fix git merge conflict

Cargo.lock

@@ -690,6 +690,23 @@ dependencies = [
  "tokio",
 ]
 
+[[package]]
+name = "brocade-switch"
+version = "0.1.0"
+dependencies = [
+ "async-trait",
+ "brocade",
+ "env_logger",
+ "harmony",
+ "harmony_cli",
+ "harmony_macros",
+ "harmony_types",
+ "log",
+ "serde",
+ "tokio",
+ "url",
+]
+
 [[package]]
 name = "brotli"
 version = "8.0.2"
@@ -2479,6 +2496,19 @@ dependencies = [
  "tokio",
 ]
 
+[[package]]
+name = "harmony_inventory_builder"
+version = "0.1.0"
+dependencies = [
+ "cidr",
+ "harmony",
+ "harmony_cli",
+ "harmony_macros",
+ "harmony_types",
+ "tokio",
+ "url",
+]
+
 [[package]]
 name = "harmony_macros"
 version = "0.1.0"
@@ -2544,6 +2574,7 @@ dependencies = [
 name = "harmony_types"
 version = "0.1.0"
 dependencies = [
+ "log",
  "rand 0.9.2",
  "serde",
  "url",

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

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

brocade/examples/main.rs

@@ -1,6 +1,6 @@
 use std::net::{IpAddr, Ipv4Addr};
 
-use brocade::BrocadeOptions;
+use brocade::{BrocadeOptions, ssh};
 use harmony_secret::{Secret, SecretManager};
 use harmony_types::switch::PortLocation;
 use serde::{Deserialize, Serialize};
@@ -16,23 +16,28 @@ 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(127, 0, 0, 1)); // brocade @ sto1
     // let ip = IpAddr::V4(Ipv4Addr::new(192, 168, 4, 11)); // brocade @ st
     let switch_addresses = vec![ip];
 
-    let config = SecretManager::get_or_prompt::<BrocadeSwitchAuth>()
-        .await
-        .unwrap();
+    // let config = SecretManager::get_or_prompt::<BrocadeSwitchAuth>()
+    //     .await
+    //     .unwrap();
 
     let brocade = brocade::init(
         &switch_addresses,
-        22,
-        &config.username,
-        &config.password,
-        Some(BrocadeOptions {
+        // &config.username,
+        // &config.password,
+        "admin",
+        "password",
+        BrocadeOptions {
             dry_run: true,
+            ssh: ssh::SshOptions {
+                port: 2222,
                 ..Default::default()
-        }),
+            },
+            ..Default::default()
+        },
     )
     .await
     .expect("Brocade client failed to connect");
@@ -54,6 +59,7 @@ async fn main() {
     }
 
     println!("--------------");
+    todo!();
     let channel_name = "1";
     brocade.clear_port_channel(channel_name).await.unwrap();
 

brocade/src/fast_iron.rs

@@ -140,7 +140,7 @@ impl BrocadeClient for FastIronClient {
 
     async fn configure_interfaces(
         &self,
-        _interfaces: Vec<(String, PortOperatingMode)>,
+        _interfaces: &Vec<(String, PortOperatingMode)>,
     ) -> Result<(), Error> {
         todo!()
     }

brocade/src/lib.rs

@@ -14,11 +14,12 @@ use async_trait::async_trait;
 use harmony_types::net::MacAddress;
 use harmony_types::switch::{PortDeclaration, PortLocation};
 use regex::Regex;
+use serde::Serialize;
 
 mod fast_iron;
 mod network_operating_system;
 mod shell;
-mod ssh;
+pub mod ssh;
 
 #[derive(Default, Clone, Debug)]
 pub struct BrocadeOptions {
@@ -118,7 +119,7 @@ impl fmt::Display for InterfaceType {
 }
 
 /// Defines the primary configuration mode of a switch interface, representing mutually exclusive roles.
-#[derive(Debug, PartialEq, Eq, Clone)]
+#[derive(Debug, PartialEq, Eq, Clone, Serialize)]
 pub enum PortOperatingMode {
     /// The interface is explicitly configured for Brocade fabric roles (ISL or Trunk enabled).
     Fabric,
@@ -141,12 +142,11 @@ pub enum InterfaceStatus {
 
 pub async fn init(
     ip_addresses: &[IpAddr],
-    port: u16,
     username: &str,
     password: &str,
-    options: Option<BrocadeOptions>,
+    options: BrocadeOptions,
 ) -> Result<Box<dyn BrocadeClient + Send + Sync>, Error> {
-    let shell = BrocadeShell::init(ip_addresses, port, username, password, options).await?;
+    let shell = BrocadeShell::init(ip_addresses, username, password, options).await?;
 
     let version_info = shell
         .with_session(ExecutionMode::Regular, |session| {
@@ -208,7 +208,7 @@ pub trait BrocadeClient: std::fmt::Debug {
     /// 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)>,
+        interfaces: &Vec<(String, PortOperatingMode)>,
     ) -> Result<(), Error>;
 
     /// Scans the existing configuration to find the next available (unused)

brocade/src/network_operating_system.rs

@@ -187,7 +187,7 @@ impl BrocadeClient for NetworkOperatingSystemClient {
 
     async fn configure_interfaces(
         &self,
-        interfaces: Vec<(String, PortOperatingMode)>,
+        interfaces: &Vec<(String, PortOperatingMode)>,
     ) -> Result<(), Error> {
         info!("[Brocade] Configuring {} interface(s)...", interfaces.len());
 
@@ -204,9 +204,12 @@ impl BrocadeClient for NetworkOperatingSystemClient {
                 PortOperatingMode::Trunk => {
                     commands.push("switchport".into());
                     commands.push("switchport mode trunk".into());
-                    commands.push("no spanning-tree shutdown".into());
+                    commands.push("switchport trunk allowed vlan all".into());
+                    commands.push("no switchport trunk tag native-vlan".into());
+                    commands.push("spanning-tree shutdown".into());
                     commands.push("no fabric isl enable".into());
                     commands.push("no fabric trunk enable".into());
+                    commands.push("no shutdown".into());
                 }
                 PortOperatingMode::Access => {
                     commands.push("switchport".into());

brocade/src/shell.rs

@@ -16,7 +16,6 @@ use tokio::time::timeout;
 #[derive(Debug)]
 pub struct BrocadeShell {
     ip: IpAddr,
-    port: u16,
     username: String,
     password: String,
     options: BrocadeOptions,
@@ -27,33 +26,31 @@ pub struct BrocadeShell {
 impl BrocadeShell {
     pub async fn init(
         ip_addresses: &[IpAddr],
-        port: u16,
         username: &str,
         password: &str,
-        options: Option<BrocadeOptions>,
+        options: 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?;
+        let brocade_ssh_client_options =
+            ssh::try_init_client(username, password, ip, options).await?;
 
         Ok(Self {
             ip: *ip,
-            port,
             username: username.to_string(),
             password: password.to_string(),
             before_all_commands: vec![],
             after_all_commands: vec![],
-            options,
+            options: brocade_ssh_client_options,
         })
     }
 
     pub async fn open_session(&self, mode: ExecutionMode) -> Result<BrocadeSession, Error> {
         BrocadeSession::open(
             self.ip,
-            self.port,
+            self.options.ssh.port,
             &self.username,
             &self.password,
             self.options.clone(),

brocade/src/ssh.rs

@@ -2,6 +2,7 @@ use std::borrow::Cow;
 use std::sync::Arc;
 
 use async_trait::async_trait;
+use log::debug;
 use russh::client::Handler;
 use russh::kex::DH_G1_SHA1;
 use russh::kex::ECDH_SHA2_NISTP256;
@@ -10,29 +11,43 @@ use russh_keys::key::SSH_RSA;
 use super::BrocadeOptions;
 use super::Error;
 
-#[derive(Default, Clone, Debug)]
+#[derive(Clone, Debug)]
 pub struct SshOptions {
     pub preferred_algorithms: russh::Preferred,
+    pub port: u16,
+}
+
+impl Default for SshOptions {
+    fn default() -> Self {
+        Self {
+            preferred_algorithms: Default::default(),
+            port: 22,
+        }
+    }
 }
 
 impl SshOptions {
-    fn ecdhsa_sha2_nistp256() -> Self {
+    fn ecdhsa_sha2_nistp256(port: u16) -> Self {
         Self {
             preferred_algorithms: russh::Preferred {
                 kex: Cow::Borrowed(&[ECDH_SHA2_NISTP256]),
                 key: Cow::Borrowed(&[SSH_RSA]),
                 ..Default::default()
             },
+            port,
+            ..Default::default()
         }
     }
 
-    fn legacy() -> Self {
+    fn legacy(port: u16) -> Self {
         Self {
             preferred_algorithms: russh::Preferred {
                 kex: Cow::Borrowed(&[DH_G1_SHA1]),
                 key: Cow::Borrowed(&[SSH_RSA]),
                 ..Default::default()
             },
+            port,
+            ..Default::default()
         }
     }
 }
@@ -57,18 +72,21 @@ pub async fn try_init_client(
     ip: &std::net::IpAddr,
     base_options: BrocadeOptions,
 ) -> Result<BrocadeOptions, Error> {
+    let mut default = SshOptions::default();
+    default.port = base_options.ssh.port;
     let ssh_options = vec![
-        SshOptions::default(),
-        SshOptions::ecdhsa_sha2_nistp256(),
-        SshOptions::legacy(),
+        default,
+        SshOptions::ecdhsa_sha2_nistp256(base_options.ssh.port),
+        SshOptions::legacy(base_options.ssh.port),
     ];
 
     for ssh in ssh_options {
         let opts = BrocadeOptions {
-            ssh,
+            ssh: ssh.clone(),
             ..base_options.clone()
         };
-        let client = create_client(*ip, 22, username, password, &opts).await;
+        debug!("Creating client {ip}:{} {username}", ssh.port);
+        let client = create_client(*ip, ssh.port, username, password, &opts).await;
 
