docs: rewrite Rolling deployments doc from Deployment strategies

* fix: format IPv6 addr correclty for HTTP URL

* test: cover changes

* test: refactor

---------

Co-authored-by: gm0stache <gm0stache@noreply.codeberg.org>

.github/workflows/go-tests.yml

@@ -36,6 +36,12 @@ jobs:
           git diff --exit-code ||
             (echo "go.mod or go.sum has changed. Please run 'go mod tidy' and commit the changes." && exit 1)
 
+      - name: Generate docs
+        run: |
+          make cli-docs
+          git diff --exit-code ||
+            (echo "Documentation is out of date. Please run 'make cli-docs' and commit the changes." && exit 1)
+
       - name: Run tests
         run: |
           make ucind-image

.gitignore

@@ -7,6 +7,8 @@
 *.dll
 *.so
 *.dylib
+/uncloud
+/uncloudd
 
 # OS X
 .DS_Store
@@ -37,3 +39,4 @@ node_modules/
 
 # VS Code
 .vscode
+.devcontainer/

AGENTS.md

@@ -1,10 +1,14 @@
-# AI.md - Uncloud Project Guide
+# AGENTS.md - Uncloud Project Guide
 
-This document provides comprehensive information about the Uncloud project for AI assistants to understand the codebase, architecture, and development practices.
+This document provides comprehensive information about the Uncloud project for AI assistants to understand the codebase,
+architecture, and development practices.
 
 ## Project Overview
 
-**Uncloud** is a lightweight clustering and container orchestration tool that enables deployment and management of web applications across cloud VMs and bare metal servers. It creates a secure WireGuard mesh network between Docker hosts and provides automatic service discovery, load balancing, HTTPS ingress, and simple CLI commands for application management.
+**Uncloud** is a lightweight clustering and container orchestration tool that enables deployment and management of web
+applications across cloud VMs and bare metal servers. It creates a secure WireGuard mesh network between Docker hosts
+and provides automatic service discovery, load balancing, HTTPS ingress, and simple CLI commands for application
+management.
 
 ### Key Characteristics
 
@@ -68,29 +72,29 @@ This document provides comprehensive information about the Uncloud project for A
 
 - **`cmd/`**: Contains main applications
 
-  - `uncloud/`: CLI tool with subcommands for machine, service, volume management
-  - `uncloudd/`: Daemon that runs on each machine
-  - `ucind/`: Development cluster management for testing
+    - `uncloud/`: CLI tool with subcommands for machine, service, volume management
+    - `uncloudd/`: Daemon that runs on each machine
+    - `ucind/`: Development cluster management for testing
 
 - **`internal/`**: Internal implementation packages
 
-  - `cli/`: Command-line interface logic
-  - `machine/`: Machine lifecycle and state management
-  - `daemon/`: Daemon implementation and gRPC services
-  - `dns/`: Internal DNS server for service discovery
+    - `cli/`: Command-line interface logic
+    - `machine/`: Machine lifecycle and state management
+    - `daemon/`: Daemon implementation and gRPC services
+    - `dns/`: Internal DNS server for service discovery
 
 - **`pkg/`**: Public API packages for external use
 
-  - `api/`: Core API types and definitions
-  - `client/`: Client libraries for interacting with Uncloud
+    - `api/`: Core API types and definitions
+    - `client/`: Client libraries for interacting with Uncloud
 
 - **`experiment/`**: Experimental features and prototypes
 - **`scripts/`**: Installation and utility scripts
 - **`test/`**: Test suites and test infrastructure
 - **`website/`**: Documentation website (Docusaurus)
 
-  - `landing/`: Landing page
-  - `docs/`: User documentation
+    - `landing/`: Landing page
+    - `docs/`: User documentation
 
 - **`misc/`**: Design documents and guides
 
@@ -100,25 +104,25 @@ This document provides comprehensive information about the Uncloud project for A
 
 ```go
 // Networking and orchestration
-github.com/docker/docker                   // Docker API client
-github.com/docker/compose/v2               // Docker Compose integration
-golang.zx2c4.com/wireguard                 // WireGuard implementation
-github.com/hashicorp/serf                  // Gossip protocol
+github.com/docker/docker // Docker API client
+github.com/docker/compose/v2 // Docker Compose integration
+golang.zx2c4.com/wireguard // WireGuard implementation
+github.com/hashicorp/serf // Gossip protocol
 
 // State management
-github.com/ipfs/go-ds-crdt                 // CRDT distributed storage
-github.com/dgraph-io/badger/v3             // Embedded database
+github.com/ipfs/go-ds-crdt // CRDT distributed storage
+github.com/dgraph-io/badger/v3 // Embedded database
 
 // Web proxy
-github.com/caddyserver/caddy/v2            // HTTP server and reverse proxy
+github.com/caddyserver/caddy/v2 // HTTP server and reverse proxy
 
 // CLI and UX
-github.com/spf13/cobra                     // CLI framework
-github.com/charmbracelet/huh               // Interactive forms
+github.com/spf13/cobra // CLI framework
+github.com/charmbracelet/huh // Interactive forms
 
 // gRPC and networking
 google.golang.org/grpc                     // gRPC framework
-github.com/siderolabs/grpc-proxy           // gRPC proxy for forwarding
+github.com/siderolabs/grpc-proxy // gRPC proxy for forwarding
 ```
 
 ## Development Workflow
@@ -189,9 +193,9 @@ uc context use <name>           # Switch context
 ### Testing
 
 - Test files and locations
-  - Unit tests alongside source files (`*_test.go`)
-  - Integration tests in `test/e2e/`
-  - Test fixtures in `test/fixtures/`
+    - Unit tests alongside source files (`*_test.go`)
+    - Integration tests in `test/e2e/`
+    - Test fixtures in `test/fixtures/`
 - Use table driven tests whenever possible
 
 ### Dependencies
@@ -225,8 +229,8 @@ uc context use <name>           # Switch context
 ### Logs and Monitoring
 
 - Systemd services (getting logs via `journalctl -u SERVICE_NAME`)
-  - `uncloud` -- Uncloud daemon
-  - `uncloud-corrosion` -- Corrosion process
+    - `uncloud` -- Uncloud daemon
+    - `uncloud-corrosion` -- Corrosion process
 - Machine daemon logs
 - Container logs via Docker
 
@@ -247,7 +251,8 @@ uc context use <name>           # Switch context
 - `Makefile`: Build and development tasks
 - `Dockerfile`: Container build instructions forUncloud-in-Docker (used for testing)
 
-This document should help AI assistants understand the project structure, make informed suggestions, and contribute effectively to the Uncloud codebase.
+This document should help AI assistants understand the project structure, make informed suggestions, and contribute
+effectively to the Uncloud codebase.
 
 ## Documentation
 
@@ -255,4 +260,6 @@ Instructions when generating documentation:
 
 - Use conversational language – write as if you were speaking to a friend.
 - Keep sentences simple, optimize for clarity and understanding.
-- Place the subject before the action whenever possible. Example: prefer “The function loads data” over “Data is loaded by the function.”
+- Do not use em dashes (—) or semicolons (;) in sentences. Instead, break complex sentences into simpler ones.
+- Place the subject before the action whenever possible. Example: prefer "The function loads data" over "Data is loaded
+  by the function."

CLAUDE.md

@@ -1 +1 @@
-./AI.md
+./AGENTS.md

README.md

@@ -1,7 +1,7 @@
 <div align="center">
   <img src="./website/landing/images/logo-title.svg#gh-light-mode-only" alt="Uncloud logo"/>
   <img src="./website/landing/images/logo-title-dark.svg#gh-dark-mode-only" alt="Uncloud logo"/>
-  <p><strong>▸ Docker simplicity. Multi-machine power ◂</strong></p>
+  <p><strong>▸ Deploy and scale containerised apps across servers without Swarm or Kubernetes overhead ◂</strong></p>
 
   <p>
     <a href="https://uncloud.run/docs"><img src="https://img.shields.io/badge/Docs-blue.svg?style=for-the-badge&logo=gitbook&logoColor=white" alt="Documentation"></a>
@@ -281,6 +281,16 @@ using the CLI or directly over SSH. They all have the complete cluster state and
 machine is a full backup of your control plane.
 </details>
 
+## 🧪 Interactive tutorials
+
+To give you a chance to play with Uncloud without even leaving your browser, we're providing interactive tutorials and playgrounds on the [iximiuz Labs](https://labs.iximiuz.com/) platform.
+
+Available tutorials:
+
+1. [Setting up a new Uncloud cluster](https://labs.iximiuz.com/tutorials/uncloud-create-cluster-ebebf72b) - the tutorial walks you through creating a new cluster with two machines and then deploying a simple web service to it.
+
+You can also launch the [Uncloud playground](https://labs.iximiuz.com/playgrounds/uncloud-cluster-64523f7c) where you can play with an already initialized Uncloud cluster.
+
 ## 🏗 Project status
 
 Uncloud is currently in active development and is **not ready for production use**. Features may change significantly

cmd/uncloud/context/connection.go

@@ -11,8 +11,9 @@ import (
 
 func NewConnectionCommand() *cobra.Command {
 	cmd := &cobra.Command{
-		Use:   "connection",
-		Short: "Choose a new default connection for the current context.",
+		Use:     "connection",
+		Aliases: []string{"conn"},
+		Short:   "Choose a new default connection for the current context.",
 		RunE: func(cmd *cobra.Command, args []string) error {
 			uncli := cmd.Context().Value("cli").(*cli.CLI)
 			return selectConnection(uncli)

cmd/uncloud/deploy.go

@@ -14,18 +14,20 @@ import (
 	"github.com/psviderski/uncloud/pkg/client"
 	"github.com/psviderski/uncloud/pkg/client/compose"
 	"github.com/psviderski/uncloud/pkg/client/deploy"
+	"github.com/psviderski/uncloud/pkg/client/deploy/operation"
 	"github.com/spf13/cobra"
 )
 
 type deployOptions struct {
 	cli.BuildServicesOptions
 
-	files    []string
-	profiles []string
-	services []string
-	noBuild  bool
-	recreate bool
-	yes      bool
+	files      []string
+	profiles   []string
+	services   []string
+	noBuild    bool
+	recreate   bool
+	skipHealth bool
+	yes        bool
 }
 
 // NewDeployCommand creates a new command to deploy services from a Compose file.
@@ -60,6 +62,10 @@ func NewDeployCommand() *cobra.Command {
 		"One or more Compose profiles to enable.")
 	cmd.Flags().BoolVar(&opts.recreate, "recreate", false,
 		"Recreate containers even if their configuration and image haven't changed.")
+	cmd.Flags().BoolVar(&opts.skipHealth, "skip-health", false,
+		"Skip the monitoring period and health checks after starting new containers. Useful for faster emergency "+
+			"deployments.\n"+
+			"Warning: This may cause downtime if new containers fail to start properly.")
 	cmd.Flags().BoolVarP(&opts.yes, "yes", "y", false,
 		"Auto-confirm deployment plan. Should be explicitly set when running non-interactively,\n"+
 			"e.g., in CI/CD pipelines. [$UNCLOUD_AUTO_CONFIRM]")
@@ -148,9 +154,9 @@ func runDeploy(ctx context.Context, uncli *cli.CLI, opts deployOptions) error {
 		fmt.Println()
 	}
 
-	var strategy deploy.Strategy
-	if opts.recreate {
-		strategy = &deploy.RollingStrategy{ForceRecreate: true}
+	strategy := &deploy.RollingStrategy{
+		ForceRecreate:     opts.recreate,
+		SkipHealthMonitor: opts.skipHealth,
 	}
 	composeDeploy, err := compose.NewDeploymentWithStrategy(ctx, clusterClient, project, strategy)
 	if err != nil {
@@ -198,7 +204,7 @@ func runDeploy(ctx context.Context, uncli *cli.CLI, opts deployOptions) error {
 	}, uncli.ProgressOut(), "Deploying services")
 }
 
-func printPlan(ctx context.Context, cli *client.Client, plan deploy.SequenceOperation) error {
+func printPlan(ctx context.Context, cli *client.Client, plan operation.SequenceOperation) error {
 	for _, op := range plan.Operations {
 		svcPlan, ok := op.(*deploy.Plan)
 		if !ok {

cmd/uncloud/machine/add.go

@@ -8,7 +8,8 @@ import (
 	"strings"
 	"time"
 
-	"github.com/cenkalti/backoff/v4"
+	"github.com/charmbracelet/huh/spinner"
+	"github.com/charmbracelet/lipgloss"
 	"github.com/docker/compose/v2/pkg/progress"
 	"github.com/psviderski/uncloud/cmd/uncloud/caddy"
 	"github.com/psviderski/uncloud/internal/cli"
@@ -16,8 +17,6 @@ import (
 	"github.com/psviderski/uncloud/pkg/api"
 	"github.com/psviderski/uncloud/pkg/client"
 	"github.com/spf13/cobra"
-	"google.golang.org/grpc/codes"
-	"google.golang.org/grpc/status"
 )
 
 type addOptions struct {
@@ -27,6 +26,7 @@ type addOptions struct {
 	publicIP  string
 	sshKey    string
 	version   string
+	yes       bool
 }
 
 func NewAddCommand() *cobra.Command {
@@ -41,6 +41,8 @@ Connection methods:
   ssh+cli://user@host   - Use system SSH command (supports ProxyJump, SSH config)`,
 		Args: cobra.ExactArgs(1),
 		RunE: func(cmd *cobra.Command, args []string) error {
+			cli.BindEnvToFlag(cmd, "yes", "UNCLOUD_AUTO_CONFIRM")
+
 			uncli := cmd.Context().Value("cli").(*cli.CLI)
 
 			// Determine if SSH CLI needs to be used and strip scheme
@@ -88,6 +90,9 @@ Connection methods:
 		&opts.version, "version", "latest",
 		"Version of the Uncloud daemon to install on the machine.",
 	)
+	cmd.Flags().BoolVarP(&opts.yes, "yes", "y", false,
+		"Auto-confirm prompts (e.g., resetting an already initialised machine).\n"+
+			"Should be explicitly set when running non-interactively, e.g., in CI/CD pipelines. [$UNCLOUD_AUTO_CONFIRM]")
 
 	return cmd
 }
@@ -113,6 +118,7 @@ func add(ctx context.Context, uncli *cli.CLI, remoteMachine *cli.RemoteMachine,
 		RemoteMachine: remoteMachine,
 		SkipInstall:   opts.noInstall,
 		Version:       opts.version,
+		AutoConfirm:   opts.yes,
 	})
 	if err != nil {
 		return err
@@ -124,79 +130,97 @@ func add(ctx context.Context, uncli *cli.CLI, remoteMachine *cli.RemoteMachine,
 		return nil
 	}
 
-	// Wait for the cluster to be initialised to be able to deploy the Caddy service.
-	fmt.Println("Waiting for the machine to be ready...")
-	fmt.Println()
-	if err = waitClusterInitialised(ctx, machineClient); err != nil {
-		return fmt.Errorf("wait for cluster to be initialised on machine: %w", err)
+	// Wait for the cluster to be initialised on the machine to be able to deploy the Caddy service.
+	err = spinner.New().
+		Title(" Waiting for the machine to join the cluster...").
+		Type(spinner.MiniDot).
+		Style(lipgloss.NewStyle().Foreground(lipgloss.Color("3"))).
+		TitleStyle(lipgloss.NewStyle()).
+		ActionWithErr(func(ctx context.Context) error {
+			return machineClient.WaitClusterReady(ctx, 5*time.Minute)
+		}).
+		Run()
+	if err != nil {
+		return fmt.Errorf("wait for machine to join the cluster: %w", err)
 	}
+	fmt.Println("Machine joined the cluster.")
 
+	// TODO: scale the existing Caddy service to the new machine instead of running a new deployment
+	//  that may cause a small downtime.
 	// Deploy a Caddy service container to the added machine. If caddy service is already deployed on other machines,
-	// use the deployed image version. Otherwise, use the latest version.
+	// use the deployed image version.
 	// NOTE: We use the cluster client to inspect and scale the Caddy service because the newly added machine may have
 	// issues accessing the Machine API of existing machines in the cluster.
 	// See the issue for more details: https://github.com/psviderski/uncloud/issues/65.
 	caddyImage := ""
 	caddySvc, err := clusterClient.InspectService(ctx, client.CaddyServiceName)
 	if err != nil {
-		if !errors.Is(err, api.ErrNotFound) {
-			return fmt.Errorf("inspect caddy service: %w", err)
+		if errors.Is(err, api.ErrNotFound) {
+			// Caddy service is not deployed.
+			return nil
 		}
-	} else {
-		caddyImage = caddySvc.Containers[0].Container.Config.Image
-		// Find the latest created container and use its image.
-		var latestCreated time.Time
-		for _, c := range caddySvc.Containers[1:] {
-			created, err := time.Parse(time.RFC3339Nano, c.Container.Created)
-			if err != nil {
-				continue
-			}
-			if created.After(latestCreated) {
-				latestCreated = created
-				caddyImage = c.Container.Config.Image
-			}
+		return fmt.Errorf("inspect caddy service: %w", err)
+	}
+	caddyImage = caddySvc.Containers[0].Container.Config.Image
+	// Find the latest created container and use its image.
+	var latestCreated time.Time
+	for _, c := range caddySvc.Containers[1:] {
+		created, err := time.Parse(time.RFC3339Nano, c.Container.Created)
+		if err != nil {
+			continue
+		}
+		if created.After(latestCreated) {
+			latestCreated = created
+			caddyImage = c.Container.Config.Image
 		}
 	}
 
-	// TODO: scale the existing Caddy service to the new machine instead of running a new deployment
-	//  that may cause a small downtime.
 	d, err := clusterClient.NewCaddyDeployment(caddyImage, "", api.Placement{})
 	if err != nil {
 		return fmt.Errorf("create caddy deployment: %w", err)
 	}
 
-	err = progress.RunWithTitle(ctx, func(ctx context.Context) error {
-		if _, err = d.Run(ctx); err != nil {
-			return fmt.Errorf("deploy caddy: %w", err)
-		}
-		return nil
-	}, uncli.ProgressOut(), fmt.Sprintf("Deploying service %s", d.Spec.Name))
+	plan, err := d.Plan(ctx)
 	if err != nil {
-		return err
+		return fmt.Errorf("plan caddy deployment: %w", err)
+	}
+
+	fmt.Println()
+	if len(plan.Operations) == 0 {
+		fmt.Printf("%s service is up to date.\n", client.CaddyServiceName)
+	} else {
+		// Initialise a machine and container name resolver to properly format the plan output.
+		resolver, err := clusterClient.ServiceOperationNameResolver(ctx, caddySvc)
+		if err != nil {
+			return fmt.Errorf("create machine and container name resolver for service operations: %w", err)
+		}
+
+		fmt.Println("caddy deployment plan:")
+		fmt.Println(plan.Format(resolver))
+		fmt.Println()
+
+		if !opts.yes {
+			confirmed, err := cli.Confirm()
+			if err != nil {
+				return fmt.Errorf("confirm deployment: %w", err)
+			}
+			if !confirmed {
+				fmt.Println("Cancelled. No changes were made.")
+				return nil
+			}
+		}
+
+		err = progress.RunWithTitle(ctx, func(ctx context.Context) error {
+			if _, err = d.Run(ctx); err != nil {
+				return fmt.Errorf("deploy caddy: %w", err)
+			}
+			return nil
+		}, uncli.ProgressOut(), fmt.Sprintf("Deploying service %s (%s mode)", d.Spec.Name, d.Spec.Mode))
+		if err != nil {
+			return err
+		}
 	}
 
 	fmt.Println()
 	return caddy.UpdateDomainRecords(ctx, machineClient, uncli.ProgressOut())
 }
-
-func waitClusterInitialised(ctx context.Context, client *client.Client) error {
-	boff := backoff.WithContext(backoff.NewExponentialBackOff(
-		backoff.WithMaxInterval(1*time.Second),
-		backoff.WithMaxElapsedTime(5*time.Minute),
-	), ctx)
-
-	check := func() error {
-		_, err := client.ListMachines(ctx, nil)
-		if err == nil {
-			return nil
-		}
-
-		statusErr := status.Convert(err)
-		if statusErr.Code() == codes.FailedPrecondition {
-			return err
-		}
-		return backoff.Permanent(err)
-	}
-
-	return backoff.Retry(check, boff)
-}

cmd/uncloud/machine/init.go

@@ -5,7 +5,10 @@ import (
 	"fmt"
 	"net/netip"
 	"strings"
+	"time"
 
+	"github.com/charmbracelet/huh/spinner"
+	"github.com/charmbracelet/lipgloss"
 	"github.com/docker/compose/v2/pkg/progress"
 	"github.com/psviderski/uncloud/cmd/uncloud/caddy"
 	"github.com/psviderski/uncloud/cmd/uncloud/dns"
@@ -28,6 +31,7 @@ type initOptions struct {
 	sshKey      string
 	version     string
 	context     string
+	yes         bool
 }
 
 func NewInitCommand() *cobra.Command {
@@ -56,6 +60,8 @@ Connection methods:
 		// TODO: support initialising a cluster on the local machine.
 		Args: cobra.MaximumNArgs(1),
 		RunE: func(cmd *cobra.Command, args []string) error {
+			cli.BindEnvToFlag(cmd, "yes", "UNCLOUD_AUTO_CONFIRM")
+
 			uncli := cmd.Context().Value("cli").(*cli.CLI)
 
 			var remoteMachine *cli.RemoteMachine
@@ -82,6 +88,11 @@ Connection methods:
 			return initCluster(cmd.Context(), uncli, remoteMachine, opts)
 		},
 	}
+
+	cmd.Flags().StringVarP(
+		&opts.context, "context", "c", cli.DefaultContextName,
+		"Name of the new context to be created in the Uncloud config to manage the cluster.",
+	)
 	cmd.Flags().StringVar(&opts.dnsEndpoint, "dns-endpoint", dns.DefaultUncloudDNSAPIEndpoint,
 		"API endpoint for the Uncloud DNS service.")
 	cmd.Flags().StringVarP(
@@ -119,10 +130,9 @@ Connection methods:
 		&opts.version, "version", "latest",
 		"Version of the Uncloud daemon to install on the machine.",
 	)
-	cmd.Flags().StringVarP(
-		&opts.context, "context", "c", cli.DefaultContextName,
-		"Name of the new context to be created in the Uncloud config to manage the cluster.",
-	)
+	cmd.Flags().BoolVarP(&opts.yes, "yes", "y", false,
+		"Auto-confirm prompts (e.g., resetting an already initialised machine).\n"+
+			"Should be explicitly set when running non-interactively, e.g., in CI/CD pipelines. [$UNCLOUD_AUTO_CONFIRM]")
 
 	return cmd
 }
@@ -159,20 +169,34 @@ func initCluster(ctx context.Context, uncli *cli.CLI, remoteMachine *cli.RemoteM
 		RemoteMachine: remoteMachine,
 		SkipInstall:   opts.noInstall,
 		Version:       opts.version,
+		AutoConfirm:   opts.yes,
 	})
 	if err != nil {
 		return err
 	}
 	defer client.Close()
 
+	// Since the cluster API needs a few moments to become ready after cluster initialisation,
+	// we keep the user informed during this wait. We wait here even if no Caddy or DNS is requested
+	// as the cluster needs to be ready so that commands such as 'uc machine ls' work immediately after init.
+	err = spinner.New().
+		Title(" Waiting for the cluster to be ready...").
+		Type(spinner.MiniDot).
+		Style(lipgloss.NewStyle().Foreground(lipgloss.Color("3"))).
+		TitleStyle(lipgloss.NewStyle()).
+		ActionWithErr(func(ctx context.Context) error {
+			return client.WaitClusterReady(ctx, 1*time.Minute)
+		}).
+		Run()
+	if err != nil {
+		return fmt.Errorf("wait for cluster to be ready: %w", err)
+	}
+	fmt.Println("Cluster is ready.")
+
 	if opts.noCaddy && opts.noDNS {
 		return nil
 	}
 
-	// Deploy the Caddy service to the initialised machine.
-	// The creation of a deployment plan talks to cluster API. Since the API needs a few moments to become available
-	// after cluster initialisation, we keep the user informed during this wait.
-	fmt.Println("Waiting for the machine to be ready...")
 	fmt.Println()
 
 	if !opts.noDNS {

cmd/uncloud/main.go

@@ -14,6 +14,7 @@ import (
 	"github.com/psviderski/uncloud/cmd/uncloud/machine"
 	"github.com/psviderski/uncloud/cmd/uncloud/service"
 	"github.com/psviderski/uncloud/cmd/uncloud/volume"
+	"github.com/psviderski/uncloud/cmd/uncloud/wg"
 	"github.com/psviderski/uncloud/internal/cli"
 	"github.com/psviderski/uncloud/internal/cli/config"
 	"github.com/psviderski/uncloud/internal/fs"
@@ -134,6 +135,7 @@ func main() {
 		service.NewStartCommand("service"),
 		service.NewStopCommand("service"),
 		volume.NewRootCommand(),
+		wg.NewRootCommand(),
 	)
 	cobra.CheckErr(cmd.Execute())
 }

cmd/uncloud/ps.go

@@ -205,18 +205,12 @@ func collectContainers(ctx context.Context, cli *client.Client) ([]containerInfo
 
 	var containers []containerInfo
 	for _, msc := range machineContainers {
-		machineName := "unknown"
-
 		// Metadata can be nil if the request was broadcasted to only one machine.
 		if msc.Metadata == nil && len(machineContainers) > 1 {
 			return nil, fmt.Errorf("something went wrong with gRPC proxy: metadata is missing for a machine response")
 		}
-		if msc.Metadata != nil && msc.Metadata.Error != "" {
-			client.PrintWarning(fmt.Sprintf("failed to list containers on machine %s: %s", machineName,
-				msc.Metadata.Error))
-			continue
-		}
 
+		machineName := "unknown"
 		if msc.Metadata != nil {
 			var ok bool
 			machineName, ok = machinesNamesByIP[msc.Metadata.Machine]
@@ -231,6 +225,12 @@ func collectContainers(ctx context.Context, cli *client.Client) ([]containerInfo
 			}
 		}
 
+		if msc.Metadata != nil && msc.Metadata.Error != "" {
+			client.PrintWarning(fmt.Sprintf("failed to list containers on machine %s: %s", machineName,
+				msc.Metadata.Error))
+			continue
+		}
+
 		for _, ctr := range msc.Containers {
 			if ctr.Container.State == nil || ctr.Container.Config == nil {
 				continue

cmd/uncloud/service/exec.go

@@ -59,7 +59,7 @@ If the service has multiple replicas and no container ID is specified, the comma
 
 	execCmd.Flags().BoolVarP(&opts.detach, "detach", "d", false, "Detached mode: run command in the background")
 
-	execCmd.Flags().BoolVarP(&opts.noTty, "no-tty", "T", !cli.IsStdoutTerminal(),
+	execCmd.Flags().BoolVarP(&opts.noTty, "no-tty", "T", false,
 		"Disable pseudo-TTY allocation. By default 'uc exec' allocates a TTY when connected to a terminal.")
 
