feat: Enhanced Instance Provisioning and Resource Limits by poyrazK · Pull Request #51 · poyrazK/thecloud

poyrazK · 2026-02-09T19:58:37Z

This PR introduces several enhancements to the instance provisioning logic:

Domain Models: Added CPULimit, MemoryLimit, DiskLimit, Env, Cmd, and VolumeBinds to the Instance and ProvisionJob entities.
Service Layer: Refactored InstanceService to use a structured LaunchParams object, allowing for more flexible provisioning.
Repository Layer: Updated PostgreSQL repository to handle new configuration fields and added a migration.
K8s Provisioner: Fixed High Availability (HA) Load Balancer cleanup in the Deprovision flow and resolved mock encryption panics in tests.
Docker Adapter: Added shell constant and supported custom commands/env in container creation.
Testing: Cleaned up duplicated literals, renamed test functions to follow conventions, and added 082 migration scripts.
API: Updated the instances endpoint and synced Swagger documentation.

…te port

…tions

…rtAdapter

+		Auth: []ssh.AuthMethod{
+			ssh.PublicKeys(signer),
+		},
+		HostKeyCallback: ssh.InsecureIgnoreHostKey(),


In general, the fix is to replace ssh.InsecureIgnoreHostKey() with a HostKeyCallback that validates the server’s host key against an allow list. The most straightforward and robust approach in Go, when you know the expected host key, is to use ssh.FixedHostKey(pubKey), where pubKey is a ssh.PublicKey parsed from a known‑good public key (for example, obtained out‑of‑band and stored alongside or derived from the private key).

For this specific code, we must avoid changing the overall behavior beyond security. The SSHExecutor already receives a private key string key and parses it to a ssh.Signer used for authentication. We can reuse that signer to derive the corresponding public key used by the server, and feed that into ssh.FixedHostKey. This avoids adding configuration fields or changing the NewSSHExecutor signature. Concretely, in Run:

After signer, err := ssh.ParsePrivateKey([]byte(e.key)), obtain pubKey := signer.PublicKey().

Replace HostKeyCallback: ssh.InsecureIgnoreHostKey(), with HostKeyCallback: ssh.FixedHostKey(pubKey),.

This change remains within internal/repositories/k8s/node_executor.go, uses only already‑imported golang.org/x/crypto/ssh, and doesn’t alter how callers construct SSHExecutor or how commands are executed, other than now failing if the host key doesn’t match the key pair being used.

coderabbitai · 2026-02-09T19:58:46Z

Important

Review skipped

Too many files!

This PR contains 183 files, which is 33 over the limit of 150.

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

Use the checkbox below for a quick retry:

🔍 Trigger review

✨ Finishing touches

🧪 Generate unit tests (beta)

Create PR with unit tests
Post copyable unit tests in a comment
Commit unit tests in branch feature/global-load-balancer

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

Copilot

Pull request overview

This PR enhances instance/cluster provisioning by introducing structured launch parameters, additional instance configuration fields (env/cmd/binds/resource limits/user-data), corresponding DB migrations, and updates across compute backends (Docker/Libvirt), workers, and API/Swagger; it also refactors and parallelizes many tests.

Changes:

Introduce ports.LaunchParams / extended CreateInstanceOptions and thread new provisioning fields through handlers, services, workers, and compute backends.
Add/adjust Postgres migrations for new instance/cluster/load-balancer schema fields and update Swagger specs accordingly.
Refactor and reorganize K8s provisioning (cloud-init templates, SG logic) and broaden test parallelization/cleanup.

Reviewed changes

Copilot reviewed 182 out of 183 changed files in this pull request and generated 11 comments.

