feat: Initialize k8s tenant properly

This Id implementation is optimized for ease of use. Ids are prefixed with the unix epoch and suffixed with 7 alphanumeric characters. But Ids can also contain any String the user wants to pass it

.gitea/workflows/check.yml

@@ -0,0 +1,14 @@
+name: Run Check Script
+on:
+  push:
+  pull_request:
+
+jobs:
+  check:
+    runs-on: rust-cargo
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+      
+      - name: Run check script
+        run: bash check.sh

CONTRIBUTING.md

@@ -0,0 +1,36 @@
+# Contributing to the Harmony project
+
+## Write small P-R
+
+Aim for the smallest piece of work that is mergeable.
+
+Mergeable means that :
+
+- it does not break the build
+- it moves the codebase one step forward
+
+P-Rs can be many things, they do not have to be complete features.
+
+### What a P-R **should** be
+
+- Introduce a new trait : This will be the place to discuss the new trait addition, its design and implementation
+- A new implementation of a trait : a new concrete implementation of the LoadBalancer trait
+- A new CI check : something that improves quality, robustness, ci performance
+- Documentation improvements
+- Refactoring
+- Bugfix
+
+### What a P-R **should not** be
+
+- Large. Anything over 200 lines (excluding generated lines) should have a very good reason to be this large.
+- A mix of refactoring, bug fixes and new features.
+- Introducing multiple new features or ideas at once.
+- Multiple new implementations of a trait/functionnality at once
+
+The general idea is to keep P-Rs small and single purpose.
+
+## Commit message formatting
+
+We follow conventional commits guidelines.
+
+https://www.conventionalcommits.org/en/v1.0.0/

Cargo.lock

@@ -1070,6 +1070,21 @@ dependencies = [
  "url",
 ]
 
+[[package]]
+name = "example-tenant"
+version = "0.1.0"
+dependencies = [
+ "cidr",
+ "env_logger",
+ "harmony",
+ "harmony_cli",
+ "harmony_macros",
+ "harmony_types",
+ "log",
+ "tokio",
+ "url",
+]
+
 [[package]]
 name = "example-tui"
 version = "0.1.0"
@@ -1409,12 +1424,14 @@ dependencies = [
  "derive-new",
  "directories",
  "dockerfile_builder",
+ "dyn-clone",
  "email_address",
  "env_logger",
  "fqdn",
  "harmony_macros",
  "harmony_types",
  "helm-wrapper-rs",
+ "hex",
  "http 1.3.1",
  "inquire",
  "k3d-rs",
@@ -1426,6 +1443,7 @@ dependencies = [
  "non-blank-string-rs",
  "opnsense-config",
  "opnsense-config-xml",
+ "rand 0.9.1",
  "reqwest 0.11.27",
  "russh",
  "rust-ipmi",
@@ -1550,6 +1568,12 @@ version = "0.3.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "d231dfb89cfffdbc30e7fc41579ed6066ad03abda9e567ccafae602b97ec5024"
 
+[[package]]
+name = "hex"
+version = "0.4.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7f24254aa9a54b5c858eaee2f5bccdb46aaf0e486a595ed5fd8f86ba55232a70"
+
 [[package]]
 name = "hex-literal"
 version = "0.4.1"

adr/000-ADR-Template.md

@@ -1,6 +1,6 @@
 # Architecture Decision Record: \<Title\>
 
-Name: \<Name\>
+Initial Author: \<Name\>
 
 Initial Date: \<Date\>
 

adr/009-helm-and-kustomize-handling.md

@@ -1,6 +1,6 @@
 # Architecture Decision Record: Helm and Kustomize Handling
 
-Name: Taha Hawa
+Initial Author: Taha Hawa
 
 Initial Date: 2025-04-15
 

adr/010-monitoring-and-alerting.md

@@ -1,7 +1,7 @@
 # Architecture Decision Record: Monitoring and Alerting
 
-Proposed by: Willem Rolleman
-Date: April 28 2025
+Initial Author : Willem Rolleman
+Date : April 28 2025
 