         match client {
             Ok(_) => {

examples/brocade_switch/Cargo.toml

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

examples/brocade_switch/src/main.rs

@@ -0,0 +1,157 @@
+use std::str::FromStr;
+
+use async_trait::async_trait;
+use brocade::{BrocadeOptions, PortOperatingMode};
+use harmony::{
+    data::Version,
+    infra::brocade::BrocadeSwitchClient,
+    interpret::{Interpret, InterpretError, InterpretName, InterpretStatus, Outcome},
+    inventory::Inventory,
+    score::Score,
+    topology::{
+        HostNetworkConfig, PortConfig, PreparationError, PreparationOutcome, Switch, SwitchClient,
+        SwitchError, Topology,
+    },
+};
+use harmony_macros::ip;
+use harmony_types::{id::Id, net::MacAddress, switch::PortLocation};
+use log::{debug, info};
+use serde::Serialize;
+
+#[tokio::main]
+async fn main() {
+    let switch_score = BrocadeSwitchScore {
+        port_channels_to_clear: vec![
+            Id::from_str("17").unwrap(),
+            Id::from_str("19").unwrap(),
+            Id::from_str("18").unwrap(),
+        ],
+        ports_to_configure: vec![
+            (PortLocation(2, 0, 17), PortOperatingMode::Trunk),
+            (PortLocation(2, 0, 19), PortOperatingMode::Trunk),
+            (PortLocation(1, 0, 18), PortOperatingMode::Trunk),
+        ],
+    };
+    harmony_cli::run(
+        Inventory::autoload(),
+        SwitchTopology::new().await,
+        vec![Box::new(switch_score)],
+        None,
+    )
+    .await
+    .unwrap();
+}
+
+#[derive(Clone, Debug, Serialize)]
+struct BrocadeSwitchScore {
+    port_channels_to_clear: Vec<Id>,
+    ports_to_configure: Vec<PortConfig>,
+}
+
+impl<T: Topology + Switch> Score<T> for BrocadeSwitchScore {
+    fn name(&self) -> String {
+        "BrocadeSwitchScore".to_string()
+    }
+
+    #[doc(hidden)]
+    fn create_interpret(&self) -> Box<dyn Interpret<T>> {
+        Box::new(BrocadeSwitchInterpret {
+            score: self.clone(),
+        })
+    }
+}
+
+#[derive(Debug)]
+struct BrocadeSwitchInterpret {
+    score: BrocadeSwitchScore,
+}
+
+#[async_trait]
+impl<T: Topology + Switch> Interpret<T> for BrocadeSwitchInterpret {
+    async fn execute(
+        &self,
+        _inventory: &Inventory,
+        topology: &T,
+    ) -> Result<Outcome, InterpretError> {
+        info!("Applying switch configuration {:?}", self.score);
+        debug!(
+            "Clearing port channel {:?}",
+            self.score.port_channels_to_clear
+        );
+        topology
+            .clear_port_channel(&self.score.port_channels_to_clear)
+            .await
+            .map_err(|e| InterpretError::new(e.to_string()))?;
+        debug!("Configuring interfaces {:?}", self.score.ports_to_configure);
+        topology
+            .configure_interface(&self.score.ports_to_configure)
+            .await
+            .map_err(|e| InterpretError::new(e.to_string()))?;
+        Ok(Outcome::success("switch configured".to_string()))
+    }
+    fn get_name(&self) -> InterpretName {
+        InterpretName::Custom("BrocadeSwitchInterpret")
+    }
+    fn get_version(&self) -> Version {
+        todo!()
+    }
+    fn get_status(&self) -> InterpretStatus {
+        todo!()
+    }
+    fn get_children(&self) -> Vec<Id> {
+        todo!()
+    }
+}
+
+struct SwitchTopology {
+    client: Box<dyn SwitchClient>,
+}
+
+#[async_trait]
+impl Topology for SwitchTopology {
+    fn name(&self) -> &str {
+        "SwitchTopology"
+    }
+
+    async fn ensure_ready(&self) -> Result<PreparationOutcome, PreparationError> {
+        Ok(PreparationOutcome::Noop)
+    }
+}
+
+impl SwitchTopology {
+    async fn new() -> Self {
+        let mut options = BrocadeOptions::default();
+        options.ssh.port = 2222;
+        let client =
+            BrocadeSwitchClient::init(&vec![ip!("127.0.0.1")], &"admin", &"password", options)
+                .await
+                .expect("Failed to connect to switch");
+
+        let client = Box::new(client);
+        Self { client }
+    }
+}
+
+#[async_trait]
+impl Switch for SwitchTopology {
+    async fn setup_switch(&self) -> Result<(), SwitchError> {
+        todo!()
+    }
+
+    async fn get_port_for_mac_address(
+        &self,
+        _mac_address: &MacAddress,
+    ) -> Result<Option<PortLocation>, SwitchError> {
+        todo!()
+    }
+
+    async fn configure_port_channel(&self, _config: &HostNetworkConfig) -> Result<(), SwitchError> {
+        todo!()
+    }
+    async fn clear_port_channel(&self, ids: &Vec<Id>) -> Result<(), SwitchError> {
+        self.client.clear_port_channel(ids).await
+    }
+    async fn configure_interface(&self, ports: &Vec<PortConfig>) -> Result<(), SwitchError> {
+        self.client.configure_interface(ports).await
+    }
+}

examples/cli/src/main.rs

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

examples/harmony_inventory_builder/Cargo.toml

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

examples/harmony_inventory_builder/build_docker.sh

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

examples/harmony_inventory_builder/docker/Dockerfile

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

examples/harmony_inventory_builder/src/main.rs

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

examples/nanodc/src/main.rs

@@ -39,10 +39,10 @@ async fn main() {
         .expect("Failed to get credentials");
 
     let switches: Vec<IpAddr> = vec![ip!("192.168.33.101")];
-    let brocade_options = Some(BrocadeOptions {
+    let brocade_options = BrocadeOptions {
         dry_run: *harmony::config::DRY_RUN,
         ..Default::default()
-    });
+    };
     let switch_client = BrocadeSwitchClient::init(
         &switches,
         &switch_auth.username,

examples/okd_installation/src/main.rs

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

examples/okd_installation/src/topology.rs

@@ -31,10 +31,10 @@ pub async fn get_topology() -> HAClusterTopology {
         .expect("Failed to get credentials");
 
     let switches: Vec<IpAddr> = vec![ip!("192.168.1.101")]; // TODO: Adjust me
-    let brocade_options = Some(BrocadeOptions {
+    let brocade_options = BrocadeOptions {
         dry_run: *harmony::config::DRY_RUN,
         ..Default::default()
-    });
+    };
     let switch_client = BrocadeSwitchClient::init(
         &switches,
         &switch_auth.username,

examples/okd_pxe/src/topology.rs

@@ -26,10 +26,10 @@ pub async fn get_topology() -> HAClusterTopology {
         .expect("Failed to get credentials");
 
     let switches: Vec<IpAddr> = vec![ip!("192.168.1.101")]; // TODO: Adjust me
-    let brocade_options = Some(BrocadeOptions {
+    let brocade_options = BrocadeOptions {
         dry_run: *harmony::config::DRY_RUN,
         ..Default::default()
-    });
+    };
     let switch_client = BrocadeSwitchClient::init(
         &switches,
         &switch_auth.username,

examples/opnsense/src/main.rs

@@ -35,10 +35,10 @@ async fn main() {
         .expect("Failed to get credentials");
 
     let switches: Vec<IpAddr> = vec![ip!("192.168.5.101")]; // TODO: Adjust me
-    let brocade_options = Some(BrocadeOptions {
+    let brocade_options = BrocadeOptions {
         dry_run: *harmony::config::DRY_RUN,
         ..Default::default()
-    });
+    };
     let switch_client = BrocadeSwitchClient::init(
         &switches,
         &switch_auth.username,

harmony/src/domain/hardware/mod.rs

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

harmony/src/domain/interpret/mod.rs

@@ -4,6 +4,8 @@ use std::error::Error;
 use async_trait::async_trait;
 use derive_new::new;
 
+use crate::inventory::HostRole;
+
 use super::{
     data::Version, executors::ExecutorError, inventory::Inventory, topology::PreparationError,
 };

harmony/src/domain/topology/ha_cluster.rs

@@ -1,4 +1,5 @@
 use async_trait::async_trait;
+use brocade::PortOperatingMode;
 use harmony_macros::ip;
 use harmony_types::{
     id::Id,
@@ -8,9 +9,9 @@ use harmony_types::{
 use log::debug;
 use log::info;
 
-use crate::infra::network_manager::OpenShiftNmStateNetworkManager;
-use crate::topology::PxeOptions;
 use crate::{data::FileContent, executors::ExecutorError};
+use crate::{infra::network_manager::OpenShiftNmStateNetworkManager, topology::PortConfig};
+use crate::{modules::inventory::HarmonyDiscoveryStrategy, topology::PxeOptions};
 
 use super::{
     DHCPStaticEntry, DhcpServer, DnsRecord, DnsRecordType, DnsServer, Firewall, HostNetworkConfig,
@@ -298,6 +299,13 @@ impl Switch for HAClusterTopology {
 
         Ok(())
     }
+
+    async fn clear_port_channel(&self, ids: &Vec<Id>) -> Result<(), SwitchError> {
+        todo!()
+    }
+    async fn configure_interface(&self, ports: &Vec<PortConfig>) -> Result<(), SwitchError> {
+        todo!()
+    }
 }
 
 #[async_trait]
@@ -521,4 +529,10 @@ impl SwitchClient for DummyInfra {
     ) -> Result<u8, SwitchError> {
         unimplemented!("{}", UNIMPLEMENTED_DUMMY_INFRA)
     }
+    async fn clear_port_channel(&self, ids: &Vec<Id>) -> Result<(), SwitchError> {
+        todo!()
+    }
+    async fn configure_interface(&self, ports: &Vec<PortConfig>) -> Result<(), SwitchError> {
+        todo!()
+    }
 }

harmony/src/domain/topology/network.rs

@@ -7,6 +7,7 @@ use std::{
 };
 
 use async_trait::async_trait;
+use brocade::PortOperatingMode;
 use derive_new::new;
 use harmony_types::{
     id::Id,
@@ -214,6 +215,8 @@ impl From<String> for NetworkError {
     }
 }
 
+pub type PortConfig = (PortLocation, PortOperatingMode);
+
 #[async_trait]
 pub trait Switch: Send + Sync {
     async fn setup_switch(&self) -> Result<(), SwitchError>;
@@ -224,6 +227,8 @@ pub trait Switch: Send + Sync {
     ) -> Result<Option<PortLocation>, SwitchError>;
 
     async fn configure_port_channel(&self, config: &HostNetworkConfig) -> Result<(), SwitchError>;
+    async fn clear_port_channel(&self, ids: &Vec<Id>) -> Result<(), SwitchError>;
+    async fn configure_interface(&self, ports: &Vec<PortConfig>) -> Result<(), SwitchError>;
 }
 
