wip: added score to make control planes unschedulable on UPI, started setting up path_resource function for K8sClient

Cargo.lock

@@ -6049,21 +6049,6 @@ version = "0.5.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "8f50febec83f5ee1df3015341d8bd429f2d1cc62bcba7ea2076759d315084683"
 
-[[package]]
-name = "test-score"
-version = "0.1.0"
-dependencies = [
- "base64 0.22.1",
- "env_logger",
- "harmony",
- "harmony_cli",
- "harmony_macros",
- "harmony_types",
- "log",
- "tokio",
- "url",
-]
-
 [[package]]
 name = "thiserror"
 version = "1.0.69"

adr/015-higher-order-topologies.md

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

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

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

harmony/src/domain/inventory/mod.rs

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

harmony/src/domain/topology/k8s.rs

@@ -27,7 +27,7 @@ use kube::{
 };
 use log::{debug, error, trace, warn};
 use serde::{Serialize, de::DeserializeOwned};
-use serde_json::json;
+use serde_json::{json, Value};
 use similar::TextDiff;
 use tokio::{io::AsyncReadExt, time::sleep};
 use url::Url;
@@ -64,6 +64,10 @@ impl K8sClient {
         })
     }
 
+    pub async fn patch_resource(&self, patch: Value, gvk: &GroupVersionKind) -> Result<(), Error> {
+        
+    }
+
     pub async fn service_account_api(&self, namespace: &str) -> Api<ServiceAccount> {
         let api: Api<ServiceAccount> = Api::namespaced(self.client.clone(), namespace);
         api

harmony/src/infra/network_manager.rs

@@ -17,12 +17,6 @@ use crate::{
     topology::{HostNetworkConfig, NetworkError, NetworkManager, k8s::K8sClient},
 };
 
-/// TODO document properly the non-intuitive behavior or "roll forward only" of nmstate in general
-/// It is documented in nmstate official doc, but worth mentionning here :
-///
-/// - You create a bond, nmstate will apply it
-/// - You delete de bond from nmstate, it will NOT delete it
-/// - To delete it you have to update it with configuration set to null
 pub struct OpenShiftNmStateNetworkManager {
     k8s_client: Arc<K8sClient>,
 }
@@ -37,7 +31,6 @@ impl std::fmt::Debug for OpenShiftNmStateNetworkManager {
 impl NetworkManager for OpenShiftNmStateNetworkManager {
     async fn ensure_network_manager_installed(&self) -> Result<(), NetworkError> {
         debug!("Installing NMState controller...");
-        // TODO use operatorhub maybe?
         self.k8s_client.apply_url(url::Url::parse("https://github.com/nmstate/kubernetes-nmstate/releases/download/v0.84.0/nmstate.io_nmstates.yaml
 ").unwrap(), Some("nmstate"))
             .await?;

harmony/src/modules/okd/bootstrap_03_control_plane.rs

@@ -1,8 +1,20 @@
 use crate::{
-    interpret::Interpret, inventory::HostRole, modules::okd::bootstrap_okd_node::OKDNodeInterpret,
+    data::Version,
-    score::Score, topology::HAClusterTopology,
+    hardware::PhysicalHost,
+    infra::inventory::InventoryRepositoryFactory,
+    interpret::{Interpret, InterpretError, InterpretName, InterpretStatus, Outcome},
+    inventory::{HostRole, Inventory},
+    modules::{
+        dhcp::DhcpHostBindingScore, http::IPxeMacBootFileScore,
+        inventory::DiscoverHostForRoleScore, okd::templates::BootstrapIpxeTpl,
+    },
+    score::Score,
+    topology::{HAClusterTopology, HostBinding},
 };
+use async_trait::async_trait;
 use derive_new::new;
+use harmony_types::id::Id;
+use log::{debug, info};
 use serde::Serialize;
 
 // -------------------------------------------------------------------------------------------------
@@ -16,13 +28,226 @@ pub struct OKDSetup03ControlPlaneScore {}
 
