Merge remote-tracking branch 'origin/master' into feat/postgresqlScore

Reviewed-on: #167

Cargo.lock

@@ -429,6 +429,15 @@ dependencies = [
  "wait-timeout",
 ]
 
+[[package]]
+name = "assertor"
+version = "0.0.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4ff24d87260733dc86d38a11c60d9400ce4a74a05d0dafa2a6f5ab249cd857cb"
+dependencies = [
+ "num-traits",
+]
+
 [[package]]
 name = "async-broadcast"
 version = "0.7.2"
@@ -665,6 +674,57 @@ dependencies = [
  "serde_with",
 ]
 
+[[package]]
+name = "brocade"
+version = "0.1.0"
+dependencies = [
+ "async-trait",
+ "env_logger",
+ "harmony_secret",
+ "harmony_types",
+ "log",
+ "regex",
+ "russh",
+ "russh-keys",
+ "serde",
+ "tokio",
+]
+
+[[package]]
+name = "brocade-snmp-server"
+version = "0.1.0"
+dependencies = [
+ "base64 0.22.1",
+ "brocade",
+ "env_logger",
+ "harmony",
+ "harmony_cli",
+ "harmony_macros",
+ "harmony_secret",
+ "harmony_types",
+ "log",
+ "serde",
+ "tokio",
+ "url",
+]
+
+[[package]]
+name = "brocade-switch"
+version = "0.1.0"
+dependencies = [
+ "async-trait",
+ "brocade",
+ "env_logger",
+ "harmony",
+ "harmony_cli",
+ "harmony_macros",
+ "harmony_types",
+ "log",
+ "serde",
+ "tokio",
+ "url",
+]
+
 [[package]]
 name = "brotli"
 version = "8.0.2"
@@ -1751,10 +1811,26 @@ dependencies = [
  "url",
 ]
 
+[[package]]
+name = "example-multisite-postgres"
+version = "0.1.0"
+dependencies = [
+ "cidr",
+ "env_logger",
+ "harmony",
+ "harmony_cli",
+ "harmony_macros",
+ "harmony_types",
+ "log",
+ "tokio",
+ "url",
+]
+
 [[package]]
 name = "example-nanodc"
 version = "0.1.0"
 dependencies = [
+ "brocade",
  "cidr",
  "env_logger",
  "harmony",
@@ -1763,6 +1839,22 @@ dependencies = [
  "harmony_tui",
  "harmony_types",
  "log",
+ "serde",
+ "tokio",
+ "url",
+]
+
+[[package]]
+name = "example-nats"
+version = "0.1.0"
+dependencies = [
+ "cidr",
+ "env_logger",
+ "harmony",
+ "harmony_cli",
+ "harmony_macros",
+ "harmony_types",
+ "log",
  "tokio",
  "url",
 ]
@@ -1781,6 +1873,7 @@ dependencies = [
 name = "example-okd-install"
 version = "0.1.0"
 dependencies = [
+ "brocade",
  "cidr",
  "env_logger",
  "harmony",
@@ -1795,25 +1888,86 @@ dependencies = [
  "url",
 ]
 
+[[package]]
+name = "example-openbao"
+version = "0.1.0"
+dependencies = [
+ "harmony",
+ "harmony_cli",
+ "harmony_macros",
+ "harmony_types",
+ "tokio",
+ "url",
+]
+
+[[package]]
+name = "example-operatorhub-catalogsource"
+version = "0.1.0"
+dependencies = [
+ "cidr",
+ "env_logger",
+ "harmony",
+ "harmony_cli",
+ "harmony_macros",
+ "harmony_types",
+ "log",
+ "tokio",
+ "url",
+]
+
 [[package]]
 name = "example-opnsense"
 version = "0.1.0"
 dependencies = [
+ "brocade",
  "cidr",
  "env_logger",
  "harmony",
  "harmony_macros",
+ "harmony_secret",
  "harmony_tui",
  "harmony_types",
  "log",
+ "serde",
+ "tokio",
+ "url",
+]
+
+[[package]]
+name = "example-postgresql"
+version = "0.1.0"
+dependencies = [
+ "cidr",
+ "env_logger",
+ "harmony",
+ "harmony_cli",
+ "harmony_macros",
+ "harmony_types",
+ "log",
  "tokio",
  "url",
 ]
 
 [[package]]
-name = "example-pxe"
+name = "example-public-postgres"
 version = "0.1.0"
 dependencies = [
+ "cidr",
+ "env_logger",
+ "harmony",
+ "harmony_cli",
+ "harmony_macros",
+ "harmony_types",
+ "log",
+ "tokio",
+ "url",
+]
+
+[[package]]
+name = "example-opnsense-node-exporter"
+version = "0.1.0"
+dependencies = [
+ "async-trait",
  "cidr",
  "env_logger",
  "harmony",
@@ -1828,6 +1982,34 @@ dependencies = [
  "url",
 ]
 
+[[package]]
+name = "example-pxe"
+version = "0.1.0"
+dependencies = [
+ "brocade",
+ "cidr",
+ "env_logger",
+ "harmony",
+ "harmony_cli",
+ "harmony_macros",
+ "harmony_secret",
+ "harmony_secret_derive",
+ "harmony_types",
+ "log",
+ "serde",
+ "tokio",
+ "url",
+]
+
+[[package]]
+name = "example-remove-rook-osd"
+version = "0.1.0"
+dependencies = [
+ "harmony",
+ "harmony_cli",
+ "tokio",
+]
+
 [[package]]
 name = "example-rust"
 version = "0.1.0"
@@ -2305,9 +2487,11 @@ name = "harmony"
 version = "0.1.0"
 dependencies = [
  "askama",
+ "assertor",
  "async-trait",
  "base64 0.22.1",
  "bollard",
+ "brocade",
  "chrono",
  "cidr",
  "convert_case",
@@ -2338,6 +2522,7 @@ dependencies = [
  "once_cell",
  "opnsense-config",
  "opnsense-config-xml",
+ "option-ext",
  "pretty_assertions",
  "reqwest 0.11.27",
  "russh",
@@ -2423,6 +2608,19 @@ dependencies = [
  "tokio",
 ]
 
+[[package]]
+name = "harmony_inventory_builder"
+version = "0.1.0"
+dependencies = [
+ "cidr",
+ "harmony",
+ "harmony_cli",
+ "harmony_macros",
+ "harmony_types",
+ "tokio",
+ "url",
+]
+
 [[package]]
 name = "harmony_macros"
 version = "0.1.0"
@@ -2488,8 +2686,10 @@ dependencies = [
 name = "harmony_types"
 version = "0.1.0"
 dependencies = [
+ "log",
  "rand 0.9.2",
  "serde",
+ "serde_json",
  "url",
 ]
 
@@ -3878,6 +4078,7 @@ checksum = "d05e27ee213611ffe7d6348b942e8f942b37114c00cc03cec254295a4a17852e"
 name = "opnsense-config"
 version = "0.1.0"
 dependencies = [
+ "assertor",
  "async-trait",
  "chrono",
  "env_logger",
@@ -4537,9 +4738,9 @@ dependencies = [
 
 [[package]]
 name = "regex"
-version = "1.11.2"
+version = "1.11.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "23d7fd106d8c02486a8d64e778353d1cffe08ce79ac2e82f540c86d0facf6912"
+checksum = "8b5288124840bee7b386bc413c487869b360b2b4ec421ea56425128692f2a82c"
 dependencies = [
  "aho-corasick 1.1.3",
  "memchr",
@@ -4549,9 +4750,9 @@ dependencies = [
 
 [[package]]
 name = "regex-automata"
-version = "0.4.10"
+version = "0.4.11"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6b9458fa0bfeeac22b5ca447c63aaf45f28439a709ccd244698632f9aa6394d6"
+checksum = "833eb9ce86d40ef33cb1306d8accf7bc8ec2bfea4355cbdebb3df68b40925cad"
 dependencies = [
  "aho-corasick 1.1.3",
  "memchr",

Cargo.toml

@@ -14,7 +14,9 @@ members = [
   "harmony_composer",
   "harmony_inventory_agent",
   "harmony_secret_derive",
-  "harmony_secret", "adr/agent_discovery/mdns",
+  "harmony_secret",
+  "adr/agent_discovery/mdns",
+  "brocade",
 ]
 
 [workspace.package]
@@ -66,5 +68,12 @@ thiserror = "2.0.14"
 serde = { version = "1.0.209", features = ["derive", "rc"] }
 serde_json = "1.0.127"
 askama = "0.14"
-sqlx = { version = "0.8", features = ["runtime-tokio", "sqlite" ] }
-reqwest = { version = "0.12", features = ["blocking", "stream", "rustls-tls", "http2", "json"], default-features = false }
+sqlx = { version = "0.8", features = ["runtime-tokio", "sqlite"] }
+reqwest = { version = "0.12", features = [
+  "blocking",
+  "stream",
+  "rustls-tls",
+  "http2",
+  "json",
+], default-features = false }
+assertor = "0.0.4"

README.md

@@ -36,48 +36,59 @@ These principles surface as simple, ergonomic Rust APIs that let teams focus on
 
 ## 2 · Quick Start
 
-The snippet below spins up a complete **production-grade LAMP stack** with monitoring. Swap it for your own scores to deploy anything from microservices to machine-learning pipelines.
+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::{
-    data::Version,
     inventory::Inventory,
-    maestro::Maestro,
     modules::{
-        lamp::{LAMPConfig, LAMPScore},
-        monitoring::monitoring_alerting::MonitoringAlertingStackScore,
+        application::{
+            ApplicationScore, RustWebFramework, RustWebapp,
+            features::{PackagingDeployment, rhob_monitoring::Monitoring},
+        },
+        monitoring::alert_channel::discord_alert_channel::DiscordWebhook,
     },
-    topology::{K8sAnywhereTopology, Url},
+    topology::K8sAnywhereTopology,
 };
+use harmony_macros::hurl;
+use std::{path::PathBuf, sync::Arc};
 
 #[tokio::main]
 async fn main() {
-    // 1. Describe what you want
-    let lamp_stack = LAMPScore {
-        name: "harmony-lamp-demo".into(),
-        domain: Url::Url(url::Url::parse("https://lampdemo.example.com").unwrap()),
-        php_version: Version::from("8.3.0").unwrap(),
-        config: LAMPConfig {
-            project_root: "./php".into(),
-            database_size: "4Gi".into(),
-            ..Default::default()
-        },
+    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,
     };
 