Show a summary per file

File	Description
tests/gateway_e2e_test.go	Improves assertions/diagnostics for gateway E2E route creation and response decoding
scripts/test_libvirt.go	Updates libvirt adapter call to `LaunchInstanceWithOptions`
internal/workers/provision_worker_test.go	Updates failing backend mock to new compute method name
internal/workers/provision_worker.go	Passes full `ProvisionJob` into instance provisioning
internal/repositories/postgres/vpc_repo_unit_test.go	Marks tests/subtests parallel
internal/repositories/postgres/secret_repo_unit_test.go	Marks tests/subtests parallel
internal/repositories/postgres/rbac_repo_unit_test.go	Marks tests parallel
internal/repositories/postgres/notify_repo_unit_test.go	Marks tests parallel
internal/repositories/postgres/migrator_unit_test.go	Adds `t.Parallel()` and whitespace cleanup
internal/repositories/postgres/migrations/082_add_instance_config_fields.up.sql	Adds instance config columns (binds/env/cmd/resource limits)
internal/repositories/postgres/migrations/082_add_instance_config_fields.down.sql	Drops instance config columns
internal/repositories/postgres/migrations/081_fix_clusters_table.up.sql	Adds/migrates missing cluster columns
internal/repositories/postgres/migrations/081_fix_clusters_table.down.sql	Drops added cluster columns
internal/repositories/postgres/migrations/080_add_lb_ip.up.sql	Adds LB `ip` column (idempotent)
internal/repositories/postgres/migrations/080_add_lb_ip.down.sql	Drops LB `ip` column
internal/repositories/postgres/migrations/078_add_api_key_expiry.up.sql	Makes `expires_at` column add idempotent
internal/repositories/postgres/migrations/077_add_gateway_methods.up.sql	Makes gateway methods/index/constraint creation idempotent
internal/repositories/postgres/migrations/076_add_gateway_pattern_matching.up.sql	Makes gateway pattern-matching column adds idempotent
internal/repositories/postgres/migrations/071_add_tenant_id_to_resources.up.sql	Simplifies table-existence checks for tenant-id migration
internal/repositories/postgres/migrations/070_create_tenants.up.sql	Makes default tenant-id column adds idempotent
internal/repositories/postgres/migrations/060_bucket_encryption.up.sql	Makes encryption columns idempotent
internal/repositories/postgres/migrations/058_add_object_versioning.up.sql	Makes object versioning columns idempotent; drops alt constraint defensively
internal/repositories/postgres/migrations/058_add_object_versioning.down.sql	Makes constraint re-add defensive in down migration
internal/repositories/postgres/migrations/054_extend_clusters_v2_2.up.sql	Makes cluster/LB column adds idempotent
internal/repositories/postgres/migrations/054_extend_clusters_v2_2.down.sql	Makes cluster/LB column drops idempotent
internal/repositories/postgres/migrations/053_add_cluster_network_isolation.up.sql	Makes network_isolation column add idempotent
internal/repositories/postgres/migrations/053_add_cluster_network_isolation.down.sql	Makes network_isolation column drop idempotent
internal/repositories/postgres/migrations/036_add_volume_backend_path.up.sql	Makes backend_path column add idempotent
internal/repositories/postgres/migrations/032_add_instance_network_fields.up.sql	Makes instance network column adds idempotent
internal/repositories/postgres/migrations/020_create_clusters.up.sql	Adds new “fresh install” clusters/cluster_nodes schema
internal/repositories/postgres/migrations/020_create_clusters.down.sql	Drops clusters/cluster_nodes tables
internal/repositories/postgres/migrations/014_resource_scoping.up.sql	Makes user_id column adds idempotent
internal/repositories/postgres/migrations/013_create_users_table.up.sql	Makes api_keys FK creation defensive
internal/repositories/postgres/migrations/012_add_failure_tracking.up.sql	Makes failure-tracking columns idempotent; cleans formatting
internal/repositories/postgres/migrations/006_create_vpcs_table.up.sql	Makes instances.vpc_id add idempotent
internal/repositories/postgres/migrations/003_add_container_id.up.sql	Makes container_id add idempotent
internal/repositories/postgres/migrations/003_add_container_id.down.sql	Makes container_id drop idempotent
internal/repositories/postgres/lifecycle_repo_unit_test.go	Marks tests/subtests parallel
internal/repositories/postgres/image_repo_unit_test.go	Marks tests parallel
internal/repositories/postgres/identity_repo_unit_test.go	Marks tests parallel
internal/repositories/postgres/helper_test.go	Adds placeholder test file for package
internal/repositories/postgres/function_repo_unit_test.go	Marks tests parallel and formats literals
internal/repositories/postgres/encryption_repo_unit_test.go	Marks tests/subtests parallel
internal/repositories/postgres/database_repo_unit_test.go	Marks tests parallel
internal/repositories/postgres/cron_repo_unit_test.go	Marks tests parallel
internal/repositories/postgres/container_repo_unit_test.go	Marks tests/subtests parallel
internal/repositories/postgres/cluster_repo_unit_test.go	Updates cluster repo expectations + parallelizes subtests
internal/repositories/postgres/accounting_repo_unit_test.go	Marks tests parallel
internal/repositories/noop/adapters_test.go	Updates method name to `LaunchInstanceWithOptions`
internal/repositories/libvirt/templates_test.go	Adds integration build tag + parallelizes
internal/repositories/libvirt/mock_client_test.go	Adds integration build tag
internal/repositories/libvirt/adapter_volume_test.go	Adds integration build tag + parallelizes
internal/repositories/libvirt/adapter_test.go	Adds integration build tag + parallelizes
internal/repositories/libvirt/adapter_network_test.go	Adds integration build tag + parallelizes
internal/repositories/libvirt/adapter_lifecycle_test.go	Adds integration build tag + parallelizes; updates method name
internal/repositories/libvirt/adapter_context_test.go	Adds integration build tag + parallelizes; updates method name
internal/repositories/libvirt/adapter.go	Renames create method, adds StartInstance, extends cloud-init generation with user-data passthrough
internal/repositories/k8s/templates/worker.yaml	Adds cloud-init template for worker bootstrap/join
internal/repositories/k8s/templates/control_plane.yaml	Adds cloud-init template for control-plane bootstrap/init
internal/repositories/k8s/security_test.go	Deleted (k8s SG/base-security tests removed)
internal/repositories/k8s/security.go	Refactors SG naming/rules and creation logic
internal/repositories/k8s/provisioner_all_test.go	Deleted (large K8s provisioner test removed)
internal/repositories/k8s/node_executor_test.go	Normalizes shell invocation in tests
internal/repositories/k8s/mocks_test.go	Adds local mocks for k8s package tests
internal/repositories/k8s/mock_provisioner.go	Deleted (old mock provisioner removed)
internal/repositories/k8s/kubeadm.go	Deleted (old kubeadm helpers removed)
internal/repositories/k8s/health_test.go	Updates mocks/constants; switches kubeconfig retrieval to secret decryption
internal/repositories/k8s/ha_test.go	Deleted (HA-related tests removed)
internal/repositories/k8s/export_test.go	Deleted (export helpers removed)
internal/repositories/k8s/cni_test.go	Deleted (CNI tests removed)
internal/repositories/k8s/cni.go	Deleted (CNI logic removed)
