fix: git ignore

Reviewed-on: #180
Reviewed-by: Ian Letourneau <ian@noma.to>

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 +674,22 @@ 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 = "brotli"
 version = "8.0.2"
@@ -1755,6 +1780,7 @@ dependencies = [
 name = "example-nanodc"
 version = "0.1.0"
 dependencies = [
+ "brocade",
  "cidr",
  "env_logger",
  "harmony",
@@ -1763,6 +1789,7 @@ dependencies = [
  "harmony_tui",
  "harmony_types",
  "log",
+ "serde",
  "tokio",
  "url",
 ]
@@ -1778,9 +1805,10 @@ dependencies = [
 ]
 
 [[package]]
-name = "example-okd-install"
+name = "example-okd-cluster-alerts"
 version = "0.1.0"
 dependencies = [
+ "brocade",
  "cidr",
  "env_logger",
  "harmony",
@@ -1795,17 +1823,51 @@ dependencies = [
  "url",
 ]
 
+[[package]]
+name = "example-okd-install"
+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-openbao"
+version = "0.1.0"
+dependencies = [
+ "harmony",
+ "harmony_cli",
+ "harmony_macros",
+ "harmony_types",
+ "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",
 ]
@@ -1814,6 +1876,7 @@ dependencies = [
 name = "example-pxe"
 version = "0.1.0"
 dependencies = [
+ "brocade",
  "cidr",
  "env_logger",
  "harmony",
@@ -1828,6 +1891,15 @@ dependencies = [
  "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 +2377,11 @@ name = "harmony"
 version = "0.1.0"
 dependencies = [
  "askama",
+ "assertor",
  "async-trait",
  "base64 0.22.1",
  "bollard",
+ "brocade",
  "chrono",
  "cidr",
  "convert_case",
@@ -2338,6 +2412,7 @@ dependencies = [
  "once_cell",
  "opnsense-config",
  "opnsense-config-xml",
+ "option-ext",
  "pretty_assertions",
  "reqwest 0.11.27",
  "russh",
@@ -3878,6 +3953,7 @@ checksum = "d05e27ee213611ffe7d6348b942e8f942b37114c00cc03cec254295a4a17852e"
 name = "opnsense-config"
 version = "0.1.0"
 dependencies = [
+ "assertor",
  "async-trait",
  "chrono",
  "env_logger",
@@ -4537,9 +4613,9 @@ 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 +4625,9 @@ 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"

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 +1,70 @@
+use std::net::{IpAddr, Ipv4Addr};
+
+use brocade::BrocadeOptions;
+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(192, 168, 55, 101)); // 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,
+        22,
+        &config.username,
+        &config.password,
+        Some(BrocadeOptions {
+            dry_run: true,
+            ..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!("--------------");
+    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 +1,212 @@
+use super::BrocadeClient;
+use crate::{
+    BrocadeInfo, Error, ExecutionMode, InterSwitchLink, InterfaceInfo, MacAddressEntry,
+    PortChannelId, PortOperatingMode, 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(())
+    }
+}

brocade/src/lib.rs

@@ -0,0 +1,338 @@
+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;
+
+mod fast_iron;
+mod network_operating_system;
+mod shell;
+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)]
+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],
+    port: u16,
+    username: &str,
+    password: &str,
+    options: Option<BrocadeOptions>,
+) -> Result<Box<dyn BrocadeClient + Send + Sync>, Error> {
+    let shell = BrocadeShell::init(ip_addresses, port, 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>;
+
+    /// 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,
+        });
+    } 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,
+        });
+    }
+
+    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 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 +1,333 @@
+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,
+    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("no spanning-tree shutdown".into());
+                    commands.push("no fabric isl enable".into());
+                    commands.push("no fabric trunk enable".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(())
+    }
+}

brocade/src/shell.rs

@@ -0,0 +1,370 @@
+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,
+    port: u16,
+    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],
+        port: u16,
+        username: &str,
+        password: &str,
+        options: Option<BrocadeOptions>,
+    ) -> Result<Self, Error> {
+        let ip = ip_addresses
+            .first()
+            .ok_or_else(|| Error::ConfigurationError("No IP addresses provided".to_string()))?;
+
+        let base_options = options.unwrap_or_default();
+        let options = ssh::try_init_client(username, password, ip, base_options).await?;
+
+        Ok(Self {
+            ip: *ip,
+            port,
+            username: username.to_string(),
+            password: password.to_string(),
+            before_all_commands: vec![],
+            after_all_commands: vec![],
+            options,
+        })
+    }
+
+    pub async fn open_session(&self, mode: ExecutionMode) -> Result<BrocadeSession, Error> {
+        BrocadeSession::open(
+            self.ip,
+            self.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 +1,113 @@
+use std::borrow::Cow;
+use std::sync::Arc;
+
+use async_trait::async_trait;
+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(Default, Clone, Debug)]
+pub struct SshOptions {
+    pub preferred_algorithms: russh::Preferred,
+}
+
+impl SshOptions {
+    fn ecdhsa_sha2_nistp256() -> Self {
+        Self {
+            preferred_algorithms: russh::Preferred {
+                kex: Cow::Borrowed(&[ECDH_SHA2_NISTP256]),
+                key: Cow::Borrowed(&[SSH_RSA]),
+                ..Default::default()
+            },
+        }
+    }
+
+    fn legacy() -> Self {
+        Self {
+            preferred_algorithms: russh::Preferred {
+                kex: Cow::Borrowed(&[DH_G1_SHA1]),
+                key: Cow::Borrowed(&[SSH_RSA]),
+                ..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 ssh_options = vec![
+        SshOptions::default(),
+        SshOptions::ecdhsa_sha2_nistp256(),
+        SshOptions::legacy(),
+    ];
+
+    for ssh in ssh_options {
+        let opts = BrocadeOptions {
+            ssh,
+            ..base_options.clone()
+        };
+        let client = create_client(*ip, 22, 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)
+}

examples/monitoring/src/main.rs

@@ -24,13 +24,14 @@ use harmony::{
     },
     topology::K8sAnywhereTopology,
 };
-use harmony_types::net::Url;
+use harmony_types::{k8s_name::K8sName, net::Url};
 
 #[tokio::main]
 async fn main() {
     let discord_receiver = DiscordWebhook {
-        name: "test-discord".to_string(),
+        name: K8sName("test-discord".to_string()),
         url: Url::Url(url::Url::parse("https://discord.doesnt.exist.com").unwrap()),
+        selectors: vec![],
     };
 
     let high_pvc_fill_rate_over_two_days_alert = high_pvc_fill_rate_over_two_days();

examples/monitoring_with_tenant/src/main.rs

@@ -22,8 +22,8 @@ use harmony::{
         tenant::{ResourceLimits, TenantConfig, TenantNetworkPolicy},
     },
 };
-use harmony_types::id::Id;
 use harmony_types::net::Url;
+use harmony_types::{id::Id, k8s_name::K8sName};
 
 #[tokio::main]
 async fn main() {
@@ -43,8 +43,9 @@ async fn main() {
     };
 
     let discord_receiver = DiscordWebhook {
-        name: "test-discord".to_string(),
+        name: K8sName("test-discord".to_string()),
         url: Url::Url(url::Url::parse("https://discord.doesnt.exist.com").unwrap()),
+        selectors: vec![],
     };
 
     let high_pvc_fill_rate_over_two_days_alert = high_pvc_fill_rate_over_two_days();

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

@@ -3,12 +3,13 @@ use std::{
     sync::Arc,
 };
 
+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 = Some(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 +106,7 @@ async fn main() {
                 name: "wk2".to_string(),
             },
         ],
-        switch: vec![],
+        switch_client: switch_client.clone(),
     };
 
     let inventory = Inventory {
@@ -166,3 +189,9 @@ async fn main() {
     .await
     .unwrap();
 }
+
+#[derive(Secret, Serialize, Deserialize, Debug)]
+pub struct BrocadeSwitchAuth {
+    pub username: String,
+    pub password: String,
+}

examples/okd_cluster_alerts/Cargo.toml

@@ -0,0 +1,22 @@
+[package]
+name = "example-okd-cluster-alerts"
+edition = "2024"
+version.workspace = true
+readme.workspace = true
+license.workspace = true
+publish = false
+
+[dependencies]
+harmony = { path = "../../harmony" }
+harmony_cli = { path = "../../harmony_cli" }
+harmony_types = { path = "../../harmony_types" }
+harmony_secret = { path = "../../harmony_secret" }
+harmony_secret_derive = { path = "../../harmony_secret_derive" }
+cidr = { workspace = true }
+tokio = { workspace = true }
+harmony_macros = { path = "../../harmony_macros" }
+log = { workspace = true }
+env_logger = { workspace = true }
+url = { workspace = true }
+serde.workspace = true
+brocade = { path = "../../brocade" }

examples/okd_cluster_alerts/src/main.rs

@@ -0,0 +1,38 @@
+use std::collections::HashMap;
+
+use harmony::{
+    inventory::Inventory,
+    modules::monitoring::{
+        alert_channel::discord_alert_channel::DiscordWebhook,
+        okd::cluster_monitoring::OpenshiftClusterAlertScore,
+    },
+    topology::K8sAnywhereTopology,
+};
+use harmony_macros::hurl;
+use harmony_types::k8s_name::K8sName;
+
+#[tokio::main]
+async fn main() {
+    let mut sel = HashMap::new();
+    sel.insert(
+        "openshift_io_alert_source".to_string(),
+        "platform".to_string(),
+    );
+    let mut sel2 = HashMap::new();
+    sel2.insert("openshift_io_alert_source".to_string(), "".to_string());
+    let selectors = vec![sel, sel2];
+    harmony_cli::run(
+        Inventory::autoload(),
+        K8sAnywhereTopology::from_env(),
+        vec![Box::new(OpenshiftClusterAlertScore {
+            receivers: vec![Box::new(DiscordWebhook {
+                name: K8sName("wills-discord-webhook-example".to_string()),
+                url: hurl!("https://something.io"),
+                selectors: selectors,
+            })],
+        })],
+        None,
+    )
+    .await
+    .unwrap();
+}

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/topology.rs

@@ -1,7 +1,8 @@
+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},
 };
@@ -22,6 +23,26 @@ 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 = Some(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 +59,7 @@ 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 +80,7 @@ pub async fn get_topology() -> HAClusterTopology {
             name: "bootstrap".to_string(),
         },
         workers: vec![],
-        switch: vec![],
+        switch_client: switch_client.clone(),
     }
 }
 
@@ -75,3 +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/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

@@ -1,13 +1,15 @@
+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 harmony_secret::{Secret, SecretManager};
+use serde::{Deserialize, Serialize};
 use std::{net::IpAddr, sync::Arc};
 
 pub async fn get_topology() -> HAClusterTopology {
@@ -16,6 +18,26 @@ 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 = Some(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 +54,7 @@ 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 +75,7 @@ pub async fn get_topology() -> HAClusterTopology {
             name: "cp0".to_string(),
         },
         workers: vec![],
-        switch: vec![],
+        switch_client: switch_client.clone(),
     }
 }
 
@@ -69,3 +92,9 @@ 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::{collections::HashMap, 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/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

@@ -3,10 +3,11 @@ use std::{
     sync::Arc,
 };
 
+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 = Some(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 +78,7 @@ async fn main() {
             name: "cp0".to_string(),
         },
         workers: vec![],
-        switch: vec![],
+        switch_client: switch_client.clone(),
     };
 
     let inventory = Inventory {
@@ -109,3 +133,9 @@ async fn main() {
     .await
     .unwrap();
 }
+
+#[derive(Secret, Serialize, Deserialize, Debug)]
+pub struct BrocadeSwitchAuth {
+    pub username: String,
+    pub password: String,
+}

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

@@ -1,4 +1,4 @@
-use std::{path::PathBuf, sync::Arc};
+use std::{collections::HashMap, path::PathBuf, sync::Arc};
 
 use harmony::{
     inventory::Inventory,
@@ -10,7 +10,7 @@ use harmony::{
     },
     topology::K8sAnywhereTopology,
 };
-use harmony_types::net::Url;
+use harmony_types::{k8s_name::K8sName, net::Url};
 
 #[tokio::main]
 async fn main() {
@@ -22,8 +22,9 @@ async fn main() {
     });
 
     let discord_receiver = DiscordWebhook {
-        name: "test-discord".to_string(),
+        name: K8sName("test-discord".to_string()),
         url: Url::Url(url::Url::parse("https://discord.doesnt.exist.com").unwrap()),
+        selectors: vec![],
     };
 
     let app = ApplicationScore {

examples/rust/.gitignore

@@ -1,3 +1,4 @@
 Dockerfile.harmony
 .harmony_generated
 harmony
+webapp

examples/rust/src/main.rs

@@ -1,4 +1,4 @@
-use std::{path::PathBuf, sync::Arc};
+use std::{collections::HashMap, path::PathBuf, sync::Arc};
 
 use harmony::{
     inventory::Inventory,
@@ -14,6 +14,7 @@ use harmony::{
     topology::K8sAnywhereTopology,
 };
 use harmony_macros::hurl;
+use harmony_types::k8s_name::K8sName;
 
 #[tokio::main]
 async fn main() {
@@ -25,8 +26,9 @@ async fn main() {
     });
 
     let discord_receiver = DiscordWebhook {
-        name: "test-discord".to_string(),
+        name: K8sName("test-discord".to_string()),
         url: hurl!("https://discord.doesnt.exist.com"),
+        selectors: vec![],
     };
 
     let webhook_receiver = WebhookReceiver {

examples/rust/webapp/helm/harmony-example-rust-webapp-chart/Chart.yaml

@@ -0,0 +1,7 @@
+
+apiVersion: v2
+name: harmony-example-rust-webapp-chart
+description: A Helm chart for the harmony-example-rust-webapp web application.
+type: application
+version: 0.1.0
+appVersion: "latest"

examples/rust/webapp/helm/harmony-example-rust-webapp-chart/templates/_helpers.tpl

@@ -0,0 +1,16 @@
+
+{{/*
+Expand the name of the chart.
+*/}}
+{{- define "chart.name" -}}
+{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" }}
+{{- end }}
+
+{{/*
+Create a default fully qualified app name.
+We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec).
+*/}}
+{{- define "chart.fullname" -}}
+{{- $name := default .Chart.Name .Values.nameOverride }}
+{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" }}
+{{- end }}

examples/rust/webapp/helm/harmony-example-rust-webapp-chart/templates/deployment.yaml

@@ -0,0 +1,23 @@
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: {{ include "chart.fullname" . }}
+spec:
+  replicas: {{ .Values.replicaCount }}
+  selector:
+    matchLabels:
+      app: {{ include "chart.name" . }}
+  template:
+    metadata:
+      labels:
+        app: {{ include "chart.name" . }}
+    spec:
+      containers:
+        - name: {{ .Chart.Name }}
+          image: "{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}"
+          imagePullPolicy: {{ .Values.image.pullPolicy }}
+          ports:
+            - name: http
+              containerPort: 3000
+              protocol: TCP

examples/rust/webapp/helm/harmony-example-rust-webapp-chart/templates/ingress.yaml

@@ -0,0 +1,35 @@
+
+{{- if .Values.ingress.enabled -}}
+apiVersion: networking.k8s.io/v1
+kind: Ingress
+metadata:
+  name: {{ include "chart.fullname" . }}
+  annotations:
+    {{- toYaml .Values.ingress.annotations | nindent 4 }}
+spec:
+  {{- if .Values.ingress.tls }}
+  tls:
+    {{- range .Values.ingress.tls }}
+    - hosts:
+        {{- range .hosts }}
+        - {{ . | quote }}
+        {{- end }}
+      secretName: {{ .secretName }}
+    {{- end }}
+  {{- end }}
+  rules:
+    {{- range .Values.ingress.hosts }}
+    - host: {{ .host | quote }}
+      http:
+        paths:
+          {{- range .paths }}
+          - path: {{ .path }}
+            pathType: {{ .pathType }}
+            backend:
+              service:
+                name: {{ include "chart.fullname" $ }}
+                port:
+                  number: 3000
+          {{- end }}
+    {{- end }}
+{{- end }}

examples/rust/webapp/helm/harmony-example-rust-webapp-chart/templates/service.yaml

@@ -0,0 +1,14 @@
+
+apiVersion: v1
+kind: Service
+metadata:
+  name: {{ include "chart.fullname" . }}
+spec:
+  type: {{ .Values.service.type }}
+  ports:
+    - port: {{ .Values.service.port }}
+      targetPort: 3000
+      protocol: TCP
+      name: http
+  selector:
+    app: {{ include "chart.name" . }}

examples/rust/webapp/helm/harmony-example-rust-webapp-chart/values.yaml

@@ -0,0 +1,34 @@
+
+# Default values for harmony-example-rust-webapp-chart.
+# This is a YAML-formatted file.
+# Declare variables to be passed into your templates.
+
+replicaCount: 1
+
+image:
+  repository: hub.nationtech.io/harmony/harmony-example-rust-webapp
+  pullPolicy: IfNotPresent
+  # Overridden by the chart's appVersion
+  tag: "latest"
+
+service:
+  type: ClusterIP
+  port: 3000
+
+ingress:
+  enabled: true
+  # Annotations for cert-manager to handle SSL.
+  annotations:
+    cert-manager.io/cluster-issuer: "letsencrypt-prod"
+    # Add other annotations like nginx ingress class if needed
+    # kubernetes.io/ingress.class: nginx
+  hosts:
+    - host: chart-example.local
+      paths:
+        - path: /
+          pathType: ImplementationSpecific
+  tls:
+   - secretName: harmony-example-rust-webapp-tls
+     hosts:
+       - chart-example.local
+

examples/try_rust_webapp/src/main.rs

@@ -3,13 +3,14 @@ use harmony::{
     modules::{
         application::{
             ApplicationScore, RustWebFramework, RustWebapp,
-            features::{PackagingDeployment, rhob_monitoring::Monitoring},
+            features::{Monitoring, PackagingDeployment},
         },
         monitoring::alert_channel::discord_alert_channel::DiscordWebhook,
     },
     topology::K8sAnywhereTopology,
 };
 use harmony_macros::hurl;
+use harmony_types::k8s_name::K8sName;
 use std::{path::PathBuf, sync::Arc};
 
 #[tokio::main]
@@ -31,8 +32,9 @@ async fn main() {
             Box::new(Monitoring {
                 application: application.clone(),
                 alert_receiver: vec![Box::new(DiscordWebhook {
-                    name: "test-discord".to_string(),
+                    name: K8sName("test-discord".to_string()),
                     url: hurl!("https://discord.doesnt.exist.com"),
+                    selectors: vec![],
                 })],
             }),
         ],

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/interpret/mod.rs

@@ -30,6 +30,7 @@ pub enum InterpretName {
     Lamp,
     ApplicationMonitoring,
     K8sPrometheusCrdAlerting,
+    CephRemoveOsd,
     DiscoverInventoryAgent,
     CephClusterHealth,
     Custom(&'static str),
@@ -61,6 +62,7 @@ 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),

harmony/src/domain/topology/ha_cluster.rs

@@ -1,33 +1,28 @@
 use async_trait::async_trait;
 use harmony_macros::ip;
-use harmony_types::net::MacAddress;
-use harmony_types::net::Url;
+use harmony_types::{
+    net::{MacAddress, Url},
+    switch::PortLocation,
+};
+use kube::api::ObjectMeta;
 use log::debug;
 use log::info;
 
-use crate::data::FileContent;
-use crate::executors::ExecutorError;
+use crate::modules::okd::crd::nmstate::{self, NodeNetworkConfigurationPolicy};
 use crate::topology::PxeOptions;
+use crate::{data::FileContent, modules::okd::crd::nmstate::NMState};
+use crate::{
+    executors::ExecutorError, modules::okd::crd::nmstate::NodeNetworkConfigurationPolicySpec,
+};
 
-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::{
+    DHCPStaticEntry, DhcpServer, DnsRecord, DnsRecordType, DnsServer, Firewall, HostNetworkConfig,
+    HttpServer, IpAddress, K8sclient, LoadBalancer, LoadBalancerService, LogicalHost,
+    PreparationError, PreparationOutcome, Router, Switch, SwitchClient, SwitchError, TftpServer,
+    Topology, k8s::K8sClient,
+};
 
-use super::Topology;
-use super::k8s::K8sClient;
+use std::collections::BTreeMap;
 use std::sync::Arc;
 
 #[derive(Debug, Clone)]
@@ -40,10 +35,11 @@ pub struct HAClusterTopology {
     pub tftp_server: Arc<dyn TftpServer>,
     pub http_server: Arc<dyn HttpServer>,
     pub dns_server: Arc<dyn DnsServer>,
+    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>,
 }
 
 #[async_trait]
@@ -62,9 +58,17 @@ 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 +93,193 @@ impl HAClusterTopology {
             .to_string()
     }
 
+    async fn ensure_nmstate_operator_installed(&self) -> Result<(), String> {
+        let k8s_client = self.k8s_client().await?;
+
+        debug!("Installing NMState controller...");
+        k8s_client.apply_url(url::Url::parse("https://github.com/nmstate/kubernetes-nmstate/releases/download/v0.84.0/nmstate.io_nmstates.yaml
+").unwrap(), Some("nmstate"))
+            .await
+            .map_err(|e| e.to_string())?;
+
+        debug!("Creating NMState namespace...");
+        k8s_client.apply_url(url::Url::parse("https://github.com/nmstate/kubernetes-nmstate/releases/download/v0.84.0/namespace.yaml
+").unwrap(), Some("nmstate"))
+            .await
+            .map_err(|e| e.to_string())?;
+
+        debug!("Creating NMState service account...");
+        k8s_client.apply_url(url::Url::parse("https://github.com/nmstate/kubernetes-nmstate/releases/download/v0.84.0/service_account.yaml
+").unwrap(), Some("nmstate"))
+            .await
+            .map_err(|e| e.to_string())?;
+
+        debug!("Creating NMState role...");
+        k8s_client.apply_url(url::Url::parse("https://github.com/nmstate/kubernetes-nmstate/releases/download/v0.84.0/role.yaml
+").unwrap(), Some("nmstate"))
+            .await
+            .map_err(|e| e.to_string())?;
+
+        debug!("Creating NMState role binding...");
+        k8s_client.apply_url(url::Url::parse("https://github.com/nmstate/kubernetes-nmstate/releases/download/v0.84.0/role_binding.yaml
+").unwrap(), Some("nmstate"))
+            .await
+            .map_err(|e| e.to_string())?;
+
+        debug!("Creating NMState operator...");
+        k8s_client.apply_url(url::Url::parse("https://github.com/nmstate/kubernetes-nmstate/releases/download/v0.84.0/operator.yaml
+").unwrap(), Some("nmstate"))
+            .await
+            .map_err(|e| e.to_string())?;
+
+        k8s_client
+            .wait_until_deployment_ready("nmstate-operator", Some("nmstate"), None)
+            .await?;
+
+        let nmstate = NMState {
+            metadata: ObjectMeta {
+                name: Some("nmstate".to_string()),
+                ..Default::default()
+            },
+            ..Default::default()
+        };
+        debug!("Creating NMState: {nmstate:#?}");
+        k8s_client
+            .apply(&nmstate, None)
+            .await
+            .map_err(|e| e.to_string())?;
+
+        Ok(())
+    }
+
+    fn get_next_bond_id(&self) -> u8 {
+        42 // FIXME: Find a better way to declare the bond id
+    }
+
+    async fn configure_bond(&self, config: &HostNetworkConfig) -> Result<(), SwitchError> {
+        self.ensure_nmstate_operator_installed()
+            .await
+            .map_err(|e| {
+                SwitchError::new(format!(
+                    "Can't configure bond, NMState operator not available: {e}"
+                ))
+            })?;
+
+        let bond_config = self.create_bond_configuration(config);
+        debug!(
+            "Applying NMState bond config for host {}: {bond_config:#?}",
+            config.host_id
+        );
+        self.k8s_client()
+            .await
+            .unwrap()
+            .apply(&bond_config, None)
+            .await
+            .map_err(|e| SwitchError::new(format!("Failed to configure bond: {e}")))?;
+
+        Ok(())
+    }
+
+    fn create_bond_configuration(
+        &self,
+        config: &HostNetworkConfig,
+    ) -> NodeNetworkConfigurationPolicy {
+        let host_name = &config.host_id;
+        let bond_id = self.get_next_bond_id();
+        let bond_name = format!("bond{bond_id}");
+
+        info!("Configuring bond '{bond_name}' for host '{host_name}'...");
+
+        let mut bond_mtu: Option<u32> = None;
+        let mut copy_mac_from: Option<String> = None;
+        let mut bond_ports = Vec::new();
+        let mut interfaces: Vec<nmstate::InterfaceSpec> = Vec::new();
+
+        for switch_port in &config.switch_ports {
+            let interface_name = switch_port.interface.name.clone();
+
+            interfaces.push(nmstate::InterfaceSpec {
+                name: interface_name.clone(),
+                description: Some(format!("Member of bond {bond_name}")),
+                r#type: "ethernet".to_string(),
+                state: "up".to_string(),
+                mtu: Some(switch_port.interface.mtu),
+                mac_address: Some(switch_port.interface.mac_address.to_string()),
+                ipv4: Some(nmstate::IpStackSpec {
+                    enabled: Some(false),
+                    ..Default::default()
+                }),
+                ipv6: Some(nmstate::IpStackSpec {
+                    enabled: Some(false),
+                    ..Default::default()
+                }),
+                link_aggregation: None,
+                ..Default::default()
+            });
+
+            bond_ports.push(interface_name.clone());
+
+            // Use the first port's details for the bond mtu and mac address
+            if bond_mtu.is_none() {
+                bond_mtu = Some(switch_port.interface.mtu);
+            }
+            if copy_mac_from.is_none() {
+                copy_mac_from = Some(interface_name);
+            }
+        }
+
+        interfaces.push(nmstate::InterfaceSpec {
+            name: bond_name.clone(),
+            description: Some(format!("Network bond for host {host_name}")),
+            r#type: "bond".to_string(),
+            state: "up".to_string(),
+            copy_mac_from,
+            ipv4: Some(nmstate::IpStackSpec {
+                dhcp: Some(true),
+                enabled: Some(true),
+                ..Default::default()
+            }),
+            ipv6: Some(nmstate::IpStackSpec {
+                dhcp: Some(true),
+                autoconf: Some(true),
+                enabled: Some(true),
+                ..Default::default()
+            }),
+            link_aggregation: Some(nmstate::BondSpec {
+                mode: "802.3ad".to_string(),
+                ports: bond_ports,
+                ..Default::default()
+            }),
+            ..Default::default()
+        });
+
+        NodeNetworkConfigurationPolicy {
+            metadata: ObjectMeta {
+                name: Some(format!("{host_name}-bond-config")),
+                ..Default::default()
+            },
+            spec: NodeNetworkConfigurationPolicySpec {
+                node_selector: Some(BTreeMap::from([(
+                    "kubernetes.io/hostname".to_string(),
+                    host_name.to_string(),
+                )])),
+                desired_state: nmstate::DesiredStateSpec { interfaces },
+            },
+        }
+    }
+
+    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 switch: {e}")))?;
+
+        Ok(())
+    }
+
     pub fn autoload() -> Self {
         let dummy_infra = Arc::new(DummyInfra {});
         let dummy_host = LogicalHost {
@@ -97,6 +288,7 @@ impl HAClusterTopology {
         };
 