 ## Status
 

adr/011-multi-tenant-cluster.md

@@ -0,0 +1,161 @@
+# Architecture Decision Record: Multi-Tenancy Strategy for Harmony Managed Clusters
+
+Initial Author: Jean-Gabriel Gill-Couture
+
+Initial Date: 2025-05-26
+
+## Status
+
+Proposed
+
+## Context
+
+Harmony manages production OKD/Kubernetes clusters that serve multiple clients with varying trust levels and operational requirements. We need a multi-tenancy strategy that provides:
+
+1. **Strong isolation** between client workloads while maintaining operational simplicity
+2. **Controlled API access** allowing clients self-service capabilities within defined boundaries
+3. **Security-first approach** protecting both the cluster infrastructure and tenant data
+4. **Harmony-native implementation** using our Score/Interpret pattern for automated tenant provisioning
+5. **Scalable management** supporting both small trusted clients and larger enterprise customers
+
+The official Kubernetes multi-tenancy documentation identifies two primary models: namespace-based isolation and virtual control planes per tenant. Given Harmony's focus on operational simplicity, provider-agnostic abstractions (ADR-003), and hexagonal architecture (ADR-002), we must choose an approach that balances security, usability, and maintainability.
+
+Our clients represent a hybrid tenancy model:
+- **Customer multi-tenancy**: Each client operates independently with no cross-tenant trust
+- **Team multi-tenancy**: Individual clients may have multiple team members requiring coordinated access
+- **API access requirement**: Unlike pure SaaS scenarios, clients need controlled Kubernetes API access for self-service operations
+
+The official kubernetes documentation on multi tenancy heavily inspired this ADR : https://kubernetes.io/docs/concepts/security/multi-tenancy/
+
+## Decision
+
+Implement **namespace-based multi-tenancy** with the following architecture:
+
+### 1. Network Security Model
+- **Private cluster access**: Kubernetes API and OpenShift console accessible only via WireGuard VPN
+- **No public exposure**: Control plane endpoints remain internal to prevent unauthorized access attempts
+- **VPN-based authentication**: Initial access control through WireGuard client certificates
+
+### 2. Tenant Isolation Strategy
+- **Dedicated namespace per tenant**: Each client receives an isolated namespace with access limited only to the required resources and operations
+- **Complete network isolation**: NetworkPolicies prevent cross-namespace communication while allowing full egress to public internet
+- **Resource governance**: ResourceQuotas and LimitRanges enforce CPU, memory, and storage consumption limits
+- **Storage access control**: Clients can create PersistentVolumeClaims but cannot directly manipulate PersistentVolumes or access other tenants' storage
+
+### 3. Access Control Framework
+- **Principle of Least Privilege**: RBAC grants only necessary permissions within tenant namespace scope
+- **Namespace-scoped**: Clients can create/modify/delete resources within their namespace
+- **Cluster-level restrictions**: No access to cluster-wide resources, other namespaces, or sensitive cluster operations
+- **Whitelisted operations**: Controlled self-service capabilities for ingress, secrets, configmaps, and workload management
+
+### 4. Identity Management Evolution
+- **Phase 1**: Manual provisioning of VPN access and Kubernetes ServiceAccounts/Users
+- **Phase 2**: Migration to Keycloak-based identity management (aligning with ADR-006) for centralized authentication and lifecycle management
+
+### 5. Harmony Integration
+- **TenantScore implementation**: Declarative tenant provisioning using Harmony's Score/Interpret pattern
+- **Topology abstraction**: Tenant configuration abstracted from underlying Kubernetes implementation details
+- **Automated deployment**: Complete tenant setup automated through Harmony's orchestration capabilities
+
+## Rationale
+
+### Network Security Through VPN Access
+- **Defense in depth**: VPN requirement adds critical security layer preventing unauthorized cluster access
+- **Simplified firewall rules**: No need for complex public endpoint protections or rate limiting
+- **Audit capability**: VPN access provides clear audit trail of cluster connections
+- **Aligns with enterprise practices**: Most enterprise customers already use VPN infrastructure
+
+### Namespace Isolation vs Virtual Control Planes
+Following Kubernetes official guidance, namespace isolation provides:
+- **Lower resource overhead**: Virtual control planes require dedicated etcd, API server, and controller manager per tenant
+- **Operational simplicity**: Single control plane to maintain, upgrade, and monitor
+- **Cross-tenant service integration**: Enables future controlled cross-tenant communication if required
+- **Proven stability**: Namespace-based isolation is well-tested and widely deployed
+- **Cost efficiency**: Significantly lower infrastructure costs compared to dedicated control planes
+
+### Hybrid Tenancy Model Suitability
+Our approach addresses both customer and team multi-tenancy requirements:
+- **Customer isolation**: Strong network and RBAC boundaries prevent cross-tenant interference
+- **Team collaboration**: Multiple team members can share namespace access through group-based RBAC
+- **Self-service balance**: Controlled API access enables client autonomy without compromising security
+
+### Harmony Architecture Alignment
+- **Provider agnostic**: TenantScore abstracts multi-tenancy concepts, enabling future support for other Kubernetes distributions
+- **Hexagonal architecture**: Tenant management becomes an infrastructure capability accessed through well-defined ports
+- **Declarative automation**: Tenant lifecycle fully managed through Harmony's Score execution model
+
+## Consequences
+
+### Positive Consequences
+- **Strong security posture**: VPN + namespace isolation provides robust tenant separation
+- **Operational efficiency**: Single cluster management with automated tenant provisioning
+- **Client autonomy**: Self-service capabilities reduce operational support burden
+- **Scalable architecture**: Can support hundreds of tenants per cluster without architectural changes
+- **Future flexibility**: Foundation supports evolution to more sophisticated multi-tenancy models
+- **Cost optimization**: Shared infrastructure maximizes resource utilization
+
+### Negative Consequences
+- **VPN operational overhead**: Requires VPN infrastructure management
+- **Manual provisioning complexity**: Phase 1 manual user management creates administrative burden
+- **Network policy dependency**: Requires CNI with NetworkPolicy support (OVN-Kubernetes provides this and is the OKD/Openshift default)
+- **Cluster-wide resource limitations**: Some advanced Kubernetes features require cluster-wide access
+- **Single point of failure**: Cluster outage affects all tenants simultaneously
+
+### Migration Challenges
+- **Legacy client integration**: Existing clients may need VPN client setup and credential migration
+- **Monitoring complexity**: Per-tenant observability requires careful metric and log segmentation
+- **Backup considerations**: Tenant data backup must respect isolation boundaries
+
+## Alternatives Considered
+
+### Alternative 1: Virtual Control Plane Per Tenant
+**Pros**: Complete control plane isolation, full Kubernetes API access per tenant
+**Cons**: 3-5x higher resource usage, complex cross-tenant networking, operational complexity scales linearly with tenants
+
+**Rejected**: Resource overhead incompatible with cost-effective multi-tenancy goals
+
+### Alternative 2: Dedicated Clusters Per Tenant
+**Pros**: Maximum isolation, independent upgrade cycles, simplified security model
+**Cons**: Exponential operational complexity, prohibitive costs, resource waste
+
+**Rejected**: Operational overhead makes this approach unsustainable for multiple clients
+
+### Alternative 3: Public API with Advanced Authentication
+**Pros**: No VPN requirement, potentially simpler client access
+**Cons**: Larger attack surface, complex rate limiting and DDoS protection, increased security monitoring requirements
+
+**Rejected**: Risk/benefit analysis favors VPN-based access control
+
+### Alternative 4: Service Mesh Based Isolation
+**Pros**: Fine-grained traffic control, encryption, advanced observability
+**Cons**: Significant operational complexity, performance overhead, steep learning curve
+
+**Rejected**: Complexity overhead outweighs benefits for current requirements; remains option for future enhancement
+
+## Additional Notes
+
+### Implementation Roadmap
+1. **Phase 1**: Implement VPN access and manual tenant provisioning
+2. **Phase 2**: Deploy TenantScore automation for namespace, RBAC, and NetworkPolicy management
+4. **Phase 3**: Work on privilege escalation from pods, audit for weaknesses, enforce security policies on pod runtimes
+3. **Phase 4**: Integrate Keycloak for centralized identity management
+4. **Phase 5**: Add advanced monitoring and per-tenant observability
+
+### TenantScore Structure Preview
+```rust
+pub struct TenantScore {
+    pub tenant_config: TenantConfig,
+    pub resource_quotas: ResourceQuotaConfig,
+    pub network_isolation: NetworkIsolationPolicy,
+    pub storage_access: StorageAccessConfig,
+    pub rbac_config: RBACConfig,
+}
+```
+
+### Future Enhancements
+- **Cross-tenant service mesh**: For approved inter-tenant communication
+- **Advanced monitoring**: Per-tenant Prometheus/Grafana instances
+- **Backup automation**: Tenant-scoped backup policies
+- **Cost allocation**: Detailed per-tenant resource usage tracking
+
+This ADR establishes the foundation for secure, scalable multi-tenancy in Harmony-managed clusters while maintaining operational simplicity and cost effectiveness. A follow-up ADR will detail the Tenant abstraction and user management mechanisms within the Harmony framework.

