusterTopology {
-    pub kubeconfig: Option<String>,
-    pub router: Arc<dyn Router>,
-    pub load_balancer: Arc<dyn LoadBalancer>,
-    pub switch_client: Arc<dyn SwitchClient>,
-    pub dhcp_server: Arc<dyn DhcpServer>,
-    pub dns_server: Arc<dyn DnsServer>,
-    // ...
-}
-
-impl K8sclient for HAClusterTopology { ... }
-impl HelmCommand for HAClusterTopology { ... }
-impl SwitchClient for HAClusterTopology { ... }
-impl DhcpServer for HAClusterTopology { ... }
-impl DnsServer for HAClusterTopology { ... }
-impl Router for HAClusterTopology { ... }
-impl LoadBalancer for HAClusterTopology { ... }
-```
-
-A Score that needs all of these can run on `HAClusterTopology` because the Topology provides all of them.
-
-## Best Practices
-
-- **Keep Capabilities focused** — one Capability per concern (Kubernetes client, Helm, switch config)
-- **Return meaningful errors** — use specific error types so Scores can handle failures appropriately
-- **Make Capabilities optional where sensible** — not every Topology needs every Capability; use `Option<T>` or a separate trait for optional features
-- **Document preconditions** — if a Capability requires the infrastructure to be in a specific state, document it in the trait doc comments

docs/guides/developer-guide.md

@@ -1,40 +0,0 @@
-# Developer Guide
-
-This section covers how to extend Harmony by building your own `Score`, `Topology`, and `Capability` implementations.
-
-## Writing a Score
-
-A `Score` is a declarative description of desired state. To create your own:
-
-1. Define a struct that represents your desired state
-2. Implement the `Score<T>` trait, where `T` is your target `Topology`
-3. Implement the `Interpret<T>` trait to define how the Score translates to infrastructure actions
-
-See the [Writing a Score](./writing-a-score.md) guide for a step-by-step walkthrough.
-
-## Writing a Topology
-
-A `Topology` models your infrastructure environment. To create your own:
-
-1. Define a struct that holds your infrastructure configuration
-2. Implement the `Topology` trait
-3. Implement the `Capability` traits your Score needs
-
-See the [Writing a Topology](./writing-a-topology.md) guide for details.
-
-## Adding Capabilities
-
-`Capabilities` are the specific APIs or features a `Topology` exposes. They are the bridge between Scores and the actual infrastructure.
-
-See the [Adding Capabilities](./adding-capabilities.md) guide for details on implementing and exposing Capabilities.
-
-## Core Traits Reference
-
-| Trait | Purpose |
-|-------|---------|
-| `Score<T>` | Declares desired state ("what") |
-| `Topology` | Represents infrastructure ("where") |
-| `Interpret<T>` | Execution logic ("how") |
-| `Capability` | A feature exposed by a Topology |
-
-See [Core Concepts](../concepts.md) for the conceptual foundation.

docs/guides/getting-started.md

@@ -1,230 +0,0 @@
-# Getting Started Guide
-
-This guide walks you through deploying your first application with Harmony — a PostgreSQL cluster on a local Kubernetes cluster (K3D). By the end, you'll understand the core workflow: compile a Score, run it through the Harmony CLI, and verify the result.
-
-## What you'll deploy
-
-A fully functional PostgreSQL cluster running in a local K3D cluster, managed by the CloudNativePG operator. This demonstrates the full Harmony pattern:
-
-1. Provision a local Kubernetes cluster (K3D)
-2. Install the required operator (CloudNativePG)
-3. Create a PostgreSQL cluster
-4. Expose it as a Kubernetes Service
-
-## Prerequisites
-
-Before you begin, install the following tools:
-
-- **Rust & Cargo:** [Install Rust](https://rust-lang.org/tools/install) (edition 2024)
-- **Docker:** [Install Docker](https://docs.docker.com/get-docker/) (required for the local K3D cluster)
-- **kubectl:** [Install kubectl](https://kubernetes.io/docs/tasks/tools/install-kubectl/) (optional, for inspecting the cluster)
-
-## Step 1: Clone and build
-
-```bash
-# Clone the repository
-git clone https://git.nationtech.io/nationtech/harmony
-cd harmony
-
-# Build the project (this may take a few minutes on first run)
-cargo build --release
-```
-
-## Step 2: Run the PostgreSQL example
-
-```bash
-cargo run -p example-postgresql
-```
-
-Harmony will output its progress as it:
-
-1. **Creates a K3D cluster** named `harmony-postgres-example` (first run only)
-2. **Installs the CloudNativePG operator** into the cluster
-3. **Creates a PostgreSQL cluster** with 1 instance and 1 GiB of storage
-4. **Prints connection details** for your new database
-
-Expected output (abbreviated):
-
-```
-[+] Cluster created
-[+] Installing CloudNativePG operator
-[+] Creating PostgreSQL cluster
-[+] PostgreSQL cluster is ready
-    Namespace: harmony-postgres-example
-    Service: harmony-postgres-example-rw
-    Username: postgres
-    Password: <stored in secret harmony-postgres-example-db-user>
-```
-
-## Step 3: Verify the deployment
-
-Check that the PostgreSQL pods are running:
-
-```bash
-kubectl get pods -n harmony-postgres-example
-```
-
-You should see something like:
-
-```
-NAME                                    READY   STATUS    RESTARTS   AGE
-harmony-postgres-example-1              1/1     Running   0          2m
-```
-
-Get the database password:
-
-```bash
-kubectl get secret -n harmony-postgres-example harmony-postgres-example-db-user -o jsonpath='{.data.password}' | base64 -d
-```
-
-## Step 4: Connect to the database
-
-Forward the PostgreSQL port to your local machine:
-
-```bash
-kubectl port-forward -n harmony-postgres-example svc/harmony-postgres-example-rw 5432:5432
-```
-
-In another terminal, connect with `psql`:
-
-```bash
-psql -h localhost -p 5432 -U postgres
-# Enter the password from Step 4 when prompted
-```
-
-Try a simple query:
-
-```sql
-SELECT version();
-```
-
-## Step 5: Clean up
-
-To delete the PostgreSQL cluster and the local K3D cluster:
-
-```bash
-k3d cluster delete harmony-postgres-example
-```
-
-Alternatively, just delete the PostgreSQL cluster without removing K3D:
-
-```bash
-kubectl delete namespace harmony-postgres-example
-```
-
-## How it works
-
-The example code (`examples/postgresql/src/main.rs`) is straightforward:
-
-```rust
-use harmony::{
-    inventory::Inventory,
-    modules::postgresql::{PostgreSQLScore, capability::PostgreSQLConfig},
-    topology::K8sAnywhereTopology,
-};
-
-#[tokio::main]
-async fn main() {
-    let postgres = PostgreSQLScore {
-        config: PostgreSQLConfig {
-            cluster_name: "harmony-postgres-example".to_string(),
-            namespace: "harmony-postgres-example".to_string(),
-            ..Default::default()
-        },
-    };
-
-    harmony_cli::run(
-        Inventory::autoload(),
-        K8sAnywhereTopology::from_env(),
-        vec![Box::new(postgres)],
-        None,
-    )
-    .await
-    .unwrap();
-}
-```
-
-- **`Inventory::autoload()`** discovers the local environment (or uses an existing inventory)
-- **`K8sAnywhereTopology::from_env()`** connects to K3D if `HARMONY_AUTOINSTALL=true` (the default), or to any Kubernetes cluster via `KUBECONFIG`
-- **`harmony_cli::run(...)`** executes the Score against the Topology, managing the full lifecycle
-
-## Connecting to an existing cluster
-
-By default, Harmony provisions a local K3D cluster. To use an existing Kubernetes cluster instead:
-
-```bash
-export KUBECONFIG=/path/to/your/kubeconfig
-export HARMONY_USE_LOCAL_K3D=false
-export HARMONY_AUTOINSTALL=false
-
-cargo run -p example-postgresql
-```
-
-## Troubleshooting
-
-### Docker is not running
-
-```
-Error: could not create cluster: docker is not running
-```
-
-Start Docker and try again.
-
-### K3D cluster creation fails
-
-```
-Error: failed to create k3d cluster
-```
-
-Ensure you have at least 2 CPU cores and 4 GiB of RAM available for Docker.
-
-### `kubectl` cannot connect to the cluster
-
-```
-error: unable to connect to a kubernetes cluster
-```
-
-After Harmony creates the cluster, it writes the kubeconfig to `~/.kube/config` or to the path in `KUBECONFIG`. Verify:
-
-```bash
-kubectl cluster-info --context k3d-harmony-postgres-example
-```
-
-### Port forward fails
-
-```
-error: unable to forward port
-```
-
-Make sure no other process is using port 5432, or use a different local port:
-
-```bash
-kubectl port-forward -n harmony-postgres-example svc/harmony-postgres-example-rw 15432:5432
-psql -h localhost -p 15432 -U postgres
-```
-
-## Next steps
-
-- [Explore the Scores Catalog](../catalogs/scores.md): See what other Scores are available
-- [Explore the Topologies Catalog](../catalogs/topologies.md): See what infrastructure Topologies are supported
-- [Read the Core Concepts](../concepts.md): Understand the Score / Topology / Interpret pattern in depth
-- [OKD on Bare Metal](../use-cases/okd-on-bare-metal.md): See a complete bare-metal deployment example
-
-## Advanced examples
-
-Once you're comfortable with the basics, these examples demonstrate more advanced use cases. Note that some require specific infrastructure (existing Kubernetes clusters, bare-metal hardware, or multi-cluster environments):
-
-| Example | Description | Prerequisites |
-|---------|-------------|---------------|
-| `monitoring` | Deploy Prometheus alerting with Discord webhooks | Existing K8s cluster |
-| `ntfy` | Deploy ntfy notification server | Existing K8s cluster |
-| `tenant` | Create a multi-tenant namespace with quotas | Existing K8s cluster |
-| `cert_manager` | Provision TLS certificates | Existing K8s cluster |
-| `validate_ceph_cluster_health` | Check Ceph cluster health | Existing Rook/Ceph cluster |
-| `okd_pxe` / `okd_installation` | Provision OKD on bare metal | HAClusterTopology, bare-metal hardware |
-
-To run any example:
-
-```bash
-cargo run -p example-<example_name>
-```