-    // 2. Enhance with extra scores (monitoring, CI/CD, …)
-    let mut monitoring = MonitoringAlertingStackScore::new();
-    monitoring.namespace = Some(lamp_stack.config.namespace.clone());
-
-    // 3. Run your scores on the desired topology & inventory
     harmony_cli::run(
-        Inventory::autoload(),                // auto-detect hardware / kube-config
-        K8sAnywhereTopology::from_env(),      // local k3d, CI, staging, prod…
-        vec![
-          Box::new(lamp_stack),
-          Box::new(monitoring)
-        ],
-        None
-    ).await.unwrap();
+        Inventory::autoload(),
+        K8sAnywhereTopology::from_env(), // <== Deploy to local automatically provisioned local k3d by default or connect to any kubernetes cluster
+        vec![Box::new(app)],
+        None,
+    )
+    .await
+    .unwrap();
 }
 ```
 

adr/015-higher-order-topologies.md

@@ -0,0 +1,114 @@
+# Architecture Decision Record: Higher-Order Topologies
+
+**Initial Author:** Jean-Gabriel Gill-Couture  
+**Initial Date:** 2025-12-08  
+**Last Updated Date:** 2025-12-08  
+
+## Status
+
+Implemented
+
+## Context
+
+Harmony models infrastructure as **Topologies** (deployment targets like `K8sAnywhereTopology`, `LinuxHostTopology`) implementing **Capabilities** (tech traits like `PostgreSQL`, `Docker`).
+
+**Higher-Order Topologies** (e.g., `FailoverTopology<T>`) compose/orchestrate capabilities *across* multiple underlying topologies (e.g., primary+replica `T`).
+
+Naive design requires manual `impl Capability for HigherOrderTopology<T>` *per T per capability*, causing:
+- **Impl explosion**: N topologies × M capabilities = N×M boilerplate.
+- **ISP violation**: Topologies forced to impl unrelated capabilities.
+- **Maintenance hell**: New topology needs impls for *all* orchestrated capabilities; new capability needs impls for *all* topologies/higher-order.
+- **Barrier to extension**: Users can't easily add topologies without todos/panics.
+
+This makes scaling Harmony impractical as ecosystem grows.
+
+## Decision
+
+Use **blanket trait impls** on higher-order topologies to *automatically* derive orchestration:
+
+````rust
+/// Higher-Order Topology: Orchestrates capabilities across sub-topologies.
+pub struct FailoverTopology<T> {
+    /// Primary sub-topology.
+    primary: T,
+    /// Replica sub-topology.
+    replica: T,
+}
+
+/// Automatically provides PostgreSQL failover for *any* `T: PostgreSQL`.
+/// Delegates to primary for queries; orchestrates deploy across both.
+#[async_trait]
+impl<T: PostgreSQL> PostgreSQL for FailoverTopology<T> {
+    async fn deploy(&self, config: &PostgreSQLConfig) -> Result<String, String> {
+        // Deploy primary; extract certs/endpoint;
+        // deploy replica with pg_basebackup + TLS passthrough.
+        // (Full impl logged/elaborated.)
+    }
+
+    // Delegate queries to primary.
+    async fn get_replication_certs(&self, cluster_name: &str) -> Result<ReplicationCerts, String> {
+        self.primary.get_replication_certs(cluster_name).await
+    }
+    // ...
+}
+
+/// Similarly for other capabilities.
+#[async_trait]
+impl<T: Docker> Docker for FailoverTopology<T> {
+    // Failover Docker orchestration.
+}
+````
+
+**Key properties:**
+- **Auto-derivation**: `Failover<K8sAnywhere>` gets `PostgreSQL` iff `K8sAnywhere: PostgreSQL`.
+- **No boilerplate**: One blanket impl per capability *per higher-order type*.
+
+## Rationale
+
+- **Composition via generics**: Rust trait solver auto-selects impls; zero runtime cost.
+- **Compile-time safety**: Missing `T: Capability` → compile error (no panics).
+- **Scalable**: O(capabilities) impls per higher-order; new `T` auto-works.
+- **ISP-respecting**: Capabilities only surface if sub-topology provides.
+- **Centralized logic**: Orchestration (e.g., cert propagation) in one place.
+
+**Example usage:**
+````rust
+// ✅ Works: K8sAnywhere: PostgreSQL → Failover provides failover PG
+let pg_failover: FailoverTopology<K8sAnywhereTopology> = ...;
+pg_failover.deploy_pg(config).await;
+
+// ✅ Works: LinuxHost: Docker → Failover provides failover Docker
+let docker_failover: FailoverTopology<LinuxHostTopology> = ...;
+docker_failover.deploy_docker(...).await;
+
+// ❌ Compile fail: K8sAnywhere !: Docker
+let invalid: FailoverTopology<K8sAnywhereTopology>;
+invalid.deploy_docker(...); // `T: Docker` bound unsatisfied
+````
+
+## Consequences
+
+**Pros:**
+- **Extensible**: New topology `AWSTopology: PostgreSQL` → instant `Failover<AWSTopology>: PostgreSQL`.
+- **Lean**: No useless impls (e.g., no `K8sAnywhere: Docker`).
+- **Observable**: Logs trace every step.
+
+**Cons:**
+- **Monomorphization**: Generics generate code per T (mitigated: few Ts).
+- **Delegation opacity**: Relies on rustdoc/logs for internals.
+
+## Alternatives considered
+
+| Approach | Pros | Cons |
+|----------|------|------|
+| **Manual per-T impls**<br>`impl PG for Failover<K8s> {..}`<br>`impl PG for Failover<Linux> {..}` | Explicit control | N×M explosion; violates ISP; hard to extend. |
+| **Dynamic trait objects**<br>`Box<dyn AnyCapability>` | Runtime flex | Perf hit; type erasure; error-prone dispatch. |
+| **Mega-topology trait**<br>All-in-one `OrchestratedTopology` | Simple wiring | Monolithic; poor composition. |
+| **Registry dispatch**<br>Runtime capability lookup | Decoupled | Complex; no compile safety; perf/debug overhead. |
+
+**Selected**: Blanket impls leverage Rust generics for safe, zero-cost composition.
+
+## Additional Notes
+
+- Applies to `MultisiteTopology<T>`, `ShardedTopology<T>`, etc.
+- `FailoverTopology` in `failover.rs` is first implementation.

adr/015-higher-order-topologies/example.rs

@@ -0,0 +1,153 @@
+//! Example of Higher-Order Topologies in Harmony.
+//! Demonstrates how `FailoverTopology<T>` automatically provides failover for *any* capability
+//! supported by a sub-topology `T` via blanket trait impls.
+//! 
+//! Key insight: No manual impls per T or capability -- scales effortlessly.
+//! Users can:
+//! - Write new `Topology` (impl capabilities on a struct).
+//! - Compose with `FailoverTopology` (gets capabilities if T has them).
+//! - Compile fails if capability missing (safety).
+
+use async_trait::async_trait;
+use tokio;
+
+/// Capability trait: Deploy and manage PostgreSQL.
+#[async_trait]
+pub trait PostgreSQL {
+    async fn deploy(&self, config: &PostgreSQLConfig) -> Result<String, String>;
+    async fn get_replication_certs(&self, cluster_name: &str) -> Result<ReplicationCerts, String>;
+}
+
+/// Capability trait: Deploy Docker.
+#[async_trait]
+pub trait Docker {
+    async fn deploy_docker(&self) -> Result<String, String>;
+}
+
+/// Configuration for PostgreSQL deployments.
+#[derive(Clone)]
+pub struct PostgreSQLConfig;
+
+/// Replication certificates.
+#[derive(Clone)]
+pub struct ReplicationCerts;
+
+/// Concrete topology: Kubernetes Anywhere (supports PostgreSQL).
+#[derive(Clone)]
+pub struct K8sAnywhereTopology;
+
+#[async_trait]
+impl PostgreSQL for K8sAnywhereTopology {
+    async fn deploy(&self, _config: &PostgreSQLConfig) -> Result<String, String> {
+        // Real impl: Use k8s helm chart, operator, etc.
+        Ok("K8sAnywhere PostgreSQL deployed".to_string())
+    }
+
+    async fn get_replication_certs(&self, _cluster_name: &str) -> Result<ReplicationCerts, String> {
+        Ok(ReplicationCerts)
+    }
+}
+
+/// Concrete topology: Linux Host (supports Docker).
+#[derive(Clone)]
+pub struct LinuxHostTopology;
+
+#[async_trait]
+impl Docker for LinuxHostTopology {
+    async fn deploy_docker(&self) -> Result<String, String> {
+        // Real impl: Install/configure Docker on host.
+        Ok("LinuxHost Docker deployed".to_string())
+    }
+}
+
+/// Higher-Order Topology: Composes multiple sub-topologies (primary + replica).
+/// Automatically derives *all* capabilities of `T` with failover orchestration.
+/// 
+/// - If `T: PostgreSQL`, then `FailoverTopology<T>: PostgreSQL` (blanket impl).
+/// - Same for `Docker`, etc. No boilerplate!
+/// - Compile-time safe: Missing `T: Capability` → error.
+#[derive(Clone)]
+pub struct FailoverTopology<T> {
+    /// Primary sub-topology.
+    pub primary: T,
+    /// Replica sub-topology.
+    pub replica: T,
+}
+
+/// Blanket impl: Failover PostgreSQL if T provides PostgreSQL.
+/// Delegates reads to primary; deploys to both.
+#[async_trait]
+impl<T: PostgreSQL + Send + Sync + Clone> PostgreSQL for FailoverTopology<T> {
+    async fn deploy(&self, config: &PostgreSQLConfig) -> Result<String, String> {
+        // Orchestrate: Deploy primary first, then replica (e.g., via pg_basebackup).
+        let primary_result = self.primary.deploy(config).await?;
+        let replica_result = self.replica.deploy(config).await?;
+        Ok(format!("Failover PG deployed: {} | {}", primary_result, replica_result))
+    }
+
+    async fn get_replication_certs(&self, cluster_name: &str) -> Result<ReplicationCerts, String> {
+        // Delegate to primary (replica follows).
+        self.primary.get_replication_certs(cluster_name).await
+    }
+}
+
+/// Blanket impl: Failover Docker if T provides Docker.
+#[async_trait]
+impl<T: Docker + Send + Sync + Clone> Docker for FailoverTopology<T> {
+    async fn deploy_docker(&self) -> Result<String, String> {
+        // Orchestrate across primary + replica.
+        let primary_result = self.primary.deploy_docker().await?;
+        let replica_result = self.replica.deploy_docker().await?;
+        Ok(format!("Failover Docker deployed: {} | {}", primary_result, replica_result))
+    }
+}
+
+#[tokio::main]
+async fn main() {
+    let config = PostgreSQLConfig;
+
+    println!("=== ✅ PostgreSQL Failover (K8sAnywhere supports PG) ===");
+    let pg_failover = FailoverTopology {
+        primary: K8sAnywhereTopology,
+        replica: K8sAnywhereTopology,
+    };
+    let result = pg_failover.deploy(&config).await.unwrap();
+    println!("Result: {}", result);
+
+    println!("\n=== ✅ Docker Failover (LinuxHost supports Docker) ===");
+    let docker_failover = FailoverTopology {
+        primary: LinuxHostTopology,
+        replica: LinuxHostTopology,
+    };
+    let result = docker_failover.deploy_docker().await.unwrap();
+    println!("Result: {}", result);
+
+    println!("\n=== ❌ Would fail to compile (K8sAnywhere !: Docker) ===");
+    // let invalid = FailoverTopology {
+    //     primary: K8sAnywhereTopology,
+    //     replica: K8sAnywhereTopology,
+    // };
+    // invalid.deploy_docker().await.unwrap(); // Error: `K8sAnywhereTopology: Docker` not satisfied!
+    // Very clear error message :
+    // error[E0599]: the method `deploy_docker` exists for struct `FailoverTopology<K8sAnywhereTopology>`, but its trait bounds were not satisfied
+    //   --> src/main.rs:90:9
+    //    |
+    //  4 | pub struct FailoverTopology<T> {
+    //    | ------------------------------ method `deploy_docker` not found for this struct because it doesn't satisfy `FailoverTopology<K8sAnywhereTopology>: Docker`
+    // ...
+    // 37 | struct K8sAnywhereTopology;
+    //    | -------------------------- doesn't satisfy `K8sAnywhereTopology: Docker`
+    // ...
+    // 90 | invalid.deploy_docker(); // `T: Docker` bound unsatisfied
+    //    |         ^^^^^^^^^^^^^ method cannot be called on `FailoverTopology<K8sAnywhereTopology>` due to unsatisfied trait bounds
+    //    |
+    // note: trait bound `K8sAnywhereTopology: Docker` was not satisfied
+    //   --> src/main.rs:61:9
+    //    |
+    // 61 | impl<T: Docker + Send + Sync> Docker for FailoverTopology<T> {
+    //    |         ^^^^^^                ------     -------------------
+    //    |         |
+    //    |         unsatisfied trait bound introduced here
+    // note: the trait `Docker` must be implemented
+}
+

adr/016-Harmony-Agent-And-Global-Mesh-For-Decentralized-Workload-Management.md

@@ -0,0 +1,90 @@
+# Architecture Decision Record: Global Orchestration Mesh & The Harmony Agent
+
+**Status:** Proposed
+**Date:** 2025-12-19
+
+## Context
+
+Harmony is designed to enable a truly decentralized infrastructure where independent clusters—owned by different organizations or running on diverse hardware—can collaborate reliably. This vision combines the decentralization of Web3 with the performance and capabilities of Web2.
+
+Currently, Harmony operates as a stateless CLI tool, invoked manually or via CI runners. While effective for deployment, this model presents a critical limitation: **a CLI cannot react to real-time events.**
+
+To achieve automated failover and dynamic workload management, we need a system that is "always on." Relying on manual intervention or scheduled CI jobs to recover from a cluster failure creates unacceptable latency and prevents us from scaling to thousands of nodes.
+
+Furthermore, we face a challenge in serving diverse workloads:
+*   **Financial workloads** require absolute consistency (CP - Consistency/Partition Tolerance).
+*   **AI/Inference workloads** require maximum availability (AP - Availability/Partition Tolerance).
+
+There are many more use cases, but those are the two extremes.
+
+We need a unified architecture that automates cluster coordination and supports both consistency models without requiring a complete re-architecture in the future.
+
+## Decision
+
+We propose a fundamental architectural evolution. It has been clear since the start of Harmony that it would be necessary to transition Harmony from a purely ephemeral CLI tool to a system that includes a persistent **Harmony Agent**. This Agent will connect to a **Global Orchestration Mesh** based on a strongly consistent protocol.
+
+The proposal consists of four key pillars:
+
+### 1. The Harmony Agent (New Component)
+We will develop a long-running process (Daemon/Agent) to be deployed alongside workloads.
+*   **Shift from CLI:** Unlike the CLI, which applies configuration and exits, the Agent maintains a persistent connection to the mesh.
+*   **Responsibility:** It actively monitors cluster health, participates in consensus, and executes lifecycle commands (start/stop/fence) instantly when the mesh dictates a state change.
+
+### 2. The Technology: NATS JetStream
+We will utilize **NATS JetStream** as the underlying transport and consensus layer for the Agent and the Mesh.
+*   **Why not raw Raft?** Implementing a raw Raft library requires building and maintaining the transport layer, log compaction, snapshotting, and peer discovery manually. NATS JetStream provides a battle-tested, distributed log and Key-Value store (based on Raft) out of the box, along with a high-performance pub/sub system for event propagation.
+*   **Role:** It will act as the "source of truth" for the cluster state.
+
+### 3. Strong Consistency at the Mesh Layer
+The mesh will operate with **Strong Consistency** by default.
+*   All critical cluster state changes (topology updates, lease acquisitions, leadership elections) will require consensus among the Agents.
+*   This ensures that in the event of a network partition, we have a mathematical guarantee of which side holds the valid state, preventing data corruption.
+
+### 4. Public UX: The `FailoverStrategy` Abstraction
+To keep the user experience stable and simple, we will expose the complexity of the mesh through a high-level configuration API, tentatively called `FailoverStrategy`.
+
+The user defines the *intent* in their config, and the Harmony Agent automates the *execution*:
+
+*   **`FailoverStrategy::AbsoluteConsistency`**:
+    *   *Use Case:* Banking, Transactional DBs.
+    *   *Behavior:* If the mesh detects a partition, the Agent on the minority side immediately halts workloads. No split-brain is ever allowed.
+*   **`FailoverStrategy::SplitBrainAllowed`**:
+    *   *Use Case:* LLM Inference, Stateless Web Servers.
+    *   *Behavior:* If a partition occurs, the Agent keeps workloads running to maximize uptime. State is reconciled when connectivity returns.
+
+## Rationale
+
+**The Necessity of an Agent**
+You cannot automate what you do not monitor. Moving to an Agent-based model is the only way to achieve sub-second reaction times to infrastructure failures. It transforms Harmony from a deployment tool into a self-healing platform.
+
+**Scaling & Decentralization**
+To allow independent clusters to collaborate, they need a shared language. A strongly consistent mesh allows Cluster A (Organization X) and Cluster B (Organization Y) to agree on workload placement without a central authority.
+
+**Why Strong Consistency First?**
+It is technically feasible to relax a strongly consistent system to allow for "Split Brain" behavior (AP) when the user requests it. However, it is nearly impossible to take an eventually consistent system and force it to be strongly consistent (CP) later. By starting with strict constraints, we cover the hardest use cases (Finance) immediately.
+
+**Future Topologies**
+While our immediate need is `FailoverTopology` (Multi-site), this architecture supports any future topology logic:
+*   **`CostTopology`**: Agents negotiate to route workloads to the cluster with the cheapest spot instances.
+*   **`HorizontalTopology`**: Spreading a single workload across 100 clusters for massive scale.
+*   **`GeoTopology`**: Ensuring data stays within specific legal jurisdictions.
+
+The mesh provides the *capability* (consensus and messaging); the topology provides the *logic*.
+
+## Consequences
+
+**Positive**
+*   **Automation:** Eliminates manual failover, enabling massive scale.
+*   **Reliability:** Guarantees data safety for critical workloads by default.
+*   **Flexibility:** A single codebase serves both high-frequency trading and AI inference.
+*   **Stability:** The public API remains abstract, allowing us to optimize the mesh internals without breaking user code.
+
+**Negative**
+*   **Deployment Complexity:** Users must now deploy and maintain a running service (the Agent) rather than just downloading a binary.
+*   **Engineering Complexity:** Integrating NATS JetStream and handling distributed state machines is significantly more complex than the current CLI logic.
+
+## Implementation Plan (Short Term)
+1.  **Agent Bootstrap:** Create the initial scaffold for the Harmony Agent (daemon).
+2.  **Mesh Integration:** Prototype NATS JetStream embedding within the Agent.
+3.  **Strategy Implementation:** Add `FailoverStrategy` to the configuration schema and implement the logic in the Agent to read and act on it.
+4.  **Migration:** Transition the current manual failover scripts into event-driven logic handled by the Agent.

brocade/Cargo.toml

@@ -0,0 +1,18 @@
+[package]
+name = "brocade"
+edition = "2024"
+version.workspace = true
+readme.workspace = true
+license.workspace = true
+
+[dependencies]
+async-trait.workspace = true
+harmony_types = { path = "../harmony_types" }
+russh.workspace = true
+russh-keys.workspace = true
+tokio.workspace = true
+log.workspace = true
+env_logger.workspace = true
+regex = "1.11.3"
+harmony_secret = { path = "../harmony_secret" }
+serde.workspace = true

brocade/examples/main.rs

@@ -0,0 +1,76 @@
+use std::net::{IpAddr, Ipv4Addr};
+
+use brocade::{BrocadeOptions, ssh};
+use harmony_secret::{Secret, SecretManager};
+use harmony_types::switch::PortLocation;
+use serde::{Deserialize, Serialize};
+
+#[derive(Secret, Clone, Debug, Serialize, Deserialize)]
+struct BrocadeSwitchAuth {
+    username: String,
+    password: String,
+}
+
+#[tokio::main]
+async fn main() {
+    env_logger::Builder::from_env(env_logger::Env::default().default_filter_or("info")).init();
+
+    // let ip = IpAddr::V4(Ipv4Addr::new(10, 0, 0, 250)); // old brocade @ ianlet
+    let ip = IpAddr::V4(Ipv4Addr::new(127, 0, 0, 1)); // brocade @ sto1
+    // 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 brocade = brocade::init(
+        &switch_addresses,
+        // &config.username,
+        // &config.password,
+        "admin",
+        "password",
+        BrocadeOptions {
+            dry_run: true,
+            ssh: ssh::SshOptions {
+                port: 2222,
+                ..Default::default()
+            },
+            ..Default::default()
+        },
+    )
+    .await
+    .expect("Brocade client failed to connect");
+
+    let entries = brocade.get_stack_topology().await.unwrap();
+    println!("Stack topology: {entries:#?}");
+
+    let entries = brocade.get_interfaces().await.unwrap();
+    println!("Interfaces: {entries:#?}");
+
+    let version = brocade.version().await.unwrap();
+    println!("Version: {version:?}");
+
+    println!("--------------");
+    let mac_adddresses = brocade.get_mac_address_table().await.unwrap();
+    println!("VLAN\tMAC\t\t\tPORT");
+    for mac in mac_adddresses {
+        println!("{}\t{}\t{}", mac.vlan, mac.mac_address, mac.port);
+    }
+
+    println!("--------------");
+    todo!();
+    let channel_name = "1";
+    brocade.clear_port_channel(channel_name).await.unwrap();
+
+    println!("--------------");
+    let channel_id = brocade.find_available_channel_id().await.unwrap();
+
+    println!("--------------");
+    let channel_name = "HARMONY_LAG";
+    let ports = [PortLocation(2, 0, 35)];
+    brocade
+        .create_port_channel(channel_id, channel_name, &ports)
+        .await
+        .unwrap();
+}

brocade/src/fast_iron.rs

@@ -0,0 +1,229 @@
+use super::BrocadeClient;
+use crate::{
+    BrocadeInfo, Error, ExecutionMode, InterSwitchLink, InterfaceInfo, MacAddressEntry,
+    PortChannelId, PortOperatingMode, SecurityLevel, parse_brocade_mac_address,
+    shell::BrocadeShell,
+};
+
+use async_trait::async_trait;
+use harmony_types::switch::{PortDeclaration, PortLocation};
+use log::{debug, info};
+use regex::Regex;
+use std::{collections::HashSet, str::FromStr};
+
+#[derive(Debug)]
+pub struct FastIronClient {
+    shell: BrocadeShell,
+    version: BrocadeInfo,
+}
+
+impl FastIronClient {
+    pub fn init(mut shell: BrocadeShell, version_info: BrocadeInfo) -> Self {
+        shell.before_all(vec!["skip-page-display".into()]);
+        shell.after_all(vec!["page".into()]);
+
+        Self {
+            shell,
+            version: version_info,
+        }
+    }
+
+    fn parse_mac_entry(&self, line: &str) -> Option<Result<MacAddressEntry, Error>> {
+        debug!("[Brocade] Parsing mac address entry: {line}");
+        let parts: Vec<&str> = line.split_whitespace().collect();
+        if parts.len() < 3 {
+            return None;
+        }
+
+        let (vlan, mac_address, port) = match parts.len() {
+            3 => (
+                u16::from_str(parts[0]).ok()?,