adr/tenant/NetworkPolicy.yaml

@@ -0,0 +1,41 @@
+apiVersion: networking.k8s.io/v1
+kind: NetworkPolicy
+metadata:
+  name: tenant-isolation-policy
+  namespace: testtenant
+spec:
+  podSelector: {}  # Selects all pods in the namespace
+  policyTypes:
+  - Ingress
+  - Egress
+  ingress:
+  - from:
+    - podSelector: {}  # Allow from all pods in the same namespace
+  egress:
+  - to:
+    - podSelector: {}  # Allow to all pods in the same namespace
+  - to:
+    - podSelector: {}
+      namespaceSelector: 
+        matchLabels:
+          kubernetes.io/metadata.name: openshift-dns # Target the openshift-dns namespace
+    # Note, only opening port 53 is not enough, will have to dig deeper into this one eventually
+    # ports:
+    # - protocol: UDP
+    #   port: 53
+    # - protocol: TCP
+    #   port: 53
+  # Allow egress to public internet only
+  - to:
+    - ipBlock:
+        cidr: 0.0.0.0/0
+        except:
+        - 10.0.0.0/8      # RFC1918
+        - 172.16.0.0/12   # RFC1918
+        - 192.168.0.0/16  # RFC1918
+        - 169.254.0.0/16  # Link-local
+        - 127.0.0.0/8     # Loopback
+        - 224.0.0.0/4     # Multicast
+        - 240.0.0.0/4     # Reserved
+        - 100.64.0.0/10   # Carrier-grade NAT
+        - 0.0.0.0/8       # Reserved

adr/tenant/TestDeployment.yaml

@@ -0,0 +1,95 @@
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: testtenant
+---
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: testtenant2
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: test-web
+  namespace: testtenant
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: test-web
+  template:
+    metadata:
+      labels:
+        app: test-web
+    spec:
+      containers:
+      - name: nginx
+        image: nginxinc/nginx-unprivileged
+        ports:
+        - containerPort: 80
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: test-web
+  namespace: testtenant
+spec:
+  selector:
+    app: test-web
+  ports:
+  - port: 80
+    targetPort: 8080
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: test-client
+  namespace: testtenant
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: test-client
+  template:
+    metadata:
+      labels:
+        app: test-client
+    spec:
+      containers:
+      - name: curl
+        image: curlimages/curl:latest
+        command: ["/bin/sh", "-c", "sleep 3600"]
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: test-web
+  namespace: testtenant2
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: test-web
+  template:
+    metadata:
+      labels:
+        app: test-web
+    spec:
+      containers:
+      - name: nginx
+        image: nginxinc/nginx-unprivileged
+        ports:
+        - containerPort: 80
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: test-web
+  namespace: testtenant2
+spec:
+  selector:
+    app: test-web
+  ports:
+  - port: 80
+    targetPort: 8080

examples/lamp/src/main.rs

@@ -4,9 +4,7 @@ use harmony::{
     maestro::Maestro,
     modules::{
         lamp::{LAMPConfig, LAMPScore},
-        monitoring::monitoring_alerting::{
-            AlertChannel, MonitoringAlertingStackScore, WebhookServiceType,
-        },
+        monitoring::monitoring_alerting::{AlertChannel, MonitoringAlertingStackScore},
     },
     topology::{K8sAnywhereTopology, Url},
 };
@@ -50,10 +48,6 @@ async fn main() {
 
     let mut monitoring_stack_score = MonitoringAlertingStackScore::new();
     monitoring_stack_score.namespace = Some(lamp_stack.config.namespace.clone());
-    monitoring_stack_score.alert_channel = Some(AlertChannel::WebHookUrl {
-        url: url,
-        webhook_service_type: WebhookServiceType::Discord,
-    });
 
     maestro.register_all(vec![Box::new(lamp_stack), Box::new(monitoring_stack_score)]);
     // Here we bootstrap the CLI, this gives some nice features if you need them

examples/tenant/Cargo.toml

@@ -0,0 +1,18 @@
+[package]
+name = "example-tenant"
+edition = "2024"
+version.workspace = true
+readme.workspace = true
+license.workspace = true
+publish = false
+
+[dependencies]
+harmony = { path = "../../harmony" }
+harmony_cli = { path = "../../harmony_cli" }
+harmony_types = { path = "../../harmony_types" }
+cidr = { workspace = true }
+tokio = { workspace = true }
+harmony_macros = { path = "../../harmony_macros" }
+log = { workspace = true }
+env_logger = { workspace = true }
+url = { workspace = true }