         Self {
+            kubeconfig: None,
             domain_name: "DummyTopology".to_string(),
             router: dummy_infra.clone(),
             load_balancer: dummy_infra.clone(),
@@ -105,10 +297,10 @@ impl HAClusterTopology {
             tftp_server: dummy_infra.clone(),
             http_server: dummy_infra.clone(),
             dns_server: dummy_infra.clone(),
+            switch_client: dummy_infra.clone(),
             bootstrap_host: dummy_host,
             control_plane: vec![],
             workers: vec![],
-            switch: vec![],
         }
     }
 }
@@ -263,6 +455,27 @@ impl HttpServer for HAClusterTopology {
     }
 }
 
+#[async_trait]
+impl Switch for HAClusterTopology {
+    async fn setup_switch(&self) -> Result<(), SwitchError> {
+        self.switch_client.setup().await?;
+        Ok(())
+    }
+
+    async fn get_port_for_mac_address(
+        &self,
+        mac_address: &MacAddress,
+    ) -> Result<Option<PortLocation>, SwitchError> {
+        let port = self.switch_client.find_port(mac_address).await?;
+        Ok(port)
+    }
+
+    async fn configure_host_network(&self, config: &HostNetworkConfig) -> Result<(), SwitchError> {
+        self.configure_bond(config).await?;
+        self.configure_port_channel(config).await
+    }
+}
+
 #[derive(Debug)]
 pub struct DummyInfra;
 
@@ -332,8 +545,8 @@ 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 +662,25 @@ impl DnsServer for DummyInfra {
         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)
+    }
+}

harmony/src/domain/topology/k8s.rs

@@ -5,14 +5,16 @@ use k8s_openapi::{
     ClusterResourceScope, NamespaceResourceScope,
     api::{
         apps::v1::Deployment,
-        core::v1::{Pod, PodStatus},
+        core::v1::{Pod, ServiceAccount},
     },
+    apimachinery::pkg::version::Info,
 };
 use kube::{
-    Client, Config, Error, Resource,
+    Client, Config, Discovery, Error, Resource,
     api::{Api, AttachParams, DeleteParams, ListParams, Patch, PatchParams, ResourceExt},
     config::{KubeConfigOptions, Kubeconfig},
-    core::ErrorResponse,
+    core::{DynamicResourceScope, ErrorResponse},
+    discovery::{ApiCapabilities, Scope},
     error::DiscoveryError,
     runtime::reflector::Lookup,
 };
@@ -21,11 +23,12 @@ use kube::{
     api::{ApiResource, GroupVersionKind},
     runtime::wait::await_condition,
 };
-use log::{debug, error, trace};
+use log::{debug, error, info, trace, warn};
 use serde::{Serialize, de::DeserializeOwned};
-use serde_json::{Value, json};
+use serde_json::json;
 use similar::TextDiff;
 use tokio::{io::AsyncReadExt, time::sleep};
+use url::Url;
 
 #[derive(new, Clone)]
 pub struct K8sClient {
@@ -59,6 +62,22 @@ impl K8sClient {
         })
     }
 
+    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,
@@ -71,7 +90,25 @@ impl K8sClient {
         } else {
             Api::default_namespaced_with(self.client.clone(), &gvk)
         };
-        Ok(resource.get(name).await?)
+
+        resource.get(name).await
+    }
+
+    pub async fn get_secret_json_value(
+        &self,
+        name: &str,
+        namespace: Option<&str>,
+    ) -> Result<DynamicObject, Error> {
+        self.get_resource_json_value(
+            name,
+            namespace,
+            &GroupVersionKind {
+                group: "".to_string(),
+                version: "v1".to_string(),
+                kind: "Secret".to_string(),
+            },
+        )
+        .await
     }
 
     pub async fn get_deployment(
@@ -80,11 +117,15 @@ 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> {
@@ -93,7 +134,8 @@ 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(
@@ -114,7 +156,7 @@ impl K8sClient {
             }
         });
         let pp = PatchParams::default();
-        let scale = Patch::Apply(&patch);
+        let scale = Patch::Merge(&patch);
         deployments.patch_scale(name, &pp, &scale).await?;
         Ok(())
     }
@@ -136,9 +178,9 @@ 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>;
 
@@ -148,9 +190,9 @@ 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(())
@@ -240,7 +282,7 @@ 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
@@ -312,6 +354,169 @@ impl K8sClient {
         }
     }
 
+    fn get_api_for_dynamic_object(
+        &self,
+        object: &DynamicObject,
+        ns: Option<&str>,
+    ) -> Result<Api<DynamicObject>, Error> {
+        let api_resource = object
+            .types
+            .as_ref()
+            .and_then(|t| {
+                let parts: Vec<&str> = t.api_version.split('/').collect();
+                match parts.as_slice() {
+                    [version] => Some(ApiResource::from_gvk(&GroupVersionKind::gvk(
+                        "", version, &t.kind,
+                    ))),
+                    [group, version] => Some(ApiResource::from_gvk(&GroupVersionKind::gvk(
+                        group, version, &t.kind,
+                    ))),
+                    _ => None,
+                }
+            })
+            .ok_or_else(|| {
+                Error::BuildRequest(kube::core::request::Error::Validation(
+                    "Invalid apiVersion in DynamicObject {object:#?}".to_string(),
+                ))
+            })?;
+
+        match ns {
+            Some(ns) => Ok(Api::namespaced_with(self.client.clone(), ns, &api_resource)),
+            None => Ok(Api::default_namespaced_with(
+                self.client.clone(),
+                &api_resource,
+            )),
+        }
+    }
+
+    pub async fn apply_dynamic_many(
+        &self,
+        resource: &[DynamicObject],
+        namespace: Option<&str>,
+        force_conflicts: bool,
+    ) -> Result<Vec<DynamicObject>, Error> {
+        let mut result = Vec::new();
+        for r in resource.iter() {
+            result.push(self.apply_dynamic(r, namespace, force_conflicts).await?);
+        }
+
+        Ok(result)
+    }
+
+    /// Apply DynamicObject resource to the cluster
+    pub async fn apply_dynamic(
+        &self,
+        resource: &DynamicObject,
+        namespace: Option<&str>,
+        force_conflicts: bool,
+    ) -> Result<DynamicObject, Error> {
+        // Build API for this dynamic object
+        let api = self.get_api_for_dynamic_object(resource, namespace)?;
+        let name = resource
+            .metadata
+            .name
+            .as_ref()
+            .ok_or_else(|| {
+                Error::BuildRequest(kube::core::request::Error::Validation(
+                    "DynamicObject must have metadata.name".to_string(),
+                ))
+            })?
+            .as_str();
+
+        debug!(
+            "Applying dynamic resource kind={:?} apiVersion={:?} name='{}' ns={:?}",
+            resource.types.as_ref().map(|t| &t.kind),
+            resource.types.as_ref().map(|t| &t.api_version),
+            name,
+            namespace
+        );
+        trace!(
+            "Dynamic resource payload:\n{:#}",
+            serde_json::to_value(resource).unwrap_or(serde_json::Value::Null)
+        );
+
+        // Using same field manager as in apply()
+        let mut patch_params = PatchParams::apply("harmony");
+        patch_params.force = force_conflicts;
+
+        if *crate::config::DRY_RUN {
+            // Dry-run path: fetch current, show diff, and return appropriate object
+            match api.get(name).await {
+                Ok(current) => {
+                    trace!("Received current dynamic value {current:#?}");
+
+                    println!("\nPerforming dry-run for resource: '{}'", name);
+
+                    // Serialize current and new, and strip status from current if present
+                    let mut current_yaml =
+                        serde_yaml::to_value(&current).unwrap_or_else(|_| serde_yaml::Value::Null);
+                    if let Some(map) = current_yaml.as_mapping_mut() {
+                        if map.contains_key(&serde_yaml::Value::String("status".to_string())) {
+                            let removed =
+                                map.remove(&serde_yaml::Value::String("status".to_string()));
+                            trace!("Removed status from current dynamic object: {:?}", removed);
+                        } else {
+                            trace!(
+                                "Did not find status entry for current dynamic object {}/{}",
+                                current.metadata.namespace.as_deref().unwrap_or(""),
+                                current.metadata.name.as_deref().unwrap_or("")
+                            );
+                        }
+                    }
+
+                    let current_yaml = serde_yaml::to_string(&current_yaml)
+                        .unwrap_or_else(|_| "Failed to serialize current resource".to_string());
+                    let new_yaml = serde_yaml::to_string(resource)
+                        .unwrap_or_else(|_| "Failed to serialize new resource".to_string());
+
+                    if current_yaml == new_yaml {
+                        println!("No changes detected.");
+                        return Ok(current);
+                    }
+
+                    println!("Changes detected:");
+                    let diff = TextDiff::from_lines(&current_yaml, &new_yaml);
+                    for change in diff.iter_all_changes() {
+                        let sign = match change.tag() {
+                            similar::ChangeTag::Delete => "-",
+                            similar::ChangeTag::Insert => "+",
+                            similar::ChangeTag::Equal => " ",
+                        };
+                        print!("{}{}", sign, change);
+                    }
+
+                    // Return the incoming resource as the would-be applied state
+                    Ok(resource.clone())
+                }
+                Err(Error::Api(ErrorResponse { code: 404, .. })) => {
+                    println!("\nPerforming dry-run for new resource: '{}'", name);
+                    println!(
+                        "Resource does not exist. It would be created with the following content:"
+                    );
+                    let new_yaml = serde_yaml::to_string(resource)
+                        .unwrap_or_else(|_| "Failed to serialize new resource".to_string());
+                    for line in new_yaml.lines() {
+                        println!("+{}", line);
+                    }
+                    Ok(resource.clone())
+                }
+                Err(e) => {
+                    error!("Failed to get dynamic resource '{}': {}", name, e);
+                    Err(e)
+                }
+            }
+        } else {
+            // Real apply via server-side apply
+            debug!("Patching (server-side apply) dynamic resource '{}'", name);
+            api.patch(name, &patch_params, &Patch::Apply(resource))
+                .await
+                .map_err(|e| {
+                    error!("Failed to apply dynamic resource '{}': {}", name, e);
+                    e
+                })
+        }
+    }
+
     /// Apply a resource in namespace
     ///
     /// See `kubectl apply` for more information on the expected behavior of this function
@@ -346,14 +551,14 @@ 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 {}/{}",
@@ -382,14 +587,14 @@ 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:"
                     );
@@ -398,14 +603,14 @@ 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)
                 }
             }
@@ -420,7 +625,7 @@ 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() {
@@ -485,10 +690,7 @@ 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?;
 
@@ -497,6 +699,51 @@ impl K8sClient {
         Ok(())
     }
 
+    /// 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(())
+    }
+
     pub(crate) async fn from_kubeconfig(path: &str) -> Option<K8sClient> {
         let k = match Kubeconfig::read_from(path) {
             Ok(k) => k,
@@ -516,6 +763,31 @@ impl K8sClient {
     }
 }
 
+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>;
 }

harmony/src/domain/topology/k8s_anywhere.rs

@@ -1,7 +1,12 @@
-use std::{process::Command, sync::Arc};
+use std::{collections::BTreeMap, process::Command, sync::Arc, time::Duration};
 
 use async_trait::async_trait;
-use kube::api::GroupVersionKind;
+use base64::{Engine, engine::general_purpose};
+use k8s_openapi::api::{
+    core::v1::Secret,
+    rbac::v1::{ClusterRoleBinding, RoleRef, Subject},
+};
+use kube::api::{DynamicObject, GroupVersionKind, ObjectMeta};
 use log::{debug, info, warn};
 use serde::Serialize;
 use tokio::sync::OnceCell;
@@ -12,14 +17,26 @@ use crate::{
     inventory::Inventory,
     modules::{
         k3d::K3DInstallationScore,
-        monitoring::kube_prometheus::crd::{
-            crd_alertmanager_config::CRDPrometheus,
-            prometheus_operator::prometheus_operator_helm_chart_score,
-            rhob_alertmanager_config::RHOBObservability,
+        k8s::ingress::{K8sIngressScore, PathType},
+        monitoring::{
+            grafana::{grafana::Grafana, helm::helm_grafana::grafana_helm_chart_score},
+            kube_prometheus::crd::{
+                crd_alertmanager_config::CRDPrometheus,
+                crd_grafana::{
+                    Grafana as GrafanaCRD, GrafanaCom, GrafanaDashboard,
+                    GrafanaDashboardDatasource, GrafanaDashboardSpec, GrafanaDatasource,
+                    GrafanaDatasourceConfig, GrafanaDatasourceJsonData,
+                    GrafanaDatasourceSecureJsonData, GrafanaDatasourceSpec, GrafanaSpec,
+                },
+                crd_prometheuses::LabelSelector,
+                prometheus_operator::prometheus_operator_helm_chart_score,
+                rhob_alertmanager_config::RHOBObservability,
+                service_monitor::ServiceMonitor,
+            },
         },
         prometheus::{
             k8s_prometheus_alerting_score::K8sPrometheusCRDAlertingScore,
-            prometheus::PrometheusApplicationMonitoring, rhob_alerting_score::RHOBAlertingScore,
+            prometheus::PrometheusMonitoring, rhob_alerting_score::RHOBAlertingScore,
         },
     },
     score::Score,
@@ -47,6 +64,13 @@ struct K8sState {
     message: String,
 }
 
+#[derive(Debug, Clone)]
+pub enum KubernetesDistribution {
+    OpenshiftFamily,
+    K3sFamily,
+    Default,
+}
+
 #[derive(Debug, Clone)]
 enum K8sSource {
     LocalK3d,
@@ -57,6 +81,7 @@ enum K8sSource {
 pub struct K8sAnywhereTopology {
     k8s_state: Arc<OnceCell<Option<K8sState>>>,
     tenant_manager: Arc<OnceCell<K8sTenantManager>>,
+    k8s_distribution: Arc<OnceCell<KubernetesDistribution>>,
     config: Arc<K8sAnywhereConfig>,
 }
 
@@ -78,41 +103,172 @@ impl K8sclient for K8sAnywhereTopology {
 }
 
 #[async_trait]
-impl PrometheusApplicationMonitoring<CRDPrometheus> for K8sAnywhereTopology {
+impl Grafana for K8sAnywhereTopology {
+    async fn ensure_grafana_operator(
+        &self,
+        inventory: &Inventory,
+    ) -> Result<PreparationOutcome, PreparationError> {
+        debug!("ensure grafana operator");
+        let client = self.k8s_client().await.unwrap();
+        let grafana_gvk = GroupVersionKind {
+            group: "grafana.integreatly.org".to_string(),
+            version: "v1beta1".to_string(),
+            kind: "Grafana".to_string(),
+        };
+        let name = "grafanas.grafana.integreatly.org";
+        let ns = "grafana";
+
+        let grafana_crd = client
+            .get_resource_json_value(name, Some(ns), &grafana_gvk)
+            .await;
+        match grafana_crd {
+            Ok(_) => {
+                return Ok(PreparationOutcome::Success {
+                    details: "Found grafana CRDs in cluster".to_string(),
+                });
+            }
+
+            Err(_) => {
+                return self
+                    .install_grafana_operator(inventory, Some("grafana"))
+                    .await;
+            }
+        };
+    }
+    async fn install_grafana(&self) -> Result<PreparationOutcome, PreparationError> {
+        let ns = "grafana";
+
+        let mut label = BTreeMap::new();
+
+        label.insert("dashboards".to_string(), "grafana".to_string());
+
+        let label_selector = LabelSelector {
+            match_labels: label.clone(),
+            match_expressions: vec![],
+        };
+
+        let client = self.k8s_client().await?;
+
+        let grafana = self.build_grafana(ns, &label);
+
+        client.apply(&grafana, Some(ns)).await?;
+        //TODO change this to a ensure ready or something better than just a timeout
+        client
+            .wait_until_deployment_ready(
+                "grafana-grafana-deployment",
+                Some("grafana"),
+                Some(Duration::from_secs(30)),
+            )
+            .await?;
+
+        let sa_name = "grafana-grafana-sa";
+        let token_secret_name = "grafana-sa-token-secret";
+
+        let sa_token_secret = self.build_sa_token_secret(token_secret_name, sa_name, ns);
+
+        client.apply(&sa_token_secret, Some(ns)).await?;
+        let secret_gvk = GroupVersionKind {
+            group: "".to_string(),
+            version: "v1".to_string(),
+            kind: "Secret".to_string(),
+        };
+
+        let secret = client
+            .get_resource_json_value(token_secret_name, Some(ns), &secret_gvk)
+            .await?;
+
+        let token = format!(
+            "Bearer {}",
+            self.extract_and_normalize_token(&secret).unwrap()
+        );
+
+        debug!("creating grafana clusterrole binding");
+
+        let clusterrolebinding =
+            self.build_cluster_rolebinding(sa_name, "cluster-monitoring-view", ns);
+
+        client.apply(&clusterrolebinding, Some(ns)).await?;
+
+        debug!("creating grafana datasource crd");
+
+        let thanos_url = format!(
+            "https://{}",
+            self.get_domain("thanos-querier-openshift-monitoring")
+                .await
+                .unwrap()
+        );
+
+        let thanos_openshift_datasource = self.build_grafana_datasource(
+            "thanos-openshift-monitoring",
+            ns,
+            &label_selector,
+            &thanos_url,
+            &token,
+        );
+
+        client.apply(&thanos_openshift_datasource, Some(ns)).await?;
+
+        debug!("creating grafana dashboard crd");
+        let dashboard = self.build_grafana_dashboard(ns, &label_selector);
+
+        client.apply(&dashboard, Some(ns)).await?;
+        debug!("creating grafana ingress");
+        let grafana_ingress = self.build_grafana_ingress(ns).await;
+
+        grafana_ingress
+            .interpret(&Inventory::empty(), self)
+            .await
+            .map_err(|e| PreparationError::new(e.to_string()))?;
+
+        Ok(PreparationOutcome::Success {
+            details: "Installed grafana composants".to_string(),
+        })
+    }
+}
+
+#[async_trait]
+impl PrometheusMonitoring<CRDPrometheus> for K8sAnywhereTopology {
     async fn install_prometheus(
         &self,
         sender: &CRDPrometheus,
-        inventory: &Inventory,
-        receivers: Option<Vec<Box<dyn AlertReceiver<CRDPrometheus>>>>,
+        _inventory: &Inventory,
+        _receivers: Option<Vec<Box<dyn AlertReceiver<CRDPrometheus>>>>,
+    ) -> Result<PreparationOutcome, PreparationError> {
+        let client = self.k8s_client().await?;
+
+        for monitor in sender.service_monitor.iter() {
+            client
+                .apply(monitor, Some(&sender.namespace))
+                .await
+                .map_err(|e| PreparationError::new(e.to_string()))?;
+        }
+        Ok(PreparationOutcome::Success {
+            details: "successfuly installed prometheus components".to_string(),
+        })
+    }
+
+    async fn ensure_prometheus_operator(
+        &self,
+        sender: &CRDPrometheus,
+        _inventory: &Inventory,
     ) -> Result<PreparationOutcome, PreparationError> {
         let po_result = self.ensure_prometheus_operator(sender).await?;
 
-        if po_result == PreparationOutcome::Noop {
-            debug!("Skipping Prometheus CR installation due to missing operator.");
-            return Ok(po_result);
-        }
-
-        let result = self
-            .get_k8s_prometheus_application_score(sender.clone(), receivers)
-            .await
-            .interpret(inventory, self)
-            .await;
-
-        match result {
-            Ok(outcome) => match outcome.status {
-                InterpretStatus::SUCCESS => Ok(PreparationOutcome::Success {
-                    details: outcome.message,
-                }),
-                InterpretStatus::NOOP => Ok(PreparationOutcome::Noop),
-                _ => Err(PreparationError::new(outcome.message)),
-            },
-            Err(err) => Err(PreparationError::new(err.to_string())),
+        match po_result {
+            PreparationOutcome::Success { details: _ } => {
+                debug!("Detected prometheus crds operator present in cluster.");
+                return Ok(po_result);
+            }
+            PreparationOutcome::Noop => {
+                debug!("Skipping Prometheus CR installation due to missing operator.");
+                return Ok(po_result);
+            }
         }
     }
 }
 
 #[async_trait]
-impl PrometheusApplicationMonitoring<RHOBObservability> for K8sAnywhereTopology {
+impl PrometheusMonitoring<RHOBObservability> for K8sAnywhereTopology {
     async fn install_prometheus(
         &self,
         sender: &RHOBObservability,
@@ -146,6 +302,14 @@ impl PrometheusApplicationMonitoring<RHOBObservability> for K8sAnywhereTopology
             Err(err) => Err(PreparationError::new(err.to_string())),
         }
     }
+
+    async fn ensure_prometheus_operator(
+        &self,
+        sender: &RHOBObservability,
+        inventory: &Inventory,
+    ) -> Result<PreparationOutcome, PreparationError> {
+        todo!()
+    }
 }
 
 impl Serialize for K8sAnywhereTopology {
@@ -162,6 +326,7 @@ impl K8sAnywhereTopology {
         Self {
             k8s_state: Arc::new(OnceCell::new()),
             tenant_manager: Arc::new(OnceCell::new()),
+            k8s_distribution: Arc::new(OnceCell::new()),
             config: Arc::new(K8sAnywhereConfig::from_env()),
         }
     }
@@ -170,10 +335,216 @@ impl K8sAnywhereTopology {
         Self {
             k8s_state: Arc::new(OnceCell::new()),
             tenant_manager: Arc::new(OnceCell::new()),
+            k8s_distribution: Arc::new(OnceCell::new()),
             config: Arc::new(config),
         }
     }
 