+                parse_brocade_mac_address(parts[1]).ok()?,
+                parts[2].to_string(),
+            ),
+            _ => (
+                1,
+                parse_brocade_mac_address(parts[0]).ok()?,
+                parts[1].to_string(),
+            ),
+        };
+
+        let port =
+            PortDeclaration::parse(&port).map_err(|e| Error::UnexpectedError(format!("{e}")));
+
+        match port {
+            Ok(p) => Some(Ok(MacAddressEntry {
+                vlan,
+                mac_address,
+                port: p,
+            })),
+            Err(e) => Some(Err(e)),
+        }
+    }
+
+    fn parse_stack_port_entry(&self, line: &str) -> Option<Result<InterSwitchLink, Error>> {
+        debug!("[Brocade] Parsing stack port entry: {line}");
+        let parts: Vec<&str> = line.split_whitespace().collect();
+        if parts.len() < 10 {
+            return None;
+        }
+
+        let local_port = PortLocation::from_str(parts[0]).ok()?;
+
+        Some(Ok(InterSwitchLink {
+            local_port,
+            remote_port: None,
+        }))
+    }
+
+    fn build_port_channel_commands(
+        &self,
+        channel_id: PortChannelId,
+        channel_name: &str,
+        ports: &[PortLocation],
+    ) -> Vec<String> {
+        let mut commands = vec![
+            "configure terminal".to_string(),
+            format!("lag {channel_name} static id {channel_id}"),
+        ];
+
+        for port in ports {
+            commands.push(format!("ports ethernet {port}"));
+        }
+
+        commands.push(format!("primary-port {}", ports[0]));
+        commands.push("deploy".into());
+        commands.push("exit".into());
+        commands.push("write memory".into());
+        commands.push("exit".into());
+
+        commands
+    }
+}
+
+#[async_trait]
+impl BrocadeClient for FastIronClient {
+    async fn version(&self) -> Result<BrocadeInfo, Error> {
+        Ok(self.version.clone())
+    }
+
+    async fn get_mac_address_table(&self) -> Result<Vec<MacAddressEntry>, Error> {
+        info!("[Brocade] Showing MAC address table...");
+
+        let output = self
+            .shell
+            .run_command("show mac-address", ExecutionMode::Regular)
+            .await?;
+
+        output
+            .lines()
+            .skip(2)
+            .filter_map(|line| self.parse_mac_entry(line))
+            .collect()
+    }
+
+    async fn get_stack_topology(&self) -> Result<Vec<InterSwitchLink>, Error> {
+        let output = self
+            .shell
+            .run_command("show interface stack-ports", crate::ExecutionMode::Regular)
+            .await?;
+
+        output
+            .lines()
+            .skip(1)
+            .filter_map(|line| self.parse_stack_port_entry(line))
+            .collect()
+    }
+
+    async fn get_interfaces(&self) -> Result<Vec<InterfaceInfo>, Error> {
+        todo!()
+    }
+
+    async fn configure_interfaces(
+        &self,
+        _interfaces: &Vec<(String, PortOperatingMode)>,
+    ) -> Result<(), Error> {
+        todo!()
+    }
+
+    async fn find_available_channel_id(&self) -> Result<PortChannelId, Error> {
+        info!("[Brocade] Finding next available channel id...");
+
+        let output = self
+            .shell
+            .run_command("show lag", ExecutionMode::Regular)
+            .await?;
+        let re = Regex::new(r"=== LAG .* ID\s+(\d+)").expect("Invalid regex");
+
+        let used_ids: HashSet<u8> = output
+            .lines()
+            .filter_map(|line| {
+                re.captures(line)
+                    .and_then(|c| c.get(1))
+                    .and_then(|id_match| id_match.as_str().parse().ok())
+            })
+            .collect();
+
+        let mut next_id: u8 = 1;
+        loop {
+            if !used_ids.contains(&next_id) {
+                break;
+            }
+            next_id += 1;
+        }
+
+        info!("[Brocade] Found channel id: {next_id}");
+        Ok(next_id)
+    }
+
+    async fn create_port_channel(
+        &self,
+        channel_id: PortChannelId,
+        channel_name: &str,
+        ports: &[PortLocation],
+    ) -> Result<(), Error> {
+        info!(
+            "[Brocade] Configuring port-channel '{channel_name} {channel_id}' with ports: {ports:?}"
+        );
+
+        let commands = self.build_port_channel_commands(channel_id, channel_name, ports);
+        self.shell
+            .run_commands(commands, ExecutionMode::Privileged)
+            .await?;
+
+        info!("[Brocade] Port-channel '{channel_name}' configured.");
+        Ok(())
+    }
+
+    async fn clear_port_channel(&self, channel_name: &str) -> Result<(), Error> {
+        info!("[Brocade] Clearing port-channel: {channel_name}");
+
+        let commands = vec![
+            "configure terminal".to_string(),
+            format!("no lag {channel_name}"),
+            "write memory".to_string(),
+        ];
+        self.shell
+            .run_commands(commands, ExecutionMode::Privileged)
+            .await?;
+
+        info!("[Brocade] Port-channel '{channel_name}' cleared.");
+        Ok(())
+    }
+
+    async fn enable_snmp(&self, user_name: &str, auth: &str, des: &str) -> Result<(), Error> {
+        let commands = vec![
+            "configure terminal".into(),
+            "snmp-server view ALL 1 included".into(),
+            "snmp-server group public v3 priv read ALL".into(),
+            format!(
+                "snmp-server user {user_name} groupname public auth md5 auth-password {auth} priv des priv-password {des}"
+            ),
+            "exit".into(),
+        ];
+        self.shell
+            .run_commands(commands, ExecutionMode::Regular)
+            .await?;
+        Ok(())
+    }
+}

brocade/src/lib.rs

@@ -0,0 +1,352 @@
+use std::net::IpAddr;
+use std::{
+    fmt::{self, Display},
+    time::Duration,
+};
+
+use crate::network_operating_system::NetworkOperatingSystemClient;
+use crate::{
+    fast_iron::FastIronClient,
+    shell::{BrocadeSession, BrocadeShell},
+};
+
+use async_trait::async_trait;
+use harmony_types::net::MacAddress;
+use harmony_types::switch::{PortDeclaration, PortLocation};
+use regex::Regex;
+use serde::Serialize;
+
+mod fast_iron;
+mod network_operating_system;
+mod shell;
+pub mod ssh;
+
+#[derive(Default, Clone, Debug)]
+pub struct BrocadeOptions {
+    pub dry_run: bool,
+    pub ssh: ssh::SshOptions,
+    pub timeouts: TimeoutConfig,
+}
+
+#[derive(Clone, Debug)]
+pub struct TimeoutConfig {
+    pub shell_ready: Duration,
+    pub command_execution: Duration,
+    pub command_output: Duration,
+    pub cleanup: Duration,
+    pub message_wait: Duration,
+}
+
+impl Default for TimeoutConfig {
+    fn default() -> Self {
+        Self {
+            shell_ready: Duration::from_secs(10),
+            command_execution: Duration::from_secs(60), // Commands like `deploy` (for a LAG) can take a while
+            command_output: Duration::from_secs(5), // Delay to start logging "waiting for command output"
+            cleanup: Duration::from_secs(10),
+            message_wait: Duration::from_millis(500),
+        }
+    }
+}
+
+enum ExecutionMode {
+    Regular,
+    Privileged,
+}
+
+#[derive(Clone, Debug)]
+pub struct BrocadeInfo {
+    os: BrocadeOs,
+    _version: String,
+}
+
+#[derive(Clone, Debug)]
+pub enum BrocadeOs {
+    NetworkOperatingSystem,
+    FastIron,
+    Unknown,
+}
+
+#[derive(Debug, PartialEq, Eq, PartialOrd, Ord, Clone)]
+pub struct MacAddressEntry {
+    pub vlan: u16,
+    pub mac_address: MacAddress,
+    pub port: PortDeclaration,
+}
+
+pub type PortChannelId = u8;
+
+/// Represents a single physical or logical link connecting two switches within a stack or fabric.
+///
+/// This structure provides a standardized view of the topology regardless of the
+/// underlying Brocade OS configuration (stacking vs. fabric).
+#[derive(Debug, PartialEq, Eq, Clone)]
+pub struct InterSwitchLink {
+    /// The local port on the switch where the topology command was run.
+    pub local_port: PortLocation,
+    /// The port on the directly connected neighboring switch.
+    pub remote_port: Option<PortLocation>,
+}
+
+/// Represents the key running configuration status of a single switch interface.
+#[derive(Debug, PartialEq, Eq, Clone)]
+pub struct InterfaceInfo {
+    /// The full configuration name (e.g., "TenGigabitEthernet 1/0/1", "FortyGigabitEthernet 2/0/2").
+    pub name: String,
+    /// The physical location of the interface.
+    pub port_location: PortLocation,
+    /// The parsed type and name prefix of the interface.
+    pub interface_type: InterfaceType,
+    /// The primary configuration mode defining the interface's behavior (L2, L3, Fabric).
+    pub operating_mode: Option<PortOperatingMode>,
+    /// Indicates the current state of the interface.
+    pub status: InterfaceStatus,
+}
+
+/// Categorizes the functional type of a switch interface.
+#[derive(Debug, PartialEq, Eq, Clone)]
+pub enum InterfaceType {
+    /// Physical or virtual Ethernet interface (e.g., TenGigabitEthernet, FortyGigabitEthernet).
+    Ethernet(String),
+}
+
+impl fmt::Display for InterfaceType {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        match self {
+            InterfaceType::Ethernet(name) => write!(f, "{name}"),
+        }
+    }
+}
+
+/// Defines the primary configuration mode of a switch interface, representing mutually exclusive roles.
+#[derive(Debug, PartialEq, Eq, Clone, Serialize)]
+pub enum PortOperatingMode {
+    /// The interface is explicitly configured for Brocade fabric roles (ISL or Trunk enabled).
+    Fabric,
+    /// The interface is configured for standard Layer 2 switching as Trunk port (`switchport mode trunk`).
+    Trunk,
+    /// The interface is configured for standard Layer 2 switching as Access port (`switchport` without trunk mode).
+    Access,
+}
+
+/// Defines the possible status of an interface.
+#[derive(Debug, PartialEq, Eq, Clone)]
+pub enum InterfaceStatus {
+    /// The interface is connected.
+    Connected,
+    /// The interface is not connected and is not expected to be.
+    NotConnected,
+    /// The interface is not connected but is expected to be (configured with `no shutdown`).
+    SfpAbsent,
+}
+
+pub async fn init(
+    ip_addresses: &[IpAddr],
+    username: &str,
+    password: &str,
+    options: BrocadeOptions,
+) -> Result<Box<dyn BrocadeClient + Send + Sync>, Error> {
+    let shell = BrocadeShell::init(ip_addresses, username, password, options).await?;
+
+    let version_info = shell
+        .with_session(ExecutionMode::Regular, |session| {
+            Box::pin(get_brocade_info(session))
+        })
+        .await?;
+
+    Ok(match version_info.os {
+        BrocadeOs::FastIron => Box::new(FastIronClient::init(shell, version_info)),
+        BrocadeOs::NetworkOperatingSystem => {
+            Box::new(NetworkOperatingSystemClient::init(shell, version_info))
+        }
+        BrocadeOs::Unknown => todo!(),
+    })
+}
+
+#[async_trait]
+pub trait BrocadeClient: std::fmt::Debug {
+    /// Retrieves the operating system and version details from the connected Brocade switch.
+    ///
+    /// This is typically the first call made after establishing a connection to determine
+    /// the switch OS family (e.g., FastIron, NOS) for feature compatibility.
+    ///
+    /// # Returns
+    ///
+    /// A `BrocadeInfo` structure containing parsed OS type and version string.
+    async fn version(&self) -> Result<BrocadeInfo, Error>;
+
+    /// Retrieves the dynamically learned MAC address table from the switch.
+    ///
+    /// This is crucial for discovering where specific network endpoints (MAC addresses)
+    /// are currently located on the physical ports.
+    ///
+    /// # Returns
+    ///
+    /// A vector of `MacAddressEntry`, where each entry typically contains VLAN, MAC address,
+    /// and the associated port name/index.
+    async fn get_mac_address_table(&self) -> Result<Vec<MacAddressEntry>, Error>;
+
+    /// Derives the physical connections used to link multiple switches together
+    /// to form a single logical entity (stack, fabric, etc.).
+    ///
+    /// This abstracts the underlying configuration (e.g., stack ports, fabric ports)
+    /// to return a standardized view of the topology.
+    ///
+    /// # Returns
+    ///
+    /// A vector of `InterSwitchLink` structs detailing which ports are used for stacking/fabric.
+    /// If the switch is not stacked, returns an empty vector.
+    async fn get_stack_topology(&self) -> Result<Vec<InterSwitchLink>, Error>;
+
+    /// Retrieves the status for all interfaces
+    ///
+    /// # Returns
+    ///
+    /// A vector of `InterfaceInfo` structures.
+    async fn get_interfaces(&self) -> Result<Vec<InterfaceInfo>, Error>;
+
+    /// Configures a set of interfaces to be operated with a specified mode (access ports, ISL, etc.).
+    async fn configure_interfaces(
+        &self,
+        interfaces: &Vec<(String, PortOperatingMode)>,
+    ) -> Result<(), Error>;
+
+    /// Scans the existing configuration to find the next available (unused)
+    /// Port-Channel ID (`lag` or `trunk`) for assignment.
+    ///
+    /// # Returns
+    ///
+    /// The smallest, unassigned `PortChannelId` within the supported range.
+    async fn find_available_channel_id(&self) -> Result<PortChannelId, Error>;
+
+    /// Creates and configures a new Port-Channel (Link Aggregation Group or LAG)
+    /// using the specified channel ID and ports.
+    ///
+    /// The resulting configuration must be persistent (saved to startup-config).
+    /// Assumes a static LAG configuration mode unless specified otherwise by the implementation.
+    ///
+    /// # Parameters
+    ///
+    /// * `channel_id`: The ID (e.g., 1-128) for the logical port channel.
+    /// * `channel_name`: A descriptive name for the LAG (used in configuration context).
+    /// * `ports`: A slice of `PortLocation` structs defining the physical member ports.
+    async fn create_port_channel(
+        &self,
+        channel_id: PortChannelId,
+        channel_name: &str,
+        ports: &[PortLocation],
+    ) -> Result<(), Error>;
+
+    /// Enables Simple Network Management Protocol (SNMP) server for switch
+    ///
+    /// # Parameters
+    ///
+    ///  * `user_name`: The user name for the snmp server
+    ///  * `auth`: The password for authentication process for verifying the identity of a device
+    ///  * `des`: The Data Encryption Standard algorithm key
+    async fn enable_snmp(&self, user_name: &str, auth: &str, des: &str) -> Result<(), Error>;
+
+    /// Removes all configuration associated with the specified Port-Channel name.
+    ///
+    /// This operation should be idempotent; attempting to clear a non-existent
+    /// channel should succeed (or return a benign error).
+    ///
+    /// # Parameters
+    ///
+    /// * `channel_name`: The name of the Port-Channel (LAG) to delete.
+    ///
+    async fn clear_port_channel(&self, channel_name: &str) -> Result<(), Error>;
+}
+
+async fn get_brocade_info(session: &mut BrocadeSession) -> Result<BrocadeInfo, Error> {
+    let output = session.run_command("show version").await?;
+
+    if output.contains("Network Operating System") {
+        let re = Regex::new(r"Network Operating System Version:\s*(?P<version>[a-zA-Z0-9.\-]+)")
+            .expect("Invalid regex");
+        let version = re
+            .captures(&output)
+            .and_then(|cap| cap.name("version"))
+            .map(|m| m.as_str().to_string())
+            .unwrap_or_default();
+
+        return Ok(BrocadeInfo {
+            os: BrocadeOs::NetworkOperatingSystem,
+            _version: version,
+        });
+    } else if output.contains("ICX") {
+        let re = Regex::new(r"(?m)^\s*SW: Version\s*(?P<version>[a-zA-Z0-9.\-]+)")
+            .expect("Invalid regex");
+        let version = re
+            .captures(&output)
+            .and_then(|cap| cap.name("version"))
+            .map(|m| m.as_str().to_string())
+            .unwrap_or_default();
+
+        return Ok(BrocadeInfo {
+            os: BrocadeOs::FastIron,
+            _version: version,
+        });
+    }
+
+    Err(Error::UnexpectedError("Unknown Brocade OS version".into()))
+}
+
+fn parse_brocade_mac_address(value: &str) -> Result<MacAddress, String> {
+    let cleaned_mac = value.replace('.', "");
+
+    if cleaned_mac.len() != 12 {
+        return Err(format!("Invalid MAC address: {value}"));
+    }
+
+    let mut bytes = [0u8; 6];
+    for (i, pair) in cleaned_mac.as_bytes().chunks(2).enumerate() {
+        let byte_str = std::str::from_utf8(pair).map_err(|_| "Invalid UTF-8")?;
+        bytes[i] =
+            u8::from_str_radix(byte_str, 16).map_err(|_| format!("Invalid hex in MAC: {value}"))?;
+    }
+
+    Ok(MacAddress(bytes))
+}
+
+#[derive(Debug)]
+pub enum SecurityLevel {
+    AuthPriv(String),
+}
+
+#[derive(Debug)]
+pub enum Error {
+    NetworkError(String),
+    AuthenticationError(String),
+    ConfigurationError(String),
+    TimeoutError(String),
+    UnexpectedError(String),
+    CommandError(String),
+}
+
+impl Display for Error {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        match self {
+            Error::NetworkError(msg) => write!(f, "Network error: {msg}"),
+            Error::AuthenticationError(msg) => write!(f, "Authentication error: {msg}"),
+            Error::ConfigurationError(msg) => write!(f, "Configuration error: {msg}"),
+            Error::TimeoutError(msg) => write!(f, "Timeout error: {msg}"),
+            Error::UnexpectedError(msg) => write!(f, "Unexpected error: {msg}"),
+            Error::CommandError(msg) => write!(f, "{msg}"),
+        }
+    }
+}
+
+impl From<Error> for String {
+    fn from(val: Error) -> Self {
+        format!("{val}")
+    }
+}
+
+impl std::error::Error for Error {}
+
+impl From<russh::Error> for Error {
+    fn from(value: russh::Error) -> Self {
+        Error::NetworkError(format!("Russh client error: {value}"))
+    }
+}

brocade/src/network_operating_system.rs

@@ -0,0 +1,352 @@
+use std::str::FromStr;
+
+use async_trait::async_trait;
+use harmony_types::switch::{PortDeclaration, PortLocation};
+use log::{debug, info};
+use regex::Regex;
+
+use crate::{
+    BrocadeClient, BrocadeInfo, Error, ExecutionMode, InterSwitchLink, InterfaceInfo,
+    InterfaceStatus, InterfaceType, MacAddressEntry, PortChannelId, PortOperatingMode,
+    SecurityLevel, parse_brocade_mac_address, shell::BrocadeShell,
+};
+
+#[derive(Debug)]
+pub struct NetworkOperatingSystemClient {
+    shell: BrocadeShell,
+    version: BrocadeInfo,
+}
+
+impl NetworkOperatingSystemClient {
+    pub fn init(mut shell: BrocadeShell, version_info: BrocadeInfo) -> Self {
+        shell.before_all(vec!["terminal length 0".into()]);
+
+        Self {
+            shell,
+            version: version_info,
+        }
+    }
+
+    fn parse_mac_entry(&self, line: &str) -> Option<Result<MacAddressEntry, Error>> {
+        debug!("[Brocade] Parsing mac address entry: {line}");
+        let parts: Vec<&str> = line.split_whitespace().collect();
+        if parts.len() < 5 {
+            return None;
+        }
+
+        let (vlan, mac_address, port) = match parts.len() {
+            5 => (
+                u16::from_str(parts[0]).ok()?,
+                parse_brocade_mac_address(parts[1]).ok()?,
+                parts[4].to_string(),
+            ),
+            _ => (
+                u16::from_str(parts[0]).ok()?,
+                parse_brocade_mac_address(parts[1]).ok()?,
+                parts[5].to_string(),
+            ),
+        };
+
+        let port =
+            PortDeclaration::parse(&port).map_err(|e| Error::UnexpectedError(format!("{e}")));
+
+        match port {
+            Ok(p) => Some(Ok(MacAddressEntry {
+                vlan,
+                mac_address,
+                port: p,
+            })),
+            Err(e) => Some(Err(e)),
+        }
+    }
+
+    fn parse_inter_switch_link_entry(&self, line: &str) -> Option<Result<InterSwitchLink, Error>> {
+        debug!("[Brocade] Parsing inter switch link entry: {line}");
+        let parts: Vec<&str> = line.split_whitespace().collect();
+        if parts.len() < 10 {
+            return None;
+        }
+
+        let local_port = PortLocation::from_str(parts[2]).ok()?;
+        let remote_port = PortLocation::from_str(parts[5]).ok()?;
+
+        Some(Ok(InterSwitchLink {
+            local_port,
+            remote_port: Some(remote_port),
+        }))
+    }
+
+    fn parse_interface_status_entry(&self, line: &str) -> Option<Result<InterfaceInfo, Error>> {
+        debug!("[Brocade] Parsing interface status entry: {line}");
+        let parts: Vec<&str> = line.split_whitespace().collect();
+        if parts.len() < 6 {
+            return None;
+        }
+
+        let interface_type = match parts[0] {
+            "Fo" => InterfaceType::Ethernet("FortyGigabitEthernet".to_string()),
+            "Te" => InterfaceType::Ethernet("TenGigabitEthernet".to_string()),
+            _ => return None,
+        };
+        let port_location = PortLocation::from_str(parts[1]).ok()?;
+        let status = match parts[2] {
+            "connected" => InterfaceStatus::Connected,
+            "notconnected" => InterfaceStatus::NotConnected,
+            "sfpAbsent" => InterfaceStatus::SfpAbsent,
+            _ => return None,
+        };
+        let operating_mode = match parts[3] {
+            "ISL" => Some(PortOperatingMode::Fabric),
+            "Trunk" => Some(PortOperatingMode::Trunk),
+            "Access" => Some(PortOperatingMode::Access),
+            "--" => None,
+            _ => return None,
+        };
+
+        Some(Ok(InterfaceInfo {
+            name: format!("{interface_type} {port_location}"),
+            port_location,
+            interface_type,
+            operating_mode,
+            status,
+        }))
+    }
+
+    fn map_configure_interfaces_error(&self, err: Error) -> Error {
+        debug!("[Brocade] {err}");
+
+        if let Error::CommandError(message) = &err {
+            if message.contains("switchport")
+                && message.contains("Cannot configure aggregator member")
+            {
+                let re = Regex::new(r"\(conf-if-([a-zA-Z]+)-([\d/]+)\)#").unwrap();
+
+                if let Some(caps) = re.captures(message) {
+                    let interface_type = &caps[1];
+                    let port_location = &caps[2];
+                    let interface = format!("{interface_type} {port_location}");
+
+                    return Error::CommandError(format!(