 	// Keep "-i" and "-t" flags hidden for compatibility with docker exec
@@ -82,6 +82,11 @@ If the service has multiple replicas and no container ID is specified, the comma
 }
 
 func runExec(ctx context.Context, uncli *cli.CLI, serviceName string, command []string, opts execCliOptions) error {
+	// Disable TTY allocation if not connected to a terminal
+	if !cli.IsStdoutTerminal() {
+		opts.noTty = true
+	}
+
 	if !opts.detach {
 		// Check if we're trying to attach to a TTY from a non-TTY client, e.g.
 		// when doing an 'cmd | uc exec ...'

cmd/uncloud/wg/wg.go

@@ -0,0 +1,132 @@
+package wg
+
+import (
+	"context"
+	"fmt"
+	"os"
+	"strings"
+	"text/tabwriter"
+	"time"
+
+	"github.com/docker/go-units"
+	"github.com/psviderski/uncloud/internal/cli"
+	"github.com/spf13/cobra"
+	"golang.zx2c4.com/wireguard/wgctrl/wgtypes"
+	"google.golang.org/grpc/codes"
+	"google.golang.org/grpc/status"
+)
+
+func NewRootCommand() *cobra.Command {
+	cmd := &cobra.Command{
+		Use:   "wg",
+		Short: "Inspect WireGuard network",
+	}
+	cmd.AddCommand(newShowCommand())
+	return cmd
+}
+
+type showOptions struct {
+	machine string
+}
+
+func newShowCommand() *cobra.Command {
+	opts := showOptions{}
+	cmd := &cobra.Command{
+		Use:   "show",
+		Short: "Show WireGuard network configuration for a machine.",
+		Long: "Show the WireGuard network configuration for the machine currently connected to " +
+			"(or specified by the global --connect flag).",
+		Args: cobra.NoArgs,
+		RunE: func(cmd *cobra.Command, args []string) error {
+			uncli := cmd.Context().Value("cli").(*cli.CLI)
+			return runShow(cmd.Context(), uncli, opts)
+		},
+	}
+	cmd.Flags().StringVarP(&opts.machine, "machine", "m", "",
+		"Name or ID of the machine to show the configuration for. (default is connected machine)")
+	return cmd
+}
+
+func runShow(ctx context.Context, uncli *cli.CLI, opts showOptions) error {
+	client, err := uncli.ConnectCluster(ctx)
+	if err != nil {
+		return fmt.Errorf("connection failed: %w", err)
+	}
+	defer client.Close()
+
+	if opts.machine != "" {
+		// Proxy requests to the specified machine.
+		ctx, _, err = client.ProxyMachinesContext(ctx, []string{opts.machine})
+		if err != nil {
+			return err
+		}
+	}
+
+	resp, err := client.MachineClient.InspectWireGuardNetwork(ctx, nil)
+	if err != nil {
+		if status.Code(err) == codes.Unimplemented {
+			return fmt.Errorf("inspect WireGuard network: "+
+				"make sure the target machine is running uncloudd daemon version >= 0.16.0: %w", err)
+		}
+		return err
+	}
+
+	machines, err := client.ListMachines(ctx, nil)
+	if err != nil {
+		return fmt.Errorf("list machines: %w", err)
+	}
+	machinesNamesByPublicKey := make(map[string]string)
+	for _, m := range machines {
+		publicKey := wgtypes.Key(m.Machine.Network.PublicKey).String()
+		machinesNamesByPublicKey[publicKey] = m.Machine.Name
+	}
+
+	// Fetch the machine's name for more descriptive output
+	inspectResp, err := client.MachineClient.InspectMachine(ctx, nil)
+	if err == nil {
+		fmt.Printf("Machine name:         %s\n", inspectResp.Machines[0].Machine.Name)
+	}
+
+	fmt.Printf("WireGuard interface:  %s\n", resp.InterfaceName)
+	fmt.Printf("WireGuard public key: %s\n", wgtypes.Key(resp.PublicKey).String())
+	fmt.Printf("WireGuard port:       %d\n", resp.ListenPort)
+	fmt.Println()
+
+	if len(resp.Peers) == 0 {
+		fmt.Println("No WireGuard peers configured.")
+		return nil
+	}
+
+	tw := tabwriter.NewWriter(os.Stdout, 0, 0, 3, ' ', 0)
+	if _, err = fmt.Fprintln(tw, "PEER\tPUBLIC KEY\tENDPOINT\tHANDSHAKE\tRECEIVED\tSENT\tALLOWED IPS"); err != nil {
+		return fmt.Errorf("write header: %w", err)
+	}
+
+	for _, peer := range resp.Peers {
+		machineName, ok := machinesNamesByPublicKey[wgtypes.Key(peer.PublicKey).String()]
+		if !ok {
+			machineName = "(unknown)"
+		}
+
+		lastHandshake := ""
+		if peer.LastHandshakeTime != nil {
+			lastHandshake = time.Since(peer.LastHandshakeTime.AsTime()).Round(time.Second).String() + " ago"
+		}
+
+		_, err = fmt.Fprintf(
+			tw,
+			"%s\t%s\t%s\t%s\t%s\t%s\t%s\n",
+			machineName,
+			wgtypes.Key(peer.PublicKey).String(),
+			peer.Endpoint,
+			lastHandshake,
+			units.HumanSize(float64(peer.ReceiveBytes)),
+			units.HumanSize(float64(peer.TransmitBytes)),
+			strings.Join(peer.AllowedIps, ", "),
+		)
+		if err != nil {
+			return fmt.Errorf("write row: %w", err)
+		}
+	}
+	return tw.Flush()
+}

go.mod

@@ -66,6 +66,7 @@ require (
 	google.golang.org/grpc v1.74.2
 	google.golang.org/protobuf v1.36.9
 	modernc.org/sqlite v1.36.3
+	tags.cncf.io/container-device-interface v1.0.1
 )
 
 require (
@@ -415,5 +416,4 @@ require (
 	sigs.k8s.io/json v0.0.0-20241010143419-9aa6b5e7a4b3 // indirect
 	sigs.k8s.io/structured-merge-diff/v4 v4.4.2 // indirect
 	sigs.k8s.io/yaml v1.4.0 // indirect
-	tags.cncf.io/container-device-interface v1.0.1 // indirect
 )

internal/cli/cli.go

@@ -162,6 +162,7 @@ type InitClusterOptions struct {
 	RemoteMachine *RemoteMachine
 	SkipInstall   bool
 	Version       string
+	AutoConfirm   bool
 }
 
 // InitCluster initialises a new cluster on a remote machine and returns a client to interact with the cluster.
@@ -197,7 +198,12 @@ func (cli *CLI) initRemoteMachine(ctx context.Context, opts InitClusterOptions)
 		return nil, fmt.Errorf("inspect machine: %w", err)
 	}
 	if minfo.Id != "" {
-		if err = promptResetMachine(ctx, machineClient.MachineClient); err != nil {
+		if !opts.AutoConfirm {
+			if err = promptResetMachine(); err != nil {
+				return nil, err
+			}
+		}
+		if err = resetAndWaitMachine(ctx, machineClient.MachineClient); err != nil {
 			return nil, err
 		}
 	}
@@ -297,6 +303,7 @@ type AddMachineOptions struct {
 	RemoteMachine *RemoteMachine
 	SkipInstall   bool
 	Version       string
+	AutoConfirm   bool
 }
 
 // AddMachine provisions a remote machine and adds it to the cluster. It returns a cluster client and a machine client.
@@ -326,6 +333,7 @@ func (cli *CLI) AddMachine(ctx context.Context, opts AddMachineOptions) (*client
 	}()
 
 	// Check if the machine is already initialised as a cluster member and prompt the user to reset it first.
+	// TODO: refactor to use client.InspectMachine.
 	minfo, err := machineClient.Inspect(ctx, &emptypb.Empty{})
 	if err != nil {
 		return nil, nil, fmt.Errorf("inspect machine: %w", err)
@@ -342,7 +350,12 @@ func (cli *CLI) AddMachine(ctx context.Context, opts AddMachineOptions) (*client
 			return nil, nil, fmt.Errorf("machine is already a member of this cluster (%s)", minfo.Name)
 		}
 
-		if err = promptResetMachine(ctx, machineClient.MachineClient); err != nil {
+		if !opts.AutoConfirm {
+			if err = promptResetMachine(); err != nil {
+				return nil, nil, err
+			}
+		}
+		if err = resetAndWaitMachine(ctx, machineClient.MachineClient); err != nil {
 			return nil, nil, err
 		}
 	}
@@ -393,6 +406,18 @@ func (cli *CLI) AddMachine(ctx context.Context, opts AddMachineOptions) (*client
 		return nil, nil, fmt.Errorf("add machine to cluster (context '%s'): %w", contextName, err)
 	}
 
+	// Get the current store DB version from the cluster to pass to the join request.
+	var storeDBVersion int64
+	inspectResp, err := c.MachineClient.InspectMachine(ctx, &emptypb.Empty{})
+	if err != nil {
+		// TODO(lhf): remove Unimplemented check when v0.17.0 is released.
+		if status.Convert(err).Code() != codes.Unimplemented {
+			return nil, nil, fmt.Errorf("inspect current cluster machine: %w", err)
+		}
+	} else {
+		storeDBVersion = inspectResp.Machines[0].StoreDbVersion
+	}
+
 	// Get the most up-to-date list of other machines in the cluster to include them in the join request.
 	machines, err := c.ListMachines(ctx, nil)
 	if err != nil {
@@ -407,8 +432,9 @@ func (cli *CLI) AddMachine(ctx context.Context, opts AddMachineOptions) (*client
 
 	// Configure the remote machine to join the cluster.
 	joinReq := &pb.JoinClusterRequest{
-		Machine:       addResp.Machine,
-		OtherMachines: otherMachines,
+		Machine:           addResp.Machine,
+		OtherMachines:     otherMachines,
+		MinStoreDbVersion: storeDBVersion,
 	}
 	if _, err = machineClient.JoinCluster(ctx, joinReq); err != nil {
 		return nil, nil, fmt.Errorf("join cluster: %w", err)

internal/cli/config/connection.go

@@ -11,11 +11,6 @@ import (
 	"github.com/psviderski/uncloud/internal/secret"
 )
 
-const (
-	DefaultSSHUser = "root"
-	DefaultSSHPort = 22
-)
-
 type MachineConnection struct {
 	SSH        SSHDestination `yaml:"ssh,omitempty"`
 	SSHCLI     SSHDestination `yaml:"ssh_cli,omitempty"`
@@ -30,7 +25,7 @@ type MachineConnection struct {
 	MachineID string        `yaml:"machine_id,omitempty"`
 }
 
-func (c MachineConnection) String() string {
+func (c *MachineConnection) String() string {
 	if c.SSH != "" {
 		return "ssh://" + string(c.SSH)
 	} else if c.SSHCLI != "" {
@@ -69,36 +64,37 @@ func (c *MachineConnection) Validate() error {
 }
 
 // SSHDestination represents an SSH destination string in the canonical form of "user@host:port".
-// The default user "root" and port 22 can be omitted.
+// Empty user or port components are omitted.
 type SSHDestination string
 
+// NewSSHDestination constructs an SSHDestination from user, host, and port components.
+// If user is empty, it is omitted.
+// If port is 0, it is omitted.
 func NewSSHDestination(user, host string, port int) SSHDestination {
 	dst := host
-	if port != 0 && port != DefaultSSHPort {
+	if port != 0 {
 		dst = net.JoinHostPort(host, strconv.Itoa(port))
 	}
-	if user == "" {
-		user = DefaultSSHUser
+	if user != "" {
+		dst = fmt.Sprintf("%s@%s", user, dst)
 	}
-	dst = user + "@" + dst
+
 	return SSHDestination(dst)
 }
 
+// Parse parses the SSH destination string into user, host, and port components.
+// If user is not specified, it returns an empty string.
+// If port is not specified, it returns 0.
 func (d SSHDestination) Parse() (user string, host string, port int, err error) {
 	host = string(d)
 	if strings.Contains(host, "@") {
 		user, host, _ = strings.Cut(host, "@")
 	}
-	if user == "" {
-		user = DefaultSSHUser
-	}
 	h, p, sErr := net.SplitHostPort(host)
 	if sErr == nil {
 		host = h
 		port, err = strconv.Atoi(p)
 	}
-	if port == 0 {
-		port = DefaultSSHPort
-	}
+
 	return
 }

internal/cli/machine.go

@@ -2,6 +2,7 @@ package cli
 
 import (
 	"context"
+	"errors"
 	"fmt"
 	"os"
 	"strings"
@@ -86,7 +87,13 @@ func provisionMachine(ctx context.Context, exec sshexec.Executor, version string
 	return nil
 }
 
-func promptResetMachine(ctx context.Context, machineClient pb.MachineClient) error {
+func promptResetMachine() error {
+	if !IsStdinTerminal() {
+		return errors.New("the remote machine is already initialised as a cluster member; " +
+			"cannot ask to confirm reset in non-interactive mode, " +
+			"use --yes flag or set UNCLOUD_AUTO_CONFIRM=true to auto-confirm")
+	}
+
 	var confirm bool
 	form := huh.NewForm(
 		huh.NewGroup(
@@ -110,10 +117,15 @@ func promptResetMachine(ctx context.Context, machineClient pb.MachineClient) err
 		return fmt.Errorf("remote machine is already initialised as a cluster member")
 	}
 
+	return nil
+}
+
+func resetAndWaitMachine(ctx context.Context, machineClient pb.MachineClient) error {
 	if _, err := machineClient.Reset(ctx, &pb.ResetRequest{}); err != nil {
 		return fmt.Errorf("reset remote machine: %w. You can also manually run 'uncloud-uninstall' "+
 			"on the remote machine to fully uninstall Uncloud from it", err)
 	}
+
 	fmt.Println("Resetting the remote machine...")
 	if err := waitMachineReady(ctx, machineClient, 1*time.Minute); err != nil {
 		return fmt.Errorf("wait for machine to be ready after reset: %w", err)

internal/machine/api/pb/machine.pb.go

@@ -10,6 +10,7 @@ import (
 	protoreflect "google.golang.org/protobuf/reflect/protoreflect"
 	protoimpl "google.golang.org/protobuf/runtime/protoimpl"
 	emptypb "google.golang.org/protobuf/types/known/emptypb"
+	timestamppb "google.golang.org/protobuf/types/known/timestamppb"
 	reflect "reflect"
 	sync "sync"
 )
@@ -371,6 +372,8 @@ type JoinClusterRequest struct {
 
 	Machine       *MachineInfo   `protobuf:"bytes,1,opt,name=machine,proto3" json:"machine,omitempty"`
 	OtherMachines []*MachineInfo `protobuf:"bytes,3,rep,name=other_machines,json=otherMachines,proto3" json:"other_machines,omitempty"`
+	// Minimum store database version the new machine should sync to before starting cluster operations.
+	MinStoreDbVersion int64 `protobuf:"varint,4,opt,name=min_store_db_version,json=minStoreDbVersion,proto3" json:"min_store_db_version,omitempty"`
 }
 
 func (x *JoinClusterRequest) Reset() {
@@ -419,6 +422,125 @@ func (x *JoinClusterRequest) GetOtherMachines() []*MachineInfo {
 	return nil
 }
 
+func (x *JoinClusterRequest) GetMinStoreDbVersion() int64 {
+	if x != nil {
+		return x.MinStoreDbVersion
+	}
+	return 0
+}
+
+type InspectMachineResponse struct {
+	state         protoimpl.MessageState
+	sizeCache     protoimpl.SizeCache
+	unknownFields protoimpl.UnknownFields
+
+	// Must contain only one repeated messages field to allow broadcasting InspectMachine requests to multiple machines.
+	Machines []*MachineDetails `protobuf:"bytes,1,rep,name=machines,proto3" json:"machines,omitempty"`
+}
+
+func (x *InspectMachineResponse) Reset() {
+	*x = InspectMachineResponse{}
+	if protoimpl.UnsafeEnabled {
+		mi := &file_internal_machine_api_pb_machine_proto_msgTypes[6]
+		ms := protoimpl.X.MessageStateOf(protoimpl.Pointer(x))
+		ms.StoreMessageInfo(mi)
+	}
+}
+
+func (x *InspectMachineResponse) String() string {
+	return protoimpl.X.MessageStringOf(x)
+}
+
+func (*InspectMachineResponse) ProtoMessage() {}
+
+func (x *InspectMachineResponse) ProtoReflect() protoreflect.Message {
+	mi := &file_internal_machine_api_pb_machine_proto_msgTypes[6]
+	if protoimpl.UnsafeEnabled && x != nil {
+		ms := protoimpl.X.MessageStateOf(protoimpl.Pointer(x))
+		if ms.LoadMessageInfo() == nil {
+			ms.StoreMessageInfo(mi)
+		}
+		return ms
+	}
+	return mi.MessageOf(x)
+}
+
+// Deprecated: Use InspectMachineResponse.ProtoReflect.Descriptor instead.
+func (*InspectMachineResponse) Descriptor() ([]byte, []int) {
+	return file_internal_machine_api_pb_machine_proto_rawDescGZIP(), []int{6}
+}
+
+func (x *InspectMachineResponse) GetMachines() []*MachineDetails {
+	if x != nil {
+		return x.Machines
+	}
+	return nil
+}
+
+type MachineDetails struct {
+	state         protoimpl.MessageState
+	sizeCache     protoimpl.SizeCache
+	unknownFields protoimpl.UnknownFields
+
+	Metadata *Metadata    `protobuf:"bytes,1,opt,name=metadata,proto3" json:"metadata,omitempty"`
+	Machine  *MachineInfo `protobuf:"bytes,2,opt,name=machine,proto3" json:"machine,omitempty"`
+	// Current Corrosion cr-sqlite database version (Lamport timestamp) of the cluster store.
+	StoreDbVersion int64 `protobuf:"varint,3,opt,name=store_db_version,json=storeDbVersion,proto3" json:"store_db_version,omitempty"`
+}
+
+func (x *MachineDetails) Reset() {
+	*x = MachineDetails{}
+	if protoimpl.UnsafeEnabled {
+		mi := &file_internal_machine_api_pb_machine_proto_msgTypes[7]
+		ms := protoimpl.X.MessageStateOf(protoimpl.Pointer(x))
+		ms.StoreMessageInfo(mi)
+	}
+}
+
+func (x *MachineDetails) String() string {
+	return protoimpl.X.MessageStringOf(x)
+}
+
+func (*MachineDetails) ProtoMessage() {}
+
+func (x *MachineDetails) ProtoReflect() protoreflect.Message {
+	mi := &file_internal_machine_api_pb_machine_proto_msgTypes[7]
+	if protoimpl.UnsafeEnabled && x != nil {
+		ms := protoimpl.X.MessageStateOf(protoimpl.Pointer(x))
+		if ms.LoadMessageInfo() == nil {
+			ms.StoreMessageInfo(mi)
+		}
+		return ms
+	}
+	return mi.MessageOf(x)
+}
+
+// Deprecated: Use MachineDetails.ProtoReflect.Descriptor instead.
+func (*MachineDetails) Descriptor() ([]byte, []int) {
+	return file_internal_machine_api_pb_machine_proto_rawDescGZIP(), []int{7}
+}
+
+func (x *MachineDetails) GetMetadata() *Metadata {
+	if x != nil {
+		return x.Metadata
+	}
+	return nil
+}
+
+func (x *MachineDetails) GetMachine() *MachineInfo {
+	if x != nil {
+		return x.Machine
+	}
+	return nil
+}
+
+func (x *MachineDetails) GetStoreDbVersion() int64 {
+	if x != nil {
+		return x.StoreDbVersion
+	}
+	return 0
+}
+
 type TokenResponse struct {
 	state         protoimpl.MessageState
 	sizeCache     protoimpl.SizeCache
@@ -430,7 +552,7 @@ type TokenResponse struct {
 func (x *TokenResponse) Reset() {
 	*x = TokenResponse{}
 	if protoimpl.UnsafeEnabled {
-		mi := &file_internal_machine_api_pb_machine_proto_msgTypes[6]
+		mi := &file_internal_machine_api_pb_machine_proto_msgTypes[8]
 		ms := protoimpl.X.MessageStateOf(protoimpl.Pointer(x))
 		ms.StoreMessageInfo(mi)
 	}
@@ -443,7 +565,7 @@ func (x *TokenResponse) String() string {
 func (*TokenResponse) ProtoMessage() {}
 
 func (x *TokenResponse) ProtoReflect() protoreflect.Message {
-	mi := &file_internal_machine_api_pb_machine_proto_msgTypes[6]
+	mi := &file_internal_machine_api_pb_machine_proto_msgTypes[8]
 	if protoimpl.UnsafeEnabled && x != nil {
 		ms := protoimpl.X.MessageStateOf(protoimpl.Pointer(x))
 		if ms.LoadMessageInfo() == nil {
@@ -456,7 +578,7 @@ func (x *TokenResponse) ProtoReflect() protoreflect.Message {
 
 // Deprecated: Use TokenResponse.ProtoReflect.Descriptor instead.
 func (*TokenResponse) Descriptor() ([]byte, []int) {
-	return file_internal_machine_api_pb_machine_proto_rawDescGZIP(), []int{6}
+	return file_internal_machine_api_pb_machine_proto_rawDescGZIP(), []int{8}
 }
 
 func (x *TokenResponse) GetToken() string {
@@ -475,7 +597,7 @@ type ResetRequest struct {
 func (x *ResetRequest) Reset() {
 	*x = ResetRequest{}
 	if protoimpl.UnsafeEnabled {
-		mi := &file_internal_machine_api_pb_machine_proto_msgTypes[7]
+		mi := &file_internal_machine_api_pb_machine_proto_msgTypes[9]
 		ms := protoimpl.X.MessageStateOf(protoimpl.Pointer(x))
 		ms.StoreMessageInfo(mi)
 	}
@@ -488,7 +610,7 @@ func (x *ResetRequest) String() string {
 func (*ResetRequest) ProtoMessage() {}
 
 func (x *ResetRequest) ProtoReflect() protoreflect.Message {
-	mi := &file_internal_machine_api_pb_machine_proto_msgTypes[7]
+	mi := &file_internal_machine_api_pb_machine_proto_msgTypes[9]
 	if protoimpl.UnsafeEnabled && x != nil {
 		ms := protoimpl.X.MessageStateOf(protoimpl.Pointer(x))
 		if ms.LoadMessageInfo() == nil {
@@ -501,7 +623,7 @@ func (x *ResetRequest) ProtoReflect() protoreflect.Message {
 
 // Deprecated: Use ResetRequest.ProtoReflect.Descriptor instead.
 func (*ResetRequest) Descriptor() ([]byte, []int) {
-	return file_internal_machine_api_pb_machine_proto_rawDescGZIP(), []int{7}
+	return file_internal_machine_api_pb_machine_proto_rawDescGZIP(), []int{9}
 }
 
 type Service struct {
@@ -518,7 +640,7 @@ type Service struct {
 func (x *Service) Reset() {
 	*x = Service{}
 	if protoimpl.UnsafeEnabled {
-		mi := &file_internal_machine_api_pb_machine_proto_msgTypes[8]
+		mi := &file_internal_machine_api_pb_machine_proto_msgTypes[10]
 		ms := protoimpl.X.MessageStateOf(protoimpl.Pointer(x))
 		ms.StoreMessageInfo(mi)
 	}
@@ -531,7 +653,7 @@ func (x *Service) String() string {
 func (*Service) ProtoMessage() {}
 
 func (x *Service) ProtoReflect() protoreflect.Message {
-	mi := &file_internal_machine_api_pb_machine_proto_msgTypes[8]
+	mi := &file_internal_machine_api_pb_machine_proto_msgTypes[10]
 	if protoimpl.UnsafeEnabled && x != nil {
 		ms := protoimpl.X.MessageStateOf(protoimpl.Pointer(x))
 		if ms.LoadMessageInfo() == nil {
@@ -544,7 +666,7 @@ func (x *Service) ProtoReflect() protoreflect.Message {
 
 // Deprecated: Use Service.ProtoReflect.Descriptor instead.
 func (*Service) Descriptor() ([]byte, []int) {
-	return file_internal_machine_api_pb_machine_proto_rawDescGZIP(), []int{8}
+	return file_internal_machine_api_pb_machine_proto_rawDescGZIP(), []int{10}
 }
 
 func (x *Service) GetId() string {
@@ -586,7 +708,7 @@ type InspectServiceRequest struct {
 func (x *InspectServiceRequest) Reset() {
 	*x = InspectServiceRequest{}
 	if protoimpl.UnsafeEnabled {
-		mi := &file_internal_machine_api_pb_machine_proto_msgTypes[9]
+		mi := &file_internal_machine_api_pb_machine_proto_msgTypes[11]
 		ms := protoimpl.X.MessageStateOf(protoimpl.Pointer(x))
 		ms.StoreMessageInfo(mi)
 	}
@@ -599,7 +721,7 @@ func (x *InspectServiceRequest) String() string {
 func (*InspectServiceRequest) ProtoMessage() {}
 
 func (x *InspectServiceRequest) ProtoReflect() protoreflect.Message {
-	mi := &file_internal_machine_api_pb_machine_proto_msgTypes[9]
+	mi := &file_internal_machine_api_pb_machine_proto_msgTypes[11]
 	if protoimpl.UnsafeEnabled && x != nil {
 		ms := protoimpl.X.MessageStateOf(protoimpl.Pointer(x))
 		if ms.LoadMessageInfo() == nil {
@@ -612,7 +734,7 @@ func (x *InspectServiceRequest) ProtoReflect() protoreflect.Message {
 
 // Deprecated: Use InspectServiceRequest.ProtoReflect.Descriptor instead.
 func (*InspectServiceRequest) Descriptor() ([]byte, []int) {
-	return file_internal_machine_api_pb_machine_proto_rawDescGZIP(), []int{9}
+	return file_internal_machine_api_pb_machine_proto_rawDescGZIP(), []int{11}
 }
 
 func (x *InspectServiceRequest) GetId() string {
@@ -633,7 +755,7 @@ type InspectServiceResponse struct {
 func (x *InspectServiceResponse) Reset() {
 	*x = InspectServiceResponse{}
 	if protoimpl.UnsafeEnabled {
-		mi := &file_internal_machine_api_pb_machine_proto_msgTypes[10]
+		mi := &file_internal_machine_api_pb_machine_proto_msgTypes[12]
 		ms := protoimpl.X.MessageStateOf(protoimpl.Pointer(x))
 		ms.StoreMessageInfo(mi)
 	}
@@ -646,7 +768,7 @@ func (x *InspectServiceResponse) String() string {
 func (*InspectServiceResponse) ProtoMessage() {}
 
 func (x *InspectServiceResponse) ProtoReflect() protoreflect.Message {
-	mi := &file_internal_machine_api_pb_machine_proto_msgTypes[10]
+	mi := &file_internal_machine_api_pb_machine_proto_msgTypes[12]
 	if protoimpl.UnsafeEnabled && x != nil {
 		ms := protoimpl.X.MessageStateOf(protoimpl.Pointer(x))
 		if ms.LoadMessageInfo() == nil {
@@ -659,7 +781,7 @@ func (x *InspectServiceResponse) ProtoReflect() protoreflect.Message {
 
 // Deprecated: Use InspectServiceResponse.ProtoReflect.Descriptor instead.
 func (*InspectServiceResponse) Descriptor() ([]byte, []int) {
-	return file_internal_machine_api_pb_machine_proto_rawDescGZIP(), []int{10}
+	return file_internal_machine_api_pb_machine_proto_rawDescGZIP(), []int{12}
 }
 
 func (x *InspectServiceResponse) GetService() *Service {
@@ -669,6 +791,164 @@ func (x *InspectServiceResponse) GetService() *Service {
 	return nil
 }
 
+type InspectWireGuardNetworkResponse struct {
+	state         protoimpl.MessageState
+	sizeCache     protoimpl.SizeCache
+	unknownFields protoimpl.UnknownFields
+
+	InterfaceName string           `protobuf:"bytes,1,opt,name=interface_name,json=interfaceName,proto3" json:"interface_name,omitempty"`
+	PublicKey     []byte           `protobuf:"bytes,2,opt,name=public_key,json=publicKey,proto3" json:"public_key,omitempty"`
+	ListenPort    int32            `protobuf:"varint,3,opt,name=listen_port,json=listenPort,proto3" json:"listen_port,omitempty"`
+	Peers         []*WireGuardPeer `protobuf:"bytes,4,rep,name=peers,proto3" json:"peers,omitempty"`
+}
+
+func (x *InspectWireGuardNetworkResponse) Reset() {
+	*x = InspectWireGuardNetworkResponse{}
+	if protoimpl.UnsafeEnabled {
+		mi := &file_internal_machine_api_pb_machine_proto_msgTypes[13]
+		ms := protoimpl.X.MessageStateOf(protoimpl.Pointer(x))
+		ms.StoreMessageInfo(mi)
+	}
+}
+
+func (x *InspectWireGuardNetworkResponse) String() string {
+	return protoimpl.X.MessageStringOf(x)
+}
+
+func (*InspectWireGuardNetworkResponse) ProtoMessage() {}
+
+func (x *InspectWireGuardNetworkResponse) ProtoReflect() protoreflect.Message {
+	mi := &file_internal_machine_api_pb_machine_proto_msgTypes[13]
+	if protoimpl.UnsafeEnabled && x != nil {
+		ms := protoimpl.X.MessageStateOf(protoimpl.Pointer(x))
+		if ms.LoadMessageInfo() == nil {
+			ms.StoreMessageInfo(mi)
+		}
+		return ms
+	}
+	return mi.MessageOf(x)
+}
+
+// Deprecated: Use InspectWireGuardNetworkResponse.ProtoReflect.Descriptor instead.
+func (*InspectWireGuardNetworkResponse) Descriptor() ([]byte, []int) {
+	return file_internal_machine_api_pb_machine_proto_rawDescGZIP(), []int{13}
+}
+
+func (x *InspectWireGuardNetworkResponse) GetInterfaceName() string {
+	if x != nil {
+		return x.InterfaceName
+	}
+	return ""
+}
+
+func (x *InspectWireGuardNetworkResponse) GetPublicKey() []byte {
+	if x != nil {
+		return x.PublicKey
+	}
+	return nil
+}
+
+func (x *InspectWireGuardNetworkResponse) GetListenPort() int32 {
+	if x != nil {
+		return x.ListenPort
+	}
+	return 0
+}
+
+func (x *InspectWireGuardNetworkResponse) GetPeers() []*WireGuardPeer {
+	if x != nil {
+		return x.Peers
+	}
+	return nil
+}
+
+type WireGuardPeer struct {
+	state         protoimpl.MessageState
+	sizeCache     protoimpl.SizeCache
+	unknownFields protoimpl.UnknownFields
+
+	PublicKey         []byte                 `protobuf:"bytes,1,opt,name=public_key,json=publicKey,proto3" json:"public_key,omitempty"`
+	Endpoint          string                 `protobuf:"bytes,2,opt,name=endpoint,proto3" json:"endpoint,omitempty"`
+	LastHandshakeTime *timestamppb.Timestamp `protobuf:"bytes,3,opt,name=last_handshake_time,json=lastHandshakeTime,proto3" json:"last_handshake_time,omitempty"`
+	ReceiveBytes      int64                  `protobuf:"varint,4,opt,name=receive_bytes,json=receiveBytes,proto3" json:"receive_bytes,omitempty"`
+	TransmitBytes     int64                  `protobuf:"varint,5,opt,name=transmit_bytes,json=transmitBytes,proto3" json:"transmit_bytes,omitempty"`
+	AllowedIps        []string               `protobuf:"bytes,6,rep,name=allowed_ips,json=allowedIps,proto3" json:"allowed_ips,omitempty"`
+}
+
+func (x *WireGuardPeer) Reset() {
+	*x = WireGuardPeer{}
+	if protoimpl.UnsafeEnabled {
+		mi := &file_internal_machine_api_pb_machine_proto_msgTypes[14]
+		ms := protoimpl.X.MessageStateOf(protoimpl.Pointer(x))
+		ms.StoreMessageInfo(mi)
+	}
+}
+
+func (x *WireGuardPeer) String() string {
+	return protoimpl.X.MessageStringOf(x)
+}
+
+func (*WireGuardPeer) ProtoMessage() {}
+
+func (x *WireGuardPeer) ProtoReflect() protoreflect.Message {
+	mi := &file_internal_machine_api_pb_machine_proto_msgTypes[14]
+	if protoimpl.UnsafeEnabled && x != nil {
+		ms := protoimpl.X.MessageStateOf(protoimpl.Pointer(x))
+		if ms.LoadMessageInfo() == nil {
+			ms.StoreMessageInfo(mi)
+		}
+		return ms
+	}
+	return mi.MessageOf(x)
+}
+
+// Deprecated: Use WireGuardPeer.ProtoReflect.Descriptor instead.
+func (*WireGuardPeer) Descriptor() ([]byte, []int) {
+	return file_internal_machine_api_pb_machine_proto_rawDescGZIP(), []int{14}
+}
+
+func (x *WireGuardPeer) GetPublicKey() []byte {
+	if x != nil {
+		return x.PublicKey
+	}
+	return nil
+}
+
+func (x *WireGuardPeer) GetEndpoint() string {
+	if x != nil {
+		return x.Endpoint
+	}
+	return ""
+}
+
+func (x *WireGuardPeer) GetLastHandshakeTime() *timestamppb.Timestamp {
+	if x != nil {
+		return x.LastHandshakeTime
+	}
+	return nil
+}
+
+func (x *WireGuardPeer) GetReceiveBytes() int64 {
+	if x != nil {
+		return x.ReceiveBytes
+	}
+	return 0
+}
+
+func (x *WireGuardPeer) GetTransmitBytes() int64 {
+	if x != nil {
+		return x.TransmitBytes
+	}
+	return 0
+}
+
+func (x *WireGuardPeer) GetAllowedIps() []string {
+	if x != nil {
+		return x.AllowedIps
+	}
+	return nil
+}
+
 type Service_Container struct {
 	state         protoimpl.MessageState
 	sizeCache     protoimpl.SizeCache
@@ -682,7 +962,7 @@ type Service_Container struct {
 func (x *Service_Container) Reset() {
 	*x = Service_Container{}
 	if protoimpl.UnsafeEnabled {
-		mi := &file_internal_machine_api_pb_machine_proto_msgTypes[11]
+		mi := &file_internal_machine_api_pb_machine_proto_msgTypes[15]
 		ms := protoimpl.X.MessageStateOf(protoimpl.Pointer(x))
 		ms.StoreMessageInfo(mi)
 	}
@@ -695,7 +975,7 @@ func (x *Service_Container) String() string {
 func (*Service_Container) ProtoMessage() {}
 
 func (x *Service_Container) ProtoReflect() protoreflect.Message {
-	mi := &file_internal_machine_api_pb_machine_proto_msgTypes[11]
+	mi := &file_internal_machine_api_pb_machine_proto_msgTypes[15]
 	if protoimpl.UnsafeEnabled && x != nil {
 		ms := protoimpl.X.MessageStateOf(protoimpl.Pointer(x))
 		if ms.LoadMessageInfo() == nil {
@@ -708,7 +988,7 @@ func (x *Service_Container) ProtoReflect() protoreflect.Message {
 