docs/guides/writing-a-score.md

@@ -1,164 +0,0 @@
-# Writing a Score
-
-A `Score` declares _what_ you want to achieve. It is decoupled from _how_ it is achieved — that logic lives in an `Interpret`.
-
-## The Pattern
-
-A Score consists of two parts:
-
-1. **A struct** — holds the configuration for your desired state
-2. **A `Score<T>` implementation** — returns an `Interpret` that knows how to execute
-
-An `Interpret` contains the actual execution logic and connects your Score to the capabilities exposed by a `Topology`.
-
-## Example: A Simple Score
-
-Here's a simplified version of `NtfyScore` from the `ntfy` module:
-
-```rust
-use async_trait::async_trait;
-use harmony::{
-    interpret::{Interpret, InterpretError, Outcome},
-    inventory::Inventory,
-    score::Score,
-    topology::{HelmCommand, K8sclient, Topology},
-};
-
-/// MyScore declares "I want to install the ntfy server"
-#[derive(Debug, Clone)]
-pub struct MyScore {
-    pub namespace: String,
-    pub host: String,
-}
-
-impl<T: Topology + HelmCommand + K8sclient> Score<T> for MyScore {
-    fn create_interpret(&self) -> Box<dyn Interpret<T>> {
-        Box::new(MyInterpret { score: self.clone() })
-    }
-
-    fn name(&self) -> String {
-        "ntfy [MyScore]".into()
-    }
-}
-
-/// MyInterpret knows _how_ to install ntfy using the Topology's capabilities
-#[derive(Debug)]
-pub struct MyInterpret {
-    pub score: MyScore,
-}
-
-#[async_trait]
-impl<T: Topology + HelmCommand + K8sclient> Interpret<T> for MyInterpret {
-    async fn execute(
-        &self,
-        inventory: &Inventory,
-        topology: &T,
-    ) -> Result<Outcome, InterpretError> {
-        // 1. Get a Kubernetes client from the Topology
-        let client = topology.k8s_client().await?;
-
-        // 2. Use Helm to install the ntfy chart
-        // (via topology's HelmCommand capability)
-
-        // 3. Wait for the deployment to be ready
-        client
-            .wait_until_deployment_ready("ntfy", Some(&self.score.namespace), None)
-            .await?;
-
-        Ok(Outcome::success("ntfy installed".to_string()))
-    }
-}
-```
-
-## The Compile-Time Safety Check
-
-The generic `Score<T>` trait is bounded by `T: Topology`. This means the compiler enforces that your Score only runs on Topologies that expose the capabilities your Interpret needs:
-
-```rust
-// This only compiles if K8sAnywhereTopology (or any T)
-// implements HelmCommand and K8sclient
-impl<T: Topology + HelmCommand + K8sclient> Score<T> for MyScore { ... }
-```
-
-If you try to run this Score against a Topology that doesn't expose `HelmCommand`, you get a compile error — before any code runs.
-
-## Using Your Score
-
-Once defined, your Score integrates with the Harmony CLI:
-
-```rust
-use harmony::{
-    inventory::Inventory,
-    topology::K8sAnywhereTopology,
-};
-
-#[tokio::main]
-async fn main() {
-    let my_score = MyScore {
-        namespace: "monitoring".to_string(),
-        host: "ntfy.example.com".to_string(),
-    };
-
-    harmony_cli::run(
-        Inventory::autoload(),
-        K8sAnywhereTopology::from_env(),
-        vec![Box::new(my_score)],
-        None,
-    )
-    .await
-    .unwrap();
-}
-```
-
-## Key Patterns
-
-### Composing Scores
-
-Scores can include other Scores via features:
-
-```rust
-let app = ApplicationScore {
-    features: vec![
-        Box::new(PackagingDeployment { application: app.clone() }),
-        Box::new(Monitoring { application: app.clone(), alert_receiver: vec![] }),
-    ],
-    application: app,
-};
-```
-
-### Reusing Interpret Logic
-
-Many Scores delegate to shared `Interpret` implementations. For example, `HelmChartScore` provides a reusable Interpret for any Helm-based deployment. Your Score can wrap it:
-
-```rust
-impl<T: Topology + HelmCommand> Score<T> for MyScore {
-    fn create_interpret(&self) -> Box<dyn Interpret<T>> {
-        Box::new(HelmChartInterpret { /* your config */ })
-    }
-}
-```
-
-### Accessing Topology Capabilities
-
-Your Interpret accesses infrastructure through Capabilities exposed by the Topology:
-
-```rust
-// Via the Topology trait directly
-let k8s_client = topology.k8s_client().await?;
-let helm = topology.get_helm_command();
-
-// Or via Capability traits
-impl<T: Topology + K8sclient> Interpret<T> for MyInterpret {
-    async fn execute(...) {
-        let client = topology.k8s_client().await?;
-        // use client...
-    }
-}
-```
-
-## Best Practices
-
-- **Keep Scores focused** — one Score per concern (deployment, monitoring, networking)
-- **Use `..Default::default()`** for optional fields so callers only need to specify what they care about
-- **Return `Outcome`** — use `Outcome::success`, `Outcome::failure`, or `Outcome::success_with_details` to communicate results clearly
-- **Handle errors gracefully** — return meaningful `InterpretError` messages that help operators debug issues