internal/repositories/docker/stats_test.go	Updates adapter ctor signature + method name changes
internal/repositories/docker/fakes_test.go	Adds call counting + mutex for thread-safe fake assertions
internal/repositories/docker/adapter_unit_test.go	Updates method names/ctor signature; adds UserData unit test
internal/repositories/docker/adapter_test.go	Updates ctor signature/method name; adds integration UserData bootstrap check
internal/handlers/ws/ws_test.go	Parallelizes WS tests
internal/handlers/ws/hub_test.go	Parallelizes hub tests
internal/handlers/ws/client_test.go	Parallelizes client tests
internal/handlers/vpc_handler_test.go	Parallelizes handler tests
internal/handlers/volume_handler_test.go	Parallelizes handler tests
internal/handlers/tenant_handler_test.go	Parallelizes handler tests
internal/handlers/subnet_handler_test.go	Parallelizes handler tests
internal/handlers/storage_handler_errors_test.go	Parallelizes test + subtests
internal/handlers/stack_handler_test.go	Parallelizes handler tests
internal/handlers/snapshot_handler_test.go	Parallelizes handler tests
internal/handlers/security_group_handler_test.go	Parallelizes handler tests
internal/handlers/secret_handler_test.go	Parallelizes handler tests
internal/handlers/rbac_handler_test.go	Parallelizes handler tests
internal/handlers/queue_handler_test.go	Parallelizes handler tests
internal/handlers/notify_handler_test.go	Re-formats constants; parallelizes tests/subtests
internal/handlers/lifecycle_handler_test.go	Parallelizes handler tests
internal/handlers/lb_handler_test.go	Parallelizes handler tests
internal/handlers/instance_type_handler_test.go	Parallelizes handler test
internal/handlers/instance_handler.go	Extends launch request fields and uses `ports.LaunchParams`
internal/handlers/image_handler_test.go	Parallelizes handler tests
internal/handlers/identity_handler_test.go	Parallelizes handler tests
internal/handlers/helper_test.go	Parallelizes helper tests
internal/handlers/health_handler_test.go	Parallelizes health handler tests
internal/handlers/global_lb_handler_test.go	Parallelizes GLB handler tests
internal/handlers/gateway_handler_test.go	Parallelizes gateway handler tests
internal/handlers/function_handler_test.go	Re-formats constants; parallelizes tests/subtests
internal/handlers/event_handler_test.go	Parallelizes event handler test
internal/handlers/dns_handler_test.go	Parallelizes DNS handler tests
internal/handlers/database_handler_test.go	Re-formats constants; parallelizes tests/subtests
internal/handlers/dashboard_handler_test.go	Parallelizes dashboard handler tests
internal/handlers/cron_handler_test.go	Re-formats constants; parallelizes tests/subtests
internal/handlers/container_handler_test.go	Parallelizes container handler tests/subtests
internal/handlers/cluster_handler_test.go	Parallelizes cluster handler tests
internal/handlers/cache_handler_test.go	Parallelizes cache handler tests
internal/handlers/autoscaling_handler_test.go	Parallelizes autoscaling handler tests/subtests
internal/handlers/auth_handler_test.go	Parallelizes auth handler tests
internal/handlers/audit_handler_test.go	Parallelizes audit handler test
internal/handlers/accounting_handler_test.go	Parallelizes accounting handler tests
internal/core/services/volume_test.go	Updates service calls to `LaunchParams` / `ProvisionJob`
internal/core/services/stack_test.go	Parallelizes stack service tests
internal/core/services/stack.go	Updates instance launch to `LaunchParams`
internal/core/services/shared_test.go	Updates instance service/compute backend mocks to new signatures
internal/core/services/scale_test.go	Updates benchmark launches to `LaunchParams`
internal/core/services/rbac_cached_test.go	Parallelizes cached RBAC tests
internal/core/services/loadbalancer_service_test.go	Parallelizes LB service tests
internal/core/services/lifecycle_svc_test.go	Parallelizes lifecycle service tests
internal/core/services/lb_worker_test.go	Parallelizes LB worker tests
internal/core/services/instance_ports_test.go	Parallelizes instance ports tests
internal/core/services/instance_internal_test.go	Parallelizes instance internal tests
internal/core/services/health_test.go	Updates Docker adapter ctor signature
internal/core/services/global_lb_test.go	Parallelizes GLB service tests
internal/core/services/function_test.go	Updates Docker adapter ctor signature
internal/core/services/database_test.go	Updates Docker adapter ctor signature
internal/core/services/database.go	Updates compute call to `LaunchInstanceWithOptions`
internal/core/services/dashboard_test.go	Parallelizes dashboard service tests
internal/core/services/cron_worker_test.go	Parallelizes cron worker tests
internal/core/services/container_worker_test.go	Parallelizes container worker tests
internal/core/services/container_worker.go	Updates instance launch to `LaunchParams`
internal/core/services/container_test.go	Updates `Provision` invocation to `ProvisionJob`
internal/core/services/cluster_test.go	Parallelizes cluster service tests; updates kubeconfig field name
internal/core/services/cluster_lifecycle_test.go	Parallelizes cluster lifecycle tests
internal/core/services/cluster.go	Adds Pod/Service CIDR defaults; migrates to encrypted kubeconfig field
internal/core/services/cached_identity_test.go	Parallelizes cached identity tests
internal/core/services/cache_test.go	Updates Docker adapter ctor signature
internal/core/services/cache.go	Updates compute call to `LaunchInstanceWithOptions`
internal/core/services/benchmarks_test.go	Updates benchmarks to `LaunchParams`
internal/core/services/autoscaling_worker_test.go	Parallelizes autoscaling worker tests
internal/core/services/autoscaling_worker.go	Updates instance launch to `LaunchParams`
internal/core/services/autoscaling_test.go	Updates `Provision` invocation to `ProvisionJob`
internal/core/ports/mocks/common_mocks.go	Adds SecretService mock
internal/core/ports/instance.go	Introduces `LaunchParams`; expands InstanceService interface
internal/core/ports/compute_options.go	Adds `UserData` to instance create options
internal/core/ports/compute.go	Renames compute create method; adds StartInstance
internal/core/ports/cluster.go	Adds PodCIDR/ServiceCIDR to cluster create params
internal/core/domain/ws_event_test.go	Parallelizes domain tests
internal/core/domain/security_group_test.go	Parallelizes domain tests
internal/core/domain/jobs.go	Extends `ProvisionJob` with provisioning config fields
internal/core/domain/instance.go	Extends Instance model with binds/env/cmd/resource limits
internal/core/domain/domain_test.go	Parallelizes domain constants test
internal/core/domain/dns_test.go	Parallelizes DNS domain tests
internal/core/domain/cluster.go	Expands cluster/node domain models (networking + encrypted secrets fields)
internal/api/setup/infrastructure.go	Updates Docker backend init to accept logger
docs/swagger/swagger.yaml	Syncs schemas/description for new fields
docs/swagger/swagger.json	Syncs schemas/description for new fields
docs/swagger/docs.go	Syncs embedded swagger doc template for new fields
cmd/cloud/queue_cli_test.go	Fixes indentation/formatting in CLI tests
.github/workflows/ci.yml	Deploy staging on feature branches; add branch-name image tagging