+                        "Cannot configure interface '{interface}', it is a member of a port-channel (LAG)"
+                    ));
+                }
+            }
+        }
+
+        err
+    }
+}
+
+#[async_trait]
+impl BrocadeClient for NetworkOperatingSystemClient {
+    async fn version(&self) -> Result<BrocadeInfo, Error> {
+        Ok(self.version.clone())
+    }
+
+    async fn get_mac_address_table(&self) -> Result<Vec<MacAddressEntry>, Error> {
+        let output = self
+            .shell
+            .run_command("show mac-address-table", ExecutionMode::Regular)
+            .await?;
+
+        output
+            .lines()
+            .skip(1)
+            .filter_map(|line| self.parse_mac_entry(line))
+            .collect()
+    }
+
+    async fn get_stack_topology(&self) -> Result<Vec<InterSwitchLink>, Error> {
+        let output = self
+            .shell
+            .run_command("show fabric isl", ExecutionMode::Regular)
+            .await?;
+
+        output
+            .lines()
+            .skip(6)
+            .filter_map(|line| self.parse_inter_switch_link_entry(line))
+            .collect()
+    }
+
+    async fn get_interfaces(&self) -> Result<Vec<InterfaceInfo>, Error> {
+        let output = self
+            .shell
+            .run_command(
+                "show interface status rbridge-id all",
+                ExecutionMode::Regular,
+            )
+            .await?;
+
+        output
+            .lines()
+            .skip(2)
+            .filter_map(|line| self.parse_interface_status_entry(line))
+            .collect()
+    }
+
+    async fn configure_interfaces(
+        &self,
+        interfaces: &Vec<(String, PortOperatingMode)>,
+    ) -> Result<(), Error> {
+        info!("[Brocade] Configuring {} interface(s)...", interfaces.len());
+
+        let mut commands = vec!["configure terminal".to_string()];
+
+        for interface in interfaces {
+            commands.push(format!("interface {}", interface.0));
+
+            match interface.1 {
+                PortOperatingMode::Fabric => {
+                    commands.push("fabric isl enable".into());
+                    commands.push("fabric trunk enable".into());
+                }
+                PortOperatingMode::Trunk => {
+                    commands.push("switchport".into());
+                    commands.push("switchport mode trunk".into());
+                    commands.push("switchport trunk allowed vlan all".into());
+                    commands.push("no switchport trunk tag native-vlan".into());
+                    commands.push("spanning-tree shutdown".into());
+                    commands.push("no fabric isl enable".into());
+                    commands.push("no fabric trunk enable".into());
+                    commands.push("no shutdown".into());
+                }
+                PortOperatingMode::Access => {
+                    commands.push("switchport".into());
+                    commands.push("switchport mode access".into());
+                    commands.push("switchport access vlan 1".into());
+                    commands.push("no spanning-tree shutdown".into());
+                    commands.push("no fabric isl enable".into());
+                    commands.push("no fabric trunk enable".into());
+                }
+            }
+
+            commands.push("no shutdown".into());
+            commands.push("exit".into());
+        }
+
+        self.shell
+            .run_commands(commands, ExecutionMode::Regular)
+            .await
+            .map_err(|err| self.map_configure_interfaces_error(err))?;
+
+        info!("[Brocade] Interfaces configured.");
+
+        Ok(())
+    }
+
+    async fn find_available_channel_id(&self) -> Result<PortChannelId, Error> {
+        info!("[Brocade] Finding next available channel id...");
+
+        let output = self
+            .shell
+            .run_command("show port-channel summary", ExecutionMode::Regular)
+            .await?;
+
+        let used_ids: Vec<u8> = output
+            .lines()
+            .skip(6)
+            .filter_map(|line| {
+                let parts: Vec<&str> = line.split_whitespace().collect();
+                if parts.len() < 8 {
+                    return None;
+                }
+
+                u8::from_str(parts[0]).ok()
+            })
+            .collect();
+
+        let mut next_id: u8 = 1;
+        loop {
+            if !used_ids.contains(&next_id) {
+                break;
+            }
+            next_id += 1;
+        }
+
+        info!("[Brocade] Found channel id: {next_id}");
+        Ok(next_id)
+    }
+
+    async fn create_port_channel(
+        &self,
+        channel_id: PortChannelId,
+        channel_name: &str,
+        ports: &[PortLocation],
+    ) -> Result<(), Error> {
+        info!(
+            "[Brocade] Configuring port-channel '{channel_id} {channel_name}' with ports: {}",
+            ports
+                .iter()
+                .map(|p| format!("{p}"))
+                .collect::<Vec<String>>()
+                .join(", ")
+        );
+
+        let interfaces = self.get_interfaces().await?;
+
+        let mut commands = vec![
+            "configure terminal".into(),
+            format!("interface port-channel {}", channel_id),
+            "no shutdown".into(),
+            "exit".into(),
+        ];
+
+        for port in ports {
+            let interface = interfaces.iter().find(|i| i.port_location == *port);
+            let Some(interface) = interface else {
+                continue;
+            };
+
+            commands.push(format!("interface {}", interface.name));
+            commands.push("no switchport".into());
+            commands.push("no ip address".into());
+            commands.push("no fabric isl enable".into());
+            commands.push("no fabric trunk enable".into());
+            commands.push(format!("channel-group {channel_id} mode active"));
+            commands.push("no shutdown".into());
+            commands.push("exit".into());
+        }
+
+        self.shell
+            .run_commands(commands, ExecutionMode::Regular)
+            .await?;
+
+        info!("[Brocade] Port-channel '{channel_name}' configured.");
+
+        Ok(())
+    }
+
+    async fn clear_port_channel(&self, channel_name: &str) -> Result<(), Error> {
+        info!("[Brocade] Clearing port-channel: {channel_name}");
+
+        let commands = vec![
+            "configure terminal".into(),
+            format!("no interface port-channel {}", channel_name),
+            "exit".into(),
+        ];
+
+        self.shell
+            .run_commands(commands, ExecutionMode::Regular)
+            .await?;
+
+        info!("[Brocade] Port-channel '{channel_name}' cleared.");
+        Ok(())
+    }
+
+    async fn enable_snmp(&self, user_name: &str, auth: &str, des: &str) -> Result<(), Error> {
+        let commands = vec![
+            "configure terminal".into(),
+            "snmp-server view ALL 1 included".into(),
+            "snmp-server group public v3 priv read ALL".into(),
+            format!(
+                "snmp-server user {user_name} groupname public auth md5 auth-password {auth} priv des priv-password {des}"
+            ),
+            "exit".into(),
+        ];
+        self.shell
+            .run_commands(commands, ExecutionMode::Regular)
+            .await?;
+        Ok(())
+    }
+}

brocade/src/shell.rs

@@ -0,0 +1,367 @@
+use std::net::IpAddr;
+use std::time::Duration;
+use std::time::Instant;
+
+use crate::BrocadeOptions;
+use crate::Error;
+use crate::ExecutionMode;
+use crate::TimeoutConfig;
+use crate::ssh;
+
+use log::debug;
+use log::info;
+use russh::ChannelMsg;
+use tokio::time::timeout;
+
+#[derive(Debug)]
+pub struct BrocadeShell {
+    ip: IpAddr,
+    username: String,
+    password: String,
+    options: BrocadeOptions,
+    before_all_commands: Vec<String>,
+    after_all_commands: Vec<String>,
+}
+
+impl BrocadeShell {
+    pub async fn init(
+        ip_addresses: &[IpAddr],
+        username: &str,
+        password: &str,
+        options: BrocadeOptions,
+    ) -> Result<Self, Error> {
+        let ip = ip_addresses
+            .first()
+            .ok_or_else(|| Error::ConfigurationError("No IP addresses provided".to_string()))?;
+
+        let brocade_ssh_client_options =
+            ssh::try_init_client(username, password, ip, options).await?;
+
+        Ok(Self {
+            ip: *ip,
+            username: username.to_string(),
+            password: password.to_string(),
+            before_all_commands: vec![],
+            after_all_commands: vec![],
+            options: brocade_ssh_client_options,
+        })
+    }
+
+    pub async fn open_session(&self, mode: ExecutionMode) -> Result<BrocadeSession, Error> {
+        BrocadeSession::open(
+            self.ip,
+            self.options.ssh.port,
+            &self.username,
+            &self.password,
+            self.options.clone(),
+            mode,
+        )
+        .await
+    }
+
+    pub async fn with_session<F, R>(&self, mode: ExecutionMode, callback: F) -> Result<R, Error>
+    where
+        F: FnOnce(
+            &mut BrocadeSession,
+        ) -> std::pin::Pin<
+            Box<dyn std::future::Future<Output = Result<R, Error>> + Send + '_>,
+        >,
+    {
+        let mut session = self.open_session(mode).await?;
+
+        let _ = session.run_commands(self.before_all_commands.clone()).await;
+        let result = callback(&mut session).await;
+        let _ = session.run_commands(self.after_all_commands.clone()).await;
+
+        session.close().await?;
+        result
+    }
+
+    pub async fn run_command(&self, command: &str, mode: ExecutionMode) -> Result<String, Error> {
+        let mut session = self.open_session(mode).await?;
+
+        let _ = session.run_commands(self.before_all_commands.clone()).await;
+        let result = session.run_command(command).await;
+        let _ = session.run_commands(self.after_all_commands.clone()).await;
+
+        session.close().await?;
+        result
+    }
+
+    pub async fn run_commands(
+        &self,
+        commands: Vec<String>,
+        mode: ExecutionMode,
+    ) -> Result<(), Error> {
+        let mut session = self.open_session(mode).await?;
+
+        let _ = session.run_commands(self.before_all_commands.clone()).await;
+        let result = session.run_commands(commands).await;
+        let _ = session.run_commands(self.after_all_commands.clone()).await;
+
+        session.close().await?;
+        result
+    }
+
+    pub fn before_all(&mut self, commands: Vec<String>) {
+        self.before_all_commands = commands;
+    }
+
+    pub fn after_all(&mut self, commands: Vec<String>) {
+        self.after_all_commands = commands;
+    }
+}
+
+pub struct BrocadeSession {
+    pub channel: russh::Channel<russh::client::Msg>,
+    pub mode: ExecutionMode,
+    pub options: BrocadeOptions,
+}
+
+impl BrocadeSession {
+    pub async fn open(
+        ip: IpAddr,
+        port: u16,
+        username: &str,
+        password: &str,
+        options: BrocadeOptions,
+        mode: ExecutionMode,
+    ) -> Result<Self, Error> {
+        let client = ssh::create_client(ip, port, username, password, &options).await?;
+        let mut channel = client.channel_open_session().await?;
+
+        channel
+            .request_pty(false, "vt100", 80, 24, 0, 0, &[])
+            .await?;
+        channel.request_shell(false).await?;
+
+        wait_for_shell_ready(&mut channel, &options.timeouts).await?;
+
+        if let ExecutionMode::Privileged = mode {
+            try_elevate_session(&mut channel, username, password, &options.timeouts).await?;
+        }
+
+        Ok(Self {
+            channel,
+            mode,
+            options,
+        })
+    }
+
+    pub async fn close(&mut self) -> Result<(), Error> {
+        debug!("[Brocade] Closing session...");
+
+        self.channel.data(&b"exit\n"[..]).await?;
+        if let ExecutionMode::Privileged = self.mode {
+            self.channel.data(&b"exit\n"[..]).await?;
+        }
+
+        let start = Instant::now();
+        while start.elapsed() < self.options.timeouts.cleanup {
+            match timeout(self.options.timeouts.message_wait, self.channel.wait()).await {
+                Ok(Some(ChannelMsg::Close)) => break,
+                Ok(Some(_)) => continue,
+                Ok(None) | Err(_) => break,
+            }
+        }
+
+        debug!("[Brocade] Session closed.");
+        Ok(())
+    }
+
+    pub async fn run_command(&mut self, command: &str) -> Result<String, Error> {
+        if self.should_skip_command(command) {
+            return Ok(String::new());
+        }
+
+        debug!("[Brocade] Running command: '{command}'...");
+
+        self.channel
+            .data(format!("{}\n", command).as_bytes())
+            .await?;
+        tokio::time::sleep(Duration::from_millis(100)).await;
+
+        let output = self.collect_command_output().await?;
+        let output = String::from_utf8(output)
+            .map_err(|_| Error::UnexpectedError("Invalid UTF-8 in command output".to_string()))?;
+
+        self.check_for_command_errors(&output, command)?;
+        Ok(output)
+    }
+
+    pub async fn run_commands(&mut self, commands: Vec<String>) -> Result<(), Error> {
+        for command in commands {
+            self.run_command(&command).await?;
+        }
+        Ok(())
+    }
+
+    fn should_skip_command(&self, command: &str) -> bool {
+        if (command.starts_with("write") || command.starts_with("deploy")) && self.options.dry_run {
+            info!("[Brocade] Dry-run mode enabled, skipping command: {command}");
+            return true;
+        }
+        false
+    }
+
+    async fn collect_command_output(&mut self) -> Result<Vec<u8>, Error> {
+        let mut output = Vec::new();
+        let start = Instant::now();
+        let read_timeout = Duration::from_millis(500);
+        let log_interval = Duration::from_secs(5);
+        let mut last_log = Instant::now();
+
+        loop {
+            if start.elapsed() > self.options.timeouts.command_execution {
+                return Err(Error::TimeoutError(
+                    "Timeout waiting for command completion.".into(),
+                ));
+            }
+
+            if start.elapsed() > self.options.timeouts.command_output
+                && last_log.elapsed() > log_interval
+            {
+                info!("[Brocade] Waiting for command output...");
+                last_log = Instant::now();
+            }
+
+            match timeout(read_timeout, self.channel.wait()).await {
+                Ok(Some(ChannelMsg::Data { data } | ChannelMsg::ExtendedData { data, .. })) => {
+                    output.extend_from_slice(&data);
+                    let current_output = String::from_utf8_lossy(&output);
+                    if current_output.contains('>') || current_output.contains('#') {
+                        return Ok(output);
+                    }
+                }
+                Ok(Some(ChannelMsg::Eof | ChannelMsg::Close)) => return Ok(output),
+                Ok(Some(ChannelMsg::ExitStatus { exit_status })) => {
+                    debug!("[Brocade] Command exit status: {exit_status}");
+                }
+                Ok(Some(_)) => continue,
+                Ok(None) | Err(_) => {
+                    if output.is_empty() {
+                        if let Ok(None) = timeout(read_timeout, self.channel.wait()).await {
+                            break;
+                        }
+                        continue;
+                    }
+
+                    tokio::time::sleep(Duration::from_millis(100)).await;
+                    let current_output = String::from_utf8_lossy(&output);
+                    if current_output.contains('>') || current_output.contains('#') {
+                        return Ok(output);
+                    }
+                }
+            }
+        }
+
+        Ok(output)
+    }
+
+    fn check_for_command_errors(&self, output: &str, command: &str) -> Result<(), Error> {
+        const ERROR_PATTERNS: &[&str] = &[
+            "invalid input",
+            "syntax error",
+            "command not found",
+            "unknown command",
+            "permission denied",
+            "access denied",
+            "authentication failed",
+            "configuration error",
+            "failed to",
+            "error:",
+        ];
+
+        let output_lower = output.to_lowercase();
+        if ERROR_PATTERNS.iter().any(|&p| output_lower.contains(p)) {
+            return Err(Error::CommandError(format!(
+                "Command error: {}",
+                output.trim()
+            )));
+        }
+
+        if !command.starts_with("show") && output.trim().is_empty() {
+            return Err(Error::CommandError(format!(
+                "Command '{command}' produced no output"
+            )));
+        }
+
+        Ok(())
+    }
+}
+
+async fn wait_for_shell_ready(
+    channel: &mut russh::Channel<russh::client::Msg>,
+    timeouts: &TimeoutConfig,
+) -> Result<(), Error> {
+    let mut buffer = Vec::new();
+    let start = Instant::now();
+
+    while start.elapsed() < timeouts.shell_ready {
+        match timeout(timeouts.message_wait, channel.wait()).await {
+            Ok(Some(ChannelMsg::Data { data })) => {
+                buffer.extend_from_slice(&data);
+                let output = String::from_utf8_lossy(&buffer);
+                let output = output.trim();
+                if output.ends_with('>') || output.ends_with('#') {
+                    debug!("[Brocade] Shell ready");
+                    return Ok(());
+                }
+            }
+            Ok(Some(_)) => continue,
+            Ok(None) => break,
+            Err(_) => continue,
+        }
+    }
+    Ok(())
+}
+
+async fn try_elevate_session(
+    channel: &mut russh::Channel<russh::client::Msg>,
+    username: &str,
+    password: &str,
+    timeouts: &TimeoutConfig,
+) -> Result<(), Error> {
+    channel.data(&b"enable\n"[..]).await?;
+    let start = Instant::now();
+    let mut buffer = Vec::new();
+
+    while start.elapsed() < timeouts.shell_ready {
+        match timeout(timeouts.message_wait, channel.wait()).await {
+            Ok(Some(ChannelMsg::Data { data })) => {
+                buffer.extend_from_slice(&data);
+                let output = String::from_utf8_lossy(&buffer);
+
+                if output.ends_with('#') {
+                    debug!("[Brocade] Privileged mode established");
+                    return Ok(());
+                }
+
+                if output.contains("User Name:") {
+                    channel.data(format!("{}\n", username).as_bytes()).await?;
+                    buffer.clear();
+                } else if output.contains("Password:") {
+                    channel.data(format!("{}\n", password).as_bytes()).await?;
+                    buffer.clear();
+                } else if output.contains('>') {
+                    return Err(Error::AuthenticationError(
+                        "Enable authentication failed".into(),
+                    ));
+                }
+            }
+            Ok(Some(_)) => continue,
+            Ok(None) => break,
+            Err(_) => continue,
+        }
+    }
+
+    let output = String::from_utf8_lossy(&buffer);
+    if output.ends_with('#') {
+        debug!("[Brocade] Privileged mode established");
+        Ok(())
+    } else {
+        Err(Error::AuthenticationError(format!(
+            "Enable failed. Output:\n{output}"
+        )))
+    }
+}

brocade/src/ssh.rs

@@ -0,0 +1,131 @@
+use std::borrow::Cow;
+use std::sync::Arc;
+
+use async_trait::async_trait;
+use log::debug;
+use russh::client::Handler;
+use russh::kex::DH_G1_SHA1;
+use russh::kex::ECDH_SHA2_NISTP256;
+use russh_keys::key::SSH_RSA;
+
+use super::BrocadeOptions;
+use super::Error;
+
+#[derive(Clone, Debug)]
+pub struct SshOptions {
+    pub preferred_algorithms: russh::Preferred,
+    pub port: u16,
+}
+
+impl Default for SshOptions {
+    fn default() -> Self {
+        Self {
+            preferred_algorithms: Default::default(),
+            port: 22,
+        }
+    }
+}
+
+impl SshOptions {
+    fn ecdhsa_sha2_nistp256(port: u16) -> Self {
+        Self {
+            preferred_algorithms: russh::Preferred {
+                kex: Cow::Borrowed(&[ECDH_SHA2_NISTP256]),
+                key: Cow::Borrowed(&[SSH_RSA]),
+                ..Default::default()
+            },
+            port,
+            ..Default::default()
+        }
+    }
+
+    fn legacy(port: u16) -> Self {
+        Self {
+            preferred_algorithms: russh::Preferred {
+                kex: Cow::Borrowed(&[DH_G1_SHA1]),
+                key: Cow::Borrowed(&[SSH_RSA]),
+                ..Default::default()
+            },
+            port,
+            ..Default::default()
+        }
+    }
+}
+
+pub struct Client;
+
+#[async_trait]
+impl Handler for Client {
+    type Error = Error;
+
+    async fn check_server_key(
+        &mut self,
+        _server_public_key: &russh_keys::key::PublicKey,
+    ) -> Result<bool, Self::Error> {
+        Ok(true)
+    }
+}
+
+pub async fn try_init_client(
+    username: &str,
+    password: &str,
+    ip: &std::net::IpAddr,
+    base_options: BrocadeOptions,
+) -> Result<BrocadeOptions, Error> {
+    let mut default = SshOptions::default();
+    default.port = base_options.ssh.port;
+    let ssh_options = vec![
+        default,
+        SshOptions::ecdhsa_sha2_nistp256(base_options.ssh.port),
+        SshOptions::legacy(base_options.ssh.port),
+    ];
+
+    for ssh in ssh_options {
+        let opts = BrocadeOptions {
+            ssh: ssh.clone(),
+            ..base_options.clone()
+        };
+        debug!("Creating client {ip}:{} {username}", ssh.port);
+        let client = create_client(*ip, ssh.port, username, password, &opts).await;
+
+        match client {
+            Ok(_) => {
+                return Ok(opts);
+            }
+            Err(e) => match e {
+                Error::NetworkError(e) => {
+                    if e.contains("No common key exchange algorithm") {
+                        continue;
+                    } else {
+                        return Err(Error::NetworkError(e));
+                    }
+                }
+                _ => return Err(e),
+            },
+        }
+    }
+
+    Err(Error::NetworkError(
+        "Could not establish ssh connection: wrong key exchange algorithm)".to_string(),
+    ))
+}
+
+pub async fn create_client(
+    ip: std::net::IpAddr,