docs/guides/writing-a-topology.md

@@ -1,176 +0,0 @@
-# Writing a Topology
-
-A `Topology` models your infrastructure environment and exposes `Capability` traits that Scores use to interact with it. Where a Score declares _what_ you want, a Topology exposes _what_ it can do.
-
-## The Minimum Implementation
-
-At minimum, a Topology needs:
-
-```rust
-use async_trait::async_trait;
-use harmony::{
-    topology::{PreparationError, PreparationOutcome, Topology},
-};
-
-#[derive(Debug, Clone)]
-pub struct MyTopology {
-    pub name: String,
-}
-
-#[async_trait]
-impl Topology for MyTopology {
-    fn name(&self) -> &str {
-        "MyTopology"
-    }
-
-    async fn ensure_ready(&self) -> Result<PreparationOutcome, PreparationError> {
-        // Verify the infrastructure is accessible and ready
-        Ok(PreparationOutcome::Success { details: "ready".to_string() })
-    }
-}
-```
-
-## Implementing Capabilities
-
-Scores express dependencies on Capabilities through trait bounds. For example, if your Topology should support Scores that deploy Helm charts, implement `HelmCommand`:
-
-```rust
-use std::process::Command;
-use harmony::topology::HelmCommand;
-
-impl HelmCommand for MyTopology {
-    fn get_helm_command(&self) -> Command {
-        let mut cmd = Command::new("helm");
-        if let Some(kubeconfig) = &self.kubeconfig {
-            cmd.arg("--kubeconfig").arg(kubeconfig);
-        }
-        cmd
-    }
-}
-```
-
-For Scores that need a Kubernetes client, implement `K8sclient`:
-
-```rust
-use std::sync::Arc;
-use harmony_k8s::K8sClient;
-use harmony::topology::K8sclient;
-
-#[async_trait]
-impl K8sclient for MyTopology {
-    async fn k8s_client(&self) -> Result<Arc<K8sClient>, String> {
-        let client = if let Some(kubeconfig) = &self.kubeconfig {
-            K8sClient::from_kubeconfig(kubeconfig).await?
-        } else {
-            K8sClient::try_default().await?
-        };
-        Ok(Arc::new(client))
-    }
-}
-```
-
-## Loading Topology from Environment
-
-For flexibility, implement `from_env()` to read configuration from environment variables:
-
-```rust
-impl MyTopology {
-    pub fn from_env() -> Self {
-        Self {
-            name: std::env::var("MY_TOPOLOGY_NAME")
-                .unwrap_or_else(|_| "default".to_string()),
-            kubeconfig: std::env::var("KUBECONFIG").ok(),
-        }
-    }
-}
-```
-
-This pattern lets operators switch between environments without recompiling:
-
-```bash
-export KUBECONFIG=/path/to/prod-cluster.kubeconfig
-cargo run --example my_example
-```
-
-## Complete Example: K8sAnywhereTopology
-
-The `K8sAnywhereTopology` is the most commonly used Topology and handles both local (K3D) and remote Kubernetes clusters:
-
-```rust
-pub struct K8sAnywhereTopology {
-    pub k8s_state: Arc<OnceCell<K8sState>>,
-    pub tenant_manager: Arc<OnceCell<TenantManager>>,
-    pub config: Arc<K8sAnywhereConfig>,
-}
-
-#[async_trait]
-impl Topology for K8sAnywhereTopology {
-    fn name(&self) -> &str {
-        "K8sAnywhereTopology"
-    }
-
-    async fn ensure_ready(&self) -> Result<PreparationOutcome, PreparationError> {
-        // 1. If autoinstall is enabled and no cluster exists, provision K3D
-        // 2. Verify kubectl connectivity
-        // 3. Optionally wait for cluster operators to be ready
-        Ok(PreparationOutcome::Success { details: "cluster ready".to_string() })
-    }
-}
-```
-
-## Key Patterns
-
-### Lazy Initialization
-
-Use `OnceCell` for expensive resources like Kubernetes clients:
-
-```rust
-pub struct K8sAnywhereTopology {
-    k8s_state: Arc<OnceCell<K8sState>>,
-}
-```
-
-### Multi-Target Topologies
-
-For Scores that span multiple clusters (like NATS supercluster), implement `MultiTargetTopology`:
-
-```rust
-pub trait MultiTargetTopology: Topology {
-    fn current_target(&self) -> &str;
-    fn set_target(&mut self, target: &str);
-}
-```
-
-### Composing Topologies
-
-Complex topologies combine multiple infrastructure components:
-
-```rust
-pub struct HAClusterTopology {
-    pub router: Arc<dyn Router>,
-    pub load_balancer: Arc<dyn LoadBalancer>,
-    pub firewall: Arc<dyn Firewall>,
-    pub dhcp_server: Arc<dyn DhcpServer>,
-    pub dns_server: Arc<dyn DnsServer>,
-    pub kubeconfig: Option<String>,
-    // ...
-}
-```
-
-## Testing Your Topology
-
-Test Topologies in isolation by implementing them against mock infrastructure:
-
-```rust
-#[cfg(test)]
-mod tests {
-    use super::*;
-
-    #[tokio::test]
-    async fn test_topology_ensure_ready() {
-        let topo = MyTopology::from_env();
-        let result = topo.ensure_ready().await;
-        assert!(result.is_ok());
-    }
-}
-```