Comments suppressed due to low confidence (1)

internal/handlers/instance_handler.go:92

validateLaunchRequest() doesn’t validate the newly added provisioning fields (VolumeBinds/Env/Cmd and CPULimit/MemoryLimit/DiskLimit). This allows negative/invalid limits or malformed env/cmd entries to reach the service layer. Add explicit validation (e.g., non-negative limits; reasonable max lengths/counts; optional format checks for env like KEY=VALUE).

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Copilot · 2026-02-09T20:15:39Z

@@ -316,6 +316,7 @@ jobs:
          push: true
          tags: |
            ghcr.io/${{ steps.repo_name.outputs.REPO_LC }}:staging
+            ghcr.io/${{ steps.repo_name.outputs.REPO_LC }}:${{ github.ref_name }}
            ghcr.io/${{ steps.repo_name.outputs.REPO_LC }}:${{ github.sha }}


Tagging images with github.ref_name will produce invalid Docker tags for branches like "feature/foo" ("/" is not allowed in tags). Sanitize the ref name (e.g., replace "/" with "-"), or use a safe identifier (sha, short sha, or a slug output) for tags.

Copilot · 2026-02-09T20:15:40Z

+CREATE TABLE IF NOT EXISTS clusters (
+    id UUID PRIMARY KEY,
+    user_id UUID NOT NULL REFERENCES users(id),
+    vpc_id UUID NOT NULL REFERENCES vpcs(id),
+    name VARCHAR(255) NOT NULL,
+    version VARCHAR(50) NOT NULL DEFAULT 'v1.29.0',


Duplicate migration prefix "020_" is already used by 020_create_notify.up.sql, so ordering depends on lexicographic filename and the history becomes ambiguous. Consider renumbering to keep migration versions unique, or consolidating/retiring the older clusters migration (037_create_clusters_table) to avoid long-term confusion.

Copilot · 2026-02-09T20:15:40Z

+      kind: ClusterConfiguration
+      kubernetesVersion: stable
+      controlPlaneEndpoint: "{{ if .HAEnabled }}{{ .LBAddress }}{{ else }}localhost{{ end }}:6443"
+      networking:
+        podSubnet: "{{ .PodCIDR }}"


controlPlaneEndpoint is set to localhost when HA is disabled, which will make the generated admin kubeconfig point to https://localhost:6443 and break remote access (and may affect cert SANs). Use the control-plane node address (or a provided API server address) instead of localhost.

Copilot · 2026-02-09T20:15:40Z

+      apiVersion: kubeadm.k8s.io/v1beta3
+      kind: ClusterConfiguration
+      kubernetesVersion: stable
+      controlPlaneEndpoint: "{{ if .HAEnabled }}{{ .LBAddress }}{{ else }}localhost{{ end }}:6443"


The kubeadm config uses kubernetesVersion: stable, but ClusterService allows selecting a version. This will ignore the requested version and may cause unexpected upgrades. Pass/render an explicit version (e.g., cluster.Version) into the template instead of "stable".

Copilot · 2026-02-09T20:15:41Z

+  # Install Containerd
+  - curl -fsSL https://download.docker.com/linux/ubuntu/gpg | gpg --dearmor -o /etc/apt/keyrings/docker.gpg
+  - echo "deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker.gpg] https://download.docker.com/linux/ubuntu $(lsb_release -cs) stable" | tee /etc/apt/sources.list.d/docker.list > /dev/null
+  - apt-get update
+  - apt-get install -y containerd.io


These commands write to /etc/apt/keyrings/*.gpg but the directory may not exist on a fresh Ubuntu image. Create /etc/apt/keyrings (e.g., mkdir -p /etc/apt/keyrings) before running gpg --dearmor to avoid provisioning failures.