+    port: u16,
+    username: &str,
+    password: &str,
+    options: &BrocadeOptions,
+) -> Result<russh::client::Handle<Client>, Error> {
+    let config = russh::client::Config {
+        preferred: options.ssh.preferred_algorithms.clone(),
+        ..Default::default()
+    };
+    let mut client = russh::client::connect(Arc::new(config), (ip, port), Client {}).await?;
+    if !client.authenticate_password(username, password).await? {
+        return Err(Error::AuthenticationError(
+            "ssh authentication failed".to_string(),
+        ));
+    }
+    Ok(client)
+}

demos/cncf-k8s-quebec-meetup-september-2025/.gitignore

@@ -0,0 +1,3 @@
+.terraform
+*.tfstate
+venv

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

@@ -0,0 +1,5 @@
+To build :
+
+```bash
+npx @marp-team/marp-cli@latest -w slides.md
+```

demos/cncf-k8s-quebec-meetup-september-2025/ansible/README.md

@@ -0,0 +1,9 @@
+To run this :
+
+```bash
+virtualenv venv
+source venv/bin/activate
+pip install ansible ansible-dev-tools
+ansible-lint download.yml
+ansible-playbook -i localhost download.yml
+```

demos/cncf-k8s-quebec-meetup-september-2025/ansible/download.yml

@@ -0,0 +1,8 @@
+- name: Test Ansible URL Validation
+  hosts: localhost
+  tasks:
+    - name: Download a file
+      ansible.builtin.get_url:
+        url: "http:/wikipedia.org/"
+        dest: "/tmp/ansible-test/wikipedia.html"
+        mode: '0900'

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

@@ -0,0 +1,241 @@
+---
+theme: uncover
+---
+
+# Voici l'histoire de Petit Poisson
+
+---
+
+<img src="./Happy_swimmer.jpg" width="600"/>
+
+---
+
+<img src="./happy_landscape_swimmer.jpg" width="1000"/>
+
+---
+
+<img src="./Happy_swimmer.jpg" width="200"/>
+
+<img src="./tryrust.org.png" width="600"/>
+
+[https://tryrust.org](https://tryrust.org)
+
+---
+
+<img src="./texto_deploy_prod_1.png" width="600"/>
+
+---
+
+<img src="./texto_deploy_prod_2.png" width="600"/>
+
+---
+
+<img src="./texto_deploy_prod_3.png" width="600"/>
+
+---
+
+<img src="./texto_deploy_prod_4.png" width="600"/>
+
+---
+
+## Demo time
+
+---
+
+<img src="./Happy_swimmer_sunglasses.jpg" width="1000"/>
+
+---
+
+<img src="./texto_download_wikipedia.png" width="600"/>
+
+---
+
+<img src="./ansible.jpg" width="200"/>
+
+## Ansible❓
+
+---
+
+<img src="./Happy_swimmer.jpg" width="200"/>
+
+```yaml
+- name: Download wikipedia
+  hosts: localhost
+  tasks:
+    - name: Download a file
+      ansible.builtin.get_url:
+        url: "https:/wikipedia.org/"
+        dest: "/tmp/ansible-test/wikipedia.html"
+        mode: '0900'
+```
+
+---
+
+<img src="./Happy_swimmer.jpg" width="200"/>
+
+```
+ansible-lint download.yml
+
+Passed: 0 failure(s), 0 warning(s) on 1 files. Last profile that met the validation criteria was 'production'.
+```
+
+---
+
+```
+git push
+```
+
+---
+
+<img src="./75_years_later.jpg" width="1100"/>
+
+---
+
+<img src="./texto_download_wikipedia_fail.png" width="600"/>
+
+---
+
+<img src="./Happy_swimmer_reversed.jpg" width="600"/>
+
+---
+
+<img src="./ansible_output_fail.jpg" width="1100"/>
+
+---
+
+<img src="./Happy_swimmer_reversed_1hit.jpg" width="600"/>
+
+---
+
+<img src="./ansible_crossed_out.jpg" width="400"/>
+
+---
+
+
+<img src="./terraform.jpg" width="400"/>
+
+## Terraform❓❗
+
+---
+
+<img src="./Happy_swimmer_reversed_1hit.jpg" width="200"/>
+<img src="./terraform.jpg" width="200"/>
+
+```tf
+provider "docker" {}
+
+resource "docker_network" "invalid_network" {
+  name = "my-invalid-network"
+
+  ipam_config {
+    subnet = "172.17.0.0/33"
+  }
+}
+```
+
+---
+
+<img src="./Happy_swimmer_reversed_1hit.jpg" width="100"/>
+<img src="./terraform.jpg" width="200"/>
+
+```
+terraform plan
+
+Terraform used the selected providers to generate the following execution plan.
+Resource actions are indicated with the following symbols:
+  + create
+
+Terraform will perform the following actions:
+
+  # docker_network.invalid_network will be created
+  + resource "docker_network" "invalid_network" {
+      + driver      = (known after apply)
+      + id          = (known after apply)
+      + internal    = (known after apply)
+      + ipam_driver = "default"
+      + name        = "my-invalid-network"
+      + options     = (known after apply)
+      + scope       = (known after apply)
+
+      + ipam_config {
+          + subnet   = "172.17.0.0/33"
+            # (2 unchanged attributes hidden)
+        }
+    }
+
+Plan: 1 to add, 0 to change, 0 to destroy.
+```
+
+---
+
+✅
+
+---
+
+```
+terraform apply
+```
+
+---
+
+```
+Plan: 1 to add, 0 to change, 0 to destroy.
+
+Do you want to perform these actions?
+  Terraform will perform the actions described above.
+  Only 'yes' will be accepted to approve.
+
+  Enter a value: yes
+```
+
+---
+
+```
+docker_network.invalid_network: Creating...
+╷
+│ Error: Unable to create network: Error response from daemon: invalid network config:
+│ invalid subnet 172.17.0.0/33: invalid CIDR block notation
+│
+│   with docker_network.invalid_network,
+│   on main.tf line 11, in resource "docker_network" "invalid_network":
+│   11: resource "docker_network" "invalid_network" {
+│
+╵
+```
+
+---
+
+
+<img src="./Happy_swimmer_reversed_fullhit.jpg" width="1100"/>
+
+---
+
+<img src="./ansible_crossed_out.jpg" width="300"/>
+<img src="./terraform_crossed_out.jpg" width="400"/>
+<img src="./Happy_swimmer_reversed_fullhit.jpg" width="300"/>
+
+---
+
+## Harmony❓❗
+
+---
+
+Demo time
+
+---
+
+<img src="./Happy_swimmer.jpg" width="300"/>
+
+---
+
+# 🎼 
+
+Harmony : [https://git.nationtech.io/nationtech/harmony](https://git.nationtech.io/nationtech/harmony)
+
+
+ <img src="./qrcode_gitea_nationtech.png" width="120"/>
+
+
+LinkedIn : [https://www.linkedin.com/in/jean-gabriel-gill-couture/](https://www.linkedin.com/in/jean-gabriel-gill-couture/)
+
+Courriel : [jg@nationtech.io](mailto:jg@nationtech.io)

demos/cncf-k8s-quebec-meetup-september-2025/terraform/.terraform.lock.hcl

@@ -0,0 +1,40 @@
+# This file is maintained automatically by "terraform init".
+# Manual edits may be lost in future updates.
+
+provider "registry.terraform.io/hashicorp/http" {
+  version = "3.5.0"
+  hashes = [
+    "h1:8bUoPwS4hahOvzCBj6b04ObLVFXCEmEN8T/5eOHmWOM=",
+    "zh:047c5b4920751b13425efe0d011b3a23a3be97d02d9c0e3c60985521c9c456b7",
+    "zh:157866f700470207561f6d032d344916b82268ecd0cf8174fb11c0674c8d0736",
+    "zh:1973eb9383b0d83dd4fd5e662f0f16de837d072b64a6b7cd703410d730499476",
+    "zh:212f833a4e6d020840672f6f88273d62a564f44acb0c857b5961cdb3bbc14c90",
+    "zh:2c8034bc039fffaa1d4965ca02a8c6d57301e5fa9fff4773e684b46e3f78e76a",
+    "zh:5df353fc5b2dd31577def9cc1a4ebf0c9a9c2699d223c6b02087a3089c74a1c6",
+    "zh:672083810d4185076c81b16ad13d1224b9e6ea7f4850951d2ab8d30fa6e41f08",
+    "zh:78d5eefdd9e494defcb3c68d282b8f96630502cac21d1ea161f53cfe9bb483b3",
+    "zh:7b4200f18abdbe39904b03537e1a78f21ebafe60f1c861a44387d314fda69da6",
+    "zh:843feacacd86baed820f81a6c9f7bd32cf302db3d7a0f39e87976ebc7a7cc2ee",
+    "zh:a9ea5096ab91aab260b22e4251c05f08dad2ed77e43e5e4fadcdfd87f2c78926",
+    "zh:d02b288922811739059e90184c7f76d45d07d3a77cc48d0b15fd3db14e928623",
+  ]
+}
+
+provider "registry.terraform.io/hashicorp/local" {
+  version = "2.5.3"
+  hashes = [
+    "h1:1Nkh16jQJMp0EuDmvP/96f5Unnir0z12WyDuoR6HjMo=",
+    "zh:284d4b5b572eacd456e605e94372f740f6de27b71b4e1fd49b63745d8ecd4927",
+    "zh:40d9dfc9c549e406b5aab73c023aa485633c1b6b730c933d7bcc2fa67fd1ae6e",
+    "zh:6243509bb208656eb9dc17d3c525c89acdd27f08def427a0dce22d5db90a4c8b",
+    "zh:78d5eefdd9e494defcb3c68d282b8f96630502cac21d1ea161f53cfe9bb483b3",
+    "zh:885d85869f927853b6fe330e235cd03c337ac3b933b0d9ae827ec32fa1fdcdbf",
+    "zh:bab66af51039bdfcccf85b25fe562cbba2f54f6b3812202f4873ade834ec201d",
+    "zh:c505ff1bf9442a889ac7dca3ac05a8ee6f852e0118dd9a61796a2f6ff4837f09",
+    "zh:d36c0b5770841ddb6eaf0499ba3de48e5d4fc99f4829b6ab66b0fab59b1aaf4f",
+    "zh:ddb6a407c7f3ec63efb4dad5f948b54f7f4434ee1a2607a49680d494b1776fe1",
+    "zh:e0dafdd4500bec23d3ff221e3a9b60621c5273e5df867bc59ef6b7e41f5c91f6",
+    "zh:ece8742fd2882a8fc9d6efd20e2590010d43db386b920b2a9c220cfecc18de47",
+    "zh:f4c6b3eb8f39105004cf720e202f04f57e3578441cfb76ca27611139bc116a82",
+  ]
+}

demos/cncf-k8s-quebec-meetup-september-2025/terraform/main.tf

@@ -0,0 +1,10 @@
+provider "http" {}
+
+data "http" "remote_file" {
+  url = "http:/example.com/file.txt"
+}
+
+resource "local_file" "downloaded_file" {
+  content  = data.http.remote_file.body
+  filename = "${path.module}/downloaded_file.txt"
+}

demos/cncf-k8s-quebec-meetup-september-2025/terraform_2/.terraform.lock.hcl

@@ -0,0 +1,24 @@
+# This file is maintained automatically by "terraform init".
+# Manual edits may be lost in future updates.
+
+provider "registry.terraform.io/kreuzwerker/docker" {
+  version     = "3.0.2"
+  constraints = "~> 3.0.1"
+  hashes = [
+    "h1:cT2ccWOtlfKYBUE60/v2/4Q6Stk1KYTNnhxSck+VPlU=",
+    "zh:15b0a2b2b563d8d40f62f83057d91acb02cd0096f207488d8b4298a59203d64f",
+    "zh:23d919de139f7cd5ebfd2ff1b94e6d9913f0977fcfc2ca02e1573be53e269f95",
+    "zh:38081b3fe317c7e9555b2aaad325ad3fa516a886d2dfa8605ae6a809c1072138",
+    "zh:4a9c5065b178082f79ad8160243369c185214d874ff5048556d48d3edd03c4da",
+    "zh:5438ef6afe057945f28bce43d76c4401254073de01a774760169ac1058830ac2",
+    "zh:60b7fadc287166e5c9873dfe53a7976d98244979e0ab66428ea0dea1ebf33e06",
+    "zh:61c5ec1cb94e4c4a4fb1e4a24576d5f39a955f09afb17dab982de62b70a9bdd1",
+    "zh:a38fe9016ace5f911ab00c88e64b156ebbbbfb72a51a44da3c13d442cd214710",
+    "zh:c2c4d2b1fd9ebb291c57f524b3bf9d0994ff3e815c0cd9c9bcb87166dc687005",
+    "zh:d567bb8ce483ab2cf0602e07eae57027a1a53994aba470fa76095912a505533d",
+    "zh:e83bf05ab6a19dd8c43547ce9a8a511f8c331a124d11ac64687c764ab9d5a792",
+    "zh:e90c934b5cd65516fbcc454c89a150bfa726e7cf1fe749790c7480bbeb19d387",
+    "zh:f05f167d2eaf913045d8e7b88c13757e3cf595dd5cd333057fdafc7c4b7fed62",
+    "zh:fcc9c1cea5ce85e8bcb593862e699a881bd36dffd29e2e367f82d15368659c3d",
+  ]
+}

demos/cncf-k8s-quebec-meetup-september-2025/terraform_2/main.tf

@@ -0,0 +1,17 @@
+terraform {
+  required_providers {
+    docker = {
+      source  = "kreuzwerker/docker"
+      version = "~> 3.0.1" # Adjust version as needed
+    }
+  }
+}
+provider "docker" {}
+
+resource "docker_network" "invalid_network" {
+  name = "my-invalid-network"
+
+  ipam_config {
+    subnet = "172.17.0.0/33"
+  }
+}

docs/doc-clone-and-restore-coreos.md

@@ -0,0 +1,133 @@
+## Working procedure to clone and restore CoreOS disk from OKD Cluster
+
+### **Step 1 - take a backup**
+```
+sudo dd if=/dev/old of=/dev/backup status=progress 
+```
+
+### **Step 2 - clone beginning of old disk to new**
+```
+sudo dd if=/dev/old of=/dev/backup status=progress count=1000 bs=1M
+```
+
+### **Step 3 - verify and modify disk partitions**
+list disk partitions
+```
+sgdisk -p /dev/new
+```
+if new disk is smaller than old disk and there is space on the xfs partition of the old disk, modify partitions of new disk
+```
+gdisk /dev/new
+```
+inside of gdisk commands
+```
+-v -> verify table
+-p -> print table
+-d -> select partition to delete partition
+-n -> recreate partition with same partition number as deleted partition
+```
+For end sector, either specify the new end or just press Enter for maximum available 
+When asked about partition type, enter the same type code (it will show the old one) 
+```
+p - >to verify 
+w -> to write
+```
+make xfs file system for new partition <new4>
+```
+sudo mkfs.xfs -f /dev/new4
+```
+
+### **Step 4 - copy old PARTUUID **
+
+**careful here**
+get old patuuid:
+```
+sgdisk -i <partition_number> /dev/old_disk  # Note the "Partition unique GUID"
+```
+get labels
+```
+sgdisk -p /dev/old_disk  # Shows partition names in the table
+
+blkid /dev/old_disk*  # Shows PARTUUIDs and labels for all partitions
+```
+set it on new disk
+```
+sgdisk -u <partition_number>:<old_partuuid> /dev/sdc
+```
+partition name:
+```
+sgdisk -c <partition_number>:"<old_name>" /dev/sdc
+```
+verify all:
+```
+lsblk -o NAME,SIZE,PARTUUID,PARTLABEL /dev/old_disk
+```
+
+### **Step 5 - Mount disks and copy files from old to new disk**
+
+mount files before copy:
+
+```
+mkdir -p /mnt/new
+mkdir -p /mnt/old
+mount /dev/old4 /mnt/old
+mount /dev/new4 /mnt/new
+```
+copy:
+
+with -n flag can run as dry-run
+```
+rsync -aAXHvn --numeric-ids /source/ /destination/
+```
+
+```
+rsync -aAXHv --numeric-ids /source/ /destination/
+```
+
+### **Step 6 - Set correct UUID for new partition 4**
+to set uuid with xfs_admin you must unmount first
+
+unmount old devices
+```
+umount /mnt/new
+umount /mnt/old
+```
+
+to set correct uuid for partition 4
+```
+blkid /dev/old4
+```
+```
+xfs_admin -U <old_uuid> /dev/new_partition
+```
+to set labels
+get it 
+```
+sgdisk -i 4 /dev/sda | grep "Partition name"
+```
+set it
+```
+sgdisk -c 4:"<label_name>" /dev/sdc
+
+or
+
+(check existing with xfs_admin -l /dev/old_partition)
+Use xfs_admin -L <label> /dev/new_partition 
+```
+
+### **Step 7 - Verify**
+
+verify everything:
+```
+sgdisk -p /dev/sda  # Old disk
+sgdisk -p /dev/sdc  # New disk
+```
+```
+lsblk -o NAME,SIZE,PARTUUID,PARTLABEL /dev/sda
+lsblk -o NAME,SIZE,PARTUUID,PARTLABEL /dev/sdc
+```
+```
+blkid /dev/sda* | grep UUID=
+blkid /dev/sdc* | grep UUID=
+```
+

docs/doc-remove-worker-flag.md

@@ -0,0 +1,56 @@
+## **Remove Worker flag from OKD Control Planes** 
+
+### **Context**
+On OKD user provisioned infrastructure the control plane nodes can have the flag node-role.kubernetes.io/worker which allows non critical workloads to be scheduled on the control-planes
+
+### **Observed Symptoms**
+- After adding HAProxy servers to the backend each back end appears down 
+- Traffic is redirected to the control planes instead of workers
+- The pods router-default are incorrectly applied on the control planes rather than on the workers
+- Pods are being scheduled on the control planes causing cluster instability
+
+```
+  ss -tlnp | grep 80
+```
+- shows process haproxy  is listening at 0.0.0.0:80 on cps
+- same problem for port 443
+- In namespace rook-ceph certain pods are deploted on cps rather than on worker nodes
+
+ ### **Cause**
+ - when intalling UPI, the roles (master, worker) are not managed by the Machine Config operator and the cps are made schedulable by default.
+
+ ### **Diagnostic**
+check node labels:
+```
+   oc get nodes --show-labels | grep control-plane
+```
+Inspecter kubelet configuration:
+
+```
+cat /etc/systemd/system/kubelet.service
+```
+
+find the line:
+```
+   --node-labels=node-role.kubernetes.io/control-plane,node-role.kubernetes.io/master,node-role.kubernetes.io/worker
+```
+   → presence of label worker confirms the problem.
+
+Verify the flag doesnt come from MCO
+```
+   oc get machineconfig | grep rendered-master
+```
+
+**Solution:**
+To make the control planes non schedulable you must patch the cluster scheduler resource
+
+```	
+oc patch scheduler cluster --type merge -p '{"spec":{"mastersSchedulable":false}}'
+```
+after the patch is applied the workloads can be deplaced by draining the nodes
+
+```
+oc adm cordon <cp-node>
+oc adm drain <cp-node> --ignore-daemonsets –delete-emptydir-data
+```
+

docs/modules/Multisite_PostgreSQL.md

@@ -0,0 +1,105 @@
+# Design Document: Harmony PostgreSQL Module
+
+**Status:** Draft
+**Last Updated:** 2025-12-01
+**Context:** Multi-site Data Replication & Orchestration
+
+## 1. Overview
+
+The Harmony PostgreSQL Module provides a high-level abstraction for deploying and managing high-availability PostgreSQL clusters across geographically distributed Kubernetes/OKD sites.
+
+Instead of manually configuring complex replication slots, firewalls, and operator settings on each cluster, users define a single intent (a **Score**), and Harmony orchestrates the underlying infrastructure (the **Arrangement**) to establish a Primary-Replica architecture.
+
+Currently, the implementation relies on the **CloudNativePG (CNPG)** operator as the backing engine.
+
+## 2. Architecture
+
+### 2.1 The Abstraction Model
+Following **ADR 003 (Infrastructure Abstraction)**, Harmony separates the *intent* from the *implementation*.
+
+1.  **The Score (Intent):** The user defines a `MultisitePostgreSQL` resource. This describes *what* is needed (e.g., "A Postgres 15 cluster with 10GB storage, Primary on Site A, Replica on Site B").
+2.  **The Interpret (Action):** Harmony MultisitePostgreSQLInterpret processes this Score and orchestrates the deployment on both sites to reach the state defined in the Score.
+3.  **The Capability (Implementation):** The PostgreSQL Capability is implemented by the K8sTopology and the interpret can deploy it, configure it and fetch information about it. The concrete implementation will rely on the mature CloudnativePG operator to manage all the Kubernetes resources required.
+
+### 2.2 Network Connectivity (TLS Passthrough)
+
+One of the critical challenges in multi-site orchestration is secure connectivity between clusters that may have dynamic IPs or strict firewalls.
+
+To solve this, we utilize **OKD/OpenShift Routes with TLS Passthrough**.
+
+*   **Mechanism:** The Primary site exposes a `Route` configured for `termination: passthrough`.
+*   **Routing:** The OpenShift HAProxy router inspects the **SNI (Server Name Indication)** header of the incoming TCP connection to route traffic to the correct PostgreSQL Pod.
+*   **Security:** SSL is **not** terminated at the ingress router. The encrypted stream is passed directly to the PostgreSQL instance. Mutual TLS (mTLS) authentication is handled natively by CNPG between the Primary and Replica instances.
+*   **Dynamic IPs:** Because connections are established via DNS hostnames (the Route URL), this architecture is resilient to dynamic IP changes at the Primary site.
+
+#### Traffic Flow Diagram
+
+```text
+[ Site B: Replica ]                 [ Site A: Primary ]
+      |                                     |
+(CNPG Instance) --[Encrypted TCP]--> (OKD HAProxy Router)
+      |           (Port 443)                |
+      |                                     |
+      |                            [SNI Inspection]
+      |                                     |
+      |                                     v
+      |                            (PostgreSQL Primary Pod)
+      |                                   (Port 5432)
+```
+
+## 3. Design Decisions
+
+### Why CloudNativePG?
+We selected CloudNativePG because it relies exclusively on standard Kubernetes primitives and uses the native PostgreSQL replication protocol (WAL shipping/Streaming). This aligns with Harmony's goal of being "K8s Native."
+
+### Why TLS Passthrough instead of VPN/NodePort?
+*   **NodePort:** Requires static IPs and opening non-standard ports on the firewall, which violates our security constraints.
+*   **VPN (e.g., Wireguard/Tailscale):** While secure, it introduces significant complexity (sidecars, key management) and external dependencies.
+*   **TLS Passthrough:** Leverages the existing Ingress/Router infrastructure already present in OKD. It requires zero additional software and respects multi-tenancy (Routes are namespaced).
+
+### Configuration Philosophy (YAGNI)
+The current design exposes a **generic configuration surface**. Users can configure standard parameters (Storage size, CPU/Memory requests, Postgres version).
+
+**We explicitly do not expose advanced CNPG or PostgreSQL configurations at this stage.**
+
+*   **Reasoning:** We aim to keep the API surface small and manageable.
+*   **Future Path:** We plan to implement a "pass-through" mechanism to allow sending raw config maps or custom parameters to the underlying engine (CNPG) *only when a concrete use case arises*. Until then, we adhere to the **YAGNI (You Ain't Gonna Need It)** principle to avoid premature optimization and API bloat.
+
+## 4. Usage Guide
+
+To deploy a multi-site cluster, apply the `MultisitePostgreSQL` resource to the Harmony Control Plane.
+
+### Example Manifest
+
+```yaml
+apiVersion: harmony.io/v1alpha1
+kind: MultisitePostgreSQL
+metadata:
+  name: finance-db
+  namespace: tenant-a
+spec:
+  version: "15"
+  storage: "10Gi"
+  resources:
+    requests:
+      cpu: "500m"
+      memory: "1Gi"
+  
+  # Topology Definition
+  topology:
+    primary:
+      site: "site-paris" # The name of the cluster in Harmony
+    replicas:
+      - site: "site-newyork"
+```
+
+### What happens next?
+1.  Harmony detects the CR.
+2.  **On Site Paris:** It deploys a CNPG Cluster (Primary) and creates a Passthrough Route `postgres-finance-db.apps.site-paris.example.com`.
+3.  **On Site New York:** It deploys a CNPG Cluster (Replica) configured with `externalClusters` pointing to the Paris Route.
+4.  Data begins replicating immediately over the encrypted channel.
+
+## 5. Troubleshooting
+
+*   **Connection Refused:** Ensure the Primary site's Route is successfully admitted by the Ingress Controller.
+*   **Certificate Errors:** CNPG manages mTLS automatically. If errors persist, ensure the CA secrets were correctly propagated by Harmony from Primary to Replica namespaces.

examples/application_monitoring_with_tenant/src/main.rs

@@ -27,6 +27,7 @@ async fn main() {
     };
     let application = Arc::new(RustWebapp {
         name: "example-monitoring".to_string(),
+        dns: "example-monitoring.harmony.mcd".to_string(),
         project_root: PathBuf::from("./examples/rust/webapp"),
         framework: Some(RustWebFramework::Leptos),
         service_port: 3000,

examples/brocade_snmp_server/Cargo.toml

@@ -0,0 +1,20 @@
+[package]
+name = "brocade-snmp-server"
+edition = "2024"
+version.workspace = true
+readme.workspace = true
+license.workspace = true
+
+[dependencies]
+harmony = { path = "../../harmony" }
+brocade = { path = "../../brocade" }
+harmony_secret = { path = "../../harmony_secret" }
+harmony_cli = { path = "../../harmony_cli" }
+harmony_types = { path = "../../harmony_types" }
+harmony_macros = { path = "../../harmony_macros" }
+tokio = { workspace = true }
+log = { workspace = true }
+env_logger = { workspace = true }
+url = { workspace = true }
+base64.workspace = true
+serde.workspace = true

examples/brocade_snmp_server/src/main.rs

@@ -0,0 +1,22 @@
+use std::net::{IpAddr, Ipv4Addr};
+
+use harmony::{
+    inventory::Inventory, modules::brocade::BrocadeEnableSnmpScore, topology::K8sAnywhereTopology,
+};
+
+#[tokio::main]
+async fn main() {
+    let brocade_snmp_server = BrocadeEnableSnmpScore {
+        switch_ips: vec![IpAddr::V4(Ipv4Addr::new(192, 168, 1, 111))],
+        dry_run: true,
+    };
+
+    harmony_cli::run(
+        Inventory::autoload(),