 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
+        Box::new(OKDSetup03ControlPlaneInterpret::new())
-        // 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))
     }
 
     fn name(&self) -> String {
         "OKDSetup03ControlPlaneScore".to_string()
     }
 }
+
+#[derive(Debug, Clone)]
+pub struct OKDSetup03ControlPlaneInterpret {
+    version: Version,
+    status: InterpretStatus,
+}
+
+impl OKDSetup03ControlPlaneInterpret {
+    pub fn new() -> Self {
+        let version = Version::from("1.0.0").unwrap();
+        Self {
+            version,
+            status: InterpretStatus::QUEUED,
+        }
+    }
+
+    /// Ensures that three physical hosts are discovered and available for the ControlPlane role.
+    /// It will trigger discovery if not enough hosts are found.
+    async fn get_nodes(
+        &self,
+        inventory: &Inventory,
+        topology: &HAClusterTopology,
+    ) -> Result<Vec<PhysicalHost>, InterpretError> {
+        const REQUIRED_HOSTS: usize = 3;
+        let repo = InventoryRepositoryFactory::build().await?;
+        let mut control_plane_hosts = repo.get_host_for_role(&HostRole::ControlPlane).await?;
+
+        while control_plane_hosts.len() < REQUIRED_HOSTS {
+            info!(
+                "Discovery of {} control plane hosts in progress, current number {}",
+                REQUIRED_HOSTS,
+                control_plane_hosts.len()
+            );
+            // This score triggers the discovery agent for a specific role.
+            DiscoverHostForRoleScore {
+                role: HostRole::ControlPlane,
+            }
+            .interpret(inventory, topology)
+            .await?;
+            control_plane_hosts = repo.get_host_for_role(&HostRole::ControlPlane).await?;
+        }
+
+        if control_plane_hosts.len() < REQUIRED_HOSTS {
+            Err(InterpretError::new(format!(
+                "OKD Requires at least {} control plane hosts, but only found {}. Cannot proceed.",
+                REQUIRED_HOSTS,
+                control_plane_hosts.len()
+            )))
+        } else {
+            // Take exactly the number of required hosts to ensure consistency.
+            Ok(control_plane_hosts
+                .into_iter()
+                .take(REQUIRED_HOSTS)
+                .collect())
+        }
+    }
+
+    /// Configures DHCP host bindings for all control plane nodes.
+    async fn configure_host_binding(
+        &self,
+        inventory: &Inventory,
+        topology: &HAClusterTopology,
+        nodes: &Vec<PhysicalHost>,
+    ) -> Result<(), InterpretError> {
+        info!("[ControlPlane] Configuring host bindings for control plane nodes.");
+
+        // Ensure the topology definition matches the number of physical nodes found.
+        if topology.control_plane.len() != nodes.len() {
+            return Err(InterpretError::new(format!(
+                "Mismatch between logical control plane hosts defined in topology ({}) and physical nodes found ({}).",
+                topology.control_plane.len(),
+                nodes.len()
+            )));
+        }
+
+        // Create a binding for each physical host to its corresponding logical host.
+        let bindings: Vec<HostBinding> = topology
+            .control_plane
+            .iter()
+            .zip(nodes.iter())
+            .map(|(logical_host, physical_host)| {
+                info!(
+                    "Creating binding: Logical Host '{}' -> Physical Host ID '{}'",
+                    logical_host.name, physical_host.id
+                );
+                HostBinding {
+                    logical_host: logical_host.clone(),
+                    physical_host: physical_host.clone(),
+                }
+            })
+            .collect();
+
+        DhcpHostBindingScore {
+            host_binding: bindings,
+            domain: Some(topology.domain_name.clone()),
+        }
+        .interpret(inventory, topology)
+        .await?;
+
+        Ok(())
+    }
+
+    /// Renders and deploys a per-MAC iPXE boot file for each control plane node.
+    async fn configure_ipxe(
+        &self,