 #[derive(Clone, Debug, PartialEq)]
@@ -283,6 +288,9 @@ pub trait SwitchClient: Debug + Send + Sync {
         channel_name: &str,
         switch_ports: Vec<PortLocation>,
     ) -> Result<u8, SwitchError>;
+
+    async fn clear_port_channel(&self, ids: &Vec<Id>) -> Result<(), SwitchError>;
+    async fn configure_interface(&self, ports: &Vec<PortConfig>) -> Result<(), SwitchError>;
 }
 
 #[cfg(test)]

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

@@ -1,12 +1,13 @@
 use async_trait::async_trait;
 use brocade::{BrocadeClient, BrocadeOptions, InterSwitchLink, InterfaceStatus, PortOperatingMode};
 use harmony_types::{
+    id::Id,
     net::{IpAddress, MacAddress},
     switch::{PortDeclaration, PortLocation},
 };
 use option_ext::OptionExt;
 
-use crate::topology::{SwitchClient, SwitchError};
+use crate::topology::{PortConfig, SwitchClient, SwitchError};
 
 #[derive(Debug)]
 pub struct BrocadeSwitchClient {
@@ -18,9 +19,9 @@ impl BrocadeSwitchClient {
         ip_addresses: &[IpAddress],
         username: &str,
         password: &str,
-        options: Option<BrocadeOptions>,
+        options: BrocadeOptions,
     ) -> Result<Self, brocade::Error> {
-        let brocade = brocade::init(ip_addresses, 22, username, password, options).await?;
+        let brocade = brocade::init(ip_addresses, username, password, options).await?;
         Ok(Self { brocade })
     }
 }
@@ -59,7 +60,7 @@ impl SwitchClient for BrocadeSwitchClient {
         }
 
         self.brocade
-            .configure_interfaces(interfaces)
+            .configure_interfaces(&interfaces)
             .await
             .map_err(|e| SwitchError::new(e.to_string()))?;
 
@@ -111,6 +112,27 @@ impl SwitchClient for BrocadeSwitchClient {
 
         Ok(channel_id)
     }
+    async fn clear_port_channel(&self, ids: &Vec<Id>) -> Result<(), SwitchError> {
+        for i in ids {
+            self.brocade
+                .clear_port_channel(&i.to_string())
+                .await
+                .map_err(|e| SwitchError::new(e.to_string()))?;
+        }
+        Ok(())
+    }
+    async fn configure_interface(&self, ports: &Vec<PortConfig>) -> Result<(), SwitchError> {
+        // FIXME hardcoded TenGigabitEthernet = bad
+        let ports = ports
+            .iter()
+            .map(|p| (format!("TenGigabitEthernet {}", p.0), p.1.clone()))
+            .collect();
+        self.brocade
+            .configure_interfaces(&ports)
+            .await
+            .map_err(|e| SwitchError::new(e.to_string()))?;
+        Ok(())
+    }
 }
 
 #[cfg(test)]
@@ -145,6 +167,7 @@ mod tests {
 
         client.setup().await.unwrap();
 
+        //TODO not sure about this
         let configured_interfaces = brocade.configured_interfaces.lock().unwrap();
         assert_that!(*configured_interfaces).contains_exactly(vec![
             (first_interface.name.clone(), PortOperatingMode::Access),
@@ -255,10 +278,10 @@ mod tests {
 
         async fn configure_interfaces(
             &self,
-            interfaces: Vec<(String, PortOperatingMode)>,
+            interfaces: &Vec<(String, PortOperatingMode)>,
         ) -> Result<(), Error> {
             let mut configured_interfaces = self.configured_interfaces.lock().unwrap();
-            *configured_interfaces = interfaces;
+            *configured_interfaces = interfaces.clone();
 
             Ok(())
         }

harmony/src/infra/kube.rs

@@ -121,7 +121,7 @@ mod test {
     #[test]
     fn deployment_to_dynamic_roundtrip() {
         // Create a sample Deployment with nested structures
-        let mut deployment = Deployment {
+        let deployment = Deployment {
             metadata: ObjectMeta {
                 name: Some("my-deployment".to_string()),
                 labels: Some({

harmony/src/infra/opnsense/mod.rs

@@ -8,7 +8,6 @@ mod tftp;
 use std::sync::Arc;
 
 pub use management::*;
-use opnsense_config_xml::Host;
 use tokio::sync::RwLock;
 
 use crate::{executors::ExecutorError, topology::LogicalHost};

harmony/src/modules/dhcp.rs

@@ -19,8 +19,11 @@ pub struct DhcpScore {
     pub host_binding: Vec<HostBinding>,
     pub next_server: Option<IpAddress>,
     pub boot_filename: Option<String>,
+    /// Boot filename to be provided to PXE clients identifying as BIOS
     pub filename: Option<String>,
+    /// Boot filename to be provided to PXE clients identifying as uefi but NOT iPXE
     pub filename64: Option<String>,
+    /// Boot filename to be provided to PXE clients identifying as iPXE
     pub filenameipxe: Option<String>,
     pub dhcp_range: (IpAddress, IpAddress),
     pub domain: Option<String>,

harmony/src/modules/inventory/discovery.rs

@@ -5,11 +5,10 @@ use serde::{Deserialize, Serialize};
 
 use crate::{
     data::Version,
-    hardware::PhysicalHost,
     infra::inventory::InventoryRepositoryFactory,
     interpret::{Interpret, InterpretError, InterpretName, InterpretStatus, Outcome},
     inventory::{HostRole, Inventory},
-    modules::inventory::LaunchDiscoverInventoryAgentScore,
+    modules::inventory::{HarmonyDiscoveryStrategy, LaunchDiscoverInventoryAgentScore},
     score::Score,
     topology::Topology,
 };
@@ -17,11 +16,13 @@ use crate::{
 #[derive(Debug, Clone, Serialize, Deserialize)]
 pub struct DiscoverHostForRoleScore {
     pub role: HostRole,
+    pub number_desired_hosts: i16,
+    pub discovery_strategy: HarmonyDiscoveryStrategy,
 }
 
 impl<T: Topology> Score<T> for DiscoverHostForRoleScore {
     fn name(&self) -> String {
-        "DiscoverInventoryAgentScore".to_string()
+        format!("DiscoverHostForRoleScore({:?})", self.role)
     }
 
     fn create_interpret(&self) -> Box<dyn Interpret<T>> {
@@ -48,13 +49,15 @@ impl<T: Topology> Interpret<T> for DiscoverHostForRoleInterpret {
         );
         LaunchDiscoverInventoryAgentScore {
             discovery_timeout: None,
+            discovery_strategy: self.score.discovery_strategy.clone(),
         }
         .interpret(inventory, topology)
         .await?;
 
-        let host: PhysicalHost;
+        let mut chosen_hosts = vec![];
         let host_repo = InventoryRepositoryFactory::build().await?;
 
+        let mut assigned_hosts = 0;
         loop {
             let all_hosts = host_repo.get_all_hosts().await?;
 
@@ -75,16 +78,25 @@ impl<T: Topology> Interpret<T> for DiscoverHostForRoleInterpret {
             match ans {
                 Ok(choice) => {
                     info!(
-                        "Selected {} as the {:?} node.",
-                        choice.summary(),
-                        self.score.role
+                        "Assigned role {:?} for node {}",
+                        self.score.role,
+                        choice.summary()
                     );
                     host_repo
                         .save_role_mapping(&self.score.role, &choice)
                         .await?;
-                    host = choice;
+                    chosen_hosts.push(choice);
+                    assigned_hosts += 1;
+
+                    info!(
+                        "Found {assigned_hosts} hosts for role {:?}",
+                        self.score.role
+                    );
+
+                    if assigned_hosts == self.score.number_desired_hosts {
                         break;
                     }
+                }
                 Err(inquire::InquireError::OperationCanceled) => {
                     info!("Refresh requested. Fetching list of discovered hosts again...");
                     continue;
@@ -100,8 +112,13 @@ impl<T: Topology> Interpret<T> for DiscoverHostForRoleInterpret {
         }
 
         Ok(Outcome::success(format!(
-            "Successfully discovered host {} for role {:?}",
-            host.summary(),
+            "Successfully discovered {} hosts {} for role {:?}",
+            self.score.number_desired_hosts,
+            chosen_hosts
+                .iter()
+                .map(|h| h.summary())
+                .collect::<Vec<String>>()
+                .join(", "),
             self.score.role
         )))
     }

harmony/src/modules/inventory/mod.rs

@@ -1,6 +1,10 @@
 mod discovery;
 pub mod inspect;
+use std::net::Ipv4Addr;
+
+use cidr::{Ipv4Cidr, Ipv4Inet};
 pub use discovery::*;
+use tokio::time::{Duration, timeout};
 
 use async_trait::async_trait;
 use harmony_inventory_agent::local_presence::DiscoveryEvent;
@@ -24,6 +28,7 @@ use harmony_types::id::Id;
 #[derive(Debug, Clone, Serialize, Deserialize)]
 pub struct LaunchDiscoverInventoryAgentScore {
     pub discovery_timeout: Option<u64>,
+    pub discovery_strategy: HarmonyDiscoveryStrategy,
 }
 
 impl<T: Topology> Score<T> for LaunchDiscoverInventoryAgentScore {
@@ -43,6 +48,12 @@ struct DiscoverInventoryAgentInterpret {
     score: LaunchDiscoverInventoryAgentScore,
 }
 
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub enum HarmonyDiscoveryStrategy {
+    MDNS,
+    SUBNET { cidr: cidr::Ipv4Cidr, port: u16 },
+}
+
 #[async_trait]
 impl<T: Topology> Interpret<T> for DiscoverInventoryAgentInterpret {
     async fn execute(
@@ -57,6 +68,37 @@ impl<T: Topology> Interpret<T> for DiscoverInventoryAgentInterpret {
             ),
         };
 
+        match self.score.discovery_strategy {
+            HarmonyDiscoveryStrategy::MDNS => self.launch_mdns_discovery().await,
+            HarmonyDiscoveryStrategy::SUBNET { cidr, port } => {
+                self.launch_cidr_discovery(&cidr, port).await
+            }
+        };
+
+        Ok(Outcome::success(
+            "Discovery process completed successfully".to_string(),
+        ))
+    }
+
+    fn get_name(&self) -> InterpretName {
+        InterpretName::DiscoverInventoryAgent
+    }
+
+    fn get_version(&self) -> Version {
+        todo!()
+    }
+
+    fn get_status(&self) -> InterpretStatus {
+        todo!()
+    }
+
+    fn get_children(&self) -> Vec<Id> {
+        todo!()
+    }
+}
+
+impl DiscoverInventoryAgentInterpret {
+    async fn launch_mdns_discovery(&self) {
         harmony_inventory_agent::local_presence::discover_agents(
             self.score.discovery_timeout,
             |event: DiscoveryEvent| -> Result<(), String> {
@@ -112,6 +154,8 @@ impl<T: Topology> Interpret<T> for DiscoverInventoryAgentInterpret {
                                 cpus,
                             };
 