+        K8sAnywhereTopology::from_env(),
+        vec![Box::new(brocade_snmp_server)],
+        None,
+    )
+    .await
+    .unwrap();
+}

examples/brocade_switch/Cargo.toml

@@ -0,0 +1,19 @@
+[package]
+name = "brocade-switch"
+edition = "2024"
+version.workspace = true
+readme.workspace = true
+license.workspace = true
+
+[dependencies]
+harmony = { path = "../../harmony" }
+harmony_cli = { path = "../../harmony_cli" }
+harmony_macros = { path = "../../harmony_macros" }
+harmony_types = { path = "../../harmony_types" }
+tokio.workspace = true
+url.workspace = true
+async-trait.workspace = true
+serde.workspace = true
+log.workspace = true
+env_logger.workspace = true
+brocade = { path = "../../brocade" }

examples/brocade_switch/src/main.rs

@@ -0,0 +1,157 @@
+use std::str::FromStr;
+
+use async_trait::async_trait;
+use brocade::{BrocadeOptions, PortOperatingMode};
+use harmony::{
+    data::Version,
+    infra::brocade::BrocadeSwitchClient,
+    interpret::{Interpret, InterpretError, InterpretName, InterpretStatus, Outcome},
+    inventory::Inventory,
+    score::Score,
+    topology::{
+        HostNetworkConfig, PortConfig, PreparationError, PreparationOutcome, Switch, SwitchClient,
+        SwitchError, Topology,
+    },
+};
+use harmony_macros::ip;
+use harmony_types::{id::Id, net::MacAddress, switch::PortLocation};
+use log::{debug, info};
+use serde::Serialize;
+
+#[tokio::main]
+async fn main() {
+    let switch_score = BrocadeSwitchScore {
+        port_channels_to_clear: vec![
+            Id::from_str("17").unwrap(),
+            Id::from_str("19").unwrap(),
+            Id::from_str("18").unwrap(),
+        ],
+        ports_to_configure: vec![
+            (PortLocation(2, 0, 17), PortOperatingMode::Trunk),
+            (PortLocation(2, 0, 19), PortOperatingMode::Trunk),
+            (PortLocation(1, 0, 18), PortOperatingMode::Trunk),
+        ],
+    };
+    harmony_cli::run(
+        Inventory::autoload(),
+        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/cli/src/main.rs

@@ -2,7 +2,7 @@ use harmony::{
     inventory::Inventory,
     modules::{
         dummy::{ErrorScore, PanicScore, SuccessScore},
-        inventory::LaunchDiscoverInventoryAgentScore,
+        inventory::{HarmonyDiscoveryStrategy, LaunchDiscoverInventoryAgentScore},
     },
     topology::LocalhostTopology,
 };
@@ -18,6 +18,7 @@ async fn main() {
             Box::new(PanicScore {}),
             Box::new(LaunchDiscoverInventoryAgentScore {
                 discovery_timeout: Some(10),
+                discovery_strategy: HarmonyDiscoveryStrategy::MDNS,
             }),
         ],
         None,

examples/harmony_inventory_builder/Cargo.toml

@@ -0,0 +1,15 @@
+[package]
+name = "harmony_inventory_builder"
+edition = "2024"
+version.workspace = true
+readme.workspace = true
+license.workspace = true
+
+[dependencies]
+harmony = { path = "../../harmony" }
+harmony_cli = { path = "../../harmony_cli" }
+harmony_macros = { path = "../../harmony_macros" }
+harmony_types = { path = "../../harmony_types" }
+tokio.workspace = true
+url.workspace = true
+cidr.workspace = true

examples/harmony_inventory_builder/build_docker.sh

@@ -0,0 +1,11 @@
+cargo build -p harmony_inventory_builder --release --target x86_64-unknown-linux-musl
+
+SCRIPT_DIR="$(dirname ${0})"
+
+cd "${SCRIPT_DIR}/docker/"
+
+cp ../../../target/x86_64-unknown-linux-musl/release/harmony_inventory_builder .
+
+docker build . -t hub.nationtech.io/harmony/harmony_inventory_builder
+
+docker push hub.nationtech.io/harmony/harmony_inventory_builder

examples/harmony_inventory_builder/docker/Dockerfile

@@ -0,0 +1,10 @@
+FROM debian:12-slim
+
+RUN mkdir  /app
+WORKDIR /app/
+
+COPY harmony_inventory_builder /app/
+
+ENV RUST_LOG=info
+
+CMD ["sleep", "infinity"]

examples/harmony_inventory_builder/src/main.rs

@@ -0,0 +1,36 @@
+use harmony::{
+    inventory::{HostRole, Inventory},
+    modules::inventory::{DiscoverHostForRoleScore, HarmonyDiscoveryStrategy},
+    topology::LocalhostTopology,
+};
+use harmony_macros::cidrv4;
+
+#[tokio::main]
+async fn main() {
+    let discover_worker = DiscoverHostForRoleScore {
+        role: HostRole::Worker,
+        number_desired_hosts: 3,
+        discovery_strategy: HarmonyDiscoveryStrategy::SUBNET {
+            cidr: cidrv4!("192.168.0.1/25"),
+            port: 25000,
+        },
+    };
+
+    let discover_control_plane = DiscoverHostForRoleScore {
+        role: HostRole::ControlPlane,
+        number_desired_hosts: 3,
+        discovery_strategy: HarmonyDiscoveryStrategy::SUBNET {
+            cidr: cidrv4!("192.168.0.1/25"),
+            port: 25000,
+        },
+    };
+
+    harmony_cli::run(
+        Inventory::autoload(),
+        LocalhostTopology::new(),
+        vec![Box::new(discover_worker), Box::new(discover_control_plane)],
+        None,
+    )
+    .await
+    .unwrap();
+}

examples/multisite_postgres/Cargo.toml

@@ -0,0 +1,18 @@
+[package]
+name = "example-multisite-postgres"
+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 }

examples/multisite_postgres/env_example.sh

@@ -0,0 +1,3 @@
+export HARMONY_FAILOVER_TOPOLOGY_K8S_PRIMARY="context=default/api-your-openshift-cluster:6443/kube:admin"
+export HARMONY_FAILOVER_TOPOLOGY_K8S_REPLICA="context=someuser/somecluster"
+export RUST_LOG="harmony=debug"

examples/multisite_postgres/src/main.rs

@@ -0,0 +1,28 @@
+use harmony::{
+    inventory::Inventory,
+    modules::postgresql::{PublicPostgreSQLScore, capability::PostgreSQLConfig},
+    topology::{FailoverTopology, K8sAnywhereTopology},
+};
+
+#[tokio::main]
+async fn main() {
+    // env_logger::init();
+    let postgres = PublicPostgreSQLScore {
+        config: PostgreSQLConfig {
+            cluster_name: "harmony-postgres-example".to_string(), // Override default name
+            namespace: "harmony-public-postgres".to_string(),
+            ..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(
+        Inventory::autoload(),
+        FailoverTopology::<K8sAnywhereTopology>::from_env(),
+        vec![Box::new(postgres)],
+        None,
+    )
+    .await
+    .unwrap();
+}

examples/nanodc/Cargo.toml

@@ -17,3 +17,5 @@ harmony_secret = { path = "../../harmony_secret" }
 log = { workspace = true }
 env_logger = { workspace = true }
 url = { workspace = true }
+serde = { workspace = true }
+brocade = { path = "../../brocade" }

examples/nanodc/src/main.rs

@@ -1,14 +1,15 @@
 use std::{
     net::{IpAddr, Ipv4Addr},
-    sync::Arc,
+    sync::{Arc, OnceLock},
 };
 
+use brocade::BrocadeOptions;
 use cidr::Ipv4Cidr;
 use harmony::{
     config::secret::SshKeyPair,
     data::{FileContent, FilePath},
     hardware::{HostCategory, Location, PhysicalHost, SwitchGroup},
-    infra::opnsense::OPNSenseManagementInterface,
+    infra::{brocade::BrocadeSwitchClient, opnsense::OPNSenseManagementInterface},
     inventory::Inventory,
     modules::{
         http::StaticFilesHttpScore,
@@ -22,8 +23,9 @@ use harmony::{
     topology::{LogicalHost, UnmanagedRouter},
 };
 use harmony_macros::{ip, mac_address};
-use harmony_secret::SecretManager;
+use harmony_secret::{Secret, SecretManager};
 use harmony_types::net::Url;
+use serde::{Deserialize, Serialize};
 
 #[tokio::main]
 async fn main() {
@@ -32,6 +34,26 @@ async fn main() {
         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,
     );
@@ -39,6 +61,7 @@ async fn main() {
     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(
@@ -83,7 +106,9 @@ async fn main() {
                 name: "wk2".to_string(),
             },
         ],
-        switch: vec![],
+        node_exporter: opnsense.clone(),
+        switch_client: switch_client.clone(),
+        network_manager: OnceLock::new(),
     };
 
     let inventory = Inventory {
@@ -166,3 +191,9 @@ async fn main() {
     .await
     .unwrap();
 }
+
+#[derive(Secret, Serialize, Deserialize, Debug)]
+pub struct BrocadeSwitchAuth {
+    pub username: String,
+    pub password: String,
+}

examples/nats/Cargo.toml

@@ -0,0 +1,18 @@
+[package]
+name = "example-nats"
+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 }

examples/nats/src/main.rs

@@ -0,0 +1,63 @@
+use std::str::FromStr;
+
+use harmony::{
+    inventory::Inventory,
+    modules::helm::chart::{HelmChartScore, HelmRepository, NonBlankString},
+    topology::K8sAnywhereTopology,
+};
+use harmony_macros::hurl;
+use log::info;
+
+#[tokio::main]
+async fn main() {
+    // env_logger::init();
+    let values_yaml = Some(
+        r#"config:
+  cluster:
+    enabled: true
+    replicas: 3
+  jetstream:
+    enabled: true
+    fileStorage:
+      enabled: true
+      size: 10Gi
+      storageDirectory: /data/jetstream
+  leafnodes:
+    enabled: false
+    # port: 7422
+  gateway:
+    enabled: false
+    # name: my-gateway
+    # port: 7522"#
+            .to_string(),
+    );
+    let namespace = "nats";
+    let nats = HelmChartScore {
+        namespace: Some(NonBlankString::from_str(namespace).unwrap()),
+        release_name: NonBlankString::from_str("nats").unwrap(),
+        chart_name: NonBlankString::from_str("nats/nats").unwrap(),
+        chart_version: None,
+        values_overrides: None,
+        values_yaml,
+        create_namespace: true,
+        install_only: true,
+        repository: Some(HelmRepository::new(
+            "nats".to_string(),
+            hurl!("https://nats-io.github.io/k8s/helm/charts/"),
+            true,
+        )),
+    };
+
+    harmony_cli::run(
+        Inventory::autoload(),
+        K8sAnywhereTopology::from_env(),
+        vec![Box::new(nats)],
+        None,
+    )
+    .await
+    .unwrap();
+
+    info!(
+        "Enjoy! You can test your nats cluster by running : `kubectl exec -n {namespace} -it deployment/nats-box -- nats pub test hi`"
+    );
+}

examples/okd_installation/Cargo.toml

@@ -19,3 +19,4 @@ log = { workspace = true }
 env_logger = { workspace = true }
 url = { workspace = true }
 serde.workspace = true
+brocade = { path = "../../brocade" }

examples/okd_installation/src/main.rs

@@ -4,7 +4,10 @@ use crate::topology::{get_inventory, get_topology};
 use harmony::{
     config::secret::SshKeyPair,
     data::{FileContent, FilePath},
-    modules::okd::{installation::OKDInstallationPipeline, ipxe::OKDIpxeScore},
+    modules::{
+        inventory::HarmonyDiscoveryStrategy,
+        okd::{installation::OKDInstallationPipeline, ipxe::OKDIpxeScore},
+    },
     score::Score,
     topology::HAClusterTopology,
 };
@@ -26,7 +29,8 @@ async fn main() {
         },
     })];
 
-    scores.append(&mut OKDInstallationPipeline::get_all_scores().await);
+    scores
+        .append(&mut OKDInstallationPipeline::get_all_scores(HarmonyDiscoveryStrategy::MDNS).await);
 
     harmony_cli::run(inventory, topology, scores, None)
         .await

examples/okd_installation/src/topology.rs

@@ -1,14 +1,18 @@
+use brocade::BrocadeOptions;
 use cidr::Ipv4Cidr;
 use harmony::{
-    hardware::{FirewallGroup, HostCategory, Location, PhysicalHost, SwitchGroup},
-    infra::opnsense::OPNSenseManagementInterface,
+    hardware::{Location, SwitchGroup},
+    infra::{brocade::BrocadeSwitchClient, opnsense::OPNSenseManagementInterface},
     inventory::Inventory,
     topology::{HAClusterTopology, LogicalHost, UnmanagedRouter},
 };
 use harmony_macros::{ip, ipv4};
 use harmony_secret::{Secret, SecretManager};
 use serde::{Deserialize, Serialize};
-use std::{net::IpAddr, sync::Arc};
+use std::{
+    net::IpAddr,
+    sync::{Arc, OnceLock},
+};
 
 #[derive(Secret, Serialize, Deserialize, Debug, PartialEq)]
 struct OPNSenseFirewallConfig {
@@ -22,6 +26,26 @@ pub async fn get_topology() -> HAClusterTopology {
         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!("192.168.1.101")]; // 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 config = SecretManager::get_or_prompt::<OPNSenseFirewallConfig>().await;
     let config = config.unwrap();
 
@@ -38,6 +62,7 @@ pub async fn get_topology() -> HAClusterTopology {
     let gateway_ipv4 = ipv4!("192.168.1.1");
     let gateway_ip = IpAddr::V4(gateway_ipv4);
     harmony::topology::HAClusterTopology {
+        kubeconfig: None,
         domain_name: "demo.harmony.mcd".to_string(),
         router: Arc::new(UnmanagedRouter::new(
             gateway_ip,
@@ -58,7 +83,9 @@ pub async fn get_topology() -> HAClusterTopology {
             name: "bootstrap".to_string(),
         },
         workers: vec![],
-        switch: vec![],
+        node_exporter: opnsense.clone(),
+        switch_client: switch_client.clone(),
+        network_manager: OnceLock::new(),
     }
 }
 
@@ -75,3 +102,9 @@ pub fn get_inventory() -> Inventory {
         control_plane_host: vec![],
     }
 }
+
+#[derive(Secret, Serialize, Deserialize, Debug)]
+pub struct BrocadeSwitchAuth {
+    pub username: String,
+    pub password: String,
+}

examples/okd_pxe/Cargo.toml

@@ -19,3 +19,4 @@ log = { workspace = true }
 env_logger = { workspace = true }
 url = { workspace = true }
 serde.workspace = true
+brocade = { path = "../../brocade" }

examples/okd_pxe/src/topology.rs

@@ -1,14 +1,19 @@
+use brocade::BrocadeOptions;
 use cidr::Ipv4Cidr;
 use harmony::{
     config::secret::OPNSenseFirewallCredentials,
     hardware::{Location, SwitchGroup},
-    infra::opnsense::OPNSenseManagementInterface,
+    infra::{brocade::BrocadeSwitchClient, opnsense::OPNSenseManagementInterface},
     inventory::Inventory,
     topology::{HAClusterTopology, LogicalHost, UnmanagedRouter},
 };
 use harmony_macros::{ip, ipv4};
-use harmony_secret::SecretManager;
-use std::{net::IpAddr, sync::Arc};
+use harmony_secret::{Secret, SecretManager};
+use serde::{Deserialize, Serialize};
+use std::{
+    net::IpAddr,
+    sync::{Arc, OnceLock},
+};
 
 pub async fn get_topology() -> HAClusterTopology {
     let firewall = harmony::topology::LogicalHost {
@@ -16,6 +21,26 @@ pub async fn get_topology() -> HAClusterTopology {
         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!("192.168.1.101")]; // 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 config = SecretManager::get_or_prompt::<OPNSenseFirewallCredentials>().await;
     let config = config.unwrap();
 
@@ -32,6 +57,7 @@ pub async fn get_topology() -> HAClusterTopology {
     let gateway_ipv4 = ipv4!("192.168.1.1");
     let gateway_ip = IpAddr::V4(gateway_ipv4);
     harmony::topology::HAClusterTopology {
+        kubeconfig: None,
         domain_name: "demo.harmony.mcd".to_string(),
         router: Arc::new(UnmanagedRouter::new(
             gateway_ip,
@@ -52,7 +78,9 @@ pub async fn get_topology() -> HAClusterTopology {
             name: "cp0".to_string(),
         },
         workers: vec![],
-        switch: vec![],
+        node_exporter: opnsense.clone(),
+        switch_client: switch_client.clone(),
+        network_manager: OnceLock::new(),
     }
 }
 
@@ -69,3 +97,9 @@ pub fn get_inventory() -> Inventory {
         control_plane_host: vec![],
     }
 }
+
+#[derive(Secret, Serialize, Deserialize, Debug)]
+pub struct BrocadeSwitchAuth {
+    pub username: String,
+    pub password: String,
+}

examples/openbao/Cargo.toml

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

examples/openbao/README.md

@@ -0,0 +1,7 @@
+To install an openbao instance with harmony simply `cargo run -p example-openbao` .
+
+Depending on your environement configuration, it will either install a k3d cluster locally and deploy on it, or install to a remote cluster.
+
+Then follow the openbao documentation to initialize and unseal, this will make openbao usable.
+
+https://openbao.org/docs/platform/k8s/helm/run/

examples/openbao/src/main.rs

@@ -0,0 +1,67 @@
+use std::str::FromStr;
+
+use harmony::{
+    inventory::Inventory,
+    modules::helm::chart::{HelmChartScore, HelmRepository, NonBlankString},
+    topology::K8sAnywhereTopology,
+};
+use harmony_macros::hurl;
+
+#[tokio::main]
+async fn main() {
+    let values_yaml = Some(
+        r#"server:
+  standalone:
+    enabled: true
+    config: |
+      listener "tcp" {
+        tls_disable = true
+        address = "[::]:8200"
+        cluster_address = "[::]:8201"
+      }
+
+      storage "file" {
+        path = "/openbao/data"
+      }
+
+  service:
+    enabled: true
+
+  dataStorage:
+    enabled: true
+    size: 10Gi
+    storageClass: null
+    accessMode: ReadWriteOnce
+
+  auditStorage:
+    enabled: true
+    size: 10Gi
+    storageClass: null
+    accessMode: ReadWriteOnce"#
+            .to_string(),
+    );
+    let openbao = HelmChartScore {
+        namespace: Some(NonBlankString::from_str("openbao").unwrap()),
+        release_name: NonBlankString::from_str("openbao").unwrap(),
+        chart_name: NonBlankString::from_str("openbao/openbao").unwrap(),
+        chart_version: None,
+        values_overrides: None,
+        values_yaml,
+        create_namespace: true,
+        install_only: true,
+        repository: Some(HelmRepository::new(
+            "openbao".to_string(),
+            hurl!("https://openbao.github.io/openbao-helm"),
+            true,
+        )),
+    };
+
+    harmony_cli::run(
+        Inventory::autoload(),
+        K8sAnywhereTopology::from_env(),
+        vec![Box::new(openbao)],
+        None,
+    )
+    .await
+    .unwrap();
+}

examples/operatorhub_catalog/Cargo.toml

@@ -0,0 +1,18 @@
+[package]
+name = "example-operatorhub-catalogsource"
+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 }

examples/operatorhub_catalog/src/main.rs

@@ -0,0 +1,22 @@
+use std::str::FromStr;
+
+use harmony::{
+    inventory::Inventory,
+    modules::{k8s::apps::OperatorHubCatalogSourceScore, postgresql::CloudNativePgOperatorScore},
+    topology::K8sAnywhereTopology,
+};
+
+#[tokio::main]
+async fn main() {
+    let operatorhub_catalog = OperatorHubCatalogSourceScore::default();
+    let cnpg_operator = CloudNativePgOperatorScore::default();
+
+    harmony_cli::run(
+        Inventory::autoload(),
+        K8sAnywhereTopology::from_env(),
+        vec![Box::new(operatorhub_catalog), Box::new(cnpg_operator)],
+        None,
+    )
+    .await
+    .unwrap();
+}

examples/opnsense/Cargo.toml

@@ -16,3 +16,6 @@ harmony_macros = { path = "../../harmony_macros" }
 log = { workspace = true }
 env_logger = { workspace = true }
 url = { workspace = true }
+harmony_secret = { path = "../../harmony_secret" }
+brocade = { path = "../../brocade" }
+serde = { workspace = true }

examples/opnsense/src/main.rs

@@ -1,12 +1,13 @@
 use std::{
     net::{IpAddr, Ipv4Addr},
-    sync::Arc,
+    sync::{Arc, OnceLock},
 };
 
+use brocade::BrocadeOptions;
 use cidr::Ipv4Cidr;
 use harmony::{
     hardware::{HostCategory, Location, PhysicalHost, SwitchGroup},
-    infra::opnsense::OPNSenseManagementInterface,
+    infra::{brocade::BrocadeSwitchClient, opnsense::OPNSenseManagementInterface},
     inventory::Inventory,
     modules::{
         dummy::{ErrorScore, PanicScore, SuccessScore},
@@ -18,7 +19,9 @@ use harmony::{
     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() {
@@ -27,6 +30,26 @@ async fn main() {
         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,
     );
@@ -34,6 +57,7 @@ async fn main() {
     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,
@@ -54,7 +78,9 @@ async fn main() {
             name: "cp0".to_string(),
         },
         workers: vec![],
-        switch: vec![],
+        node_exporter: opnsense.clone(),
+        switch_client: switch_client.clone(),
+        network_manager: OnceLock::new(),
     };
 
     let inventory = Inventory {
@@ -109,3 +135,9 @@ async fn main() {
     .await
     .unwrap();
 }
+
+#[derive(Secret, Serialize, Deserialize, Debug)]
+pub struct BrocadeSwitchAuth {
+    pub username: String,
+    pub password: String,
+}

examples/opnsense_node_exporter/Cargo.toml

@@ -0,0 +1,21 @@
+[package]
+name = "example-opnsense-node-exporter"
+edition = "2024"
+version.workspace = true
+readme.workspace = true
+license.workspace = true
+
+[dependencies]
+harmony = { path = "../../harmony" }
+harmony_cli = { path = "../../harmony_cli" }
+harmony_types = { path = "../../harmony_types" }
+harmony_secret = { path = "../../harmony_secret" }
+harmony_secret_derive = { path = "../../harmony_secret_derive" }
+cidr = { workspace = true }
+tokio = { workspace = true }
+harmony_macros = { path = "../../harmony_macros" }
+log = { workspace = true }
+env_logger = { workspace = true }
+url = { workspace = true }
+serde.workspace = true
+async-trait.workspace = true

examples/opnsense_node_exporter/src/main.rs

@@ -0,0 +1,80 @@
+use std::{
+    net::{IpAddr, Ipv4Addr},
+    sync::Arc,
+};
+
+use async_trait::async_trait;
+use cidr::Ipv4Cidr;
+use harmony::{
+    executors::ExecutorError,
+    hardware::{HostCategory, Location, PhysicalHost, SwitchGroup},
+    infra::opnsense::OPNSenseManagementInterface,
+    inventory::Inventory,
+    modules::opnsense::node_exporter::NodeExporterScore,
+    topology::{
+        HAClusterTopology, LogicalHost, PreparationError, PreparationOutcome, Topology,
+        UnmanagedRouter, node_exporter::NodeExporter,
+    },
+};
+use harmony_macros::{ip, ipv4, mac_address};
+
+#[derive(Debug)]
+struct OpnSenseTopology {
+    node_exporter: Arc<dyn NodeExporter>,
+}
+
+#[async_trait]
+impl Topology for OpnSenseTopology {
+    async fn ensure_ready(&self) -> Result<PreparationOutcome, PreparationError> {
+        Ok(PreparationOutcome::Success {
+            details: "Success".to_string(),
+        })
+    }
+    fn name(&self) -> &str {
+        "OpnsenseTopology"
+    }
+}
+
+#[async_trait]
+impl NodeExporter for OpnSenseTopology {
+    async fn ensure_initialized(&self) -> Result<(), ExecutorError> {
+        self.node_exporter.ensure_initialized().await
+    }
+
+    async fn commit_config(&self) -> Result<(), ExecutorError> {
+        self.node_exporter.commit_config().await
+    }
+
+    async fn reload_restart(&self) -> Result<(), ExecutorError> {
+        self.node_exporter.reload_restart().await
+    }
+}
+
+#[tokio::main]
+async fn main() {
+    let firewall = harmony::topology::LogicalHost {
+        ip: ip!("192.168.1.1"),
+        name: String::from("fw0"),
+    };
+
+    let opnsense = Arc::new(
+        harmony::infra::opnsense::OPNSenseFirewall::new(firewall, None, "root", "opnsense").await,
+    );
+
+    let topology = OpnSenseTopology {
+        node_exporter: opnsense.clone(),
+    };
+
+    let inventory = Inventory::empty();
+
+    let node_exporter_score = NodeExporterScore {};
+
+    harmony_cli::run(
+        inventory,
+        topology,
+        vec![Box::new(node_exporter_score)],
+        None,
+    )
+    .await
+    .unwrap();
+}