+        inventory: &Inventory,
+        topology: &HAClusterTopology,
+        nodes: &Vec<PhysicalHost>,
+    ) -> Result<(), InterpretError> {
+        info!("[ControlPlane] Rendering per-MAC iPXE configurations.");
+
+        // The iPXE script content is the same for all control plane nodes,
+        // pointing to the 'master.ign' ignition file.
+        let content = BootstrapIpxeTpl {
+            http_ip: &topology.http_server.get_ip().to_string(),
+            scos_path: "scos",
+            ignition_http_path: "okd_ignition_files",
+            installation_device: "/dev/sda", // This might need to be configurable per-host in the future
+            ignition_file_name: "master.ign", // Control plane nodes use the master ignition file
+        }
+        .to_string();
+
+        debug!("[ControlPlane] iPXE content template:\n{content}");
+
+        // Create and apply an iPXE boot file for each node.
+        for node in nodes {
+            let mac_address = node.get_mac_address();
+            if mac_address.is_empty() {
+                return Err(InterpretError::new(format!(
+                    "Physical host with ID '{}' has no MAC addresses defined.",
+                    node.id
+                )));
+            }
+            info!(
+                "[ControlPlane] Applying iPXE config for node ID '{}' with MACs: {:?}",
+                node.id, mac_address
+            );
+
+            IPxeMacBootFileScore {
+                mac_address,
+                content: content.clone(),
+            }
+            .interpret(inventory, topology)
+            .await?;
+        }
+
+        Ok(())
+    }
+
+    /// Prompts the user to reboot the target control plane nodes.
+    async fn reboot_targets(&self, nodes: &Vec<PhysicalHost>) -> Result<(), InterpretError> {
+        let node_ids: Vec<String> = nodes.iter().map(|n| n.id.to_string()).collect();
+        info!("[ControlPlane] Requesting reboot for control plane nodes: {node_ids:?}",);
+
+        let confirmation = inquire::Confirm::new(
+                &format!("Please reboot the {} control plane nodes ({}) to apply their PXE configuration. Press enter when ready.", nodes.len(), node_ids.join(", ")),
+        )
+        .prompt()
+        .map_err(|e| InterpretError::new(format!("User prompt failed: {e}")))?;
+
+        if !confirmation {
+            return Err(InterpretError::new(
+                "User aborted the operation.".to_string(),
+            ));
+        }
+
+        Ok(())
+    }
+}
+
+#[async_trait]
+impl Interpret<HAClusterTopology> for OKDSetup03ControlPlaneInterpret {
+    fn get_name(&self) -> InterpretName {
+        InterpretName::Custom("OKDSetup03ControlPlane")
+    }
+
+    fn get_version(&self) -> Version {
+        self.version.clone()
+    }
+
+    fn get_status(&self) -> InterpretStatus {
+        self.status.clone()
+    }
+
+    fn get_children(&self) -> Vec<Id> {
+        vec![]
+    }
+
+    async fn execute(
+        &self,
+        inventory: &Inventory,
+        topology: &HAClusterTopology,
+    ) -> Result<Outcome, InterpretError> {
+        // 1. Ensure we have 3 physical hosts for the control plane.
+        let nodes = self.get_nodes(inventory, topology).await?;
+
+        // 2. Create DHCP reservations for the control plane nodes.
+        self.configure_host_binding(inventory, topology, &nodes)
+            .await?;
+
+        // 3. Create iPXE files for each control plane node to boot from the master ignition.
+        self.configure_ipxe(inventory, topology, &nodes).await?;
+
+        // 4. Reboot the nodes to start the OS installation.
+        self.reboot_targets(&nodes).await?;
+
+        // TODO: Implement a step to wait for the control plane nodes to join the cluster
+        // and for the cluster operators to become available. This would be similar to
+        // the `wait-for bootstrap-complete` command.
+        info!("[ControlPlane] Provisioning initiated. Monitor the cluster convergence manually.");
+
+        Ok(Outcome::success(
+            "Control plane provisioning has been successfully initiated.".into(),
+        ))
+    }
+}