Copilot · 2026-02-09T20:15:41Z

@@ -0,0 +1,3 @@
+package postgres
+
+// Dont remove this file


Spelling: "Dont" -> "Don't" (and consider adding a short reason why this file must exist).

Copilot · 2026-02-09T20:15:42Z

+	sg, err := p.sgSvc.GetGroup(ctx, sgName, cluster.VpcID)
+	if err == nil && sg != nil {
+		return nil
 	}

-	// Create
-	sg, err := p.sgSvc.CreateGroup(ctx, cluster.VpcID, sgName, "Kubernetes cluster security group")
+	p.logger.Info("creating cluster security group", "sg_name", sgName)
+	newSG, err := p.sgSvc.CreateGroup(ctx, cluster.VpcID, sgName, "Managed security group for K8s cluster "+cluster.Name)
 	if err != nil {
-		return err
+		return fmt.Errorf("failed to create security group: %w", err)


ensureClusterSecurityGroup() creates a new security group on any GetGroup error. This can mask real failures (e.g., DB/network) and potentially create duplicates. Consider only creating when the error is a definite "not found" case; otherwise return/wrap the GetGroup error.

Copilot · 2026-02-09T20:15:42Z

+	// Add default rules (K8s control plane ports)
 	rules := []domain.SecurityRule{
-		{Protocol: "tcp", PortMin: 6443, PortMax: 6443, CIDR: AnyCIDR, Direction: domain.RuleIngress, Priority: 100},   // API Server
-		{Protocol: "udp", PortMin: 4789, PortMax: 4789, CIDR: AnyCIDR, Direction: domain.RuleIngress, Priority: 100},   // VXLAN
-		{Protocol: "tcp", PortMin: 179, PortMax: 179, CIDR: AnyCIDR, Direction: domain.RuleIngress, Priority: 100},     // BGP
-		{Protocol: "tcp", PortMin: 10250, PortMax: 10250, CIDR: AnyCIDR, Direction: domain.RuleIngress, Priority: 100}, // Kubelet
-		{Protocol: "tcp", PortMin: 30000, PortMax: 32767, CIDR: AnyCIDR, Direction: domain.RuleIngress, Priority: 100}, // NodePort TCP
-		{Protocol: "udp", PortMin: 30000, PortMax: 32767, CIDR: AnyCIDR, Direction: domain.RuleIngress, Priority: 100}, // NodePort UDP
-	}
-
-	for _, r := range rules {
-		_, _ = p.sgSvc.AddRule(ctx, sg.ID, r)
+		{Direction: domain.RuleIngress, Protocol: "tcp", PortMin: 6443, PortMax: 6443, CIDR: "0.0.0.0/0"},
+		{Direction: domain.RuleIngress, Protocol: "tcp", PortMin: 22, PortMax: 22, CIDR: "0.0.0.0/0"},
+		{Direction: domain.RuleIngress, Protocol: "tcp", PortMin: 2379, PortMax: 2380, CIDR: "10.0.0.0/8"},   // etcd (internal)
+		{Direction: domain.RuleIngress, Protocol: "tcp", PortMin: 10250, PortMax: 10250, CIDR: "10.0.0.0/8"}, // kubelet
 	}

-	return nil
-}
-
-func (p *KubeadmProvisioner) applyBaseSecurity(ctx context.Context, cluster *domain.Cluster, masterIP string) error {
-	exec, err := p.getExecutor(ctx, cluster, masterIP)
-	if err != nil {
-		return err
-	}
-
-	p.logger.Info("applying base security manifests", "ip", masterIP, "isolation", cluster.NetworkIsolation)
-
-	var securityManifests string
-	if cluster.NetworkIsolation {
-		// Apply a default-deny ingress policy for the default namespace
-		securityManifests = `
-apiVersion: networking.k8s.io/v1
-kind: NetworkPolicy
-metadata:
-  name: default-deny-ingress
-  namespace: default
-spec:
-  podSelector: {}
-  policyTypes:
-  - Ingress
-`
-	}
-	if securityManifests != "" {
-		manifestFile := "/tmp/base-security.yaml"
-		_, _ = exec.Run(ctx, fmt.Sprintf("cat <<EOF > %s\n%s\nEOF", manifestFile, securityManifests))
-		_, err = exec.Run(ctx, fmt.Sprintf("%s apply -f %s", kubectlBase, manifestFile))
-		return err
+	for _, rule := range rules {
+		_, _ = p.sgSvc.AddRule(ctx, newSG.ID, rule)
 	}


Errors from AddRule are ignored, so the cluster may proceed with an incomplete/incorrect security group configuration. Handle and return/report AddRule errors (and consider cleanup/rollback if rule creation fails).