+    pub async fn get_k8s_distribution(&self) -> Result<&KubernetesDistribution, PreparationError> {
+        self.k8s_distribution
+            .get_or_try_init(async || {
+                let client = self.k8s_client().await.unwrap();
+
+                let discovery = client.discovery().await.map_err(|e| {
+                    PreparationError::new(format!("Could not discover API groups: {}", e))
+                })?;
+
+                let version = client.get_apiserver_version().await.map_err(|e| {
+                    PreparationError::new(format!("Could not get server version: {}", e))
+                })?;
+
+                // OpenShift / OKD
+                if discovery
+                    .groups()
+                    .any(|g| g.name() == "project.openshift.io")
+                {
+                    return Ok(KubernetesDistribution::OpenshiftFamily);
+                }
+
+                // K3d / K3s
+                if version.git_version.contains("k3s") {
+                    return Ok(KubernetesDistribution::K3sFamily);
+                }
+
+                return Ok(KubernetesDistribution::Default);
+            })
+            .await
+    }
+
+    fn extract_and_normalize_token(&self, secret: &DynamicObject) -> Option<String> {
+        let token_b64 = secret
+            .data
+            .get("token")
+            .or_else(|| secret.data.get("data").and_then(|d| d.get("token")))
+            .and_then(|v| v.as_str())?;
+
+        let bytes = general_purpose::STANDARD.decode(token_b64).ok()?;
+
+        let s = String::from_utf8(bytes).ok()?;
+
+        let cleaned = s
+            .trim_matches(|c: char| c.is_whitespace() || c == '\0')
+            .to_string();
+        Some(cleaned)
+    }
+
+    pub fn build_cluster_rolebinding(
+        &self,
+        service_account_name: &str,
+        clusterrole_name: &str,
+        ns: &str,
+    ) -> ClusterRoleBinding {
+        ClusterRoleBinding {
+            metadata: ObjectMeta {
+                name: Some(format!("{}-view-binding", service_account_name)),
+                ..Default::default()
+            },
+            role_ref: RoleRef {
+                api_group: "rbac.authorization.k8s.io".into(),
+                kind: "ClusterRole".into(),
+                name: clusterrole_name.into(),
+            },
+            subjects: Some(vec![Subject {
+                kind: "ServiceAccount".into(),
+                name: service_account_name.into(),
+                namespace: Some(ns.into()),
+                ..Default::default()
+            }]),
+        }
+    }
+
+    pub fn build_sa_token_secret(
+        &self,
+        secret_name: &str,
+        service_account_name: &str,
+        ns: &str,
+    ) -> Secret {
+        let mut annotations = BTreeMap::new();
+        annotations.insert(
+            "kubernetes.io/service-account.name".to_string(),
+            service_account_name.to_string(),
+        );
+
+        Secret {
+            metadata: ObjectMeta {
+                name: Some(secret_name.into()),
+                namespace: Some(ns.into()),
+                annotations: Some(annotations),
+                ..Default::default()
+            },
+            type_: Some("kubernetes.io/service-account-token".to_string()),
+            ..Default::default()
+        }
+    }
+
+    fn build_grafana_datasource(
+        &self,
+        name: &str,
+        ns: &str,
+        label_selector: &LabelSelector,
+        url: &str,
+        token: &str,
+    ) -> GrafanaDatasource {
+        let mut json_data = BTreeMap::new();
+        json_data.insert("timeInterval".to_string(), "5s".to_string());
+
+        GrafanaDatasource {
+            metadata: ObjectMeta {
+                name: Some(name.to_string()),
+                namespace: Some(ns.to_string()),
+                ..Default::default()
+            },
+            spec: GrafanaDatasourceSpec {
+                instance_selector: label_selector.clone(),
+                allow_cross_namespace_import: Some(true),
+                values_from: None,
+                datasource: GrafanaDatasourceConfig {
+                    access: "proxy".to_string(),
+                    name: name.to_string(),
+                    r#type: "prometheus".to_string(),
+                    url: url.to_string(),
+                    database: None,
+                    json_data: Some(GrafanaDatasourceJsonData {
+                        time_interval: Some("60s".to_string()),
+                        http_header_name1: Some("Authorization".to_string()),
+                        tls_skip_verify: Some(true),
+                        oauth_pass_thru: Some(true),
+                    }),
+                    secure_json_data: Some(GrafanaDatasourceSecureJsonData {
+                        http_header_value1: Some(format!("Bearer {token}")),
+                    }),
+                    is_default: Some(false),
+                    editable: Some(true),
+                },
+            },
+        }
+    }
+
+    fn build_grafana_dashboard(
+        &self,
+        ns: &str,
+        label_selector: &LabelSelector,
+    ) -> GrafanaDashboard {
+        let graf_dashboard = GrafanaDashboard {
+            metadata: ObjectMeta {
+                name: Some(format!("grafana-dashboard-{}", ns)),
+                namespace: Some(ns.to_string()),
+                ..Default::default()
+            },
+            spec: GrafanaDashboardSpec {
+                resync_period: Some("30s".to_string()),
+                instance_selector: label_selector.clone(),
+                datasources: Some(vec![GrafanaDashboardDatasource {
+                    input_name: "DS_PROMETHEUS".to_string(),
+                    datasource_name: "thanos-openshift-monitoring".to_string(),
+                }]),
+                json: None,
+                grafana_com: Some(GrafanaCom {
+                    id: 17406,
+                    revision: None,
+                }),
+            },
+        };
+        graf_dashboard
+    }
+
+    fn build_grafana(&self, ns: &str, labels: &BTreeMap<String, String>) -> GrafanaCRD {
+        let grafana = GrafanaCRD {
+            metadata: ObjectMeta {
+                name: Some(format!("grafana-{}", ns)),
+                namespace: Some(ns.to_string()),
+                labels: Some(labels.clone()),
+                ..Default::default()
+            },
+            spec: GrafanaSpec {
+                config: None,
+                admin_user: None,
+                admin_password: None,
+                ingress: None,
+                persistence: None,
+                resources: None,
+            },
+        };
+        grafana
+    }
+
+    async fn build_grafana_ingress(&self, ns: &str) -> K8sIngressScore {
+        let domain = self.get_domain(&format!("grafana-{}", ns)).await.unwrap();
+        let name = format!("{}-grafana", ns);
+        let backend_service = format!("grafana-{}-service", ns);
+
+        K8sIngressScore {
+            name: fqdn::fqdn!(&name),
+            host: fqdn::fqdn!(&domain),
+            backend_service: fqdn::fqdn!(&backend_service),
+            port: 3000,
+            path: Some("/".to_string()),
+            path_type: Some(PathType::Prefix),
+            namespace: Some(fqdn::fqdn!(&ns)),
+            ingress_class_name: Some("openshift-default".to_string()),
+        }
+    }
+
     async fn get_cluster_observability_operator_prometheus_application_score(
         &self,
         sender: RHOBObservability,
@@ -191,13 +562,14 @@ impl K8sAnywhereTopology {
         &self,
         sender: CRDPrometheus,
         receivers: Option<Vec<Box<dyn AlertReceiver<CRDPrometheus>>>>,
+        service_monitors: Option<Vec<ServiceMonitor>>,
     ) -> K8sPrometheusCRDAlertingScore {
-        K8sPrometheusCRDAlertingScore {
+        return K8sPrometheusCRDAlertingScore {
             sender,
             receivers: receivers.unwrap_or_default(),
-            service_monitors: vec![],
+            service_monitors: service_monitors.unwrap_or_default(),
             prometheus_rules: vec![],
-        }
+        };
     }
 
     async fn openshift_ingress_operator_available(&self) -> Result<(), PreparationError> {
@@ -465,6 +837,30 @@ impl K8sAnywhereTopology {
             details: "prometheus operator present in cluster".into(),
         })
     }
+
+    async fn install_grafana_operator(
+        &self,
+        inventory: &Inventory,
+        ns: Option<&str>,
+    ) -> Result<PreparationOutcome, PreparationError> {
+        let namespace = ns.unwrap_or("grafana");
+        info!("installing grafana operator in ns {namespace}");
+        let tenant = self.get_k8s_tenant_manager()?.get_tenant_config().await;
+        let mut namespace_scope = false;
+        if tenant.is_some() {
+            namespace_scope = true;
+        }
+        let _grafana_operator_score = grafana_helm_chart_score(namespace, namespace_scope)
+            .interpret(inventory, self)
+            .await
+            .map_err(|e| PreparationError::new(e.to_string()));
+        Ok(PreparationOutcome::Success {
+            details: format!(
+                "Successfully installed grafana operator in ns {}",
+                ns.unwrap()
+            ),
+        })
+    }
 }
 
 #[derive(Clone, Debug)]

harmony/src/domain/topology/load_balancer.rs

@@ -28,13 +28,7 @@ pub trait LoadBalancer: Send + Sync {
         &self,
         service: &LoadBalancerService,
     ) -> Result<(), ExecutorError> {
-        debug!(
-            "Listing LoadBalancer services {:?}",
-            self.list_services().await
-        );
-        if !self.list_services().await.contains(service) {
-            self.add_service(service).await?;
-        }
+        self.add_service(service).await?;
         Ok(())
     }
 }

harmony/src/domain/topology/network.rs

@@ -1,10 +1,21 @@
-use std::{net::Ipv4Addr, str::FromStr, sync::Arc};
+use std::{
+    error::Error,
+    fmt::{self, Debug},
+    net::Ipv4Addr,
+    str::FromStr,
+    sync::Arc,
+};
 
 use async_trait::async_trait;
-use harmony_types::net::{IpAddress, MacAddress};
+use derive_new::new;
+use harmony_types::{
+    id::Id,
+    net::{IpAddress, MacAddress},
+    switch::PortLocation,
+};
 use serde::Serialize;
 
-use crate::executors::ExecutorError;
+use crate::{executors::ExecutorError, hardware::PhysicalHost};
 
 use super::{LogicalHost, k8s::K8sClient};
 
@@ -15,8 +26,8 @@ pub struct DHCPStaticEntry {
     pub ip: Ipv4Addr,
 }
 
-impl std::fmt::Display for DHCPStaticEntry {
-    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+impl fmt::Display for DHCPStaticEntry {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
         let mac = self
             .mac
             .iter()
@@ -38,8 +49,8 @@ pub trait Firewall: Send + Sync {
     fn get_host(&self) -> LogicalHost;
 }
 
-impl std::fmt::Debug for dyn Firewall {
-    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+impl Debug for dyn Firewall {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
         f.write_fmt(format_args!("Firewall {}", self.get_ip()))
     }
 }
@@ -61,7 +72,7 @@ pub struct PxeOptions {
 }
 
 #[async_trait]
-pub trait DhcpServer: Send + Sync + std::fmt::Debug {
+pub trait DhcpServer: Send + Sync + Debug {
     async fn add_static_mapping(&self, entry: &DHCPStaticEntry) -> Result<(), ExecutorError>;
     async fn remove_static_mapping(&self, mac: &MacAddress) -> Result<(), ExecutorError>;
     async fn list_static_mappings(&self) -> Vec<(MacAddress, IpAddress)>;
@@ -100,8 +111,8 @@ pub trait DnsServer: Send + Sync {
     }
 }
 
-impl std::fmt::Debug for dyn DnsServer {
-    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+impl Debug for dyn DnsServer {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
         f.write_fmt(format_args!("DnsServer {}", self.get_ip()))
     }
 }
@@ -137,8 +148,8 @@ pub enum DnsRecordType {
     TXT,
 }
 
-impl std::fmt::Display for DnsRecordType {
-    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+impl fmt::Display for DnsRecordType {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
         match self {
             DnsRecordType::A => write!(f, "A"),
             DnsRecordType::AAAA => write!(f, "AAAA"),
@@ -172,6 +183,77 @@ impl FromStr for DnsRecordType {
     }
 }
 
+#[async_trait]
+pub trait Switch: Send + Sync {
+    async fn setup_switch(&self) -> Result<(), SwitchError>;
+
+    async fn get_port_for_mac_address(
+        &self,
+        mac_address: &MacAddress,
+    ) -> Result<Option<PortLocation>, SwitchError>;
+
+    async fn configure_host_network(&self, config: &HostNetworkConfig) -> Result<(), SwitchError>;
+}
+
+#[derive(Clone, Debug, PartialEq)]
+pub struct HostNetworkConfig {
+    pub host_id: Id,
+    pub switch_ports: Vec<SwitchPort>,
+}
+
+#[derive(Clone, Debug, PartialEq)]
+pub struct SwitchPort {
+    pub interface: NetworkInterface,
+    pub port: PortLocation,
+}
+
+#[derive(Clone, Debug, PartialEq)]
+pub struct NetworkInterface {
+    pub name: String,
+    pub mac_address: MacAddress,
+    pub speed_mbps: Option<u32>,
+    pub mtu: u32,
+}
+
+#[derive(Debug, Clone, new)]
+pub struct SwitchError {
+    msg: String,
+}
+
+impl fmt::Display for SwitchError {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        f.write_str(&self.msg)
+    }
+}
+
+impl Error for SwitchError {}
+
+#[async_trait]
+pub trait SwitchClient: Debug + Send + Sync {
+    /// Executes essential, idempotent, one-time initial configuration steps.
+    ///
+    /// This is an opiniated procedure that setups a switch to provide high availability
+    /// capabilities as decided by the NationTech team.
+    ///
+    /// This includes tasks like enabling switchport for all interfaces
+    /// except the ones intended for Fabric Networking, etc.
+    ///
+    /// The implementation must ensure the operation is **idempotent** (safe to run multiple times)
+    /// and that it doesn't break existing configurations.
+    async fn setup(&self) -> Result<(), SwitchError>;
+
+    async fn find_port(
+        &self,
+        mac_address: &MacAddress,
+    ) -> Result<Option<PortLocation>, SwitchError>;
+
+    async fn configure_port_channel(
+        &self,
+        channel_name: &str,
+        switch_ports: Vec<PortLocation>,
+    ) -> Result<u8, SwitchError>;
+}
+
 #[cfg(test)]
 mod test {
     use std::sync::Arc;

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

@@ -1,6 +1,7 @@
-use std::any::Any;
+use std::{any::Any, collections::HashMap};
 
 use async_trait::async_trait;
+use kube::api::DynamicObject;
 use log::debug;
 
 use crate::{
@@ -21,6 +22,7 @@ pub struct AlertingInterpret<S: AlertSender> {
     pub sender: S,
     pub receivers: Vec<Box<dyn AlertReceiver<S>>>,
     pub rules: Vec<Box<dyn AlertRule<S>>>,
+    pub scrape_targets: Option<Vec<Box<dyn ScrapeTarget<S>>>>,
 }
 
 #[async_trait]
@@ -30,6 +32,7 @@ impl<S: AlertSender + Installable<T>, T: Topology> Interpret<T> for AlertingInte
         inventory: &Inventory,
         topology: &T,
     ) -> Result<Outcome, InterpretError> {
+        debug!("hit sender configure for AlertingInterpret");
         self.sender.configure(inventory, topology).await?;
         for receiver in self.receivers.iter() {
             receiver.install(&self.sender).await?;
@@ -38,6 +41,12 @@ impl<S: AlertSender + Installable<T>, T: Topology> Interpret<T> for AlertingInte
             debug!("installing rule: {:#?}", rule);
             rule.install(&self.sender).await?;
         }
+        if let Some(targets) = &self.scrape_targets {
+            for target in targets.iter() {
+                debug!("installing scrape_target: {:#?}", target);
+                target.install(&self.sender).await?;
+            }
+        }
         self.sender.ensure_installed(inventory, topology).await?;
         Ok(Outcome::success(format!(
             "successfully installed alert sender {}",
@@ -68,6 +77,15 @@ pub trait AlertReceiver<S: AlertSender>: std::fmt::Debug + Send + Sync {
     fn name(&self) -> String;
     fn clone_box(&self) -> Box<dyn AlertReceiver<S>>;
     fn as_any(&self) -> &dyn Any;
+    fn as_alertmanager_receiver(&self) -> Result<AlertManagerReceiver, String>;
+}
+
+#[derive(Debug)]
+pub struct AlertManagerReceiver {
+    pub receiver_config: serde_json::Value,
+    // FIXME we should not leak k8s here. DynamicObject is k8s specific
+    pub additional_ressources: Vec<DynamicObject>,
+    pub route_config: serde_json::Value,
 }
 
 #[async_trait]
@@ -77,6 +95,7 @@ pub trait AlertRule<S: AlertSender>: std::fmt::Debug + Send + Sync {
 }
 
 #[async_trait]
-pub trait ScrapeTarget<S: AlertSender> {
-    async fn install(&self, sender: &S) -> Result<(), InterpretError>;
+pub trait ScrapeTarget<S: AlertSender>: std::fmt::Debug + Send + Sync {
+    async fn install(&self, sender: &S) -> Result<Outcome, InterpretError>;
+    fn clone_box(&self) -> Box<dyn ScrapeTarget<S>>;
 }

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

@@ -14,7 +14,7 @@ use k8s_openapi::{
     },
     apimachinery::pkg::util::intstr::IntOrString,
 };
-use kube::Resource;
+use kube::{Resource, api::DynamicObject};
 use log::debug;
 use serde::de::DeserializeOwned;
 use serde_json::json;

harmony/src/infra/brocade.rs

@@ -0,0 +1,378 @@
+use async_trait::async_trait;
+use brocade::{BrocadeClient, BrocadeOptions, InterSwitchLink, InterfaceStatus, PortOperatingMode};
+use harmony_types::{
+    net::{IpAddress, MacAddress},
+    switch::{PortDeclaration, PortLocation},
+};
+use option_ext::OptionExt;
+
+use crate::topology::{SwitchClient, SwitchError};
+
+#[derive(Debug)]
+pub struct BrocadeSwitchClient {
+    brocade: Box<dyn BrocadeClient + Send + Sync>,
+}
+
+impl BrocadeSwitchClient {
+    pub async fn init(
+        ip_addresses: &[IpAddress],
+        username: &str,
+        password: &str,
+        options: Option<BrocadeOptions>,
+    ) -> Result<Self, brocade::Error> {
+        let brocade = brocade::init(ip_addresses, 22, username, password, options).await?;
+        Ok(Self { brocade })
+    }
+}
+
+#[async_trait]
+impl SwitchClient for BrocadeSwitchClient {
+    async fn setup(&self) -> Result<(), SwitchError> {
+        let stack_topology = self
+            .brocade
+            .get_stack_topology()
+            .await
+            .map_err(|e| SwitchError::new(e.to_string()))?;
+
+        let interfaces = self
+            .brocade
+            .get_interfaces()
+            .await
+            .map_err(|e| SwitchError::new(e.to_string()))?;
+
+        let interfaces: Vec<(String, PortOperatingMode)> = interfaces
+            .into_iter()
+            .filter(|interface| {
+                interface.operating_mode.is_none() && interface.status == InterfaceStatus::Connected
+            })
+            .filter(|interface| {
+                !stack_topology.iter().any(|link: &InterSwitchLink| {
+                    link.local_port == interface.port_location
+                        || link.remote_port.contains(&interface.port_location)
+                })
+            })
+            .map(|interface| (interface.name.clone(), PortOperatingMode::Access))
+            .collect();
+
+        if interfaces.is_empty() {
+            return Ok(());
+        }
+
+        self.brocade
+            .configure_interfaces(interfaces)
+            .await
+            .map_err(|e| SwitchError::new(e.to_string()))?;
+
+        Ok(())
+    }
+
+    async fn find_port(
+        &self,
+        mac_address: &MacAddress,
+    ) -> Result<Option<PortLocation>, SwitchError> {
+        let table = self
+            .brocade
+            .get_mac_address_table()
+            .await
+            .map_err(|e| SwitchError::new(format!("{e}")))?;
+
+        let port = table
+            .iter()
+            .find(|entry| entry.mac_address == *mac_address)
+            .map(|entry| match &entry.port {
+                PortDeclaration::Single(port_location) => Ok(port_location.clone()),
+                _ => Err(SwitchError::new(
+                    "Multiple ports found for MAC address".into(),
+                )),
+            });
+
+        match port {
+            Some(Ok(p)) => Ok(Some(p)),
+            Some(Err(e)) => Err(e),
+            None => Ok(None),
+        }
+    }
+
+    async fn configure_port_channel(
+        &self,
+        channel_name: &str,
+        switch_ports: Vec<PortLocation>,
+    ) -> Result<u8, SwitchError> {
+        let channel_id = self
+            .brocade
+            .find_available_channel_id()
+            .await
+            .map_err(|e| SwitchError::new(format!("{e}")))?;
+
+        self.brocade
+            .create_port_channel(channel_id, channel_name, &switch_ports)
+            .await
+            .map_err(|e| SwitchError::new(format!("{e}")))?;
+
+        Ok(channel_id)
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use std::sync::{Arc, Mutex};
+
+    use assertor::*;
+    use async_trait::async_trait;
+    use brocade::{
+        BrocadeClient, BrocadeInfo, Error, InterSwitchLink, InterfaceInfo, InterfaceStatus,
+        InterfaceType, MacAddressEntry, PortChannelId, PortOperatingMode,
+    };
+    use harmony_types::switch::PortLocation;
+
+    use crate::{infra::brocade::BrocadeSwitchClient, topology::SwitchClient};
+
+    #[tokio::test]
+    async fn setup_should_configure_ethernet_interfaces_as_access_ports() {
+        let first_interface = given_interface()
+            .with_port_location(PortLocation(1, 0, 1))
+            .build();
+        let second_interface = given_interface()
+            .with_port_location(PortLocation(1, 0, 4))
+            .build();
+        let brocade = Box::new(FakeBrocadeClient::new(
+            vec![],
+            vec![first_interface.clone(), second_interface.clone()],
+        ));
+        let client = BrocadeSwitchClient {
+            brocade: brocade.clone(),
+        };
+
+        client.setup().await.unwrap();
+
+        let configured_interfaces = brocade.configured_interfaces.lock().unwrap();
+        assert_that!(*configured_interfaces).contains_exactly(vec![
+            (first_interface.name.clone(), PortOperatingMode::Access),
+            (second_interface.name.clone(), PortOperatingMode::Access),
+        ]);
+    }
+
+    #[tokio::test]
+    async fn setup_with_an_already_configured_interface_should_skip_configuration() {
+        let brocade = Box::new(FakeBrocadeClient::new(
+            vec![],
+            vec![
+                given_interface()
+                    .with_operating_mode(Some(PortOperatingMode::Access))
+                    .build(),
+            ],
+        ));
+        let client = BrocadeSwitchClient {
+            brocade: brocade.clone(),
+        };
+
+        client.setup().await.unwrap();
+
+        let configured_interfaces = brocade.configured_interfaces.lock().unwrap();
+        assert_that!(*configured_interfaces).is_empty();
+    }
+
+    #[tokio::test]
+    async fn setup_with_a_disconnected_interface_should_skip_configuration() {
+        let brocade = Box::new(FakeBrocadeClient::new(
+            vec![],
+            vec![
+                given_interface()
+                    .with_status(InterfaceStatus::SfpAbsent)
+                    .build(),
+                given_interface()
+                    .with_status(InterfaceStatus::NotConnected)
+                    .build(),
+            ],
+        ));
+        let client = BrocadeSwitchClient {
+            brocade: brocade.clone(),
+        };
+
+        client.setup().await.unwrap();
+
+        let configured_interfaces = brocade.configured_interfaces.lock().unwrap();
+        assert_that!(*configured_interfaces).is_empty();
+    }
+
+    #[tokio::test]
+    async fn setup_with_inter_switch_links_should_not_configure_interfaces_used_to_form_stack() {
+        let brocade = Box::new(FakeBrocadeClient::new(
+            vec![
+                given_inter_switch_link()
+                    .between(PortLocation(1, 0, 1), PortLocation(2, 0, 1))
+                    .build(),
+                given_inter_switch_link()
+                    .between(PortLocation(2, 0, 2), PortLocation(3, 0, 1))
+                    .build(),
+            ],
+            vec![
+                given_interface()
+                    .with_port_location(PortLocation(1, 0, 1))
+                    .build(),
+                given_interface()
+                    .with_port_location(PortLocation(2, 0, 1))
+                    .build(),
+                given_interface()
+                    .with_port_location(PortLocation(3, 0, 1))
+                    .build(),
+            ],
+        ));
+        let client = BrocadeSwitchClient {
+            brocade: brocade.clone(),
+        };
+
+        client.setup().await.unwrap();
+
+        let configured_interfaces = brocade.configured_interfaces.lock().unwrap();
+        assert_that!(*configured_interfaces).is_empty();
+    }
+
+    #[derive(Debug, Clone)]
+    struct FakeBrocadeClient {
+        stack_topology: Vec<InterSwitchLink>,
+        interfaces: Vec<InterfaceInfo>,
+        configured_interfaces: Arc<Mutex<Vec<(String, PortOperatingMode)>>>,
+    }
+
+    #[async_trait]
+    impl BrocadeClient for FakeBrocadeClient {
+        async fn version(&self) -> Result<BrocadeInfo, Error> {
+            todo!()
+        }
+
+        async fn get_mac_address_table(&self) -> Result<Vec<MacAddressEntry>, Error> {
+            todo!()
+        }
+
+        async fn get_stack_topology(&self) -> Result<Vec<InterSwitchLink>, Error> {
+            Ok(self.stack_topology.clone())
+        }
+
+        async fn get_interfaces(&self) -> Result<Vec<InterfaceInfo>, Error> {
+            Ok(self.interfaces.clone())
+        }
+
+        async fn configure_interfaces(
+            &self,
+            interfaces: Vec<(String, PortOperatingMode)>,
+        ) -> Result<(), Error> {
+            let mut configured_interfaces = self.configured_interfaces.lock().unwrap();
+            *configured_interfaces = interfaces;
+
+            Ok(())
+        }
+
+        async fn find_available_channel_id(&self) -> Result<PortChannelId, Error> {
+            todo!()
+        }
+
+        async fn create_port_channel(
+            &self,
+            _channel_id: PortChannelId,
+            _channel_name: &str,
+            _ports: &[PortLocation],
+        ) -> Result<(), Error> {
+            todo!()
+        }
+
+        async fn clear_port_channel(&self, _channel_name: &str) -> Result<(), Error> {
+            todo!()
+        }
+    }
+
+    impl FakeBrocadeClient {
+        fn new(stack_topology: Vec<InterSwitchLink>, interfaces: Vec<InterfaceInfo>) -> Self {
+            Self {
+                stack_topology,
+                interfaces,
+                configured_interfaces: Arc::new(Mutex::new(vec![])),
+            }
+        }
+    }
+
+    struct InterfaceInfoBuilder {
+        port_location: Option<PortLocation>,
+        interface_type: Option<InterfaceType>,
+        operating_mode: Option<PortOperatingMode>,
+        status: Option<InterfaceStatus>,
+    }
+
+    impl InterfaceInfoBuilder {
+        fn build(&self) -> InterfaceInfo {
+            let interface_type = self
+                .interface_type
+                .clone()
+                .unwrap_or(InterfaceType::Ethernet("TenGigabitEthernet".into()));
+            let port_location = self.port_location.clone().unwrap_or(PortLocation(1, 0, 1));
+            let name = format!("{interface_type} {port_location}");
+            let status = self.status.clone().unwrap_or(InterfaceStatus::Connected);
+
+            InterfaceInfo {
+                name,
+                port_location,
+                interface_type,
+                operating_mode: self.operating_mode.clone(),
+                status,
+            }
+        }
+
+        fn with_port_location(self, port_location: PortLocation) -> Self {
+            Self {
+                port_location: Some(port_location),
+                ..self
+            }
+        }
+
+        fn with_operating_mode(self, operating_mode: Option<PortOperatingMode>) -> Self {
+            Self {
+                operating_mode,
+                ..self
+            }
+        }
+
+        fn with_status(self, status: InterfaceStatus) -> Self {
+            Self {
+                status: Some(status),
+                ..self
+            }
+        }
+    }
+
+    struct InterSwitchLinkBuilder {
+        link: Option<(PortLocation, PortLocation)>,
+    }
+
+    impl InterSwitchLinkBuilder {
+        fn build(&self) -> InterSwitchLink {
+            let link = self
+                .link
+                .clone()
+                .unwrap_or((PortLocation(1, 0, 1), PortLocation(2, 0, 1)));
+
+            InterSwitchLink {
+                local_port: link.0,
+                remote_port: Some(link.1),
+            }
+        }
+
+        fn between(self, local_port: PortLocation, remote_port: PortLocation) -> Self {
+            Self {
+                link: Some((local_port, remote_port)),
+            }
+        }
+    }
+
+    fn given_interface() -> InterfaceInfoBuilder {
+        InterfaceInfoBuilder {
+            port_location: None,
+            interface_type: None,
+            operating_mode: None,
+            status: None,
+        }
+    }
+
+    fn given_inter_switch_link() -> InterSwitchLinkBuilder {
+        InterSwitchLinkBuilder { link: None }
+    }
+}

harmony/src/infra/inventory/mod.rs

@@ -11,7 +11,7 @@ pub struct InventoryRepositoryFactory;
 impl InventoryRepositoryFactory {
     pub async fn build() -> Result<Box<dyn InventoryRepository>, RepoError> {
         Ok(Box::new(
-            SqliteInventoryRepository::new(&(*DATABASE_URL)).await?,
+            SqliteInventoryRepository::new(&DATABASE_URL).await?,
         ))
     }
 }