 // Deprecated: Use Service_Container.ProtoReflect.Descriptor instead.
 func (*Service_Container) Descriptor() ([]byte, []int) {
-	return file_internal_machine_api_pb_machine_proto_rawDescGZIP(), []int{8, 0}
+	return file_internal_machine_api_pb_machine_proto_rawDescGZIP(), []int{10, 0}
 }
 
 func (x *Service_Container) GetMachineId() string {
@@ -732,113 +1012,170 @@ var file_internal_machine_api_pb_machine_proto_rawDesc = []byte{
 	0x6e, 0x65, 0x2f, 0x61, 0x70, 0x69, 0x2f, 0x70, 0x62, 0x2f, 0x6d, 0x61, 0x63, 0x68, 0x69, 0x6e,
 	0x65, 0x2e, 0x70, 0x72, 0x6f, 0x74, 0x6f, 0x12, 0x03, 0x61, 0x70, 0x69, 0x1a, 0x1b, 0x67, 0x6f,
 	0x6f, 0x67, 0x6c, 0x65, 0x2f, 0x70, 0x72, 0x6f, 0x74, 0x6f, 0x62, 0x75, 0x66, 0x2f, 0x65, 0x6d,
-	0x70, 0x74, 0x79, 0x2e, 0x70, 0x72, 0x6f, 0x74, 0x6f, 0x1a, 0x24, 0x69, 0x6e, 0x74, 0x65, 0x72,
-	0x6e, 0x61, 0x6c, 0x2f, 0x6d, 0x61, 0x63, 0x68, 0x69, 0x6e, 0x65, 0x2f, 0x61, 0x70, 0x69, 0x2f,
-	0x70, 0x62, 0x2f, 0x63, 0x6f, 0x6d, 0x6d, 0x6f, 0x6e, 0x2e, 0x70, 0x72, 0x6f, 0x74, 0x6f, 0x22,
-	0x85, 0x01, 0x0a, 0x0b, 0x4d, 0x61, 0x63, 0x68, 0x69, 0x6e, 0x65, 0x49, 0x6e, 0x66, 0x6f, 0x12,
-	0x0e, 0x0a, 0x02, 0x69, 0x64, 0x18, 0x01, 0x20, 0x01, 0x28, 0x09, 0x52, 0x02, 0x69, 0x64, 0x12,
-	0x12, 0x0a, 0x04, 0x6e, 0x61, 0x6d, 0x65, 0x18, 0x02, 0x20, 0x01, 0x28, 0x09, 0x52, 0x04, 0x6e,
-	0x61, 0x6d, 0x65, 0x12, 0x2c, 0x0a, 0x07, 0x6e, 0x65, 0x74, 0x77, 0x6f, 0x72, 0x6b, 0x18, 0x03,
-	0x20, 0x01, 0x28, 0x0b, 0x32, 0x12, 0x2e, 0x61, 0x70, 0x69, 0x2e, 0x4e, 0x65, 0x74, 0x77, 0x6f,
-	0x72, 0x6b, 0x43, 0x6f, 0x6e, 0x66, 0x69, 0x67, 0x52, 0x07, 0x6e, 0x65, 0x74, 0x77, 0x6f, 0x72,
-	0x6b, 0x12, 0x24, 0x0a, 0x09, 0x70, 0x75, 0x62, 0x6c, 0x69, 0x63, 0x5f, 0x69, 0x70, 0x18, 0x04,
-	0x20, 0x01, 0x28, 0x0b, 0x32, 0x07, 0x2e, 0x61, 0x70, 0x69, 0x2e, 0x49, 0x50, 0x52, 0x08, 0x70,
-	0x75, 0x62, 0x6c, 0x69, 0x63, 0x49, 0x70, 0x22, 0xae, 0x01, 0x0a, 0x0d, 0x4e, 0x65, 0x74, 0x77,
-	0x6f, 0x72, 0x6b, 0x43, 0x6f, 0x6e, 0x66, 0x69, 0x67, 0x12, 0x25, 0x0a, 0x06, 0x73, 0x75, 0x62,
-	0x6e, 0x65, 0x74, 0x18, 0x01, 0x20, 0x01, 0x28, 0x0b, 0x32, 0x0d, 0x2e, 0x61, 0x70, 0x69, 0x2e,
-	0x49, 0x50, 0x50, 0x72, 0x65, 0x66, 0x69, 0x78, 0x52, 0x06, 0x73, 0x75, 0x62, 0x6e, 0x65, 0x74,
-	0x12, 0x2c, 0x0a, 0x0d, 0x6d, 0x61, 0x6e, 0x61, 0x67, 0x65, 0x6d, 0x65, 0x6e, 0x74, 0x5f, 0x69,
-	0x70, 0x18, 0x02, 0x20, 0x01, 0x28, 0x0b, 0x32, 0x07, 0x2e, 0x61, 0x70, 0x69, 0x2e, 0x49, 0x50,
-	0x52, 0x0c, 0x6d, 0x61, 0x6e, 0x61, 0x67, 0x65, 0x6d, 0x65, 0x6e, 0x74, 0x49, 0x70, 0x12, 0x29,
-	0x0a, 0x09, 0x65, 0x6e, 0x64, 0x70, 0x6f, 0x69, 0x6e, 0x74, 0x73, 0x18, 0x03, 0x20, 0x03, 0x28,
-	0x0b, 0x32, 0x0b, 0x2e, 0x61, 0x70, 0x69, 0x2e, 0x49, 0x50, 0x50, 0x6f, 0x72, 0x74, 0x52, 0x09,
-	0x65, 0x6e, 0x64, 0x70, 0x6f, 0x69, 0x6e, 0x74, 0x73, 0x12, 0x1d, 0x0a, 0x0a, 0x70, 0x75, 0x62,
-	0x6c, 0x69, 0x63, 0x5f, 0x6b, 0x65, 0x79, 0x18, 0x04, 0x20, 0x01, 0x28, 0x0c, 0x52, 0x09, 0x70,
-	0x75, 0x62, 0x6c, 0x69, 0x63, 0x4b, 0x65, 0x79, 0x22, 0x50, 0x0a, 0x1a, 0x43, 0x68, 0x65, 0x63,
-	0x6b, 0x50, 0x72, 0x65, 0x72, 0x65, 0x71, 0x75, 0x69, 0x73, 0x69, 0x74, 0x65, 0x73, 0x52, 0x65,
-	0x73, 0x70, 0x6f, 0x6e, 0x73, 0x65, 0x12, 0x1c, 0x0a, 0x09, 0x73, 0x61, 0x74, 0x69, 0x73, 0x66,
-	0x69, 0x65, 0x64, 0x18, 0x01, 0x20, 0x01, 0x28, 0x08, 0x52, 0x09, 0x73, 0x61, 0x74, 0x69, 0x73,
-	0x66, 0x69, 0x65, 0x64, 0x12, 0x14, 0x0a, 0x05, 0x65, 0x72, 0x72, 0x6f, 0x72, 0x18, 0x02, 0x20,
-	0x01, 0x28, 0x09, 0x52, 0x05, 0x65, 0x72, 0x72, 0x6f, 0x72, 0x22, 0xc3, 0x01, 0x0a, 0x12, 0x49,
-	0x6e, 0x69, 0x74, 0x43, 0x6c, 0x75, 0x73, 0x74, 0x65, 0x72, 0x52, 0x65, 0x71, 0x75, 0x65, 0x73,
-	0x74, 0x12, 0x20, 0x0a, 0x0b, 0x6d, 0x61, 0x63, 0x68, 0x69, 0x6e, 0x65, 0x4e, 0x61, 0x6d, 0x65,
-	0x18, 0x01, 0x20, 0x01, 0x28, 0x09, 0x52, 0x0b, 0x6d, 0x61, 0x63, 0x68, 0x69, 0x6e, 0x65, 0x4e,
-	0x61, 0x6d, 0x65, 0x12, 0x27, 0x0a, 0x07, 0x6e, 0x65, 0x74, 0x77, 0x6f, 0x72, 0x6b, 0x18, 0x02,
-	0x20, 0x01, 0x28, 0x0b, 0x32, 0x0d, 0x2e, 0x61, 0x70, 0x69, 0x2e, 0x49, 0x50, 0x50, 0x72, 0x65,
-	0x66, 0x69, 0x78, 0x52, 0x07, 0x6e, 0x65, 0x74, 0x77, 0x6f, 0x72, 0x6b, 0x12, 0x26, 0x0a, 0x09,
-	0x70, 0x75, 0x62, 0x6c, 0x69, 0x63, 0x5f, 0x69, 0x70, 0x18, 0x03, 0x20, 0x01, 0x28, 0x0b, 0x32,
-	0x07, 0x2e, 0x61, 0x70, 0x69, 0x2e, 0x49, 0x50, 0x48, 0x00, 0x52, 0x08, 0x70, 0x75, 0x62, 0x6c,
-	0x69, 0x63, 0x49, 0x70, 0x12, 0x26, 0x0a, 0x0e, 0x70, 0x75, 0x62, 0x6c, 0x69, 0x63, 0x5f, 0x69,
-	0x70, 0x5f, 0x61, 0x75, 0x74, 0x6f, 0x18, 0x04, 0x20, 0x01, 0x28, 0x08, 0x48, 0x00, 0x52, 0x0c,
-	0x70, 0x75, 0x62, 0x6c, 0x69, 0x63, 0x49, 0x70, 0x41, 0x75, 0x74, 0x6f, 0x42, 0x12, 0x0a, 0x10,
-	0x70, 0x75, 0x62, 0x6c, 0x69, 0x63, 0x5f, 0x69, 0x70, 0x5f, 0x63, 0x6f, 0x6e, 0x66, 0x69, 0x67,
-	0x22, 0x41, 0x0a, 0x13, 0x49, 0x6e, 0x69, 0x74, 0x43, 0x6c, 0x75, 0x73, 0x74, 0x65, 0x72, 0x52,
-	0x65, 0x73, 0x70, 0x6f, 0x6e, 0x73, 0x65, 0x12, 0x2a, 0x0a, 0x07, 0x6d, 0x61, 0x63, 0x68, 0x69,
-	0x6e, 0x65, 0x18, 0x01, 0x20, 0x01, 0x28, 0x0b, 0x32, 0x10, 0x2e, 0x61, 0x70, 0x69, 0x2e, 0x4d,
-	0x61, 0x63, 0x68, 0x69, 0x6e, 0x65, 0x49, 0x6e, 0x66, 0x6f, 0x52, 0x07, 0x6d, 0x61, 0x63, 0x68,
-	0x69, 0x6e, 0x65, 0x22, 0x79, 0x0a, 0x12, 0x4a, 0x6f, 0x69, 0x6e, 0x43, 0x6c, 0x75, 0x73, 0x74,
-	0x65, 0x72, 0x52, 0x65, 0x71, 0x75, 0x65, 0x73, 0x74, 0x12, 0x2a, 0x0a, 0x07, 0x6d, 0x61, 0x63,
-	0x68, 0x69, 0x6e, 0x65, 0x18, 0x01, 0x20, 0x01, 0x28, 0x0b, 0x32, 0x10, 0x2e, 0x61, 0x70, 0x69,
-	0x2e, 0x4d, 0x61, 0x63, 0x68, 0x69, 0x6e, 0x65, 0x49, 0x6e, 0x66, 0x6f, 0x52, 0x07, 0x6d, 0x61,
-	0x63, 0x68, 0x69, 0x6e, 0x65, 0x12, 0x37, 0x0a, 0x0e, 0x6f, 0x74, 0x68, 0x65, 0x72, 0x5f, 0x6d,
-	0x61, 0x63, 0x68, 0x69, 0x6e, 0x65, 0x73, 0x18, 0x03, 0x20, 0x03, 0x28, 0x0b, 0x32, 0x10, 0x2e,
-	0x61, 0x70, 0x69, 0x2e, 0x4d, 0x61, 0x63, 0x68, 0x69, 0x6e, 0x65, 0x49, 0x6e, 0x66, 0x6f, 0x52,
-	0x0d, 0x6f, 0x74, 0x68, 0x65, 0x72, 0x4d, 0x61, 0x63, 0x68, 0x69, 0x6e, 0x65, 0x73, 0x22, 0x25,
-	0x0a, 0x0d, 0x54, 0x6f, 0x6b, 0x65, 0x6e, 0x52, 0x65, 0x73, 0x70, 0x6f, 0x6e, 0x73, 0x65, 0x12,
-	0x14, 0x0a, 0x05, 0x74, 0x6f, 0x6b, 0x65, 0x6e, 0x18, 0x01, 0x20, 0x01, 0x28, 0x09, 0x52, 0x05,
-	0x74, 0x6f, 0x6b, 0x65, 0x6e, 0x22, 0x0e, 0x0a, 0x0c, 0x52, 0x65, 0x73, 0x65, 0x74, 0x52, 0x65,
-	0x71, 0x75, 0x65, 0x73, 0x74, 0x22, 0xc3, 0x01, 0x0a, 0x07, 0x53, 0x65, 0x72, 0x76, 0x69, 0x63,
-	0x65, 0x12, 0x0e, 0x0a, 0x02, 0x69, 0x64, 0x18, 0x01, 0x20, 0x01, 0x28, 0x09, 0x52, 0x02, 0x69,
-	0x64, 0x12, 0x12, 0x0a, 0x04, 0x6e, 0x61, 0x6d, 0x65, 0x18, 0x02, 0x20, 0x01, 0x28, 0x09, 0x52,
-	0x04, 0x6e, 0x61, 0x6d, 0x65, 0x12, 0x12, 0x0a, 0x04, 0x6d, 0x6f, 0x64, 0x65, 0x18, 0x03, 0x20,
-	0x01, 0x28, 0x09, 0x52, 0x04, 0x6d, 0x6f, 0x64, 0x65, 0x12, 0x36, 0x0a, 0x0a, 0x63, 0x6f, 0x6e,
-	0x74, 0x61, 0x69, 0x6e, 0x65, 0x72, 0x73, 0x18, 0x04, 0x20, 0x03, 0x28, 0x0b, 0x32, 0x16, 0x2e,
-	0x61, 0x70, 0x69, 0x2e, 0x53, 0x65, 0x72, 0x76, 0x69, 0x63, 0x65, 0x2e, 0x43, 0x6f, 0x6e, 0x74,
-	0x61, 0x69, 0x6e, 0x65, 0x72, 0x52, 0x0a, 0x63, 0x6f, 0x6e, 0x74, 0x61, 0x69, 0x6e, 0x65, 0x72,
-	0x73, 0x1a, 0x48, 0x0a, 0x09, 0x43, 0x6f, 0x6e, 0x74, 0x61, 0x69, 0x6e, 0x65, 0x72, 0x12, 0x1d,
-	0x0a, 0x0a, 0x6d, 0x61, 0x63, 0x68, 0x69, 0x6e, 0x65, 0x5f, 0x69, 0x64, 0x18, 0x01, 0x20, 0x01,
-	0x28, 0x09, 0x52, 0x09, 0x6d, 0x61, 0x63, 0x68, 0x69, 0x6e, 0x65, 0x49, 0x64, 0x12, 0x1c, 0x0a,
-	0x09, 0x63, 0x6f, 0x6e, 0x74, 0x61, 0x69, 0x6e, 0x65, 0x72, 0x18, 0x02, 0x20, 0x01, 0x28, 0x0c,
-	0x52, 0x09, 0x63, 0x6f, 0x6e, 0x74, 0x61, 0x69, 0x6e, 0x65, 0x72, 0x22, 0x27, 0x0a, 0x15, 0x49,
-	0x6e, 0x73, 0x70, 0x65, 0x63, 0x74, 0x53, 0x65, 0x72, 0x76, 0x69, 0x63, 0x65, 0x52, 0x65, 0x71,
-	0x75, 0x65, 0x73, 0x74, 0x12, 0x0e, 0x0a, 0x02, 0x69, 0x64, 0x18, 0x01, 0x20, 0x01, 0x28, 0x09,
-	0x52, 0x02, 0x69, 0x64, 0x22, 0x40, 0x0a, 0x16, 0x49, 0x6e, 0x73, 0x70, 0x65, 0x63, 0x74, 0x53,
-	0x65, 0x72, 0x76, 0x69, 0x63, 0x65, 0x52, 0x65, 0x73, 0x70, 0x6f, 0x6e, 0x73, 0x65, 0x12, 0x26,
-	0x0a, 0x07, 0x73, 0x65, 0x72, 0x76, 0x69, 0x63, 0x65, 0x18, 0x01, 0x20, 0x01, 0x28, 0x0b, 0x32,
-	0x0c, 0x2e, 0x61, 0x70, 0x69, 0x2e, 0x53, 0x65, 0x72, 0x76, 0x69, 0x63, 0x65, 0x52, 0x07, 0x73,
-	0x65, 0x72, 0x76, 0x69, 0x63, 0x65, 0x32, 0xc3, 0x03, 0x0a, 0x07, 0x4d, 0x61, 0x63, 0x68, 0x69,
-	0x6e, 0x65, 0x12, 0x4d, 0x0a, 0x12, 0x43, 0x68, 0x65, 0x63, 0x6b, 0x50, 0x72, 0x65, 0x72, 0x65,
-	0x71, 0x75, 0x69, 0x73, 0x69, 0x74, 0x65, 0x73, 0x12, 0x16, 0x2e, 0x67, 0x6f, 0x6f, 0x67, 0x6c,
+	0x70, 0x74, 0x79, 0x2e, 0x70, 0x72, 0x6f, 0x74, 0x6f, 0x1a, 0x1f, 0x67, 0x6f, 0x6f, 0x67, 0x6c,
+	0x65, 0x2f, 0x70, 0x72, 0x6f, 0x74, 0x6f, 0x62, 0x75, 0x66, 0x2f, 0x74, 0x69, 0x6d, 0x65, 0x73,
+	0x74, 0x61, 0x6d, 0x70, 0x2e, 0x70, 0x72, 0x6f, 0x74, 0x6f, 0x1a, 0x24, 0x69, 0x6e, 0x74, 0x65,
+	0x72, 0x6e, 0x61, 0x6c, 0x2f, 0x6d, 0x61, 0x63, 0x68, 0x69, 0x6e, 0x65, 0x2f, 0x61, 0x70, 0x69,
+	0x2f, 0x70, 0x62, 0x2f, 0x63, 0x6f, 0x6d, 0x6d, 0x6f, 0x6e, 0x2e, 0x70, 0x72, 0x6f, 0x74, 0x6f,
+	0x22, 0x85, 0x01, 0x0a, 0x0b, 0x4d, 0x61, 0x63, 0x68, 0x69, 0x6e, 0x65, 0x49, 0x6e, 0x66, 0x6f,
+	0x12, 0x0e, 0x0a, 0x02, 0x69, 0x64, 0x18, 0x01, 0x20, 0x01, 0x28, 0x09, 0x52, 0x02, 0x69, 0x64,
+	0x12, 0x12, 0x0a, 0x04, 0x6e, 0x61, 0x6d, 0x65, 0x18, 0x02, 0x20, 0x01, 0x28, 0x09, 0x52, 0x04,
+	0x6e, 0x61, 0x6d, 0x65, 0x12, 0x2c, 0x0a, 0x07, 0x6e, 0x65, 0x74, 0x77, 0x6f, 0x72, 0x6b, 0x18,
+	0x03, 0x20, 0x01, 0x28, 0x0b, 0x32, 0x12, 0x2e, 0x61, 0x70, 0x69, 0x2e, 0x4e, 0x65, 0x74, 0x77,
+	0x6f, 0x72, 0x6b, 0x43, 0x6f, 0x6e, 0x66, 0x69, 0x67, 0x52, 0x07, 0x6e, 0x65, 0x74, 0x77, 0x6f,
+	0x72, 0x6b, 0x12, 0x24, 0x0a, 0x09, 0x70, 0x75, 0x62, 0x6c, 0x69, 0x63, 0x5f, 0x69, 0x70, 0x18,
+	0x04, 0x20, 0x01, 0x28, 0x0b, 0x32, 0x07, 0x2e, 0x61, 0x70, 0x69, 0x2e, 0x49, 0x50, 0x52, 0x08,
+	0x70, 0x75, 0x62, 0x6c, 0x69, 0x63, 0x49, 0x70, 0x22, 0xae, 0x01, 0x0a, 0x0d, 0x4e, 0x65, 0x74,
+	0x77, 0x6f, 0x72, 0x6b, 0x43, 0x6f, 0x6e, 0x66, 0x69, 0x67, 0x12, 0x25, 0x0a, 0x06, 0x73, 0x75,
+	0x62, 0x6e, 0x65, 0x74, 0x18, 0x01, 0x20, 0x01, 0x28, 0x0b, 0x32, 0x0d, 0x2e, 0x61, 0x70, 0x69,
+	0x2e, 0x49, 0x50, 0x50, 0x72, 0x65, 0x66, 0x69, 0x78, 0x52, 0x06, 0x73, 0x75, 0x62, 0x6e, 0x65,
+	0x74, 0x12, 0x2c, 0x0a, 0x0d, 0x6d, 0x61, 0x6e, 0x61, 0x67, 0x65, 0x6d, 0x65, 0x6e, 0x74, 0x5f,
+	0x69, 0x70, 0x18, 0x02, 0x20, 0x01, 0x28, 0x0b, 0x32, 0x07, 0x2e, 0x61, 0x70, 0x69, 0x2e, 0x49,
+	0x50, 0x52, 0x0c, 0x6d, 0x61, 0x6e, 0x61, 0x67, 0x65, 0x6d, 0x65, 0x6e, 0x74, 0x49, 0x70, 0x12,
+	0x29, 0x0a, 0x09, 0x65, 0x6e, 0x64, 0x70, 0x6f, 0x69, 0x6e, 0x74, 0x73, 0x18, 0x03, 0x20, 0x03,
+	0x28, 0x0b, 0x32, 0x0b, 0x2e, 0x61, 0x70, 0x69, 0x2e, 0x49, 0x50, 0x50, 0x6f, 0x72, 0x74, 0x52,
+	0x09, 0x65, 0x6e, 0x64, 0x70, 0x6f, 0x69, 0x6e, 0x74, 0x73, 0x12, 0x1d, 0x0a, 0x0a, 0x70, 0x75,
+	0x62, 0x6c, 0x69, 0x63, 0x5f, 0x6b, 0x65, 0x79, 0x18, 0x04, 0x20, 0x01, 0x28, 0x0c, 0x52, 0x09,
+	0x70, 0x75, 0x62, 0x6c, 0x69, 0x63, 0x4b, 0x65, 0x79, 0x22, 0x50, 0x0a, 0x1a, 0x43, 0x68, 0x65,
+	0x63, 0x6b, 0x50, 0x72, 0x65, 0x72, 0x65, 0x71, 0x75, 0x69, 0x73, 0x69, 0x74, 0x65, 0x73, 0x52,
+	0x65, 0x73, 0x70, 0x6f, 0x6e, 0x73, 0x65, 0x12, 0x1c, 0x0a, 0x09, 0x73, 0x61, 0x74, 0x69, 0x73,
+	0x66, 0x69, 0x65, 0x64, 0x18, 0x01, 0x20, 0x01, 0x28, 0x08, 0x52, 0x09, 0x73, 0x61, 0x74, 0x69,
+	0x73, 0x66, 0x69, 0x65, 0x64, 0x12, 0x14, 0x0a, 0x05, 0x65, 0x72, 0x72, 0x6f, 0x72, 0x18, 0x02,
+	0x20, 0x01, 0x28, 0x09, 0x52, 0x05, 0x65, 0x72, 0x72, 0x6f, 0x72, 0x22, 0xc3, 0x01, 0x0a, 0x12,
+	0x49, 0x6e, 0x69, 0x74, 0x43, 0x6c, 0x75, 0x73, 0x74, 0x65, 0x72, 0x52, 0x65, 0x71, 0x75, 0x65,
+	0x73, 0x74, 0x12, 0x20, 0x0a, 0x0b, 0x6d, 0x61, 0x63, 0x68, 0x69, 0x6e, 0x65, 0x4e, 0x61, 0x6d,
+	0x65, 0x18, 0x01, 0x20, 0x01, 0x28, 0x09, 0x52, 0x0b, 0x6d, 0x61, 0x63, 0x68, 0x69, 0x6e, 0x65,
+	0x4e, 0x61, 0x6d, 0x65, 0x12, 0x27, 0x0a, 0x07, 0x6e, 0x65, 0x74, 0x77, 0x6f, 0x72, 0x6b, 0x18,
+	0x02, 0x20, 0x01, 0x28, 0x0b, 0x32, 0x0d, 0x2e, 0x61, 0x70, 0x69, 0x2e, 0x49, 0x50, 0x50, 0x72,
+	0x65, 0x66, 0x69, 0x78, 0x52, 0x07, 0x6e, 0x65, 0x74, 0x77, 0x6f, 0x72, 0x6b, 0x12, 0x26, 0x0a,
+	0x09, 0x70, 0x75, 0x62, 0x6c, 0x69, 0x63, 0x5f, 0x69, 0x70, 0x18, 0x03, 0x20, 0x01, 0x28, 0x0b,
+	0x32, 0x07, 0x2e, 0x61, 0x70, 0x69, 0x2e, 0x49, 0x50, 0x48, 0x00, 0x52, 0x08, 0x70, 0x75, 0x62,
+	0x6c, 0x69, 0x63, 0x49, 0x70, 0x12, 0x26, 0x0a, 0x0e, 0x70, 0x75, 0x62, 0x6c, 0x69, 0x63, 0x5f,
+	0x69, 0x70, 0x5f, 0x61, 0x75, 0x74, 0x6f, 0x18, 0x04, 0x20, 0x01, 0x28, 0x08, 0x48, 0x00, 0x52,
+	0x0c, 0x70, 0x75, 0x62, 0x6c, 0x69, 0x63, 0x49, 0x70, 0x41, 0x75, 0x74, 0x6f, 0x42, 0x12, 0x0a,
+	0x10, 0x70, 0x75, 0x62, 0x6c, 0x69, 0x63, 0x5f, 0x69, 0x70, 0x5f, 0x63, 0x6f, 0x6e, 0x66, 0x69,
+	0x67, 0x22, 0x41, 0x0a, 0x13, 0x49, 0x6e, 0x69, 0x74, 0x43, 0x6c, 0x75, 0x73, 0x74, 0x65, 0x72,
+	0x52, 0x65, 0x73, 0x70, 0x6f, 0x6e, 0x73, 0x65, 0x12, 0x2a, 0x0a, 0x07, 0x6d, 0x61, 0x63, 0x68,
+	0x69, 0x6e, 0x65, 0x18, 0x01, 0x20, 0x01, 0x28, 0x0b, 0x32, 0x10, 0x2e, 0x61, 0x70, 0x69, 0x2e,
+	0x4d, 0x61, 0x63, 0x68, 0x69, 0x6e, 0x65, 0x49, 0x6e, 0x66, 0x6f, 0x52, 0x07, 0x6d, 0x61, 0x63,
+	0x68, 0x69, 0x6e, 0x65, 0x22, 0xaa, 0x01, 0x0a, 0x12, 0x4a, 0x6f, 0x69, 0x6e, 0x43, 0x6c, 0x75,
+	0x73, 0x74, 0x65, 0x72, 0x52, 0x65, 0x71, 0x75, 0x65, 0x73, 0x74, 0x12, 0x2a, 0x0a, 0x07, 0x6d,
+	0x61, 0x63, 0x68, 0x69, 0x6e, 0x65, 0x18, 0x01, 0x20, 0x01, 0x28, 0x0b, 0x32, 0x10, 0x2e, 0x61,
+	0x70, 0x69, 0x2e, 0x4d, 0x61, 0x63, 0x68, 0x69, 0x6e, 0x65, 0x49, 0x6e, 0x66, 0x6f, 0x52, 0x07,
+	0x6d, 0x61, 0x63, 0x68, 0x69, 0x6e, 0x65, 0x12, 0x37, 0x0a, 0x0e, 0x6f, 0x74, 0x68, 0x65, 0x72,
+	0x5f, 0x6d, 0x61, 0x63, 0x68, 0x69, 0x6e, 0x65, 0x73, 0x18, 0x03, 0x20, 0x03, 0x28, 0x0b, 0x32,
+	0x10, 0x2e, 0x61, 0x70, 0x69, 0x2e, 0x4d, 0x61, 0x63, 0x68, 0x69, 0x6e, 0x65, 0x49, 0x6e, 0x66,
+	0x6f, 0x52, 0x0d, 0x6f, 0x74, 0x68, 0x65, 0x72, 0x4d, 0x61, 0x63, 0x68, 0x69, 0x6e, 0x65, 0x73,