Copilot · 2026-02-09T20:15:42Z

 	rules := []domain.SecurityRule{
-		{Protocol: "tcp", PortMin: 6443, PortMax: 6443, CIDR: AnyCIDR, Direction: domain.RuleIngress, Priority: 100},   // API Server
-		{Protocol: "udp", PortMin: 4789, PortMax: 4789, CIDR: AnyCIDR, Direction: domain.RuleIngress, Priority: 100},   // VXLAN
-		{Protocol: "tcp", PortMin: 179, PortMax: 179, CIDR: AnyCIDR, Direction: domain.RuleIngress, Priority: 100},     // BGP
-		{Protocol: "tcp", PortMin: 10250, PortMax: 10250, CIDR: AnyCIDR, Direction: domain.RuleIngress, Priority: 100}, // Kubelet
-		{Protocol: "tcp", PortMin: 30000, PortMax: 32767, CIDR: AnyCIDR, Direction: domain.RuleIngress, Priority: 100}, // NodePort TCP
-		{Protocol: "udp", PortMin: 30000, PortMax: 32767, CIDR: AnyCIDR, Direction: domain.RuleIngress, Priority: 100}, // NodePort UDP
-	}
-
-	for _, r := range rules {
-		_, _ = p.sgSvc.AddRule(ctx, sg.ID, r)
+		{Direction: domain.RuleIngress, Protocol: "tcp", PortMin: 6443, PortMax: 6443, CIDR: "0.0.0.0/0"},
+		{Direction: domain.RuleIngress, Protocol: "tcp", PortMin: 22, PortMax: 22, CIDR: "0.0.0.0/0"},
+		{Direction: domain.RuleIngress, Protocol: "tcp", PortMin: 2379, PortMax: 2380, CIDR: "10.0.0.0/8"},   // etcd (internal)
+		{Direction: domain.RuleIngress, Protocol: "tcp", PortMin: 10250, PortMax: 10250, CIDR: "10.0.0.0/8"}, // kubelet


The default rules open SSH (22) and the Kubernetes API (6443) to 0.0.0.0/0. Unless this is strictly intended, this is a high-risk default. Consider restricting to VPC CIDR / admin CIDRs and/or making these CIDRs configurable per cluster.

Copilot · 2026-02-09T20:15:42Z

+  # Install Containerd
+  - curl -fsSL https://download.docker.com/linux/ubuntu/gpg | gpg --dearmor -o /etc/apt/keyrings/docker.gpg
+  - echo "deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker.gpg] https://download.docker.com/linux/ubuntu $(lsb_release -cs) stable" | tee /etc/apt/sources.list.d/docker.list > /dev/null
+  - apt-get update
+  - apt-get install -y containerd.io
+  - mkdir -p /etc/containerd


These commands write to /etc/apt/keyrings/*.gpg but the directory may not exist on a fresh Ubuntu image. Create /etc/apt/keyrings (e.g., mkdir -p /etc/apt/keyrings) before running gpg --dearmor to avoid provisioning failures.

Copilot

Pull request overview

Copilot reviewed 182 out of 183 changed files in this pull request and generated 6 comments.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Copilot · 2026-02-09T20:25:08Z

+CREATE TABLE IF NOT EXISTS clusters (
+    id UUID PRIMARY KEY,
+    user_id UUID NOT NULL REFERENCES users(id),
+    vpc_id UUID NOT NULL REFERENCES vpcs(id),
+    name VARCHAR(255) NOT NULL,
+    version VARCHAR(50) NOT NULL DEFAULT 'v1.29.0',
+    status VARCHAR(50) NOT NULL DEFAULT 'pending',
+    worker_count INT NOT NULL DEFAULT 2,
+    ha_enabled BOOLEAN NOT NULL DEFAULT FALSE,
+    network_isolation BOOLEAN NOT NULL DEFAULT FALSE,
+    -- Networking
+    pod_cidr VARCHAR(50) NOT NULL DEFAULT '10.244.0.0/16',


This repository already contains 020_create_notify.* and 037_create_clusters_table.*. Introducing another 020_create_clusters.* means duplicate migration numbers and multiple “create clusters table” migrations, which can cause schema divergence (fresh DB vs existing DB) given the migrator reruns all .up.sql files without tracking. Prefer a new sequential migration (e.g., 083_...) that alters the existing clusters/cluster_nodes schema in-place.

Copilot · 2026-02-09T20:25:08Z

+	// UserData execution occurs asynchronously in a background goroutine.
+	// A brief pause ensures that the goroutine has sufficient time to initiate its Exec calls.
+	time.Sleep(50 * time.Millisecond)
+
+	// Verify the two-stage bootstrap sequence:
+	// Stage 1: Payload delivery (writing the bootstrap script to the container filesystem).
+	// Stage 2: Bootstrap execution (invoking the script via a background Exec operation).
+	// Each 'Exec' operation sequentially triggers ContainerExecCreate, ContainerExecAttach,
+	// and ContainerExecInspect according to the adapter's implementation.
+	require.Equal(t, 2, cli.CallCount("ContainerExecCreate"), "Expected dual Stage (delivery + execution) Exec invocations")
+	require.Equal(t, 2, cli.CallCount("ContainerExecAttach"), "Expected associated ExecAttach calls for I/O")
+	require.Equal(t, 2, cli.CallCount("ContainerExecInspect"), "Expected ExecInspect calls to verify termination state")
+}


time.Sleep(50ms) makes this test timing-dependent and potentially flaky on slower CI runners. Prefer synchronizing on a deterministic signal (e.g., require.Eventually until the expected call counts are observed, or expose a hook/waitgroup in the adapter for testability).

Copilot · 2026-02-09T20:25:09Z

+	VolumeBinds  []string                  `json:"volume_binds"`
+	Env          []string                  `json:"env"`
+	Cmd          []string                  `json:"cmd"`
+	CPULimit     int64                     `json:"cpu_limit"`
+	MemoryLimit  int64                     `json:"memory_limit"`
+	DiskLimit    int64                     `json:"disk_limit"`


New request fields (cpu_limit, memory_limit, disk_limit) are accepted and forwarded without validation. Negative values (or nonsensical limits) can now reach the service/provisioner layer. Add validation (e.g., must be >= 0, and optionally enforce reasonable upper bounds / units).