harmony/src/infra/kube.rs

@@ -0,0 +1,182 @@
+use k8s_openapi::Resource as K8sResource;
+use kube::api::{ApiResource, DynamicObject, GroupVersionKind};
+use kube::core::TypeMeta;
+use serde::Serialize;
+use serde::de::DeserializeOwned;
+use serde_json::Value;
+
+/// Convert a typed Kubernetes resource `K` into a `DynamicObject`.
+///
+/// Requirements:
+/// - `K` must be a k8s_openapi resource (provides static GVK via `Resource`).
+/// - `K` must have standard Kubernetes shape (metadata + payload fields).
+///
+/// Notes:
+/// - We set `types` (apiVersion/kind) and copy `metadata`.
+/// - We place the remaining top-level fields into `obj.data` as JSON.
+/// - Scope is not encoded on the object itself; you still need the corresponding
+///   `DynamicResource` (derived from K::group/version/kind) when constructing an Api.
+///
+/// Example usage:
+///   let dyn_obj = kube_resource_to_dynamic(secret)?;
+///   let api: Api<DynamicObject> = Api::namespaced_with(client, "ns", &dr);
+///   api.patch(&dyn_obj.name_any(), &PatchParams::apply("mgr"), &Patch::Apply(dyn_obj)).await?;
+pub fn kube_resource_to_dynamic<K>(res: &K) -> Result<DynamicObject, String>
+where
+    K: K8sResource + Serialize + DeserializeOwned,
+{
+    // Serialize the typed resource to JSON so we can split metadata and payload
+    let mut v = serde_json::to_value(res).map_err(|e| format!("Failed to serialize : {e}"))?;
+    let obj = v
+        .as_object_mut()
+        .ok_or_else(|| "expected object JSON".to_string())?;
+
+    // Extract and parse metadata into kube::core::ObjectMeta
+    let metadata_value = obj
+        .remove("metadata")
+        .ok_or_else(|| "missing metadata".to_string())?;
+    let metadata: kube::core::ObjectMeta = serde_json::from_value(metadata_value)
+        .map_err(|e| format!("Failed to deserialize : {e}"))?;
+
+    // Name is required for DynamicObject::new; prefer metadata.name
+    let name = metadata
+        .name
+        .clone()
+        .ok_or_else(|| "metadata.name is required".to_string())?;
+
+    // Remaining fields (spec/status/data/etc.) become the dynamic payload
+    let payload = Value::Object(obj.clone());
+
+    // Construct the DynamicObject
+    let mut dyn_obj = DynamicObject::new(
+        &name,
+        &ApiResource::from_gvk(&GroupVersionKind::gvk(K::GROUP, K::VERSION, K::KIND)),
+    );
+    dyn_obj.types = Some(TypeMeta {
+        api_version: api_version_for::<K>(),
+        kind: K::KIND.into(),
+    });
+
+    // Preserve namespace/labels/annotations/etc.
+    dyn_obj.metadata = metadata;
+
+    // Attach payload
+    dyn_obj.data = payload;
+
+    Ok(dyn_obj)
+}
+
+/// Helper: compute apiVersion string ("group/version" or "v1" for core).
+fn api_version_for<K>() -> String
+where
+    K: K8sResource,
+{
+    let group = K::GROUP;
+    let version = K::VERSION;
+    if group.is_empty() {
+        version.to_string() // core/v1 => "v1"
+    } else {
+        format!("{}/{}", group, version)
+    }
+}
+#[cfg(test)]
+mod test {
+    use super::*;
+    use k8s_openapi::api::{
+        apps::v1::{Deployment, DeploymentSpec},
+        core::v1::{PodTemplateSpec, Secret},
+    };
+    use kube::api::ObjectMeta;
+    use pretty_assertions::assert_eq;
+
+    #[test]
+    fn secret_to_dynamic_roundtrip() {
+        // Create a sample Secret resource
+        let mut secret = Secret {
+            metadata: ObjectMeta {
+                name: Some("my-secret".to_string()),
+                ..Default::default()
+            },
+            type_: Some("kubernetes.io/service-account-token".to_string()),
+            ..Default::default()
+        };
+
+        // Convert to DynamicResource
+        let dynamic: DynamicObject =
+            kube_resource_to_dynamic(&secret).expect("Failed to convert Secret to DynamicResource");
+
+        // Serialize both the original and dynamic resources to Value
+        let original_value = serde_json::to_value(&secret).expect("Failed to serialize Secret");
+        let dynamic_value =
+            serde_json::to_value(&dynamic).expect("Failed to serialize DynamicResource");
+
+        // Assert that they are identical
+        assert_eq!(original_value, dynamic_value);
+
+        secret.metadata.namespace = Some("false".to_string());
+        let modified_value = serde_json::to_value(&secret).expect("Failed to serialize Secret");
+        assert_ne!(modified_value, dynamic_value);
+    }
+
+    #[test]
+    fn deployment_to_dynamic_roundtrip() {
+        // Create a sample Deployment with nested structures
+        let mut deployment = Deployment {
+            metadata: ObjectMeta {
+                name: Some("my-deployment".to_string()),
+                labels: Some({
+                    let mut map = std::collections::BTreeMap::new();
+                    map.insert("app".to_string(), "nginx".to_string());
+                    map
+                }),
+                ..Default::default()
+            },
+            spec: Some(DeploymentSpec {
+                replicas: Some(3),
+                selector: Default::default(),
+                template: PodTemplateSpec {
+                    metadata: Some(ObjectMeta {
+                        labels: Some({
+                            let mut map = std::collections::BTreeMap::new();
+                            map.insert("app".to_string(), "nginx".to_string());
+                            map
+                        }),
+                        ..Default::default()
+                    }),
+                    spec: Some(Default::default()), // PodSpec with empty containers for simplicity
+                },
+                ..Default::default()
+            }),
+            ..Default::default()
+        };
+
+        let dynamic = kube_resource_to_dynamic(&deployment).expect("Failed to convert Deployment");
+
+        let original_value = serde_json::to_value(&deployment).unwrap();
+        let dynamic_value = serde_json::to_value(&dynamic).unwrap();
+
+        assert_eq!(original_value, dynamic_value);
+
+        assert_eq!(
+            dynamic.data.get("spec").unwrap().get("replicas").unwrap(),
+            3
+        );
+        assert_eq!(
+            dynamic
+                .data
+                .get("spec")
+                .unwrap()
+                .get("template")
+                .unwrap()
+                .get("metadata")
+                .unwrap()
+                .get("labels")
+                .unwrap()
+                .get("app")
+                .unwrap()
+                .as_str()
+                .unwrap(),
+            "nginx".to_string()
+        );
+    }
+}

harmony/src/infra/mod.rs

@@ -1,6 +1,8 @@
+pub mod brocade;
 pub mod executors;
 pub mod hp_ilo;
 pub mod intel_amt;
 pub mod inventory;
+pub mod kube;
 pub mod opnsense;
 mod sqlx;

harmony/src/infra/opnsense/load_balancer.rs

@@ -26,19 +26,13 @@ impl LoadBalancer for OPNSenseFirewall {
     }
 
     async fn add_service(&self, service: &LoadBalancerService) -> Result<(), ExecutorError> {
-        warn!(
-            "TODO : the current implementation does not check / cleanup / merge with existing haproxy services properly. Make sure to manually verify that the configuration is correct after executing any operation here"
-        );
         let mut config = self.opnsense_config.write().await;
+        let mut load_balancer = config.load_balancer();
+
         let (frontend, backend, servers, healthcheck) =
             harmony_load_balancer_service_to_haproxy_xml(service);
-        let mut load_balancer = config.load_balancer();
-        load_balancer.add_backend(backend);
-        load_balancer.add_frontend(frontend);
-        load_balancer.add_servers(servers);
-        if let Some(healthcheck) = healthcheck {
-            load_balancer.add_healthcheck(healthcheck);
-        }
+
+        load_balancer.configure_service(frontend, backend, servers, healthcheck);
 
         Ok(())
     }
@@ -106,7 +100,7 @@ pub(crate) fn haproxy_xml_config_to_harmony_loadbalancer(
                 .backends
                 .backends
                 .iter()
-                .find(|b| b.uuid == frontend.default_backend);
+                .find(|b| Some(b.uuid.clone()) == frontend.default_backend);
 
             let mut health_check = None;
             match matching_backend {
@@ -116,8 +110,7 @@ pub(crate) fn haproxy_xml_config_to_harmony_loadbalancer(
                 }
                 None => {
                     warn!(
-                        "HAProxy config could not find a matching backend for frontend {:?}",
-                        frontend
+                        "HAProxy config could not find a matching backend for frontend {frontend:?}"
                     );
                 }
             }
@@ -152,11 +145,11 @@ pub(crate) fn get_servers_for_backend(
         .servers
         .iter()
         .filter_map(|server| {
+            let address = server.address.clone()?;
+            let port = server.port?;
+
             if backend_servers.contains(&server.uuid.as_str()) {
-                return Some(BackendServer {
-                    address: server.address.clone(),
-                    port: server.port,
-                });
+                return Some(BackendServer { address, port });
             }
             None
         })
@@ -347,7 +340,7 @@ pub(crate) fn harmony_load_balancer_service_to_haproxy_xml(
         name: format!("frontend_{}", service.listening_port),
         bind: service.listening_port.to_string(),
         mode: "tcp".to_string(), // TODO do not depend on health check here
-        default_backend: backend.uuid.clone(),
+        default_backend: Some(backend.uuid.clone()),
         ..Default::default()
     };
     info!("HAPRoxy frontend and backend mode currently hardcoded to tcp");
@@ -361,8 +354,8 @@ fn server_to_haproxy_server(server: &BackendServer) -> HAProxyServer {
         uuid: Uuid::new_v4().to_string(),
         name: format!("{}_{}", &server.address, &server.port),
         enabled: 1,
-        address: server.address.clone(),
-        port: server.port,
+        address: Some(server.address.clone()),
+        port: Some(server.port),
         mode: "active".to_string(),
         server_type: "static".to_string(),
         ..Default::default()
@@ -385,8 +378,8 @@ mod tests {
         let mut haproxy = HAProxy::default();
         let server = HAProxyServer {
             uuid: "server1".to_string(),
-            address: "192.168.1.1".to_string(),
-            port: 80,
+            address: Some("192.168.1.1".to_string()),
+            port: Some(80),
             ..Default::default()
         };
         haproxy.servers.servers.push(server);
@@ -411,8 +404,8 @@ mod tests {
         let mut haproxy = HAProxy::default();
         let server = HAProxyServer {
             uuid: "server1".to_string(),
-            address: "192.168.1.1".to_string(),
-            port: 80,
+            address: Some("192.168.1.1".to_string()),
+            port: Some(80),
             ..Default::default()
         };
         haproxy.servers.servers.push(server);
@@ -431,8 +424,8 @@ mod tests {
         let mut haproxy = HAProxy::default();
         let server = HAProxyServer {
             uuid: "server1".to_string(),
-            address: "192.168.1.1".to_string(),
-            port: 80,
+            address: Some("192.168.1.1".to_string()),
+            port: Some(80),
             ..Default::default()
         };
         haproxy.servers.servers.push(server);
@@ -453,16 +446,16 @@ mod tests {
         let mut haproxy = HAProxy::default();
         let server = HAProxyServer {
             uuid: "server1".to_string(),
-            address: "some-hostname.test.mcd".to_string(),
-            port: 80,
+            address: Some("some-hostname.test.mcd".to_string()),
+            port: Some(80),
             ..Default::default()
         };
         haproxy.servers.servers.push(server);
 
         let server = HAProxyServer {
             uuid: "server2".to_string(),
-            address: "192.168.1.2".to_string(),
-            port: 8080,
+            address: Some("192.168.1.2".to_string()),
+            port: Some(8080),
             ..Default::default()
         };
         haproxy.servers.servers.push(server);

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

@@ -1,4 +1,5 @@
 use async_trait::async_trait;
+use harmony_macros::hurl;
 use kube::{Api, api::GroupVersionKind};
 use log::{debug, warn};
 use non_blank_string_rs::NonBlankString;
@@ -1051,7 +1052,7 @@ commitServer:
         install_only: false,
         repository: Some(HelmRepository::new(
             "argo".to_string(),
-            url::Url::parse("https://argoproj.github.io/argo-helm").unwrap(),
+            hurl!("https://argoproj.github.io/argo-helm"),
             true,
         )),
     }

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

@@ -2,7 +2,11 @@ use crate::modules::application::{
     Application, ApplicationFeature, InstallationError, InstallationOutcome,
 };
 use crate::modules::monitoring::application_monitoring::application_monitoring_score::ApplicationMonitoringScore;
+use crate::modules::monitoring::grafana::grafana::Grafana;
 use crate::modules::monitoring::kube_prometheus::crd::crd_alertmanager_config::CRDPrometheus;
+use crate::modules::monitoring::kube_prometheus::crd::service_monitor::{
+    ServiceMonitor, ServiceMonitorSpec,
+};
 use crate::topology::MultiTargetTopology;
 use crate::topology::ingress::Ingress;
 use crate::{
@@ -14,7 +18,7 @@ use crate::{
     topology::{HelmCommand, K8sclient, Topology, tenant::TenantManager},
 };
 use crate::{
-    modules::prometheus::prometheus::PrometheusApplicationMonitoring,
+    modules::prometheus::prometheus::PrometheusMonitoring,
     topology::oberservability::monitoring::AlertReceiver,
 };
 use async_trait::async_trait;
@@ -22,6 +26,7 @@ use base64::{Engine as _, engine::general_purpose};
 use harmony_secret::SecretManager;
 use harmony_secret_derive::Secret;
 use harmony_types::net::Url;
+use kube::api::ObjectMeta;
 use log::{debug, info};
 use serde::{Deserialize, Serialize};
 use std::sync::Arc;
@@ -40,7 +45,8 @@ impl<
         + TenantManager
         + K8sclient
         + MultiTargetTopology
-        + PrometheusApplicationMonitoring<CRDPrometheus>
+        + PrometheusMonitoring<CRDPrometheus>
+        + Grafana
         + Ingress
         + std::fmt::Debug,
 > ApplicationFeature<T> for Monitoring
@@ -57,10 +63,20 @@ impl<
             .unwrap_or_else(|| self.application.name());
         let domain = topology.get_domain("ntfy").await.unwrap();
 
+        let app_service_monitor = ServiceMonitor {
+            metadata: ObjectMeta {
+                name: Some(self.application.name()),
+                namespace: Some(namespace.clone()),
+                ..Default::default()
+            },
+            spec: ServiceMonitorSpec::default(),
+        };
+
         let mut alerting_score = ApplicationMonitoringScore {
             sender: CRDPrometheus {
                 namespace: namespace.clone(),
                 client: topology.k8s_client().await.unwrap(),
+                service_monitor: vec![app_service_monitor],
             },
             application: self.application.clone(),
             receivers: self.alert_receiver.clone(),

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

@@ -18,7 +18,7 @@ use crate::{
     topology::{HelmCommand, K8sclient, Topology, tenant::TenantManager},
 };
 use crate::{
-    modules::prometheus::prometheus::PrometheusApplicationMonitoring,
+    modules::prometheus::prometheus::PrometheusMonitoring,
     topology::oberservability::monitoring::AlertReceiver,
 };
 use async_trait::async_trait;
@@ -42,7 +42,7 @@ impl<
         + MultiTargetTopology
         + Ingress
         + std::fmt::Debug
-        + PrometheusApplicationMonitoring<RHOBObservability>,
+        + PrometheusMonitoring<RHOBObservability>,
 > ApplicationFeature<T> for Monitoring
 {
     async fn ensure_installed(

harmony/src/modules/cert_manager/cluster_issuer.rs

@@ -0,0 +1,209 @@
+use std::sync::Arc;
+
+use async_trait::async_trait;
+use harmony_types::id::Id;
+use kube::{CustomResource, api::ObjectMeta};
+use schemars::JsonSchema;
+use serde::{Deserialize, Serialize};
+
+use crate::{
+    data::Version,
+    interpret::{Interpret, InterpretError, InterpretName, InterpretStatus, Outcome},
+    inventory::Inventory,
+    score::Score,
+    topology::{K8sclient, Topology, k8s::K8sClient},
+};
+
+#[derive(Clone, Debug, Serialize)]
+pub struct ClusterIssuerScore {
+    email: String,
+    server: String,
+    issuer_name: String,
+    namespace: String,
+}
+
+impl<T: Topology + K8sclient> Score<T> for ClusterIssuerScore {
+    fn name(&self) -> String {
+        "ClusterIssuerScore".to_string()
+    }
+
+    #[doc(hidden)]
+    fn create_interpret(&self) -> Box<dyn Interpret<T>> {
+        Box::new(ClusterIssuerInterpret {
+            score: self.clone(),
+        })
+    }
+}
+
+#[derive(Debug, Clone)]
+pub struct ClusterIssuerInterpret {
+    score: ClusterIssuerScore,
+}
+
+#[async_trait]
+impl<T: Topology + K8sclient> Interpret<T> for ClusterIssuerInterpret {
+    async fn execute(
+        &self,
+        _inventory: &Inventory,
+        topology: &T,
+    ) -> Result<Outcome, InterpretError> {
+        self.apply_cluster_issuer(topology.k8s_client().await.unwrap())
+            .await
+    }
+
+    fn get_name(&self) -> InterpretName {
+        InterpretName::Custom("ClusterIssuer")
+    }
+
+    fn get_version(&self) -> Version {
+        todo!()
+    }
+
+    fn get_status(&self) -> InterpretStatus {
+        todo!()
+    }
+
+    fn get_children(&self) -> Vec<Id> {
+        todo!()
+    }
+}
+
+impl ClusterIssuerInterpret {
+    async fn validate_cert_manager(
+        &self,
+        client: &Arc<K8sClient>,
+    ) -> Result<Outcome, InterpretError> {
+        let cert_manager = "cert-manager".to_string();
+        let operator_namespace = "openshift-operators".to_string();
+        match client
+            .get_deployment(&cert_manager, Some(&operator_namespace))
+            .await
+        {
+            Ok(Some(deployment)) => {
+                if let Some(status) = deployment.status {
+                    let ready_count = status.ready_replicas.unwrap_or(0);
+                    if ready_count >= 1 {
+                        return Ok(Outcome::success(format!(
+                            "'{}' is ready with {} replica(s).",
+                            &cert_manager, ready_count
+                        )));
+                    } else {
+                        return Err(InterpretError::new(
+                            "cert-manager operator not ready in cluster".to_string(),
+                        ));
+                    }
+                } else {
+                    Err(InterpretError::new(format!(
+                        "failed to get deployment status {} in ns {}",
+                        &cert_manager, &operator_namespace
+                    )))
+                }
+            }
+            Ok(None) => Err(InterpretError::new(format!(
+                "Deployment '{}' not found in namespace '{}'.",
+                &cert_manager, &operator_namespace
+            ))),
+            Err(e) => Err(InterpretError::new(format!(
+                "Failed to query for deployment '{}': {}",
+                &cert_manager, e
+            ))),
+        }
+    }
+
+    fn build_cluster_issuer(&self) -> Result<ClusterIssuer, InterpretError> {
+        let issuer_name = &self.score.issuer_name;
+        let email = &self.score.email;
+        let server = &self.score.server;
+        let namespace = &self.score.namespace;
+        let cluster_issuer = ClusterIssuer {
+            metadata: ObjectMeta {
+                name: Some(issuer_name.to_string()),
+                namespace: Some(namespace.to_string()),
+                ..Default::default()
+            },
+            spec: ClusterIssuerSpec {
+                acme: AcmeSpec {
+                    email: email.to_string(),
+                    private_key_secret_ref: PrivateKeySecretRef {
+                        name: issuer_name.to_string(),
+                    },
+                    server: server.to_string(),
+                    solvers: vec![SolverSpec {
+                        http01: Some(Http01Solver {
+                            ingress: Http01Ingress {
+                                class: "nginx".to_string(),
+                            },
+                        }),
+                    }],
+                },
+            },
+        };
+
+        Ok(cluster_issuer)
+    }
+
+    pub async fn apply_cluster_issuer(
+        &self,
+        client: Arc<K8sClient>,
+    ) -> Result<Outcome, InterpretError> {
+        let namespace = self.score.namespace.clone();
+        self.validate_cert_manager(&client).await?;
+        let cluster_issuer = self.build_cluster_issuer().unwrap();
+        client
+            .apply_yaml(
+                &serde_yaml::to_value(cluster_issuer).unwrap(),
+                Some(&namespace),
+            )
+            .await?;
+        Ok(Outcome::success(format!(
+            "successfully deployed cluster operator: {} in namespace: {}",
+            self.score.issuer_name, self.score.namespace
+        )))
+    }
+}
+
+#[derive(CustomResource, Deserialize, Serialize, Clone, Debug, JsonSchema)]
+#[kube(
+    group = "cert-manager.io",
+    version = "v1",
+    kind = "ClusterIssuer",
+    plural = "clusterissuers"
+)]
+#[serde(rename_all = "camelCase")]
+pub struct ClusterIssuerSpec {
+    pub acme: AcmeSpec,
+}
+
+#[derive(Deserialize, Serialize, Clone, Debug, JsonSchema)]
+#[serde(rename_all = "camelCase")]
+pub struct AcmeSpec {
+    pub email: String,
+    pub private_key_secret_ref: PrivateKeySecretRef,
+    pub server: String,
+    pub solvers: Vec<SolverSpec>,
+}
+
+#[derive(Deserialize, Serialize, Clone, Debug, JsonSchema)]
+#[serde(rename_all = "camelCase")]
+pub struct PrivateKeySecretRef {
+    pub name: String,
+}
+
+#[derive(Deserialize, Serialize, Clone, Debug, JsonSchema)]
+#[serde(rename_all = "camelCase")]
+pub struct SolverSpec {
+    pub http01: Option<Http01Solver>,
+    // Other solver types (e.g., dns01) would go here as Options
+}
+
+#[derive(Deserialize, Serialize, Clone, Debug, JsonSchema)]
+#[serde(rename_all = "camelCase")]
+pub struct Http01Solver {
+    pub ingress: Http01Ingress,
+}
+
+#[derive(Deserialize, Serialize, Clone, Debug, JsonSchema)]
+#[serde(rename_all = "camelCase")]
+pub struct Http01Ingress {
+    pub class: String,
+}

harmony/src/modules/cert_manager/helm.rs

@@ -1,5 +1,6 @@
 use std::{collections::HashMap, str::FromStr};
 
+use harmony_macros::hurl;
 use non_blank_string_rs::NonBlankString;
 use serde::Serialize;
 use url::Url;
@@ -33,7 +34,7 @@ impl<T: Topology + HelmCommand> Score<T> for CertManagerHelmScore {
             install_only: true,
             repository: Some(HelmRepository::new(
                 "jetstack".to_string(),
-                Url::parse("https://charts.jetstack.io").unwrap(),
+                hurl!("https://charts.jetstack.io"),
                 true,
             )),
         }

harmony/src/modules/cert_manager/mod.rs

@@ -1,2 +1,3 @@
+pub mod cluster_issuer;
 mod helm;
 pub use helm::*;

harmony/src/modules/helm/chart.rs

@@ -5,6 +5,7 @@ use crate::score::Score;
 use crate::topology::{HelmCommand, Topology};
 use async_trait::async_trait;
 use harmony_types::id::Id;
+use harmony_types::net::Url;
 use helm_wrapper_rs;
 use helm_wrapper_rs::blocking::{DefaultHelmExecutor, HelmExecutor};
 use log::{debug, info, warn};
@@ -15,7 +16,6 @@ use std::path::Path;
 use std::process::{Command, Output, Stdio};
 use std::str::FromStr;
 use temp_file::TempFile;
-use url::Url;
 
 #[derive(Debug, Clone, Serialize)]
 pub struct HelmRepository {
@@ -78,7 +78,8 @@ impl HelmChartInterpret {
             repo.name, repo.url, repo.force_update
         );
 