docs/use-cases/README.md

@@ -1,17 +0,0 @@
-# Use Cases
-
-Real-world scenarios demonstrating Harmony in action.
-
-## Available Use Cases
-
-### [PostgreSQL on Local K3D](./postgresql-on-local-k3d.md)
-
-Deploy a fully functional PostgreSQL cluster on a local K3D cluster in under 10 minutes. The quickest way to see Harmony in action.
-
-### [OKD on Bare Metal](./okd-on-bare-metal.md)
-
-A complete walkthrough of bootstrapping a high-availability OKD cluster from physical hardware. Covers inventory discovery, bootstrap, control plane, and worker provisioning.
-
----
-
-_These use cases are community-tested scenarios. For questions or contributions, open an issue on the [Harmony repository](https://git.nationtech.io/NationTech/harmony/issues)._

docs/use-cases/okd-on-bare-metal.md

@@ -1,159 +0,0 @@
-# Use Case: OKD on Bare Metal
-
-Provision a production-grade OKD (OpenShift Kubernetes Distribution) cluster from physical hardware using Harmony. This use case covers the full lifecycle: hardware discovery, bootstrap, control plane, workers, and post-install validation.
-
-## What you'll have at the end
-
-A highly-available OKD cluster with:
-- 3 control plane nodes
-- 2+ worker nodes
-- Network bonding configured on nodes and switches
-- Load balancer routing API and ingress traffic
-- DNS and DHCP services for the cluster
-- Post-install health validation
-
-## Target hardware model
-
-This setup assumes a typical lab environment:
-
-```
-┌─────────────────────────────────────────────────────────┐
-│  Network 192.168.x.0/24 (flat, DHCP + PXE capable)     │
-│                                                         │
-│  ┌──────────┐  ┌──────────┐  ┌──────────┐            │
-│  │  cp0     │  │  cp1     │  │  cp2     │  (control) │
-│  └──────────┘  └──────────┘  └──────────┘            │
-│  ┌──────────┐  ┌──────────┐                            │
-│  │  wk0     │  │  wk1     │  ...        (workers)    │
-│  └──────────┘  └──────────┘                            │
-│  ┌──────────┐                                          │
-│  │ bootstrap│  (temporary, can be repurposed)          │
-│  └──────────┘                                          │
-│                                                         │
-│  ┌──────────┐  ┌──────────┐                            │
-│  │ firewall │  │  switch  │  (OPNsense + Brocade)     │
-│  └──────────┘  └──────────┘                            │
-└─────────────────────────────────────────────────────────┘
-```
-
-## Required infrastructure
-
-Harmony models this as an `HAClusterTopology`, which requires these capabilities:
-
-| Capability | Implementation |
-|------------|---------------|
-| **Router** | OPNsense firewall |
-| **Load Balancer** | OPNsense HAProxy |
-| **Firewall** | OPNsense |
-| **DHCP Server** | OPNsense |
-| **TFTP Server** | OPNsense |
-| **HTTP Server** | OPNsense |
-| **DNS Server** | OPNsense |
-| **Node Exporter** | Prometheus node_exporter on OPNsense |
-| **Switch Client** | Brocade SNMP |
-
-See `examples/okd_installation/` for a reference topology implementation.
-
-## The Provisioning Pipeline
-
-Harmony orchestrates OKD installation in ordered stages:
-
-### Stage 1: Inventory Discovery (`OKDSetup01InventoryScore`)
-
-Harmony boots all nodes via PXE into a CentOS Stream live environment, runs an inventory agent on each, and collects:
-- MAC addresses and NIC details
-- IP addresses assigned by DHCP
-- Hardware profile (CPU, RAM, storage)
-
-This is the "discovery-first" approach: no pre-configuration required on nodes.
-
-### Stage 2: Bootstrap Node (`OKDSetup02BootstrapScore`)
-
-The user selects one discovered node to serve as the bootstrap node. Harmony:
-- Renders per-MAC iPXE boot configuration with OKD 4.19 SCOS live assets + ignition
-- Reboots the bootstrap node via SSH
-- Waits for the bootstrap process to complete (API server becomes available)
-
-### Stage 3: Control Plane (`OKDSetup03ControlPlaneScore`)
-
-With bootstrap complete, Harmony provisions the control plane nodes:
-- Renders per-MAC iPXE for each control plane node
-- Reboots via SSH and waits for node to join the cluster
-- Applies network bond configuration via NMState MachineConfig where relevant
-
-### Stage 4: Network Bonding (`OKDSetupPersistNetworkBondScore`)
-
-Configures LACP bonds on nodes and corresponding port-channels on the switch stack for high-availability.
-
-### Stage 5: Worker Nodes (`OKDSetup04WorkersScore`)
-
-Provisions worker nodes similarly to control plane, joining them to the cluster.
-
-### Stage 6: Sanity Check (`OKDSetup05SanityCheckScore`)
-
-Validates:
-- API server is reachable
-- Ingress controller is operational
-- Cluster operators are healthy
-- SDN (software-defined networking) is functional
-
-### Stage 7: Installation Report (`OKDSetup06InstallationReportScore`)
-
-Produces a machine-readable JSON report and human-readable summary of the installation.
-
-## Network notes
-
-**During discovery:** Ports must be in access mode (no LACP). DHCP succeeds; iPXE loads CentOS Stream live with Kickstart and starts the inventory endpoint.
-
-**During provisioning:** After SCOS is on disk and Ignition/MachineConfig can be applied, bonds are set persistently. This avoids the PXE/DHCP recovery race condition that occurs if bonding is configured too early.
-
-**PXE limitation:** The generic discovery path cannot use bonded networks for PXE boot because the DHCP recovery process conflicts with bond formation.
-
-## Configuration knobs
-
-When using `OKDInstallationPipeline`, configure these domains:
-
-| Parameter | Example | Description |
-|-----------|---------|-------------|
-| `public_domain` | `apps.example.com` | Wildcard domain for application ingress |
-| `internal_domain` | `cluster.local` | Internal cluster DNS domain |
-
-## Running the example
-
-See `examples/okd_installation/` for a complete reference. The topology must be configured with your infrastructure details:
-
-```bash
-# Configure the example with your hardware/network specifics
-# See examples/okd_installation/src/topology.rs
-
-cargo run -p example-okd_installation
-```
-
-This example requires:
-- Physical hardware configured as described above
-- OPNsense firewall with SSH access
-- Brocade switch with SNMP access
-- All nodes connected to the same Layer 2 network
-
-## Post-install
-
-After the cluster is bootstrapped, `~/.kube/config` is updated with the cluster credentials. Verify:
-
-```bash
-kubectl get nodes
-kubectl get pods -n openshift-monitoring
-oc get routes -n openshift-console
-```
-
-## Next steps
-
-- Enable monitoring with `PrometheusAlertScore` or `OpenshiftClusterAlertScore`
-- Configure TLS certificates with `CertManagerHelmScore`
-- Add storage with Rook Ceph
-- Scale workers with `OKDSetup04WorkersScore`
-
-## Further reading
-
-- [OKD Installation Module](../../harmony/src/modules/okd/installation.rs) — source of truth for pipeline stages
-- [HAClusterTopology](../../harmony/src/domain/topology/ha_cluster.rs) — infrastructure capability model
-- [Scores Catalog](../catalogs/scores.md) — all available Scores including OKD-specific ones