harmony/src/modules/okd/bootstrap_04_workers.rs

@@ -1,9 +1,15 @@
+use async_trait::async_trait;
 use derive_new::new;
+use harmony_types::id::Id;
+use log::info;
 use serde::Serialize;
 
 use crate::{
-    interpret::Interpret, inventory::HostRole, modules::okd::bootstrap_okd_node::OKDNodeInterpret,
+    data::Version,
-    score::Score, topology::HAClusterTopology,
+    interpret::{Interpret, InterpretError, InterpretName, InterpretStatus, Outcome},
+    inventory::Inventory,
+    score::Score,
+    topology::HAClusterTopology,
 };
 
 // -------------------------------------------------------------------------------------------------
@@ -17,10 +23,61 @@ pub struct OKDSetup04WorkersScore {}
 
 impl Score<HAClusterTopology> for OKDSetup04WorkersScore {
     fn create_interpret(&self) -> Box<dyn Interpret<HAClusterTopology>> {
-        Box::new(OKDNodeInterpret::new(HostRole::Worker))
+        Box::new(OKDSetup04WorkersInterpret::new(self.clone()))
     }
 
     fn name(&self) -> String {
         "OKDSetup04WorkersScore".to_string()
     }
 }
+
+#[derive(Debug, Clone)]
+pub struct OKDSetup04WorkersInterpret {
+    score: OKDSetup04WorkersScore,
+    version: Version,
+    status: InterpretStatus,
+}
+
+impl OKDSetup04WorkersInterpret {
+    pub fn new(score: OKDSetup04WorkersScore) -> Self {
+        let version = Version::from("1.0.0").unwrap();
+        Self {
+            version,
+            score,
+            status: InterpretStatus::QUEUED,
+        }
+    }
+
+    async fn render_and_reboot(&self) -> Result<(), InterpretError> {
+        info!("[Workers] Rendering per-MAC PXE for workers and rebooting");
+        Ok(())
+    }
+}
+
+#[async_trait]
+impl Interpret<HAClusterTopology> for OKDSetup04WorkersInterpret {
+    fn get_name(&self) -> InterpretName {
+        InterpretName::Custom("OKDSetup04Workers")
+    }
+
+    fn get_version(&self) -> Version {
+        self.version.clone()
+    }
+
+    fn get_status(&self) -> InterpretStatus {
+        self.status.clone()
+    }
+
+    fn get_children(&self) -> Vec<Id> {
+        vec![]
+    }
+
+    async fn execute(
+        &self,
+        _inventory: &Inventory,
+        _topology: &HAClusterTopology,
+    ) -> Result<Outcome, InterpretError> {
+        self.render_and_reboot().await?;
+        Ok(Outcome::success("Workers provisioned".into()))
+    }
+}