-        let mut add_args = vec!["repo", "add", &repo.name, repo.url.as_str()];
+        let repo_url = repo.url.to_string();
+        let mut add_args = vec!["repo", "add", &repo.name, &repo_url];
         if repo.force_update {
             add_args.push("--force-update");
         }

harmony/src/modules/helm/command.rs

@@ -1,364 +0,0 @@
-use async_trait::async_trait;
-use log::debug;
-use serde::Serialize;
-use std::collections::HashMap;
-use std::io::ErrorKind;
-use std::path::PathBuf;
-use std::process::{Command, Output};
-use temp_dir::{self, TempDir};
-use temp_file::TempFile;
-
-use crate::data::Version;
-use crate::interpret::{Interpret, InterpretError, InterpretName, InterpretStatus, Outcome};
-use crate::inventory::Inventory;
-use crate::score::Score;
-use crate::topology::{HelmCommand, K8sclient, Topology};
-use harmony_types::id::Id;
-
-#[derive(Clone)]
-pub struct HelmCommandExecutor {
-    pub env: HashMap<String, String>,
-    pub path: Option<PathBuf>,
-    pub args: Vec<String>,
-    pub api_versions: Option<Vec<String>>,
-    pub kube_version: String,
-    pub debug: Option<bool>,
-    pub globals: HelmGlobals,
-    pub chart: HelmChart,
-}
-
-#[derive(Clone)]
-pub struct HelmGlobals {
-    pub chart_home: Option<PathBuf>,
-    pub config_home: Option<PathBuf>,
-}
-
-#[derive(Debug, Clone, Serialize)]
-pub struct HelmChart {
-    pub name: String,
-    pub version: Option<String>,
-    pub repo: Option<String>,
-    pub release_name: Option<String>,
-    pub namespace: Option<String>,
-    pub additional_values_files: Vec<PathBuf>,
-    pub values_file: Option<PathBuf>,
-    pub values_inline: Option<String>,
-    pub include_crds: Option<bool>,
-    pub skip_hooks: Option<bool>,
-    pub api_versions: Option<Vec<String>>,
-    pub kube_version: Option<String>,
-    pub name_template: String,
-    pub skip_tests: Option<bool>,
-    pub debug: Option<bool>,
-}
-
-impl HelmCommandExecutor {
-    pub fn generate(mut self) -> Result<String, std::io::Error> {
-        if self.globals.chart_home.is_none() {
-            self.globals.chart_home = Some(PathBuf::from("charts"));
-        }
-
-        if self
-            .clone()
-            .chart
-            .clone()
-            .chart_exists_locally(self.clone().globals.chart_home.unwrap())
-            .is_none()
-        {
-            if self.chart.repo.is_none() {
-                return Err(std::io::Error::new(
-                    ErrorKind::Other,
-                    "Chart doesn't exist locally and no repo specified",
-                ));
-            }
-            self.clone().run_command(
-                self.chart
-                    .clone()
-                    .pull_command(self.globals.chart_home.clone().unwrap()),
-            )?;
-        }
-
-        let out = self.clone().run_command(
-            self.chart
-                .clone()
-                .helm_args(self.globals.chart_home.clone().unwrap()),
-        )?;
-
-        // TODO: don't use unwrap here
-        let s = String::from_utf8(out.stdout).unwrap();
-        debug!("helm stderr: {}", String::from_utf8(out.stderr).unwrap());
-        debug!("helm status: {}", out.status);
-        debug!("helm output: {s}");
-
-        let clean = s.split_once("---").unwrap().1;
-
-        Ok(clean.to_string())
-    }
-
-    pub fn version(self) -> Result<String, std::io::Error> {
-        let out = self.run_command(vec![
-            "version".to_string(),
-            "-c".to_string(),
-            "--short".to_string(),
-        ])?;
-
-        // TODO: don't use unwrap
-        Ok(String::from_utf8(out.stdout).unwrap())
-    }
-
-    pub fn run_command(mut self, mut args: Vec<String>) -> Result<Output, std::io::Error> {
-        if let Some(d) = self.debug {
-            if d {
-                args.push("--debug".to_string());
-            }
-        }
-
-        let path = if let Some(p) = self.path {
-            p
-        } else {
-            PathBuf::from("helm")
-        };
-
-        let config_home = match self.globals.config_home {
-            Some(p) => p,
-            None => PathBuf::from(TempDir::new()?.path()),
-        };
-
-        if let Some(yaml_str) = self.chart.values_inline {
-            let tf: TempFile = temp_file::with_contents(yaml_str.as_bytes());
-            self.chart
-                .additional_values_files
-                .push(PathBuf::from(tf.path()));
-        };
-
-        self.env.insert(
-            "HELM_CONFIG_HOME".to_string(),
-            config_home.to_str().unwrap().to_string(),
-        );
-        self.env.insert(
-            "HELM_CACHE_HOME".to_string(),
-            config_home.to_str().unwrap().to_string(),
-        );
-        self.env.insert(
-            "HELM_DATA_HOME".to_string(),
-            config_home.to_str().unwrap().to_string(),
-        );
-
-        Command::new(path).envs(self.env).args(args).output()
-    }
-}
-
-impl HelmChart {
-    pub fn chart_exists_locally(self, chart_home: PathBuf) -> Option<PathBuf> {
-        let chart_path =
-            PathBuf::from(chart_home.to_str().unwrap().to_string() + "/" + &self.name.to_string());
-
-        if chart_path.exists() {
-            Some(chart_path)
-        } else {
-            None
-        }
-    }
-
-    pub fn pull_command(self, chart_home: PathBuf) -> Vec<String> {
-        let mut args = vec![
-            "pull".to_string(),
-            "--untar".to_string(),
-            "--untardir".to_string(),
-            chart_home.to_str().unwrap().to_string(),
-        ];
-
-        match self.repo {
-            Some(r) => {
-                if r.starts_with("oci://") {
-                    args.push(
-                        r.trim_end_matches("/").to_string() + "/" + self.name.clone().as_str(),
-                    );
-                } else {
-                    args.push("--repo".to_string());
-                    args.push(r.to_string());
-
-                    args.push(self.name);
-                }
-            }
-            None => args.push(self.name),
-        };
-
-        if let Some(v) = self.version {
-            args.push("--version".to_string());
-            args.push(v.to_string());
-        }
-
-        args
-    }
-
-    pub fn helm_args(self, chart_home: PathBuf) -> Vec<String> {
-        let mut args: Vec<String> = vec!["template".to_string()];
-
-        match self.release_name {
-            Some(rn) => args.push(rn.to_string()),
-            None => args.push("--generate-name".to_string()),
-        }
-
-        args.push(
-            PathBuf::from(chart_home.to_str().unwrap().to_string() + "/" + self.name.as_str())
-                .to_str()
-                .unwrap()
-                .to_string(),
-        );
-
-        if let Some(n) = self.namespace {
-            args.push("--namespace".to_string());
-            args.push(n.to_string());
-        }
-
-        if let Some(f) = self.values_file {
-            args.push("-f".to_string());
-            args.push(f.to_str().unwrap().to_string());
-        }
-
-        for f in self.additional_values_files {
-            args.push("-f".to_string());
-            args.push(f.to_str().unwrap().to_string());
-        }
-
-        if let Some(vv) = self.api_versions {
-            for v in vv {
-                args.push("--api-versions".to_string());
-                args.push(v);
-            }
-        }
-
-        if let Some(kv) = self.kube_version {
-            args.push("--kube-version".to_string());
-            args.push(kv);
-        }
-
-        if let Some(crd) = self.include_crds {
-            if crd {
-                args.push("--include-crds".to_string());
-            }
-        }
-
-        if let Some(st) = self.skip_tests {
-            if st {
-                args.push("--skip-tests".to_string());
-            }
-        }
-
-        if let Some(sh) = self.skip_hooks {
-            if sh {
-                args.push("--no-hooks".to_string());
-            }
-        }
-
-        if let Some(d) = self.debug {
-            if d {
-                args.push("--debug".to_string());
-            }
-        }
-
-        args
-    }
-}
-
-#[derive(Debug, Clone, Serialize)]
-pub struct HelmChartScoreV2 {
-    pub chart: HelmChart,
-}
-
-impl<T: Topology + K8sclient + HelmCommand> Score<T> for HelmChartScoreV2 {
-    fn create_interpret(&self) -> Box<dyn Interpret<T>> {
-        Box::new(HelmChartInterpretV2 {
-            score: self.clone(),
-        })
-    }
-
-    fn name(&self) -> String {
-        format!(
-            "{} {} HelmChartScoreV2",
-            self.chart
-                .release_name
-                .clone()
-                .unwrap_or("Unknown".to_string()),
-            self.chart.name
-        )
-    }
-}
-
-#[derive(Debug, Serialize)]
-pub struct HelmChartInterpretV2 {
-    pub score: HelmChartScoreV2,
-}
-impl HelmChartInterpretV2 {}
-
-#[async_trait]
-impl<T: Topology + K8sclient + HelmCommand> Interpret<T> for HelmChartInterpretV2 {
-    async fn execute(
-        &self,
-        _inventory: &Inventory,
-        _topology: &T,
-    ) -> Result<Outcome, InterpretError> {
-        let _ns = self
-            .score
-            .chart
-            .namespace
-            .as_ref()
-            .unwrap_or_else(|| todo!("Get namespace from active kubernetes cluster"));
-
-        let helm_executor = HelmCommandExecutor {
-            env: HashMap::new(),
-            path: None,
-            args: vec![],
-            api_versions: None,
-            kube_version: "v1.33.0".to_string(),
-            debug: Some(false),
-            globals: HelmGlobals {
-                chart_home: None,
-                config_home: None,
-            },
-            chart: self.score.chart.clone(),
-        };
-
-        // let mut helm_options = Vec::new();
-        // if self.score.create_namespace {
-        //     helm_options.push(NonBlankString::from_str("--create-namespace").unwrap());
-        // }
-
-        let res = helm_executor.generate();
-
-        let _output = match res {
-            Ok(output) => output,
-            Err(err) => return Err(InterpretError::new(err.to_string())),
-        };
-
-        // TODO: implement actually applying the YAML from the templating in the generate function to a k8s cluster, having trouble passing in straight YAML into the k8s client
-
-        // let k8s_resource = k8s_openapi::serde_json::from_str(output.as_str()).unwrap();
-
-        // let client = topology
-        //     .k8s_client()
-        //     .await
-        //     .expect("Environment should provide enough information to instanciate a client")
-        //     .apply_namespaced(&vec![output], Some(ns.to_string().as_str()));
-        // match client.apply_yaml(output) {
-        //     Ok(_) => return Ok(Outcome::success("Helm chart deployed".to_string())),
-        //     Err(e) => return Err(InterpretError::new(e)),
-        // }
-
-        Ok(Outcome::success("Helm chart deployed".to_string()))
-    }
-
-    fn get_name(&self) -> InterpretName {
-        InterpretName::HelmCommand
-    }
-    fn get_version(&self) -> Version {
-        todo!()
-    }
-    fn get_status(&self) -> InterpretStatus {
-        todo!()
-    }
-    fn get_children(&self) -> Vec<Id> {
-        todo!()
-    }
-}

harmony/src/modules/helm/mod.rs

@@ -1,2 +1 @@
 pub mod chart;
-pub mod command;

harmony/src/modules/k8s/resource.rs

@@ -38,13 +38,15 @@ impl<
         + 'static
         + Send
         + Clone,
-    T: Topology,
+    T: Topology + K8sclient,
 > Score<T> for K8sResourceScore<K>
 where
     <K as kube::Resource>::DynamicType: Default,
 {
     fn create_interpret(&self) -> Box<dyn Interpret<T>> {
-        todo!()
+        Box::new(K8sResourceInterpret {
+            score: self.clone(),
+        })
     }
 
     fn name(&self) -> String {

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

@@ -1,18 +1,23 @@
 use std::any::Any;
-use std::collections::BTreeMap;
+use std::collections::{BTreeMap, HashMap};
 
 use async_trait::async_trait;
+use harmony_types::k8s_name::K8sName;
 use k8s_openapi::api::core::v1::Secret;
-use kube::api::ObjectMeta;
-use log::debug;
+use kube::Resource;
+use kube::api::{DynamicObject, ObjectMeta};
+use log::{debug, trace};
 use serde::Serialize;
 use serde_json::json;
 use serde_yaml::{Mapping, Value};
 
+use crate::infra::kube::kube_resource_to_dynamic;
 use crate::modules::monitoring::kube_prometheus::crd::crd_alertmanager_config::{
     AlertmanagerConfig, AlertmanagerConfigSpec, CRDPrometheus,
 };
 use crate::modules::monitoring::kube_prometheus::crd::rhob_alertmanager_config::RHOBObservability;
+use crate::modules::monitoring::okd::OpenshiftClusterAlertSender;
+use crate::topology::oberservability::monitoring::AlertManagerReceiver;
 use crate::{
     interpret::{InterpretError, Outcome},
     modules::monitoring::{
@@ -28,14 +33,13 @@ use harmony_types::net::Url;
 
 #[derive(Debug, Clone, Serialize)]
 pub struct DiscordWebhook {
-    pub name: String,
+    pub name: K8sName,
     pub url: Url,
+    pub selectors: Vec<HashMap<String, String>>,
 }
 
-#[async_trait]
-impl AlertReceiver<RHOBObservability> for DiscordWebhook {
-    async fn install(&self, sender: &RHOBObservability) -> Result<Outcome, InterpretError> {
-        let ns = sender.namespace.clone();
+impl DiscordWebhook {
+    fn get_receiver_config(&self) -> Result<AlertManagerReceiver, String> {
         let secret_name = format!("{}-secret", self.name.clone());
         let webhook_key = format!("{}", self.url.clone());
 
@@ -52,33 +56,91 @@ impl AlertReceiver<RHOBObservability> for DiscordWebhook {
             ..Default::default()
         };
 
-        let _ = sender.client.apply(&secret, Some(&ns)).await;
+        let mut matchers: Vec<String> = Vec::new();
+        for selector in &self.selectors {
+            trace!("selector: {:#?}", selector);
+            for (k, v) in selector {
+                matchers.push(format!("{} = {}", k, v));
+            }
+        }
+
+        Ok(AlertManagerReceiver {
+            additional_ressources: vec![kube_resource_to_dynamic(&secret)?],
+
+            receiver_config: json!({
+                "name": self.name,
+                "discord_configs": [
+                    {
+                    "webhook_url": self.url.clone(),
+                    "title": "{{ template \"discord.default.title\" . }}",
+                    "message": "{{ template \"discord.default.message\" . }}"
+                    }
+                ]
+            }),
+            route_config: json!({
+                "receiver": self.name,
+                "matchers": matchers,
+
+            }),
+        })
+    }
+}
+
+#[async_trait]
+impl AlertReceiver<OpenshiftClusterAlertSender> for DiscordWebhook {
+    async fn install(
+        &self,
+        sender: &OpenshiftClusterAlertSender,
+    ) -> Result<Outcome, InterpretError> {
+        todo!()
+    }
+
+    fn name(&self) -> String {
+        self.name.clone().to_string()
+    }
+
+    fn clone_box(&self) -> Box<dyn AlertReceiver<OpenshiftClusterAlertSender>> {
+        Box::new(self.clone())
+    }
+
+    fn as_any(&self) -> &dyn Any {
+        todo!()
+    }
+
+    fn as_alertmanager_receiver(&self) -> Result<AlertManagerReceiver, String> {
+        self.get_receiver_config()
+    }
+}
+
+#[async_trait]
+impl AlertReceiver<RHOBObservability> for DiscordWebhook {
+    fn as_alertmanager_receiver(&self) -> Result<AlertManagerReceiver, String> {
+        todo!()
+    }
+
+    async fn install(&self, sender: &RHOBObservability) -> Result<Outcome, InterpretError> {
+        let ns = sender.namespace.clone();
+
+        let config = self.get_receiver_config()?;
+        for resource in config.additional_ressources.iter() {
+            todo!("can I apply a dynamicresource");
+            // sender.client.apply(resource, Some(&ns)).await;
+        }
+
         let spec = crate::modules::monitoring::kube_prometheus::crd::rhob_alertmanager_config::AlertmanagerConfigSpec {
             data: json!({
                 "route": {
                     "receiver": self.name,
                 },
                 "receivers": [
-                    {
-                        "name": self.name,
-                        "discordConfigs": [
-                            {
-                            "apiURL": {
-                                "name": secret_name,
-                                "key":  "webhook-url",
-                            },
-                            "title": "{{ template \"discord.default.title\" . }}",
-                            "message": "{{ template \"discord.default.message\" . }}"
-                            }
-                        ]
-                    }
+                    config.receiver_config
                 ]
             }),
         };
 
         let alertmanager_configs = crate::modules::monitoring::kube_prometheus::crd::rhob_alertmanager_config::AlertmanagerConfig {
             metadata: ObjectMeta {
-                name: Some(self.name.clone()),
+                name: Some(self.name.clone().to_string()),
                 labels: Some(std::collections::BTreeMap::from([(
                     "alertmanagerConfig".to_string(),
                     "enabled".to_string(),
@@ -122,6 +184,9 @@ impl AlertReceiver<RHOBObservability> for DiscordWebhook {
 
 #[async_trait]
 impl AlertReceiver<CRDPrometheus> for DiscordWebhook {
+    fn as_alertmanager_receiver(&self) -> Result<AlertManagerReceiver, String> {
+        todo!()
+    }
     async fn install(&self, sender: &CRDPrometheus) -> Result<Outcome, InterpretError> {
         let ns = sender.namespace.clone();
         let secret_name = format!("{}-secret", self.name.clone());
@@ -167,7 +232,7 @@ impl AlertReceiver<CRDPrometheus> for DiscordWebhook {
 
         let alertmanager_configs = AlertmanagerConfig {
             metadata: ObjectMeta {
-                name: Some(self.name.clone()),
+                name: Some(self.name.clone().to_string()),
                 labels: Some(std::collections::BTreeMap::from([(
                     "alertmanagerConfig".to_string(),
                     "enabled".to_string(),
@@ -200,6 +265,9 @@ impl AlertReceiver<CRDPrometheus> for DiscordWebhook {
 
 #[async_trait]
 impl AlertReceiver<Prometheus> for DiscordWebhook {
+    fn as_alertmanager_receiver(&self) -> Result<AlertManagerReceiver, String> {
+        todo!()
+    }
     async fn install(&self, sender: &Prometheus) -> Result<Outcome, InterpretError> {
         sender.install_receiver(self).await
     }
@@ -217,7 +285,7 @@ impl AlertReceiver<Prometheus> for DiscordWebhook {
 #[async_trait]
 impl PrometheusReceiver for DiscordWebhook {
     fn name(&self) -> String {
-        self.name.clone()
+        self.name.clone().to_string()
     }
     async fn configure_receiver(&self) -> AlertManagerChannelConfig {
         self.get_config().await
@@ -226,6 +294,9 @@ impl PrometheusReceiver for DiscordWebhook {
 
 #[async_trait]
 impl AlertReceiver<KubePrometheus> for DiscordWebhook {
+    fn as_alertmanager_receiver(&self) -> Result<AlertManagerReceiver, String> {
+        todo!()
+    }
     async fn install(&self, sender: &KubePrometheus) -> Result<Outcome, InterpretError> {
         sender.install_receiver(self).await
     }
@@ -243,7 +314,7 @@ impl AlertReceiver<KubePrometheus> for DiscordWebhook {
 #[async_trait]
 impl KubePrometheusReceiver for DiscordWebhook {
     fn name(&self) -> String {
-        self.name.clone()
+        self.name.clone().to_string()
     }
     async fn configure_receiver(&self) -> AlertManagerChannelConfig {
         self.get_config().await
@@ -270,7 +341,7 @@ impl DiscordWebhook {
         let mut route = Mapping::new();
         route.insert(
             Value::String("receiver".to_string()),
-            Value::String(self.name.clone()),
+            Value::String(self.name.clone().to_string()),
         );
         route.insert(
             Value::String("matchers".to_string()),
@@ -284,7 +355,7 @@ impl DiscordWebhook {
         let mut receiver = Mapping::new();
         receiver.insert(
             Value::String("name".to_string()),
-            Value::String(self.name.clone()),
+            Value::String(self.name.clone().to_string()),
         );
 
         let mut discord_config = Mapping::new();
@@ -309,8 +380,9 @@ mod tests {
     #[tokio::test]
     async fn discord_serialize_should_match() {
         let discord_receiver = DiscordWebhook {
-            name: "test-discord".to_string(),
+            name: K8sName("test-discord".to_string()),
             url: Url::Url(url::Url::parse("https://discord.i.dont.exist.com").unwrap()),
+            selectors: vec![],
         };
 
         let discord_receiver_receiver =

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

@@ -19,7 +19,7 @@ use crate::{
         },
         prometheus::prometheus::{Prometheus, PrometheusReceiver},
     },
-    topology::oberservability::monitoring::AlertReceiver,
+    topology::oberservability::monitoring::{AlertManagerReceiver, AlertReceiver},
 };
 use harmony_types::net::Url;
 
@@ -31,6 +31,9 @@ pub struct WebhookReceiver {
 
 #[async_trait]
 impl AlertReceiver<RHOBObservability> for WebhookReceiver {
+    fn as_alertmanager_receiver(&self) -> Result<AlertManagerReceiver, String> {
+        todo!()
+    }
     async fn install(&self, sender: &RHOBObservability) -> Result<Outcome, InterpretError> {
         let spec = crate::modules::monitoring::kube_prometheus::crd::rhob_alertmanager_config::AlertmanagerConfigSpec {
             data: json!({
@@ -97,6 +100,9 @@ impl AlertReceiver<RHOBObservability> for WebhookReceiver {
 
 #[async_trait]
 impl AlertReceiver<CRDPrometheus> for WebhookReceiver {
+    fn as_alertmanager_receiver(&self) -> Result<AlertManagerReceiver, String> {
+        todo!()
+    }
     async fn install(&self, sender: &CRDPrometheus) -> Result<Outcome, InterpretError> {
         let spec = crate::modules::monitoring::kube_prometheus::crd::crd_alertmanager_config::AlertmanagerConfigSpec {
             data: json!({
@@ -158,6 +164,9 @@ impl AlertReceiver<CRDPrometheus> for WebhookReceiver {
 
 #[async_trait]
 impl AlertReceiver<Prometheus> for WebhookReceiver {
+    fn as_alertmanager_receiver(&self) -> Result<AlertManagerReceiver, String> {
+        todo!()
+    }
     async fn install(&self, sender: &Prometheus) -> Result<Outcome, InterpretError> {
         sender.install_receiver(self).await
     }
@@ -184,6 +193,9 @@ impl PrometheusReceiver for WebhookReceiver {
 
 #[async_trait]
 impl AlertReceiver<KubePrometheus> for WebhookReceiver {
+    fn as_alertmanager_receiver(&self) -> Result<AlertManagerReceiver, String> {
+        todo!()
+    }
     async fn install(&self, sender: &KubePrometheus) -> Result<Outcome, InterpretError> {
         sender.install_receiver(self).await
     }

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

@@ -1,21 +1,23 @@
 use std::sync::Arc;
 
-use async_trait::async_trait;
+use log::debug;
 use serde::Serialize;
 
 use crate::{
-    data::Version,
-    interpret::{Interpret, InterpretError, InterpretName, InterpretStatus, Outcome},
-    inventory::Inventory,
+    interpret::Interpret,
     modules::{
         application::Application,
-        monitoring::kube_prometheus::crd::crd_alertmanager_config::CRDPrometheus,
-        prometheus::prometheus::PrometheusApplicationMonitoring,
+        monitoring::{
+            grafana::grafana::Grafana, kube_prometheus::crd::crd_alertmanager_config::CRDPrometheus,
+        },
+        prometheus::prometheus::PrometheusMonitoring,
     },
     score::Score,
-    topology::{PreparationOutcome, Topology, oberservability::monitoring::AlertReceiver},
+    topology::{
+        K8sclient, Topology,
+        oberservability::monitoring::{AlertReceiver, AlertingInterpret, ScrapeTarget},
+    },
 };
-use harmony_types::id::Id;
 
 #[derive(Debug, Clone, Serialize)]
 pub struct ApplicationMonitoringScore {
@@ -24,12 +26,16 @@ pub struct ApplicationMonitoringScore {
     pub receivers: Vec<Box<dyn AlertReceiver<CRDPrometheus>>>,
 }
 
-impl<T: Topology + PrometheusApplicationMonitoring<CRDPrometheus>> Score<T>
+impl<T: Topology + PrometheusMonitoring<CRDPrometheus> + K8sclient + Grafana> Score<T>
     for ApplicationMonitoringScore
 {
     fn create_interpret(&self) -> Box<dyn Interpret<T>> {
-        Box::new(ApplicationMonitoringInterpret {
-            score: self.clone(),
+        debug!("creating alerting interpret");
+        Box::new(AlertingInterpret {
+            sender: self.sender.clone(),
+            receivers: self.receivers.clone(),
+            rules: vec![],
+            scrape_targets: None,
         })
     }
 
@@ -40,55 +46,3 @@ impl<T: Topology + PrometheusApplicationMonitoring<CRDPrometheus>> Score<T>
         )
     }
 }
-
-#[derive(Debug)]
-pub struct ApplicationMonitoringInterpret {
-    score: ApplicationMonitoringScore,
-}
-
-#[async_trait]
-impl<T: Topology + PrometheusApplicationMonitoring<CRDPrometheus>> Interpret<T>
-    for ApplicationMonitoringInterpret
-{
-    async fn execute(
-        &self,
-        inventory: &Inventory,
-        topology: &T,
-    ) -> Result<Outcome, InterpretError> {
-        let result = topology
-            .install_prometheus(
-                &self.score.sender,
-                inventory,
-                Some(self.score.receivers.clone()),
-            )
-            .await;
-
-        match result {
-            Ok(outcome) => match outcome {
-                PreparationOutcome::Success { details: _ } => {
-                    Ok(Outcome::success("Prometheus installed".into()))
-                }
-                PreparationOutcome::Noop => {
-                    Ok(Outcome::noop("Prometheus installation skipped".into()))
-                }
-            },
-            Err(err) => Err(InterpretError::from(err)),
-        }
-    }
-
-    fn get_name(&self) -> InterpretName {
-        InterpretName::ApplicationMonitoring
-    }
-
-    fn get_version(&self) -> Version {
-        todo!()
-    }
-
-    fn get_status(&self) -> InterpretStatus {
-        todo!()
-    }
-
-    fn get_children(&self) -> Vec<Id> {
-        todo!()
-    }
-}

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

@@ -12,7 +12,7 @@ use crate::{
         monitoring::kube_prometheus::crd::{
             crd_alertmanager_config::CRDPrometheus, rhob_alertmanager_config::RHOBObservability,
         },
-        prometheus::prometheus::PrometheusApplicationMonitoring,
+        prometheus::prometheus::PrometheusMonitoring,
     },
     score::Score,
     topology::{PreparationOutcome, Topology, oberservability::monitoring::AlertReceiver},
@@ -26,7 +26,7 @@ pub struct ApplicationRHOBMonitoringScore {
     pub receivers: Vec<Box<dyn AlertReceiver<RHOBObservability>>>,
 }
 
-impl<T: Topology + PrometheusApplicationMonitoring<RHOBObservability>> Score<T>
+impl<T: Topology + PrometheusMonitoring<RHOBObservability>> Score<T>
     for ApplicationRHOBMonitoringScore
 {
     fn create_interpret(&self) -> Box<dyn Interpret<T>> {
@@ -49,7 +49,7 @@ pub struct ApplicationRHOBMonitoringInterpret {
 }
 
 #[async_trait]
-impl<T: Topology + PrometheusApplicationMonitoring<RHOBObservability>> Interpret<T>
+impl<T: Topology + PrometheusMonitoring<RHOBObservability>> Interpret<T>
     for ApplicationRHOBMonitoringInterpret
 {
     async fn execute(

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

@@ -0,0 +1,17 @@
+use async_trait::async_trait;
+use k8s_openapi::Resource;
+
+use crate::{
+    inventory::Inventory,
+    topology::{PreparationError, PreparationOutcome},
+};
+
+#[async_trait]
+pub trait Grafana {
+    async fn ensure_grafana_operator(
+        &self,
+        inventory: &Inventory,
+    ) -> Result<PreparationOutcome, PreparationError>;
+
+    async fn install_grafana(&self) -> Result<PreparationOutcome, PreparationError>;
+}

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

@@ -1,27 +1,28 @@
+use harmony_macros::hurl;
 use non_blank_string_rs::NonBlankString;
-use std::str::FromStr;
+use std::{collections::HashMap, str::FromStr};
 
-use crate::modules::helm::chart::HelmChartScore;
-
-pub fn grafana_helm_chart_score(ns: &str) -> HelmChartScore {
-    let values = r#"
-rbac:
-  namespaced: true
-sidecar:
-  dashboards:
-    enabled: true
-        "#
-    .to_string();
+use crate::modules::helm::chart::{HelmChartScore, HelmRepository};
 