docs/use-cases/postgresql-on-local-k3d.md

@@ -1,115 +0,0 @@
-# Use Case: PostgreSQL on Local K3D
-
-Deploy a production-grade PostgreSQL cluster on a local Kubernetes cluster (K3D) using Harmony. This is the fastest way to get started with Harmony and requires no external infrastructure.
-
-## What you'll have at the end
-
-A fully operational PostgreSQL cluster with:
-- 1 primary instance with 1 GiB of storage
-- CloudNativePG operator managing the cluster lifecycle
-- Automatic failover support (foundation for high-availability)
-- Exposed as a Kubernetes Service for easy connection
-
-## Prerequisites
-
-- Rust 2024 edition
-- Docker running locally
-- ~5 minutes
-
-## The Score
-
-The entire deployment is expressed in ~20 lines of Rust:
-
-```rust
-use harmony::{
-    inventory::Inventory,
-    modules::postgresql::{PostgreSQLScore, capability::PostgreSQLConfig},
-    topology::K8sAnywhereTopology,
-};
-
-#[tokio::main]
-async fn main() {
-    let postgres = PostgreSQLScore {
-        config: PostgreSQLConfig {
-            cluster_name: "harmony-postgres-example".to_string(),
-            namespace: "harmony-postgres-example".to_string(),
-            ..Default::default()
-        },
-    };
-
-    harmony_cli::run(
-        Inventory::autoload(),
-        K8sAnywhereTopology::from_env(),
-        vec![Box::new(postgres)],
-        None,
-    )
-    .await
-    .unwrap();
-}
-```
-
-## What Harmony does
-
-When you run this, Harmony:
-
-1. **Connects to K8sAnywhereTopology** — this auto-provisions a K3D cluster if none exists
-2. **Installs the CloudNativePG operator** — one-time setup that enables PostgreSQL cluster management in Kubernetes
-3. **Creates a PostgreSQL cluster** — Harmony translates the Score into a `Cluster` CRD and applies it
-4. **Exposes the database** — creates a Kubernetes Service for the PostgreSQL primary
-
-## Running it
-
-```bash
-cargo run -p example-postgresql
-```
-
-## Verifying the deployment
-
-```bash
-# Check pods
-kubectl get pods -n harmony-postgres-example
-
-# Get the password
-PASSWORD=$(kubectl get secret -n harmony-postgres-example \
-  harmony-postgres-example-db-user \
-  -o jsonpath='{.data.password}' | base64 -d)
-
-# Connect via port-forward
-kubectl port-forward -n harmony-postgres-example svc/harmony-postgres-example-rw 5432:5432
-psql -h localhost -p 5432 -U postgres -W "$PASSWORD"
-```
-
-## Customizing the deployment
-
-The `PostgreSQLConfig` struct supports:
-
-| Field | Default | Description |
-|-------|---------|-------------|
-| `cluster_name` | — | Name of the PostgreSQL cluster |
-| `namespace` | — | Kubernetes namespace to deploy to |
-| `instances` | `1` | Number of instances |
-| `storage_size` | `1Gi` | Persistent storage size per instance |
-
-Example with custom settings:
-
-```rust
-let postgres = PostgreSQLScore {
-    config: PostgreSQLConfig {
-        cluster_name: "my-prod-db".to_string(),
-        namespace: "database".to_string(),
-        instances: 3,
-        storage_size: "10Gi".to_string().into(),
-        ..Default::default()
-    },
-};
-```
-
-## Extending the pattern
-
-This pattern extends to any Kubernetes-native workload:
-
-- Add **monitoring** by including a `Monitoring` feature alongside your Score
-- Add **TLS certificates** by including a `CertificateScore`
-- Add **tenant isolation** by wrapping in a `TenantScore`
-
-See [Scores Catalog](../catalogs/scores.md) for the full list.