Copilot · 2026-02-09T20:25:09Z

@@ -0,0 +1,3 @@
+package postgres
+
+// Dont remove this file


Spelling/grammar: comment should be "Don't remove this file" (and ideally explain why it must exist, e.g., to ensure the package is included in test compilation).

Copilot · 2026-02-09T20:25:09Z

+	// Add default rules (K8s control plane ports)
 	rules := []domain.SecurityRule{
-		{Protocol: "tcp", PortMin: 6443, PortMax: 6443, CIDR: AnyCIDR, Direction: domain.RuleIngress, Priority: 100},   // API Server
-		{Protocol: "udp", PortMin: 4789, PortMax: 4789, CIDR: AnyCIDR, Direction: domain.RuleIngress, Priority: 100},   // VXLAN
-		{Protocol: "tcp", PortMin: 179, PortMax: 179, CIDR: AnyCIDR, Direction: domain.RuleIngress, Priority: 100},     // BGP
-		{Protocol: "tcp", PortMin: 10250, PortMax: 10250, CIDR: AnyCIDR, Direction: domain.RuleIngress, Priority: 100}, // Kubelet
-		{Protocol: "tcp", PortMin: 30000, PortMax: 32767, CIDR: AnyCIDR, Direction: domain.RuleIngress, Priority: 100}, // NodePort TCP
-		{Protocol: "udp", PortMin: 30000, PortMax: 32767, CIDR: AnyCIDR, Direction: domain.RuleIngress, Priority: 100}, // NodePort UDP
-	}
-
-	for _, r := range rules {
-		_, _ = p.sgSvc.AddRule(ctx, sg.ID, r)
+		{Direction: domain.RuleIngress, Protocol: "tcp", PortMin: 6443, PortMax: 6443, CIDR: "0.0.0.0/0"},
+		{Direction: domain.RuleIngress, Protocol: "tcp", PortMin: 22, PortMax: 22, CIDR: "0.0.0.0/0"},
+		{Direction: domain.RuleIngress, Protocol: "tcp", PortMin: 2379, PortMax: 2380, CIDR: "10.0.0.0/8"},   // etcd (internal)
+		{Direction: domain.RuleIngress, Protocol: "tcp", PortMin: 10250, PortMax: 10250, CIDR: "10.0.0.0/8"}, // kubelet
 	}


Security group rules here allow SSH (22) and Kubernetes API server (6443) from 0.0.0.0/0 by default. This is an insecure default and can expose clusters to the public internet. Prefer scoping these CIDRs (e.g., VPC CIDR / admin IP allowlist) and/or make public access an explicit opt-in.

Copilot · 2026-02-09T20:25:09Z


 swagger:
-	@$(HOME)/go/bin/swag init -d cmd/api,internal/handlers -g main.go -o docs/swagger --parseDependency --parseInternal
+	@/Users/poyrazk/go/bin/swag init -d ./ -g cmd/api/main.go -o docs/swagger --parseDependency --parseInternal


The swagger target uses an absolute, user-specific path (/Users/poyrazk/...) which will break for other developers and in CI. Use swag from PATH (or a configurable var like SWAG ?= $(HOME)/go/bin/swag) and keep paths repo-relative.

Copilot

Pull request overview

Copilot reviewed 182 out of 183 changed files in this pull request and generated 4 comments.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Copilot · 2026-02-09T20:37:48Z

+		workerInst, err := p.instSvc.LaunchInstanceWithOptions(ctx, ports.CreateInstanceOptions{
+			Name:      workerName,
+			ImageName: "ubuntu-22.04",
+			NetworkID: cluster.VpcID.String(),
+			UserData:  userData,
+		})


Worker nodes are launched with image name "ubuntu-22.04" while control-plane uses "ubuntu:22.04". "ubuntu-22.04" is not a standard Docker image tag and is likely to fail pulls; consider using the same canonical image reference consistently.

Copilot · 2026-02-09T20:37:48Z

+	// UserData execution occurs asynchronously in a background goroutine.
+	// A brief pause ensures that the goroutine has sufficient time to initiate its Exec calls.
+	time.Sleep(50 * time.Millisecond)
+


This test comment says UserData execution is asynchronous and uses a fixed sleep, but DockerAdapter.handleUserData executes synchronously in LaunchInstanceWithOptions. The sleep is unnecessary and can make the test slower/flakier; consider removing it or switching to require.Eventually only if the implementation is actually async.

Copilot · 2026-02-09T20:37:49Z

@@ -0,0 +1,3 @@
+package postgres
+
+// Dont remove this file


The comment has a typo and is unclear. If the intent is to keep the package’s *_test build working, update the wording (e.g., “Don’t remove this file”) and briefly explain why it’s needed.