+pub fn grafana_helm_chart_score(ns: &str, namespace_scope: bool) -> HelmChartScore {
+    let mut values_overrides = HashMap::new();
+    values_overrides.insert(
+        NonBlankString::from_str("namespaceScope").unwrap(),
+        namespace_scope.to_string(),
+    );
     HelmChartScore {
         namespace: Some(NonBlankString::from_str(ns).unwrap()),
-        release_name: NonBlankString::from_str("grafana").unwrap(),
-        chart_name: NonBlankString::from_str("oci://ghcr.io/grafana/helm-charts/grafana").unwrap(),
+        release_name: NonBlankString::from_str("grafana-operator").unwrap(),
+        chart_name: NonBlankString::from_str("grafana/grafana-operator").unwrap(),
         chart_version: None,
-        values_overrides: None,
-        values_yaml: Some(values.to_string()),
+        values_overrides: Some(values_overrides),
+        values_yaml: None,
         create_namespace: true,
         install_only: true,
-        repository: None,
+        repository: Some(HelmRepository::new(
+            "grafana".to_string(),
+            hurl!("https://grafana.github.io/helm-charts"),
+            true,
+        )),
     }
 }

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

@@ -1 +1,2 @@
+pub mod grafana;
 pub mod helm;

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

@@ -1,12 +1,25 @@
 use std::sync::Arc;
 
+use async_trait::async_trait;
 use kube::CustomResource;
 use schemars::JsonSchema;
 use serde::{Deserialize, Serialize};
 
-use crate::topology::{
-    k8s::K8sClient,
-    oberservability::monitoring::{AlertReceiver, AlertSender},
+use crate::{
+    interpret::{InterpretError, Outcome},
+    inventory::Inventory,
+    modules::{
+        monitoring::{
+            grafana::grafana::Grafana, kube_prometheus::crd::service_monitor::ServiceMonitor,
+        },
+        prometheus::prometheus::PrometheusMonitoring,
+    },
+    topology::{
+        K8sclient, Topology,
+        installable::Installable,
+        k8s::K8sClient,
+        oberservability::monitoring::{AlertReceiver, AlertSender, ScrapeTarget},
+    },
 };
 
 #[derive(CustomResource, Serialize, Deserialize, Debug, Clone, JsonSchema)]
@@ -26,6 +39,7 @@ pub struct AlertmanagerConfigSpec {
 pub struct CRDPrometheus {
     pub namespace: String,
     pub client: Arc<K8sClient>,
+    pub service_monitor: Vec<ServiceMonitor>,
 }
 
 impl AlertSender for CRDPrometheus {
@@ -40,6 +54,12 @@ impl Clone for Box<dyn AlertReceiver<CRDPrometheus>> {
     }
 }
 
+impl Clone for Box<dyn ScrapeTarget<CRDPrometheus>> {
+    fn clone(&self) -> Self {
+        self.clone_box()
+    }
+}
+
 impl Serialize for Box<dyn AlertReceiver<CRDPrometheus>> {
     fn serialize<S>(&self, _serializer: S) -> Result<S::Ok, S::Error>
     where
@@ -48,3 +68,24 @@ impl Serialize for Box<dyn AlertReceiver<CRDPrometheus>> {
         todo!()
     }
 }
+
+#[async_trait]
+impl<T: Topology + K8sclient + PrometheusMonitoring<CRDPrometheus> + Grafana> Installable<T>
+    for CRDPrometheus
+{
+    async fn configure(&self, inventory: &Inventory, topology: &T) -> Result<(), InterpretError> {
+        topology.ensure_grafana_operator(inventory).await?;
+        topology.ensure_prometheus_operator(self, inventory).await?;
+        Ok(())
+    }
+
+    async fn ensure_installed(
+        &self,
+        inventory: &Inventory,
+        topology: &T,
+    ) -> Result<(), InterpretError> {
+        topology.install_grafana().await?;
+        topology.install_prometheus(&self, inventory, None).await?;
+        Ok(())
+    }
+}

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

@@ -103,9 +103,34 @@ pub struct GrafanaDashboardSpec {
     #[serde(default, skip_serializing_if = "Option::is_none")]
     pub resync_period: Option<String>,
 
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub datasources: Option<Vec<GrafanaDashboardDatasource>>,
+
     pub instance_selector: LabelSelector,
 
-    pub json: String,
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub json: Option<String>,
+
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub grafana_com: Option<GrafanaCom>,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, JsonSchema)]
+#[serde(rename_all = "camelCase")]
+pub struct GrafanaDashboardDatasource {
+    pub input_name: String,
+    pub datasource_name: String,
+}
+
+// ------------------------------------------------------------------------------------------------
+
+#[derive(Serialize, Deserialize, Debug, Clone, JsonSchema)]
+#[serde(rename_all = "camelCase")]
+pub struct GrafanaCom {
+    pub id: u32,
+
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub revision: Option<u32>,
 }
 
 // ------------------------------------------------------------------------------------------------
@@ -126,20 +151,79 @@ pub struct GrafanaDatasourceSpec {
     pub allow_cross_namespace_import: Option<bool>,
 
     pub datasource: GrafanaDatasourceConfig,
+
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub values_from: Option<Vec<GrafanaValueFrom>>,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, JsonSchema)]
+#[serde(rename_all = "camelCase")]
+pub struct GrafanaValueFrom {
+    pub target_path: String,
+    pub value_from: GrafanaValueSource,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, JsonSchema)]
+#[serde(rename_all = "camelCase")]
+pub struct GrafanaValueSource {
+    pub secret_key_ref: GrafanaSecretKeyRef,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, JsonSchema)]
+#[serde(rename_all = "camelCase")]
+pub struct GrafanaSecretKeyRef {
+    pub name: String,
+    pub key: String,
 }
 
 #[derive(Serialize, Deserialize, Debug, Clone, JsonSchema)]
 #[serde(rename_all = "camelCase")]
 pub struct GrafanaDatasourceConfig {
     pub access: String,
-    pub database: Option<String>,
     #[serde(default, skip_serializing_if = "Option::is_none")]
-    pub json_data: Option<BTreeMap<String, String>>,
+    pub database: Option<String>,
     pub name: String,
     pub r#type: String,
     pub url: String,
+    /// Represents jsonData in the GrafanaDatasource spec
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub json_data: Option<GrafanaDatasourceJsonData>,
+
+    /// Represents secureJsonData (secrets)
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub secure_json_data: Option<GrafanaDatasourceSecureJsonData>,
+
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub is_default: Option<bool>,
+
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub editable: Option<bool>,
 }
 
+#[derive(Serialize, Deserialize, Debug, Clone, JsonSchema)]
+#[serde(rename_all = "camelCase")]
+pub struct GrafanaDatasourceJsonData {
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub time_interval: Option<String>,
+
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub http_header_name1: Option<String>,
+
+    /// Disable TLS skip verification (false = verify)
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub tls_skip_verify: Option<bool>,
+
+    /// Auth type - set to "forward" for OpenShift OAuth identity
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub oauth_pass_thru: Option<bool>,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, JsonSchema)]
+#[serde(rename_all = "camelCase")]
+pub struct GrafanaDatasourceSecureJsonData {
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub http_header_value1: Option<String>,
+}
 // ------------------------------------------------------------------------------------------------
 
 #[derive(Serialize, Deserialize, Debug, Clone, JsonSchema, Default)]

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

@@ -0,0 +1,187 @@
+use std::net::IpAddr;
+
+use async_trait::async_trait;
+use kube::CustomResource;
+use schemars::JsonSchema;
+use serde::{Deserialize, Serialize};
+
+use crate::{
+    modules::monitoring::kube_prometheus::crd::{
+        crd_alertmanager_config::CRDPrometheus, crd_prometheuses::LabelSelector,
+    },
+    topology::oberservability::monitoring::ScrapeTarget,
+};
+
+#[derive(CustomResource, Serialize, Deserialize, Debug, Clone, JsonSchema)]
+#[kube(
+    group = "monitoring.coreos.com",
+    version = "v1alpha1",
+    kind = "ScrapeConfig",
+    plural = "scrapeconfigs",
+    namespaced
+)]
+#[serde(rename_all = "camelCase")]
+pub struct ScrapeConfigSpec {
+    /// List of static configurations.
+    pub static_configs: Option<Vec<StaticConfig>>,
+
+    /// Kubernetes service discovery.
+    pub kubernetes_sd_configs: Option<Vec<KubernetesSDConfig>>,
+
+    /// HTTP-based service discovery.
+    pub http_sd_configs: Option<Vec<HttpSDConfig>>,
+
+    /// File-based service discovery.
+    pub file_sd_configs: Option<Vec<FileSDConfig>>,
+
+    /// DNS-based service discovery.
+    pub dns_sd_configs: Option<Vec<DnsSDConfig>>,
+
+    /// Consul service discovery.
+    pub consul_sd_configs: Option<Vec<ConsulSDConfig>>,
+
+    /// Relabeling configuration applied to discovered targets.
+    pub relabel_configs: Option<Vec<RelabelConfig>>,
+
+    /// Metric relabeling configuration applied to scraped samples.
+    pub metric_relabel_configs: Option<Vec<RelabelConfig>>,
+
+    /// Path to scrape metrics from (defaults to `/metrics`).
+    pub metrics_path: Option<String>,
+
+    /// Interval at which Prometheus scrapes targets (e.g., "30s").
+    pub scrape_interval: Option<String>,
+
+    /// Timeout for scraping (e.g., "10s").
+    pub scrape_timeout: Option<String>,
+
+    /// Optional job name override.
+    pub job_name: Option<String>,
+
+    /// Optional scheme (http or https).
+    pub scheme: Option<String>,
+
+    /// Authorization paramaters for snmp walk
+    pub params: Option<Params>,
+}
+
+/// Static configuration section of a ScrapeConfig.
+#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema)]
+#[serde(rename_all = "camelCase")]
+pub struct StaticConfig {
+    pub targets: Vec<String>,
+
+    pub labels: Option<LabelSelector>,
+}
+
+/// Relabeling configuration for target or metric relabeling.
+#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema)]
+#[serde(rename_all = "camelCase")]
+pub struct RelabelConfig {
+    pub source_labels: Option<Vec<String>>,
+    pub separator: Option<String>,
+    pub target_label: Option<String>,
+    pub regex: Option<String>,
+    pub modulus: Option<u64>,
+    pub replacement: Option<String>,
+    pub action: Option<String>,
+}
+
+/// Kubernetes service discovery configuration.
+#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema)]
+#[serde(rename_all = "camelCase")]
+pub struct KubernetesSDConfig {
+    ///"pod", "service", "endpoints"pub role: String,
+    pub namespaces: Option<NamespaceSelector>,
+    pub selectors: Option<Vec<LabelSelector>>,
+    pub api_server: Option<String>,
+    pub bearer_token_file: Option<String>,
+    pub tls_config: Option<TLSConfig>,
+}
+
+/// Namespace selector for Kubernetes service discovery.
+#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema)]
+#[serde(rename_all = "camelCase")]
+pub struct NamespaceSelector {
+    pub any: Option<bool>,
+    pub match_names: Option<Vec<String>>,
+}
+
+/// HTTP-based service discovery configuration.
+#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema)]
+#[serde(rename_all = "camelCase")]
+pub struct HttpSDConfig {
+    pub url: String,
+    pub refresh_interval: Option<String>,
+    pub basic_auth: Option<BasicAuth>,
+    pub authorization: Option<Authorization>,
+    pub tls_config: Option<TLSConfig>,
+}
+
+/// File-based service discovery configuration.
+#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema)]
+#[serde(rename_all = "camelCase")]
+pub struct FileSDConfig {
+    pub files: Vec<String>,
+    pub refresh_interval: Option<String>,
+}
+
+/// DNS-based service discovery configuration.
+#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema)]
+#[serde(rename_all = "camelCase")]
+pub struct DnsSDConfig {
+    pub names: Vec<String>,
+    pub refresh_interval: Option<String>,
+    pub type_: Option<String>, // SRV, A, AAAA
+    pub port: Option<u16>,
+}
+
+/// Consul service discovery configuration.
+#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema)]
+#[serde(rename_all = "camelCase")]
+pub struct ConsulSDConfig {
+    pub server: String,
+    pub services: Option<Vec<String>>,
+    pub scheme: Option<String>,
+    pub datacenter: Option<String>,
+    pub tag_separator: Option<String>,
+    pub refresh_interval: Option<String>,
+    pub tls_config: Option<TLSConfig>,
+}
+
+/// Basic authentication credentials.
+#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema)]
+#[serde(rename_all = "camelCase")]
+pub struct BasicAuth {
+    pub username: String,
+    pub password: Option<String>,
+    pub password_file: Option<String>,
+}
+
+/// Bearer token or other auth mechanisms.
+#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema)]
+#[serde(rename_all = "camelCase")]
+pub struct Authorization {
+    pub credentials: Option<String>,
+    pub credentials_file: Option<String>,
+    pub type_: Option<String>,
+}
+
+/// TLS configuration for secure scraping.
+#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema)]
+#[serde(rename_all = "camelCase")]
+pub struct TLSConfig {
+    pub ca_file: Option<String>,
+    pub cert_file: Option<String>,
+    pub key_file: Option<String>,
+    pub server_name: Option<String>,
+    pub insecure_skip_verify: Option<bool>,
+}
+
+/// Authorization parameters for SNMP walk.
+#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema)]
+#[serde(rename_all = "camelCase")]
+pub struct Params {
+    pub auth: Option<Vec<String>>,
+    pub module: Option<Vec<String>>,
+}

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

@@ -4,6 +4,7 @@ pub mod crd_default_rules;
 pub mod crd_grafana;
 pub mod crd_prometheus_rules;
 pub mod crd_prometheuses;
+pub mod crd_scrape_config;
 pub mod grafana_default_dashboard;
 pub mod grafana_operator;
 pub mod prometheus_operator;

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

@@ -31,6 +31,7 @@ impl<T: Topology + HelmCommand + TenantManager> Score<T> for HelmPrometheusAlert
             sender: KubePrometheus { config },
             receivers: self.receivers.clone(),
             rules: self.rules.clone(),
+            scrape_targets: None,
         })
     }
     fn name(&self) -> String {

harmony/src/modules/monitoring/mod.rs

@@ -6,3 +6,4 @@ pub mod kube_prometheus;
 pub mod ntfy;
 pub mod okd;
 pub mod prometheus;
+pub mod scrape_target;

harmony/src/modules/monitoring/ntfy/ntfy.rs

@@ -100,11 +100,7 @@ impl<T: Topology + HelmCommand + K8sclient + MultiTargetTopology> Interpret<T> f
 
         info!("deploying ntfy...");
         client
-            .wait_until_deployment_ready(
-                "ntfy".to_string(),
-                Some(self.score.namespace.as_str()),
-                None,
-            )
+            .wait_until_deployment_ready("ntfy", Some(self.score.namespace.as_str()), None)
             .await?;
         info!("ntfy deployed");
 

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

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

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

@@ -0,0 +1,90 @@
+use std::{collections::BTreeMap, sync::Arc};
+
+use crate::{
+    interpret::{InterpretError, Outcome},
+    topology::k8s::K8sClient,
+};
+use k8s_openapi::api::core::v1::ConfigMap;
+use kube::api::ObjectMeta;
+
+pub(crate) struct Config;
+
+impl Config {
+    pub async fn create_cluster_monitoring_config_cm(
+        client: &Arc<K8sClient>,
+    ) -> Result<Outcome, InterpretError> {
+        let mut data = BTreeMap::new();
+        data.insert(
+            "config.yaml".to_string(),
+            r#"
+enableUserWorkload: true
+alertmanagerMain:
+  enableUserAlertmanagerConfig: true
+"#
+            .to_string(),
+        );
+
+        let cm = ConfigMap {
+            metadata: ObjectMeta {
+                name: Some("cluster-monitoring-config".to_string()),
+                namespace: Some("openshift-monitoring".to_string()),
+                ..Default::default()
+            },
+            data: Some(data),
+            ..Default::default()
+        };
+        client.apply(&cm, Some("openshift-monitoring")).await?;
+
+        Ok(Outcome::success(
+            "updated cluster-monitoring-config-map".to_string(),
+        ))
+    }
+
+    pub async fn create_user_workload_monitoring_config_cm(
+        client: &Arc<K8sClient>,
+    ) -> Result<Outcome, InterpretError> {
+        let mut data = BTreeMap::new();
+        data.insert(
+            "config.yaml".to_string(),
+            r#"
+alertmanager: 
+  enabled: true
+  enableAlertmanagerConfig: true
+"#
+            .to_string(),
+        );
+        let cm = ConfigMap {
+            metadata: ObjectMeta {
+                name: Some("user-workload-monitoring-config".to_string()),
+                namespace: Some("openshift-user-workload-monitoring".to_string()),
+                ..Default::default()
+            },
+            data: Some(data),
+            ..Default::default()
+        };
+        client
+            .apply(&cm, Some("openshift-user-workload-monitoring"))
+            .await?;
+
+        Ok(Outcome::success(
+            "updated openshift-user-monitoring-config-map".to_string(),
+        ))
+    }
+
+    pub async fn verify_user_workload(client: &Arc<K8sClient>) -> Result<Outcome, InterpretError> {
+        let namespace = "openshift-user-workload-monitoring";
+        let alertmanager_name = "alertmanager-user-workload-0";
+        let prometheus_name = "prometheus-user-workload-0";
+        client
+            .wait_for_pod_ready(alertmanager_name, Some(namespace))
+            .await?;
+        client
+            .wait_for_pod_ready(prometheus_name, Some(namespace))
+            .await?;
+
+        Ok(Outcome::success(format!(
+            "pods: {}, {} ready in ns: {}",
+            alertmanager_name, prometheus_name, namespace
+        )))
+    }
+}

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

@@ -1,16 +1,13 @@
-use std::{collections::BTreeMap, sync::Arc};
-
 use crate::{
     data::Version,
     interpret::{Interpret, InterpretError, InterpretName, InterpretStatus, Outcome},
     inventory::Inventory,
+    modules::monitoring::okd::config::Config,
     score::Score,
-    topology::{K8sclient, Topology, k8s::K8sClient},
+    topology::{K8sclient, Topology},
 };
 use async_trait::async_trait;
 use harmony_types::id::Id;
-use k8s_openapi::api::core::v1::ConfigMap;
-use kube::api::ObjectMeta;
 use serde::Serialize;
 
 #[derive(Clone, Debug, Serialize)]
@@ -37,10 +34,9 @@ impl<T: Topology + K8sclient> Interpret<T> for OpenshiftUserWorkloadMonitoringIn
         topology: &T,
     ) -> Result<Outcome, InterpretError> {
         let client = topology.k8s_client().await.unwrap();
-        self.update_cluster_monitoring_config_cm(&client).await?;
-        self.update_user_workload_monitoring_config_cm(&client)
-            .await?;
-        self.verify_user_workload(&client).await?;
+        Config::create_cluster_monitoring_config_cm(&client).await?;
+        Config::create_user_workload_monitoring_config_cm(&client).await?;
+        Config::verify_user_workload(&client).await?;
         Ok(Outcome::success(
             "successfully enabled user-workload-monitoring".to_string(),
         ))
@@ -62,88 +58,3 @@ impl<T: Topology + K8sclient> Interpret<T> for OpenshiftUserWorkloadMonitoringIn
         todo!()
     }
 }
-
-impl OpenshiftUserWorkloadMonitoringInterpret {
-    pub async fn update_cluster_monitoring_config_cm(
-        &self,
-        client: &Arc<K8sClient>,
-    ) -> Result<Outcome, InterpretError> {
-        let mut data = BTreeMap::new();
-        data.insert(
-            "config.yaml".to_string(),
-            r#"
-enableUserWorkload: true
-alertmanagerMain:
-  enableUserAlertmanagerConfig: true
-"#
-            .to_string(),
-        );
-
-        let cm = ConfigMap {
-            metadata: ObjectMeta {
-                name: Some("cluster-monitoring-config".to_string()),
-                namespace: Some("openshift-monitoring".to_string()),
-                ..Default::default()
-            },
-            data: Some(data),
-            ..Default::default()
-        };
-        client.apply(&cm, Some("openshift-monitoring")).await?;
-
-        Ok(Outcome::success(
-            "updated cluster-monitoring-config-map".to_string(),
-        ))
-    }
-
-    pub async fn update_user_workload_monitoring_config_cm(
-        &self,
-        client: &Arc<K8sClient>,
-    ) -> Result<Outcome, InterpretError> {
-        let mut data = BTreeMap::new();
-        data.insert(
-            "config.yaml".to_string(),
-            r#"
-alertmanager: 
-  enabled: true
-  enableAlertmanagerConfig: true
-"#
-            .to_string(),
-        );
-        let cm = ConfigMap {
-            metadata: ObjectMeta {
-                name: Some("user-workload-monitoring-config".to_string()),
-                namespace: Some("openshift-user-workload-monitoring".to_string()),
-                ..Default::default()
-            },
-            data: Some(data),
-            ..Default::default()
-        };
-        client
-            .apply(&cm, Some("openshift-user-workload-monitoring"))
-            .await?;
-
-        Ok(Outcome::success(
-            "updated openshift-user-monitoring-config-map".to_string(),
-        ))
-    }
-
-    pub async fn verify_user_workload(
-        &self,
-        client: &Arc<K8sClient>,
-    ) -> Result<Outcome, InterpretError> {
-        let namespace = "openshift-user-workload-monitoring";
-        let alertmanager_name = "alertmanager-user-workload-0";
-        let prometheus_name = "prometheus-user-workload-0";
-        client
-            .wait_for_pod_ready(alertmanager_name, Some(namespace))
-            .await?;
-        client
-            .wait_for_pod_ready(prometheus_name, Some(namespace))
-            .await?;
-
-        Ok(Outcome::success(format!(
-            "pods: {}, {} ready in ns: {}",
-            alertmanager_name, prometheus_name, namespace
-        )))
-    }
-}

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

@@ -1 +1,14 @@
+use crate::topology::oberservability::monitoring::AlertSender;
+
+pub mod cluster_monitoring;
+pub(crate) mod config;
 pub mod enable_user_workload;
+
+#[derive(Debug)]
+pub struct OpenshiftClusterAlertSender;
+
+impl AlertSender for OpenshiftClusterAlertSender {
+    fn name(&self) -> String {
+        "OpenshiftClusterAlertSender".to_string()
+    }
+}

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

@@ -114,7 +114,7 @@ impl Prometheus {
         };
 
         if let Some(ns) = namespace.as_deref() {
-            grafana_helm_chart_score(ns)
+            grafana_helm_chart_score(ns, false)
                 .interpret(inventory, topology)
                 .await
         } else {

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

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

harmony/src/modules/monitoring/scrape_target/server.rs

@@ -0,0 +1,80 @@
+use std::net::IpAddr;
+
+use async_trait::async_trait;
+use kube::api::ObjectMeta;
+use serde::Serialize;
+
+use crate::{
+    interpret::{InterpretError, Outcome},
+    modules::monitoring::kube_prometheus::crd::{
+        crd_alertmanager_config::CRDPrometheus,
+        crd_scrape_config::{Params, RelabelConfig, ScrapeConfig, ScrapeConfigSpec, StaticConfig},
+    },
+    topology::oberservability::monitoring::ScrapeTarget,
+};
+
+#[derive(Debug, Clone, Serialize)]
+pub struct Server {
+    pub name: String,
+    pub ip: IpAddr,
+    pub auth: String,
+    pub module: String,
+    pub domain: String,
+}
+
+#[async_trait]
+impl ScrapeTarget<CRDPrometheus> for Server {
+    async fn install(&self, sender: &CRDPrometheus) -> Result<Outcome, InterpretError> {
+        let scrape_config_spec = ScrapeConfigSpec {
+            static_configs: Some(vec![StaticConfig {
+                targets: vec![self.ip.to_string()],
+                labels: None,
+            }]),
+            scrape_interval: Some("2m".to_string()),
+            kubernetes_sd_configs: None,
+            http_sd_configs: None,
+            file_sd_configs: None,
+            dns_sd_configs: None,
+            params: Some(Params {
+                auth: Some(vec![self.auth.clone()]),
+                module: Some(vec![self.module.clone()]),
+            }),
+            consul_sd_configs: None,
+            relabel_configs: Some(vec![RelabelConfig {
+                action: None,
+                source_labels: Some(vec!["__address__".to_string()]),
+                separator: None,
+                target_label: Some("__param_target".to_string()),
+                regex: None,
+                replacement: Some(format!("snmp.{}:31080", self.domain.clone())),
+                modulus: None,
+            }]),
+            metric_relabel_configs: None,
+            metrics_path: Some("/snmp".to_string()),
+            scrape_timeout: Some("2m".to_string()),
+            job_name: Some(format!("snmp_exporter/cloud/{}", self.name.clone())),
+            scheme: None,
+        };
+
+        let scrape_config = ScrapeConfig {
+            metadata: ObjectMeta {
+                name: Some(self.name.clone()),
+                namespace: Some(sender.namespace.clone()),
+                ..Default::default()
+            },
+            spec: scrape_config_spec,
+        };
+        sender
+            .client
+            .apply(&scrape_config, Some(&sender.namespace.clone()))
+            .await?;
+        Ok(Outcome::success(format!(
+            "installed scrape target {}",
+            self.name.clone()
+        )))
+    }
+
+    fn clone_box(&self) -> Box<dyn ScrapeTarget<CRDPrometheus>> {
+        Box::new(self.clone())
+    }
+}

harmony/src/modules/okd/bootstrap_03_control_plane.rs

@@ -28,7 +28,7 @@ pub struct OKDSetup03ControlPlaneScore {}
 
 impl Score<HAClusterTopology> for OKDSetup03ControlPlaneScore {
     fn create_interpret(&self) -> Box<dyn Interpret<HAClusterTopology>> {
-        Box::new(OKDSetup03ControlPlaneInterpret::new(self.clone()))
+        Box::new(OKDSetup03ControlPlaneInterpret::new())
     }
 
     fn name(&self) -> String {
@@ -38,17 +38,15 @@ impl Score<HAClusterTopology> for OKDSetup03ControlPlaneScore {
 
 #[derive(Debug, Clone)]
 pub struct OKDSetup03ControlPlaneInterpret {
-    score: OKDSetup03ControlPlaneScore,
     version: Version,
     status: InterpretStatus,
 }
 
 impl OKDSetup03ControlPlaneInterpret {
-    pub fn new(score: OKDSetup03ControlPlaneScore) -> Self {
+    pub fn new() -> Self {
         let version = Version::from("1.0.0").unwrap();
         Self {
             version,
-            score,
             status: InterpretStatus::QUEUED,
         }
     }
@@ -159,7 +157,7 @@ impl OKDSetup03ControlPlaneInterpret {
         }
         .to_string();
 