examples/README.md

@@ -1,127 +0,0 @@
-# Examples
-
-This directory contains runnable examples demonstrating Harmony's capabilities. Each example is a self-contained program that can be run with `cargo run -p example-<name>`.
-
-## Quick Reference
-
-| Example | Description | Local K3D | Existing Cluster | Hardware Needed |
-|---------|-------------|:---------:|:----------------:|:---------------:|
-| `postgresql` | Deploy a PostgreSQL cluster | ✅ | ✅ | — |
-| `ntfy` | Deploy ntfy notification server | ✅ | ✅ | — |
-| `tenant` | Create a multi-tenant namespace | ✅ | ✅ | — |
-| `cert_manager` | Provision TLS certificates | ✅ | ✅ | — |
-| `node_health` | Check Kubernetes node health | ✅ | ✅ | — |
-| `monitoring` | Deploy Prometheus alerting | ✅ | ✅ | — |
-| `monitoring_with_tenant` | Monitoring + tenant isolation | ✅ | ✅ | — |
-| `operatorhub_catalog` | Install OperatorHub catalog | ✅ | ✅ | — |
-| `validate_ceph_cluster_health` | Verify Ceph cluster health | — | ✅ | Rook/Ceph |
-| `remove_rook_osd` | Remove a Rook OSD | — | ✅ | Rook/Ceph |
-| `brocade_snmp_server` | Configure Brocade switch SNMP | — | ✅ | Brocade switch |
-| `opnsense_node_exporter` | Node exporter on OPNsense | — | ✅ | OPNsense firewall |
-| `okd_pxe` | PXE boot configuration for OKD | — | — | ✅ |
-| `okd_installation` | Full OKD bare-metal install | — | — | ✅ |
-| `okd_cluster_alerts` | OKD cluster monitoring alerts | — | ✅ | OKD cluster |
-| `multisite_postgres` | Multi-site PostgreSQL failover | — | ✅ | Multi-cluster |
-| `nats` | Deploy NATS messaging | — | ✅ | Multi-cluster |
-| `nats-supercluster` | NATS supercluster across sites | — | ✅ | Multi-cluster |
-| `lamp` | LAMP stack deployment | ✅ | ✅ | — |
-| `openbao` | Deploy OpenBao vault | ✅ | ✅ | — |
-| `zitadel` | Deploy Zitadel identity provider | ✅ | ✅ | — |
-| `try_rust_webapp` | Rust webapp with packaging | ✅ | ✅ | Submodule |
-| `rust` | Rust webapp with full monitoring | ✅ | ✅ | — |
-| `rhob_application_monitoring` | RHOB monitoring setup | ✅ | ✅ | — |
-| `sttest` | Full OKD stack test | — | — | ✅ |
-| `application_monitoring_with_tenant` | App monitoring + tenant | — | ✅ | OKD cluster |
-| `kube-rs` | Direct kube-rs client usage | ✅ | ✅ | — |
-| `k8s_drain_node` | Drain a Kubernetes node | ✅ | ✅ | — |
-| `k8s_write_file_on_node` | Write files to K8s nodes | ✅ | ✅ | — |
-| `harmony_inventory_builder` | Discover hosts via subnet scan | ✅ | — | — |
-| `cli` | CLI tool with inventory discovery | ✅ | — | — |
-| `tui` | Terminal UI demonstration | ✅ | — | — |
-
-## Status Legend
-
-| Symbol | Meaning |
-|--------|---------|
-| ✅ | Works out-of-the-box |
-| — | Not applicable or requires specific setup |
-
-## By Category
-
-### Data Services
-- **`postgresql`** — Deploy a PostgreSQL cluster via CloudNativePG
-- **`multisite_postgres`** — Multi-site PostgreSQL with failover
-- **`public_postgres`** — Public-facing PostgreSQL (⚠️ uses NationTech DNS)
-
-### Kubernetes Utilities
-- **`node_health`** — Check node health in a cluster
-- **`k8s_drain_node`** — Drain and reboot a node
-- **`k8s_write_file_on_node`** — Write files to nodes
-- **`validate_ceph_cluster_health`** — Verify Ceph/Rook cluster health
-- **`remove_rook_osd`** — Remove an OSD from Rook/Ceph
-- **`kube-rs`** — Direct Kubernetes client usage demo
-
-### Monitoring & Alerting
-- **`monitoring`** — Deploy Prometheus alerting with Discord webhooks
-- **`monitoring_with_tenant`** — Monitoring with tenant isolation
-- **`ntfy`** — Deploy ntfy notification server
-- **`okd_cluster_alerts`** — OKD-specific cluster alerts
-
-### Application Deployment
-- **`try_rust_webapp`** — Deploy a Rust webapp with packaging (⚠️ requires `tryrust.org` submodule)
-- **`rust`** — Rust webapp with full monitoring features
-- **`rhob_application_monitoring`** — Red Hat Observability Stack monitoring
-- **`lamp`** — LAMP stack deployment (⚠️ uses NationTech DNS)
-- **`application_monitoring_with_tenant`** — App monitoring with tenant isolation
-
-### Infrastructure & Bare Metal
-- **`okd_installation`** — Full OKD cluster from scratch
-- **`okd_pxe`** — PXE boot configuration for OKD
-- **`sttest`** — Full OKD stack test with specific hardware
-- **`brocade_snmp_server`** — Configure Brocade switch via SNMP
-- **`opnsense_node_exporter`** — Node exporter on OPNsense firewall
-
-### Multi-Cluster
-- **`nats`** — NATS deployment on a cluster
-- **`nats-supercluster`** — NATS supercluster across multiple sites
-- **`multisite_postgres`** — PostgreSQL with multi-site failover
-
-### Identity & Secrets
-- **`openbao`** — Deploy OpenBao vault (⚠️ uses NationTech DNS)
-- **`zitadel`** — Deploy Zitadel identity provider (⚠️ uses NationTech DNS)
-
-### Cluster Services
-- **`cert_manager`** — Provision TLS certificates
-- **`tenant`** — Create a multi-tenant namespace
-- **`operatorhub_catalog`** — Install OperatorHub catalog sources
-
-### Development & Testing
-- **`cli`** — CLI tool with inventory discovery
-- **`tui`** — Terminal UI demonstration
-- **`harmony_inventory_builder`** — Host discovery via subnet scan
-
-## Running Examples
-
-```bash
-# Build first
-cargo build --release
-
-# Run any example
-cargo run -p example-postgresql
-cargo run -p example-ntfy
-cargo run -p example-tenant
-```
-
-For examples that need an existing Kubernetes cluster:
-
-```bash
-export KUBECONFIG=/path/to/your/kubeconfig
-export HARMONY_USE_LOCAL_K3D=false
-export HARMONY_AUTOINSTALL=false
-
-cargo run -p example-monitoring
-```
-
-## Notes on Private Infrastructure
-
-Some examples use NationTech-hosted infrastructure by default (DNS domains like `*.nationtech.io`, `*.harmony.mcd`). These are not suitable for public use without modification. See the [Getting Started Guide](../docs/guides/getting-started.md) for the recommended public examples.

examples/brocade_switch/src/main.rs

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

examples/cert_manager/Cargo.toml

@@ -1,19 +0,0 @@
-[package]
-name = "cert_manager"
-edition = "2024"
-version.workspace = true
-readme.workspace = true
-license.workspace = true
-publish = false
-
-[dependencies]
-harmony = { path = "../../harmony" }
-harmony_cli = { path = "../../harmony_cli" }
-harmony_types = { path = "../../harmony_types" }
-cidr = { workspace = true }
-tokio = { workspace = true }
-harmony_macros = { path = "../../harmony_macros" }
-log = { workspace = true }
-env_logger = { workspace = true }
-url = { workspace = true }
-assert_cmd = "2.0.16"

examples/cert_manager/src/main.rs

@@ -1,42 +0,0 @@
-use harmony::{
-    inventory::Inventory,
-    modules::cert_manager::{
-        capability::CertificateManagementConfig, score_certificate::CertificateScore,
-        score_issuer::CertificateIssuerScore,
-    },
-    topology::K8sAnywhereTopology,
-};
-
-#[tokio::main]
-async fn main() {
-    let config = CertificateManagementConfig {
-        namespace: Some("test".to_string()),
-        acme_issuer: None,
-        ca_issuer: None,
-        self_signed: true,
-    };
-
-    let issuer_name = "test-self-signed-issuer".to_string();
-    let issuer = CertificateIssuerScore {
-        issuer_name: issuer_name.clone(),
-        config: config.clone(),
-    };
-
-    let cert = CertificateScore {
-        config: config.clone(),
-        issuer_name,
-        cert_name: "test-self-signed-cert".to_string(),
-        common_name: None,
-        dns_names: Some(vec!["test.dns.name".to_string()]),
-        is_ca: Some(false),
-    };
-
-    harmony_cli::run(
-        Inventory::autoload(),
-        K8sAnywhereTopology::from_env(),
-        vec![Box::new(issuer), Box::new(cert)],
-        None,
-    )
-    .await
-    .unwrap();
-}

examples/ha_cluster/Cargo.toml

@@ -1,5 +1,5 @@
 [package]
-name = "sttest"
+name = "example-ha-cluster"
 edition = "2024"
 version.workspace = true
 readme.workspace = true
@@ -8,16 +8,14 @@ publish = false
 
 [dependencies]
 harmony = { path = "../../harmony" }
-harmony_cli = { path = "../../harmony_cli" }
+harmony_tui = { path = "../../harmony_tui" }
 harmony_types = { path = "../../harmony_types" }
 cidr = { workspace = true }
 tokio = { workspace = true }
 harmony_macros = { path = "../../harmony_macros" }
-harmony_secret = { path = "../../harmony_secret" }
-harmony_secret_derive = { path = "../../harmony_secret_derive" }
 log = { workspace = true }
 env_logger = { workspace = true }
 url = { workspace = true }
-serde = { workspace = true }
+harmony_secret = { path = "../../harmony_secret" }
 brocade = { path = "../../brocade" }
-schemars = "0.8"
+serde = { workspace = true }

examples/ha_cluster/README.md

@@ -0,0 +1,15 @@
+## OPNSense demo
+
+Download the virtualbox snapshot from {{TODO URL}}
+
+Start the virtualbox image
+
+This virtualbox image is configured to use a bridge on the host's physical interface, make sure the bridge is up and the virtual machine can reach internet.
+
+Credentials are opnsense default (root/opnsense)
+
+Run the project with the correct ip address on the command line :
+
+```bash
+cargo run -p example-opnsense -- 192.168.5.229
+```