+	0x12, 0x2f, 0x0a, 0x14, 0x6d, 0x69, 0x6e, 0x5f, 0x73, 0x74, 0x6f, 0x72, 0x65, 0x5f, 0x64, 0x62,
+	0x5f, 0x76, 0x65, 0x72, 0x73, 0x69, 0x6f, 0x6e, 0x18, 0x04, 0x20, 0x01, 0x28, 0x03, 0x52, 0x11,
+	0x6d, 0x69, 0x6e, 0x53, 0x74, 0x6f, 0x72, 0x65, 0x44, 0x62, 0x56, 0x65, 0x72, 0x73, 0x69, 0x6f,
+	0x6e, 0x22, 0x49, 0x0a, 0x16, 0x49, 0x6e, 0x73, 0x70, 0x65, 0x63, 0x74, 0x4d, 0x61, 0x63, 0x68,
+	0x69, 0x6e, 0x65, 0x52, 0x65, 0x73, 0x70, 0x6f, 0x6e, 0x73, 0x65, 0x12, 0x2f, 0x0a, 0x08, 0x6d,
+	0x61, 0x63, 0x68, 0x69, 0x6e, 0x65, 0x73, 0x18, 0x01, 0x20, 0x03, 0x28, 0x0b, 0x32, 0x13, 0x2e,
+	0x61, 0x70, 0x69, 0x2e, 0x4d, 0x61, 0x63, 0x68, 0x69, 0x6e, 0x65, 0x44, 0x65, 0x74, 0x61, 0x69,
+	0x6c, 0x73, 0x52, 0x08, 0x6d, 0x61, 0x63, 0x68, 0x69, 0x6e, 0x65, 0x73, 0x22, 0x91, 0x01, 0x0a,
+	0x0e, 0x4d, 0x61, 0x63, 0x68, 0x69, 0x6e, 0x65, 0x44, 0x65, 0x74, 0x61, 0x69, 0x6c, 0x73, 0x12,
+	0x29, 0x0a, 0x08, 0x6d, 0x65, 0x74, 0x61, 0x64, 0x61, 0x74, 0x61, 0x18, 0x01, 0x20, 0x01, 0x28,
+	0x0b, 0x32, 0x0d, 0x2e, 0x61, 0x70, 0x69, 0x2e, 0x4d, 0x65, 0x74, 0x61, 0x64, 0x61, 0x74, 0x61,
+	0x52, 0x08, 0x6d, 0x65, 0x74, 0x61, 0x64, 0x61, 0x74, 0x61, 0x12, 0x2a, 0x0a, 0x07, 0x6d, 0x61,
+	0x63, 0x68, 0x69, 0x6e, 0x65, 0x18, 0x02, 0x20, 0x01, 0x28, 0x0b, 0x32, 0x10, 0x2e, 0x61, 0x70,
+	0x69, 0x2e, 0x4d, 0x61, 0x63, 0x68, 0x69, 0x6e, 0x65, 0x49, 0x6e, 0x66, 0x6f, 0x52, 0x07, 0x6d,
+	0x61, 0x63, 0x68, 0x69, 0x6e, 0x65, 0x12, 0x28, 0x0a, 0x10, 0x73, 0x74, 0x6f, 0x72, 0x65, 0x5f,
+	0x64, 0x62, 0x5f, 0x76, 0x65, 0x72, 0x73, 0x69, 0x6f, 0x6e, 0x18, 0x03, 0x20, 0x01, 0x28, 0x03,
+	0x52, 0x0e, 0x73, 0x74, 0x6f, 0x72, 0x65, 0x44, 0x62, 0x56, 0x65, 0x72, 0x73, 0x69, 0x6f, 0x6e,
+	0x22, 0x25, 0x0a, 0x0d, 0x54, 0x6f, 0x6b, 0x65, 0x6e, 0x52, 0x65, 0x73, 0x70, 0x6f, 0x6e, 0x73,
+	0x65, 0x12, 0x14, 0x0a, 0x05, 0x74, 0x6f, 0x6b, 0x65, 0x6e, 0x18, 0x01, 0x20, 0x01, 0x28, 0x09,
+	0x52, 0x05, 0x74, 0x6f, 0x6b, 0x65, 0x6e, 0x22, 0x0e, 0x0a, 0x0c, 0x52, 0x65, 0x73, 0x65, 0x74,
+	0x52, 0x65, 0x71, 0x75, 0x65, 0x73, 0x74, 0x22, 0xc3, 0x01, 0x0a, 0x07, 0x53, 0x65, 0x72, 0x76,
+	0x69, 0x63, 0x65, 0x12, 0x0e, 0x0a, 0x02, 0x69, 0x64, 0x18, 0x01, 0x20, 0x01, 0x28, 0x09, 0x52,
+	0x02, 0x69, 0x64, 0x12, 0x12, 0x0a, 0x04, 0x6e, 0x61, 0x6d, 0x65, 0x18, 0x02, 0x20, 0x01, 0x28,
+	0x09, 0x52, 0x04, 0x6e, 0x61, 0x6d, 0x65, 0x12, 0x12, 0x0a, 0x04, 0x6d, 0x6f, 0x64, 0x65, 0x18,
+	0x03, 0x20, 0x01, 0x28, 0x09, 0x52, 0x04, 0x6d, 0x6f, 0x64, 0x65, 0x12, 0x36, 0x0a, 0x0a, 0x63,
+	0x6f, 0x6e, 0x74, 0x61, 0x69, 0x6e, 0x65, 0x72, 0x73, 0x18, 0x04, 0x20, 0x03, 0x28, 0x0b, 0x32,
+	0x16, 0x2e, 0x61, 0x70, 0x69, 0x2e, 0x53, 0x65, 0x72, 0x76, 0x69, 0x63, 0x65, 0x2e, 0x43, 0x6f,
+	0x6e, 0x74, 0x61, 0x69, 0x6e, 0x65, 0x72, 0x52, 0x0a, 0x63, 0x6f, 0x6e, 0x74, 0x61, 0x69, 0x6e,
+	0x65, 0x72, 0x73, 0x1a, 0x48, 0x0a, 0x09, 0x43, 0x6f, 0x6e, 0x74, 0x61, 0x69, 0x6e, 0x65, 0x72,
+	0x12, 0x1d, 0x0a, 0x0a, 0x6d, 0x61, 0x63, 0x68, 0x69, 0x6e, 0x65, 0x5f, 0x69, 0x64, 0x18, 0x01,
+	0x20, 0x01, 0x28, 0x09, 0x52, 0x09, 0x6d, 0x61, 0x63, 0x68, 0x69, 0x6e, 0x65, 0x49, 0x64, 0x12,
+	0x1c, 0x0a, 0x09, 0x63, 0x6f, 0x6e, 0x74, 0x61, 0x69, 0x6e, 0x65, 0x72, 0x18, 0x02, 0x20, 0x01,
+	0x28, 0x0c, 0x52, 0x09, 0x63, 0x6f, 0x6e, 0x74, 0x61, 0x69, 0x6e, 0x65, 0x72, 0x22, 0x27, 0x0a,
+	0x15, 0x49, 0x6e, 0x73, 0x70, 0x65, 0x63, 0x74, 0x53, 0x65, 0x72, 0x76, 0x69, 0x63, 0x65, 0x52,
+	0x65, 0x71, 0x75, 0x65, 0x73, 0x74, 0x12, 0x0e, 0x0a, 0x02, 0x69, 0x64, 0x18, 0x01, 0x20, 0x01,
+	0x28, 0x09, 0x52, 0x02, 0x69, 0x64, 0x22, 0x40, 0x0a, 0x16, 0x49, 0x6e, 0x73, 0x70, 0x65, 0x63,
+	0x74, 0x53, 0x65, 0x72, 0x76, 0x69, 0x63, 0x65, 0x52, 0x65, 0x73, 0x70, 0x6f, 0x6e, 0x73, 0x65,
+	0x12, 0x26, 0x0a, 0x07, 0x73, 0x65, 0x72, 0x76, 0x69, 0x63, 0x65, 0x18, 0x01, 0x20, 0x01, 0x28,
+	0x0b, 0x32, 0x0c, 0x2e, 0x61, 0x70, 0x69, 0x2e, 0x53, 0x65, 0x72, 0x76, 0x69, 0x63, 0x65, 0x52,
+	0x07, 0x73, 0x65, 0x72, 0x76, 0x69, 0x63, 0x65, 0x22, 0xb2, 0x01, 0x0a, 0x1f, 0x49, 0x6e, 0x73,
+	0x70, 0x65, 0x63, 0x74, 0x57, 0x69, 0x72, 0x65, 0x47, 0x75, 0x61, 0x72, 0x64, 0x4e, 0x65, 0x74,
+	0x77, 0x6f, 0x72, 0x6b, 0x52, 0x65, 0x73, 0x70, 0x6f, 0x6e, 0x73, 0x65, 0x12, 0x25, 0x0a, 0x0e,
+	0x69, 0x6e, 0x74, 0x65, 0x72, 0x66, 0x61, 0x63, 0x65, 0x5f, 0x6e, 0x61, 0x6d, 0x65, 0x18, 0x01,
+	0x20, 0x01, 0x28, 0x09, 0x52, 0x0d, 0x69, 0x6e, 0x74, 0x65, 0x72, 0x66, 0x61, 0x63, 0x65, 0x4e,
+	0x61, 0x6d, 0x65, 0x12, 0x1d, 0x0a, 0x0a, 0x70, 0x75, 0x62, 0x6c, 0x69, 0x63, 0x5f, 0x6b, 0x65,
+	0x79, 0x18, 0x02, 0x20, 0x01, 0x28, 0x0c, 0x52, 0x09, 0x70, 0x75, 0x62, 0x6c, 0x69, 0x63, 0x4b,
+	0x65, 0x79, 0x12, 0x1f, 0x0a, 0x0b, 0x6c, 0x69, 0x73, 0x74, 0x65, 0x6e, 0x5f, 0x70, 0x6f, 0x72,
+	0x74, 0x18, 0x03, 0x20, 0x01, 0x28, 0x05, 0x52, 0x0a, 0x6c, 0x69, 0x73, 0x74, 0x65, 0x6e, 0x50,
+	0x6f, 0x72, 0x74, 0x12, 0x28, 0x0a, 0x05, 0x70, 0x65, 0x65, 0x72, 0x73, 0x18, 0x04, 0x20, 0x03,
+	0x28, 0x0b, 0x32, 0x12, 0x2e, 0x61, 0x70, 0x69, 0x2e, 0x57, 0x69, 0x72, 0x65, 0x47, 0x75, 0x61,
+	0x72, 0x64, 0x50, 0x65, 0x65, 0x72, 0x52, 0x05, 0x70, 0x65, 0x65, 0x72, 0x73, 0x22, 0x83, 0x02,
+	0x0a, 0x0d, 0x57, 0x69, 0x72, 0x65, 0x47, 0x75, 0x61, 0x72, 0x64, 0x50, 0x65, 0x65, 0x72, 0x12,
+	0x1d, 0x0a, 0x0a, 0x70, 0x75, 0x62, 0x6c, 0x69, 0x63, 0x5f, 0x6b, 0x65, 0x79, 0x18, 0x01, 0x20,
+	0x01, 0x28, 0x0c, 0x52, 0x09, 0x70, 0x75, 0x62, 0x6c, 0x69, 0x63, 0x4b, 0x65, 0x79, 0x12, 0x1a,
+	0x0a, 0x08, 0x65, 0x6e, 0x64, 0x70, 0x6f, 0x69, 0x6e, 0x74, 0x18, 0x02, 0x20, 0x01, 0x28, 0x09,
+	0x52, 0x08, 0x65, 0x6e, 0x64, 0x70, 0x6f, 0x69, 0x6e, 0x74, 0x12, 0x4a, 0x0a, 0x13, 0x6c, 0x61,
+	0x73, 0x74, 0x5f, 0x68, 0x61, 0x6e, 0x64, 0x73, 0x68, 0x61, 0x6b, 0x65, 0x5f, 0x74, 0x69, 0x6d,
+	0x65, 0x18, 0x03, 0x20, 0x01, 0x28, 0x0b, 0x32, 0x1a, 0x2e, 0x67, 0x6f, 0x6f, 0x67, 0x6c, 0x65,
+	0x2e, 0x70, 0x72, 0x6f, 0x74, 0x6f, 0x62, 0x75, 0x66, 0x2e, 0x54, 0x69, 0x6d, 0x65, 0x73, 0x74,
+	0x61, 0x6d, 0x70, 0x52, 0x11, 0x6c, 0x61, 0x73, 0x74, 0x48, 0x61, 0x6e, 0x64, 0x73, 0x68, 0x61,
+	0x6b, 0x65, 0x54, 0x69, 0x6d, 0x65, 0x12, 0x23, 0x0a, 0x0d, 0x72, 0x65, 0x63, 0x65, 0x69, 0x76,
+	0x65, 0x5f, 0x62, 0x79, 0x74, 0x65, 0x73, 0x18, 0x04, 0x20, 0x01, 0x28, 0x03, 0x52, 0x0c, 0x72,
+	0x65, 0x63, 0x65, 0x69, 0x76, 0x65, 0x42, 0x79, 0x74, 0x65, 0x73, 0x12, 0x25, 0x0a, 0x0e, 0x74,
+	0x72, 0x61, 0x6e, 0x73, 0x6d, 0x69, 0x74, 0x5f, 0x62, 0x79, 0x74, 0x65, 0x73, 0x18, 0x05, 0x20,
+	0x01, 0x28, 0x03, 0x52, 0x0d, 0x74, 0x72, 0x61, 0x6e, 0x73, 0x6d, 0x69, 0x74, 0x42, 0x79, 0x74,
+	0x65, 0x73, 0x12, 0x1f, 0x0a, 0x0b, 0x61, 0x6c, 0x6c, 0x6f, 0x77, 0x65, 0x64, 0x5f, 0x69, 0x70,
+	0x73, 0x18, 0x06, 0x20, 0x03, 0x28, 0x09, 0x52, 0x0a, 0x61, 0x6c, 0x6c, 0x6f, 0x77, 0x65, 0x64,
+	0x49, 0x70, 0x73, 0x32, 0xe3, 0x04, 0x0a, 0x07, 0x4d, 0x61, 0x63, 0x68, 0x69, 0x6e, 0x65, 0x12,
+	0x4d, 0x0a, 0x12, 0x43, 0x68, 0x65, 0x63, 0x6b, 0x50, 0x72, 0x65, 0x72, 0x65, 0x71, 0x75, 0x69,
+	0x73, 0x69, 0x74, 0x65, 0x73, 0x12, 0x16, 0x2e, 0x67, 0x6f, 0x6f, 0x67, 0x6c, 0x65, 0x2e, 0x70,
+	0x72, 0x6f, 0x74, 0x6f, 0x62, 0x75, 0x66, 0x2e, 0x45, 0x6d, 0x70, 0x74, 0x79, 0x1a, 0x1f, 0x2e,
+	0x61, 0x70, 0x69, 0x2e, 0x43, 0x68, 0x65, 0x63, 0x6b, 0x50, 0x72, 0x65, 0x72, 0x65, 0x71, 0x75,
+	0x69, 0x73, 0x69, 0x74, 0x65, 0x73, 0x52, 0x65, 0x73, 0x70, 0x6f, 0x6e, 0x73, 0x65, 0x12, 0x40,
+	0x0a, 0x0b, 0x49, 0x6e, 0x69, 0x74, 0x43, 0x6c, 0x75, 0x73, 0x74, 0x65, 0x72, 0x12, 0x17, 0x2e,
+	0x61, 0x70, 0x69, 0x2e, 0x49, 0x6e, 0x69, 0x74, 0x43, 0x6c, 0x75, 0x73, 0x74, 0x65, 0x72, 0x52,
+	0x65, 0x71, 0x75, 0x65, 0x73, 0x74, 0x1a, 0x18, 0x2e, 0x61, 0x70, 0x69, 0x2e, 0x49, 0x6e, 0x69,
+	0x74, 0x43, 0x6c, 0x75, 0x73, 0x74, 0x65, 0x72, 0x52, 0x65, 0x73, 0x70, 0x6f, 0x6e, 0x73, 0x65,
+	0x12, 0x3e, 0x0a, 0x0b, 0x4a, 0x6f, 0x69, 0x6e, 0x43, 0x6c, 0x75, 0x73, 0x74, 0x65, 0x72, 0x12,
+	0x17, 0x2e, 0x61, 0x70, 0x69, 0x2e, 0x4a, 0x6f, 0x69, 0x6e, 0x43, 0x6c, 0x75, 0x73, 0x74, 0x65,
+	0x72, 0x52, 0x65, 0x71, 0x75, 0x65, 0x73, 0x74, 0x1a, 0x16, 0x2e, 0x67, 0x6f, 0x6f, 0x67, 0x6c,
 	0x65, 0x2e, 0x70, 0x72, 0x6f, 0x74, 0x6f, 0x62, 0x75, 0x66, 0x2e, 0x45, 0x6d, 0x70, 0x74, 0x79,
-	0x1a, 0x1f, 0x2e, 0x61, 0x70, 0x69, 0x2e, 0x43, 0x68, 0x65, 0x63, 0x6b, 0x50, 0x72, 0x65, 0x72,
-	0x65, 0x71, 0x75, 0x69, 0x73, 0x69, 0x74, 0x65, 0x73, 0x52, 0x65, 0x73, 0x70, 0x6f, 0x6e, 0x73,
-	0x65, 0x12, 0x40, 0x0a, 0x0b, 0x49, 0x6e, 0x69, 0x74, 0x43, 0x6c, 0x75, 0x73, 0x74, 0x65, 0x72,
-	0x12, 0x17, 0x2e, 0x61, 0x70, 0x69, 0x2e, 0x49, 0x6e, 0x69, 0x74, 0x43, 0x6c, 0x75, 0x73, 0x74,
-	0x65, 0x72, 0x52, 0x65, 0x71, 0x75, 0x65, 0x73, 0x74, 0x1a, 0x18, 0x2e, 0x61, 0x70, 0x69, 0x2e,
-	0x49, 0x6e, 0x69, 0x74, 0x43, 0x6c, 0x75, 0x73, 0x74, 0x65, 0x72, 0x52, 0x65, 0x73, 0x70, 0x6f,
-	0x6e, 0x73, 0x65, 0x12, 0x3e, 0x0a, 0x0b, 0x4a, 0x6f, 0x69, 0x6e, 0x43, 0x6c, 0x75, 0x73, 0x74,
-	0x65, 0x72, 0x12, 0x17, 0x2e, 0x61, 0x70, 0x69, 0x2e, 0x4a, 0x6f, 0x69, 0x6e, 0x43, 0x6c, 0x75,
-	0x73, 0x74, 0x65, 0x72, 0x52, 0x65, 0x71, 0x75, 0x65, 0x73, 0x74, 0x1a, 0x16, 0x2e, 0x67, 0x6f,
-	0x6f, 0x67, 0x6c, 0x65, 0x2e, 0x70, 0x72, 0x6f, 0x74, 0x6f, 0x62, 0x75, 0x66, 0x2e, 0x45, 0x6d,
-	0x70, 0x74, 0x79, 0x12, 0x33, 0x0a, 0x05, 0x54, 0x6f, 0x6b, 0x65, 0x6e, 0x12, 0x16, 0x2e, 0x67,
-	0x6f, 0x6f, 0x67, 0x6c, 0x65, 0x2e, 0x70, 0x72, 0x6f, 0x74, 0x6f, 0x62, 0x75, 0x66, 0x2e, 0x45,
-	0x6d, 0x70, 0x74, 0x79, 0x1a, 0x12, 0x2e, 0x61, 0x70, 0x69, 0x2e, 0x54, 0x6f, 0x6b, 0x65, 0x6e,
-	0x52, 0x65, 0x73, 0x70, 0x6f, 0x6e, 0x73, 0x65, 0x12, 0x33, 0x0a, 0x07, 0x49, 0x6e, 0x73, 0x70,
-	0x65, 0x63, 0x74, 0x12, 0x16, 0x2e, 0x67, 0x6f, 0x6f, 0x67, 0x6c, 0x65, 0x2e, 0x70, 0x72, 0x6f,
-	0x74, 0x6f, 0x62, 0x75, 0x66, 0x2e, 0x45, 0x6d, 0x70, 0x74, 0x79, 0x1a, 0x10, 0x2e, 0x61, 0x70,
-	0x69, 0x2e, 0x4d, 0x61, 0x63, 0x68, 0x69, 0x6e, 0x65, 0x49, 0x6e, 0x66, 0x6f, 0x12, 0x32, 0x0a,
-	0x05, 0x52, 0x65, 0x73, 0x65, 0x74, 0x12, 0x11, 0x2e, 0x61, 0x70, 0x69, 0x2e, 0x52, 0x65, 0x73,
-	0x65, 0x74, 0x52, 0x65, 0x71, 0x75, 0x65, 0x73, 0x74, 0x1a, 0x16, 0x2e, 0x67, 0x6f, 0x6f, 0x67,
+	0x12, 0x33, 0x0a, 0x05, 0x54, 0x6f, 0x6b, 0x65, 0x6e, 0x12, 0x16, 0x2e, 0x67, 0x6f, 0x6f, 0x67,
 	0x6c, 0x65, 0x2e, 0x70, 0x72, 0x6f, 0x74, 0x6f, 0x62, 0x75, 0x66, 0x2e, 0x45, 0x6d, 0x70, 0x74,
-	0x79, 0x12, 0x49, 0x0a, 0x0e, 0x49, 0x6e, 0x73, 0x70, 0x65, 0x63, 0x74, 0x53, 0x65, 0x72, 0x76,
-	0x69, 0x63, 0x65, 0x12, 0x1a, 0x2e, 0x61, 0x70, 0x69, 0x2e, 0x49, 0x6e, 0x73, 0x70, 0x65, 0x63,
-	0x74, 0x53, 0x65, 0x72, 0x76, 0x69, 0x63, 0x65, 0x52, 0x65, 0x71, 0x75, 0x65, 0x73, 0x74, 0x1a,
-	0x1b, 0x2e, 0x61, 0x70, 0x69, 0x2e, 0x49, 0x6e, 0x73, 0x70, 0x65, 0x63, 0x74, 0x53, 0x65, 0x72,
-	0x76, 0x69, 0x63, 0x65, 0x52, 0x65, 0x73, 0x70, 0x6f, 0x6e, 0x73, 0x65, 0x42, 0x37, 0x5a, 0x35,
-	0x67, 0x69, 0x74, 0x68, 0x75, 0x62, 0x2e, 0x63, 0x6f, 0x6d, 0x2f, 0x70, 0x73, 0x76, 0x69, 0x64,
-	0x65, 0x72, 0x73, 0x6b, 0x69, 0x2f, 0x75, 0x6e, 0x63, 0x6c, 0x6f, 0x75, 0x64, 0x2f, 0x69, 0x6e,
-	0x74, 0x65, 0x72, 0x6e, 0x61, 0x6c, 0x2f, 0x6d, 0x61, 0x63, 0x68, 0x69, 0x6e, 0x65, 0x2f, 0x61,
-	0x70, 0x69, 0x2f, 0x70, 0x62, 0x62, 0x06, 0x70, 0x72, 0x6f, 0x74, 0x6f, 0x33,
+	0x79, 0x1a, 0x12, 0x2e, 0x61, 0x70, 0x69, 0x2e, 0x54, 0x6f, 0x6b, 0x65, 0x6e, 0x52, 0x65, 0x73,
+	0x70, 0x6f, 0x6e, 0x73, 0x65, 0x12, 0x33, 0x0a, 0x07, 0x49, 0x6e, 0x73, 0x70, 0x65, 0x63, 0x74,
+	0x12, 0x16, 0x2e, 0x67, 0x6f, 0x6f, 0x67, 0x6c, 0x65, 0x2e, 0x70, 0x72, 0x6f, 0x74, 0x6f, 0x62,
+	0x75, 0x66, 0x2e, 0x45, 0x6d, 0x70, 0x74, 0x79, 0x1a, 0x10, 0x2e, 0x61, 0x70, 0x69, 0x2e, 0x4d,
+	0x61, 0x63, 0x68, 0x69, 0x6e, 0x65, 0x49, 0x6e, 0x66, 0x6f, 0x12, 0x45, 0x0a, 0x0e, 0x49, 0x6e,
+	0x73, 0x70, 0x65, 0x63, 0x74, 0x4d, 0x61, 0x63, 0x68, 0x69, 0x6e, 0x65, 0x12, 0x16, 0x2e, 0x67,
+	0x6f, 0x6f, 0x67, 0x6c, 0x65, 0x2e, 0x70, 0x72, 0x6f, 0x74, 0x6f, 0x62, 0x75, 0x66, 0x2e, 0x45,
+	0x6d, 0x70, 0x74, 0x79, 0x1a, 0x1b, 0x2e, 0x61, 0x70, 0x69, 0x2e, 0x49, 0x6e, 0x73, 0x70, 0x65,
+	0x63, 0x74, 0x4d, 0x61, 0x63, 0x68, 0x69, 0x6e, 0x65, 0x52, 0x65, 0x73, 0x70, 0x6f, 0x6e, 0x73,
+	0x65, 0x12, 0x57, 0x0a, 0x17, 0x49, 0x6e, 0x73, 0x70, 0x65, 0x63, 0x74, 0x57, 0x69, 0x72, 0x65,
+	0x47, 0x75, 0x61, 0x72, 0x64, 0x4e, 0x65, 0x74, 0x77, 0x6f, 0x72, 0x6b, 0x12, 0x16, 0x2e, 0x67,
+	0x6f, 0x6f, 0x67, 0x6c, 0x65, 0x2e, 0x70, 0x72, 0x6f, 0x74, 0x6f, 0x62, 0x75, 0x66, 0x2e, 0x45,
+	0x6d, 0x70, 0x74, 0x79, 0x1a, 0x24, 0x2e, 0x61, 0x70, 0x69, 0x2e, 0x49, 0x6e, 0x73, 0x70, 0x65,
+	0x63, 0x74, 0x57, 0x69, 0x72, 0x65, 0x47, 0x75, 0x61, 0x72, 0x64, 0x4e, 0x65, 0x74, 0x77, 0x6f,
+	0x72, 0x6b, 0x52, 0x65, 0x73, 0x70, 0x6f, 0x6e, 0x73, 0x65, 0x12, 0x32, 0x0a, 0x05, 0x52, 0x65,
+	0x73, 0x65, 0x74, 0x12, 0x11, 0x2e, 0x61, 0x70, 0x69, 0x2e, 0x52, 0x65, 0x73, 0x65, 0x74, 0x52,
+	0x65, 0x71, 0x75, 0x65, 0x73, 0x74, 0x1a, 0x16, 0x2e, 0x67, 0x6f, 0x6f, 0x67, 0x6c, 0x65, 0x2e,
+	0x70, 0x72, 0x6f, 0x74, 0x6f, 0x62, 0x75, 0x66, 0x2e, 0x45, 0x6d, 0x70, 0x74, 0x79, 0x12, 0x49,
+	0x0a, 0x0e, 0x49, 0x6e, 0x73, 0x70, 0x65, 0x63, 0x74, 0x53, 0x65, 0x72, 0x76, 0x69, 0x63, 0x65,
+	0x12, 0x1a, 0x2e, 0x61, 0x70, 0x69, 0x2e, 0x49, 0x6e, 0x73, 0x70, 0x65, 0x63, 0x74, 0x53, 0x65,
+	0x72, 0x76, 0x69, 0x63, 0x65, 0x52, 0x65, 0x71, 0x75, 0x65, 0x73, 0x74, 0x1a, 0x1b, 0x2e, 0x61,
+	0x70, 0x69, 0x2e, 0x49, 0x6e, 0x73, 0x70, 0x65, 0x63, 0x74, 0x53, 0x65, 0x72, 0x76, 0x69, 0x63,
+	0x65, 0x52, 0x65, 0x73, 0x70, 0x6f, 0x6e, 0x73, 0x65, 0x42, 0x37, 0x5a, 0x35, 0x67, 0x69, 0x74,
+	0x68, 0x75, 0x62, 0x2e, 0x63, 0x6f, 0x6d, 0x2f, 0x70, 0x73, 0x76, 0x69, 0x64, 0x65, 0x72, 0x73,
+	0x6b, 0x69, 0x2f, 0x75, 0x6e, 0x63, 0x6c, 0x6f, 0x75, 0x64, 0x2f, 0x69, 0x6e, 0x74, 0x65, 0x72,
+	0x6e, 0x61, 0x6c, 0x2f, 0x6d, 0x61, 0x63, 0x68, 0x69, 0x6e, 0x65, 0x2f, 0x61, 0x70, 0x69, 0x2f,
+	0x70, 0x62, 0x62, 0x06, 0x70, 0x72, 0x6f, 0x74, 0x6f, 0x33,
 }
 