examples/tenant/src/main.rs

@@ -0,0 +1,41 @@
+use harmony::{
+    data::Id,
+    inventory::Inventory,
+    maestro::Maestro,
+    modules::tenant::TenantScore,
+    topology::{K8sAnywhereTopology, tenant::TenantConfig},
+};
+
+#[tokio::main]
+async fn main() {
+    let tenant = TenantScore {
+        config: TenantConfig {
+            id: Id::default(),
+            name: "TestTenant".to_string(),
+            ..Default::default()
+        },
+    };
+
+    let mut maestro = Maestro::<K8sAnywhereTopology>::initialize(
+        Inventory::autoload(),
+        K8sAnywhereTopology::new(),
+    )
+    .await
+    .unwrap();
+
+    maestro.register_all(vec![Box::new(tenant)]);
+    harmony_cli::init(maestro, None).await.unwrap();
+}
+
+// TODO write tests
+// - Create Tenant with default config mostly, make sure namespace is created
+// - deploy sample client/server app with nginx unprivileged and a service
+// - exec in the client pod and validate the following
+//  - can reach internet
+//  - can reach server pod
+//  - can resolve dns queries to internet
+//  - can resolve dns queries to services
+//  - cannot reach services and pods in other namespaces
+// - Create Tenant with specific cpu/ram/storage requests / limits and make sure they are enforced by trying to
+// deploy a pod with lower requests/limits (accepted) and higher requests/limits (rejected)
+// - Create TenantCredentials and make sure they give only access to the correct tenant

harmony/Cargo.toml

@@ -6,6 +6,8 @@ readme.workspace = true
 license.workspace = true
 
 [dependencies]
+rand = "0.9"
+hex = "0.4"
 libredfish = "0.1.1"
 reqwest = { version = "0.11", features = ["blocking", "json"] }
 russh = "0.45.0"
@@ -49,3 +51,4 @@ fqdn = { version = "0.4.6", features = [
     "serde",
 ] }
 temp-dir = "0.1.14"
+dyn-clone = "1.0.19"

harmony/src/domain/data/id.rs

@@ -1,6 +1,24 @@
+use rand::distr::Alphanumeric;
+use rand::distr::SampleString;
+use std::time::SystemTime;
+use std::time::UNIX_EPOCH;
+
 use serde::{Deserialize, Serialize};
 
-#[derive(Debug, Clone, Serialize, Deserialize)]
+/// A unique identifier designed for ease of use.
+///
+/// You can pass it any String to use and Id, or you can use the default format with `Id::default()`
+///
+/// The default format looks like this
+///
+/// `462d4c_g2COgai`
+///
+/// The first part is the unix timesamp in hexadecimal which makes Id easily sorted by creation time.
+/// Second part is a serie of 7 random characters.
+///
+/// **It is not meant to be very secure or unique**, it is suitable to generate up to 10 000 items per
+/// second with a reasonable collision rate of 0,000014 % as calculated by this calculator : https://kevingal.com/apps/collision.html
+#[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
 pub struct Id {
     value: String,
 }
@@ -10,3 +28,26 @@ impl Id {
         Self { value }
     }
 }
+
+impl std::fmt::Display for Id {
+    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+        f.write_str(&self.value)
+    }
+}
+
+impl Default for Id {
+    fn default() -> Self {
+        let start = SystemTime::now();
+        let since_the_epoch = start
+            .duration_since(UNIX_EPOCH)
+            .expect("Time went backwards");
+        let timestamp = since_the_epoch.as_secs();
+
+        let hex_timestamp = format!("{:x}", timestamp & 0xffffff);
+
+        let random_part: String = Alphanumeric.sample_string(&mut rand::rng(), 7);
+
+        let value = format!("{}_{}", hex_timestamp, random_part);
+        Self { value }
+    }
+}

harmony/src/domain/interpret/mod.rs

@@ -20,6 +20,7 @@ pub enum InterpretName {
     Panic,
     OPNSense,
     K3dInstallation,
+    TenantInterpret,
 }
 
 impl std::fmt::Display for InterpretName {
@@ -35,6 +36,7 @@ impl std::fmt::Display for InterpretName {
             InterpretName::Panic => f.write_str("Panic"),
             InterpretName::OPNSense => f.write_str("OPNSense"),
             InterpretName::K3dInstallation => f.write_str("K3dInstallation"),
+            InterpretName::TenantInterpret => f.write_str("Tenant"),
         }
     }
 }

harmony/src/domain/topology/k8s_anywhere.rs

@@ -1,4 +1,4 @@
-use std::{process::Command, sync::Arc};
+use std::{io::Error, process::Command, sync::Arc};
 
 use async_trait::async_trait;
 use inquire::Confirm;
@@ -6,6 +6,7 @@ use log::{info, warn};
 use tokio::sync::OnceCell;
 
 use crate::{
+    executors::ExecutorError,
     interpret::{InterpretError, Outcome},
     inventory::Inventory,
     maestro::Maestro,
@@ -13,7 +14,13 @@ use crate::{
     topology::LocalhostTopology,
 };
 
-use super::{HelmCommand, K8sclient, Topology, k8s::K8sClient};
+use super::{
+    HelmCommand, K8sclient, Topology,
+    k8s::K8sClient,
+    tenant::{
+        ResourceLimits, TenantConfig, TenantManager, TenantNetworkPolicy, k8s::K8sTenantManager,
+    },
+};
 
 struct K8sState {
     client: Arc<K8sClient>,
@@ -21,6 +28,7 @@ struct K8sState {
     message: String,
 }
 
+#[derive(Debug)]
 enum K8sSource {
     LocalK3d,
     Kubeconfig,
@@ -28,6 +36,7 @@ enum K8sSource {
 
 pub struct K8sAnywhereTopology {
     k8s_state: OnceCell<Option<K8sState>>,
+    tenant_manager: OnceCell<K8sTenantManager>,
 }
 