+                            // FIXME only save the host when it is new or something changed in it.
+                            // we currently are saving the host every time it is discovered.
                             let repo = InventoryRepositoryFactory::build()
                                 .await
                                 .map_err(|e| format!("Could not build repository : {e}"))
@@ -132,25 +176,111 @@ impl<T: Topology> Interpret<T> for DiscoverInventoryAgentInterpret {
                 Ok(())
             },
         )
-        .await;
-        Ok(Outcome::success(
-            "Discovery process completed successfully".to_string(),
-        ))
+        .await
     }
 
-    fn get_name(&self) -> InterpretName {
-        InterpretName::DiscoverInventoryAgent
+    // async fn launch_cidr_discovery(&self, cidr : &Ipv4Cidr, port: u16) {
+    //     todo!("launnch cidr discovery for {cidr} : {port}
+    //         - Iterate over all possible addresses in cidr
+    //         - make calls in batches of 20 attempting to reach harmony inventory agent on <addr, port> using same as above harmony_inventory_agent::client::get_host_inventory(&address, port)
+    //         - Log warn when response is 404, it means the port was used by something else unexpected
+    //         - Log error when response is 5xx
+    //         - Log debug when no response (timeout 15 seconds)
+    //         - Log info when found and response is 2xx
+    //         ");
+    // }
+    async fn launch_cidr_discovery(&self, cidr: &Ipv4Cidr, port: u16) {
+        let addrs: Vec<Ipv4Inet> = cidr.iter().collect();
+        let total = addrs.len();
+        info!(
+            "Starting CIDR discovery for {} hosts on {}/{} (port {})",
+            total,
+            cidr.network_length(),
+            cidr,
+            port
+        );
+
+        let batch_size: usize = 20;
+        let timeout_secs = 5;
+        let request_timeout = Duration::from_secs(timeout_secs);
+
+        let mut current_batch = 0;
+        let num_batches = addrs.len() / batch_size;
+
+        for batch in addrs.chunks(batch_size) {
+            current_batch += 1;
+            info!("Starting query batch {current_batch} of {num_batches}, timeout {timeout_secs}");
+            let mut tasks = Vec::with_capacity(batch.len());
+
+            for addr in batch {
+                let addr = addr.address().to_string();
+                let port = port;
+
+                let task = tokio::spawn(async move {
+                    match timeout(
+                        request_timeout,
+                        harmony_inventory_agent::client::get_host_inventory(&addr, port),
+                    )
+                    .await
+                    {
+                        Ok(Ok(host)) => {
+                            info!("Found and response is 2xx for {addr}:{port}");
+
+                            // Reuse the same conversion to PhysicalHost as MDNS flow
+                            let harmony_inventory_agent::hwinfo::PhysicalHost {
+                                storage_drives,
+                                storage_controller,
+                                memory_modules,
+                                cpus,
+                                chipset,
+                                network_interfaces,
+                                management_interface,
+                                host_uuid,
+                            } = host;
+
+                            let host = PhysicalHost {
+                                id: Id::from(host_uuid),
+                                category: HostCategory::Server,
+                                network: network_interfaces,
+                                storage: storage_drives,
+                                labels: vec![Label {
+                                    name: "discovered-by".to_string(),
+                                    value: "harmony-inventory-agent".to_string(),
+                                }],
+                                memory_modules,
+                                cpus,
+                            };
+
+                            // Save host to inventory
+                            let repo = InventoryRepositoryFactory::build()
+                                .await
+                                .map_err(|e| format!("Could not build repository : {e}"))
+                                .unwrap();
+                            if let Err(e) = repo.save(&host).await {
+                                log::debug!("Failed to save host {}: {e}", host.id);
+                            } else {
+                                info!("Saved host id {}, summary : {}", host.id, host.summary());
+                            }
+                        }
+                        Ok(Err(e)) => {
+                            log::info!("Error querying inventory agent on {addr}:{port} : {e}");
+                        }
+                        Err(_) => {
+                            // Timeout for this host
+                            log::debug!("No response (timeout) for {addr}:{port}");
+                        }
+                    }
+                });
+
+                tasks.push(task);
             }
 
-    fn get_version(&self) -> Version {
-        todo!()
+            // Wait for this batch to complete
+            for t in tasks {
+                let _ = t.await;
+            }
         }
 
-    fn get_status(&self) -> InterpretStatus {
-        todo!()
-    }
-
-    fn get_children(&self) -> Vec<Id> {
-        todo!()
+        info!("CIDR discovery completed");
     }
 }

harmony/src/modules/okd/bootstrap_01_prepare.rs

@@ -4,7 +4,7 @@ use crate::{
     infra::inventory::InventoryRepositoryFactory,
     interpret::{Interpret, InterpretError, InterpretName, InterpretStatus, Outcome},
     inventory::{HostRole, Inventory},
-    modules::inventory::DiscoverHostForRoleScore,
+    modules::inventory::{DiscoverHostForRoleScore, HarmonyDiscoveryStrategy},
     score::Score,
     topology::HAClusterTopology,
 };
@@ -104,6 +104,8 @@ When you can dig them, confirm to continue.
             bootstrap_host = hosts.into_iter().next().to_owned();
             DiscoverHostForRoleScore {
                 role: HostRole::Bootstrap,
+                number_desired_hosts: 1,
+                discovery_strategy: HarmonyDiscoveryStrategy::MDNS,
             }
             .interpret(inventory, topology)
             .await?;

harmony/src/modules/okd/bootstrap_03_control_plane.rs

@@ -1,8 +1,10 @@
 use crate::{
-    interpret::Interpret, inventory::HostRole, modules::okd::bootstrap_okd_node::OKDNodeInterpret,
-    score::Score, topology::HAClusterTopology,
+    interpret::Interpret,
+    inventory::HostRole,
+    modules::{inventory::HarmonyDiscoveryStrategy, okd::bootstrap_okd_node::OKDNodeInterpret},
+    score::Score,
+    topology::HAClusterTopology,
 };
-use derive_new::new;
 use serde::Serialize;
 
 // -------------------------------------------------------------------------------------------------
@@ -11,15 +13,20 @@ use serde::Serialize;
 // - Persist bonding via MachineConfigs (or NNCP) once SCOS is active.
 // -------------------------------------------------------------------------------------------------
 
-#[derive(Debug, Clone, Serialize, new)]
-pub struct OKDSetup03ControlPlaneScore {}
+#[derive(Debug, Clone, Serialize)]
+pub struct OKDSetup03ControlPlaneScore {
+    pub discovery_strategy: HarmonyDiscoveryStrategy,
+}
 
 impl Score<HAClusterTopology> for OKDSetup03ControlPlaneScore {
     fn create_interpret(&self) -> Box<dyn Interpret<HAClusterTopology>> {
         // 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.
-        Box::new(OKDNodeInterpret::new(HostRole::ControlPlane))
+        Box::new(OKDNodeInterpret::new(
+            HostRole::ControlPlane,
+            self.discovery_strategy.clone(),
+        ))
     }
 
     fn name(&self) -> String {

harmony/src/modules/okd/bootstrap_04_workers.rs

@@ -1,9 +1,11 @@
-use derive_new::new;
 use serde::Serialize;
 
 use crate::{
-    interpret::Interpret, inventory::HostRole, modules::okd::bootstrap_okd_node::OKDNodeInterpret,
-    score::Score, topology::HAClusterTopology,
+    interpret::Interpret,
+    inventory::HostRole,
+    modules::{inventory::HarmonyDiscoveryStrategy, okd::bootstrap_okd_node::OKDNodeInterpret},
+    score::Score,
+    topology::HAClusterTopology,
 };
 
 // -------------------------------------------------------------------------------------------------
@@ -12,12 +14,17 @@ use crate::{
 // - Persist bonding via MC/NNCP as required (same approach as masters).
 // -------------------------------------------------------------------------------------------------
 
-#[derive(Debug, Clone, Serialize, new)]
-pub struct OKDSetup04WorkersScore {}
+#[derive(Debug, Clone, Serialize)]
+pub struct OKDSetup04WorkersScore {
+    pub discovery_strategy: HarmonyDiscoveryStrategy,
+}
 
 impl Score<HAClusterTopology> for OKDSetup04WorkersScore {
     fn create_interpret(&self) -> Box<dyn Interpret<HAClusterTopology>> {
-        Box::new(OKDNodeInterpret::new(HostRole::Worker))
+        Box::new(OKDNodeInterpret::new(
+            HostRole::ControlPlane,
+            self.discovery_strategy.clone(),
+        ))
     }
 
     fn name(&self) -> String {

harmony/src/modules/okd/bootstrap_okd_node.rs

@@ -13,11 +13,9 @@ use crate::{
     modules::{
         dhcp::DhcpHostBindingScore,
         http::IPxeMacBootFileScore,
-        inventory::DiscoverHostForRoleScore,
+        inventory::{DiscoverHostForRoleScore, HarmonyDiscoveryStrategy},
         okd::{
-            okd_node::{
-                BootstrapRole, ControlPlaneRole, OKDRoleProperties, StorageRole, WorkerRole,
-            },
+            okd_node::{BootstrapRole, ControlPlaneRole, OKDRoleProperties, WorkerRole},
             templates::BootstrapIpxeTpl,
         },
     },
@@ -28,6 +26,7 @@ use crate::{
 #[derive(Debug, Clone, Serialize, new)]
 pub struct OKDNodeInstallationScore {
     host_role: HostRole,
+    discovery_strategy: HarmonyDiscoveryStrategy,
 }
 
 impl Score<HAClusterTopology> for OKDNodeInstallationScore {
@@ -36,18 +35,25 @@ impl Score<HAClusterTopology> for OKDNodeInstallationScore {
     }
 
     fn create_interpret(&self) -> Box<dyn Interpret<HAClusterTopology>> {
-        Box::new(OKDNodeInterpret::new(self.host_role.clone()))
+        Box::new(OKDNodeInterpret::new(
+            self.host_role.clone(),
+            self.discovery_strategy.clone(),
+        ))
     }
 }
 