 var (
@@ -853,57 +1190,72 @@ func file_internal_machine_api_pb_machine_proto_rawDescGZIP() []byte {
 	return file_internal_machine_api_pb_machine_proto_rawDescData
 }
 
-var file_internal_machine_api_pb_machine_proto_msgTypes = make([]protoimpl.MessageInfo, 12)
+var file_internal_machine_api_pb_machine_proto_msgTypes = make([]protoimpl.MessageInfo, 16)
 var file_internal_machine_api_pb_machine_proto_goTypes = []any{
-	(*MachineInfo)(nil),                // 0: api.MachineInfo
-	(*NetworkConfig)(nil),              // 1: api.NetworkConfig
-	(*CheckPrerequisitesResponse)(nil), // 2: api.CheckPrerequisitesResponse
-	(*InitClusterRequest)(nil),         // 3: api.InitClusterRequest
-	(*InitClusterResponse)(nil),        // 4: api.InitClusterResponse
-	(*JoinClusterRequest)(nil),         // 5: api.JoinClusterRequest
-	(*TokenResponse)(nil),              // 6: api.TokenResponse
-	(*ResetRequest)(nil),               // 7: api.ResetRequest
-	(*Service)(nil),                    // 8: api.Service
-	(*InspectServiceRequest)(nil),      // 9: api.InspectServiceRequest
-	(*InspectServiceResponse)(nil),     // 10: api.InspectServiceResponse
-	(*Service_Container)(nil),          // 11: api.Service.Container
-	(*IP)(nil),                         // 12: api.IP
-	(*IPPrefix)(nil),                   // 13: api.IPPrefix
-	(*IPPort)(nil),                     // 14: api.IPPort
-	(*emptypb.Empty)(nil),              // 15: google.protobuf.Empty
+	(*MachineInfo)(nil),                     // 0: api.MachineInfo
+	(*NetworkConfig)(nil),                   // 1: api.NetworkConfig
+	(*CheckPrerequisitesResponse)(nil),      // 2: api.CheckPrerequisitesResponse
+	(*InitClusterRequest)(nil),              // 3: api.InitClusterRequest
+	(*InitClusterResponse)(nil),             // 4: api.InitClusterResponse
+	(*JoinClusterRequest)(nil),              // 5: api.JoinClusterRequest
+	(*InspectMachineResponse)(nil),          // 6: api.InspectMachineResponse
+	(*MachineDetails)(nil),                  // 7: api.MachineDetails
+	(*TokenResponse)(nil),                   // 8: api.TokenResponse
+	(*ResetRequest)(nil),                    // 9: api.ResetRequest
+	(*Service)(nil),                         // 10: api.Service
+	(*InspectServiceRequest)(nil),           // 11: api.InspectServiceRequest
+	(*InspectServiceResponse)(nil),          // 12: api.InspectServiceResponse
+	(*InspectWireGuardNetworkResponse)(nil), // 13: api.InspectWireGuardNetworkResponse
+	(*WireGuardPeer)(nil),                   // 14: api.WireGuardPeer
+	(*Service_Container)(nil),               // 15: api.Service.Container
+	(*IP)(nil),                              // 16: api.IP
+	(*IPPrefix)(nil),                        // 17: api.IPPrefix
+	(*IPPort)(nil),                          // 18: api.IPPort
+	(*Metadata)(nil),                        // 19: api.Metadata
+	(*timestamppb.Timestamp)(nil),           // 20: google.protobuf.Timestamp
+	(*emptypb.Empty)(nil),                   // 21: google.protobuf.Empty
 }
 var file_internal_machine_api_pb_machine_proto_depIdxs = []int32{
 	1,  // 0: api.MachineInfo.network:type_name -> api.NetworkConfig
-	12, // 1: api.MachineInfo.public_ip:type_name -> api.IP
-	13, // 2: api.NetworkConfig.subnet:type_name -> api.IPPrefix
-	12, // 3: api.NetworkConfig.management_ip:type_name -> api.IP
-	14, // 4: api.NetworkConfig.endpoints:type_name -> api.IPPort
-	13, // 5: api.InitClusterRequest.network:type_name -> api.IPPrefix
-	12, // 6: api.InitClusterRequest.public_ip:type_name -> api.IP
+	16, // 1: api.MachineInfo.public_ip:type_name -> api.IP
+	17, // 2: api.NetworkConfig.subnet:type_name -> api.IPPrefix
+	16, // 3: api.NetworkConfig.management_ip:type_name -> api.IP
+	18, // 4: api.NetworkConfig.endpoints:type_name -> api.IPPort
+	17, // 5: api.InitClusterRequest.network:type_name -> api.IPPrefix
+	16, // 6: api.InitClusterRequest.public_ip:type_name -> api.IP
 	0,  // 7: api.InitClusterResponse.machine:type_name -> api.MachineInfo
 	0,  // 8: api.JoinClusterRequest.machine:type_name -> api.MachineInfo
 	0,  // 9: api.JoinClusterRequest.other_machines:type_name -> api.MachineInfo
-	11, // 10: api.Service.containers:type_name -> api.Service.Container
-	8,  // 11: api.InspectServiceResponse.service:type_name -> api.Service
-	15, // 12: api.Machine.CheckPrerequisites:input_type -> google.protobuf.Empty
-	3,  // 13: api.Machine.InitCluster:input_type -> api.InitClusterRequest
-	5,  // 14: api.Machine.JoinCluster:input_type -> api.JoinClusterRequest
-	15, // 15: api.Machine.Token:input_type -> google.protobuf.Empty
-	15, // 16: api.Machine.Inspect:input_type -> google.protobuf.Empty
-	7,  // 17: api.Machine.Reset:input_type -> api.ResetRequest
-	9,  // 18: api.Machine.InspectService:input_type -> api.InspectServiceRequest
-	2,  // 19: api.Machine.CheckPrerequisites:output_type -> api.CheckPrerequisitesResponse
-	4,  // 20: api.Machine.InitCluster:output_type -> api.InitClusterResponse
-	15, // 21: api.Machine.JoinCluster:output_type -> google.protobuf.Empty
-	6,  // 22: api.Machine.Token:output_type -> api.TokenResponse
-	0,  // 23: api.Machine.Inspect:output_type -> api.MachineInfo
-	15, // 24: api.Machine.Reset:output_type -> google.protobuf.Empty
-	10, // 25: api.Machine.InspectService:output_type -> api.InspectServiceResponse
-	19, // [19:26] is the sub-list for method output_type
-	12, // [12:19] is the sub-list for method input_type
-	12, // [12:12] is the sub-list for extension type_name
-	12, // [12:12] is the sub-list for extension extendee
-	0,  // [0:12] is the sub-list for field type_name
+	7,  // 10: api.InspectMachineResponse.machines:type_name -> api.MachineDetails
+	19, // 11: api.MachineDetails.metadata:type_name -> api.Metadata
+	0,  // 12: api.MachineDetails.machine:type_name -> api.MachineInfo
+	15, // 13: api.Service.containers:type_name -> api.Service.Container
+	10, // 14: api.InspectServiceResponse.service:type_name -> api.Service
+	14, // 15: api.InspectWireGuardNetworkResponse.peers:type_name -> api.WireGuardPeer
+	20, // 16: api.WireGuardPeer.last_handshake_time:type_name -> google.protobuf.Timestamp
+	21, // 17: api.Machine.CheckPrerequisites:input_type -> google.protobuf.Empty
+	3,  // 18: api.Machine.InitCluster:input_type -> api.InitClusterRequest
+	5,  // 19: api.Machine.JoinCluster:input_type -> api.JoinClusterRequest
+	21, // 20: api.Machine.Token:input_type -> google.protobuf.Empty
+	21, // 21: api.Machine.Inspect:input_type -> google.protobuf.Empty
+	21, // 22: api.Machine.InspectMachine:input_type -> google.protobuf.Empty
+	21, // 23: api.Machine.InspectWireGuardNetwork:input_type -> google.protobuf.Empty
+	9,  // 24: api.Machine.Reset:input_type -> api.ResetRequest
+	11, // 25: api.Machine.InspectService:input_type -> api.InspectServiceRequest
+	2,  // 26: api.Machine.CheckPrerequisites:output_type -> api.CheckPrerequisitesResponse
+	4,  // 27: api.Machine.InitCluster:output_type -> api.InitClusterResponse
+	21, // 28: api.Machine.JoinCluster:output_type -> google.protobuf.Empty
+	8,  // 29: api.Machine.Token:output_type -> api.TokenResponse
+	0,  // 30: api.Machine.Inspect:output_type -> api.MachineInfo
+	6,  // 31: api.Machine.InspectMachine:output_type -> api.InspectMachineResponse
+	13, // 32: api.Machine.InspectWireGuardNetwork:output_type -> api.InspectWireGuardNetworkResponse
+	21, // 33: api.Machine.Reset:output_type -> google.protobuf.Empty
+	12, // 34: api.Machine.InspectService:output_type -> api.InspectServiceResponse
+	26, // [26:35] is the sub-list for method output_type
+	17, // [17:26] is the sub-list for method input_type
+	17, // [17:17] is the sub-list for extension type_name
+	17, // [17:17] is the sub-list for extension extendee
+	0,  // [0:17] is the sub-list for field type_name
 }
 
 func init() { file_internal_machine_api_pb_machine_proto_init() }
@@ -986,7 +1338,7 @@ func file_internal_machine_api_pb_machine_proto_init() {
 			}
 		}
 		file_internal_machine_api_pb_machine_proto_msgTypes[6].Exporter = func(v any, i int) any {
-			switch v := v.(*TokenResponse); i {
+			switch v := v.(*InspectMachineResponse); i {
 			case 0:
 				return &v.state
 			case 1:
@@ -998,7 +1350,7 @@ func file_internal_machine_api_pb_machine_proto_init() {
 			}
 		}
 		file_internal_machine_api_pb_machine_proto_msgTypes[7].Exporter = func(v any, i int) any {
-			switch v := v.(*ResetRequest); i {
+			switch v := v.(*MachineDetails); i {
 			case 0:
 				return &v.state
 			case 1:
@@ -1010,7 +1362,7 @@ func file_internal_machine_api_pb_machine_proto_init() {
 			}
 		}
 		file_internal_machine_api_pb_machine_proto_msgTypes[8].Exporter = func(v any, i int) any {
-			switch v := v.(*Service); i {
+			switch v := v.(*TokenResponse); i {
 			case 0:
 				return &v.state
 			case 1:
@@ -1022,7 +1374,7 @@ func file_internal_machine_api_pb_machine_proto_init() {
 			}
 		}
 		file_internal_machine_api_pb_machine_proto_msgTypes[9].Exporter = func(v any, i int) any {
-			switch v := v.(*InspectServiceRequest); i {
+			switch v := v.(*ResetRequest); i {
 			case 0:
 				return &v.state
 			case 1:
@@ -1034,7 +1386,7 @@ func file_internal_machine_api_pb_machine_proto_init() {
 			}
 		}
 		file_internal_machine_api_pb_machine_proto_msgTypes[10].Exporter = func(v any, i int) any {
-			switch v := v.(*InspectServiceResponse); i {
+			switch v := v.(*Service); i {
 			case 0:
 				return &v.state
 			case 1:
@@ -1046,6 +1398,54 @@ func file_internal_machine_api_pb_machine_proto_init() {
 			}
 		}
 		file_internal_machine_api_pb_machine_proto_msgTypes[11].Exporter = func(v any, i int) any {
+			switch v := v.(*InspectServiceRequest); i {
+			case 0:
+				return &v.state
+			case 1:
+				return &v.sizeCache
+			case 2:
+				return &v.unknownFields
+			default:
+				return nil
+			}
+		}
+		file_internal_machine_api_pb_machine_proto_msgTypes[12].Exporter = func(v any, i int) any {
+			switch v := v.(*InspectServiceResponse); i {
+			case 0:
+				return &v.state
+			case 1:
+				return &v.sizeCache
+			case 2:
+				return &v.unknownFields
+			default:
+				return nil
+			}
+		}
+		file_internal_machine_api_pb_machine_proto_msgTypes[13].Exporter = func(v any, i int) any {
+			switch v := v.(*InspectWireGuardNetworkResponse); i {
+			case 0:
+				return &v.state
+			case 1:
+				return &v.sizeCache
+			case 2:
+				return &v.unknownFields
+			default:
+				return nil
+			}
+		}
+		file_internal_machine_api_pb_machine_proto_msgTypes[14].Exporter = func(v any, i int) any {
+			switch v := v.(*WireGuardPeer); i {
+			case 0:
+				return &v.state
+			case 1:
+				return &v.sizeCache
+			case 2:
+				return &v.unknownFields
+			default:
+				return nil
+			}
+		}
+		file_internal_machine_api_pb_machine_proto_msgTypes[15].Exporter = func(v any, i int) any {
 			switch v := v.(*Service_Container); i {
 			case 0:
 				return &v.state
@@ -1068,7 +1468,7 @@ func file_internal_machine_api_pb_machine_proto_init() {
 			GoPackagePath: reflect.TypeOf(x{}).PkgPath(),
 			RawDescriptor: file_internal_machine_api_pb_machine_proto_rawDesc,
 			NumEnums:      0,
-			NumMessages:   12,
+			NumMessages:   16,
 			NumExtensions: 0,
 			NumServices:   1,
 		},

internal/machine/api/pb/machine.proto

@@ -5,6 +5,7 @@ package api;
 option go_package = "github.com/psviderski/uncloud/internal/machine/api/pb";
 
 import "google/protobuf/empty.proto";
+import "google/protobuf/timestamp.proto";
 import "internal/machine/api/pb/common.proto";
 
 service Machine {
@@ -13,7 +14,12 @@ service Machine {
   rpc InitCluster(InitClusterRequest) returns (InitClusterResponse);
   rpc JoinCluster(JoinClusterRequest) returns (google.protobuf.Empty);
   rpc Token(google.protobuf.Empty) returns (TokenResponse);
+  // Deprecated: use InspectMachine instead.
   rpc Inspect(google.protobuf.Empty) returns (MachineInfo);
+  // InspectMachine retrieves detailed information about the machine. Supports broadcasting to multiple machines.
+  rpc InspectMachine(google.protobuf.Empty) returns (InspectMachineResponse);
+  // InspectWireGuardNetwork retrieves the current WireGuard network configuration and peer status.
+  rpc InspectWireGuardNetwork(google.protobuf.Empty) returns (InspectWireGuardNetworkResponse);
   // Reset restores the machine to a clean state, removing all cluster-related configuration and data.
   rpc Reset(ResetRequest) returns (google.protobuf.Empty);
 
@@ -58,6 +64,20 @@ message InitClusterResponse {
 message JoinClusterRequest {
   MachineInfo machine = 1;
   repeated MachineInfo other_machines = 3;
+  // Minimum store database version the new machine should sync to before starting cluster operations.
+  int64 min_store_db_version = 4;
+}
+
+message InspectMachineResponse {
+  // Must contain only one repeated messages field to allow broadcasting InspectMachine requests to multiple machines.
+  repeated MachineDetails machines = 1;
+}
+
+message MachineDetails {
+  Metadata metadata = 1;
+  MachineInfo machine = 2;
+  // Current Corrosion cr-sqlite database version (Lamport timestamp) of the cluster store.
+  int64 store_db_version = 3;
 }
 
 message TokenResponse {
@@ -88,3 +108,19 @@ message InspectServiceRequest {
 message InspectServiceResponse {
   Service service = 1;
 }
+
+message InspectWireGuardNetworkResponse {
+  string interface_name = 1;
+  bytes public_key = 2;
+  int32 listen_port = 3;
+  repeated WireGuardPeer peers = 4;
+}
+
+message WireGuardPeer {
+  bytes public_key = 1;
+  string endpoint = 2;
+  google.protobuf.Timestamp last_handshake_time = 3;
+  int64 receive_bytes = 4;
+  int64 transmit_bytes = 5;
+  repeated string allowed_ips = 6;
+}

internal/machine/api/pb/machine_grpc.pb.go

@@ -20,13 +20,15 @@ import (
 const _ = grpc.SupportPackageIsVersion9
 
 const (
-	Machine_CheckPrerequisites_FullMethodName = "/api.Machine/CheckPrerequisites"
-	Machine_InitCluster_FullMethodName        = "/api.Machine/InitCluster"
-	Machine_JoinCluster_FullMethodName        = "/api.Machine/JoinCluster"
-	Machine_Token_FullMethodName              = "/api.Machine/Token"
-	Machine_Inspect_FullMethodName            = "/api.Machine/Inspect"
-	Machine_Reset_FullMethodName              = "/api.Machine/Reset"
-	Machine_InspectService_FullMethodName     = "/api.Machine/InspectService"
+	Machine_CheckPrerequisites_FullMethodName      = "/api.Machine/CheckPrerequisites"
+	Machine_InitCluster_FullMethodName             = "/api.Machine/InitCluster"
+	Machine_JoinCluster_FullMethodName             = "/api.Machine/JoinCluster"
+	Machine_Token_FullMethodName                   = "/api.Machine/Token"
+	Machine_Inspect_FullMethodName                 = "/api.Machine/Inspect"
+	Machine_InspectMachine_FullMethodName          = "/api.Machine/InspectMachine"
+	Machine_InspectWireGuardNetwork_FullMethodName = "/api.Machine/InspectWireGuardNetwork"
+	Machine_Reset_FullMethodName                   = "/api.Machine/Reset"
+	Machine_InspectService_FullMethodName          = "/api.Machine/InspectService"
 )
 
 // MachineClient is the client API for Machine service.
@@ -38,7 +40,12 @@ type MachineClient interface {
 	InitCluster(ctx context.Context, in *InitClusterRequest, opts ...grpc.CallOption) (*InitClusterResponse, error)
 	JoinCluster(ctx context.Context, in *JoinClusterRequest, opts ...grpc.CallOption) (*emptypb.Empty, error)
 	Token(ctx context.Context, in *emptypb.Empty, opts ...grpc.CallOption) (*TokenResponse, error)
+	// Deprecated: use InspectMachine instead.
 	Inspect(ctx context.Context, in *emptypb.Empty, opts ...grpc.CallOption) (*MachineInfo, error)
+	// InspectMachine retrieves detailed information about the machine. Supports broadcasting to multiple machines.
+	InspectMachine(ctx context.Context, in *emptypb.Empty, opts ...grpc.CallOption) (*InspectMachineResponse, error)
+	// InspectWireGuardNetwork retrieves the current WireGuard network configuration and peer status.
+	InspectWireGuardNetwork(ctx context.Context, in *emptypb.Empty, opts ...grpc.CallOption) (*InspectWireGuardNetworkResponse, error)
 	// Reset restores the machine to a clean state, removing all cluster-related configuration and data.
 	Reset(ctx context.Context, in *ResetRequest, opts ...grpc.CallOption) (*emptypb.Empty, error)
 	InspectService(ctx context.Context, in *InspectServiceRequest, opts ...grpc.CallOption) (*InspectServiceResponse, error)
@@ -102,6 +109,26 @@ func (c *machineClient) Inspect(ctx context.Context, in *emptypb.Empty, opts ...
 	return out, nil
 }
 
+func (c *machineClient) InspectMachine(ctx context.Context, in *emptypb.Empty, opts ...grpc.CallOption) (*InspectMachineResponse, error) {
+	cOpts := append([]grpc.CallOption{grpc.StaticMethod()}, opts...)
+	out := new(InspectMachineResponse)
+	err := c.cc.Invoke(ctx, Machine_InspectMachine_FullMethodName, in, out, cOpts...)
+	if err != nil {
+		return nil, err
+	}
+	return out, nil
+}
+
+func (c *machineClient) InspectWireGuardNetwork(ctx context.Context, in *emptypb.Empty, opts ...grpc.CallOption) (*InspectWireGuardNetworkResponse, error) {
+	cOpts := append([]grpc.CallOption{grpc.StaticMethod()}, opts...)
+	out := new(InspectWireGuardNetworkResponse)
+	err := c.cc.Invoke(ctx, Machine_InspectWireGuardNetwork_FullMethodName, in, out, cOpts...)
+	if err != nil {
+		return nil, err
+	}
+	return out, nil
+}
+
 func (c *machineClient) Reset(ctx context.Context, in *ResetRequest, opts ...grpc.CallOption) (*emptypb.Empty, error) {
 	cOpts := append([]grpc.CallOption{grpc.StaticMethod()}, opts...)
 	out := new(emptypb.Empty)
@@ -131,7 +158,12 @@ type MachineServer interface {
 	InitCluster(context.Context, *InitClusterRequest) (*InitClusterResponse, error)
 	JoinCluster(context.Context, *JoinClusterRequest) (*emptypb.Empty, error)
 	Token(context.Context, *emptypb.Empty) (*TokenResponse, error)
+	// Deprecated: use InspectMachine instead.
 	Inspect(context.Context, *emptypb.Empty) (*MachineInfo, error)
+	// InspectMachine retrieves detailed information about the machine. Supports broadcasting to multiple machines.
+	InspectMachine(context.Context, *emptypb.Empty) (*InspectMachineResponse, error)
+	// InspectWireGuardNetwork retrieves the current WireGuard network configuration and peer status.
+	InspectWireGuardNetwork(context.Context, *emptypb.Empty) (*InspectWireGuardNetworkResponse, error)
 	// Reset restores the machine to a clean state, removing all cluster-related configuration and data.
 	Reset(context.Context, *ResetRequest) (*emptypb.Empty, error)
 	InspectService(context.Context, *InspectServiceRequest) (*InspectServiceResponse, error)
@@ -160,6 +192,12 @@ func (UnimplementedMachineServer) Token(context.Context, *emptypb.Empty) (*Token
 func (UnimplementedMachineServer) Inspect(context.Context, *emptypb.Empty) (*MachineInfo, error) {
 	return nil, status.Errorf(codes.Unimplemented, "method Inspect not implemented")
 }
+func (UnimplementedMachineServer) InspectMachine(context.Context, *emptypb.Empty) (*InspectMachineResponse, error) {
+	return nil, status.Errorf(codes.Unimplemented, "method InspectMachine not implemented")
+}
+func (UnimplementedMachineServer) InspectWireGuardNetwork(context.Context, *emptypb.Empty) (*InspectWireGuardNetworkResponse, error) {
+	return nil, status.Errorf(codes.Unimplemented, "method InspectWireGuardNetwork not implemented")
+}
 func (UnimplementedMachineServer) Reset(context.Context, *ResetRequest) (*emptypb.Empty, error) {
 	return nil, status.Errorf(codes.Unimplemented, "method Reset not implemented")
 }
@@ -277,6 +315,42 @@ func _Machine_Inspect_Handler(srv interface{}, ctx context.Context, dec func(int
 	return interceptor(ctx, in, info, handler)
 }
 
+func _Machine_InspectMachine_Handler(srv interface{}, ctx context.Context, dec func(interface{}) error, interceptor grpc.UnaryServerInterceptor) (interface{}, error) {
+	in := new(emptypb.Empty)
+	if err := dec(in); err != nil {
+		return nil, err
+	}
+	if interceptor == nil {
+		return srv.(MachineServer).InspectMachine(ctx, in)
+	}
+	info := &grpc.UnaryServerInfo{
+		Server:     srv,
+		FullMethod: Machine_InspectMachine_FullMethodName,
+	}
+	handler := func(ctx context.Context, req interface{}) (interface{}, error) {
+		return srv.(MachineServer).InspectMachine(ctx, req.(*emptypb.Empty))
+	}
+	return interceptor(ctx, in, info, handler)
+}
+
+func _Machine_InspectWireGuardNetwork_Handler(srv interface{}, ctx context.Context, dec func(interface{}) error, interceptor grpc.UnaryServerInterceptor) (interface{}, error) {
+	in := new(emptypb.Empty)
+	if err := dec(in); err != nil {
+		return nil, err
+	}
+	if interceptor == nil {
+		return srv.(MachineServer).InspectWireGuardNetwork(ctx, in)
+	}
+	info := &grpc.UnaryServerInfo{
+		Server:     srv,
+		FullMethod: Machine_InspectWireGuardNetwork_FullMethodName,
+	}
+	handler := func(ctx context.Context, req interface{}) (interface{}, error) {
+		return srv.(MachineServer).InspectWireGuardNetwork(ctx, req.(*emptypb.Empty))
+	}
+	return interceptor(ctx, in, info, handler)
+}
+
 func _Machine_Reset_Handler(srv interface{}, ctx context.Context, dec func(interface{}) error, interceptor grpc.UnaryServerInterceptor) (interface{}, error) {
 	in := new(ResetRequest)
 	if err := dec(in); err != nil {
@@ -340,6 +414,14 @@ var Machine_ServiceDesc = grpc.ServiceDesc{
 			MethodName: "Inspect",
 			Handler:    _Machine_Inspect_Handler,
 		},
+		{
+			MethodName: "InspectMachine",
+			Handler:    _Machine_InspectMachine_Handler,
+		},
+		{
+			MethodName: "InspectWireGuardNetwork",
+			Handler:    _Machine_InspectWireGuardNetwork_Handler,
+		},
 		{
 			MethodName: "Reset",
 			Handler:    _Machine_Reset_Handler,

internal/machine/api/proxy/remote.go

@@ -80,6 +80,8 @@ func (b *RemoteBackend) GetConnection(ctx context.Context, _ string) (context.Co
 	backoffConfig.MaxDelay = 15 * time.Second
 
 	var err error
+	// This client keeps retrying connection in the background indefinitely even after the first connection fails
+	// and the Unavailable error is returned to the caller.
 	b.conn, err = grpc.NewClient(
 		b.target,
 		grpc.WithTransportCredentials(insecure.NewCredentials()),
@@ -88,7 +90,7 @@ func (b *RemoteBackend) GetConnection(ctx context.Context, _ string) (context.Co
 			// Not published as a constant in gRPC library.
 			// See: https://github.com/grpc/grpc-go/blob/d5dee5fdbdeb52f6ea10b37b2cc7ce37814642d7/clientconn.go#L55-L56
 			// Each connection attempt can take up to MinConnectTimeout.
-			MinConnectTimeout: 20 * time.Second,
+			MinConnectTimeout: 10 * time.Second,
 		}),
 		grpc.WithDefaultCallOptions(
 			grpc.ForceCodecV2(proxy.Codec()),

internal/machine/caddyconfig/caddyfile.go

@@ -12,14 +12,16 @@ import (
 	"strconv"
 	"strings"
 	"text/template"
+	"time"
 
 	"github.com/psviderski/uncloud/internal/machine/store"
 	"github.com/psviderski/uncloud/pkg/api"
 )
 
 const (
-	caddyfileHeader = `# This file is autogenerated by Uncloud based on the configuration of running services.
-# Do not edit manually. Any manual changes will be overwritten on the next update.
+	caddyfileHeaderFmt = `# Caddyfile autogenerated by Uncloud (DO NOT EDIT): %s
+# Automatically updated on service or health status changes.
+# Docs: https://uncloud.run/docs/concepts/ingress/overview
 `
 	caddyfileTemplate = `# Health check endpoint to verify Caddy reachability on this machine.
 http:// {
@@ -56,7 +58,9 @@ https://{{$hostname}} {
 }{{end}}
 `
 	caddyfileUnavailabeFooter = `# NOTE: User-defined configs for services were skipped because Caddy is not running on this machine
-#       or the latest generated config is invalid. Please check the Caddy logs if it's running.
+#       (not accessible via the shared admin socket /run/uncloud/caddy/admin.sock) or the latest
+#       generated config is invalid. Please check the service 'caddy' is running (uc inspect caddy)
+#       and its logs for more details (uc logs caddy).
 `
 )
 
@@ -120,6 +124,7 @@ func (g *CaddyfileGenerator) Generate(
 		return "", fmt.Errorf("generate base Caddyfile from service ports: %w", err)
 	}
 
+	caddyfileHeader := fmt.Sprintf(caddyfileHeaderFmt, time.Now().UTC().Format(time.RFC3339))
 	if !includeCustom {
 		return fmt.Sprintf("%s\n%s\n%s", caddyfileHeader, caddyfile, caddyfileUnavailabeFooter), nil
 	}

internal/machine/caddyconfig/caddyfile_test.go

@@ -3,6 +3,7 @@ package caddyconfig
 import (
 	"context"
 	"errors"
+	"regexp"
 	"strings"
 	"testing"
 	"time"
@@ -17,8 +18,17 @@ import (
 	"github.com/stretchr/testify/require"
 )
 
-const testCaddyfileHeader = `# This file is autogenerated by Uncloud based on the configuration of running services.
-# Do not edit manually. Any manual changes will be overwritten on the next update.
+// generatedTimestampRegex matches the "(DO NOT EDIT): <RFC3339 timestamp>" part of the header.
+var generatedTimestampRegex = regexp.MustCompile(`\(DO NOT EDIT\): \d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}Z`)
+
+// normaliseGeneratedTimestamp replaces dynamic timestamps with a placeholder for test comparison.
+func normaliseGeneratedTimestamp(caddyfile string) string {
+	return generatedTimestampRegex.ReplaceAllString(caddyfile, "(DO NOT EDIT): TIMESTAMP_PLACEHOLDER")
+}
+
+const testCaddyfileHeader = `# Caddyfile autogenerated by Uncloud (DO NOT EDIT): TIMESTAMP_PLACEHOLDER
+# Automatically updated on service or health status changes.
+# Docs: https://uncloud.run/docs/concepts/ingress/overview
 
 # Health check endpoint to verify Caddy reachability on this machine.
 http:// {
@@ -190,7 +200,7 @@ https://secure.example.com {
 			}
 			require.NoError(t, err)
 
-			assert.Equal(t, tt.want, config, "Generated Caddyfile doesn't match")
+			assert.Equal(t, tt.want, normaliseGeneratedTimestamp(config), "Generated Caddyfile doesn't match")
 		})
 	}
 }
@@ -216,8 +226,9 @@ func TestCaddyfileGeneratorWithCustomConfigs(t *testing.T) {
 					time.Now(),
 				),
 			},
-			want: `# This file is autogenerated by Uncloud based on the configuration of running services.
-# Do not edit manually. Any manual changes will be overwritten on the next update.
+			want: `# Caddyfile autogenerated by Uncloud (DO NOT EDIT): TIMESTAMP_PLACEHOLDER
+# Automatically updated on service or health status changes.
+# Docs: https://uncloud.run/docs/concepts/ingress/overview
 
 # User-defined global config from service 'caddy'.
 # Global Caddy configuration
@@ -412,8 +423,9 @@ web.example.com {
 					time.Now(),
 				),
 			},
-			want: `# This file is autogenerated by Uncloud based on the configuration of running services.
-# Do not edit manually. Any manual changes will be overwritten on the next update.
+			want: `# Caddyfile autogenerated by Uncloud (DO NOT EDIT): TIMESTAMP_PLACEHOLDER
+# Automatically updated on service or health status changes.
+# Docs: https://uncloud.run/docs/concepts/ingress/overview
 
 # User-defined global config from service 'caddy'.
 # Global config
@@ -649,8 +661,9 @@ badconfig.com {
 					time.Now(),
 				),
 			},
-			want: `# This file is autogenerated by Uncloud based on the configuration of running services.
-# Do not edit manually. Any manual changes will be overwritten on the next update.
+			want: `# Caddyfile autogenerated by Uncloud (DO NOT EDIT): TIMESTAMP_PLACEHOLDER
+# Automatically updated on service or health status changes.
+# Docs: https://uncloud.run/docs/concepts/ingress/overview
 
 # User-defined global config from service 'caddy'.
 # Global config from test machine
@@ -831,7 +844,7 @@ valid.example.com {
 			}
 			require.NoError(t, err)
 
-			assert.Equal(t, tt.want, config, "Generated Caddyfile doesn't match")
+			assert.Equal(t, tt.want, normaliseGeneratedTimestamp(config), "Generated Caddyfile doesn't match")
 		})
 	}
 }
@@ -926,7 +939,9 @@ http://api.example.com {
 }
 
 # NOTE: User-defined configs for services were skipped because Caddy is not running on this machine
-#       or the latest generated config is invalid. Please check the Caddy logs if it's running.
+#       (not accessible via the shared admin socket /run/uncloud/caddy/admin.sock) or the latest
+#       generated config is invalid. Please check the service 'caddy' is running (uc inspect caddy)
+#       and its logs for more details (uc logs caddy).
 `,
 		},
 		{
@@ -950,7 +965,9 @@ http://api.example.com {
 }
 
 # NOTE: User-defined configs for services were skipped because Caddy is not running on this machine
-#       or the latest generated config is invalid. Please check the Caddy logs if it's running.
+#       (not accessible via the shared admin socket /run/uncloud/caddy/admin.sock) or the latest
+#       generated config is invalid. Please check the service 'caddy' is running (uc inspect caddy)
+#       and its logs for more details (uc logs caddy).
 `,
 		},
 	}
@@ -964,7 +981,7 @@ http://api.example.com {
 			config, err := generator.Generate(ctx, tt.containers, false)
 			require.NoError(t, err)
 
-			assert.Equal(t, tt.want, config, "Generated Caddyfile doesn't match")
+			assert.Equal(t, tt.want, normaliseGeneratedTimestamp(config), "Generated Caddyfile doesn't match")
 		})
 	}
 }

internal/machine/cluster.go

@@ -40,7 +40,9 @@ type clusterController struct {
 	corroService corroservice.Service
 	dockerCtrl   *docker.Controller
 	// dockerReady is signalled when Docker is configured and ready for containers.
-	dockerReady     chan<- struct{}
+	dockerReady chan<- struct{}
+	// clusterReady is signalled when the cluster controller has finished initializing all components.
+	clusterReady    chan<- struct{}
 	caddyconfigCtrl *caddyconfig.Controller
 
 	// dnsServer is the embedded internal DNS server for the cluster listening on the machine IP.
@@ -60,6 +62,7 @@ func newClusterController(
 	corroService corroservice.Service,
 	dockerService *docker.Service,
 	dockerReady chan<- struct{},
+	clusterReady chan<- struct{},
 	caddyfileCtrl *caddyconfig.Controller,
 	dnsServer *dns.Server,
 	dnsResolver *dns.ClusterResolver,
@@ -81,6 +84,7 @@ func newClusterController(
 		corroService:    corroService,
 		dockerCtrl:      docker.NewController(state.ID, dockerService, store),
 		dockerReady:     dockerReady,
+		clusterReady:    clusterReady,
 		caddyconfigCtrl: caddyfileCtrl,
 		dnsServer:       dnsServer,
 		dnsResolver:     dnsResolver,
@@ -123,6 +127,21 @@ func (cc *clusterController) Run(ctx context.Context) error {
 
 	errGroup, ctx := errgroup.WithContext(ctx)
 