 #[async_trait]
@@ -51,6 +60,7 @@ impl K8sAnywhereTopology {
     pub fn new() -> Self {
         Self {
             k8s_state: OnceCell::new(),
+            tenant_manager: OnceCell::new(),
         }
     }
 
@@ -159,6 +169,31 @@ impl K8sAnywhereTopology {
 
         Ok(Some(state))
     }
+
+    async fn ensure_k8s_tenant_manager(&self) -> Result<(), String> {
+        if let Some(_) = self.tenant_manager.get() {
+            return Ok(());
+        }
+
+        self.tenant_manager
+            .get_or_try_init(async || -> Result<K8sTenantManager, String> {
+                let k8s_client = self.k8s_client().await?;
+                Ok(K8sTenantManager::new(k8s_client))
+            })
+            .await
+            .unwrap();
+
+        Ok(())
+    }
+
+    fn get_k8s_tenant_manager(&self) -> Result<&K8sTenantManager, ExecutorError> {
+        match self.tenant_manager.get() {
+            Some(t) => Ok(t),
+            None => Err(ExecutorError::UnexpectedError(
+                "K8sTenantManager not available".to_string(),
+            )),
+        }
+    }
 }
 
 struct K8sAnywhereConfig {
@@ -198,6 +233,10 @@ impl Topology for K8sAnywhereTopology {
             "No K8s client could be found or installed".to_string(),
         ))?;
 
+        self.ensure_k8s_tenant_manager()
+            .await
+            .map_err(|e| InterpretError::new(e))?;
+
         match self.is_helm_available() {
             Ok(()) => Ok(Outcome::success(format!(
                 "{} + helm available",
@@ -209,3 +248,38 @@ impl Topology for K8sAnywhereTopology {
 }
 
 impl HelmCommand for K8sAnywhereTopology {}
+
+#[async_trait]
+impl TenantManager for K8sAnywhereTopology {
+    async fn provision_tenant(&self, config: &TenantConfig) -> Result<(), ExecutorError> {
+        self.get_k8s_tenant_manager()?
+            .provision_tenant(config)
+            .await
+    }
+
+    async fn update_tenant_resource_limits(
+        &self,
+        tenant_name: &str,
+        new_limits: &ResourceLimits,
+    ) -> Result<(), ExecutorError> {
+        self.get_k8s_tenant_manager()?
+            .update_tenant_resource_limits(tenant_name, new_limits)
+            .await
+    }
+
+    async fn update_tenant_network_policy(
+        &self,
+        tenant_name: &str,
+        new_policy: &TenantNetworkPolicy,
+    ) -> Result<(), ExecutorError> {
+        self.get_k8s_tenant_manager()?
+            .update_tenant_network_policy(tenant_name, new_policy)
+            .await
+    }
+
+    async fn deprovision_tenant(&self, tenant_name: &str) -> Result<(), ExecutorError> {
+        self.get_k8s_tenant_manager()?
+            .deprovision_tenant(tenant_name)
+            .await
+    }
+}

harmony/src/domain/topology/load_balancer.rs

@@ -7,6 +7,12 @@ use serde::Serialize;
 use super::{IpAddress, LogicalHost};
 use crate::executors::ExecutorError;
 
+impl std::fmt::Debug for dyn LoadBalancer {
+    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+        f.write_fmt(format_args!("LoadBalancer {}", self.get_ip()))
+    }
+}
+
 #[async_trait]
 pub trait LoadBalancer: Send + Sync {
     fn get_ip(&self) -> IpAddress;
@@ -32,11 +38,6 @@ pub trait LoadBalancer: Send + Sync {
     }
 }
 
-impl std::fmt::Debug for dyn LoadBalancer {
-    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
-        f.write_fmt(format_args!("LoadBalancer {}", self.get_ip()))
-    }
-}
 #[derive(Debug, PartialEq, Clone, Serialize)]
 pub struct LoadBalancerService {
     pub backend_servers: Vec<BackendServer>,

harmony/src/domain/topology/mod.rs

@@ -3,6 +3,8 @@ mod host_binding;
 mod http;
 mod k8s_anywhere;
 mod localhost;
+pub mod oberservability;
+pub mod tenant;
 pub use k8s_anywhere::*;
 pub use localhost::*;
 pub mod k8s;

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

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

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

@@ -0,0 +1,31 @@
+use async_trait::async_trait;
+
+use std::fmt::Debug;
+use url::Url;
+
+use crate::interpret::InterpretError;
+
+use crate::{interpret::Outcome, topology::Topology};
+
+/// Represents an entity responsible for collecting and organizing observability data
+/// from various telemetry sources
+/// A `Monitor` abstracts the logic required to scrape, aggregate, and structure
+/// monitoring data, enabling consistent processing regardless of the underlying data source.
+#[async_trait]
+pub trait Monitor<T: Topology>: Debug + Send + Sync {
+    async fn deploy_monitor(
+        &self,
+        topology: &T,
+        alert_receivers: Vec<AlertReceiver>,
+    ) -> Result<Outcome, InterpretError>;
+
+    async fn delete_monitor(
+        &self,
+        topolgy: &T,
+        alert_receivers: Vec<AlertReceiver>,
+    ) -> Result<Outcome, InterpretError>;
+}
+
+pub struct AlertReceiver {
+    pub receiver_id: String,
+}