 #[derive(Debug, Clone)]
 pub struct OKDNodeInterpret {
     host_role: HostRole,
+    discovery_strategy: HarmonyDiscoveryStrategy,
 }
 
 impl OKDNodeInterpret {
-    pub fn new(host_role: HostRole) -> Self {
-        Self { host_role }
+    pub fn new(host_role: HostRole, discovery_strategy: HarmonyDiscoveryStrategy) -> Self {
+        Self {
+            host_role,
+            discovery_strategy,
+        }
     }
 
     fn okd_role_properties(&self, role: &HostRole) -> &'static dyn OKDRoleProperties {
@@ -69,9 +75,8 @@ impl OKDNodeInterpret {
 
         let okd_host_properties = self.okd_role_properties(&self.host_role);
 
-        let required_hosts: usize = okd_host_properties.required_hosts();
+        let required_hosts: i16 = okd_host_properties.required_hosts();
 
-        while hosts.len() < required_hosts {
         info!(
             "Discovery of {} {} hosts in progress, current number {}",
             required_hosts,
@@ -81,13 +86,15 @@ impl OKDNodeInterpret {
         // This score triggers the discovery agent for a specific role.
         DiscoverHostForRoleScore {
             role: self.host_role.clone(),
+            number_desired_hosts: required_hosts,
+            discovery_strategy: self.discovery_strategy.clone(),
         }
         .interpret(inventory, topology)
         .await?;
-            hosts = repo.get_host_for_role(&self.host_role).await?;
-        }
 
-        if hosts.len() < required_hosts {
+        hosts = repo.get_host_for_role(&self.host_role).await?;
+
+        if hosts.len() < required_hosts.try_into().unwrap_or(0) {
             Err(InterpretError::new(format!(
                 "OKD Requires at least {} {} hosts, but only found {}. Cannot proceed.",
                 required_hosts,
@@ -96,7 +103,10 @@ impl OKDNodeInterpret {
             )))
         } else {
             // Take exactly the number of required hosts to ensure consistency.
-            Ok(hosts.into_iter().take(required_hosts).collect())
+            Ok(hosts
+                .into_iter()
+                .take(required_hosts.try_into().unwrap())
+                .collect())
         }
     }
 

harmony/src/modules/okd/host_network.rs

@@ -251,14 +251,15 @@ impl<T: Topology + NetworkManager + Switch> Interpret<T> for HostNetworkConfigur
 #[cfg(test)]
 mod tests {
     use assertor::*;
+    use brocade::PortOperatingMode;
     use harmony_types::{net::MacAddress, switch::PortLocation};
     use lazy_static::lazy_static;
 
     use crate::{
         hardware::HostCategory,
         topology::{
-            HostNetworkConfig, NetworkError, PreparationError, PreparationOutcome, SwitchError,
-            SwitchPort,
+            HostNetworkConfig, NetworkError, PortConfig, PreparationError, PreparationOutcome,
+            SwitchError, SwitchPort,
         },
     };
     use std::{
@@ -692,5 +693,14 @@ mod tests {
 
             Ok(())
         }
+        async fn clear_port_channel(&self, ids: &Vec<Id>) -> Result<(), SwitchError> {
+            todo!()
+        }
+        async fn configure_interface(
+            &self,
+            port_config: &Vec<PortConfig>,
+        ) -> Result<(), SwitchError> {
+            todo!()
+        }
     }
 }

harmony/src/modules/okd/installation.rs

@@ -48,11 +48,14 @@
 //! - internal_domain: Internal cluster domain (e.g., cluster.local or harmony.mcd).
 
 use crate::{
-    modules::okd::{
+    modules::{
+        inventory::HarmonyDiscoveryStrategy,
+        okd::{
             OKDSetup01InventoryScore, OKDSetup02BootstrapScore, OKDSetup03ControlPlaneScore,
             OKDSetup04WorkersScore, OKDSetup05SanityCheckScore, OKDSetupPersistNetworkBondScore,
             bootstrap_06_installation_report::OKDSetup06InstallationReportScore,
         },
+    },
     score::Score,
     topology::HAClusterTopology,
 };
@@ -60,13 +63,19 @@ use crate::{
 pub struct OKDInstallationPipeline;
 
 impl OKDInstallationPipeline {
-    pub async fn get_all_scores() -> Vec<Box<dyn Score<HAClusterTopology>>> {
+    pub async fn get_all_scores(
+        discovery_strategy: HarmonyDiscoveryStrategy,
+    ) -> Vec<Box<dyn Score<HAClusterTopology>>> {
         vec![
             Box::new(OKDSetup01InventoryScore::new()),
             Box::new(OKDSetup02BootstrapScore::new()),
-            Box::new(OKDSetup03ControlPlaneScore::new()),
+            Box::new(OKDSetup03ControlPlaneScore {
+                discovery_strategy: discovery_strategy.clone(),
+            }),
             Box::new(OKDSetupPersistNetworkBondScore::new()),
-            Box::new(OKDSetup04WorkersScore::new()),
+            Box::new(OKDSetup04WorkersScore {
+                discovery_strategy: discovery_strategy.clone(),
+            }),
             Box::new(OKDSetup05SanityCheckScore::new()),
             Box::new(OKDSetup06InstallationReportScore::new()),
         ]

harmony/src/modules/okd/okd_node.rs

@@ -2,7 +2,7 @@ use crate::topology::{HAClusterTopology, LogicalHost};
 
 pub trait OKDRoleProperties {
     fn ignition_file(&self) -> &'static str;
-    fn required_hosts(&self) -> usize;
+    fn required_hosts(&self) -> i16;
     fn logical_hosts<'a>(&self, t: &'a HAClusterTopology) -> &'a Vec<LogicalHost>;
 }
 
@@ -16,7 +16,7 @@ impl OKDRoleProperties for BootstrapRole {
         "bootstrap.ign"
     }
 
-    fn required_hosts(&self) -> usize {
+    fn required_hosts(&self) -> i16 {
         1
     }
 
@@ -30,7 +30,7 @@ impl OKDRoleProperties for ControlPlaneRole {
         "master.ign"
     }
 
-    fn required_hosts(&self) -> usize {
+    fn required_hosts(&self) -> i16 {
         3
     }
 
@@ -44,7 +44,7 @@ impl OKDRoleProperties for WorkerRole {
         "worker.ign"
     }
 
-    fn required_hosts(&self) -> usize {
+    fn required_hosts(&self) -> i16 {
         2
     }
 

harmony_inventory_agent/build_docker.sh

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

harmony_inventory_agent/docker/.gitignore

@@ -0,0 +1 @@
+harmony_inventory_agent

harmony_inventory_agent/docker/Dockerfile

@@ -0,0 +1,17 @@
+FROM debian:12-slim
+
+# install packages required to make these commands available : lspci, lsmod, dmidecode, smartctl, ip
+RUN apt-get update && \
+    apt-get install -y --no-install-recommends pciutils kmod dmidecode smartmontools iproute2 && \
+    rm -rf /var/lib/apt/lists/*
+
+
+RUN mkdir  /app
+WORKDIR /app/
+
+COPY harmony_inventory_agent /app/
+
+ENV RUST_LOG=info
+
+CMD [ "/app/harmony_inventory_agent" ]
+

harmony_inventory_agent/harmony-inventory-agent-daemonset.yaml

@@ -0,0 +1,117 @@
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: harmony-inventory-agent
+  labels:
+    pod-security.kubernetes.io/enforce: privileged
+    pod-security.kubernetes.io/audit: privileged
+    pod-security.kubernetes.io/warn: privileged
+---
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: harmony-inventory-agent
+  namespace: harmony-inventory-agent
+---
+# Grant the built-in "privileged" SCC to the SA
+apiVersion: rbac.authorization.k8s.io/v1
+kind: Role
+metadata:
+  name: use-privileged-scc
+  namespace: harmony-inventory-agent
+rules:
+- apiGroups: ["security.openshift.io"]
+  resources: ["securitycontextconstraints"]
+  resourceNames: ["privileged"]
+  verbs: ["use"]
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: RoleBinding
+metadata:
+  name: use-privileged-scc
+  namespace: harmony-inventory-agent
+subjects:
+- kind: ServiceAccount
+  name: harmony-inventory-agent
+  namespace: harmony-inventory-agent
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: Role
+  name: use-privileged-scc
+---
+apiVersion: apps/v1
+kind: DaemonSet
+metadata:
+  name: harmony-inventory-agent
+  namespace: harmony-inventory-agent
+spec:
+  selector:
+    matchLabels:
+      app: harmony-inventory-agent
+  template:
+    metadata:
+      labels:
+        app: harmony-inventory-agent
+    spec:
+      serviceAccountName: harmony-inventory-agent
+      hostNetwork: true
+      dnsPolicy: ClusterFirstWithHostNet
+      tolerations:
+      - key: "node-role.kubernetes.io/master"
+        operator: "Exists"
+        effect: "NoSchedule"
+      containers:
+      - name: inventory-agent
+        image: hub.nationtech.io/harmony/harmony_inventory_agent
+        imagePullPolicy: Always
+        env:
+          - name: RUST_LOG
+            value: "harmony_inventory_agent=trace,info"
+        resources:
+          limits:
+            cpu: 200m
+            memory: 256Mi
+          requests:
+            cpu: 100m
+            memory: 128Mi
+        securityContext:
+          privileged: true
+          # optional: leave the rest unset since privileged SCC allows it
+          #
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: harmony-inventory-builder
+  namespace: harmony-inventory-agent
+spec:
+  replicas: 1
+  strategy: {}
+  selector:
+    matchLabels:
+      app: harmony-inventory-builder
+  template:
+    metadata:
+      labels:
+        app: harmony-inventory-builder
+    spec:
+      serviceAccountName: harmony-inventory-agent
+      hostNetwork: true
+      dnsPolicy: ClusterFirstWithHostNet
+      containers:
+      - name: inventory-agent
+        image: hub.nationtech.io/harmony/harmony_inventory_builder
+        imagePullPolicy: Always
+        env:
+          - name: RUST_LOG
+            value: "harmony_inventory_builder=trace,info"
+        resources:
+          limits:
+            cpu: 200m
+            memory: 256Mi
+          requests:
+            cpu: 100m
+            memory: 128Mi
+        securityContext:
+          privileged: true
+          # optional: leave the rest unset since privileged SCC allows it

harmony_inventory_agent/src/hwinfo.rs

@@ -1,5 +1,5 @@
 use harmony_types::net::MacAddress;
-use log::{debug, warn};
+use log::{debug, trace, warn};
 use serde::{Deserialize, Serialize};
 use serde_json::Value;
 use std::fs;
@@ -121,20 +121,48 @@ pub struct ManagementInterface {
 
 impl PhysicalHost {
     pub fn gather() -> Result<Self, String> {
+        trace!("Start gathering physical host information");
         let mut sys = System::new_all();
+        trace!("System new_all called");
         sys.refresh_all();
+        trace!("System refresh_all called");
 