examples/ha_cluster/src/main.rs

@@ -0,0 +1,143 @@
+use std::{
+    net::{IpAddr, Ipv4Addr},
+    sync::{Arc, OnceLock},
+};
+
+use brocade::BrocadeOptions;
+use cidr::Ipv4Cidr;
+use harmony::{
+    hardware::{HostCategory, Location, PhysicalHost, SwitchGroup},
+    infra::{brocade::BrocadeSwitchClient, opnsense::OPNSenseManagementInterface},
+    inventory::Inventory,
+    modules::{
+        dummy::{ErrorScore, PanicScore, SuccessScore},
+        http::StaticFilesHttpScore,
+        okd::{dhcp::OKDDhcpScore, dns::OKDDnsScore, load_balancer::OKDLoadBalancerScore},
+        opnsense::OPNsenseShellCommandScore,
+        tftp::TftpScore,
+    },
+    topology::{LogicalHost, UnmanagedRouter},
+};
+use harmony_macros::{ip, mac_address};
+use harmony_secret::{Secret, SecretManager};
+use harmony_types::net::Url;
+use serde::{Deserialize, Serialize};
+
+#[tokio::main]
+async fn main() {
+    let firewall = harmony::topology::LogicalHost {
+        ip: ip!("192.168.5.229"),
+        name: String::from("opnsense-1"),
+    };
+
+    let switch_auth = SecretManager::get_or_prompt::<BrocadeSwitchAuth>()
+        .await
+        .expect("Failed to get credentials");
+
+    let switches: Vec<IpAddr> = vec![ip!("192.168.5.101")]; // TODO: Adjust me
+    let brocade_options = BrocadeOptions {
+        dry_run: *harmony::config::DRY_RUN,
+        ..Default::default()
+    };
+    let switch_client = BrocadeSwitchClient::init(
+        &switches,
+        &switch_auth.username,
+        &switch_auth.password,
+        brocade_options,
+    )
+    .await
+    .expect("Failed to connect to switch");
+
+    let switch_client = Arc::new(switch_client);
+
+    let opnsense = Arc::new(
+        harmony::infra::opnsense::OPNSenseFirewall::new(firewall, None, "root", "opnsense").await,
+    );
+    let lan_subnet = Ipv4Addr::new(10, 100, 8, 0);
+    let gateway_ipv4 = Ipv4Addr::new(10, 100, 8, 1);
+    let gateway_ip = IpAddr::V4(gateway_ipv4);
+    let topology = harmony::topology::HAClusterTopology {
+        kubeconfig: None,
+        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_client: switch_client.clone(),
+        node_exporter: opnsense.clone(),
+        network_manager: OnceLock::new(),
+    };
+
+    let inventory = Inventory {
+        location: Location::new(
+            "232 des Éperviers, Wendake, Qc, G0A 4V0".to_string(),
+            "wk".to_string(),
+        ),
+        switch: SwitchGroup::from([]),
+        firewall_mgmt: Box::new(OPNSenseManagementInterface::new()),
+        storage_host: vec![],
+        worker_host: vec![],
+        control_plane_host: vec![
+            PhysicalHost::empty(HostCategory::Server)
+                .mac_address(mac_address!("08:00:27:62:EC:C3")),
+        ],
+    };
+
+    // TODO regroup smaller scores in a larger one such as this
+    // let okd_boostrap_preparation();
+
+    let dhcp_score = OKDDhcpScore::new(&topology, &inventory);
+    let dns_score = OKDDnsScore::new(&topology);
+    let load_balancer_score = 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![],
+        remote_path: None,
+    };
+
+    harmony_tui::run(
+        inventory,
+        topology,
+        vec![
+            Box::new(dns_score),
+            Box::new(dhcp_score),
+            Box::new(load_balancer_score),
+            Box::new(tftp_score),
+            Box::new(http_score),
+            Box::new(OPNsenseShellCommandScore {
+                opnsense: opnsense.get_opnsense_config(),
+                command: "touch /tmp/helloharmonytouching".to_string(),
+            }),
+            Box::new(SuccessScore {}),
+            Box::new(ErrorScore {}),
+            Box::new(PanicScore {}),
+        ],
+    )
+    .await
+    .unwrap();
+}
+
+#[derive(Secret, Serialize, Deserialize, Debug)]
+pub struct BrocadeSwitchAuth {
+    pub username: String,
+    pub password: String,
+}

examples/k8s_drain_node/Cargo.toml

@@ -1,21 +0,0 @@
-[package]
-name = "example-k8s-drain-node"
-edition = "2024"
-version.workspace = true
-readme.workspace = true
-license.workspace = true
-publish = false
-
-[dependencies]
-harmony = { path = "../../harmony" }
-harmony_cli = { path = "../../harmony_cli" }
-harmony_types = { path = "../../harmony_types" }
-harmony_macros = { path = "../../harmony_macros" }
-harmony-k8s = { path = "../../harmony-k8s" }
-cidr.workspace = true
-tokio.workspace = true
-log.workspace = true
-env_logger.workspace = true
-url.workspace = true
-assert_cmd = "2.0.16"
-inquire.workspace = true

examples/k8s_drain_node/src/main.rs

@@ -1,61 +0,0 @@
-use std::time::Duration;
-
-use harmony_k8s::{DrainOptions, K8sClient};
-use log::{info, trace};
-
-#[tokio::main]
-async fn main() {
-    env_logger::init();
-    let k8s = K8sClient::try_default().await.unwrap();
-    let nodes = k8s.get_nodes(None).await.unwrap();
-    trace!("Got nodes : {nodes:#?}");
-    let node_names = nodes
-        .iter()
-        .map(|n| n.metadata.name.as_ref().unwrap())
-        .collect::<Vec<&String>>();
-
-    info!("Got nodes : {:?}", node_names);
-
-    let node_name = inquire::Select::new("What node do you want to operate on?", node_names)
-        .prompt()
-        .unwrap();
-
-    let drain = inquire::Confirm::new("Do you wish to drain the node now ?")
-        .prompt()
-        .unwrap();
-
-    if drain {
-        let mut options = DrainOptions::default_ignore_daemonset_delete_emptydir_data();
-        options.timeout = Duration::from_secs(1);
-        k8s.drain_node(&node_name, &options).await.unwrap();
-
-        info!("Node {node_name} successfully drained");
-    }
-
-    let uncordon =
-        inquire::Confirm::new("Do you wish to uncordon node to resume scheduling workloads now?")
-            .prompt()
-            .unwrap();
-
-    if uncordon {
-        info!("Uncordoning node {node_name}");
-        k8s.uncordon_node(node_name).await.unwrap();
-        info!("Node {node_name} uncordoned");
-    }
-
-    let reboot = inquire::Confirm::new("Do you wish to reboot node now?")
-        .prompt()
-        .unwrap();
-
-    if reboot {
-        k8s.reboot_node(
-            &node_name,
-            &DrainOptions::default_ignore_daemonset_delete_emptydir_data(),
-            Duration::from_secs(3600),
-        )
-        .await
-        .unwrap();
-    }
-
-    info!("All done playing with nodes, happy harmonizing!");
-}