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

@@ -0,0 +1,110 @@
+use std::sync::Arc;
+
+use crate::{executors::ExecutorError, topology::k8s::K8sClient};
+use async_trait::async_trait;
+use derive_new::new;
+use k8s_openapi::api::core::v1::Namespace;
+use serde_json::json;
+
+use super::{ResourceLimits, TenantConfig, TenantManager, TenantNetworkPolicy};
+
+#[derive(new)]
+pub struct K8sTenantManager {
+    k8s_client: Arc<K8sClient>,
+}
+
+#[async_trait]
+impl TenantManager for K8sTenantManager {
+    async fn provision_tenant(&self, config: &TenantConfig) -> Result<(), ExecutorError> {
+        let namespace = json!(
+            {
+                "apiVersion": "v1",
+                "kind": "Namespace",
+                "metadata": {
+                    "labels": {
+                        "harmony.nationtech.io/tenant.id": config.id,
+                        "harmony.nationtech.io/tenant.name": config.name,
+                    },
+                "name": config.name,
+                },
+            }
+        );
+        todo!("Validate that when tenant already exists (by id) that name has not changed");
+
+        let namespace: Namespace = serde_json::from_value(namespace).unwrap();
+
+        let resource_quota = json!(
+         {
+           "apiVersion": "v1",
+           "kind": "List",
+           "items": [
+             {
+               "apiVersion": "v1",
+               "kind": "ResourceQuota",
+               "metadata": {
+                 "name": config.name,
+                 "labels": {
+                  "harmony.nationtech.io/tenant.id": config.id,
+                  "harmony.nationtech.io/tenant.name": config.name,
+                 },
+                 "namespace": config.name,
+               },
+               "spec": {
+                 "hard": {
+                   "limits.cpu": format!("{:.0}",config.resource_limits.cpu_limit_cores),
+                   "limits.memory": format!("{:.3}Gi", config.resource_limits.memory_limit_gb),
+                   "requests.cpu": format!("{:.0}",config.resource_limits.cpu_request_cores),
+                   "requests.memory": format!("{:.3}Gi", config.resource_limits.memory_request_gb),
+                   "requests.storage": format!("{:.3}", config.resource_limits.storage_total_gb),
+                   "pods": "20",
+                   "services": "10",
+                   "configmaps": "30",
+                   "secrets": "30",
+                   "persistentvolumeclaims": "15",
+                   "services.loadbalancers": "2",
+                   "services.nodeports": "5",
+
+                 }
+               }
+             }
+           ]
+         }
+
+        );
+
+        let network_policy = json!({
+          "apiVersion": "networking.k8s.io/v1",
+          "kind": "NetworkPolicy",
+          "metadata": {
+              "name": format!("{}-network-policy", config.name),
+          },
+          "spec": {
+            "podSelector": {},
+            "egress": [],
+            "ingress": [],
+            "policyTypes": [
+            ]
+          }
+        });
+    }
+
+    async fn update_tenant_resource_limits(
+        &self,
+        tenant_name: &str,
+        new_limits: &ResourceLimits,
+    ) -> Result<(), ExecutorError> {
+        todo!()
+    }
+
+    async fn update_tenant_network_policy(
+        &self,
+        tenant_name: &str,
+        new_policy: &TenantNetworkPolicy,
+    ) -> Result<(), ExecutorError> {
+        todo!()
+    }
+
+    async fn deprovision_tenant(&self, tenant_name: &str) -> Result<(), ExecutorError> {
+        todo!()
+    }
+}

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

@@ -0,0 +1,46 @@
+use super::*;
+use async_trait::async_trait;
+
+use crate::executors::ExecutorError;
+
+#[async_trait]
+pub trait TenantManager {
+    /// Provisions a new tenant based on the provided configuration.
+    /// This operation should be idempotent; if a tenant with the same `config.name`
+    /// already exists and matches the config, it will succeed without changes.
+    /// If it exists but differs, it will be updated, or return an error if the update
+    /// action is not supported
+    ///
+    /// # Arguments
+    /// * `config`: The desired configuration for the new tenant.
+    async fn provision_tenant(&self, config: &TenantConfig) -> Result<(), ExecutorError>;
+
+    /// Updates the resource limits for an existing tenant.
+    ///
+    /// # Arguments
+    /// * `tenant_name`: The logical name of the tenant to update.
+    /// * `new_limits`: The new set of resource limits to apply.
+    async fn update_tenant_resource_limits(
+        &self,
+        tenant_name: &str,
+        new_limits: &ResourceLimits,
+    ) -> Result<(), ExecutorError>;
+
+    /// Updates the high-level network isolation policy for an existing tenant.
+    ///
+    /// # Arguments
+    /// * `tenant_name`: The logical name of the tenant to update.
+    /// * `new_policy`: The new network policy to apply.
+    async fn update_tenant_network_policy(
+        &self,
+        tenant_name: &str,
+        new_policy: &TenantNetworkPolicy,
+    ) -> Result<(), ExecutorError>;
+
+    /// Decommissions an existing tenant, removing its isolated context and associated resources.
+    /// This operation should be idempotent.
+    ///
+    /// # Arguments
+    /// * `tenant_name`: The logical name of the tenant to deprovision.
+    async fn deprovision_tenant(&self, tenant_name: &str) -> Result<(), ExecutorError>;
+}