+	// Start the WireGuard control loop before waiting for store sync. This ensures endpoint rotation happens
+	// while waiting, allowing Corrosion to connect to peers.
+	errGroup.Go(func() error {
+		if err := cc.wgnet.Run(ctx); err != nil {
+			return fmt.Errorf("WireGuard network failed: %w", err)
+		}
+		return nil
+	})
+
+	// Watch for WireGuard peer endpoint changes and update the machine state accordingly.
+	errGroup.Go(func() error {
+		cc.handleEndpointChanges(ctx)
+		return nil
+	})
+
 	// Start the network API server. Assume the management IP can't be changed when the network is running.
 	apiAddr := net.JoinHostPort(cc.state.Network.ManagementIP.String(), strconv.Itoa(constants.MachineAPIPort))
 	listener, err := net.Listen("tcp", apiAddr)
@@ -137,6 +156,22 @@ func (cc *clusterController) Run(ctx context.Context) error {
 		return nil
 	})
 
+	// Wait for the store database to sync to the minimum version before starting store-dependent components.
+	// This prevents issues with using partially replicated data when the machine just joined the cluster,
+	// e.g., an empty machine list causing WireGuard peer misconfiguration.
+	cc.waitStoreSync(ctx)
+
+	// Check if waitStoreSync exited because the context was cancelled. Return early in that case.
+	if ctx.Err() != nil {
+		cc.stopAPIServer()
+
+		err := errGroup.Wait()
+		if corroErr := cc.stopCorrosion(); corroErr != nil {
+			err = errors.Join(err, corroErr)
+		}
+		return err
+	}
+
 	errGroup.Go(func() error {
 		slog.Info("Starting embedded DNS resolver.")
 		if err := cc.dnsResolver.Run(ctx); err != nil {
@@ -169,44 +204,6 @@ func (cc *clusterController) Run(ctx context.Context) error {
 		return nil
 	})
 
-	// Watch for WireGuard peer endpoint changes and update the machine state accordingly.
-	errGroup.Go(func() error {
-		for {
-			select {
-			case e, ok := <-cc.endpointChanges:
-				if !ok {
-					// The channel was closed, stop watching for changes.
-					cc.endpointChanges = nil
-					return nil
-				}
-
-				cc.state.mu.Lock()
-				for i := range cc.state.Network.Peers {
-					if cc.state.Network.Peers[i].PublicKey.Equal(e.PublicKey) {
-						cc.state.Network.Peers[i].Endpoint = &e.Endpoint
-						break
-					}
-				}
-				if err := cc.state.Save(); err != nil {
-					slog.Error("Failed to save machine state.", "err", err)
-				}
-				cc.state.mu.Unlock()
-
-				slog.Debug("Preserved endpoint change in the machine state.",
-					"public_key", e.PublicKey, "endpoint", e.Endpoint)
-			case <-ctx.Done():
-				return nil
-			}
-		}
-	})
-
-	errGroup.Go(func() error {
-		if err := cc.wgnet.Run(ctx); err != nil {
-			return fmt.Errorf("WireGuard network failed: %w", err)
-		}
-		return nil
-	})
-
 	errGroup.Go(func() error {
 		slog.Info("Starting caddyconfig controller.")
 		if err := cc.caddyconfigCtrl.Run(ctx); err != nil {
@@ -225,12 +222,13 @@ func (cc *clusterController) Run(ctx context.Context) error {
 		})
 	}
 
-	// Wait for the context to be done and stop the network API server.
+	// Signal that the cluster controller has finished starting all components.
+	close(cc.clusterReady)
+	slog.Info("Cluster controller finished starting all components.")
+	// Wait for the context to be done and stop all servers and controllers.
 	<-ctx.Done()
-	slog.Info("Stopping network API server.")
-	// TODO: implement timeout for graceful shutdown.
-	cc.server.GracefulStop()
-	slog.Info("Network API server stopped.")
+
+	cc.stopAPIServer()
 
 	// Stop the unregistry server with a timeout if it was started.
 	if cc.unregistry != nil {
@@ -248,19 +246,50 @@ func (cc *clusterController) Run(ctx context.Context) error {
 	// Wait for all controllers to finish.
 	err = errGroup.Wait()
 
-	// It's safe to stop the Corrosion service after the controllers depending on it and API server are stopped.
-	// Use a new context with a timeout as the current context is already canceled.
-	ctx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
-	defer cancel()
-	if corroErr := cc.corroService.Stop(ctx); corroErr != nil {
-		err = errors.Join(err, fmt.Errorf("stop corrosion service: %w", corroErr))
-	} else {
-		slog.Info("Corrosion service stopped.")
+	// Stop Corrosion after all controllers depending on it and API server are stopped.
+	if corroErr := cc.stopCorrosion(); corroErr != nil {
+		err = errors.Join(err, corroErr)
 	}
 
 	return err
 }
 
+// stopAPIServer gracefully stops the network API server with a timeout.
+func (cc *clusterController) stopAPIServer() {
+	timeout := 10 * time.Second
+	ctx, cancel := context.WithTimeout(context.Background(), timeout)
+	defer cancel()
+
+	stopped := make(chan struct{})
+	go func() {
+		slog.Info("Stopping network API server.")
+		cc.server.GracefulStop()
+		close(stopped)
+	}()
+
+	select {
+	case <-ctx.Done():
+		slog.Warn("Network API server graceful stop timed out, forcing stop.", "timeout", timeout)
+		cc.server.Stop()
+	case <-stopped:
+	}
+
+	slog.Info("Network API server stopped.")
+}
+
+// stopCorrosion stops the Corrosion service with a timeout.
+func (cc *clusterController) stopCorrosion() error {
+	ctx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
+	defer cancel()
+
+	if err := cc.corroService.Stop(ctx); err != nil {
+		return fmt.Errorf("stop corrosion service: %w", err)
+	}
+	slog.Info("Corrosion service stopped.")
+
+	return nil
+}
+
 // ensureDockerNetwork ensures that the Docker network is configured and ready for containers.
 func (cc *clusterController) ensureDockerNetwork(ctx context.Context) error {
 	if err := cc.dockerCtrl.WaitDaemonReady(ctx); err != nil {
@@ -281,6 +310,95 @@ func (cc *clusterController) ensureDockerNetwork(ctx context.Context) error {
 	return nil
 }
 
+// handleEndpointChanges watches for WireGuard peer endpoint changes and persists them to the machine state.
+func (cc *clusterController) handleEndpointChanges(ctx context.Context) {
+	for {
+		select {
+		case e, ok := <-cc.endpointChanges:
+			if !ok {
+				// The channel was closed, stop watching for changes.
+				cc.endpointChanges = nil
+				return
+			}
+
+			cc.state.mu.Lock()
+			for i := range cc.state.Network.Peers {
+				if cc.state.Network.Peers[i].PublicKey.Equal(e.PublicKey) {
+					cc.state.Network.Peers[i].Endpoint = &e.Endpoint
+					break
+				}
+			}
+			if err := cc.state.Save(); err != nil {
+				slog.Error("Failed to save machine state.", "err", err)
+			}
+			cc.state.mu.Unlock()
+
+			slog.Debug("Preserved endpoint change in the machine state.",
+				"public_key", e.PublicKey, "endpoint", e.Endpoint)
+		case <-ctx.Done():
+			return
+		}
+	}
+}
+
+// waitStoreSync waits for the store database to sync to the minimum required DB version if set in the machine state.
+// Blocks until synced or context is cancelled.
+func (cc *clusterController) waitStoreSync(ctx context.Context) {
+	minVersion := cc.state.MinStoreDBVersion
+	if minVersion == 0 {
+		return
+	}
+
+	slog.Info("Waiting for the initial cluster store sync.", "min_version", minVersion)
+
+	ticker := time.NewTicker(500 * time.Millisecond)
+	defer ticker.Stop()
+
+	var (
+		lastVersion    int64
+		lastLogTime    time.Time
+		lastErrLogTime time.Time
+	)
+
+	for {
+		select {
+		case <-ctx.Done():
+			return
+		case <-ticker.C:
+			version, err := cc.store.DBVersion(ctx)
+			if err != nil {
+				// Log errors at most once every 5 seconds.
+				if time.Since(lastErrLogTime) >= 5*time.Second {
+					slog.Error("Failed to get the cluster store DB version, retrying.", "err", err)
+					lastErrLogTime = time.Now()
+				}
+				continue
+			}
+
+			if version >= minVersion {
+				slog.Info("Cluster store completed the initial sync.", "version", version, "min_version", minVersion)
+
+				// Clear MinStoreDBVersion so next restart doesn't wait for sync.
+				cc.state.mu.Lock()
+				cc.state.MinStoreDBVersion = 0
+				if err := cc.state.Save(); err != nil {
+					slog.Error("Failed to save machine state after the initial cluster store sync.", "err", err)
+				}
+				cc.state.mu.Unlock()
+
+				return
+			}
+
+			// Log progress only once a second.
+			if version != lastVersion && time.Since(lastLogTime) >= 1*time.Second {
+				slog.Info("Syncing cluster store.", "version", version, "min_version", minVersion)
+				lastLogTime = time.Now()
+				lastVersion = version
+			}
+		}
+	}
+}
+
 // syncDockerContainers watches local Docker containers and syncs them to the cluster store.
 // TODO: move this to the Docker controller.
 func (cc *clusterController) syncDockerContainers(ctx context.Context) error {
@@ -340,6 +458,7 @@ func (cc *clusterController) handleMachineChanges(ctx context.Context) error {
 
 		// The machine store may be empty when a machine first joins the cluster, before store synchronization
 		// completes. Skip configuration now and apply it when the store changes are received.
+		// TODO: remove this check after releasing 0.17.0 and assuming cluster machines wait for store sync on join.
 		if len(machines) > 0 {
 			slog.Info("Reconfiguring network peers with the current machines.", "machines", len(machines))
 			if err = cc.configurePeers(machines); err != nil {

internal/machine/cluster/cluster.go

@@ -26,12 +26,19 @@ type Cluster struct {
 	corroAdmin *corrosion.AdminClient
 	// machineID is the ID of the current machine that is running the cluster service.
 	machineID string
+	// initialised is closed when the machine is configured as a member of a cluster.
+	initialised <-chan struct{}
+	// ready is closed when the cluster controller has finished starting all components
+	// and the machine is ready to serve cluster requests.
+	ready <-chan struct{}
 }
 
-func NewCluster(store *store.Store, corroAdmin *corrosion.AdminClient) *Cluster {
+func NewCluster(store *store.Store, corroAdmin *corrosion.AdminClient, initialised, ready <-chan struct{}) *Cluster {
 	return &Cluster{
-		store:      store,
-		corroAdmin: corroAdmin,
+		store:       store,
+		corroAdmin:  corroAdmin,
+		initialised: initialised,
+		ready:       ready,
 	}
 }
 
@@ -41,67 +48,45 @@ func (c *Cluster) UpdateMachineID(mid string) {
 }
 
 func (c *Cluster) Init(ctx context.Context, network netip.Prefix) error {
-	initialised, err := c.Initialised(ctx)
-	if err != nil {
-		return err
-	}
-	if initialised {
-		return fmt.Errorf("cluster is already initialised")
+	select {
+	case <-c.initialised:
+		return fmt.Errorf("cluster is already initialised on this machine")
+	default:
 	}
 
-	if err = c.store.Put(ctx, "network", network.String()); err != nil {
+	if err := c.store.Put(ctx, "network", network.String()); err != nil {
 		return fmt.Errorf("put network to store: %w", err)
 	}
-	if err = c.store.Put(ctx, "created_at", time.Now().UTC().Format(time.RFC3339)); err != nil {
+	if err := c.store.Put(ctx, "created_at", time.Now().UTC().Format(time.RFC3339)); err != nil {
 		return fmt.Errorf("put created_at to store: %w", err)
 	}
 	return nil
 }
 
-func (c *Cluster) Initialised(ctx context.Context) (bool, error) {
-	var createdAt string
-	if err := c.store.Get(ctx, "created_at", &createdAt); err != nil {
-		if errors.Is(err, store.ErrKeyNotFound) {
-			return false, nil
-		}
-		return false, status.Errorf(codes.Internal, "get created_at from store: %v", err)
+// checkReady checks if the machine is ready to serve cluster requests (store synced, cluster components started).
+func (c *Cluster) checkReady() error {
+	select {
+	case <-c.ready:
+		return nil
+	default:
+		return status.Error(codes.Unavailable, "machine is not ready to serve cluster requests")
 	}
-	return true, nil
-}
-
-func (c *Cluster) checkInitialised(ctx context.Context) error {
-	initialised, err := c.Initialised(ctx)
-	if err != nil {
-		return err
-	}
-	if !initialised {
-		return status.Error(codes.FailedPrecondition, "cluster is not initialised")
-	}
-	return nil
-}
-
-func (c *Cluster) Network(ctx context.Context) (netip.Prefix, error) {
-	if err := c.checkInitialised(ctx); err != nil {
-		return netip.Prefix{}, err
-	}
-
-	var net string
-	if err := c.store.Get(ctx, "network", &net); err != nil {
-		return netip.Prefix{}, status.Errorf(codes.Internal, "get network from store: %v", err)
-	}
-	prefix, err := netip.ParsePrefix(net)
-	if err != nil {
-		return netip.Prefix{}, status.Errorf(codes.Internal, "parse network prefix: %v", err)
-	}
-	return prefix, nil
 }
 
 // AddMachine adds a machine to the cluster.
 func (c *Cluster) AddMachine(ctx context.Context, req *pb.AddMachineRequest) (*pb.AddMachineResponse, error) {
-	if err := c.checkInitialised(ctx); err != nil {
+	if err := c.checkReady(); err != nil {
 		return nil, err
 	}
 
+	return c.AddMachineWithoutReadyCheck(ctx, req)
+}
+
+// AddMachineWithoutReadyCheck adds a machine to the cluster without checking if the cluster is ready.
+// This is used internally during cluster initialisation to add the first machine.
+func (c *Cluster) AddMachineWithoutReadyCheck(
+	ctx context.Context, req *pb.AddMachineRequest,
+) (*pb.AddMachineResponse, error) {
 	if req.Network == nil {
 		return nil, status.Error(codes.InvalidArgument, "network not set")
 	}
@@ -162,7 +147,7 @@ func (c *Cluster) AddMachine(ctx context.Context, req *pb.AddMachineRequest) (*p
 		manageIP = pb.NewIP(network.ManagementIP(req.Network.PublicKey))
 	}
 	// Allocate a subnet for the machine from the cluster network.
-	clusterNetwork, err := c.Network(ctx)
+	clusterNetwork, err := c.network(ctx)
 	if err != nil {
 		return nil, status.Errorf(codes.Internal, "get cluster network: %v", err)
 	}
@@ -198,9 +183,21 @@ func (c *Cluster) AddMachine(ctx context.Context, req *pb.AddMachineRequest) (*p
 	return resp, nil
 }
 
+func (c *Cluster) network(ctx context.Context) (netip.Prefix, error) {
+	var net string
+	if err := c.store.Get(ctx, "network", &net); err != nil {
+		return netip.Prefix{}, status.Errorf(codes.Internal, "get network from store: %v", err)
+	}
+	prefix, err := netip.ParsePrefix(net)
+	if err != nil {
+		return netip.Prefix{}, status.Errorf(codes.Internal, "parse network prefix: %v", err)
+	}
+	return prefix, nil
+}
+
 // UpdateMachine updates machine configuration in the cluster.
 func (c *Cluster) UpdateMachine(ctx context.Context, req *pb.UpdateMachineRequest) (*pb.UpdateMachineResponse, error) {
-	if err := c.checkInitialised(ctx); err != nil {
+	if err := c.checkReady(); err != nil {
 		return nil, err
 	}
 
@@ -283,7 +280,7 @@ func (c *Cluster) UpdateMachine(ctx context.Context, req *pb.UpdateMachineReques
 
 // ListMachines lists all machines in the cluster including their membership states.
 func (c *Cluster) ListMachines(ctx context.Context, _ *emptypb.Empty) (*pb.ListMachinesResponse, error) {
-	if err := c.checkInitialised(ctx); err != nil {
+	if err := c.checkReady(); err != nil {
 		return nil, err
 	}
 
@@ -329,7 +326,7 @@ func (c *Cluster) ListMachines(ctx context.Context, _ *emptypb.Empty) (*pb.ListM
 
 // RemoveMachine removes a machine from the cluster.
 func (c *Cluster) RemoveMachine(ctx context.Context, req *pb.RemoveMachineRequest) (*emptypb.Empty, error) {
-	if err := c.checkInitialised(ctx); err != nil {
+	if err := c.checkReady(); err != nil {
 		return nil, err
 	}
 

internal/machine/cluster/dns.go

@@ -25,7 +25,7 @@ type uncloudDNSDomain struct {
 }
 
 func (c *Cluster) ReserveDomain(ctx context.Context, req *pb.ReserveDomainRequest) (*pb.Domain, error) {
-	if err := c.checkInitialised(ctx); err != nil {
+	if err := c.checkReady(); err != nil {
 		return nil, err
 	}
 
@@ -64,7 +64,7 @@ func (c *Cluster) ReserveDomain(ctx context.Context, req *pb.ReserveDomainReques
 }
 
 func (c *Cluster) GetDomain(ctx context.Context, _ *emptypb.Empty) (*pb.Domain, error) {
-	if err := c.checkInitialised(ctx); err != nil {
+	if err := c.checkReady(); err != nil {
 		return nil, err
 	}
 
@@ -95,7 +95,7 @@ func (c *Cluster) storedDomain(ctx context.Context) (uncloudDNSDomain, error) {
 }
 
 func (c *Cluster) ReleaseDomain(ctx context.Context, _ *emptypb.Empty) (*pb.Domain, error) {
-	if err := c.checkInitialised(ctx); err != nil {
+	if err := c.checkReady(); err != nil {
 		return nil, err
 	}
 
@@ -115,7 +115,7 @@ func (c *Cluster) ReleaseDomain(ctx context.Context, _ *emptypb.Empty) (*pb.Doma
 func (c *Cluster) CreateDomainRecords(
 	ctx context.Context, req *pb.CreateDomainRecordsRequest,
 ) (*pb.CreateDomainRecordsResponse, error) {
-	if err := c.checkInitialised(ctx); err != nil {
+	if err := c.checkReady(); err != nil {
 		return nil, err
 	}
 

internal/machine/docker/server.go

@@ -33,6 +33,7 @@ import (
 	"github.com/docker/docker/client"
 	"github.com/docker/docker/pkg/stdcopy"
 	"github.com/docker/go-connections/nat"
+	"github.com/docker/go-units"
 	"github.com/google/go-containerregistry/pkg/authn"
 	"github.com/google/go-containerregistry/pkg/name"
 	"github.com/google/go-containerregistry/pkg/v1/remote"
@@ -566,6 +567,22 @@ func (s *Server) CreateServiceContainer(
 	if spec.Mode == "" {
 		config.Labels[api.LabelServiceMode] = api.ServiceModeReplicated
 	}
+	if hc := spec.Container.Healthcheck; hc != nil {
+		if hc.Disable {
+			config.Healthcheck = &container.HealthConfig{
+				Test: []string{"NONE"},
+			}
+		} else {
+			config.Healthcheck = &container.HealthConfig{
+				Test:          hc.Test,
+				Interval:      hc.Interval,
+				Timeout:       hc.Timeout,
+				StartPeriod:   hc.StartPeriod,
+				StartInterval: hc.StartInterval,
+				Retries:       int(hc.Retries),
+			}
+		}
+	}
 
 	// TODO: do not set the ports as container labels once migrated to retrieve them from the spec in DB.
 	var err error
@@ -605,6 +622,8 @@ func (s *Server) CreateServiceContainer(
 		}
 	}
 	hostConfig := &container.HostConfig{
+		CapAdd:       spec.Container.CapAdd,
+		CapDrop:      spec.Container.CapDrop,
 		Binds:        spec.Container.Volumes,
 		Init:         spec.Container.Init,
 		Mounts:       mounts,
@@ -614,13 +633,16 @@ func (s *Server) CreateServiceContainer(
 			NanoCPUs:          spec.Container.Resources.CPU,
 			Memory:            spec.Container.Resources.Memory,
 			MemoryReservation: spec.Container.Resources.MemoryReservation,
+			Devices:           toDockerDevices(spec.Container.Resources.Devices),
 			DeviceRequests:    spec.Container.Resources.DeviceReservations,
+			Ulimits:           toDockerUlimits(spec.Container.Resources.Ulimits),
 		},
 		// Restart service containers if they exit or a machine restarts unless they are explicitly stopped.
 		// For one-off containers and batch jobs we plan to use a different service type/mode.
 		RestartPolicy: container.RestartPolicy{
 			Name: container.RestartPolicyUnlessStopped,
 		},
+		Sysctls: spec.Container.Sysctls,
 	}
 
 	// Configure the container to use the internal DNS server if it's available.
@@ -801,14 +823,17 @@ func (s *Server) injectConfigs(ctx context.Context, containerID string, configs
 }
 
 // copyContentToContainer copies content directly to a file in the container using Docker's CopyToContainer API.
+// It will create any intermediate directories in the target path that don't exist.
 func (s *Server) copyContentToContainer(ctx context.Context, containerID string, content []byte, targetPath string, uid *uint64, gid *uint64, fileMode os.FileMode) error {
-	// Create a tar archive containing the file
 	var buf bytes.Buffer
 	tw := tar.NewWriter(&buf)
 
-	// Create tar header
+	// Trim leading slash(es) to avoid double slashes in the tar path
+	tarPath := strings.TrimPrefix(targetPath, "/")
+
+	// Create tar header with full path
 	header := &tar.Header{
-		Name:     filepath.Base(targetPath),
+		Name:     tarPath,
 		Size:     int64(len(content)),
 		Mode:     int64(fileMode),
 		ModTime:  time.Now(),
@@ -834,16 +859,12 @@ func (s *Server) copyContentToContainer(ctx context.Context, containerID string,
 		return fmt.Errorf("close tar writer: %w", err)
 	}
 
-	// Copy the tar archive to the container
-	targetDir := filepath.Dir(targetPath)
-	if targetDir == "." {
-		targetDir = "/"
-	}
-
+	// Always extract to root. The tar archive contains the full path, so tar will
+	// automatically create any intermediate directories that don't exist in the container.
 	if err := s.client.CopyToContainer(
 		ctx,
 		containerID,
-		targetDir,
+		"/",
 		&buf,
 		container.CopyToContainerOptions{CopyUIDGID: true},
 	); err != nil {
@@ -875,6 +896,40 @@ func toDockerBindOptions(opts *api.BindOptions) *mount.BindOptions {
 	return dockerOpts
 }
 
+func toDockerUlimits(ulimits map[string]api.Ulimit) []*units.Ulimit {
+	if len(ulimits) == 0 {
+		return nil
+	}
+
+	dockerUlimits := make([]*units.Ulimit, 0, len(ulimits))
+	for name, u := range ulimits {
+		dockerUlimits = append(dockerUlimits, &units.Ulimit{
+			Name: name,
+			Soft: u.Soft,
+			Hard: u.Hard,
+		})
+	}
+
+	return dockerUlimits
+}
+
+func toDockerDevices(devices []api.DeviceMapping) []container.DeviceMapping {
+	if len(devices) == 0 {
+		return nil
+	}
+
+	dockerDevices := make([]container.DeviceMapping, 0, len(devices))
+	for _, d := range devices {
+		dockerDevices = append(dockerDevices, container.DeviceMapping{
+			PathOnHost:        d.HostPath,
+			PathInContainer:   d.ContainerPath,
+			CgroupPermissions: d.CgroupPermissions,
+		})
+	}
+
+	return dockerDevices
+}
+
 // verifyDockerVolumesExist checks if the Docker named volumes referenced in the mounts exist on the machine.
 func (s *Server) verifyDockerVolumesExist(ctx context.Context, mounts []mount.Mount) error {
 	for _, m := range mounts {

internal/machine/machine.go

@@ -33,10 +33,12 @@ import (
 	"github.com/psviderski/unregistry"
 	"github.com/siderolabs/grpc-proxy/proxy"
 	"golang.org/x/sync/errgroup"
+	"golang.zx2c4.com/wireguard/wgctrl"
 	"google.golang.org/grpc"
 	"google.golang.org/grpc/codes"
 	"google.golang.org/grpc/status"
 	"google.golang.org/protobuf/types/known/emptypb"
+	"google.golang.org/protobuf/types/known/timestamppb"
 )
 
 const (
@@ -174,10 +176,13 @@ type Machine struct {
 	state  *State
 	// started is closed when the machine is ready to serve requests on the local API server.
 	started chan struct{}
-	// initialised is signalled when the machine is configured as a member of a cluster.
+	// initialised is closed when the machine is configured as a member of a cluster.
 	initialised chan struct{}
-	// networkReady is signalled when the Docker network is configured and ready for containers.
+	// networkReady is closed when the Docker network is configured and ready for containers.
 	networkReady chan struct{}
+	// clusterReady is closed when the cluster controller has finished starting all components
+	// and the machine is ready to serve cluster requests.
+	clusterReady chan struct{}
 	// resetting is true when the machine is being reset.
 	resetting bool
 	// stop cancels the Run method context to stop the machine gracefully.
@@ -246,7 +251,10 @@ func NewMachine(config *Config) (*Machine, error) {
 	if err != nil {
 		return nil, fmt.Errorf("create corrosion admin client: %w", err)
 	}
-	c := cluster.NewCluster(corroStore, corroAdmin)
+
+	initialised := make(chan struct{})
+	clusterReady := make(chan struct{})
+	c := cluster.NewCluster(corroStore, corroAdmin, initialised, clusterReady)
 
 	// Init dependencies for a gRPC Docker server that proxies requests to the local Docker daemon.
 	dbFilePath := filepath.Join(config.DataDir, DBFileName)
@@ -269,8 +277,9 @@ func NewMachine(config *Config) (*Machine, error) {
 		config:           *config,
 		state:            state,
 		started:          make(chan struct{}),
-		initialised:      make(chan struct{}, 1),
+		initialised:      initialised,
 		networkReady:     make(chan struct{}),
+		clusterReady:     clusterReady,
 		store:            corroStore,
 		cluster:          c,
 		dockerService:    dockerService,
@@ -294,7 +303,7 @@ func NewMachine(config *Config) (*Machine, error) {
 	m.localMachineServer = newGRPCServer(m, c, m.dockerServer, caddyServer)
 
 	if m.Initialised() {
-		m.initialised <- struct{}{}
+		close(m.initialised)
 	}
 
 	return m, nil
@@ -475,6 +484,7 @@ func (m *Machine) Run(ctx context.Context) error {
 				m.config.CorrosionService,
 				m.dockerService,
 				m.networkReady,
+				m.clusterReady,
 				caddyconfigCtrl,
 				dnsServer,
 				dnsResolver,
@@ -722,7 +732,7 @@ func (m *Machine) InitCluster(ctx context.Context, req *pb.InitClusterRequest) (
 		addReq.PublicIp = pb.NewIP(publicIP)
 	}
 
-	addResp, err := m.cluster.AddMachine(ctx, addReq)
+	addResp, err := m.cluster.AddMachineWithoutReadyCheck(ctx, addReq)
 	if err != nil {
 		return nil, status.Errorf(codes.Internal, "add machine to cluster: %v", err)
 	}
@@ -749,7 +759,7 @@ func (m *Machine) InitCluster(ctx context.Context, req *pb.InitClusterRequest) (
 	}
 	slog.Info("Cluster initialised with machine.", "id", m.state.ID, "machine", m.state.Name)
 	// Signal that the machine is initialised as a member of a cluster.
-	m.initialised <- struct{}{}
+	close(m.initialised)
 
 	resp := &pb.InitClusterResponse{
 		Machine: addResp.Machine,
@@ -792,6 +802,7 @@ func (m *Machine) JoinCluster(_ context.Context, req *pb.JoinClusterRequest) (*e
 		PrivateKey:   m.state.Network.PrivateKey,
 		PublicKey:    m.state.Network.PublicKey,
 	}
+	m.state.MinStoreDBVersion = req.MinStoreDbVersion
 
 	// Build a peers config from other cluster machines.
 	m.state.Network.Peers = make([]network.PeerConfig, 0, len(req.OtherMachines))
@@ -830,7 +841,7 @@ func (m *Machine) JoinCluster(_ context.Context, req *pb.JoinClusterRequest) (*e
 		"peers", len(m.state.Network.Peers),
 	)
 	// Signal that the machine is initialised as a member of a cluster.
-	m.initialised <- struct{}{}
+	close(m.initialised)
 
 	return &emptypb.Empty{}, nil
 }
@@ -864,6 +875,7 @@ func (m *Machine) Token(_ context.Context, _ *emptypb.Empty) (*pb.TokenResponse,
 	return &pb.TokenResponse{Token: tokenStr}, nil
 }
 
+// Deprecated: use InspectMachine instead.
 func (m *Machine) Inspect(_ context.Context, _ *emptypb.Empty) (*pb.MachineInfo, error) {
 	return &pb.MachineInfo{
 		Id:   m.state.ID,
@@ -876,6 +888,31 @@ func (m *Machine) Inspect(_ context.Context, _ *emptypb.Empty) (*pb.MachineInfo,
 	}, nil
 }
 
+func (m *Machine) InspectMachine(ctx context.Context, _ *emptypb.Empty) (*pb.InspectMachineResponse, error) {
+	dbVersion, err := m.store.DBVersion(ctx)
+	if err != nil {
+		return nil, status.Errorf(codes.Internal, "get database version of the cluster store: %v", err)
+	}
+
+	return &pb.InspectMachineResponse{
+		Machines: []*pb.MachineDetails{
+			{
+				// Metadata is injected by the gRPC proxy.
+				Machine: &pb.MachineInfo{
+					Id:   m.state.ID,
+					Name: m.state.Name,
+					Network: &pb.NetworkConfig{
+						Subnet:       pb.NewIPPrefix(m.state.Network.Subnet),
+						ManagementIp: pb.NewIP(m.state.Network.ManagementIP),
+						PublicKey:    m.state.Network.PublicKey,
+					},
+				},
+				StoreDbVersion: dbVersion,
+			},
+		},
+	}, nil
+}
+
 // IsNetworkReady returns true if the Docker network is ready for containers.
 func (m *Machine) IsNetworkReady() bool {
 	if !m.Initialised() {
@@ -909,6 +946,58 @@ func (m *Machine) WaitForNetworkReady(ctx context.Context) error {
 	}
 }
 