         Self::all_tools_available()?;
 
+        trace!("All tools_available success");
+
+        let storage_drives = Self::gather_storage_drives()?;
+        trace!("got storage drives");
+
+        let storage_controller = Self::gather_storage_controller()?;
+        trace!("got storage controller");
+
+        let memory_modules = Self::gather_memory_modules()?;
+        trace!("got memory_modules");
+
+        let cpus = Self::gather_cpus(&sys)?;
+        trace!("got cpus");
+
+        let chipset = Self::gather_chipset()?;
+        trace!("got chipsets");
+
+        let network_interfaces = Self::gather_network_interfaces()?;
+        trace!("got network_interfaces");
+
+        let management_interface = Self::gather_management_interface()?;
+        trace!("got management_interface");
+
+        let host_uuid = Self::get_host_uuid()?;
+
         Ok(Self {
-            storage_drives: Self::gather_storage_drives()?,
-            storage_controller: Self::gather_storage_controller()?,
-            memory_modules: Self::gather_memory_modules()?,
-            cpus: Self::gather_cpus(&sys)?,
-            chipset: Self::gather_chipset()?,
-            network_interfaces: Self::gather_network_interfaces()?,
-            management_interface: Self::gather_management_interface()?,
-            host_uuid: Self::get_host_uuid()?,
+            storage_drives,
+            storage_controller,
+            memory_modules,
+            cpus,
+            chipset,
+            network_interfaces,
+            management_interface,
+            host_uuid,
         })
     }
 
@@ -208,6 +236,8 @@ impl PhysicalHost {
             ));
         }
 
+        debug!("All tools found!");
+
         Ok(())
     }
 
@@ -231,7 +261,10 @@ impl PhysicalHost {
     fn gather_storage_drives() -> Result<Vec<StorageDrive>, String> {
         let mut drives = Vec::new();
 
+        trace!("Starting storage drive discovery using lsblk");
+
         // Use lsblk with JSON output for robust parsing
+        trace!("Executing 'lsblk -d -o NAME,MODEL,SERIAL,SIZE,ROTA,WWN -n -e 7 --json'");
         let output = Command::new("lsblk")
             .args([
                 "-d",
@@ -245,13 +278,18 @@ impl PhysicalHost {
             .output()
             .map_err(|e| format!("Failed to execute lsblk: {}", e))?;
 
+        trace!(
+            "lsblk command executed successfully (status: {:?})",
+            output.status
+        );
+
         if !output.status.success() {
-            return Err(format!(
-                "lsblk command failed: {}",
-                String::from_utf8_lossy(&output.stderr)
-            ));
+            let stderr_str = String::from_utf8_lossy(&output.stderr);
+            debug!("lsblk command failed: {stderr_str}");
+            return Err(format!("lsblk command failed: {stderr_str}"));
         }
 
+        trace!("Parsing lsblk JSON output");
         let json: Value = serde_json::from_slice(&output.stdout)
             .map_err(|e| format!("Failed to parse lsblk JSON output: {}", e))?;
 
@@ -260,6 +298,8 @@ impl PhysicalHost {
             .and_then(|v| v.as_array())
             .ok_or("Invalid lsblk JSON: missing 'blockdevices' array")?;
 
+        trace!("Found {} blockdevices in lsblk output", blockdevices.len());
+
         for device in blockdevices {
             let name = device
                 .get("name")
@@ -268,52 +308,72 @@ impl PhysicalHost {
                 .to_string();
 
             if name.is_empty() {
+                trace!("Skipping unnamed device entry: {:?}", device);
                 continue;
             }
 
+            trace!("Inspecting block device: {name}");
+
+            // Extract metadata fields
             let model = device
                 .get("model")
                 .and_then(|v| v.as_str())
                 .map(|s| s.trim().to_string())
                 .unwrap_or_default();
+            trace!("Model for {name}: '{}'", model);
 
             let serial = device
                 .get("serial")
                 .and_then(|v| v.as_str())
                 .map(|s| s.trim().to_string())
                 .unwrap_or_default();
+            trace!("Serial for {name}: '{}'", serial);
 
             let size_str = device
                 .get("size")
                 .and_then(|v| v.as_str())
                 .ok_or("Missing 'size' in lsblk device")?;
+            trace!("Reported size for {name}: {}", size_str);
             let size_bytes = Self::parse_size(size_str)?;
+            trace!("Parsed size for {name}: {} bytes", size_bytes);
 
             let rotational = device
                 .get("rota")
                 .and_then(|v| v.as_bool())
                 .ok_or("Missing 'rota' in lsblk device")?;
+            trace!("Rotational flag for {name}: {}", rotational);
 
             let wwn = device
                 .get("wwn")
                 .and_then(|v| v.as_str())
                 .map(|s| s.trim().to_string())
                 .filter(|s| !s.is_empty() && s != "null");
+            trace!("WWN for {name}: {:?}", wwn);
 
             let device_path = Path::new("/sys/block").join(&name);
+            trace!("Sysfs path for {name}: {:?}", device_path);
 
+            trace!("Reading logical block size for {name}");
             let logical_block_size = Self::read_sysfs_u32(
                 &device_path.join("queue/logical_block_size"),
             )
             .map_err(|e| format!("Failed to read logical block size for {}: {}", name, e))?;
+            trace!("Logical block size for {name}: {}", logical_block_size);
 
+            trace!("Reading physical block size for {name}");
             let physical_block_size = Self::read_sysfs_u32(
                 &device_path.join("queue/physical_block_size"),
             )
             .map_err(|e| format!("Failed to read physical block size for {}: {}", name, e))?;
+            trace!("Physical block size for {name}: {}", physical_block_size);
 
+            trace!("Determining interface type for {name}");
             let interface_type = Self::get_interface_type(&name, &device_path)?;
+            trace!("Interface type for {name}: {}", interface_type);
+
+            trace!("Getting SMART status for {name}");
             let smart_status = Self::get_smart_status(&name)?;
+            trace!("SMART status for {name}: {:?}", smart_status);
 
             let mut drive = StorageDrive {
                 name: name.clone(),
@@ -330,19 +390,31 @@ impl PhysicalHost {
 
             // Enhance with additional sysfs info if available
             if device_path.exists() {
+                trace!("Enhancing drive {name} with extra sysfs metadata");
                 if drive.model.is_empty() {
+                    trace!("Reading model from sysfs for {name}");
                     drive.model = Self::read_sysfs_string(&device_path.join("device/model"))
-                        .unwrap_or(format!("Failed to read model for {}", name));
+                        .unwrap_or_else(|_| format!("Failed to read model for {}", name));
                 }
                 if drive.serial.is_empty() {
+                    trace!("Reading serial from sysfs for {name}");
                     drive.serial = Self::read_sysfs_string(&device_path.join("device/serial"))
-                        .unwrap_or(format!("Failed to read serial for {}", name));
+                        .unwrap_or_else(|_| format!("Failed to read serial for {}", name));
                 }
+            } else {
+                trace!(
+                    "Sysfs path {:?} not found for drive {name}, skipping extra metadata",
+                    device_path
+                );
             }
 
+            debug!("Discovered storage drive: {drive:?}");
             drives.push(drive);
         }
 
+        debug!("Discovered total {} storage drives", drives.len());
+        trace!("All discovered dives: {drives:?}");
+
         Ok(drives)
     }
 
@@ -418,6 +490,8 @@ impl PhysicalHost {
             }
         }
 
+        debug!("Found storage controller {controller:?}");
+
         Ok(controller)
     }
 
@@ -486,6 +560,7 @@ impl PhysicalHost {
             }
         }
 
+        debug!("Found memory modules {modules:?}");
         Ok(modules)
     }
 
@@ -501,22 +576,30 @@ impl PhysicalHost {
             frequency_mhz: global_cpu.frequency(),
         });
 
+        debug!("Found cpus {cpus:?}");
+
         Ok(cpus)
     }
 
     fn gather_chipset() -> Result<Chipset, String> {
-        Ok(Chipset {
+        let chipset = Chipset {
             name: Self::read_dmi("baseboard-product-name")?,
             vendor: Self::read_dmi("baseboard-manufacturer")?,
-        })
+        };
+
+        debug!("Found chipset {chipset:?}");
+
+        Ok(chipset)
     }
 
     fn gather_network_interfaces() -> Result<Vec<NetworkInterface>, String> {
         let mut interfaces = Vec::new();
         let sys_net_path = Path::new("/sys/class/net");
+        trace!("Reading /sys/class/net");
 
         let entries = fs::read_dir(sys_net_path)
             .map_err(|e| format!("Failed to read /sys/class/net: {}", e))?;
+        trace!("Got entries {entries:?}");
 
         for entry in entries {
             let entry = entry.map_err(|e| format!("Failed to read directory entry: {}", e))?;
@@ -525,6 +608,7 @@ impl PhysicalHost {
                 .into_string()
                 .map_err(|_| "Invalid UTF-8 in interface name")?;
             let iface_path = entry.path();
+            trace!("Inspecting interface {iface_name} path {iface_path:?}");
 
             // Skip virtual interfaces
             if iface_name.starts_with("lo")
@@ -535,70 +619,101 @@ impl PhysicalHost {
                 || iface_name.starts_with("tun")
                 || iface_name.starts_with("wg")
             {
+                trace!(
+                    "Skipping interface {iface_name} because it appears to be virtual/unsupported"
+                );
                 continue;
             }
 
             // Check if it's a physical interface by looking for device directory
             if !iface_path.join("device").exists() {
+                trace!(
+                    "Skipping interface {iface_name} since {iface_path:?}/device does not exist"
+                );
                 continue;
             }
 
+            trace!("Reading MAC address for {iface_name}");
             let mac_address = Self::read_sysfs_string(&iface_path.join("address"))
                 .map_err(|e| format!("Failed to read MAC address for {}: {}", iface_name, e))?;
             let mac_address = MacAddress::try_from(mac_address).map_err(|e| e.to_string())?;
+            trace!("MAC address for {iface_name}: {mac_address}");
 