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

@@ -0,0 +1,89 @@
+pub mod k8s;
+mod manager;
+pub use manager::*;
+use serde::{Deserialize, Serialize};
+
+use std::collections::HashMap;
+
+use crate::data::Id;
+
+#[derive(Debug, Clone, PartialEq, Serialize, Deserialize)] // Assuming serde for Scores
+pub struct TenantConfig {
+    /// This will be used as the primary unique identifier for management operations and will never
+    /// change for the entire lifetime of the tenant
+    pub id: Id,
+
+    /// A human-readable name for the tenant (e.g., "client-alpha", "project-phoenix").
+    pub name: String,
+
+    /// Desired resource allocations and limits for the tenant.
+    pub resource_limits: ResourceLimits,
+
+    /// High-level network isolation policies for the tenant.
+    pub network_policy: TenantNetworkPolicy,
+
+    /// Key-value pairs for provider-specific tagging, labeling, or metadata.
+    /// Useful for billing, organization, or filtering within the provider's console.
+    pub labels_or_tags: HashMap<String, String>,
+}
+
+impl Default for TenantConfig {
+    fn default() -> Self {
+        let id = Id::default();
+        Self {
+            name: format!("tenant_{id}"),
+            id,
+            resource_limits: ResourceLimits {
+                cpu_request_cores: 4.0,
+                cpu_limit_cores: 4.0,
+                memory_request_gb: 4.0,
+                memory_limit_gb: 4.0,
+                storage_total_gb: 20.0,
+            },
+            network_policy: TenantNetworkPolicy {
+                default_inter_tenant_ingress: InterTenantIngressPolicy::DenyAll,
+                default_internet_egress: InternetEgressPolicy::AllowAll,
+            },
+            labels_or_tags: HashMap::new(),
+        }
+    }
+}
+
+#[derive(Debug, Clone, PartialEq, Serialize, Deserialize, Default)]
+pub struct ResourceLimits {
+    /// Requested/guaranteed CPU cores (e.g., 2.0).
+    pub cpu_request_cores: f32,
+    /// Maximum CPU cores the tenant can burst to (e.g., 4.0).
+    pub cpu_limit_cores: f32,
+
+    /// Requested/guaranteed memory in Gigabytes (e.g., 8.0).
+    pub memory_request_gb: f32,
+    /// Maximum memory in Gigabytes tenant can burst to (e.g., 16.0).
+    pub memory_limit_gb: f32,
+
+    /// Total persistent storage allocation in Gigabytes across all volumes.
+    pub storage_total_gb: f32,
+}
+
+#[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
+pub struct TenantNetworkPolicy {
+    /// Policy for ingress traffic originating from other tenants within the same Harmony-managed environment.
+    pub default_inter_tenant_ingress: InterTenantIngressPolicy,
+
+    /// Policy for egress traffic destined for the public internet.
+    pub default_internet_egress: InternetEgressPolicy,
+}
+
+#[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
+pub enum InterTenantIngressPolicy {
+    /// Deny all traffic from other tenants by default.
+    DenyAll,
+}
+
+#[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
+pub enum InternetEgressPolicy {
+    /// Allow all outbound traffic to the internet.
+    AllowAll,
+    /// Deny all outbound traffic to the internet by default.
+    DenyAll,
+}

harmony/src/modules/helm/chart.rs

@@ -23,7 +23,7 @@ pub struct HelmRepository {
     force_update: bool,
 }
 impl HelmRepository {
-    pub(crate) fn new(name: String, url: Url, force_update: bool) -> Self {
+    pub fn new(name: String, url: Url, force_update: bool) -> Self {
         Self {
             name,
             url,
@@ -104,7 +104,10 @@ impl HelmChartInterpret {
 
 fn run_helm_command(args: &[&str]) -> Result<Output, InterpretError> {
     let command_str = format!("helm {}", args.join(" "));
-    debug!("Got KUBECONFIG: `{}`", std::env::var("KUBECONFIG").unwrap());
+    debug!(
+        "Got KUBECONFIG: `{}`",
+        std::env::var("KUBECONFIG").unwrap_or("".to_string())
+    );
     debug!("Running Helm command: `{}`", command_str);
 
     let output = Command::new("helm")

harmony/src/modules/helm/command.rs

@@ -1,12 +1,9 @@
 use async_trait::async_trait;
 use log::debug;
-use non_blank_string_rs::NonBlankString;
 use serde::Serialize;
 use std::collections::HashMap;
-use std::env::temp_dir;
-use std::ffi::OsStr;
 use std::io::ErrorKind;
-use std::path::{Path, PathBuf};
+use std::path::PathBuf;
 use std::process::{Command, Output};
 use temp_dir::{self, TempDir};
 use temp_file::TempFile;

harmony/src/modules/mod.rs

@@ -12,4 +12,5 @@ pub mod load_balancer;
 pub mod monitoring;
 pub mod okd;
 pub mod opnsense;
+pub mod tenant;
 pub mod tftp;

harmony/src/modules/monitoring/config.rs

@@ -2,7 +2,6 @@ use serde::Serialize;
 
 use super::monitoring_alerting::AlertChannel;
 
-
 #[derive(Debug, Clone, Serialize)]
 pub struct KubePrometheusConfig {
     pub namespace: String,

harmony/src/modules/monitoring/discord_alert_manager.rs

@@ -1,32 +1,29 @@
 use std::str::FromStr;
 
 use non_blank_string_rs::NonBlankString;
+use url::Url;
 
 use crate::modules::helm::chart::HelmChartScore;
 
-use super::{config::KubePrometheusConfig, monitoring_alerting::AlertChannel};
-
-fn get_discord_alert_manager_score(config: &KubePrometheusConfig) -> Option<HelmChartScore> {
-    let (url, name) = config.alert_channel.iter().find_map(|channel| {
-        if let AlertChannel::Discord { webhook_url, name } = channel {
-            Some((webhook_url, name))
-        } else {
-            None
-        }
-    })?;
-
+pub fn discord_alert_manager_score(
+    webhook_url: Url,
+    namespace: String,
+    name: String,
+) -> HelmChartScore {
     let values = format!(
         r#"
 environment:
   - name: "DISCORD_WEBHOOK"
-    value: "{url}"
+    value: "{webhook_url}"
 "#,
     );
 