harmony/src/modules/okd/bootstrap_okd_node.rs

@@ -1,303 +0,0 @@
-use async_trait::async_trait;
-use derive_new::new;
-use harmony_types::id::Id;
-use log::{debug, info};
-use serde::Serialize;
-
-use crate::{
-    data::Version,
-    hardware::PhysicalHost,
-    infra::inventory::InventoryRepositoryFactory,
-    interpret::{Interpret, InterpretError, InterpretName, InterpretStatus, Outcome},
-    inventory::{HostRole, Inventory},
-    modules::{
-        dhcp::DhcpHostBindingScore,
-        http::IPxeMacBootFileScore,
-        inventory::DiscoverHostForRoleScore,
-        okd::{
-            okd_node::{
-                BootstrapRole, ControlPlaneRole, OKDRoleProperties, StorageRole, WorkerRole,
-            },
-            templates::BootstrapIpxeTpl,
-        },
-    },
-    score::Score,
-    topology::{HAClusterTopology, HostBinding, LogicalHost},
-};
-
-#[derive(Debug, Clone, Serialize, new)]
-pub struct OKDNodeInstallationScore {
-    host_role: HostRole,
-}
-
-impl Score<HAClusterTopology> for OKDNodeInstallationScore {
-    fn name(&self) -> String {
-        "OKDNodeScore".to_string()
-    }
-
-    fn create_interpret(&self) -> Box<dyn Interpret<HAClusterTopology>> {
-        Box::new(OKDNodeInterpret::new(self.host_role.clone()))
-    }
-}
-
-#[derive(Debug, Clone)]
-pub struct OKDNodeInterpret {
-    host_role: HostRole,
-}
-
-impl OKDNodeInterpret {
-    pub fn new(host_role: HostRole) -> Self {
-        Self { host_role }
-    }
-
-    fn okd_role_properties(&self, role: &HostRole) -> &'static dyn OKDRoleProperties {
-        match role {
-            HostRole::Bootstrap => &BootstrapRole,
-            HostRole::ControlPlane => &ControlPlaneRole,
-            HostRole::Worker => &WorkerRole,
-        }
-    }
-
-    async fn get_nodes(
-        &self,
-        inventory: &Inventory,
-        topology: &HAClusterTopology,
-    ) -> Result<Vec<PhysicalHost>, InterpretError> {
-        let repo = InventoryRepositoryFactory::build().await?;
-
-        let mut hosts = repo.get_host_for_role(&self.host_role).await?;
-
-        let okd_host_properties = self.okd_role_properties(&self.host_role);
-
-        let required_hosts: usize = okd_host_properties.required_hosts();
-
-        while hosts.len() < required_hosts {
-            info!(
-                "Discovery of {} {} hosts in progress, current number {}",
-                required_hosts,
-                self.host_role,
-                hosts.len()
-            );
-            // This score triggers the discovery agent for a specific role.
-            DiscoverHostForRoleScore {
-                role: self.host_role.clone(),
-            }
-            .interpret(inventory, topology)
-            .await?;
-            hosts = repo.get_host_for_role(&self.host_role).await?;
-        }
-
-        if hosts.len() < required_hosts {
-            Err(InterpretError::new(format!(
-                "OKD Requires at least {} {} hosts, but only found {}. Cannot proceed.",
-                required_hosts,
-                self.host_role,
-                hosts.len()
-            )))
-        } else {
-            // Take exactly the number of required hosts to ensure consistency.
-            Ok(hosts.into_iter().take(required_hosts).collect())
-        }
-    }
-
-    /// Configures DHCP host bindings for all nodes.
-    async fn configure_host_binding(
-        &self,
-        inventory: &Inventory,
-        topology: &HAClusterTopology,
-        nodes: &Vec<PhysicalHost>,
-    ) -> Result<(), InterpretError> {
-        info!(
-            "[{}] Configuring host bindings for {} plane nodes.",
-            self.host_role, self.host_role,
-        );
-
-        let host_properties = self.okd_role_properties(&self.host_role);
-
-        self.validate_host_node_match(nodes, host_properties.logical_hosts(topology))?;
-
-        let bindings: Vec<HostBinding> =
-            self.host_bindings(nodes, host_properties.logical_hosts(topology));
-
-        DhcpHostBindingScore {
-            host_binding: bindings,
-            domain: Some(topology.domain_name.clone()),
-        }
-        .interpret(inventory, topology)
-        .await?;
-
-        Ok(())
-    }
-
-    // Ensure the topology definition matches the number of physical nodes found.
-    fn validate_host_node_match(
-        &self,
-        nodes: &Vec<PhysicalHost>,
-        hosts: &Vec<LogicalHost>,
-    ) -> Result<(), InterpretError> {
-        if hosts.len() != nodes.len() {
-            return Err(InterpretError::new(format!(
-                "Mismatch between logical hosts defined in topology ({}) and physical nodes found ({}).",
-                hosts.len(),
-                nodes.len()
-            )));
-        }
-        Ok(())
-    }
-
-    // Create a binding for each physical host to its corresponding logical host.
-    fn host_bindings(
-        &self,
-        nodes: &Vec<PhysicalHost>,
-        hosts: &Vec<LogicalHost>,
-    ) -> Vec<HostBinding> {
-        hosts
-            .iter()
-            .zip(nodes.iter())
-            .map(|(logical_host, physical_host)| {
-                info!(
-                    "Creating binding: Logical Host '{}' -> Physical Host ID '{}'",