-            let speed_mbps = if iface_path.join("speed").exists() {
-                match Self::read_sysfs_u32(&iface_path.join("speed")) {
-                    Ok(speed) => Some(speed),
+            let speed_path = iface_path.join("speed");
+            let speed_mbps = if speed_path.exists() {
+                trace!("Reading speed for {iface_name} from {:?}", speed_path);
+                match Self::read_sysfs_u32(&speed_path) {
+                    Ok(speed) => {
+                        trace!("Speed for {iface_name}: {speed} Mbps");
+                        Some(speed)
+                    }
                     Err(e) => {
                         debug!(
-                            "Failed to read speed for {}: {} . This is expected to fail on wifi interfaces.",
+                            "Failed to read speed for {}: {} (this may be expected on Wi‑Fi interfaces)",
                             iface_name, e
                         );
                         None
                     }
                 }
             } else {
+                trace!("Speed file not found for {iface_name}, skipping");
                 None
             };
 
+            trace!("Reading operstate for {iface_name}");
             let operstate = Self::read_sysfs_string(&iface_path.join("operstate"))
                 .map_err(|e| format!("Failed to read operstate for {}: {}", iface_name, e))?;
+            trace!("Operstate for {iface_name}: {operstate}");
 
+            trace!("Reading MTU for {iface_name}");
             let mtu = Self::read_sysfs_u32(&iface_path.join("mtu"))
                 .map_err(|e| format!("Failed to read MTU for {}: {}", iface_name, e))?;
+            trace!("MTU for {iface_name}: {mtu}");
 
+            trace!("Reading driver for {iface_name}");
             let driver =
                 Self::read_sysfs_symlink_basename(&iface_path.join("device/driver/module"))
                     .map_err(|e| format!("Failed to read driver for {}: {}", iface_name, e))?;
+            trace!("Driver for {iface_name}: {driver}");
 
+            trace!("Reading firmware version for {iface_name}");
             let firmware_version = Self::read_sysfs_opt_string(
                 &iface_path.join("device/firmware_version"),
             )
             .map_err(|e| format!("Failed to read firmware version for {}: {}", iface_name, e))?;
+            trace!("Firmware version for {iface_name}: {firmware_version:?}");
 
-            // Get IP addresses using ip command with JSON output
+            trace!("Fetching IP addresses for {iface_name}");
             let (ipv4_addresses, ipv6_addresses) = Self::get_interface_ips_json(&iface_name)
                 .map_err(|e| format!("Failed to get IP addresses for {}: {}", iface_name, e))?;
+            trace!("Interface {iface_name} has IPv4: {ipv4_addresses:?}, IPv6: {ipv6_addresses:?}");
 
-            interfaces.push(NetworkInterface {
-                name: iface_name,
+            let is_up = operstate == "up";
+            trace!("Constructing NetworkInterface for {iface_name} (is_up={is_up})");
+
+            let iface = NetworkInterface {
+                name: iface_name.clone(),
                 mac_address,
                 speed_mbps,
-                is_up: operstate == "up",
+                is_up,
                 mtu,
                 ipv4_addresses,
                 ipv6_addresses,
                 driver,
                 firmware_version,
-            });
+            };
+
+            debug!("Discovered interface: {iface:?}");
+            interfaces.push(iface);
         }
 
+        debug!("Discovered total {} network interfaces", interfaces.len());
+        trace!("Interfaces collected: {interfaces:?}");
         Ok(interfaces)
     }
 
     fn gather_management_interface() -> Result<Option<ManagementInterface>, String> {
-        if Path::new("/dev/ipmi0").exists() {
+        let mgmt = if Path::new("/dev/ipmi0").exists() {
             Ok(Some(ManagementInterface {
                 kind: "IPMI".to_string(),
                 address: None,
@@ -612,11 +727,16 @@ impl PhysicalHost {
             }))
         } else {
             Ok(None)
-        }
+        };
+
+        debug!("Found management interface {mgmt:?}");
+        mgmt
     }
 
     fn get_host_uuid() -> Result<String, String> {
-        Self::read_dmi("system-uuid")
+        let uuid = Self::read_dmi("system-uuid");
+        debug!("Found uuid {uuid:?}");
+        uuid
     }
 
     // Helper methods
@@ -709,7 +829,8 @@ impl PhysicalHost {
             Ok("Ramdisk".to_string())
         } else {
             // Try to determine from device path
-            let subsystem = Self::read_sysfs_string(&device_path.join("device/subsystem"))?;
+            let subsystem = Self::read_sysfs_string(&device_path.join("device/subsystem"))
+                .unwrap_or(String::new());
             Ok(subsystem
                 .split('/')
                 .next_back()
@@ -779,6 +900,8 @@ impl PhysicalHost {
         size.map(|s| s as u64)
     }
 
+    // FIXME when scanning an interface that is part of a bond/bridge we won't get an address on the
+    // interface, we should be looking at the bond/bridge device. For example, br-ex on k8s nodes.
     fn get_interface_ips_json(iface_name: &str) -> Result<(Vec<String>, Vec<String>), String> {
         let mut ipv4 = Vec::new();
         let mut ipv6 = Vec::new();

harmony_inventory_agent/src/local_presence/advertise.rs

@@ -1,4 +1,4 @@
-use log::{debug, error, info, warn};
+use log::{debug, error, info, trace, warn};
 use mdns_sd::{ServiceDaemon, ServiceInfo};
 use std::collections::HashMap;
 
@@ -12,6 +12,7 @@ use crate::{
 /// This function is synchronous and non-blocking. It spawns a background Tokio task
 /// to handle the mDNS advertisement for the lifetime of the application.
 pub fn advertise(service_port: u16) -> Result<(), PresenceError> {
+    trace!("starting advertisement process for port {service_port}");
     let host_id = match PhysicalHost::gather() {
         Ok(host) => Some(host.host_uuid),
         Err(e) => {
@@ -20,11 +21,15 @@ pub fn advertise(service_port: u16) -> Result<(), PresenceError> {
         }
     };
 
+    trace!("Found host id {host_id:?}");
+
     let instance_name = format!(
         "inventory-agent-{}",
         host_id.clone().unwrap_or("unknown".to_string())
     );
 
+    trace!("Found host id {host_id:?}, name : {instance_name}");
+
     let spawned_msg = format!("Spawned local presence advertisement task for '{instance_name}'.");
 
     tokio::spawn(async move {

harmony_inventory_agent/src/main.rs

@@ -28,7 +28,7 @@ async fn inventory() -> impl Responder {
 async fn main() -> std::io::Result<()> {
     env_logger::init();
 
-    let port = env::var("HARMONY_INVENTORY_AGENT_PORT").unwrap_or_else(|_| "8080".to_string());
+    let port = env::var("HARMONY_INVENTORY_AGENT_PORT").unwrap_or_else(|_| "25000".to_string());
     let port = port
         .parse::<u16>()
         .expect(&format!("Invalid port number, cannot parse to u16 {port}"));

harmony_macros/src/lib.rs

@@ -135,15 +135,17 @@ pub fn ingress_path(input: TokenStream) -> TokenStream {
 
 #[proc_macro]
 pub fn cidrv4(input: TokenStream) -> TokenStream {
-    let input = parse_macro_input!(input as LitStr);
-    let cidr_str = input.value();
+    let lit = parse_macro_input!(input as LitStr);
 
-    if cidr_str.parse::<cidr::Ipv4Cidr>().is_ok() {
-        let expanded = quote! { #cidr_str.parse::<cidr::Ipv4Cidr>().unwrap() };
-        return TokenStream::from(expanded);
-    }
+    // This is the IMPORTANT part:
+    // we re-emit the *string literal itself*
+    let expanded = quote! {
+        #lit
+            .parse::<cidr::Ipv4Cidr>()
+            .expect("Invalid IPv4 CIDR literal")
+    };
 
-    panic!("Invalid IPv4 CIDR : {}", cidr_str);
+    TokenStream::from(expanded)
 }
 
 /// Creates a `harmony_types::net::Url::Url` from a string literal.

harmony_types/Cargo.toml

@@ -9,3 +9,4 @@ license.workspace = true
 serde.workspace = true
 url.workspace = true
 rand.workspace = true
+log.workspace = true

harmony_types/src/switch.rs

@@ -1,3 +1,5 @@
+use log::trace;
+use serde::Serialize;
 use std::{fmt, str::FromStr};
 
 /// Simple error type for port parsing failures.
@@ -21,7 +23,7 @@ impl fmt::Display for PortParseError {
 /// Represents the atomic, physical location of a switch port: `<Stack>/<Module>/<Port>`.
 ///
 /// Example: `1/1/1`
-#[derive(Debug, PartialEq, Eq, PartialOrd, Ord, Clone)]
+#[derive(Debug, PartialEq, Eq, PartialOrd, Ord, Clone, Serialize)]
 pub struct PortLocation(pub u8, pub u8, pub u8);
 
 impl fmt::Display for PortLocation {
@@ -70,6 +72,12 @@ impl FromStr for PortLocation {
 pub enum PortDeclaration {
     /// A single switch port defined by its location. Example: `PortDeclaration::Single(1/1/1)`
     Single(PortLocation),
+    /// A Named port, often used for virtual ports such as PortChannels. Example
+    /// ```rust
+    /// # use harmony_types::switch::PortDeclaration;
+    /// PortDeclaration::Named("1".to_string());
+    /// ```
+    Named(String),
     /// A strictly sequential range defined by two endpoints using the hyphen separator (`-`).
     /// All ports between the endpoints (inclusive) are implicitly included.
     /// Example: `PortDeclaration::Range(1/1/1, 1/1/4)`
@@ -130,8 +138,25 @@ impl PortDeclaration {
             return Ok(PortDeclaration::Set(start_port, end_port));
         }
 
-        let location = PortLocation::from_str(port_str)?;
-        Ok(PortDeclaration::Single(location))
+        match PortLocation::from_str(port_str) {
+            Ok(loc) => Ok(PortDeclaration::Single(loc)),
+            Err(e) => {
+                let segments: Vec<&str> = port_str.split('/').collect();
+                let segment_count = segments.len();
+
+                // Logic:
+                // If it has 3 segments but failed (e.g., "1/A/1"), it's an InvalidSegment.
+                // If it has MORE than 3 segments (e.g., "1/1/1/1" or "1/1/1/"), it's an InvalidFormat.
+                if segment_count >= 3 {
+                    return Err(e);
+                }
+
+                // Otherwise, it's something else entirely (e.g., "eth0", "vlan10"),
+                // so we treat it as a Named port.
+                trace!("Falling back on named port for: {port_str}");
+                Ok(PortDeclaration::Named(port_str.to_string()))
+            }
+        }
     }
 }
 