-        debug!("[ControlPlane] iPXE content template:\n{}", content);
+        debug!("[ControlPlane] iPXE content template:\n{content}");
 
         // Create and apply an iPXE boot file for each node.
         for node in nodes {
@@ -189,16 +187,13 @@ impl OKDSetup03ControlPlaneInterpret {
     /// Prompts the user to reboot the target control plane nodes.
     async fn reboot_targets(&self, nodes: &Vec<PhysicalHost>) -> Result<(), InterpretError> {
         let node_ids: Vec<String> = nodes.iter().map(|n| n.id.to_string()).collect();
-        info!(
-            "[ControlPlane] Requesting reboot for control plane nodes: {:?}",
-            node_ids
-        );
+        info!("[ControlPlane] Requesting reboot for control plane nodes: {node_ids:?}",);
 
         let confirmation = inquire::Confirm::new(
                 &format!("Please reboot the {} control plane nodes ({}) to apply their PXE configuration. Press enter when ready.", nodes.len(), node_ids.join(", ")),
         )
         .prompt()
-        .map_err(|e| InterpretError::new(format!("User prompt failed: {}", e)))?;
+        .map_err(|e| InterpretError::new(format!("User prompt failed: {e}")))?;
 
         if !confirmation {
             return Err(InterpretError::new(
@@ -208,19 +203,6 @@ impl OKDSetup03ControlPlaneInterpret {
 
         Ok(())
     }
-
-    /// Placeholder for automating network bonding configuration.
-    async fn persist_network_bond(&self) -> Result<(), InterpretError> {
-        // Generate MC or NNCP from inventory NIC data; apply via ignition or post-join.
-        info!("[ControlPlane] Ensuring persistent bonding via MachineConfig/NNCP");
-        inquire::Confirm::new(
-            "Network configuration for control plane nodes is not automated yet. Configure it manually if needed.",
-        )
-        .prompt()
-        .map_err(|e| InterpretError::new(format!("User prompt failed: {}", e)))?;
-
-        Ok(())
-    }
 }
 
 #[async_trait]
@@ -259,9 +241,6 @@ impl Interpret<HAClusterTopology> for OKDSetup03ControlPlaneInterpret {
         // 4. Reboot the nodes to start the OS installation.
         self.reboot_targets(&nodes).await?;
 
-        // 5. Placeholder for post-boot network configuration (e.g., bonding).
-        self.persist_network_bond().await?;
-
         // TODO: Implement a step to wait for the control plane nodes to join the cluster
         // and for the cluster operators to become available. This would be similar to
         // the `wait-for bootstrap-complete` command.

harmony/src/modules/okd/bootstrap_load_balancer.rs

@@ -77,6 +77,8 @@ impl OKDBootstrapLoadBalancerScore {
             address: topology.bootstrap_host.ip.to_string(),
             port,
         });
+
+        backend.dedup();
         backend
     }
 }

harmony/src/modules/okd/bootstrap_persist_network_bond.rs

@@ -0,0 +1,130 @@
+use crate::{
+    data::Version,
+    hardware::PhysicalHost,
+    infra::inventory::InventoryRepositoryFactory,
+    interpret::{Interpret, InterpretError, InterpretName, InterpretStatus, Outcome},
+    inventory::{HostRole, Inventory},
+    modules::okd::host_network::HostNetworkConfigurationScore,
+    score::Score,
+    topology::HAClusterTopology,
+};
+use async_trait::async_trait;
+use derive_new::new;
+use harmony_types::id::Id;
+use log::info;
+use serde::Serialize;
+
+// -------------------------------------------------------------------------------------------------
+// Persist Network Bond
+// - Persist bonding via NMState
+// - Persist port channels on the Switch
+// -------------------------------------------------------------------------------------------------
+
+#[derive(Debug, Clone, Serialize, new)]
+pub struct OKDSetupPersistNetworkBondScore {}
+
+impl Score<HAClusterTopology> for OKDSetupPersistNetworkBondScore {
+    fn create_interpret(&self) -> Box<dyn Interpret<HAClusterTopology>> {
+        Box::new(OKDSetupPersistNetworkBondInterpet::new())
+    }
+
+    fn name(&self) -> String {
+        "OKDSetupPersistNetworkBondScore".to_string()
+    }
+}
+
+#[derive(Debug, Clone)]
+pub struct OKDSetupPersistNetworkBondInterpet {
+    version: Version,
+    status: InterpretStatus,
+}
+
+impl OKDSetupPersistNetworkBondInterpet {
+    pub fn new() -> Self {
+        let version = Version::from("1.0.0").unwrap();
+        Self {
+            version,
+            status: InterpretStatus::QUEUED,
+        }
+    }
+
+    /// Ensures that three physical hosts are discovered and available for the ControlPlane role.
+    /// It will trigger discovery if not enough hosts are found.
+    async fn get_nodes(
+        &self,
+        _inventory: &Inventory,
+        _topology: &HAClusterTopology,
+    ) -> Result<Vec<PhysicalHost>, InterpretError> {
+        const REQUIRED_HOSTS: usize = 3;
+        let repo = InventoryRepositoryFactory::build().await?;
+        let control_plane_hosts = repo.get_host_for_role(&HostRole::ControlPlane).await?;
+
+        if control_plane_hosts.len() < REQUIRED_HOSTS {
+            Err(InterpretError::new(format!(
+                "OKD Requires at least {} control plane hosts, but only found {}. Cannot proceed.",
+                REQUIRED_HOSTS,
+                control_plane_hosts.len()
+            )))
+        } else {
+            // Take exactly the number of required hosts to ensure consistency.
+            Ok(control_plane_hosts
+                .into_iter()
+                .take(REQUIRED_HOSTS)
+                .collect())
+        }
+    }
+
+    async fn persist_network_bond(
+        &self,
+        inventory: &Inventory,
+        topology: &HAClusterTopology,
+        hosts: &Vec<PhysicalHost>,
+    ) -> Result<(), InterpretError> {
+        info!("Ensuring persistent bonding");
+
+        let score = HostNetworkConfigurationScore {
+            hosts: hosts.clone(),
+        };
+        score.interpret(inventory, topology).await?;
+
+        Ok(())
+    }
+}
+
+#[async_trait]
+impl Interpret<HAClusterTopology> for OKDSetupPersistNetworkBondInterpet {
+    fn get_name(&self) -> InterpretName {
+        InterpretName::Custom("OKDSetupPersistNetworkBondInterpet")
+    }
+
+    fn get_version(&self) -> Version {
+        self.version.clone()
+    }
+
+    fn get_status(&self) -> InterpretStatus {
+        self.status.clone()
+    }
+
+    fn get_children(&self) -> Vec<Id> {
+        vec![]
+    }
+
+    async fn execute(
+        &self,
+        inventory: &Inventory,
+        topology: &HAClusterTopology,
+    ) -> Result<Outcome, InterpretError> {
+        let nodes = self.get_nodes(inventory, topology).await?;
+
+        let res = self.persist_network_bond(inventory, topology, &nodes).await;
+
+        match res {
+            Ok(_) => Ok(Outcome::success(
+                "Network bond successfully persisted".into(),
+            )),
+            Err(_) => Err(InterpretError::new(
+                "Failed to persist network bond".to_string(),
+            )),
+        }
+    }
+}

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

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

harmony/src/modules/okd/crd/nmstate.rs

@@ -0,0 +1,322 @@
+use std::collections::BTreeMap;
+
+use kube::CustomResource;
+use schemars::JsonSchema;
+use serde::{Deserialize, Serialize};
+use serde_json::Value;
+
+#[derive(CustomResource, Deserialize, Serialize, Clone, Debug, JsonSchema)]
+#[kube(
+    group = "nmstate.io",
+    version = "v1",
+    kind = "NMState",
+    plural = "nmstates",
+    namespaced = false
+)]
+#[serde(rename_all = "camelCase")]
+pub struct NMStateSpec {
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub probe_configuration: Option<ProbeConfig>,
+}
+
+impl Default for NMState {
+    fn default() -> Self {
+        Self {
+            metadata: Default::default(),
+            spec: NMStateSpec {
+                probe_configuration: None,
+            },
+        }
+    }
+}
+
+#[derive(Deserialize, Serialize, Clone, Debug, JsonSchema)]
+#[serde(rename_all = "camelCase")]
+pub struct ProbeConfig {
+    pub dns: ProbeDns,
+}
+
+#[derive(Deserialize, Serialize, Clone, Debug, JsonSchema)]
+#[serde(rename_all = "camelCase")]
+pub struct ProbeDns {
+    pub host: String,
+}
+
+#[derive(CustomResource, Deserialize, Serialize, Clone, Debug, JsonSchema)]
+#[kube(
+    group = "nmstate.io",
+    version = "v1",
+    kind = "NodeNetworkConfigurationPolicy",
+    namespaced
+)]
+#[serde(rename_all = "camelCase")]
+pub struct NodeNetworkConfigurationPolicySpec {
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub node_selector: Option<BTreeMap<String, String>>,
+    pub desired_state: DesiredStateSpec,
+}
+
+#[derive(Deserialize, Serialize, Clone, Debug, JsonSchema)]
+#[serde(rename_all = "kebab-case")]
+pub struct DesiredStateSpec {
+    pub interfaces: Vec<InterfaceSpec>,
+}
+
+#[derive(Deserialize, Serialize, Clone, Debug, Default, JsonSchema)]
+#[serde(rename_all = "kebab-case")]
+pub struct InterfaceSpec {
+    pub name: String,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub description: Option<String>,
+    pub r#type: String,
+    pub state: String,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub mac_address: Option<String>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub copy_mac_from: Option<String>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub mtu: Option<u32>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub controller: Option<String>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub ipv4: Option<IpStackSpec>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub ipv6: Option<IpStackSpec>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub ethernet: Option<EthernetSpec>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub link_aggregation: Option<BondSpec>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub vlan: Option<VlanSpec>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub vxlan: Option<VxlanSpec>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub mac_vtap: Option<MacVtapSpec>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub mac_vlan: Option<MacVlanSpec>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub infiniband: Option<InfinibandSpec>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub linux_bridge: Option<LinuxBridgeSpec>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub ovs_bridge: Option<OvsBridgeSpec>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub ethtool: Option<EthtoolSpec>,
+}
+
+#[derive(Deserialize, Serialize, Clone, Debug, Default, JsonSchema)]
+#[serde(rename_all = "kebab-case")]
+pub struct IpStackSpec {
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub enabled: Option<bool>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub dhcp: Option<bool>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub autoconf: Option<bool>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub address: Option<Vec<IpAddressSpec>>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub auto_dns: Option<bool>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub auto_gateway: Option<bool>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub auto_routes: Option<bool>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub dhcp_client_id: Option<String>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub dhcp_duid: Option<String>,
+}
+
+#[derive(Deserialize, Serialize, Clone, Debug, Default, JsonSchema)]
+#[serde(rename_all = "kebab-case")]
+pub struct IpAddressSpec {
+    pub ip: String,
+    pub prefix_length: u8,
+}
+
+#[derive(Deserialize, Serialize, Clone, Debug, Default, JsonSchema)]
+#[serde(rename_all = "kebab-case")]
+pub struct EthernetSpec {
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub speed: Option<u32>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub duplex: Option<String>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub auto_negotiation: Option<bool>,
+}
+
+#[derive(Deserialize, Serialize, Clone, Debug, Default, JsonSchema)]
+#[serde(rename_all = "kebab-case")]
+pub struct BondSpec {
+    pub mode: String,
+    pub ports: Vec<String>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub options: Option<BTreeMap<String, Value>>,
+}
+
+#[derive(Deserialize, Serialize, Clone, Debug, Default, JsonSchema)]
+#[serde(rename_all = "kebab-case")]
+pub struct VlanSpec {
+    pub base_iface: String,
+    pub id: u16,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub protocol: Option<String>,
+}
+
+#[derive(Deserialize, Serialize, Clone, Debug, Default, JsonSchema)]
+#[serde(rename_all = "kebab-case")]
+pub struct VxlanSpec {
+    pub base_iface: String,
+    pub id: u32,
+    pub remote: String,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub local: Option<String>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub learning: Option<bool>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub destination_port: Option<u16>,
+}
+
+#[derive(Deserialize, Serialize, Clone, Debug, Default, JsonSchema)]
+#[serde(rename_all = "kebab-case")]
+pub struct MacVtapSpec {
+    pub base_iface: String,
+    pub mode: String,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub promiscuous: Option<bool>,
+}
+
+#[derive(Deserialize, Serialize, Clone, Debug, Default, JsonSchema)]
+#[serde(rename_all = "kebab-case")]
+pub struct MacVlanSpec {
+    pub base_iface: String,
+    pub mode: String,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub promiscuous: Option<bool>,
+}
+
+#[derive(Deserialize, Serialize, Clone, Debug, Default, JsonSchema)]
+#[serde(rename_all = "kebab-case")]
+pub struct InfinibandSpec {
+    pub base_iface: String,
+    pub pkey: String,
+    pub mode: String,
+}
+
+#[derive(Deserialize, Serialize, Clone, Debug, Default, JsonSchema)]
+#[serde(rename_all = "kebab-case")]
+pub struct LinuxBridgeSpec {
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub options: Option<LinuxBridgeOptions>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub ports: Option<Vec<LinuxBridgePort>>,
+}
+
+#[derive(Deserialize, Serialize, Clone, Debug, Default, JsonSchema)]
+#[serde(rename_all = "kebab-case")]
+pub struct LinuxBridgeOptions {
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub mac_ageing_time: Option<u32>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub multicast_snooping: Option<bool>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub stp: Option<StpOptions>,
+}
+
+#[derive(Deserialize, Serialize, Clone, Debug, Default, JsonSchema)]
+#[serde(rename_all = "kebab-case")]
+pub struct StpOptions {
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub enabled: Option<bool>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub forward_delay: Option<u16>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub hello_time: Option<u16>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub max_age: Option<u16>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub priority: Option<u16>,
+}
+
+#[derive(Deserialize, Serialize, Clone, Debug, Default, JsonSchema)]
+#[serde(rename_all = "kebab-case")]
+pub struct LinuxBridgePort {
+    pub name: String,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub vlan: Option<LinuxBridgePortVlan>,
+}
+
+#[derive(Deserialize, Serialize, Clone, Debug, Default, JsonSchema)]
+#[serde(rename_all = "kebab-case")]
+pub struct LinuxBridgePortVlan {
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub mode: Option<String>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub trunk_tags: Option<Vec<VlanTag>>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub tag: Option<u16>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub enable_native: Option<bool>,
+}
+
+#[derive(Deserialize, Serialize, Clone, Debug, Default, JsonSchema)]
+#[serde(rename_all = "kebab-case")]
+pub struct VlanTag {
+    pub id: u16,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub id_range: Option<VlanIdRange>,
+}
+
+#[derive(Deserialize, Serialize, Clone, Debug, Default, JsonSchema)]
+#[serde(rename_all = "kebab-case")]
+pub struct VlanIdRange {
+    pub min: u16,
+    pub max: u16,
+}
+
+#[derive(Deserialize, Serialize, Clone, Debug, Default, JsonSchema)]
+#[serde(rename_all = "kebab-case")]
+pub struct OvsBridgeSpec {
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub options: Option<OvsBridgeOptions>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub ports: Option<Vec<OvsPortSpec>>,
+}
+
+#[derive(Deserialize, Serialize, Clone, Debug, Default, JsonSchema)]
+#[serde(rename_all = "kebab-case")]
+pub struct OvsBridgeOptions {
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub stp: Option<bool>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub rstp: Option<bool>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub mcast_snooping_enable: Option<bool>,
+}
+
+#[derive(Deserialize, Serialize, Clone, Debug, Default, JsonSchema)]
+#[serde(rename_all = "kebab-case")]
+pub struct OvsPortSpec {
+    pub name: String,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub link_aggregation: Option<BondSpec>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub vlan: Option<LinuxBridgePortVlan>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub r#type: Option<String>,
+}
+
+#[derive(Deserialize, Serialize, Clone, Debug, Default, JsonSchema)]
+#[serde(rename_all = "kebab-case")]
+pub struct EthtoolSpec {
+    // TODO: Properly describe this spec (https://nmstate.io/devel/yaml_api.html#ethtool)
+}
+
+#[derive(Deserialize, Serialize, Clone, Debug, Default, JsonSchema)]
+#[serde(rename_all = "kebab-case")]
+pub struct EthtoolFecSpec {
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub auto: Option<bool>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub mode: Option<String>,
+}

harmony/src/modules/okd/host_network.rs

@@ -0,0 +1,489 @@
+use async_trait::async_trait;
+use harmony_types::id::Id;
+use log::{debug, info};
+use serde::Serialize;
+
+use crate::{
+    data::Version,
+    hardware::PhysicalHost,
+    interpret::{Interpret, InterpretError, InterpretName, InterpretStatus, Outcome},
+    inventory::Inventory,
+    score::Score,
+    topology::{HostNetworkConfig, NetworkInterface, Switch, SwitchPort, Topology},
+};
+
+#[derive(Debug, Clone, Serialize)]
+pub struct HostNetworkConfigurationScore {
+    pub hosts: Vec<PhysicalHost>,
+}
+
+impl<T: Topology + Switch> Score<T> for HostNetworkConfigurationScore {
+    fn name(&self) -> String {
+        "HostNetworkConfigurationScore".into()
+    }
+
+    fn create_interpret(&self) -> Box<dyn Interpret<T>> {
+        Box::new(HostNetworkConfigurationInterpret {
+            score: self.clone(),
+        })
+    }
+}
+
+#[derive(Debug)]
+pub struct HostNetworkConfigurationInterpret {
+    score: HostNetworkConfigurationScore,
+}
+
+impl HostNetworkConfigurationInterpret {
+    async fn configure_network_for_host<T: Topology + Switch>(
+        &self,
+        topology: &T,
+        host: &PhysicalHost,
+        current_host: &usize,
+        total_hosts: &usize,
+    ) -> Result<HostNetworkConfig, InterpretError> {
+        if host.network.is_empty() {
+            info!("[Host {current_host}/{total_hosts}] No interfaces to configure, skipping");
+            return Ok(HostNetworkConfig {
+                host_id: host.id.clone(),
+                switch_ports: vec![],
+            });
+        }
+
+        let switch_ports = self
+            .collect_switch_ports_for_host(topology, host, current_host, total_hosts)
+            .await?;
+
+        let config = HostNetworkConfig {
+            host_id: host.id.clone(),
+            switch_ports,
+        };
+
+        if !config.switch_ports.is_empty() {
+            info!(
+                "[Host {current_host}/{total_hosts}] Found {} ports for {} interfaces",
+                config.switch_ports.len(),
+                host.network.len()
+            );
+
+            info!("[Host {current_host}/{total_hosts}] Configuring host network...");
+            topology
+                .configure_host_network(&config)
+                .await
+                .map_err(|e| InterpretError::new(format!("Failed to configure host: {e}")))?;
+        } else {
+            info!(
+                "[Host {current_host}/{total_hosts}] No ports found for {} interfaces, skipping",
+                host.network.len()
+            );
+        }
+
+        Ok(config)
+    }
+
+    async fn collect_switch_ports_for_host<T: Topology + Switch>(
+        &self,
+        topology: &T,
+        host: &PhysicalHost,
+        current_host: &usize,
+        total_hosts: &usize,
+    ) -> Result<Vec<SwitchPort>, InterpretError> {
+        let mut switch_ports = vec![];
+
+        if host.network.is_empty() {
+            return Ok(switch_ports);
+        }
+
+        info!("[Host {current_host}/{total_hosts}] Collecting ports on switch...");
+        for network_interface in &host.network {
+            let mac_address = network_interface.mac_address;
+
+            match topology.get_port_for_mac_address(&mac_address).await {
+                Ok(Some(port)) => {
+                    info!(
+                        "[Host {current_host}/{total_hosts}] Found port '{port}' for '{mac_address}'"
+                    );
+                    switch_ports.push(SwitchPort {
+                        interface: NetworkInterface {
+                            name: network_interface.name.clone(),
+                            mac_address,
+                            speed_mbps: network_interface.speed_mbps,
+                            mtu: network_interface.mtu,
+                        },
+                        port,
+                    });
+                }
+                Ok(None) => debug!("No port found for '{mac_address}', skipping"),
+                Err(e) => {
+                    return Err(InterpretError::new(format!(
+                        "Failed to get port for host '{}': {}",
+                        host.id, e
+                    )));
+                }
+            }
+        }
+
+        Ok(switch_ports)
+    }
+
+    fn format_host_configuration(&self, configs: Vec<HostNetworkConfig>) -> Vec<String> {
+        let mut report = vec![
+            "Network Configuration Report".to_string(),
+            "------------------------------------------------------------------".to_string(),
+        ];
+
+        for config in configs {
+            let host = self
+                .score
+                .hosts
+                .iter()
+                .find(|h| h.id == config.host_id)
+                .unwrap();
+
+            println!("[Host] {host}");
+
+            if config.switch_ports.is_empty() {
+                report.push(format!(
+                    "⏭️ Host {}: SKIPPED (No matching switch ports found)",
+                    config.host_id
+                ));
+            } else {
+                let mappings: Vec<String> = config
+                    .switch_ports
+                    .iter()
+                    .map(|p| format!("[{} -> {}]", p.interface.name, p.port))
+                    .collect();
+
+                report.push(format!(
+                    "✅ Host {}: Bonded {} port(s) {}",
+                    config.host_id,
+                    config.switch_ports.len(),
+                    mappings.join(", ")
+                ));
+            }
+        }
+        report
+            .push("------------------------------------------------------------------".to_string());
+        report
+    }
+}
+
+#[async_trait]
+impl<T: Topology + Switch> Interpret<T> for HostNetworkConfigurationInterpret {
+    fn get_name(&self) -> InterpretName {
+        InterpretName::Custom("HostNetworkConfigurationInterpret")
+    }
+
+    fn get_version(&self) -> Version {
+        todo!()
+    }
+
+    fn get_status(&self) -> InterpretStatus {
+        todo!()
+    }
+
+    fn get_children(&self) -> Vec<Id> {
+        vec![]
+    }
+
+    async fn execute(
+        &self,
+        _inventory: &Inventory,
+        topology: &T,
+    ) -> Result<Outcome, InterpretError> {
+        if self.score.hosts.is_empty() {
+            return Ok(Outcome::noop("No hosts to configure".into()));
+        }
+
+        let host_count = self.score.hosts.len();
+        info!("Started network configuration for {host_count} host(s)...",);
+
+        info!("Setting up switch with sane defaults...");
+        topology
+            .setup_switch()
+            .await
+            .map_err(|e| InterpretError::new(format!("Switch setup failed: {e}")))?;
+        info!("Switch ready");
+
+        let mut current_host = 1;
+        let mut host_configurations = vec![];
+
+        for host in &self.score.hosts {
+            let host_configuration = self
+                .configure_network_for_host(topology, host, &current_host, &host_count)
+                .await?;
+
+            host_configurations.push(host_configuration);
+            current_host += 1;
+        }
+        if current_host > 1 {
+            let details = self.format_host_configuration(host_configurations);
+
+            Ok(Outcome::success_with_details(
+                format!(
+                    "Configured {}/{} host(s)",
+                    current_host - 1,
+                    self.score.hosts.len()
+                ),
+                details,
+            ))
+        } else {
+            Ok(Outcome::noop("No hosts configured".into()))
+        }
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use assertor::*;
+    use harmony_types::{net::MacAddress, switch::PortLocation};
+    use lazy_static::lazy_static;
+
+    use crate::{
+        hardware::HostCategory,
+        topology::{
+            HostNetworkConfig, PreparationError, PreparationOutcome, SwitchError, SwitchPort,
+        },
+    };
+    use std::{
+        str::FromStr,
+        sync::{Arc, Mutex},
+    };
+
+    use super::*;
+
+    lazy_static! {
+        pub static ref HOST_ID: Id = Id::from_str("host-1").unwrap();
+        pub static ref ANOTHER_HOST_ID: Id = Id::from_str("host-2").unwrap();
+        pub static ref EXISTING_INTERFACE: NetworkInterface = NetworkInterface {
+            mac_address: MacAddress::try_from("AA:BB:CC:DD:EE:F1".to_string()).unwrap(),
+            name: "interface-1".into(),
+            speed_mbps: None,
+            mtu: 1,
+        };
+        pub static ref ANOTHER_EXISTING_INTERFACE: NetworkInterface = NetworkInterface {
+            mac_address: MacAddress::try_from("AA:BB:CC:DD:EE:F2".to_string()).unwrap(),
+            name: "interface-2".into(),
+            speed_mbps: None,
+            mtu: 1,
+        };
+        pub static ref UNKNOWN_INTERFACE: NetworkInterface = NetworkInterface {
+            mac_address: MacAddress::try_from("11:22:33:44:55:61".to_string()).unwrap(),
+            name: "unknown-interface".into(),
+            speed_mbps: None,
+            mtu: 1,
+        };
+        pub static ref PORT: PortLocation = PortLocation(1, 0, 42);
+        pub static ref ANOTHER_PORT: PortLocation = PortLocation(2, 0, 42);
+    }
+
+    #[tokio::test]
+    async fn should_setup_switch() {
+        let host = given_host(&HOST_ID, vec![EXISTING_INTERFACE.clone()]);
+        let score = given_score(vec![host]);
+        let topology = TopologyWithSwitch::new();
+
+        let _ = score.interpret(&Inventory::empty(), &topology).await;
+
+        let switch_setup = topology.switch_setup.lock().unwrap();
+        assert_that!(*switch_setup).is_true();
+    }
+
+    #[tokio::test]
+    async fn host_with_one_mac_address_should_create_bond_with_one_interface() {
+        let host = given_host(&HOST_ID, vec![EXISTING_INTERFACE.clone()]);
+        let score = given_score(vec![host]);
+        let topology = TopologyWithSwitch::new();
+
+        let _ = score.interpret(&Inventory::empty(), &topology).await;
+
+        let configured_host_networks = topology.configured_host_networks.lock().unwrap();
+        assert_that!(*configured_host_networks).contains_exactly(vec![(
+            HOST_ID.clone(),
+            HostNetworkConfig {
+                host_id: HOST_ID.clone(),
+                switch_ports: vec![SwitchPort {
+                    interface: EXISTING_INTERFACE.clone(),
+                    port: PORT.clone(),
+                }],
+            },
+        )]);
+    }
+
+    #[tokio::test]
+    async fn host_with_multiple_mac_addresses_should_create_one_bond_with_all_interfaces() {
+        let score = given_score(vec![given_host(
+            &HOST_ID,
+            vec![
+                EXISTING_INTERFACE.clone(),
+                ANOTHER_EXISTING_INTERFACE.clone(),
+            ],
+        )]);
+        let topology = TopologyWithSwitch::new();
+
+        let _ = score.interpret(&Inventory::empty(), &topology).await;
+
+        let configured_host_networks = topology.configured_host_networks.lock().unwrap();
+        assert_that!(*configured_host_networks).contains_exactly(vec![(
+            HOST_ID.clone(),
+            HostNetworkConfig {
+                host_id: HOST_ID.clone(),
+                switch_ports: vec![
+                    SwitchPort {
+                        interface: EXISTING_INTERFACE.clone(),
+                        port: PORT.clone(),
+                    },
+                    SwitchPort {
+                        interface: ANOTHER_EXISTING_INTERFACE.clone(),
+                        port: ANOTHER_PORT.clone(),
+                    },
+                ],
+            },
+        )]);
+    }
+
+    #[tokio::test]
+    async fn multiple_hosts_should_create_one_bond_per_host() {
+        let score = given_score(vec![
+            given_host(&HOST_ID, vec![EXISTING_INTERFACE.clone()]),
+            given_host(&ANOTHER_HOST_ID, vec![ANOTHER_EXISTING_INTERFACE.clone()]),
+        ]);
+        let topology = TopologyWithSwitch::new();
+
+        let _ = score.interpret(&Inventory::empty(), &topology).await;
+
+        let configured_host_networks = topology.configured_host_networks.lock().unwrap();
+        assert_that!(*configured_host_networks).contains_exactly(vec![
+            (
+                HOST_ID.clone(),
+                HostNetworkConfig {
+                    host_id: HOST_ID.clone(),
+                    switch_ports: vec![SwitchPort {
+                        interface: EXISTING_INTERFACE.clone(),
+                        port: PORT.clone(),
+                    }],
+                },
+            ),
+            (
+                ANOTHER_HOST_ID.clone(),
+                HostNetworkConfig {
+                    host_id: ANOTHER_HOST_ID.clone(),
+                    switch_ports: vec![SwitchPort {
+                        interface: ANOTHER_EXISTING_INTERFACE.clone(),
+                        port: ANOTHER_PORT.clone(),
+                    }],
+                },
+            ),
+        ]);
+    }
+
+    #[tokio::test]
+    async fn port_not_found_for_mac_address_should_not_configure_interface() {
+        let score = given_score(vec![given_host(&HOST_ID, vec![UNKNOWN_INTERFACE.clone()])]);
+        let topology = TopologyWithSwitch::new_port_not_found();
+
+        let _ = score.interpret(&Inventory::empty(), &topology).await;
+
+        let configured_host_networks = topology.configured_host_networks.lock().unwrap();
+        assert_that!(*configured_host_networks).is_empty();
+    }
+
+    fn given_score(hosts: Vec<PhysicalHost>) -> HostNetworkConfigurationScore {
+        HostNetworkConfigurationScore { hosts }
+    }
+
+    fn given_host(id: &Id, network_interfaces: Vec<NetworkInterface>) -> PhysicalHost {
+        let network = network_interfaces.iter().map(given_interface).collect();
+
+        PhysicalHost {
+            id: id.clone(),
+            category: HostCategory::Server,
+            network,
+            storage: vec![],
+            labels: vec![],
+            memory_modules: vec![],
+            cpus: vec![],
+        }
+    }
+
+    fn given_interface(
+        interface: &NetworkInterface,
+    ) -> harmony_inventory_agent::hwinfo::NetworkInterface {
+        harmony_inventory_agent::hwinfo::NetworkInterface {
+            name: interface.name.clone(),
+            mac_address: interface.mac_address,
+            speed_mbps: interface.speed_mbps,
+            is_up: true,
+            mtu: interface.mtu,
+            ipv4_addresses: vec![],
+            ipv6_addresses: vec![],
+            driver: "driver".into(),
+            firmware_version: None,
+        }
+    }
+
+    struct TopologyWithSwitch {
+        available_ports: Arc<Mutex<Vec<PortLocation>>>,
+        configured_host_networks: Arc<Mutex<Vec<(Id, HostNetworkConfig)>>>,
+        switch_setup: Arc<Mutex<bool>>,
+    }
+
+    impl TopologyWithSwitch {
+        fn new() -> Self {
+            Self {
+                available_ports: Arc::new(Mutex::new(vec![PORT.clone(), ANOTHER_PORT.clone()])),
+                configured_host_networks: Arc::new(Mutex::new(vec![])),
+                switch_setup: Arc::new(Mutex::new(false)),
+            }
+        }
+
+        fn new_port_not_found() -> Self {
+            Self {
+                available_ports: Arc::new(Mutex::new(vec![])),
+                configured_host_networks: Arc::new(Mutex::new(vec![])),
+                switch_setup: Arc::new(Mutex::new(false)),
+            }
+        }
+    }
+
+    #[async_trait]
+    impl Topology for TopologyWithSwitch {
+        fn name(&self) -> &str {
+            "SwitchWithPortTopology"
+        }
+
+        async fn ensure_ready(&self) -> Result<PreparationOutcome, PreparationError> {
+            Ok(PreparationOutcome::Success { details: "".into() })
+        }
+    }
+
+    #[async_trait]
+    impl Switch for TopologyWithSwitch {
+        async fn setup_switch(&self) -> Result<(), SwitchError> {
+            let mut switch_configured = self.switch_setup.lock().unwrap();
+            *switch_configured = true;
+            Ok(())
+        }
+
+        async fn get_port_for_mac_address(
+            &self,
+            _mac_address: &MacAddress,
+        ) -> Result<Option<PortLocation>, SwitchError> {
+            let mut ports = self.available_ports.lock().unwrap();
+            if ports.is_empty() {
+                return Ok(None);
+            }
+            Ok(Some(ports.remove(0)))
+        }
+
+        async fn configure_host_network(
+            &self,
+            config: &HostNetworkConfig,
+        ) -> Result<(), SwitchError> {
+            let mut configured_host_networks = self.configured_host_networks.lock().unwrap();
+            configured_host_networks.push((config.host_id.clone(), config.clone()));
+
+            Ok(())
+        }
+    }
+}