Copilot · 2026-02-09T20:37:49Z

+      kubernetesVersion: stable
+      controlPlaneEndpoint: "{{ if .HAEnabled }}{{ .LBAddress }}{{ else }}localhost{{ end }}:6443"
+      networking:
+        podSubnet: "{{ .PodCIDR }}"
+        serviceSubnet: "{{ .ServiceCIDR }}"


When HA is disabled, setting kubeadm controlPlaneEndpoint to "localhost:6443" will produce a kubeconfig/server endpoint that’s not reachable from outside the control-plane node (and may break worker joins). Consider omitting controlPlaneEndpoint unless HA is enabled, or set it to a reachable address (e.g., the node IP) at runtime.

poyrazK added 30 commits February 3, 2026 18:16

refactor: rename CreateInstance to LaunchInstanceWithOptions in compu…

690099e

…te port

feat: add UserData to CreateInstanceOptions

390ccf1

feat: implement UserData support and logging in DockerAdapter

8c8218a

test: update DockerAdapter integration tests for LaunchInstanceWithOp…

f55cee4

…tions

test: update DockerAdapter unit tests

09231df

test: update Docker stats tests

9c6cdac

feat: pass UserData in InstanceService.Provision

1c22f56

refactor: use LaunchInstanceWithOptions in CacheService

5409b65

refactor: use LaunchInstanceWithOptions in DatabaseService

e33151d

refactor: update NoopComputeBackend for LaunchInstanceWithOptions

4ebd4e9

test: update Noop compute tests

2a68d5c

refactor: rename CreateInstance to LaunchInstanceWithOptions in Libvi…

50b06b0

…rtAdapter

test: update Libvirt lifecycle tests

3536477

refactor: pass logger to DockerAdapter initialization

abc702c

feat: add HA and networking fields to Cluster domain

e5e1fd4

feat: add UserData to ProvisionJob

445e3cc

feat: add ClusterProvisioner and ClusterRepository interfaces

6679b9c

feat: add UserData to Provision port

3899fd9

test: update MockComputeBackend for LaunchInstanceWithOptions

6295d06

test: update autoscaling tests for interface changes

9879d9e

feat: implement ClusterService with background provisioning

b6ff8e9

test: update cluster service tests

cf622e2

test: update container service tests

ba41bd7

test: update instance service tests

3d3f921

test: update volume service tests

8f49a83

test: update instance handler tests

ff4905b

feat: implement HA API Server LoadBalancer in KubeadmProvisioner

f13eef8

refactor: remove old bootstrap logic in favor of Cloud-Init

1220c24

refactor: remove old CNI logic

7d4e5fc

refactor: remove old CNI tests

9dd81f0

poyrazK added 9 commits February 9, 2026 13:04

test(repo): update k8s health tests for InstanceService changes

09ae443

test(repo): update k8s provisioner tests for InstanceService changes

0307a25

test(repo): update k8s lifecycle tests for InstanceService change

9cd97fe

test(repo): update k8s mocks for InstanceService changes

15c5f53

test(services): update autoscaling tests for InstanceService changes

324da6f

test(services): update benchmark tests for InstanceService changes

ced01f9

test(services): update container tests for InstanceService changes

d08f61e

test(services): update volume tests for InstanceService changes

7155cd7

refactor(workers): update provision worker for InstanceService changes

94bf39c

Copilot AI review requested due to automatic review settings February 9, 2026 19:58

github-advanced-security AI found potential problems Feb 9, 2026

View reviewed changes

Copilot started reviewing on behalf of poyrazK February 9, 2026 19:59 View session

poyrazK added 2 commits February 9, 2026 23:08

fix(ci): fix flaky tests and align swagger command with CI

2dc46e1

fix(repo): update instance repo tests to match new schema

816050f

Copilot AI reviewed Feb 9, 2026

View reviewed changes

poyrazK added 2 commits February 9, 2026 23:15

fix(repo): pass subnetID as pointer to avoid scan error in mock

023fceb

fix(services): use constant in TestInstanceServiceFailure

e1e3995

Copilot AI review requested due to automatic review settings February 9, 2026 20:17

Copilot started reviewing on behalf of poyrazK February 9, 2026 20:18 View session

Copilot AI reviewed Feb 9, 2026

View reviewed changes

poyrazK added 2 commits February 9, 2026 23:26

fix(ci): fix unit tests and makefile for CI

8e4d2f5

fix(services): fix AssertNotCalled in autoscaling worker test

2ec05e7

Copilot AI review requested due to automatic review settings February 9, 2026 20:28

Copilot started reviewing on behalf of poyrazK February 9, 2026 20:28 View session

ci: update Verify Swagger to use make and show diff

50ffff7

Copilot AI reviewed Feb 9, 2026

View reviewed changes

ci: bump swag version to v1.16.6

265bea0

poyrazK merged commit 7f20697 into main Feb 9, 2026
33 of 35 checks passed

poyrazK deleted the feature/global-load-balancer branch April 12, 2026 15:56

@@ -69,12 +69,14 @@
             		return "", fmt.Errorf("failed to parse private key: %w", err)
             	}
+            	pubKey := signer.PublicKey()
             	config := &ssh.ClientConfig{
             		User: e.user,
             		Auth: []ssh.AuthMethod{
             			ssh.PublicKeys(signer),
             		},
-            		HostKeyCallback: ssh.InsecureIgnoreHostKey(),
+            		HostKeyCallback: ssh.FixedHostKey(pubKey),
             		Timeout:         10 * time.Second,
             	}

Conversation

poyrazK commented Feb 9, 2026

Uh oh!

Check failure

Uh oh!

Copilot Autofix

coderabbitai Bot commented Feb 9, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Review skipped

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Reviewed changes

Uh oh!

Copilot AI Feb 9, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Feb 9, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Feb 9, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Feb 9, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Feb 9, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Feb 9, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Feb 9, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Feb 9, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Feb 9, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Feb 9, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Copilot AI Feb 9, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Feb 9, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Feb 9, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Feb 9, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Feb 9, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Feb 9, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Copilot AI Feb 9, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Feb 9, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Feb 9, 2026

Choose a reason for hiding this comment

Uh oh!

coderabbitai Bot commented Feb 9, 2026 •

edited

Loading