+// InspectWireGuardNetwork retrieves the current WireGuard network configuration and peer status.
+func (m *Machine) InspectWireGuardNetwork(
+	_ context.Context, _ *emptypb.Empty,
+) (*pb.InspectWireGuardNetworkResponse, error) {
+	deviceName := network.WireGuardInterfaceName
+
+	wg, err := wgctrl.New()
+	if err != nil {
+		return nil, fmt.Errorf("create WireGuard client: %w", err)
+	}
+	defer wg.Close()
+
+	dev, err := wg.Device(deviceName)
+	if err != nil {
+		return nil, fmt.Errorf("get WireGuard device '%s': %w", deviceName, err)
+	}
+
+	peers := make([]*pb.WireGuardPeer, len(dev.Peers))
+	for i, p := range dev.Peers {
+		var lastHandshake *timestamppb.Timestamp
+		if !p.LastHandshakeTime.IsZero() {
+			lastHandshake = timestamppb.New(p.LastHandshakeTime)
+		}
+
+		allowedIPs := make([]string, len(p.AllowedIPs))
+		for j, ip := range p.AllowedIPs {
+			allowedIPs[j] = ip.String()
+		}
+
+		var endpoint string
+		if p.Endpoint != nil {
+			endpoint = p.Endpoint.String()
+		}
+
+		peers[i] = &pb.WireGuardPeer{
+			PublicKey:         p.PublicKey[:],
+			Endpoint:          endpoint,
+			LastHandshakeTime: lastHandshake,
+			ReceiveBytes:      p.ReceiveBytes,
+			TransmitBytes:     p.TransmitBytes,
+			AllowedIps:        allowedIPs,
+		}
+	}
+
+	return &pb.InspectWireGuardNetworkResponse{
+		InterfaceName: dev.Name,
+		PublicKey:     dev.PublicKey[:],
+		ListenPort:    int32(dev.ListenPort),
+		Peers:         peers,
+	}, nil
+}
+
 // Reset restores the machine to a clean state, scheduling a graceful shutdown and removing all cluster-related
 // configuration and resource. The uncloud daemon will restart the machine if managed by systemd.
 func (m *Machine) Reset(_ context.Context, _ *pb.ResetRequest) (*emptypb.Empty, error) {

internal/machine/state.go

@@ -24,6 +24,9 @@ type State struct {
 	Name string
 	// Network specifies the network configuration for this machine.
 	Network *network.Config
+	// MinStoreDBVersion is the latest database version of one of the existing cluster machines at the time this machine
+	// joined the cluster. The machine should sync to at least this version before starting any cluster operations.
+	MinStoreDBVersion int64 `json:",omitempty"`
 
 	// path is the file path config is read from and saved to.
 	path string
@@ -66,7 +69,7 @@ func (c *State) Encode() ([]byte, error) {
 	return data, nil
 }
 
-// Save writes the state data to the file at the given path.
+// Save atomically writes the state data to the file at the configured path.
 func (c *State) Save() error {
 	if c.path == "" {
 		return fmt.Errorf("state path not set")
@@ -80,5 +83,37 @@ func (c *State) Save() error {
 	if err != nil {
 		return err
 	}
-	return os.WriteFile(c.path, data, 0o600)
+
+	// Write to a temporary file and rename for atomic save. CreateTemp creates a file with mode 0o600.
+	tmpFile, err := os.CreateTemp(dir, ".machine.json.*")
+	if err != nil {
+		return fmt.Errorf("create temp file: %w", err)
+	}
+	tmpPath := tmpFile.Name()
+
+	// Clean up temp file on error.
+	defer func() {
+		if err != nil {
+			os.Remove(tmpPath)
+		}
+	}()
+
+	if _, err = tmpFile.Write(data); err != nil {
+		tmpFile.Close()
+		return fmt.Errorf("write temp file: %w", err)
+	}
+	// Without fsync, the data may only be in the OS buffer cache. If the system crashes before the OS flushes
+	// it to disk, the file could be empty or corrupted even after rename.
+	if err = tmpFile.Sync(); err != nil {
+		tmpFile.Close()
+		return fmt.Errorf("sync temp file: %w", err)
+	}
+	if err = tmpFile.Close(); err != nil {
+		return fmt.Errorf("close temp file: %w", err)
+	}
+	if err = os.Rename(tmpPath, c.path); err != nil {
+		return fmt.Errorf("rename temp file: %w", err)
+	}
+
+	return nil
 }

internal/machine/store/container.go

@@ -82,7 +82,7 @@ func (s *Store) CreateOrUpdateContainer(ctx context.Context, ctr api.ServiceCont
 
 // ListContainers returns a list of container records from the store database that match the given options.
 func (s *Store) ListContainers(ctx context.Context, opts ListOptions) ([]ContainerRecord, error) {
-	q := sq.Select("container", "machine_id", "sync_status", "updated_at").From("containers").
+	q := sq.Select("id", "container", "machine_id", "sync_status", "updated_at").From("containers").
 		Where(sq.Eq{"sync_status": SyncStatusSynced})
 
 	if len(opts.MachineIDs) > 0 {
@@ -112,14 +112,23 @@ func (s *Store) ListContainers(ctx context.Context, opts ListOptions) ([]Contain
 	defer rows.Close()
 
 	var containers []ContainerRecord
-	var cJSON, machineID, syncStatus, updatedAtStr string
+	var id, cJSON, machineID, syncStatus, updatedAtStr string
 	var updatedAt time.Time
+	skipped := 0
 
 	for rows.Next() {
-		if err = rows.Scan(&cJSON, &machineID, &syncStatus, &updatedAtStr); err != nil {
+		if err = rows.Scan(&id, &cJSON, &machineID, &syncStatus, &updatedAtStr); err != nil {
 			return nil, fmt.Errorf("scan container record: %w", err)
 		}
 
+		// Skip containers with empty JSON data. This can happen during partial replication
+		// when cr-sqlite has created the row but the container column hasn't been synced yet.
+		if cJSON == "" || cJSON == "{}" {
+			slog.Debug("Skipping container with empty data in the store (partial replication?).", "id", id)
+			skipped++
+			continue
+		}
+
 		var c api.ServiceContainer
 		if err = json.Unmarshal([]byte(cJSON), &c); err != nil {
 			return nil, fmt.Errorf("unmarshal container: %w", err)
@@ -135,6 +144,11 @@ func (s *Store) ListContainers(ctx context.Context, opts ListOptions) ([]Contain
 		})
 	}
 
+	if skipped > 0 {
+		slog.Warn("Listing containers from the store skipped empty records (possibly due to partial replication).",
+			"skipped", skipped, "valid", len(containers))
+	}
+
 	return containers, nil
 }
 
@@ -166,7 +180,7 @@ func (s *Store) DeleteContainers(ctx context.Context, opts DeleteOptions) error
 // receive any values, it just signals when a container(s) has been added, updated, or deleted in the database.
 func (s *Store) SubscribeContainers(ctx context.Context) ([]ContainerRecord, <-chan struct{}, error) {
 	// TODO: figure out whether we need sync_status at all (not used at the moment).
-	q := sq.Select("container", "machine_id", "sync_status", "updated_at").From("containers").
+	q := sq.Select("id", "container", "machine_id", "sync_status", "updated_at").From("containers").
 		Where(sq.Eq{"sync_status": SyncStatusSynced})
 	query, args, err := q.ToSql()
 	if err != nil {
@@ -179,15 +193,24 @@ func (s *Store) SubscribeContainers(ctx context.Context) ([]ContainerRecord, <-c
 	}
 
 	var containers []ContainerRecord
-	var cJSON, updatedAtStr string
+	var id, cJSON, updatedAtStr string
+	skipped := 0
 
 	rows := sub.Rows()
 	for rows.Next() {
 		var cr ContainerRecord
-		if err = rows.Scan(&cJSON, &cr.MachineID, &cr.SyncStatus, &updatedAtStr); err != nil {
+		if err = rows.Scan(&id, &cJSON, &cr.MachineID, &cr.SyncStatus, &updatedAtStr); err != nil {
 			return nil, nil, err
 		}
 
+		// Skip containers with empty JSON data. This can happen during partial replication
+		// when cr-sqlite has created the row but the container column hasn't been synced yet.
+		if cJSON == "" || cJSON == "{}" {
+			slog.Debug("Skipping container with empty data in the store (partial replication?).", "id", id)
+			skipped++
+			continue
+		}
+
 		if err = json.Unmarshal([]byte(cJSON), &cr.Container); err != nil {
 			return nil, nil, fmt.Errorf("unmarshal container: %w", err)
 		}
@@ -196,6 +219,12 @@ func (s *Store) SubscribeContainers(ctx context.Context) ([]ContainerRecord, <-c
 		}
 		containers = append(containers, cr)
 	}
+
+	if skipped > 0 {
+		slog.Warn("Container subscription skipped empty records in the store (possibly due to partial replication).",
+			"skipped", skipped, "valid", len(containers))
+	}
+
 	events, err := sub.Changes()
 	if err != nil {
 		return nil, nil, fmt.Errorf("get subscription changes: %w", err)

internal/machine/store/store.go

@@ -56,6 +56,25 @@ func (s *Store) Delete(ctx context.Context, key string) error {
 	return err
 }
 
+// DBVersion returns the current cr-sqlite database version (Lamport timestamp).
+func (s *Store) DBVersion(ctx context.Context) (int64, error) {
+	rows, err := s.corro.QueryContext(ctx, "SELECT crsql_db_version()")
+	if err != nil {
+		return 0, fmt.Errorf("query crsql_db_version(): %w", err)
+	}
+	defer rows.Close()
+
+	if !rows.Next() {
+		return 0, fmt.Errorf("no result from crsql_db_version()")
+	}
+
+	var version int64
+	if err = rows.Scan(&version); err != nil {
+		return 0, fmt.Errorf("scan db version: %w", err)
+	}
+	return version, nil
+}
+
 func (s *Store) CreateMachine(ctx context.Context, m *pb.MachineInfo) error {
 	mJSON, err := protojson.Marshal(m)
 	if err != nil {
@@ -116,19 +135,29 @@ func (s *Store) GetMachine(ctx context.Context, machineID string) (*pb.MachineIn
 }
 
 func (s *Store) ListMachines(ctx context.Context) ([]*pb.MachineInfo, error) {
-	rows, err := s.corro.QueryContext(ctx, "SELECT info FROM machines ORDER BY name")
+	rows, err := s.corro.QueryContext(ctx, "SELECT id, info FROM machines ORDER BY name")
 	if err != nil {
 		return nil, err
 	}
 	defer rows.Close()
 
 	var machines []*pb.MachineInfo
+	skipped := 0
+
 	for rows.Next() {
-		var mJSON string
-		if err = rows.Scan(&mJSON); err != nil {
+		var id, mJSON string
+		if err = rows.Scan(&id, &mJSON); err != nil {
 			return nil, err
 		}
 
+		// Skip machines with empty JSON data. This can happen during partial replication
+		// when cr-sqlite has created the row but the info column hasn't been synced yet.
+		if mJSON == "" || mJSON == "{}" {
+			slog.Debug("Skipping machine with empty data in the store (partial replication?).", "id", id)
+			skipped++
+			continue
+		}
+
 		protojsonParser := protojson.UnmarshalOptions{DiscardUnknown: true}
 		var m pb.MachineInfo
 		if err = protojsonParser.Unmarshal([]byte(mJSON), &m); err != nil {
@@ -141,6 +170,12 @@ func (s *Store) ListMachines(ctx context.Context) ([]*pb.MachineInfo, error) {
 		}
 		machines = append(machines, &m)
 	}
+
+	if skipped > 0 {
+		slog.Warn("Listing machines from the store skipped empty records (possibly due to partial replication).",
+			"skipped", skipped, "valid", len(machines))
+	}
+
 	return machines, nil
 }
 
@@ -186,24 +221,41 @@ func (s *Store) DeleteMachine(ctx context.Context, id string) error {
 // SubscribeMachines returns a list of machines and a channel that signals changes to the list. The channel doesn't
 // receive any values, it just signals when a machine has been added, updated, or deleted in the database.
 func (s *Store) SubscribeMachines(ctx context.Context) ([]*pb.MachineInfo, <-chan struct{}, error) {
-	sub, err := s.corro.SubscribeContext(ctx, "SELECT info FROM machines ORDER BY name", nil, false)
+	sub, err := s.corro.SubscribeContext(ctx, "SELECT id, info FROM machines ORDER BY name", nil, false)
 	if err != nil {
 		return nil, nil, err
 	}
 
 	rows := sub.Rows()
 	var machines []*pb.MachineInfo
+	skipped := 0
+
 	for rows.Next() {
-		var mJSON string
-		if err = rows.Scan(&mJSON); err != nil {
+		var id, mJSON string
+		if err = rows.Scan(&id, &mJSON); err != nil {
 			return nil, nil, err
 		}
+
+		// Skip machines with empty JSON data. This can happen during partial replication
+		// when cr-sqlite has created the row but the info column hasn't been synced yet.
+		if mJSON == "" || mJSON == "{}" {
+			slog.Debug("Skipping machine with empty data in the store (partial replication?).", "id", id)
+			skipped++
+			continue
+		}
+
 		var m pb.MachineInfo
 		if err = protojson.Unmarshal([]byte(mJSON), &m); err != nil {
 			return nil, nil, fmt.Errorf("unmarshal machine info: %w", err)
 		}
 		machines = append(machines, &m)
 	}
+
+	if skipped > 0 {
+		slog.Warn("Machine subscription skipped empty records in the store (possibly due to partial replication).",
+			"skipped", skipped, "valid", len(machines))
+	}
+
 	events, err := sub.Changes()
 	if err != nil {
 		return nil, nil, fmt.Errorf("get subscription changes: %w", err)

internal/sshexec/ssh.go

@@ -4,6 +4,7 @@ import (
 	"fmt"
 	"net"
 	"os"
+	osuser "os/user"
 	"strconv"
 	"time"
 
@@ -13,7 +14,17 @@ import (
 )
 
 func Connect(user, host string, port int, sshKeyPath string) (*ssh.Client, error) {
+	// Use the current OS user if no user is specified to be make it consistent with ssh CLI behavior.
+	if user == "" {
+		if u, err := osuser.Current(); err == nil {
+			user = u.Username
+		}
+	}
+	if port == 0 {
+		port = 22
+	}
 	addr := net.JoinHostPort(host, strconv.Itoa(port))
+
 	// Try to connect using SSH agent only.
 	agentAuth, agentClose, agentErr := sshAgentAuth()
 	if agentErr == nil {

internal/sshexec/sshcli.go

@@ -30,7 +30,7 @@ func NewSSHCLIRemote(user, host string, port int, keyPath string) *SSHCLIRemote
 func (r *SSHCLIRemote) buildSSHArgs() []string {
 	args := []string{"-o", "ConnectTimeout=5"}
 
-	if r.port != 0 && r.port != 22 {
+	if r.port != 0 {
 		args = append(args, "-p", strconv.Itoa(r.port))
 	}
 
@@ -38,7 +38,12 @@ func (r *SSHCLIRemote) buildSSHArgs() []string {
 		args = append(args, "-i", r.keyPath)
 	}
 
-	args = append(args, r.user+"@"+r.host)
+	dst := r.host
+	if r.user != "" {
+		dst = fmt.Sprintf("%s@%s", r.user, dst)
+	}
+	args = append(args, dst)
+
 	return args
 }
 

internal/sshexec/sshcli_test.go

@@ -18,29 +18,49 @@ func TestSSHCLIRemote_buildSSHArgs(t *testing.T) {
 		expected []string
 	}{
 		{
-			name:     "default port, no key",
+			name:     "host only",
+			host:     "example.com",
+			expected: []string{"-o", "ConnectTimeout=5", "example.com"},
+		},
+		{
+			name:     "with user",
 			user:     "root",
 			host:     "example.com",
-			port:     22,
-			keyPath:  "",
 			expected: []string{"-o", "ConnectTimeout=5", "root@example.com"},
 		},
 		{
-			name:     "custom port",
+			name:     "with port",
+			host:     "example.com",
+			port:     2222,
+			expected: []string{"-o", "ConnectTimeout=5", "-p", "2222", "example.com"},
+		},
+		{
+			name:     "with key",
+			host:     "example.com",
+			keyPath:  "/path/to/key",
+			expected: []string{"-o", "ConnectTimeout=5", "-i", "/path/to/key", "example.com"},
+		},
+		{
+			name:     "user and port",
 			user:     "ubuntu",
 			host:     "192.168.1.10",
 			port:     2222,
-			keyPath:  "",
 			expected: []string{"-o", "ConnectTimeout=5", "-p", "2222", "ubuntu@192.168.1.10"},
 		},
 		{
-			name:     "with key path",
+			name:     "user and key",
 			user:     "root",
 			host:     "example.com",
-			port:     22,
 			keyPath:  "/path/to/key",
 			expected: []string{"-o", "ConnectTimeout=5", "-i", "/path/to/key", "root@example.com"},
 		},
+		{
+			name:     "port and key",
+			host:     "example.com",
+			port:     22,
+			keyPath:  "~/.ssh/id_rsa",
+			expected: []string{"-o", "ConnectTimeout=5", "-p", "22", "-i", "~/.ssh/id_rsa", "example.com"},
+		},
 		{
 			name:     "all options",
 			user:     "admin",
@@ -49,14 +69,6 @@ func TestSSHCLIRemote_buildSSHArgs(t *testing.T) {
 			keyPath:  "~/.ssh/id_rsa",
 			expected: []string{"-o", "ConnectTimeout=5", "-p", "2222", "-i", "~/.ssh/id_rsa", "admin@server.local"},
 		},
-		{
-			name:     "port zero (default)",
-			user:     "root",
-			host:     "example.com",
-			port:     0,
-			keyPath:  "",
-			expected: []string{"-o", "ConnectTimeout=5", "root@example.com"},
-		},
 	}
 
 	for _, tt := range tests {

internal/ucind/cluster.go

@@ -119,17 +119,16 @@ func (p *Provisioner) CreateCluster(ctx context.Context, name string, opts Creat
 func (p *Provisioner) initCluster(ctx context.Context, machines []Machine) error {
 	// Init a new cluster on the first machine.
 	initMachine := machines[0]
-
-	if err := WaitMachineReady(ctx, initMachine, 30*time.Second); err != nil {
-		return fmt.Errorf("wait for machine %q to be ready: %w", initMachine.Name, err)
-	}
-
 	initClient, err := initMachine.Connect(ctx)
 	if err != nil {
 		return fmt.Errorf("create machine client over TCP '%s': %w", initMachine.APIAddress, err)
 	}
 	defer initClient.Close()
 
+	if err := initClient.WaitMachineReady(ctx, 30*time.Second); err != nil {
+		return fmt.Errorf("wait for machine %q to be ready: %w", initMachine.Name, err)
+	}
+
 	req := &pb.InitClusterRequest{
 		MachineName: initMachine.Name,
 		Network:     pb.NewIPPrefix(cluster.DefaultNetwork),
@@ -138,14 +137,22 @@ func (p *Provisioner) initCluster(ctx context.Context, machines []Machine) error
 	if err != nil {
 		return fmt.Errorf("init cluster: %w", err)
 	}
+
 	fmt.Printf("Cluster %q initialised with machine %q\n", initMachine.ClusterName, initResp.Machine.Name)
+	fmt.Printf("Waiting for cluster to be ready...")
+	if err = initClient.WaitClusterReady(ctx, 30*time.Second); err != nil {
+		return fmt.Errorf("wait for cluster to be ready: %w", err)
+	}
+	fmt.Println(" done.")
+
+	// Get the current store DB version from the init machine to pass to the join requests.
+	inspectResp, err := initClient.MachineClient.InspectMachine(ctx, &emptypb.Empty{})
+	if err != nil {
+		return fmt.Errorf("inspect init machine: %w", err)
+	}
 
 	// Join the rest of the machines to the cluster.
 	for _, m := range machines[1:] {
-		if err = WaitMachineReady(ctx, m, 30*time.Second); err != nil {
-			return fmt.Errorf("wait for machine %q to be ready: %w", m.Name, err)
-		}
-
 		cli, err := m.Connect(ctx)
 		if err != nil {
 			return fmt.Errorf("create machine client over TCP '%s': %w", m.APIAddress, err)
@@ -153,6 +160,10 @@ func (p *Provisioner) initCluster(ctx context.Context, machines []Machine) error
 		//goland:noinspection GoDeferInLoop
 		defer cli.Close()
 
+		if err := cli.WaitMachineReady(ctx, 30*time.Second); err != nil {
+			return fmt.Errorf("wait for machine %q to be ready: %w", m.Name, err)
+		}
+
 		tokenResp, err := cli.Token(ctx, &emptypb.Empty{})
 		if err != nil {
 			return fmt.Errorf("get machine token: %w", err)
@@ -181,8 +192,9 @@ func (p *Provisioner) initCluster(ctx context.Context, machines []Machine) error
 
 		// Configure the machine to join the cluster.
 		joinReq := &pb.JoinClusterRequest{
-			Machine:       addResp.Machine,
-			OtherMachines: []*pb.MachineInfo{initResp.Machine},
+			Machine:           addResp.Machine,
+			OtherMachines:     []*pb.MachineInfo{initResp.Machine},
+			MinStoreDbVersion: inspectResp.Machines[0].StoreDbVersion,
 		}
 		if _, err = cli.JoinCluster(ctx, joinReq); err != nil {
 			return fmt.Errorf("join cluster: %w", err)
@@ -256,16 +268,16 @@ func (p *Provisioner) InspectCluster(ctx context.Context, name string) (Cluster,
 // WaitClusterReady waits for all machines in the cluster to be ready and UP.
 func (p *Provisioner) WaitClusterReady(ctx context.Context, c Cluster, timeout time.Duration) error {
 	firstMachine := c.Machines[0]
-	if err := WaitMachineReady(ctx, firstMachine, timeout); err != nil {
-		return fmt.Errorf("wait for machine '%s' to be ready: %w", firstMachine.Name, err)
-	}
-
 	cli, err := firstMachine.Connect(ctx)
 	if err != nil {
 		return fmt.Errorf("connect to machine over TCP '%s': %w", firstMachine.APIAddress, err)
 	}
 	defer cli.Close()
 
+	if err = cli.WaitClusterReady(ctx, timeout); err != nil {
+		return fmt.Errorf("wait for cluster to be ready: %w", err)
+	}
+
 	boff := backoff.WithContext(backoff.NewExponentialBackOff(
 		backoff.WithInitialInterval(100*time.Millisecond),
 		backoff.WithMaxInterval(1*time.Second),
@@ -289,7 +301,25 @@ func (p *Provisioner) WaitClusterReady(ctx context.Context, c Cluster, timeout t
 		}
 		return nil
 	}
-	return backoff.Retry(checkMachinesUp, boff)
+	if err = backoff.Retry(checkMachinesUp, boff); err != nil {
+		return err
+	}
+
+	// Wait for each machine to sync the cluster store and be ready to serve cluster requests.
+	for _, m := range c.Machines[1:] {
+		mcli, err := m.Connect(ctx)
+		if err != nil {
+			return fmt.Errorf("connect to machine over TCP '%s': %w", m.APIAddress, err)
+		}
+		//goland:noinspection GoDeferInLoop
+		defer mcli.Close()
+
+		if err = mcli.WaitClusterReady(ctx, timeout); err != nil {
+			return fmt.Errorf("wait for cluster to be ready on machine '%s': %w", m.Name, err)
+		}
+	}
+
+	return nil
 }
 
 func (p *Provisioner) RemoveCluster(ctx context.Context, name string) error {

internal/ucind/machine.go

@@ -9,7 +9,6 @@ import (
 	"net/netip"
 	"time"
 
-	"github.com/cenkalti/backoff/v4"
 	"github.com/containerd/errdefs"
 	"github.com/docker/docker/api/types/container"
 	"github.com/docker/docker/api/types/image"
@@ -17,7 +16,6 @@ import (
 	"github.com/psviderski/uncloud/internal/secret"
 	"github.com/psviderski/uncloud/pkg/client"
 	"github.com/psviderski/uncloud/pkg/client/connector"
-	"google.golang.org/protobuf/types/known/emptypb"
 )
 
 const (
@@ -194,26 +192,3 @@ func randomMachineName() (string, error) {
 	}
 	return "machine-" + suffix, nil
 }
-
-// WaitMachineReady waits for the machine API to respond.
-func WaitMachineReady(ctx context.Context, m Machine, timeout time.Duration) error {
-	cli, err := m.Connect(ctx)
-	if err != nil {
-		return fmt.Errorf("connect to machine over TCP '%s': %w", m.APIAddress, err)
-	}
-	defer cli.Close()
-
-	boff := backoff.WithContext(backoff.NewExponentialBackOff(
-		backoff.WithInitialInterval(100*time.Millisecond),
-		backoff.WithMaxInterval(10*time.Second),
-		backoff.WithMaxElapsedTime(timeout),
-	), ctx)
-
-	inspect := func() error {
-		if _, err := cli.Inspect(ctx, &emptypb.Empty{}); err != nil {
-			return fmt.Errorf("inspect machine: %w", err)
-		}
-		return nil
-	}
-	return backoff.Retry(inspect, boff)
-}

pkg/api/client.go

@@ -21,11 +21,14 @@ type ContainerClient interface {
 	CreateContainer(
 		ctx context.Context, serviceID string, spec ServiceSpec, machineID string,
 	) (container.CreateResponse, error)
+	ExecContainer(ctx context.Context, serviceNameOrID, containerNameOrID string, config ExecOptions) (int, error)
 	InspectContainer(ctx context.Context, serviceNameOrID, containerNameOrID string) (MachineServiceContainer, error)
-	RemoveContainer(ctx context.Context, serviceNameOrID, containerNameOrID string, opts container.RemoveOptions) error
 	StartContainer(ctx context.Context, serviceNameOrID, containerNameOrID string) error
 	StopContainer(ctx context.Context, serviceNameOrID, containerNameOrID string, opts container.StopOptions) error
-	ExecContainer(ctx context.Context, serviceNameOrID, containerNameOrID string, config ExecOptions) (int, error)
+	RemoveContainer(ctx context.Context, serviceNameOrID, containerNameOrID string, opts container.RemoveOptions) error
+	WaitContainerHealthy(
+		ctx context.Context, serviceNameOrID, containerNameOrID string, opts WaitContainerHealthyOptions,
+	) error
 }
 
 type DNSClient interface {
@@ -57,3 +60,8 @@ type VolumeClient interface {
 	ListVolumes(ctx context.Context, filter *VolumeFilter) ([]MachineVolume, error)
 	RemoveVolume(ctx context.Context, machineNameOrID, volumeName string, force bool) error
 }
+
+// AsPtr returns a pointer to the given value. Useful for optional fields in API structs.
+func AsPtr[T any](v T) *T {
+	return &v
+}

pkg/api/config.go

@@ -6,6 +6,7 @@ import (
 	"fmt"
 	"os"
 	"path/filepath"
+	"sort"
 	"strconv"
 )
 
@@ -98,6 +99,76 @@ func (c *ConfigMount) Validate() error {
 	return nil
 }
 
+// Compare compares this ConfigMount with another.
+// Returns:
+//
+//	-1 if c < other
+//	 0 if c == other
+//	+1 if c > other
+func (c *ConfigMount) Compare(other *ConfigMount) int {
+	if c.ConfigName != other.ConfigName {
+		if c.ConfigName < other.ConfigName {
+			return -1
+		}
+		return 1
+	}
+	if c.ContainerPath != other.ContainerPath {
+		if c.ContainerPath < other.ContainerPath {
+			return -1
+		}
+		return 1
+	}
+	if c.Uid != other.Uid {
+		if c.Uid < other.Uid {
+			return -1
+		}
+		return 1
+	}
+	if c.Gid != other.Gid {
+		if c.Gid < other.Gid {
+			return -1
+		}
+		return 1
+	}
+	// Compare Mode (handle nil cases)
+	if c.Mode == nil && other.Mode != nil {
+		return -1
+	}
+	if c.Mode != nil && other.Mode == nil {
+		return 1
+	}
+	if c.Mode != nil && other.Mode != nil {
+		if *c.Mode < *other.Mode {
+			return -1
+		}
+		if *c.Mode > *other.Mode {
+			return 1
+		}
+	}
+	return 0
+}
+
+// Equals compares two ConfigMount instances for equality.
+func (c *ConfigMount) Equals(other *ConfigMount) bool {
+	return c.Compare(other) == 0
+}
+
+func (c *ConfigMount) Clone() ConfigMount {
+	clone := *c
+	if c.Mode != nil {
+		mode := *c.Mode
+		clone.Mode = &mode
+	}
+	return clone
+}
+
+// sortConfigMounts sorts a slice of ConfigMount instances.
+func sortConfigMounts(mounts []ConfigMount) {
+	sort.Slice(mounts, func(i, j int) bool {
+		return mounts[i].Compare(&mounts[j]) < 0
+	})
+}
+
 // ValidateConfigsAndMounts takes config specs and config mounts and validates that all mounts refer to existing specs
 func ValidateConfigsAndMounts(configs []ConfigSpec, mounts []ConfigMount) error {
 	configMap := make(map[string]struct{})

pkg/api/container.go

@@ -3,7 +3,9 @@ package api
 import (
 	"encoding/json"
 	"fmt"
+	"io"
 	"net/netip"
+	"os"
 	"strings"
 	"time"
 
@@ -41,6 +43,19 @@ func (c *Container) CreatedTime() time.Time {
 	return c.created
 }
 
+// HasHealthcheck returns true if the container has a health check configured.
+func (c *Container) HasHealthcheck() bool {
+	hc := c.Config.Healthcheck
+	if hc == nil {
+		return false
+	}
+
+	if len(hc.Test) > 0 && hc.Test[0] == "NONE" {
+		return false
+	}
+	return true
+}
+
 // Healthy determines if the container is running and healthy.
 // A running container with no health check configured is considered healthy.
 func (c *Container) Healthy() bool {
@@ -135,6 +150,10 @@ func (c *Container) UnmarshalJSON(data []byte) error {
 	}
 