harmony/src/modules/okd/installation.rs

@@ -50,7 +50,7 @@
 use crate::{
     modules::okd::{
         OKDSetup01InventoryScore, OKDSetup02BootstrapScore, OKDSetup03ControlPlaneScore,
-        OKDSetup04WorkersScore, OKDSetup05SanityCheckScore,
+        OKDSetup04WorkersScore, OKDSetup05SanityCheckScore, OKDSetupPersistNetworkBondScore,
         bootstrap_06_installation_report::OKDSetup06InstallationReportScore,
     },
     score::Score,
@@ -65,6 +65,7 @@ impl OKDInstallationPipeline {
             Box::new(OKDSetup01InventoryScore::new()),
             Box::new(OKDSetup02BootstrapScore::new()),
             Box::new(OKDSetup03ControlPlaneScore::new()),
+            Box::new(OKDSetupPersistNetworkBondScore::new()),
             Box::new(OKDSetup04WorkersScore::new()),
             Box::new(OKDSetup05SanityCheckScore::new()),
             Box::new(OKDSetup06InstallationReportScore::new()),

harmony/src/modules/okd/mod.rs

@@ -6,6 +6,7 @@ mod bootstrap_05_sanity_check;
 mod bootstrap_06_installation_report;
 pub mod bootstrap_dhcp;
 pub mod bootstrap_load_balancer;
+mod bootstrap_persist_network_bond;
 pub mod dhcp;
 pub mod dns;
 pub mod installation;
@@ -19,3 +20,6 @@ pub use bootstrap_03_control_plane::*;
 pub use bootstrap_04_workers::*;
 pub use bootstrap_05_sanity_check::*;
 pub use bootstrap_06_installation_report::*;
+pub use bootstrap_persist_network_bond::*;
+pub mod crd;
+pub mod host_network;

harmony/src/modules/prometheus/k8s_prometheus_alerting_score.rs

@@ -12,7 +12,8 @@ use crate::modules::monitoring::kube_prometheus::crd::crd_alertmanager_config::C
 use crate::modules::monitoring::kube_prometheus::crd::crd_default_rules::build_default_application_rules;
 use crate::modules::monitoring::kube_prometheus::crd::crd_grafana::{
     Grafana, GrafanaDashboard, GrafanaDashboardSpec, GrafanaDatasource, GrafanaDatasourceConfig,
-    GrafanaDatasourceSpec, GrafanaSpec,
+    GrafanaDatasourceJsonData, GrafanaDatasourceSpec, GrafanaSecretKeyRef, GrafanaSpec,
+    GrafanaValueFrom, GrafanaValueSource,
 };
 use crate::modules::monitoring::kube_prometheus::crd::crd_prometheus_rules::{
     PrometheusRule, PrometheusRuleSpec, RuleGroup,
@@ -39,7 +40,7 @@ use crate::{
 };
 use harmony_types::id::Id;
 
-use super::prometheus::PrometheusApplicationMonitoring;
+use super::prometheus::PrometheusMonitoring;
 
 #[derive(Clone, Debug, Serialize)]
 pub struct K8sPrometheusCRDAlertingScore {
@@ -49,7 +50,7 @@ pub struct K8sPrometheusCRDAlertingScore {
     pub prometheus_rules: Vec<RuleGroup>,
 }
 
-impl<T: Topology + K8sclient + PrometheusApplicationMonitoring<CRDPrometheus>> Score<T>
+impl<T: Topology + K8sclient + PrometheusMonitoring<CRDPrometheus>> Score<T>
     for K8sPrometheusCRDAlertingScore
 {
     fn create_interpret(&self) -> Box<dyn crate::interpret::Interpret<T>> {
@@ -75,7 +76,7 @@ pub struct K8sPrometheusCRDAlertingInterpret {
 }
 
 #[async_trait]
-impl<T: Topology + K8sclient + PrometheusApplicationMonitoring<CRDPrometheus>> Interpret<T>
+impl<T: Topology + K8sclient + PrometheusMonitoring<CRDPrometheus>> Interpret<T>
     for K8sPrometheusCRDAlertingInterpret
 {
     async fn execute(
@@ -466,10 +467,13 @@ impl K8sPrometheusCRDAlertingInterpret {
             match_labels: label.clone(),
             match_expressions: vec![],
         };
-        let mut json_data = BTreeMap::new();
-        json_data.insert("timeInterval".to_string(), "5s".to_string());
         let namespace = self.sender.namespace.clone();
-
+        let json_data = GrafanaDatasourceJsonData {
+            time_interval: Some("5s".to_string()),
+            http_header_name1: None,
+            tls_skip_verify: Some(true),
+            oauth_pass_thru: Some(true),
+        };
         let json = build_default_dashboard(&namespace);
 
         let graf_data_source = GrafanaDatasource {
@@ -495,7 +499,11 @@ impl K8sPrometheusCRDAlertingInterpret {
                         "http://prometheus-operated.{}.svc.cluster.local:9090",
                         self.sender.namespace.clone()
                     ),
+                    secure_json_data: None,
+                    is_default: None,
+                    editable: None,
                 },
+                values_from: None,
             },
         };
 
@@ -516,7 +524,9 @@ impl K8sPrometheusCRDAlertingInterpret {
             spec: GrafanaDashboardSpec {
                 resync_period: Some("30s".to_string()),
                 instance_selector: labels.clone(),
-                json,
+                json: Some(json),
+                grafana_com: None,
+                datasources: None,
             },
         };
 

harmony/src/modules/prometheus/prometheus.rs

@@ -9,11 +9,17 @@ use crate::{
 };
 
 #[async_trait]
-pub trait PrometheusApplicationMonitoring<S: AlertSender> {
+pub trait PrometheusMonitoring<S: AlertSender> {
     async fn install_prometheus(
         &self,
         sender: &S,
         inventory: &Inventory,
         receivers: Option<Vec<Box<dyn AlertReceiver<S>>>>,
     ) -> Result<PreparationOutcome, PreparationError>;
+
+    async fn ensure_prometheus_operator(
+        &self,
+        sender: &S,
+        inventory: &Inventory,
+    ) -> Result<PreparationOutcome, PreparationError>;
 }

harmony/src/modules/prometheus/rhob_alerting_score.rs

@@ -38,7 +38,7 @@ use crate::{
 };
 use harmony_types::id::Id;
 
-use super::prometheus::PrometheusApplicationMonitoring;
+use super::prometheus::PrometheusMonitoring;
 
 #[derive(Clone, Debug, Serialize)]
 pub struct RHOBAlertingScore {
@@ -48,8 +48,8 @@ pub struct RHOBAlertingScore {
     pub prometheus_rules: Vec<RuleGroup>,
 }
 
-impl<T: Topology + K8sclient + Ingress + PrometheusApplicationMonitoring<RHOBObservability>>
-    Score<T> for RHOBAlertingScore
+impl<T: Topology + K8sclient + Ingress + PrometheusMonitoring<RHOBObservability>> Score<T>
+    for RHOBAlertingScore
 {
     fn create_interpret(&self) -> Box<dyn crate::interpret::Interpret<T>> {
         Box::new(RHOBAlertingInterpret {
@@ -74,8 +74,8 @@ pub struct RHOBAlertingInterpret {
 }
 
 #[async_trait]
-impl<T: Topology + K8sclient + Ingress + PrometheusApplicationMonitoring<RHOBObservability>>
-    Interpret<T> for RHOBAlertingInterpret
+impl<T: Topology + K8sclient + Ingress + PrometheusMonitoring<RHOBObservability>> Interpret<T>
+    for RHOBAlertingInterpret
 {
     async fn execute(
         &self,

harmony/src/modules/storage/ceph/ceph_remove_osd_score.rs

@@ -4,7 +4,7 @@ use std::{
 };
 
 use async_trait::async_trait;
-use log::{info, warn};
+use log::{debug, warn};
 use serde::{Deserialize, Serialize};
 use tokio::time::sleep;
 
@@ -19,8 +19,8 @@ use harmony_types::id::Id;
 
 #[derive(Debug, Clone, Serialize)]
 pub struct CephRemoveOsd {
-    osd_deployment_name: String,
-    rook_ceph_namespace: String,
+    pub osd_deployment_name: String,
+    pub rook_ceph_namespace: String,
 }
 
 impl<T: Topology + K8sclient> Score<T> for CephRemoveOsd {
@@ -54,18 +54,17 @@ impl<T: Topology + K8sclient> Interpret<T> for CephRemoveOsdInterpret {
         self.verify_deployment_scaled(client.clone()).await?;
         self.delete_deployment(client.clone()).await?;
         self.verify_deployment_deleted(client.clone()).await?;
-        let osd_id_full = self.get_ceph_osd_id().unwrap();
-        self.purge_ceph_osd(client.clone(), &osd_id_full).await?;
-        self.verify_ceph_osd_removal(client.clone(), &osd_id_full)
-            .await?;
+        self.purge_ceph_osd(client.clone()).await?;
+        self.verify_ceph_osd_removal(client.clone()).await?;
 
+        let osd_id_full = self.get_ceph_osd_id().unwrap();
         Ok(Outcome::success(format!(
             "Successfully removed OSD {} from rook-ceph cluster by deleting deployment {}",
             osd_id_full, self.score.osd_deployment_name
         )))
     }
     fn get_name(&self) -> InterpretName {
-        todo!()
+        InterpretName::CephRemoveOsd
     }
 
     fn get_version(&self) -> Version {
@@ -82,7 +81,7 @@ impl<T: Topology + K8sclient> Interpret<T> for CephRemoveOsdInterpret {
 }
 
 impl CephRemoveOsdInterpret {
-    pub fn get_ceph_osd_id(&self) -> Result<String, InterpretError> {
+    pub fn get_ceph_osd_id_numeric(&self) -> Result<String, InterpretError> {
         let osd_id_numeric = self
             .score
             .osd_deployment_name
@@ -94,9 +93,14 @@ impl CephRemoveOsdInterpret {
                     self.score.osd_deployment_name
                 ))
             })?;
+        Ok(osd_id_numeric.to_string())
+    }
+
+    pub fn get_ceph_osd_id(&self) -> Result<String, InterpretError> {
+        let osd_id_numeric = self.get_ceph_osd_id_numeric().unwrap();
         let osd_id_full = format!("osd.{}", osd_id_numeric);
 
-        info!(
+        debug!(
             "Targeting Ceph OSD: {} (parsed from deployment {})",
             osd_id_full, self.score.osd_deployment_name
         );
@@ -108,6 +112,7 @@ impl CephRemoveOsdInterpret {
         &self,
         client: Arc<K8sClient>,
     ) -> Result<Outcome, InterpretError> {
+        debug!("verifying toolbox exists");
         let toolbox_dep = "rook-ceph-tools".to_string();
 
         match client
@@ -149,7 +154,7 @@ impl CephRemoveOsdInterpret {
         &self,
         client: Arc<K8sClient>,
     ) -> Result<Outcome, InterpretError> {
-        info!(
+        debug!(
             "Scaling down OSD deployment: {}",
             self.score.osd_deployment_name
         );
@@ -172,7 +177,7 @@ impl CephRemoveOsdInterpret {
     ) -> Result<Outcome, InterpretError> {
         let (timeout, interval, start) = self.build_timer();
 
-        info!("Waiting for OSD deployment to scale down to 0 replicas");
+        debug!("Waiting for OSD deployment to scale down to 0 replicas");
         loop {
             let dep = client
                 .get_deployment(
@@ -180,11 +185,9 @@ impl CephRemoveOsdInterpret {
                     Some(&self.score.rook_ceph_namespace),
                 )
                 .await?;
-
             if let Some(deployment) = dep {
                 if let Some(status) = deployment.status {
-                    if status.replicas.unwrap_or(1) == 0 && status.ready_replicas.unwrap_or(1) == 0
-                    {
+                    if status.replicas == None && status.ready_replicas == None {
                         return Ok(Outcome::success(
                             "Deployment successfully scaled down.".to_string(),
                         ));
@@ -212,7 +215,7 @@ impl CephRemoveOsdInterpret {
         &self,
         client: Arc<K8sClient>,
     ) -> Result<Outcome, InterpretError> {
-        info!(
+        debug!(
             "Deleting OSD deployment: {}",
             self.score.osd_deployment_name
         );
@@ -234,7 +237,7 @@ impl CephRemoveOsdInterpret {
     ) -> Result<Outcome, InterpretError> {
         let (timeout, interval, start) = self.build_timer();
 
-        info!("Waiting for OSD deployment to scale down to 0 replicas");
+        debug!("Verifying OSD deployment deleted");
         loop {
             let dep = client
                 .get_deployment(
@@ -244,7 +247,7 @@ impl CephRemoveOsdInterpret {
                 .await?;
 
             if dep.is_none() {
-                info!(
+                debug!(
                     "Deployment {} successfully deleted.",
                     self.score.osd_deployment_name
                 );
@@ -276,12 +279,10 @@ impl CephRemoveOsdInterpret {
         Ok(tree)
     }
 
-    pub async fn purge_ceph_osd(
-        &self,
-        client: Arc<K8sClient>,
-        osd_id_full: &str,
-    ) -> Result<Outcome, InterpretError> {
-        info!(
+    pub async fn purge_ceph_osd(&self, client: Arc<K8sClient>) -> Result<Outcome, InterpretError> {
+        let osd_id_numeric = self.get_ceph_osd_id_numeric().unwrap();
+        let osd_id_full = self.get_ceph_osd_id().unwrap();
+        debug!(
             "Purging OSD {} from Ceph cluster and removing its auth key",
             osd_id_full
         );
@@ -291,8 +292,9 @@ impl CephRemoveOsdInterpret {
                 "app".to_string(),
                 Some(&self.score.rook_ceph_namespace),
                 vec![
-                    format!("ceph osd purge {osd_id_full} --yes-i-really-mean-it").as_str(),
-                    format!("ceph auth del osd.{osd_id_full}").as_str(),
+                    "sh",
+                    "-c",
+                    format!("ceph osd purge {osd_id_numeric} --yes-i-really-mean-it && ceph auth del {osd_id_full}").as_str(),
                 ],
             )
             .await?;
@@ -305,10 +307,10 @@ impl CephRemoveOsdInterpret {
     pub async fn verify_ceph_osd_removal(
         &self,
         client: Arc<K8sClient>,
-        osd_id_full: &str,
     ) -> Result<Outcome, InterpretError> {
         let (timeout, interval, start) = self.build_timer();
-        info!(
+        let osd_id_full = self.get_ceph_osd_id().unwrap();
+        debug!(
             "Verifying OSD {} has been removed from the Ceph tree...",
             osd_id_full
         );
@@ -318,7 +320,7 @@ impl CephRemoveOsdInterpret {
                     "rook-ceph-tools".to_string(),
                     "app".to_string(),
                     Some(&self.score.rook_ceph_namespace),
-                    vec!["ceph osd tree -f json"],
+                    vec!["sh", "-c", "ceph osd tree -f json"],
                 )
                 .await?;
             let tree =

harmony/src/modules/storage/ceph/mod.rs

@@ -1,2 +1,2 @@
-pub mod ceph_osd_replacement_score;
+pub mod ceph_remove_osd_score;
 pub mod ceph_validate_health_score;

harmony_cli/src/cli_reporter.rs

@@ -40,7 +40,7 @@ pub fn init() {
                 HarmonyEvent::HarmonyFinished => {
                     if !details.is_empty() {
                         println!(
-                            "\n{} All done! Here's what's next for you:",
+                            "\n{} All done! Here's a few info for you:",
                             theme::EMOJI_SUMMARY
                         );
                         for detail in details.iter() {

harmony_composer/src/main.rs

@@ -54,6 +54,9 @@ struct DeployArgs {
 
     #[arg(long = "profile", short = 'p', default_value = "dev")]
     harmony_profile: HarmonyProfile,
+
+    #[arg(long = "dry-run", short = 'd', default_value = "false")]
+    dry_run: bool,
 }
 
 #[derive(Args, Clone, Debug)]
@@ -178,6 +181,7 @@ async fn main() {
                 command
                     .env("HARMONY_USE_LOCAL_K3D", format!("{use_local_k3d}"))
                     .env("HARMONY_PROFILE", format!("{}", args.harmony_profile))
+                    .env("HARMONY_DRY_RUN", format!("{}", args.dry_run))
                     .arg("-y")
                     .arg("-a");
 

harmony_types/src/id.rs

@@ -19,7 +19,7 @@ use serde::{Deserialize, Serialize};
 ///
 /// **It is not meant to be very secure or unique**, it is suitable to generate up to 10 000 items per
 /// second with a reasonable collision rate of 0,000014 % as calculated by this calculator : https://kevingal.com/apps/collision.html
-#[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
+#[derive(Debug, Clone, Eq, PartialEq, PartialOrd, Ord, Serialize, Deserialize)]
 pub struct Id {
     value: String,
 }

harmony_types/src/k8s_name.rs

@@ -0,0 +1,96 @@
+use std::str::FromStr;
+
+use serde::Serialize;
+
+#[derive(Debug, Clone, PartialEq, Eq, Hash, Serialize)]
+pub struct K8sName(pub String);
+
+impl K8sName {
+    #[cfg(test)]
+    pub fn dummy() -> Self {
+        K8sName("example".to_string())
+    }
+
+    fn is_valid(name: &str) -> bool {
+        if name.is_empty() || name.len() > 63 {
+            return false;
+        }
+
+        let b = name.as_bytes();
+
+        if !b[0].is_ascii_alphanumeric() || !b[b.len() - 1].is_ascii_alphanumeric() {
+            return false;
+        }
+
+        b.iter()
+            .all(|c| c.is_ascii_lowercase() || c.is_ascii_digit() || *c == b'-')
+    }
+}
+
+impl FromStr for K8sName {
+    type Err = K8sNameError;
+
+    fn from_str(s: &str) -> Result<Self, Self::Err> {
+        if !Self::is_valid(s) {
+            return Err(K8sNameError::InvalidFormat(format!(
+                "Invalid Kubernetes resource name '{s}': \
+                     must match DNS-1123 (lowercase alphanumeric, hyphens, <=63 chars)"
+            )));
+        };
+
+        Ok(K8sName(s.to_string()))
+    }
+}
+
+#[derive(Debug)]
+pub enum K8sNameError {
+    InvalidFormat(String),
+}
+
+impl From<&K8sName> for String {
+    fn from(value: &K8sName) -> Self {
+        value.0.clone()
+    }
+}
+
+impl std::fmt::Display for K8sName {
+    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+        f.write_str(&self.0)
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn test_valid_name() {
+        assert!(K8sName::from_str("k8s-name-test").is_ok());
+        assert!(K8sName::from_str("n").is_ok());
+        assert!(K8sName::from_str("node1").is_ok());
+        assert!(K8sName::from_str("my-app-v2").is_ok());
+        assert!(K8sName::from_str("service123").is_ok());
+        assert!(K8sName::from_str("abcdefghijklmnopqrstuvwxyz-1234567890").is_ok());
+    }
+
+    #[test]
+    fn test_invalid_name() {
+        assert!(K8sName::from_str("").is_err());
+        assert!(K8sName::from_str(".config").is_err());
+        assert!(K8sName::from_str("_hidden").is_err());
+        assert!(K8sName::from_str("UPPER-CASE").is_err());
+        assert!(K8sName::from_str("123-$$$").is_err());
+        assert!(K8sName::from_str("app!name").is_err());
+        assert!(K8sName::from_str("my..app").is_err());
+        assert!(K8sName::from_str("backend-").is_err());
+        assert!(K8sName::from_str("-frontend").is_err());
+        assert!(K8sName::from_str("InvalidName").is_err());
+        assert!(
+            K8sName::from_str("aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa")
+                .is_err()
+        );
+        assert!(K8sName::from_str("k8s name").is_err());
+        assert!(K8sName::from_str("k8s_name").is_err());
+        assert!(K8sName::from_str("k8s@name").is_err());
+    }
+}

harmony_types/src/lib.rs

@@ -1,2 +1,4 @@
 pub mod id;
+pub mod k8s_name;
 pub mod net;
+pub mod switch;