-                    logical_host.name, physical_host.id
-                );
-                HostBinding {
-                    logical_host: logical_host.clone(),
-                    physical_host: physical_host.clone(),
-                }
-            })
-            .collect()
-    }
-
-    /// Renders and deploys a per-MAC iPXE boot file for each node.
-    async fn configure_ipxe(
-        &self,
-        inventory: &Inventory,
-        topology: &HAClusterTopology,
-        nodes: &Vec<PhysicalHost>,
-    ) -> Result<(), InterpretError> {
-        info!(
-            "[{}] Rendering per-MAC iPXE configurations.",
-            self.host_role
-        );
-
-        let okd_role_properties = self.okd_role_properties(&self.host_role);
-        // The iPXE script content is the same for all control plane nodes,
-        // pointing to the 'master.ign' ignition file.
-        let content = BootstrapIpxeTpl {
-            http_ip: &topology.http_server.get_ip().to_string(),
-            scos_path: "scos",
-            ignition_http_path: "okd_ignition_files",
-            //TODO must be refactored to not only use /dev/sda
-            installation_device: "/dev/sda", // This might need to be configurable per-host in the future
-            ignition_file_name: okd_role_properties.ignition_file(),
-        }
-        .to_string();
-
-        debug!("[{}] iPXE content template:\n{content}", self.host_role);
-
-        // Create and apply an iPXE boot file for each node.
-        for node in nodes {
-            let mac_address = node.get_mac_address();
-            if mac_address.is_empty() {
-                return Err(InterpretError::new(format!(
-                    "Physical host with ID '{}' has no MAC addresses defined.",
-                    node.id
-                )));
-            }
-            info!(
-                "[{}] Applying iPXE config for node ID '{}' with MACs: {:?}",
-                self.host_role, node.id, mac_address
-            );
-
-            IPxeMacBootFileScore {
-                mac_address,
-                content: content.clone(),
-            }
-            .interpret(inventory, topology)
-            .await?;
-        }
-
-        Ok(())
-    }
-
-    /// Prompts the user to reboot the target control plane nodes.
-    async fn reboot_targets(&self, nodes: &Vec<PhysicalHost>) -> Result<(), InterpretError> {
-        let node_ids: Vec<String> = nodes.iter().map(|n| n.id.to_string()).collect();
-        info!(
-            "[{}] Requesting reboot for control plane nodes: {node_ids:?}",
-            self.host_role
-        );
-
-        let confirmation = inquire::Confirm::new(
-                &format!("Please reboot the {} {} nodes ({}) to apply their PXE configuration. Press enter when ready.", nodes.len(), self.host_role, node_ids.join(", ")),
-        )
-        .prompt()
-        .map_err(|e| InterpretError::new(format!("User prompt failed: {e}")))?;
-
-        if !confirmation {
-            return Err(InterpretError::new(
-                "User aborted the operation.".to_string(),
-            ));
-        }
-
-        Ok(())
-    }
-}
-
-#[async_trait]
-impl Interpret<HAClusterTopology> for OKDNodeInterpret {
-    async fn execute(
-        &self,
-        inventory: &Inventory,
-        topology: &HAClusterTopology,
-    ) -> Result<Outcome, InterpretError> {
-        // 1. Ensure we have the specfied number of physical hosts.
-        let nodes = self.get_nodes(inventory, topology).await?;
-
-        // 2. Create DHCP reservations for the nodes.
-        self.configure_host_binding(inventory, topology, &nodes)
-            .await?;
-
-        // 3. Create iPXE files for each node to boot from the ignition.
-        self.configure_ipxe(inventory, topology, &nodes).await?;
-
-        // 4. Reboot the nodes to start the OS installation.
-        self.reboot_targets(&nodes).await?;
-        // TODO: Implement a step to validate that the installation of the nodes is
-        // complete and for the cluster operators to become available.
-        //
-        // The OpenShift installer only provides two wait commands which currently need to be
-        // run manually:
-        //   - `openshift-install wait-for bootstrap-complete`
-        //   - `openshift-install wait-for install-complete`
-        //
-        // There is no installer command that waits specifically for worker node
-        // provisioning. Worker nodes join asynchronously (via ignition + CSR approval),
-        // and the cluster becomes fully functional only once all nodes are Ready and the
-        // cluster operators report Available=True.
-        info!(
-            "[{}] Provisioning initiated. Monitor the cluster convergence manually.",
-            self.host_role
-        );
-
-        Ok(Outcome::success(format!(
-            "{} provisioning has been successfully initiated.",
-            self.host_role
-        )))
-    }
-
-    fn get_name(&self) -> InterpretName {
-        InterpretName::Custom("OKDNodeSetup".into())
-    }
-
-    fn get_version(&self) -> Version {
-        todo!()
-    }
-
-    fn get_status(&self) -> InterpretStatus {
-        todo!()
-    }
-
-    fn get_children(&self) -> Vec<Id> {
-        todo!()
-    }
-}