examples/postgresql/Cargo.toml

@@ -0,0 +1,18 @@
+[package]
+name = "example-postgresql"
+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 }

examples/postgresql/src/main.rs

@@ -0,0 +1,26 @@
+use harmony::{
+    inventory::Inventory,
+    modules::postgresql::{PostgreSQLScore, capability::PostgreSQLConfig},
+    topology::K8sAnywhereTopology,
+};
+
+#[tokio::main]
+async fn main() {
+    let postgresql = PostgreSQLScore {
+        config: PostgreSQLConfig {
+            cluster_name: "harmony-postgres-example".to_string(), // Override default name
+            namespace: "harmony-postgres-example".to_string(),
+            ..Default::default() // Use harmony defaults, they are based on CNPG's default values :
+                                 // "default" namespace, 1 instance, 1Gi storage
+        },
+    };
+
+    harmony_cli::run(
+        Inventory::autoload(),
+        K8sAnywhereTopology::from_env(),
+        vec![Box::new(postgresql)],
+        None,
+    )
+    .await
+    .unwrap();
+}

examples/public_postgres/Cargo.toml

@@ -0,0 +1,18 @@
+[package]
+name = "example-public-postgres"
+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 }

examples/public_postgres/src/main.rs

@@ -0,0 +1,38 @@
+use harmony::{
+    inventory::Inventory,
+    modules::postgresql::{
+        K8sPostgreSQLScore, PostgreSQLConnectionScore, PublicPostgreSQLScore,
+        capability::PostgreSQLConfig,
+    },
+    topology::K8sAnywhereTopology,
+};
+
+#[tokio::main]
+async fn main() {
+    let postgres = PublicPostgreSQLScore {
+        config: PostgreSQLConfig {
+            cluster_name: "harmony-postgres-example".to_string(), // Override default name
+            namespace: "harmony-public-postgres".to_string(),
+            ..Default::default() // Use harmony defaults, they are based on CNPG's default values :
+                                 // 1 instance, 1Gi storage
+        },
+        hostname: "postgrestest.sto1.nationtech.io".to_string(),
+    };
+
+    let test_connection = PostgreSQLConnectionScore {
+        name: "harmony-postgres-example".to_string(),
+        namespace: "harmony-public-postgres".to_string(),
+        cluster_name: "harmony-postgres-example".to_string(),
+        hostname: Some("postgrestest.sto1.nationtech.io".to_string()),
+        port_override: Some(443),
+    };
+
+    harmony_cli::run(
+        Inventory::autoload(),
+        K8sAnywhereTopology::from_env(),
+        vec![Box::new(postgres), Box::new(test_connection)],
+        None,
+    )
+    .await
+    .unwrap();
+}

examples/remove_rook_osd/Cargo.toml

@@ -0,0 +1,11 @@
+[package]
+name = "example-remove-rook-osd"
+edition = "2024"
+version.workspace = true
+readme.workspace = true
+license.workspace = true
+
+[dependencies]
+harmony = { version = "0.1.0", path = "../../harmony" }
+harmony_cli = { version = "0.1.0", path = "../../harmony_cli" }
+tokio.workspace = true

examples/remove_rook_osd/src/main.rs

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

examples/rhob_application_monitoring/src/main.rs

@@ -16,6 +16,7 @@ use harmony_types::net::Url;
 async fn main() {
     let application = Arc::new(RustWebapp {
         name: "test-rhob-monitoring".to_string(),
+        dns: "test-rhob-monitoring.harmony.mcd".to_string(),
         project_root: PathBuf::from("./webapp"), // Relative from 'harmony-path' param
         framework: Some(RustWebFramework::Leptos),
         service_port: 3000,

examples/rust/src/main.rs

@@ -19,6 +19,7 @@ use harmony_macros::hurl;
 async fn main() {
     let application = Arc::new(RustWebapp {
         name: "harmony-example-rust-webapp".to_string(),
+        dns: "harmony-example-rust-webapp.harmony.mcd".to_string(),
         project_root: PathBuf::from("./webapp"),
         framework: Some(RustWebFramework::Leptos),
         service_port: 3000,

examples/try_rust_webapp/files_to_add/main.rs

@@ -2,12 +2,11 @@ use harmony::{
     inventory::Inventory,
     modules::{
         application::{
-            ApplicationScore, RustWebFramework, RustWebapp,
-            features::{PackagingDeployment, rhob_monitoring::Monitoring},
+            features::{rhob_monitoring::Monitoring, PackagingDeployment}, ApplicationScore, RustWebFramework, RustWebapp
         },
         monitoring::alert_channel::discord_alert_channel::DiscordWebhook,
     },
-    topology::K8sAnywhereTopology,
+    topology::{K8sAnywhereTopology, LocalhostTopology},
 };
 use harmony_macros::hurl;
 use std::{path::PathBuf, sync::Arc};
@@ -22,8 +21,8 @@ async fn main() {
     });
 
     let discord_webhook = DiscordWebhook {
-        name: "harmony_demo".to_string(),
-        url: hurl!("http://not_a_url.com"),
+        name: "harmony-demo".to_string(),
+        url: hurl!("https://discord.com/api/webhooks/1415391405681021050/V6KzV41vQ7yvbn7BchejRu9C8OANxy0i2ESZOz2nvCxG8xAY3-2i3s5MS38k568JKTzH"),
     };
 
     let app = ApplicationScore {

examples/try_rust_webapp/src/main.rs

@@ -3,7 +3,7 @@ use harmony::{
     modules::{
         application::{
             ApplicationScore, RustWebFramework, RustWebapp,
-            features::{PackagingDeployment, rhob_monitoring::Monitoring},
+            features::{Monitoring, PackagingDeployment},
         },
         monitoring::alert_channel::discord_alert_channel::DiscordWebhook,
     },
@@ -16,16 +16,14 @@ use std::{path::PathBuf, sync::Arc};
 async fn main() {
     let application = Arc::new(RustWebapp {
         name: "harmony-example-tryrust".to_string(),
-        project_root: PathBuf::from("./tryrust.org"),
+        dns: "tryrust.example.harmony.mcd".to_string(),
+        project_root: PathBuf::from("./tryrust.org"), // <== Project root, in this case it is a
+        // submodule
         framework: Some(RustWebFramework::Leptos),
         service_port: 8080,
     });
 
-    let discord_receiver = DiscordWebhook {
-        name: "test-discord".to_string(),
-        url: hurl!("https://discord.doesnt.exist.com"),
-    };
-
+    // Define your Application deployment and the features you want
     let app = ApplicationScore {
         features: vec![
             Box::new(PackagingDeployment {
@@ -33,7 +31,10 @@ async fn main() {
             }),
             Box::new(Monitoring {
                 application: application.clone(),
-                alert_receiver: vec![Box::new(discord_receiver)],
+                alert_receiver: vec![Box::new(DiscordWebhook {
+                    name: "test-discord".to_string(),
+                    url: hurl!("https://discord.doesnt.exist.com"),
+                })],
             }),
         ],
         application,
@@ -41,7 +42,7 @@ async fn main() {
 
     harmony_cli::run(
         Inventory::autoload(),
-        K8sAnywhereTopology::from_env(),
+        K8sAnywhereTopology::from_env(), // <== Deploy to local automatically provisioned k3d by default or connect to any kubernetes cluster
         vec![Box::new(app)],
         None,
     )

harmony/Cargo.toml

@@ -77,6 +77,9 @@ harmony_secret = { path = "../harmony_secret" }
 askama.workspace = true
 sqlx.workspace = true
 inquire.workspace = true
+brocade = { path = "../brocade" }
+option-ext = "0.2.0"
 
 [dev-dependencies]
 pretty_assertions.workspace = true
+assertor.workspace = true

harmony/src/domain/hardware/mod.rs

@@ -152,10 +152,10 @@ impl PhysicalHost {
     pub fn parts_list(&self) -> String {
         let PhysicalHost {
             id,
-            category,
+            category: _,
             network,
             storage,
-            labels,
+            labels: _,
             memory_modules,
             cpus,
         } = self;
@@ -226,8 +226,8 @@ impl PhysicalHost {
                 speed_mhz,
                 manufacturer,
                 part_number,
-                serial_number,
-                rank,
+                serial_number: _,
+                rank: _,
             } = mem;
             parts_list.push_str(&format!(
                 "\n{}Gb, {}Mhz, Manufacturer ({}), Part Number ({})",

harmony/src/domain/interpret/mod.rs

@@ -4,6 +4,8 @@ use std::error::Error;
 use async_trait::async_trait;
 use derive_new::new;
 
+use crate::inventory::HostRole;
+
 use super::{
     data::Version, executors::ExecutorError, inventory::Inventory, topology::PreparationError,
 };
@@ -30,10 +32,12 @@ pub enum InterpretName {
     Lamp,
     ApplicationMonitoring,
     K8sPrometheusCrdAlerting,
+    CephRemoveOsd,
     DiscoverInventoryAgent,
     CephClusterHealth,
     Custom(&'static str),
     RHOBAlerting,
+    K8sIngress,
 }
 
 impl std::fmt::Display for InterpretName {
@@ -60,10 +64,12 @@ impl std::fmt::Display for InterpretName {
             InterpretName::Lamp => f.write_str("LAMP"),
             InterpretName::ApplicationMonitoring => f.write_str("ApplicationMonitoring"),
             InterpretName::K8sPrometheusCrdAlerting => f.write_str("K8sPrometheusCrdAlerting"),
+            InterpretName::CephRemoveOsd => f.write_str("CephRemoveOsd"),
             InterpretName::DiscoverInventoryAgent => f.write_str("DiscoverInventoryAgent"),
             InterpretName::CephClusterHealth => f.write_str("CephClusterHealth"),
             InterpretName::Custom(name) => f.write_str(name),
             InterpretName::RHOBAlerting => f.write_str("RHOBAlerting"),
+            InterpretName::K8sIngress => f.write_str("K8sIngress"),
         }
     }
 }
@@ -82,13 +88,15 @@ pub trait Interpret<T>: std::fmt::Debug + Send {
 pub struct Outcome {
     pub status: InterpretStatus,
     pub message: String,
+    pub details: Vec<String>,
 }
 
 impl Outcome {
-    pub fn noop() -> Self {
+    pub fn noop(message: String) -> Self {
         Self {
             status: InterpretStatus::NOOP,
-            message: String::new(),
+            message,
+            details: vec![],
         }
     }
 
@@ -96,6 +104,23 @@ impl Outcome {
         Self {
             status: InterpretStatus::SUCCESS,
             message,
+            details: vec![],
+        }
+    }
+
+    pub fn success_with_details(message: String, details: Vec<String>) -> Self {
+        Self {
+            status: InterpretStatus::SUCCESS,
+            message,
+            details,
+        }
+    }
+
+    pub fn running(message: String) -> Self {
+        Self {
+            status: InterpretStatus::RUNNING,
+            message,
+            details: vec![],
         }
     }
 }
@@ -129,6 +154,12 @@ pub struct InterpretError {
     msg: String,
 }
 
+impl From<InterpretError> for String {
+    fn from(e: InterpretError) -> String {
+        format!("InterpretError : {}", e.msg)
+    }
+}
+
 impl std::fmt::Display for InterpretError {
     fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
         f.write_str(&self.msg)

harmony/src/domain/inventory/mod.rs

@@ -1,4 +1,6 @@
 mod repository;
+use std::fmt;
+
 pub use repository::*;
 
 #[derive(Debug, new, Clone)]
@@ -69,5 +71,14 @@ pub enum HostRole {
     Bootstrap,
     ControlPlane,
     Worker,
-    Storage,
+}
+
+impl fmt::Display for HostRole {
+    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
+        match self {
+            HostRole::Bootstrap => write!(f, "Bootstrap"),
+            HostRole::ControlPlane => write!(f, "ControlPlane"),
+            HostRole::Worker => write!(f, "Worker"),
+        }
+    }
 }

harmony/src/domain/topology/failover.rs

@@ -0,0 +1,64 @@
+use async_trait::async_trait;
+
+use crate::topology::k8s_anywhere::K8sAnywhereConfig;
+use crate::topology::{K8sAnywhereTopology, PreparationError, PreparationOutcome, Topology};
+
+pub struct FailoverTopology<T> {
+    pub primary: T,
+    pub replica: T,
+}
+
+#[async_trait]
+impl<T: Topology + Send + Sync> Topology for FailoverTopology<T> {
+    fn name(&self) -> &str {
+        "FailoverTopology"
+    }
+
+    async fn ensure_ready(&self) -> Result<PreparationOutcome, PreparationError> {
+        let primary_outcome = self.primary.ensure_ready().await?;
+        let replica_outcome = self.replica.ensure_ready().await?;
+
+        match (primary_outcome, replica_outcome) {
+            (PreparationOutcome::Noop, PreparationOutcome::Noop) => Ok(PreparationOutcome::Noop),
+            (p, r) => {
+                let mut details = Vec::new();
+                if let PreparationOutcome::Success { details: d } = p {
+                    details.push(format!("Primary: {}", d));
+                }
+                if let PreparationOutcome::Success { details: d } = r {
+                    details.push(format!("Replica: {}", d));
+                }
+                Ok(PreparationOutcome::Success {
+                    details: details.join(", "),
+                })
+            }
+        }
+    }
+}
+
+impl FailoverTopology<K8sAnywhereTopology> {
+    /// Creates a new `FailoverTopology` from environment variables.
+    ///
+    /// Expects two environment variables:
+    /// - `HARMONY_FAILOVER_TOPOLOGY_K8S_PRIMARY`: Comma-separated `key=value` pairs, e.g.,
+    ///   `kubeconfig=/path/to/primary.kubeconfig,context_name=primary-ctx`
+    /// - `HARMONY_FAILOVER_TOPOLOGY_K8S_REPLICA`: Same format for the replica.
+    ///
+    /// Parses `kubeconfig` (path to kubeconfig file) and `context_name` (Kubernetes context),
+    /// and constructs `K8sAnywhereConfig` with local installs disabled (`use_local_k3d=false`,
+    /// `autoinstall=false`, `use_system_kubeconfig=false`).
+    /// `harmony_profile` is read from `HARMONY_PROFILE` env or defaults to `"dev"`.
+    ///
+    /// Panics if required env vars are missing or malformed.
+    pub fn from_env() -> Self {
+        let primary_config =
+            K8sAnywhereConfig::remote_k8s_from_env_var("HARMONY_FAILOVER_TOPOLOGY_K8S_PRIMARY");
+        let replica_config =
+            K8sAnywhereConfig::remote_k8s_from_env_var("HARMONY_FAILOVER_TOPOLOGY_K8S_REPLICA");
+
+        let primary = K8sAnywhereTopology::with_config(primary_config);
+        let replica = K8sAnywhereTopology::with_config(replica_config);
+
+        Self { primary, replica }
+    }
+}

harmony/src/domain/topology/ha_cluster.rs

@@ -1,34 +1,25 @@
 use async_trait::async_trait;
+use brocade::PortOperatingMode;
 use harmony_macros::ip;
-use harmony_types::net::MacAddress;
-use harmony_types::net::Url;
+use harmony_types::{
+    id::Id,
+    net::{MacAddress, Url},
+    switch::PortLocation,
+};
 use log::debug;
 use log::info;
 
-use crate::data::FileContent;
-use crate::executors::ExecutorError;
-use crate::topology::PxeOptions;
+use crate::{data::FileContent, executors::ExecutorError, topology::node_exporter::NodeExporter};
+use crate::{infra::network_manager::OpenShiftNmStateNetworkManager, topology::PortConfig};
+use crate::{modules::inventory::HarmonyDiscoveryStrategy, topology::PxeOptions};
 
-use super::DHCPStaticEntry;
-use super::DhcpServer;
-use super::DnsRecord;
-use super::DnsRecordType;
-use super::DnsServer;
-use super::Firewall;
-use super::HttpServer;
-use super::IpAddress;
-use super::K8sclient;
-use super::LoadBalancer;
-use super::LoadBalancerService;
-use super::LogicalHost;
-use super::PreparationError;
-use super::PreparationOutcome;
-use super::Router;
-use super::TftpServer;
-
-use super::Topology;
-use super::k8s::K8sClient;
-use std::sync::Arc;
+use super::{
+    DHCPStaticEntry, DhcpServer, DnsRecord, DnsRecordType, DnsServer, Firewall, HostNetworkConfig,
+    HttpServer, IpAddress, K8sclient, LoadBalancer, LoadBalancerService, LogicalHost, NetworkError,
+    NetworkManager, PreparationError, PreparationOutcome, Router, Switch, SwitchClient,
+    SwitchError, TftpServer, Topology, k8s::K8sClient,
+};
+use std::sync::{Arc, OnceLock};
 
 #[derive(Debug, Clone)]
 pub struct HAClusterTopology {
@@ -40,10 +31,13 @@ pub struct HAClusterTopology {
     pub tftp_server: Arc<dyn TftpServer>,
     pub http_server: Arc<dyn HttpServer>,
     pub dns_server: Arc<dyn DnsServer>,
+    pub node_exporter: Arc<dyn NodeExporter>,
+    pub switch_client: Arc<dyn SwitchClient>,
     pub bootstrap_host: LogicalHost,
     pub control_plane: Vec<LogicalHost>,
     pub workers: Vec<LogicalHost>,
-    pub switch: Vec<LogicalHost>,
+    pub kubeconfig: Option<String>,
+    pub network_manager: OnceLock<Arc<dyn NetworkManager>>,
 }
 
 #[async_trait]
@@ -62,9 +56,17 @@ impl Topology for HAClusterTopology {
 #[async_trait]
 impl K8sclient for HAClusterTopology {
     async fn k8s_client(&self) -> Result<Arc<K8sClient>, String> {
-        Ok(Arc::new(
-            K8sClient::try_default().await.map_err(|e| e.to_string())?,
-        ))
+        match &self.kubeconfig {
+            None => Ok(Arc::new(
+                K8sClient::try_default().await.map_err(|e| e.to_string())?,
+            )),
+            Some(kubeconfig) => {
+                let Some(client) = K8sClient::from_kubeconfig(kubeconfig).await else {
+                    return Err("Failed to create k8s client".to_string());
+                };
+                Ok(Arc::new(client))
+            }
+        }
     }
 }
 
@@ -89,6 +91,14 @@ impl HAClusterTopology {
             .to_string()
     }
 
+    pub async fn network_manager(&self) -> &dyn NetworkManager {
+        let k8s_client = self.k8s_client().await.unwrap();
+
+        self.network_manager
+            .get_or_init(|| Arc::new(OpenShiftNmStateNetworkManager::new(k8s_client.clone())))
+            .as_ref()
+    }
+
     pub fn autoload() -> Self {
         let dummy_infra = Arc::new(DummyInfra {});
         let dummy_host = LogicalHost {
@@ -97,6 +107,7 @@ impl HAClusterTopology {
         };
 
         Self {
+            kubeconfig: None,
             domain_name: "DummyTopology".to_string(),
             router: dummy_infra.clone(),
             load_balancer: dummy_infra.clone(),
@@ -105,10 +116,12 @@ impl HAClusterTopology {
             tftp_server: dummy_infra.clone(),
             http_server: dummy_infra.clone(),
             dns_server: dummy_infra.clone(),
+            node_exporter: dummy_infra.clone(),
+            switch_client: dummy_infra.clone(),
             bootstrap_host: dummy_host,
             control_plane: vec![],
             workers: vec![],
-            switch: vec![],
+            network_manager: OnceLock::new(),
         }
     }
 }
@@ -263,6 +276,70 @@ impl HttpServer for HAClusterTopology {
     }
 }
 
+#[async_trait]
+impl Switch for HAClusterTopology {
+    async fn setup_switch(&self) -> Result<(), SwitchError> {
+        self.switch_client.setup().await.map(|_| ())
+    }
+
+    async fn get_port_for_mac_address(
+        &self,
+        mac_address: &MacAddress,
+    ) -> Result<Option<PortLocation>, SwitchError> {
+        self.switch_client.find_port(mac_address).await
+    }
+
+    async fn configure_port_channel(&self, config: &HostNetworkConfig) -> Result<(), SwitchError> {
+        debug!("Configuring port channel: {config:#?}");
+        let switch_ports = config.switch_ports.iter().map(|s| s.port.clone()).collect();
+
+        self.switch_client
+            .configure_port_channel(&format!("Harmony_{}", config.host_id), switch_ports)
+            .await
+            .map_err(|e| SwitchError::new(format!("Failed to configure port-channel: {e}")))?;
+
+        Ok(())
+    }
+
+    async fn clear_port_channel(&self, ids: &Vec<Id>) -> Result<(), SwitchError> {
+        todo!()
+    }
+    async fn configure_interface(&self, ports: &Vec<PortConfig>) -> Result<(), SwitchError> {
+        todo!()
+    }
+}
+
+#[async_trait]
+impl NetworkManager for HAClusterTopology {
+    async fn ensure_network_manager_installed(&self) -> Result<(), NetworkError> {
+        self.network_manager()
+            .await
+            .ensure_network_manager_installed()
+            .await
+    }
+
+    async fn configure_bond(&self, config: &HostNetworkConfig) -> Result<(), NetworkError> {
+        self.network_manager().await.configure_bond(config).await
+    }
+
+    //TODO add snmp here
+}
+
+#[async_trait]
+impl NodeExporter for HAClusterTopology {
+    async fn ensure_initialized(&self) -> Result<(), ExecutorError> {
+        self.node_exporter.ensure_initialized().await
+    }
+
+    async fn commit_config(&self) -> Result<(), ExecutorError> {
+        self.node_exporter.commit_config().await
+    }
+
+    async fn reload_restart(&self) -> Result<(), ExecutorError> {
+        self.node_exporter.reload_restart().await
+    }
+}
+
 #[derive(Debug)]
 pub struct DummyInfra;
 
@@ -332,8 +409,8 @@ impl DhcpServer for DummyInfra {
     }
     async fn set_dhcp_range(
         &self,
-        start: &IpAddress,
-        end: &IpAddress,
+        _start: &IpAddress,
+        _end: &IpAddress,
     ) -> Result<(), ExecutorError> {
         unimplemented!("{}", UNIMPLEMENTED_DUMMY_INFRA)
     }
@@ -449,3 +526,46 @@ impl DnsServer for DummyInfra {
         unimplemented!("{}", UNIMPLEMENTED_DUMMY_INFRA)
     }
 }
+
+#[async_trait]
+impl NodeExporter for DummyInfra {
+    async fn ensure_initialized(&self) -> Result<(), ExecutorError> {
+        unimplemented!("{}", UNIMPLEMENTED_DUMMY_INFRA)
+    }
+
+    async fn commit_config(&self) -> Result<(), ExecutorError> {
+        unimplemented!("{}", UNIMPLEMENTED_DUMMY_INFRA)
+    }
+
+    async fn reload_restart(&self) -> Result<(), ExecutorError> {
+        unimplemented!("{}", UNIMPLEMENTED_DUMMY_INFRA)
+    }
+}
+
+#[async_trait]
+impl SwitchClient for DummyInfra {
+    async fn setup(&self) -> Result<(), SwitchError> {
+        unimplemented!("{}", UNIMPLEMENTED_DUMMY_INFRA)
+    }
+
+    async fn find_port(
+        &self,
+        _mac_address: &MacAddress,
+    ) -> Result<Option<PortLocation>, SwitchError> {
+        unimplemented!("{}", UNIMPLEMENTED_DUMMY_INFRA)
+    }
+
+    async fn configure_port_channel(
+        &self,
+        _channel_name: &str,
+        _switch_ports: Vec<PortLocation>,
+    ) -> Result<u8, SwitchError> {
+        unimplemented!("{}", UNIMPLEMENTED_DUMMY_INFRA)
+    }
+    async fn clear_port_channel(&self, ids: &Vec<Id>) -> Result<(), SwitchError> {
+        todo!()
+    }
+    async fn configure_interface(&self, ports: &Vec<PortConfig>) -> Result<(), SwitchError> {
+        todo!()
+    }
+}

harmony/src/domain/topology/k8s.rs

@@ -1,13 +1,24 @@
+use std::{collections::HashMap, time::Duration};
+
 use derive_new::new;
 use k8s_openapi::{
     ClusterResourceScope, NamespaceResourceScope,
-    api::{apps::v1::Deployment, core::v1::Pod},
+    api::{
+        apps::v1::Deployment,
+        core::v1::{Node, Pod, ServiceAccount},
+    },
+    apiextensions_apiserver::pkg::apis::apiextensions::v1::CustomResourceDefinition,
+    apimachinery::pkg::version::Info,
 };
 use kube::{
-    Client, Config, Error, Resource,