examples/k8s_write_file_on_node/Cargo.toml

@@ -1,21 +0,0 @@
-[package]
-name = "example-k8s-write-file-on-node"
-edition = "2024"
-version.workspace = true
-readme.workspace = true
-license.workspace = true
-publish = false
-
-[dependencies]
-harmony = { path = "../../harmony" }
-harmony_cli = { path = "../../harmony_cli" }
-harmony_types = { path = "../../harmony_types" }
-harmony_macros = { path = "../../harmony_macros" }
-harmony-k8s = { path = "../../harmony-k8s" }
-cidr.workspace = true
-tokio.workspace = true
-log.workspace = true
-env_logger.workspace = true
-url.workspace = true
-assert_cmd = "2.0.16"
-inquire.workspace = true

examples/k8s_write_file_on_node/src/main.rs

@@ -1,45 +0,0 @@
-use harmony_k8s::{K8sClient, NodeFile};
-use log::{info, trace};
-
-#[tokio::main]
-async fn main() {
-    env_logger::init();
-    let k8s = K8sClient::try_default().await.unwrap();
-    let nodes = k8s.get_nodes(None).await.unwrap();
-    trace!("Got nodes : {nodes:#?}");
-    let node_names = nodes
-        .iter()
-        .map(|n| n.metadata.name.as_ref().unwrap())
-        .collect::<Vec<&String>>();
-
-    info!("Got nodes : {:?}", node_names);
-
-    let node = inquire::Select::new("What node do you want to write file to?", node_names)
-        .prompt()
-        .unwrap();
-
-    let path = inquire::Text::new("File path on node").prompt().unwrap();
-    let content = inquire::Text::new("File content").prompt().unwrap();
-
-    let node_file = NodeFile {
-        path: path,
-        content: content,
-        mode: 0o600,
-    };
-
-    k8s.write_files_to_node(&node, &vec![node_file.clone()])
-        .await
-        .unwrap();
-
-    let cmd = inquire::Text::new("Command to run on node")
-        .prompt()
-        .unwrap();
-    k8s.run_privileged_command_on_node(&node, &cmd)
-        .await
-        .unwrap();
-
-    info!(
-        "File {} mode {} written in node {node}",
-        node_file.path, node_file.mode
-    );
-}

examples/multisite_postgres/src/main.rs

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

examples/nanodc/Cargo.toml

@@ -1,5 +1,5 @@
 [package]
-name = "example-nats-supercluster"
+name = "example-nanodc"
 edition = "2024"
 version.workspace = true
 readme.workspace = true
@@ -8,12 +8,14 @@ publish = false
 
 [dependencies]
 harmony = { path = "../../harmony" }
-harmony_cli = { path = "../../harmony_cli" }
+harmony_tui = { path = "../../harmony_tui" }
 harmony_types = { path = "../../harmony_types" }
 cidr = { workspace = true }
 tokio = { workspace = true }
 harmony_macros = { path = "../../harmony_macros" }
+harmony_secret = { path = "../../harmony_secret" }
 log = { workspace = true }
 env_logger = { workspace = true }
 url = { workspace = true }
-k8s-openapi.workspace = true
+serde = { workspace = true }
+brocade = { path = "../../brocade" }

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

@@ -0,0 +1,199 @@
+use std::{
+    net::{IpAddr, Ipv4Addr},
+    sync::{Arc, OnceLock},
+};
+
+use brocade::BrocadeOptions;
+use cidr::Ipv4Cidr;
+use harmony::{
+    config::secret::SshKeyPair,
+    data::{FileContent, FilePath},
+    hardware::{HostCategory, Location, PhysicalHost, SwitchGroup},
+    infra::{brocade::BrocadeSwitchClient, opnsense::OPNSenseManagementInterface},
+    inventory::Inventory,
+    modules::{
+        http::StaticFilesHttpScore,
+        okd::{
+            bootstrap_dhcp::OKDBootstrapDhcpScore,
+            bootstrap_load_balancer::OKDBootstrapLoadBalancerScore, dhcp::OKDDhcpScore,
+            dns::OKDDnsScore, ipxe::OKDIpxeScore,
+        },
+        tftp::TftpScore,
+    },
+    topology::{LogicalHost, UnmanagedRouter},
+};
+use harmony_macros::{ip, mac_address};
+use harmony_secret::{Secret, SecretManager};
+use harmony_types::net::Url;
+use serde::{Deserialize, Serialize};
+
+#[tokio::main]
+async fn main() {
+    let firewall = harmony::topology::LogicalHost {
+        ip: ip!("192.168.33.1"),
+        name: String::from("fw0"),
+    };
+
+    let switch_auth = SecretManager::get_or_prompt::<BrocadeSwitchAuth>()
+        .await
+        .expect("Failed to get credentials");
+
+    let switches: Vec<IpAddr> = vec![ip!("192.168.33.101")];
+    let brocade_options = BrocadeOptions {
+        dry_run: *harmony::config::DRY_RUN,
+        ..Default::default()
+    };
+    let switch_client = BrocadeSwitchClient::init(
+        &switches,
+        &switch_auth.username,
+        &switch_auth.password,
+        brocade_options,
+    )
+    .await
+    .expect("Failed to connect to switch");
+
+    let switch_client = Arc::new(switch_client);
+
+    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 {
+        kubeconfig: None,
+        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(),
+            },
+        ],
+        node_exporter: opnsense.clone(),
+        switch_client: switch_client.clone(),
+        network_manager: OnceLock::new(),
+    };
+
+    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 ssh_key = SecretManager::get_or_prompt::<SshKeyPair>().await.unwrap();
+
+    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![],
+        remote_path: None,
+    };
+
+    let kickstart_filename = "inventory.kickstart".to_string();
+    let harmony_inventory_agent = "harmony_inventory_agent".to_string();
+
+    let ipxe_score = OKDIpxeScore {
+        kickstart_filename,
+        harmony_inventory_agent,
+        cluster_pubkey: FileContent {
+            path: FilePath::Relative("cluster_ssh_key.pub".to_string()),
+            content: ssh_key.public,
+        },
+    };
+
+    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();
+}
+
+#[derive(Secret, Serialize, Deserialize, Debug)]
+pub struct BrocadeSwitchAuth {
+    pub username: String,
+    pub password: String,
+}

examples/nats-module/Cargo.toml

@@ -1,19 +0,0 @@
-[package]
-name = "example-nats-module-supercluster"
-edition = "2024"
-version.workspace = true
-readme.workspace = true
-license.workspace = true
-publish = false
-
-[dependencies]
-harmony = { path = "../../harmony" }
-harmony_cli = { path = "../../harmony_cli" }
-harmony_types = { path = "../../harmony_types" }
-cidr = { workspace = true }
-tokio = { workspace = true }
-harmony_macros = { path = "../../harmony_macros" }
-log = { workspace = true }
-env_logger = { workspace = true }
-url = { workspace = true }
-k8s-openapi.workspace = true