harmony/src/modules/okd/control_plane.rs

@@ -0,0 +1,87 @@
+use std::sync::Arc;
+
+use async_trait::async_trait;
+use harmony_types::id::Id;
+use kube::api::GroupVersionKind;
+use serde::Serialize;
+use serde_json::json;
+
+use crate::{
+    data::Version,
+    interpret::{Interpret, InterpretError, InterpretName, InterpretStatus, Outcome},
+    inventory::Inventory,
+    score::Score,
+    topology::{K8sclient, Topology, k8s::K8sClient},
+};
+
+#[derive(Debug, Clone, Serialize)]
+pub struct ControlPlaneConfig {}
+
+impl<T: Topology + K8sclient> Score<T> for ControlPlaneConfig {
+    fn name(&self) -> String {
+        "ControlPlaneConfig".to_string()
+    }
+
+    #[doc(hidden)]
+    fn create_interpret(&self) -> Box<dyn Interpret<T>> {
+        todo!()
+    }
+}
+
+#[derive(Debug, Clone, Serialize)]
+pub struct ControlPlaneConfigInterpret {
+    score: ControlPlaneConfig,
+}
+
+#[async_trait]
+impl<T: Topology + K8sclient> Interpret<T> for ControlPlaneConfigInterpret {
+    async fn execute(
+        &self,
+        inventory: &Inventory,
+        topology: &T,
+    ) -> Result<Outcome, InterpretError> {
+        let client = topology.k8s_client().await.unwrap();
+        self.control_plane_unschedulable(&client).await
+    }
+
+    fn get_name(&self) -> InterpretName {
+        todo!()
+    }
+
+    fn get_version(&self) -> Version {
+        todo!()
+    }
+
+    fn get_status(&self) -> InterpretStatus {
+        todo!()
+    }
+
+    fn get_children(&self) -> Vec<Id> {
+        todo!()
+    }
+}
+
+impl ControlPlaneConfigInterpret {
+    async fn control_plane_unschedulable(
+        &self,
+        client: &Arc<K8sClient>,
+    ) -> Result<Outcome, InterpretError> {
+        let patch = json!({
+            "spec": {
+                "mastersSchedulable": false
+            }
+        });
+
+        let resource = GroupVersionKind {
+            group: "config.openshift.io".to_string(),
+            version: "v1".to_string(),
+            kind: "Scheduler".to_string(),
+        };
+
+        client.patch_resource(patch, &resource).await?;
+
+        Ok(Outcome::success(
+            "control planes are no longer schedulable".to_string(),
+        ))
+    }
+}

harmony/src/modules/okd/mod.rs

@@ -6,14 +6,12 @@ mod bootstrap_05_sanity_check;
 mod bootstrap_06_installation_report;
 pub mod bootstrap_dhcp;
 pub mod bootstrap_load_balancer;
-pub mod bootstrap_okd_node;
 mod bootstrap_persist_network_bond;
 pub mod dhcp;
 pub mod dns;
 pub mod installation;
 pub mod ipxe;
 pub mod load_balancer;
-pub mod okd_node;
 pub mod templates;
 pub mod upgrade;
 pub use bootstrap_01_prepare::*;

harmony/src/modules/okd/okd_node.rs

@@ -1,54 +0,0 @@
-use crate::topology::{HAClusterTopology, LogicalHost};
-
-pub trait OKDRoleProperties {
-    fn ignition_file(&self) -> &'static str;
-    fn required_hosts(&self) -> usize;
-    fn logical_hosts<'a>(&self, t: &'a HAClusterTopology) -> &'a Vec<LogicalHost>;
-}
-
-pub struct BootstrapRole;
-pub struct ControlPlaneRole;
-pub struct WorkerRole;
-pub struct StorageRole;
-
-impl OKDRoleProperties for BootstrapRole {
-    fn ignition_file(&self) -> &'static str {
-        "bootstrap.ign"
-    }
-
-    fn required_hosts(&self) -> usize {
-        1
-    }
-
-    fn logical_hosts<'a>(&self, t: &'a HAClusterTopology) -> &'a Vec<LogicalHost> {
-        todo!()
-    }
-}
-
-impl OKDRoleProperties for ControlPlaneRole {
-    fn ignition_file(&self) -> &'static str {
-        "master.ign"
-    }
-
-    fn required_hosts(&self) -> usize {
-        3
-    }
-
-    fn logical_hosts<'a>(&self, t: &'a HAClusterTopology) -> &'a Vec<LogicalHost> {
-        &t.control_plane
-    }
-}
-
-impl OKDRoleProperties for WorkerRole {
-    fn ignition_file(&self) -> &'static str {
-        "worker.ign"
-    }
-
-    fn required_hosts(&self) -> usize {
-        2
-    }
-
-    fn logical_hosts<'a>(&self, t: &'a HAClusterTopology) -> &'a Vec<LogicalHost> {
-        &t.workers
-    }
-}