-    api::{Api, AttachParams, DeleteParams, ListParams, Patch, PatchParams, ResourceExt},
+    Client, Config, Discovery, Error, Resource,
+    api::{
+        Api, AttachParams, DeleteParams, ListParams, ObjectList, Patch, PatchParams, ResourceExt,
+    },
     config::{KubeConfigOptions, Kubeconfig},
     core::ErrorResponse,
+    discovery::{ApiCapabilities, Scope},
+    error::DiscoveryError,
     runtime::reflector::Lookup,
 };
 use kube::{api::DynamicObject, runtime::conditions};
@@ -15,11 +26,12 @@ use kube::{
     api::{ApiResource, GroupVersionKind},
     runtime::wait::await_condition,
 };
-use log::{debug, error, trace};
+use log::{debug, error, trace, warn};
 use serde::{Serialize, de::DeserializeOwned};
 use serde_json::{Value, json};
 use similar::TextDiff;
-use tokio::io::AsyncReadExt;
+use tokio::{io::AsyncReadExt, time::sleep};
+use url::Url;
 
 #[derive(new, Clone)]
 pub struct K8sClient {
@@ -53,6 +65,165 @@ impl K8sClient {
         })
     }
 
+    /// Returns true if any deployment in the given namespace matching the label selector
+    /// has status.availableReplicas > 0 (or condition Available=True).
+    pub async fn has_healthy_deployment_with_label(
+        &self,
+        namespace: &str,
+        label_selector: &str,
+    ) -> Result<bool, Error> {
+        let api: Api<Deployment> = Api::namespaced(self.client.clone(), namespace);
+        let lp = ListParams::default().labels(label_selector);
+        let list = api.list(&lp).await?;
+        for d in list.items {
+            // Check AvailableReplicas > 0 or Available condition
+            let available = d
+                .status
+                .as_ref()
+                .and_then(|s| s.available_replicas)
+                .unwrap_or(0);
+            if available > 0 {
+                return Ok(true);
+            }
+            // Fallback: scan conditions
+            if let Some(conds) = d.status.as_ref().and_then(|s| s.conditions.as_ref()) {
+                if conds
+                    .iter()
+                    .any(|c| c.type_ == "Available" && c.status == "True")
+                {
+                    return Ok(true);
+                }
+            }
+        }
+        Ok(false)
+    }
+
+    /// Cluster-wide: returns namespaces that have at least one healthy deployment
+    /// matching the label selector (equivalent to kubectl -A -l ...).
+    pub async fn list_namespaces_with_healthy_deployments(
+        &self,
+        label_selector: &str,
+    ) -> Result<Vec<String>, Error> {
+        let api: Api<Deployment> = Api::all(self.client.clone());
+        let lp = ListParams::default().labels(label_selector);
+        let list = api.list(&lp).await?;
+
+        let mut healthy_ns: HashMap<String, bool> = HashMap::new();
+        for d in list.items {
+            let ns = match d.metadata.namespace.clone() {
+                Some(n) => n,
+                None => continue,
+            };
+            let available = d
+                .status
+                .as_ref()
+                .and_then(|s| s.available_replicas)
+                .unwrap_or(0);
+            let is_healthy = if available > 0 {
+                true
+            } else {
+                d.status
+                    .as_ref()
+                    .and_then(|s| s.conditions.as_ref())
+                    .map(|conds| {
+                        conds
+                            .iter()
+                            .any(|c| c.type_ == "Available" && c.status == "True")
+                    })
+                    .unwrap_or(false)
+            };
+            if is_healthy {
+                healthy_ns.insert(ns, true);
+            }
+        }
+
+        Ok(healthy_ns.into_keys().collect())
+    }
+
+    /// Get the application-controller ServiceAccount name (fallback to default)
+    pub async fn get_controller_service_account_name(
+        &self,
+        ns: &str,
+    ) -> Result<Option<String>, Error> {
+        let api: Api<Deployment> = Api::namespaced(self.client.clone(), ns);
+        let lp = ListParams::default().labels("app.kubernetes.io/component=controller");
+        let list = api.list(&lp).await?;
+        if let Some(dep) = list.items.get(0) {
+            if let Some(sa) = dep
+                .spec
+                .as_ref()
+                .and_then(|ds| ds.template.spec.as_ref())
+                .and_then(|ps| ps.service_account_name.clone())
+            {
+                return Ok(Some(sa));
+            }
+        }
+        Ok(None)
+    }
+
+    // List ClusterRoleBindings dynamically and return as JSON values
+    pub async fn list_clusterrolebindings_json(&self) -> Result<Vec<Value>, Error> {
+        let gvk = kube::api::GroupVersionKind::gvk(
+            "rbac.authorization.k8s.io",
+            "v1",
+            "ClusterRoleBinding",
+        );
+        let ar = kube::api::ApiResource::from_gvk(&gvk);
+        let api: Api<kube::api::DynamicObject> = Api::all_with(self.client.clone(), &ar);
+        let crbs = api.list(&ListParams::default()).await?;
+        let mut out = Vec::new();
+        for o in crbs {
+            let v = serde_json::to_value(&o).unwrap_or(Value::Null);
+            out.push(v);
+        }
+        Ok(out)
+    }
+
+    /// Determine if Argo controller in ns has cluster-wide permissions via CRBs
+    // TODO This does not belong in the generic k8s client, should be refactored at some point
+    pub async fn is_service_account_cluster_wide(&self, sa: &str, ns: &str) -> Result<bool, Error> {
+        let crbs = self.list_clusterrolebindings_json().await?;
+        let sa_user = format!("system:serviceaccount:{}:{}", ns, sa);
+        for crb in crbs {
+            if let Some(subjects) = crb.get("subjects").and_then(|s| s.as_array()) {
+                for subj in subjects {
+                    let kind = subj.get("kind").and_then(|v| v.as_str()).unwrap_or("");
+                    let name = subj.get("name").and_then(|v| v.as_str()).unwrap_or("");
+                    let subj_ns = subj.get("namespace").and_then(|v| v.as_str()).unwrap_or("");
+                    if (kind == "ServiceAccount" && name == sa && subj_ns == ns)
+                        || (kind == "User" && name == sa_user)
+                    {
+                        return Ok(true);
+                    }
+                }
+            }
+        }
+        Ok(false)
+    }
+
+    pub async fn has_crd(&self, name: &str) -> Result<bool, Error> {
+        let api: Api<CustomResourceDefinition> = Api::all(self.client.clone());
+        let lp = ListParams::default().fields(&format!("metadata.name={}", name));
+        let crds = api.list(&lp).await?;
+        Ok(!crds.items.is_empty())
+    }
+
+    pub async fn service_account_api(&self, namespace: &str) -> Api<ServiceAccount> {
+        let api: Api<ServiceAccount> = Api::namespaced(self.client.clone(), namespace);
+        api
+    }
+
+    pub async fn get_apiserver_version(&self) -> Result<Info, Error> {
+        let client: Client = self.client.clone();
+        let version_info: Info = client.apiserver_version().await?;
+        Ok(version_info)
+    }
+
+    pub async fn discovery(&self) -> Result<Discovery, Error> {
+        let discovery: Discovery = Discovery::new(self.client.clone()).run().await?;
+        Ok(discovery)
+    }
+
     pub async fn get_resource_json_value(
         &self,
         name: &str,
@@ -65,7 +236,8 @@ impl K8sClient {
         } else {
             Api::default_namespaced_with(self.client.clone(), &gvk)
         };
-        Ok(resource.get(name).await?)
+
+        resource.get(name).await
     }
 
     pub async fn get_deployment(
@@ -74,11 +246,15 @@ impl K8sClient {
         namespace: Option<&str>,
     ) -> Result<Option<Deployment>, Error> {
         let deps: Api<Deployment> = if let Some(ns) = namespace {
+            debug!("getting namespaced deployment");
             Api::namespaced(self.client.clone(), ns)
         } else {
+            debug!("getting default namespace deployment");
             Api::default_namespaced(self.client.clone())
         };
-        Ok(deps.get_opt(name).await?)
+
+        debug!("getting deployment {} in ns {}", name, namespace.unwrap());
+        deps.get_opt(name).await
     }
 
     pub async fn get_pod(&self, name: &str, namespace: Option<&str>) -> Result<Option<Pod>, Error> {
@@ -87,7 +263,8 @@ impl K8sClient {
         } else {
             Api::default_namespaced(self.client.clone())
         };
-        Ok(pods.get_opt(name).await?)
+
+        pods.get_opt(name).await
     }
 
     pub async fn scale_deployment(
@@ -108,7 +285,7 @@ impl K8sClient {
             }
         });
         let pp = PatchParams::default();
-        let scale = Patch::Apply(&patch);
+        let scale = Patch::Merge(&patch);
         deployments.patch_scale(name, &pp, &scale).await?;
         Ok(())
     }
@@ -130,9 +307,9 @@ impl K8sClient {
 
     pub async fn wait_until_deployment_ready(
         &self,
-        name: String,
+        name: &str,
         namespace: Option<&str>,
-        timeout: Option<u64>,
+        timeout: Option<Duration>,
     ) -> Result<(), String> {
         let api: Api<Deployment>;
 
@@ -142,9 +319,9 @@ impl K8sClient {
             api = Api::default_namespaced(self.client.clone());
         }
 
-        let establish = await_condition(api, name.as_str(), conditions::is_deployment_completed());
-        let t = timeout.unwrap_or(300);
-        let res = tokio::time::timeout(std::time::Duration::from_secs(t), establish).await;
+        let establish = await_condition(api, name, conditions::is_deployment_completed());
+        let timeout = timeout.unwrap_or(Duration::from_secs(120));
+        let res = tokio::time::timeout(timeout, establish).await;
 
         if res.is_ok() {
             Ok(())
@@ -153,6 +330,41 @@ impl K8sClient {
         }
     }
 
+    pub async fn wait_for_pod_ready(
+        &self,
+        pod_name: &str,
+        namespace: Option<&str>,
+    ) -> Result<(), Error> {
+        let mut elapsed = 0;
+        let interval = 5; // seconds between checks
+        let timeout_secs = 120;
+        loop {
+            let pod = self.get_pod(pod_name, namespace).await?;
+
+            if let Some(p) = pod {
+                if let Some(status) = p.status {
+                    if let Some(phase) = status.phase {
+                        if phase.to_lowercase() == "running" {
+                            return Ok(());
+                        }
+                    }
+                }
+            }
+
+            if elapsed >= timeout_secs {
+                return Err(Error::Discovery(DiscoveryError::MissingResource(format!(
+                    "'{}' in ns '{}' did not become ready within {}s",
+                    pod_name,
+                    namespace.unwrap(),
+                    timeout_secs
+                ))));
+            }
+
+            sleep(Duration::from_secs(interval)).await;
+            elapsed += interval;
+        }
+    }
+
     /// Will execute a commond in the first pod found that matches the specified label
     /// '{label}={name}'
     pub async fn exec_app_capture_output(
@@ -199,7 +411,7 @@ impl K8sClient {
 
                 if let Some(s) = status.status {
                     let mut stdout_buf = String::new();
-                    if let Some(mut stdout) = process.stdout().take() {
+                    if let Some(mut stdout) = process.stdout() {
                         stdout
                             .read_to_string(&mut stdout_buf)
                             .await
@@ -305,14 +517,14 @@ impl K8sClient {
                 Ok(current) => {
                     trace!("Received current value {current:#?}");
                     // The resource exists, so we calculate and display a diff.
-                    println!("\nPerforming dry-run for resource: '{}'", name);
+                    println!("\nPerforming dry-run for resource: '{name}'");
                     let mut current_yaml = serde_yaml::to_value(&current).unwrap_or_else(|_| {
                         panic!("Could not serialize current value : {current:#?}")
                     });
                     if current_yaml.is_mapping() && current_yaml.get("status").is_some() {
                         let map = current_yaml.as_mapping_mut().unwrap();
                         let removed = map.remove_entry("status");
-                        trace!("Removed status {:?}", removed);
+                        trace!("Removed status {removed:?}");
                     } else {
                         trace!(
                             "Did not find status entry for current object {}/{}",
@@ -341,14 +553,14 @@ impl K8sClient {
                             similar::ChangeTag::Insert => "+",
                             similar::ChangeTag::Equal => " ",
                         };
-                        print!("{}{}", sign, change);
+                        print!("{sign}{change}");
                     }
                     // In a dry run, we return the new resource state that would have been applied.
                     Ok(resource.clone())
                 }
                 Err(Error::Api(ErrorResponse { code: 404, .. })) => {
                     // The resource does not exist, so the "diff" is the entire new resource.
-                    println!("\nPerforming dry-run for new resource: '{}'", name);
+                    println!("\nPerforming dry-run for new resource: '{name}'");
                     println!(
                         "Resource does not exist. It would be created with the following content:"
                     );
@@ -357,14 +569,14 @@ impl K8sClient {
 
                     // Print each line of the new resource with a '+' prefix.
                     for line in new_yaml.lines() {
-                        println!("+{}", line);
+                        println!("+{line}");
                     }
                     // In a dry run, we return the new resource state that would have been created.
                     Ok(resource.clone())
                 }
                 Err(e) => {
                     // Another API error occurred.
-                    error!("Failed to get resource '{}': {}", name, e);
+                    error!("Failed to get resource '{name}': {e}");
                     Err(e)
                 }
             }
@@ -379,11 +591,24 @@ impl K8sClient {
     where
         K: Resource + Clone + std::fmt::Debug + DeserializeOwned + serde::Serialize,
         <K as Resource>::Scope: ApplyStrategy<K>,
-        <K as kube::Resource>::DynamicType: Default,
+        <K as Resource>::DynamicType: Default,
     {
         let mut result = Vec::new();
         for r in resource.iter() {
-            result.push(self.apply(r, ns).await?);
+            let apply_result = self.apply(r, ns).await;
+            if apply_result.is_err() {
+                // NOTE : We should be careful about this one, it may leak sensitive information in
+                // logs
+                // Maybe just reducing it to debug would be enough as we already know debug logs
+                // are unsafe.
+                // But keeping it at warn makes it much easier to understand what is going on. So be it for now.
+                warn!(
+                    "Failed to apply k8s resource : {}",
+                    serde_json::to_string_pretty(r).map_err(|e| Error::SerdeError(e))?
+                );
+            }
+
+            result.push(apply_result?);
         }
 
         Ok(result)
@@ -419,9 +644,12 @@ impl K8sClient {
             .as_str()
             .expect("couldn't get kind as str");
 
-        let split: Vec<&str> = api_version.splitn(2, "/").collect();
-        let g = split[0];
-        let v = split[1];
+        let mut it = api_version.splitn(2, '/');
+        let first = it.next().unwrap();
+        let (g, v) = match it.next() {
+            Some(second) => (first, second),
+            None => ("", first),
+        };
 
         let gvk = GroupVersionKind::gvk(g, v, kind);
         let api_resource = ApiResource::from_gvk(&gvk);
@@ -441,10 +669,7 @@ impl K8sClient {
 
         // 6. Apply the object to the cluster using Server-Side Apply.
         //    This will create the resource if it doesn't exist, or update it if it does.
-        println!(
-            "Applying Argo Application '{}' in namespace '{}'...",
-            name, namespace
-        );
+        println!("Applying '{name}' in namespace '{namespace}'...",);
         let patch_params = PatchParams::apply("harmony"); // Use a unique field manager name
         let result = api.patch(name, &patch_params, &Patch::Apply(&obj)).await?;
 
@@ -453,7 +678,120 @@ impl K8sClient {
         Ok(())
     }
 
-    pub(crate) async fn from_kubeconfig(path: &str) -> Option<K8sClient> {
+    /// Apply a resource from a URL
+    ///
+    /// It is the equivalent of `kubectl apply -f <url>`
+    pub async fn apply_url(&self, url: Url, ns: Option<&str>) -> Result<(), Error> {
+        let patch_params = PatchParams::apply("harmony");
+        let discovery = kube::Discovery::new(self.client.clone()).run().await?;
+
+        let yaml = reqwest::get(url)
+            .await
+            .expect("Could not get URL")
+            .text()
+            .await
+            .expect("Could not get content from URL");
+
+        for doc in multidoc_deserialize(&yaml).expect("failed to parse YAML from file") {
+            let obj: DynamicObject =
+                serde_yaml::from_value(doc).expect("cannot apply without valid YAML");
+            let namespace = obj.metadata.namespace.as_deref().or(ns);
+            let type_meta = obj
+                .types
+                .as_ref()
+                .expect("cannot apply object without valid TypeMeta");
+            let gvk = GroupVersionKind::try_from(type_meta)
+                .expect("cannot apply object without valid GroupVersionKind");
+            let name = obj.name_any();
+
+            if let Some((ar, caps)) = discovery.resolve_gvk(&gvk) {
+                let api = get_dynamic_api(ar, caps, self.client.clone(), namespace, false);
+                trace!(
+                    "Applying {}: \n{}",
+                    gvk.kind,
+                    serde_yaml::to_string(&obj).expect("Failed to serialize YAML")
+                );
+                let data: serde_json::Value =
+                    serde_json::to_value(&obj).expect("Failed to serialize JSON");
+                let _r = api.patch(&name, &patch_params, &Patch::Apply(data)).await?;
+                debug!("applied {} {}", gvk.kind, name);
+            } else {
+                warn!("Cannot apply document for unknown {gvk:?}");
+            }
+        }
+
+        Ok(())
+    }
+
+    /// Gets a single named resource of a specific type `K`.
+    ///
+    /// This function uses the `ApplyStrategy` trait to correctly determine
+    /// whether to look in a specific namespace or in the entire cluster.
+    ///
+    /// Returns `Ok(None)` if the resource is not found (404).
+    pub async fn get_resource<K>(
+        &self,
+        name: &str,
+        namespace: Option<&str>,
+    ) -> Result<Option<K>, Error>
+    where
+        K: Resource + Clone + std::fmt::Debug + DeserializeOwned,
+        <K as Resource>::Scope: ApplyStrategy<K>,
+        <K as kube::Resource>::DynamicType: Default,
+    {
+        let api: Api<K> =
+            <<K as Resource>::Scope as ApplyStrategy<K>>::get_api(&self.client, namespace);
+
+        api.get_opt(name).await
+    }
+
+    /// Lists all resources of a specific type `K`.
+    ///
+    /// This function uses the `ApplyStrategy` trait to correctly determine
+    /// whether to list from a specific namespace or from the entire cluster.
+    pub async fn list_resources<K>(
+        &self,
+        namespace: Option<&str>,
+        list_params: Option<ListParams>,
+    ) -> Result<ObjectList<K>, Error>
+    where
+        K: Resource + Clone + std::fmt::Debug + DeserializeOwned,
+        <K as Resource>::Scope: ApplyStrategy<K>,
+        <K as kube::Resource>::DynamicType: Default,
+    {
+        let api: Api<K> =
+            <<K as Resource>::Scope as ApplyStrategy<K>>::get_api(&self.client, namespace);
+
+        let list_params = list_params.unwrap_or_default();
+        api.list(&list_params).await
+    }
+
+    /// Fetches a list of all Nodes in the cluster.
+    pub async fn get_nodes(
+        &self,
+        list_params: Option<ListParams>,
+    ) -> Result<ObjectList<Node>, Error> {
+        self.list_resources(None, list_params).await
+    }
+
+    pub async fn from_kubeconfig(path: &str) -> Option<K8sClient> {
+        Self::from_kubeconfig_with_opts(path, &KubeConfigOptions::default()).await
+    }
+
+    pub async fn from_kubeconfig_with_context(
+        path: &str,
+        context: Option<String>,
+    ) -> Option<K8sClient> {
+        let mut opts = KubeConfigOptions::default();
+        opts.context = context;
+
+        Self::from_kubeconfig_with_opts(path, &opts).await
+    }
+
+    pub async fn from_kubeconfig_with_opts(
+        path: &str,
+        opts: &KubeConfigOptions,
+    ) -> Option<K8sClient> {
         let k = match Kubeconfig::read_from(path) {
             Ok(k) => k,
             Err(e) => {
@@ -461,17 +799,38 @@ impl K8sClient {
                 return None;
             }
         };
+
         Some(K8sClient::new(
-            Client::try_from(
-                Config::from_custom_kubeconfig(k, &KubeConfigOptions::default())
-                    .await
-                    .unwrap(),
-            )
-            .unwrap(),
+            Client::try_from(Config::from_custom_kubeconfig(k, &opts).await.unwrap()).unwrap(),
         ))
     }
 }
 
+fn get_dynamic_api(
+    resource: ApiResource,
+    capabilities: ApiCapabilities,
+    client: Client,
+    ns: Option<&str>,
+    all: bool,
+) -> Api<DynamicObject> {
+    if capabilities.scope == Scope::Cluster || all {
+        Api::all_with(client, &resource)
+    } else if let Some(namespace) = ns {
+        Api::namespaced_with(client, namespace, &resource)
+    } else {
+        Api::default_namespaced_with(client, &resource)
+    }
+}
+
+fn multidoc_deserialize(data: &str) -> Result<Vec<serde_yaml::Value>, serde_yaml::Error> {
+    use serde::Deserialize;
+    let mut docs = vec![];
+    for de in serde_yaml::Deserializer::from_str(data) {
+        docs.push(serde_yaml::Value::deserialize(de)?);
+    }
+    Ok(docs)
+}
+
 pub trait ApplyStrategy<K: Resource> {
     fn get_api(client: &Client, ns: Option<&str>) -> Api<K>;
 }