-    Some(HelmChartScore {
-        namespace: Some(NonBlankString::from_str(&config.namespace).unwrap()),
+    HelmChartScore {
+        namespace: Some(NonBlankString::from_str(&namespace).unwrap()),
         release_name: NonBlankString::from_str(&name).unwrap(),
-        chart_name: NonBlankString::from_str("oci://hub.nationtech.io/library/alertmanager-discord")
+        chart_name: NonBlankString::from_str(
+            "oci://hub.nationtech.io/library/alertmanager-discord",
+        )
         .unwrap(),
         chart_version: None,
         values_overrides: None,
@@ -34,13 +31,5 @@ environment:
         create_namespace: true,
         install_only: true,
         repository: None,
-    })
-}
-
-pub fn discord_alert_manager_score(config: &KubePrometheusConfig) -> HelmChartScore {
-    if let Some(chart) = get_discord_alert_manager_score(config) {
-        chart
-    } else {
-        panic!("Expected discord alert manager helm chart");
     }
 }

harmony/src/modules/monitoring/discord_webhook_sender.rs

@@ -0,0 +1,55 @@
+use async_trait::async_trait;
+use serde_json::Value;
+use url::Url;
+
+use crate::{
+    interpret::{InterpretError, Outcome},
+    topology::K8sAnywhereTopology,
+};
+
+#[derive(Debug, Clone)]
+pub struct DiscordWebhookConfig {
+    pub webhook_url: Url,
+    pub name: String,
+    pub send_resolved_notifications: bool,
+}
+
+pub trait DiscordWebhookReceiver {
+    fn deploy_discord_webhook_receiver(
+        &self,
+        _notification_adapter_id: &str,
+    ) -> Result<Outcome, InterpretError>;
+
+    fn delete_discord_webhook_receiver(
+        &self,
+        _notification_adapter_id: &str,
+    ) -> Result<Outcome, InterpretError>;
+}
+
+// trait used to generate alert manager config values impl<T: Topology + AlertManagerConfig> Monitor for KubePrometheus
+pub trait AlertManagerConfig<T> {
+    fn get_alert_manager_config(&self) -> Result<Value, InterpretError>;
+}
+
+#[async_trait]
+impl<T: DiscordWebhookReceiver> AlertManagerConfig<T> for DiscordWebhookConfig {
+    fn get_alert_manager_config(&self) -> Result<Value, InterpretError> {
+        todo!()
+    }
+}
+
+#[async_trait]
+impl DiscordWebhookReceiver for K8sAnywhereTopology {
+    fn deploy_discord_webhook_receiver(
+        &self,
+        _notification_adapter_id: &str,
+    ) -> Result<Outcome, InterpretError> {
+        todo!()
+    }
+    fn delete_discord_webhook_receiver(
+        &self,
+        _notification_adapter_id: &str,
+    ) -> Result<Outcome, InterpretError> {
+        todo!()
+    }
+}

harmony/src/modules/monitoring/mod.rs

@@ -1,4 +1,5 @@
+mod config;
+mod discord_alert_manager;
+pub mod discord_webhook_sender;
 mod kube_prometheus;
 pub mod monitoring_alerting;
-mod discord_alert_manager;
-mod config;

harmony/src/modules/monitoring/monitoring_alerting.rs

@@ -96,28 +96,28 @@ impl MonitoringAlertingStackInterpret {
         topology: &T,
         config: &KubePrometheusConfig,
     ) -> Result<Outcome, InterpretError> {
-        let mut outcomes = vec![];
+        //let mut outcomes = vec![];
 
-        for channel in &self.score.alert_channel {
-            let outcome = match channel {
-                AlertChannel::Discord { .. } => {
-                    discord_alert_manager_score(config)
-                        .create_interpret()
-                        .execute(inventory, topology)
-                        .await
-                }
-                AlertChannel::Slack { .. } => Ok(Outcome::success(
-                    "No extra configs for slack alerting".to_string(),
-                )),
-                AlertChannel::Smpt { .. } => {
-                    todo!()
-                }
-            };
-            outcomes.push(outcome);
-        }
-        for result in outcomes {
-            result?; 
-        }
+        //for channel in &self.score.alert_channel {
+        //    let outcome = match channel {
+        //        AlertChannel::Discord { .. } => {
+        //            discord_alert_manager_score(config)
+        //                .create_interpret()
+        //                .execute(inventory, topology)
+        //                .await
+        //        }
+        //        AlertChannel::Slack { .. } => Ok(Outcome::success(
+        //            "No extra configs for slack alerting".to_string(),
+        //        )),
+        //        AlertChannel::Smpt { .. } => {
+        //            todo!()
+        //        }
+        //    };
+        //    outcomes.push(outcome);
+        //}
+        //for result in outcomes {
+        //    result?;
+        //}
 
         Ok(Outcome::success("All alert channels deployed".to_string()))
     }

harmony/src/modules/tenant/mod.rs

@@ -0,0 +1,67 @@
+use async_trait::async_trait;
+use serde::Serialize;
+
+use crate::{
+    data::{Id, Version},
+    interpret::{Interpret, InterpretError, InterpretName, InterpretStatus, Outcome},
+    inventory::Inventory,
+    score::Score,
+    topology::{
+        Topology,
+        tenant::{TenantConfig, TenantManager},
+    },
+};
+
+#[derive(Debug, Serialize, Clone)]
+pub struct TenantScore {
+    pub config: TenantConfig,
+}
+
+impl<T: Topology + TenantManager> Score<T> for TenantScore {
+    fn create_interpret(&self) -> Box<dyn crate::interpret::Interpret<T>> {
+        Box::new(TenantInterpret {
+            tenant_config: self.config.clone(),
+        })
+    }
+
+    fn name(&self) -> String {
+        format!("{} TenantScore", self.config.name)
+    }
+}
+
+#[derive(Debug)]
+pub struct TenantInterpret {
+    tenant_config: TenantConfig,
+}
+
+#[async_trait]
+impl<T: Topology + TenantManager> Interpret<T> for TenantInterpret {
+    async fn execute(
+        &self,
+        _inventory: &Inventory,
+        topology: &T,
+    ) -> Result<Outcome, InterpretError> {
+        topology.provision_tenant(&self.tenant_config).await?;
+
+        Ok(Outcome::success(format!(
+            "Successfully provisioned tenant {} with id {}",
+            self.tenant_config.name, self.tenant_config.id
+        )))
+    }
+
+    fn get_name(&self) -> InterpretName {
+        InterpretName::TenantInterpret
+    }
+
+    fn get_version(&self) -> Version {
+        todo!()
+    }
+
+    fn get_status(&self) -> InterpretStatus {
+        todo!()
+    }
+
+    fn get_children(&self) -> Vec<Id> {
+        todo!()
+    }
+}