@@ -141,6 +166,7 @@ impl fmt::Display for PortDeclaration {
             PortDeclaration::Single(port) => write!(f, "{port}"),
             PortDeclaration::Range(start, end) => write!(f, "{start}-{end}"),
             PortDeclaration::Set(start, end) => write!(f, "{start}*{end}"),
+            PortDeclaration::Named(name) => write!(f, "{name}"),
         }
     }
 }

opnsense-config-xml/src/data/opnsense.rs

@@ -196,7 +196,7 @@ pub struct System {
     pub disablechecksumoffloading: u8,
     pub disablesegmentationoffloading: u8,
     pub disablelargereceiveoffloading: u8,
-    pub ipv6allow: u8,
+    pub ipv6allow: Option<u8>,
     pub powerd_ac_mode: String,
     pub powerd_battery_mode: String,
     pub powerd_normal_mode: String,
@@ -227,6 +227,7 @@ pub struct System {
     pub dns6gw: Option<String>,
     pub dns7gw: Option<String>,
     pub dns8gw: Option<String>,
+    pub prefer_ipv4: Option<String>,
     pub dnsallowoverride: u8,
     pub dnsallowoverride_exclude: Option<MaybeString>,
 }
@@ -330,6 +331,7 @@ pub struct Range {
 pub struct StaticMap {
     pub mac: String,
     pub ipaddr: String,
+    pub cid: Option<MaybeString>,
     pub hostname: String,
     pub descr: Option<MaybeString>,
     pub winsserver: MaybeString,
@@ -765,9 +767,19 @@ pub struct Jobs {
 pub struct Job {
     #[yaserde(attribute = true)]
     pub uuid: MaybeString,
-    #[yaserde(rename = "name")]
-    pub name: MaybeString,
+    pub name: Option<MaybeString>,
     // Add other fields as needed
+    pub origin: Option<MaybeString>,
+    pub enabled: Option<MaybeString>,
+    pub minutes: Option<MaybeString>,
+    pub hours: Option<MaybeString>,
+    pub days: Option<MaybeString>,
+    pub months: Option<MaybeString>,
+    pub weekdays: Option<MaybeString>,
+    pub who: Option<MaybeString>,
+    pub command: Option<MaybeString>,
+    pub parameters: Option<MaybeString>,
+    pub description: Option<MaybeString>,
 }
 
 #[derive(Default, PartialEq, Debug, YaSerialize, YaDeserialize)]
@@ -896,28 +908,28 @@ pub struct Proxy {
 #[derive(Default, PartialEq, Debug, YaSerialize, YaDeserialize)]
 pub struct ProxyGeneral {
     pub enabled: i8,
-    pub error_pages: String,
+    pub error_pages: Option<MaybeString>,
     #[yaserde(rename = "icpPort")]
     pub icp_port: MaybeString,
     pub logging: Logging,
     #[yaserde(rename = "alternateDNSservers")]
     pub alternate_dns_servers: MaybeString,
     #[yaserde(rename = "dnsV4First")]
-    pub dns_v4_first: i8,
+    pub dns_v4_first: Option<MaybeString>,
     #[yaserde(rename = "forwardedForHandling")]
-    pub forwarded_for_handling: String,
+    pub forwarded_for_handling: Option<MaybeString>,
     #[yaserde(rename = "uriWhitespaceHandling")]
-    pub uri_whitespace_handling: String,
+    pub uri_whitespace_handling: Option<MaybeString>,
     #[yaserde(rename = "enablePinger")]
     pub enable_pinger: i8,
     #[yaserde(rename = "useViaHeader")]
-    pub use_via_header: i8,
+    pub use_via_header: Option<MaybeString>,
     #[yaserde(rename = "suppressVersion")]
-    pub suppress_version: i32,
+    pub suppress_version: Option<MaybeString>,
     #[yaserde(rename = "connecttimeout")]
-    pub connect_timeout: MaybeString,
+    pub connect_timeout: Option<MaybeString>,
     #[yaserde(rename = "VisibleEmail")]
-    pub visible_email: String,
+    pub visible_email: Option<MaybeString>,
     #[yaserde(rename = "VisibleHostname")]
     pub visible_hostname: MaybeString,
     pub cache: Cache,
@@ -954,7 +966,7 @@ pub struct LocalCache {
     pub cache_mem: i32,
     pub maximum_object_size: MaybeString,
     pub maximum_object_size_in_memory: MaybeString,
-    pub memory_cache_mode: String,
+    pub memory_cache_mode: MaybeString,
     pub size: i32,
     pub l1: i32,
     pub l2: i32,
@@ -966,13 +978,13 @@ pub struct LocalCache {
 pub struct Traffic {
     pub enabled: i32,
     #[yaserde(rename = "maxDownloadSize")]
-    pub max_download_size: i32,
+    pub max_download_size: MaybeString,
     #[yaserde(rename = "maxUploadSize")]
-    pub max_upload_size: i32,
+    pub max_upload_size: MaybeString,
     #[yaserde(rename = "OverallBandwidthTrotteling")]
-    pub overall_bandwidth_trotteling: i32,
+    pub overall_bandwidth_trotteling: MaybeString,
     #[yaserde(rename = "perHostTrotteling")]
-    pub per_host_trotteling: i32,
+    pub per_host_trotteling: MaybeString,
 }
 
 #[derive(Default, PartialEq, Debug, YaSerialize, YaDeserialize)]
@@ -989,7 +1001,7 @@ pub struct ParentProxy {
 
 #[derive(Default, PartialEq, Debug, YaSerialize, YaDeserialize)]
 pub struct Forward {
-    pub interfaces: String,
+    pub interfaces: MaybeString,
     pub port: i32,
     pub sslbumpport: i32,
     pub sslbump: i32,
@@ -1034,9 +1046,9 @@ pub struct Acl {
     pub google_apps: MaybeString,
     pub youtube: MaybeString,
     #[yaserde(rename = "safePorts")]
-    pub safe_ports: String,
+    pub safe_ports: MaybeString,
     #[yaserde(rename = "sslPorts")]
-    pub ssl_ports: String,
+    pub ssl_ports: MaybeString,
     #[yaserde(rename = "remoteACLs")]
     pub remote_acls: RemoteAcls,
 }
@@ -1052,9 +1064,9 @@ pub struct RemoteAcls {
 pub struct Icap {
     pub enable: i32,
     #[yaserde(rename = "RequestURL")]
-    pub request_url: String,
+    pub request_url: MaybeString,
     #[yaserde(rename = "ResponseURL")]
-    pub response_url: String,
+    pub response_url: MaybeString,
     #[yaserde(rename = "SendClientIP")]
     pub send_client_ip: i32,
     #[yaserde(rename = "SendUsername")]
@@ -1062,7 +1074,7 @@ pub struct Icap {
     #[yaserde(rename = "EncodeUsername")]
     pub encode_username: i32,
     #[yaserde(rename = "UsernameHeader")]
-    pub username_header: String,
+    pub username_header: MaybeString,
     #[yaserde(rename = "EnablePreview")]
     pub enable_preview: i32,
     #[yaserde(rename = "PreviewSize")]
@@ -1077,9 +1089,9 @@ pub struct Authentication {
     pub method: MaybeString,
     #[yaserde(rename = "authEnforceGroup")]
     pub auth_enforce_group: MaybeString,
-    pub realm: String,
-    pub credentialsttl: i32, // This field is already in snake_case
-    pub children: i32,
+    pub realm: MaybeString,
+    pub credentialsttl: MaybeString, // This field is already in snake_case
+    pub children: MaybeString,
 }
 
 #[derive(Default, PartialEq, Debug, YaSerialize, YaDeserialize)]
@@ -1295,9 +1307,9 @@ pub struct WireguardServerItem {
     pub gateway: MaybeString,
     pub carp_depend_on: MaybeString,
     pub peers: String,
-    pub debug: MaybeString,
     pub endpoint: MaybeString,
     pub peer_dns: MaybeString,
+    pub debug: Option<MaybeString>,
 }
 
 #[derive(Default, PartialEq, Debug, YaSerialize, YaDeserialize)]
@@ -1482,6 +1494,7 @@ pub struct Ppp {
     pub ports: Option<MaybeString>,
     pub username: Option<MaybeString>,
     pub password: Option<MaybeString>,
+    pub provider: Option<MaybeString>,
 }
 
 #[derive(Default, PartialEq, Debug, YaSerialize, YaDeserialize)]

opnsense-config/src/modules/dhcp_legacy.rs

@@ -86,10 +86,7 @@ impl<'a> DhcpConfigLegacyISC<'a> {
             mac,
             ipaddr: ipaddr.to_string(),
             hostname,
-            descr: Default::default(),
-            winsserver: Default::default(),
-            dnsserver: Default::default(),
-            ntpserver: Default::default(),
+            ..Default::default()
         };
 
         existing_mappings.push(static_map);
@@ -126,9 +123,7 @@ impl<'a> DhcpConfigLegacyISC<'a> {
                 ipaddr: entry["ipaddr"].as_str().unwrap_or_default().to_string(),
                 hostname: entry["hostname"].as_str().unwrap_or_default().to_string(),
                 descr: entry["descr"].as_str().map(MaybeString::from),
-                winsserver: MaybeString::default(),
-                dnsserver: MaybeString::default(),
-                ntpserver: MaybeString::default(),
+                ..Default::default()
             })
             .collect();
 

opnsense-config/src/tests/data/config-structure-with-dhcp-staticmap-entry.xml

@@ -842,9 +842,9 @@
             <gateway/>
             <carp_depend_on/>
             <peers>03031aec-2e84-462e-9eab-57762dde667a,98e6ca3d-1de9-449b-be80-77022221b509,67c0ace5-e802-4d2b-a536-f8b7a2db6f99,74b60fff-7844-4097-9966-f1c2b1ad29ff,3de82ad5-bc1b-4b91-9598-f906e58ac937,a95e6b5e-24a4-40b5-bb41-b79e784f6f1c,6c9a12c6-c1ca-4c14-866b-975406a30590,c33b308b-7125-4688-9561-989ace8787b5,e43f004a-23bf-4027-8fb0-953fbb40479f</peers>
-            <debug/>
             <endpoint/>
             <peer_dns/>
+            <debug/>
           </server>
         </servers>
       </server>