 	*c = Container(temp)
+	if c.ContainerJSONBase == nil {
+		return fmt.Errorf("container data is missing mandatory base fields: %s", data)
+	}
+
 	c.Name = strings.TrimPrefix(c.Name, "/")
 
 	return nil
@@ -240,3 +259,61 @@ func (c *ServiceContainer) UnmarshalJSON(data []byte) error {
 
 	return nil
 }
+
+// DefaultHealthMonitorPeriod is the default duration (5 seconds) to wait before checking that the container is still
+// running and not restarting. Can be overridden with the UNCLOUD_HEALTH_MONITOR_PERIOD environment variable
+// (e.g. "10s" or "0").
+var DefaultHealthMonitorPeriod = defaultHealthMonitorPeriod()
+
+func defaultHealthMonitorPeriod() time.Duration {
+	if v, ok := os.LookupEnv("UNCLOUD_HEALTH_MONITOR_PERIOD"); ok {
+		if d, err := time.ParseDuration(v); err == nil {
+			return d
+		}
+	}
+
+	return 5 * time.Second
+}
+
+// WaitContainerHealthyOptions configures the behaviour of WaitContainerHealthy.
+type WaitContainerHealthyOptions struct {
+	// MonitorPeriod is how long to wait before checking that the container is still running and not restarting.
+	// Containers with a health check that become healthy before the period ends succeed early.
+	// nil means use the default DefaultHealthMonitorPeriod.
+	// Zero skips the monitoring and checks the container's health immediately after starting.
+	MonitorPeriod *time.Duration
+}
+
+// ExecOptions contains configuration for executing a command in a container.
+type ExecOptions struct {
+	// Command is the command to run in the container.
+	Command []string
+	// AttachStdin attaches the stdin stream to the exec session.
+	AttachStdin bool
+	// AttachStdout attaches the stdout stream to the exec session.
+	AttachStdout bool
+	// AttachStderr attaches the stderr stream to the exec session.
+	AttachStderr bool
+	// Tty allocates a pseudo-TTY for the exec session.
+	Tty bool
+	// Detach runs the command in the background without attaching to streams.
+	Detach bool
+
+	//// Not yet implemented fields
+	// User specifies the user to run the command as.
+	User string
+	// Privileged runs the command in privileged mode.
+	Privileged bool
+	// WorkingDir sets the working directory for the command.
+	WorkingDir string
+	// Env sets environment variables for the command.
+	Env []string
+
+	// Client-side only fields (not serialized, not sent to server)
+	// Stdin is the input stream. Defaults to os.Stdin if nil.
+	Stdin io.Reader `json:"-"`
+	// Stdout is the output stream. Defaults to os.Stdout if nil.
+	Stdout io.Writer `json:"-"`
+	// Stderr is the error stream. Defaults to os.Stderr if nil.
+	Stderr io.Writer `json:"-"`
+}

pkg/api/container_exec.go

@@ -1,37 +0,0 @@
-package api
-
-import "io"
-
-// ExecOptions contains configuration for executing a command in a container.
-type ExecOptions struct {
-	// Command is the command to run in the container.
-	Command []string
-	// AttachStdin attaches the stdin stream to the exec session.
-	AttachStdin bool
-	// AttachStdout attaches the stdout stream to the exec session.
-	AttachStdout bool
-	// AttachStderr attaches the stderr stream to the exec session.
-	AttachStderr bool
-	// Tty allocates a pseudo-TTY for the exec session.
-	Tty bool
-	// Detach runs the command in the background without attaching to streams.
-	Detach bool
-
-	//// Not yet implemented fields
-	// User specifies the user to run the command as.
-	User string
-	// Privileged runs the command in privileged mode.
-	Privileged bool
-	// WorkingDir sets the working directory for the command.
-	WorkingDir string
-	// Env sets environment variables for the command.
-	Env []string
-
-	// Client-side only fields (not serialized, not sent to server)
-	// Stdin is the input stream. Defaults to os.Stdin if nil.
-	Stdin io.Reader `json:"-"`
-	// Stdout is the output stream. Defaults to os.Stdout if nil.
-	Stdout io.Writer `json:"-"`
-	// Stderr is the error stream. Defaults to os.Stderr if nil.
-	Stderr io.Writer `json:"-"`
-}

pkg/api/resources.go

@@ -17,6 +17,25 @@ type ContainerResources struct {
 	// MemoryReservation is the minimum amount of memory (in bytes) the container needs to run efficiently.
 	// TODO: implement a placement constraint that checks available memory on machines.
 	MemoryReservation int64
-	// Device reservations/requests for access to things like GPUs
+	// Devices provides direct access to host devices.
+	Devices []DeviceMapping
+	// DeviceReservations requests for access to things like GPUs.
 	DeviceReservations []container.DeviceRequest
+	// Ulimits defines the resource limits for the container.
+	Ulimits map[string]Ulimit
+}
+
+// DeviceMapping represents a device mapping between host and container.
+type DeviceMapping struct {
+	// HostPath is the path to the device on the host.
+	HostPath string
+	// ContainerPath is the path to the device in the container.
+	ContainerPath string
+	// CgroupPermissions is the cgroup permissions for the device (e.g., "rwm").
+	CgroupPermissions string
+}
+
+type Ulimit struct {
+	Soft int64
+	Hard int64
 }

pkg/api/service.go

@@ -7,6 +7,7 @@ import (
 	"regexp"
 	"slices"
 	"strings"
+	"time"
 
 	mapset "github.com/deckarep/golang-set/v2"
 	"github.com/distribution/reference"
@@ -19,6 +20,13 @@ const (
 	ServiceModeReplicated = "replicated"
 	ServiceModeGlobal     = "global"
 
+	// UpdateOrderStartFirst starts the new container before stopping the old one.
+	// This minimizes downtime but briefly runs both containers.
+	UpdateOrderStartFirst = "start-first"
+	// UpdateOrderStopFirst stops the old container before starting the new one.
+	// This prevents data corruption for stateful services but causes brief downtime.
+	UpdateOrderStopFirst = "stop-first"
+
 	// PullPolicyAlways means the image is always pulled from the registry.
 	PullPolicyAlways = "always"
 	// PullPolicyMissing means the image is pulled from the registry only if it's not available on the machine where
@@ -59,6 +67,8 @@ type ServiceSpec struct {
 	Ports []PortSpec
 	// Replicas is the number of containers to run for the service. Only valid for a replicated service.
 	Replicas uint `json:",omitempty"`
+	// UpdateConfig configures how the service is updated during a deployment.
+	UpdateConfig UpdateConfig `json:",omitempty"`
 	// Volumes is list of data volumes that can be mounted into the container.
 	Volumes []VolumeSpec
 	// Configs is list of configuration objects that can be mounted into the container.
@@ -225,13 +235,20 @@ func (s *ServiceSpec) Clone() ServiceSpec {
 // ContainerSpec defines the desired state of a container in a service.
 // ATTENTION: after changing this struct, verify if deploy.EvalContainerSpecChange needs to be updated.
 type ContainerSpec struct {
+	// Specifies which additional capabilities should be added for the container.
+	CapAdd []string
+	// Specifies which capabilities should be dropped from the container.
+	CapDrop []string
 	// Command overrides the default CMD of the image to be executed when running a container.
 	Command []string
 	// Entrypoint overrides the default ENTRYPOINT of the image.
 	Entrypoint []string
 	// Env defines the environment variables to set inside the container.
-	Env   EnvVars
-	Image string
+	Env EnvVars
+	// Healthcheck defines the health check configuration for the container or overrides the health check options
+	// defined in the image. If nil, the image's default health check is used.
+	Healthcheck *HealthcheckSpec `json:",omitempty"`
+	Image       string
 	// Run a custom init inside the container. If nil, use the daemon's configured settings.
 	Init *bool
 	// LogDriver overrides the default logging driver for the container. Each Docker daemon can have its own default.
@@ -243,6 +260,8 @@ type ContainerSpec struct {
 	PullPolicy string
 	// Resource allocation for the container.
 	Resources ContainerResources
+	// Namespaced kernel parameters to be set in container
+	Sysctls map[string]string
 	// User overrides the default user of the image used to run the container. Format: user|UID[:group|GID].
 	User string
 	// VolumeMounts specifies how volumes are mounted into the container filesystem.
@@ -290,18 +309,32 @@ func (s *ContainerSpec) Equals(spec ContainerSpec) bool {
 	orig := s.SetDefaults()
 	spec = spec.SetDefaults()
 
+	// Volumes
 	slices.Sort(orig.Volumes)
 	slices.Sort(spec.Volumes)
 
+	// Volume mounts
 	sortVolumeMounts(orig.VolumeMounts)
 	sortVolumeMounts(spec.VolumeMounts)
 
+	// Config mounts
+	sortConfigMounts(orig.ConfigMounts)
+	sortConfigMounts(spec.ConfigMounts)
+
 	return cmp.Equal(orig, spec, cmpopts.EquateEmpty())
 }
 
 func (s *ContainerSpec) Clone() ContainerSpec {
 	spec := *s
 
+	if s.CapAdd != nil {
+		spec.CapAdd = make([]string, len(s.CapAdd))
+		copy(spec.CapAdd, s.CapAdd)
+	}
+	if s.CapDrop != nil {
+		spec.CapDrop = make([]string, len(s.CapDrop))
+		copy(spec.CapDrop, s.CapDrop)
+	}
 	if s.Command != nil {
 		spec.Command = make([]string, len(s.Command))
 		copy(spec.Command, s.Command)
@@ -310,6 +343,17 @@ func (s *ContainerSpec) Clone() ContainerSpec {
 		spec.Entrypoint = make([]string, len(s.Entrypoint))
 		copy(spec.Entrypoint, s.Entrypoint)
 	}
+	if s.Env != nil {
+		spec.Env = make(EnvVars, len(s.Env))
+		for k, v := range s.Env {
+			spec.Env[k] = v
+		}
+	}
+	if s.Healthcheck != nil {
+		hc := *s.Healthcheck
+		hc.Test = slices.Clone(s.Healthcheck.Test)
+		spec.Healthcheck = &hc
+	}
 	if s.LogDriver != nil {
 		logDriver := *s.LogDriver
 		if s.LogDriver.Options != nil {
@@ -325,6 +369,27 @@ func (s *ContainerSpec) Clone() ContainerSpec {
 		spec.VolumeMounts = make([]VolumeMount, len(s.VolumeMounts))
 		copy(spec.VolumeMounts, s.VolumeMounts)
 	}
+	if s.ConfigMounts != nil {
+		spec.ConfigMounts = make([]ConfigMount, len(s.ConfigMounts))
+		for i, cm := range s.ConfigMounts {
+			spec.ConfigMounts[i] = cm.Clone()
+		}
+	}
+	if s.Sysctls != nil {
+		spec.Sysctls = make(map[string]string, len(s.Sysctls))
+		for k, v := range s.Sysctls {
+			spec.Sysctls[k] = v
+		}
+	}
+	if s.Resources.Ulimits != nil {
+		spec.Resources.Ulimits = maps.Clone(s.Resources.Ulimits)
+	}
+	if s.Resources.Devices != nil {
+		spec.Resources.Devices = slices.Clone(s.Resources.Devices)
+	}
+	if s.Resources.DeviceReservations != nil {
+		spec.Resources.DeviceReservations = slices.Clone(s.Resources.DeviceReservations)
+	}
 
 	return spec
 }
@@ -343,6 +408,26 @@ func (e EnvVars) ToSlice() []string {
 	return env
 }
 
+// HealthcheckSpec defines the health check configuration for a container.
+type HealthcheckSpec struct {
+	// Test is the command used to check health.
+	// Formats: ["CMD", args...], ["CMD-SHELL", "command"], or ["NONE"] to disable.
+	Test []string `json:",omitempty"`
+	// Interval is the time between health checks.
+	// Zero means to inherit the value from the image or use the Docker default (30s) if not defined in the image.
+	Interval time.Duration `json:",omitempty"`
+	// Timeout is how long to wait before considering the checck to have hung.
+	Timeout time.Duration `json:",omitempty"`
+	// StartPeriod is the initialisation time for a container before the retries start to count down.
+	StartPeriod time.Duration `json:",omitempty"`
+	// StartInterval is the time between health checks during the start period.
+	StartInterval time.Duration `json:",omitempty"`
+	// Retries is the number of consecutive failures needed to consider a container unhealthy.
+	Retries uint `json:",omitempty"`
+	// Disable disables the health check defined in the image. true is equivalent to setting Test to ["NONE"].
+	Disable bool `json:",omitempty"`
+}
+
 type LogDriver struct {
 	// Name of the logging driver to use.
 	Name string
@@ -350,6 +435,19 @@ type LogDriver struct {
 	Options map[string]string
 }
 
+// UpdateConfig configures how a service is updated during a deployment.
+type UpdateConfig struct {
+	// Order specifies the order of operations during an update.
+	// Valid values are "start-first" (default for stateless services) and "stop-first" (default for services with
+	// volumes). Empty value means the strategy will determine the order based on service characteristics.
+	Order string `json:",omitempty"`
+	// MonitorPeriod is how long to wait after starting a container before checking that it's still running
+	// and not restarting. Containers with a health check that become healthy before the period ends succeed early.
+	// nil means use the default api.DefaultHealthMonitorPeriod.
+	// Zero skips the monitoring and checks the container's health immediately after starting.
+	MonitorPeriod *time.Duration `json:",omitempty"`
+}
+
 type RunServiceResponse struct {
 	ID   string
 	Name string

pkg/api/service_test.go

@@ -1,11 +1,20 @@
 package api
 
 import (
+	"os"
 	"testing"
 
+	"github.com/docker/docker/api/types/container"
+	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 )
 
+// boolPtr is a convenience function to create a pointer to a uint64 value
+// TODO: Make this a generic function that works for any type
+func boolPtr(b bool) *bool {
+	return &b
+}
+
 func TestServiceSpec_Validate_CaddyAndPorts(t *testing.T) {
 	tests := []struct {
 		name    string
@@ -197,3 +206,101 @@ func TestServiceSpec_Validate_CaddyAndPorts(t *testing.T) {
 		})
 	}
 }
+
+func TestContainerSpec_Clone(t *testing.T) {
+	mode := os.FileMode(0o644)
+	original := ContainerSpec{
+		CapAdd:     []string{"NET_ADMIN"},
+		CapDrop:    []string{"ALL"},
+		Command:    []string{"sh", "-c", "echo hello"},
+		Entrypoint: []string{"/bin/bash"},
+		Env: EnvVars{
+			"FOO": "bar",
+			"BAZ": "qux",
+		},
+		Image: "nginx:latest",
+		Init:  boolPtr(true),
+		LogDriver: &LogDriver{
+			Name: "json-file",
+			Options: map[string]string{
+				"max-size": "10m",
+			},
+		},
+		Privileged: true,
+		PullPolicy: PullPolicyAlways,
+		Resources: ContainerResources{
+			CPU:               1234,
+			Memory:            2345,
+			MemoryReservation: 3456,
+			Devices: []DeviceMapping{
+				{HostPath: "/dev/sda", ContainerPath: "/dev/xvda", CgroupPermissions: "rwm"},
+			},
+			DeviceReservations: []container.DeviceRequest{
+				{Count: 1, Capabilities: [][]string{{"gpu"}}, Driver: "nvidia"},
+			},
+		},
+		Sysctls: map[string]string{
+			"net.ipv4.ip_forward": "1",
+		},
+		User:    "1000:1000",
+		Volumes: []string{"/data", "/config"},
+		VolumeMounts: []VolumeMount{
+			{VolumeName: "data", ContainerPath: "/data"},
+		},
+		ConfigMounts: []ConfigMount{
+			{ConfigName: "app-config", ContainerPath: "/etc/config", Mode: &mode},
+		},
+	}
+
+	cloned := original.Clone()
+
+	// Check ContainerSpec equality
+	assert.True(t, original.Equals(cloned))
+
+	// Verify deep copy by modifying the original
+	stringModified := "modified"
+	original.CapAdd[0] = stringModified
+	original.CapDrop[0] = stringModified
+	original.Command[0] = stringModified
+	original.Entrypoint[0] = stringModified
+	original.Env["FOO"] = stringModified
+	original.LogDriver.Options["max-size"] = stringModified
+	original.Volumes[0] = stringModified
+	original.VolumeMounts[0].ContainerPath = stringModified
+	original.ConfigMounts[0].ContainerPath = stringModified
+	*original.ConfigMounts[0].Mode = 0o755 // Modify the Mode pointer value
+	original.Sysctls["net.ipv4.ip_forward"] = stringModified
+	original.Resources.Devices[0].HostPath = stringModified
+	original.Resources.DeviceReservations[0].Count = 2
+	original.Resources.DeviceReservations[0].Driver = stringModified
+
+	assert.False(t, original.Equals(cloned))
+	// Assert cloned values are unchanged
+	assert.Equal(t, "NET_ADMIN", cloned.CapAdd[0])
+	assert.Equal(t, "ALL", cloned.CapDrop[0])
+	assert.Equal(t, "sh", cloned.Command[0])
+	assert.Equal(t, "/bin/bash", cloned.Entrypoint[0])
+	assert.Equal(t, "bar", cloned.Env["FOO"])
+	assert.Equal(t, "qux", cloned.Env["BAZ"])
+	assert.Equal(t, "nginx:latest", cloned.Image)
+	assert.NotNil(t, cloned.Init)
+	assert.Equal(t, true, *cloned.Init)
+	assert.NotNil(t, cloned.LogDriver)
+	assert.Equal(t, "json-file", cloned.LogDriver.Name)
+	assert.Equal(t, "10m", cloned.LogDriver.Options["max-size"])
+	assert.Equal(t, true, cloned.Privileged)
+	assert.Equal(t, PullPolicyAlways, cloned.PullPolicy)
+	assert.Equal(t, int64(1234), cloned.Resources.CPU)
+	assert.Equal(t, int64(2345), cloned.Resources.Memory)
+	assert.Equal(t, int64(3456), cloned.Resources.MemoryReservation)
+	assert.Equal(t, "/dev/sda", cloned.Resources.Devices[0].HostPath)
+	assert.Equal(t, 1, cloned.Resources.DeviceReservations[0].Count)
+	assert.Equal(t, "nvidia", cloned.Resources.DeviceReservations[0].Driver)
+	assert.Equal(t, "1000:1000", cloned.User)
+	assert.Equal(t, "/data", cloned.Volumes[0])
+	assert.Equal(t, "/data", cloned.VolumeMounts[0].ContainerPath)
+	assert.Equal(t, "/etc/config", cloned.ConfigMounts[0].ContainerPath)
+	assert.NotNil(t, cloned.ConfigMounts[0].Mode)
+	assert.Equal(t, os.FileMode(0o644), *cloned.ConfigMounts[0].Mode, "Mode should be deep copied")
+	assert.Equal(t, "1", cloned.Sysctls["net.ipv4.ip_forward"])
+}

pkg/client/compose/config.go

@@ -13,18 +13,27 @@ import (
 func configSpecsFromCompose(
 	configs types.Configs, serviceConfigs []types.ServiceConfigObjConfig, workingDir string,
 ) ([]api.ConfigSpec, []api.ConfigMount, error) {
-	var configSpecs []api.ConfigSpec
 	var configMounts []api.ConfigMount
 
+	// Temporary map to hold config specs
+	configSpecsMap := make(map[string]api.ConfigSpec)
+
+	// We iterate over all service config objects (config mounts)
 	for _, serviceConfig := range serviceConfigs {
 		var spec api.ConfigSpec
 
-		if projectConfig, exists := configs[serviceConfig.Source]; exists {
-			if projectConfig.External {
-				return nil, nil, fmt.Errorf("external configs are not supported: %s",
-					serviceConfig.Source)
-			}
+		projectConfig, exists := configs[serviceConfig.Source]
+		if !exists {
+			return nil, nil, fmt.Errorf("config '%s' not found in project configs", serviceConfig.Source)
+		}
 
+		if projectConfig.External {
+			return nil, nil, fmt.Errorf("external configs are not supported: %s",
+				serviceConfig.Source)
+		}
+
+		spec, exists = configSpecsMap[serviceConfig.Source]
+		if !exists {
 			spec = api.ConfigSpec{
 				Name:    serviceConfig.Source,
 				Content: []byte(projectConfig.Content),
@@ -44,11 +53,9 @@ func configSpecsFromCompose(
 				}
 				spec.Content = fileContent
 			}
-		} else {
-			return nil, nil, fmt.Errorf("config '%s' not found in project configs", serviceConfig.Source)
-		}
 
-		configSpecs = append(configSpecs, spec)
+			configSpecsMap[serviceConfig.Source] = spec
+		}
 
 		// Create config mount
 		target := serviceConfig.Target
@@ -71,5 +78,11 @@ func configSpecsFromCompose(
 		configMounts = append(configMounts, mount)
 	}
 
+	var configSpecs []api.ConfigSpec
+	// Convert config spec map to slice
+	for _, spec := range configSpecsMap {
+		configSpecs = append(configSpecs, spec)
+	}
+
 	return configSpecs, configMounts, nil
 }

pkg/client/compose/config_test.go

@@ -77,6 +77,147 @@ func TestConfigSpecsFromCompose(t *testing.T) {
 				},
 			},
 		},
+		{
+			name: "same source mounted to different targets",
+			configs: types.Configs{
+				"shared-config": types.ConfigObjConfig{
+					File: "testdata/config1.txt",
+				},
+			},
+			serviceConfigs: []types.ServiceConfigObjConfig{
+				{
+					Source: "shared-config",
+					Target: "/app/config.json",
+					UID:    "1000",
+					GID:    "1000",
+				},
+				{
+					Source: "shared-config",
+					Target: "/backup/config.json",
+					UID:    "1001",
+					GID:    "1001",
+				},
+			},
+			expectedSpecs: []api.ConfigSpec{
+				{
+					Name:    "shared-config",
+					Content: []byte("test config content\n"),
+				},
+			},
+			expectedMounts: []api.ConfigMount{
+				{
+					ConfigName:    "shared-config",
+					ContainerPath: "/app/config.json",
+					Uid:           "1000",
+					Gid:           "1000",
+				},
+				{
+					ConfigName:    "shared-config",
+					ContainerPath: "/backup/config.json",
+					Uid:           "1001",
+					Gid:           "1001",
+				},
+			},
+		},
+		{
+			name: "config with default target path",
+			configs: types.Configs{
+				"default-config": types.ConfigObjConfig{
+					Content: "inline config content",
+				},
+			},
+			serviceConfigs: []types.ServiceConfigObjConfig{
+				{
+					Source: "default-config",
+					// No Target specified - should use default
+				},
+			},
+			expectedSpecs: []api.ConfigSpec{
+				{
+					Name:    "default-config",
+					Content: []byte("inline config content"),
+				},
+			},
+			expectedMounts: []api.ConfigMount{
+				{
+					ConfigName:    "default-config",
+					ContainerPath: "/default-config",
+				},
+			},
+		},
+		{
+			name: "config with inline content",
+			configs: types.Configs{
+				"inline-config": types.ConfigObjConfig{
+					Content: "server {\n  listen 80;\n}",
+				},
+			},
+			serviceConfigs: []types.ServiceConfigObjConfig{
+				{
+					Source: "inline-config",
+					Target: "/etc/nginx/sites-available/default",
+					Mode:   func() *types.FileMode { m := types.FileMode(0o755); return &m }(),
+				},
+			},
+			expectedSpecs: []api.ConfigSpec{
+				{
+					Name:    "inline-config",
+					Content: []byte("server {\n  listen 80;\n}"),
+				},
+			},
+			expectedMounts: []api.ConfigMount{
+				{
+					ConfigName:    "inline-config",
+					ContainerPath: "/etc/nginx/sites-available/default",
+					Mode:          func() *os.FileMode { m := os.FileMode(0o755); return &m }(),
+				},
+			},
+		},
+		{
+			name: "config not found error",
+			configs: types.Configs{
+				"existing-config": types.ConfigObjConfig{
+					Content: "some content",
+				},
+			},
+			serviceConfigs: []types.ServiceConfigObjConfig{
+				{
+					Source: "missing-config",
+					Target: "/app/config.json",
+				},
+			},
+			expectError: true,
+		},
+		{
+			name: "external config error",
+			configs: types.Configs{
+				"external-config": types.ConfigObjConfig{
+					External: true,
+				},
+			},
+			serviceConfigs: []types.ServiceConfigObjConfig{
+				{
+					Source: "external-config",
+					Target: "/app/config.json",
+				},
+			},
+			expectError: true,
+		},
+		{
+			name: "file not found error",
+			configs: types.Configs{
+				"missing-file-config": types.ConfigObjConfig{
+					File: "testdata/nonexistent.txt",
+				},
+			},
+			serviceConfigs: []types.ServiceConfigObjConfig{
+				{
+					Source: "missing-file-config",
+					Target: "/app/config.json",
+				},
+			},
+			expectError: true,
+		},
 	}
 
 	for _, tt := range tests {

pkg/client/compose/deploy.go

@@ -13,6 +13,7 @@ import (
 	"github.com/docker/docker/api/types/volume"
 	"github.com/psviderski/uncloud/pkg/api"
 	"github.com/psviderski/uncloud/pkg/client/deploy"
+	"github.com/psviderski/uncloud/pkg/client/deploy/operation"
 	"github.com/psviderski/uncloud/pkg/client/deploy/scheduler"
 )
 
@@ -27,7 +28,7 @@ type Deployment struct {
 	SpecResolver *deploy.ServiceSpecResolver
 	Strategy     deploy.Strategy
 	state        *scheduler.ClusterState
-	plan         *deploy.SequenceOperation
+	plan         *operation.SequenceOperation
 }
 
 func NewDeployment(ctx context.Context, cli Client, project *types.Project) (*Deployment, error) {
@@ -58,11 +59,11 @@ func NewDeploymentWithStrategy(ctx context.Context, cli Client, project *types.P
 	}, nil
 }
 
-func (d *Deployment) Plan(ctx context.Context) (deploy.SequenceOperation, error) {
+func (d *Deployment) Plan(ctx context.Context) (operation.SequenceOperation, error) {
 	if d.plan != nil {
 		return *d.plan, nil
 	}
-	plan := deploy.SequenceOperation{}
+	plan := operation.SequenceOperation{}
 
 	// Generate service specs for all services in the project.
 	var serviceSpecs []api.ServiceSpec
@@ -123,7 +124,7 @@ func (d *Deployment) ServiceSpec(name string) (api.ServiceSpec, error) {
 }
 
 // PlanVolumes checks if the external volumes exist and plans the creation of missing volumes.
-func (d *Deployment) planVolumes(serviceSpecs []api.ServiceSpec) ([]*deploy.CreateVolumeOperation, error) {
+func (d *Deployment) planVolumes(serviceSpecs []api.ServiceSpec) ([]*operation.CreateVolumeOperation, error) {
 	if len(d.Project.Volumes) == 0 {
 		// No volumes to check or create.
 		return nil, nil
@@ -145,7 +146,7 @@ func (d *Deployment) planVolumes(serviceSpecs []api.ServiceSpec) ([]*deploy.Crea
 	}
 
 	// Generate operations to create scheduled missing volumes.
-	var ops []*deploy.CreateVolumeOperation
+	var ops []*operation.CreateVolumeOperation
 	for machineID, volumes := range scheduledVolumes {
 		for _, v := range volumes {
 			machineName := machineID
@@ -153,7 +154,7 @@ func (d *Deployment) planVolumes(serviceSpecs []api.ServiceSpec) ([]*deploy.Crea
 				machineName = m.Info.Name
 			}
 
-			ops = append(ops, &deploy.CreateVolumeOperation{
+			ops = append(ops, &operation.CreateVolumeOperation{
 				MachineID:   machineID,
 				MachineName: machineName,
 				VolumeSpec:  v,

pkg/client/compose/project.go

@@ -6,13 +6,23 @@ import (
 	"os"
 	"path/filepath"
 	"strings"
+	"sync"
 
 	composecli "github.com/compose-spec/compose-go/v2/cli"
+	"github.com/compose-spec/compose-go/v2/transform"
+	"github.com/compose-spec/compose-go/v2/tree"
 	"github.com/compose-spec/compose-go/v2/types"
+	"github.com/psviderski/uncloud/pkg/api"
 )
 
+var registerComposeOverrides sync.Once
+
 // LoadProject loads a Compose project from the default locations or the given paths.
 func LoadProject(ctx context.Context, paths []string, opts ...composecli.ProjectOptionsFn) (*types.Project, error) {
+	registerComposeOverrides.Do(func() {
+		transform.RegisterDefaultValue("services.*.deploy.update_config", setUpdateConfigDefaults)
+	})
+
 	defaultOpts := []composecli.ProjectOptionsFn{
 		// First apply os.Environment, always wins.
 		composecli.WithOsEnv,
@@ -92,3 +102,14 @@ func removeProjectPrefixFromNames(project *types.Project) {
 		project.Volumes[name] = vol
 	}
 }
+
+// setUpdateConfigDefaults sets default values for deploy.update_config attributes when not specified in the compose file.
+func setUpdateConfigDefaults(data any, _ tree.Path, _ bool) (any, error) {
+	switch v := data.(type) {
+	case map[string]any:
+		if _, ok := v["monitor"]; !ok {
+			v["monitor"] = api.DefaultHealthMonitorPeriod.String()
+		}
+	}
+	return data, nil
+}

pkg/client/compose/service.go

@@ -5,12 +5,14 @@ import (
 	"maps"
 	"os"
 	"slices"
+	"time"
 
 	"github.com/compose-spec/compose-go/v2/types"
 	"github.com/docker/docker/api/types/container"
 	"github.com/docker/docker/api/types/mount"
 	"github.com/opencontainers/go-digest"
 	"github.com/psviderski/uncloud/pkg/api"
+	cdi "tags.cncf.io/container-device-interface/pkg/parser"
 )
 
 func ServiceSpecFromCompose(project *types.Project, serviceName string) (api.ServiceSpec, error) {
@@ -43,15 +45,19 @@ func ServiceSpecFromCompose(project *types.Project, serviceName string) (api.Ser
 
 	spec := api.ServiceSpec{
 		Container: api.ContainerSpec{
-			Command:    service.Command,
-			Entrypoint: service.Entrypoint,
-			Env:        env,
-			Image:      service.Image,
-			Init:       service.Init,
-			Privileged: service.Privileged,
-			PullPolicy: pullPolicy,
-			Resources:  resourcesFromCompose(service),
-			User:       service.User,
+			CapAdd:      service.CapAdd,
+			CapDrop:     service.CapDrop,
+			Command:     service.Command,
+			Entrypoint:  service.Entrypoint,
+			Env:         env,
+			Healthcheck: healthcheckFromCompose(service.HealthCheck),
+			Image:       service.Image,
+			Init:        service.Init,
+			Privileged:  service.Privileged,
+			PullPolicy:  pullPolicy,
+			Resources:   resourcesFromCompose(service),
+			Sysctls:     service.Sysctls,
+			User:        service.User,
 		},
 		Name: serviceName,
 		Mode: api.ServiceModeReplicated,
@@ -94,6 +100,22 @@ func ServiceSpecFromCompose(project *types.Project, serviceName string) (api.Ser
 		default:
 			return spec, fmt.Errorf("unsupported deploy mode: '%s'", service.Deploy.Mode)
 		}
+
+		if cfg := service.Deploy.UpdateConfig; cfg != nil {
+			switch cfg.Order {
+			case "":
+				// No order specified, use default behavior.
+			case "start-first":
+				spec.UpdateConfig.Order = api.UpdateOrderStartFirst
+			case "stop-first":
+				spec.UpdateConfig.Order = api.UpdateOrderStopFirst
+			default:
+				return spec, fmt.Errorf("unsupported deploy.update_config.order: '%s'", cfg.Order)
+			}
+
+			d := time.Duration(cfg.Monitor)
+			spec.UpdateConfig.MonitorPeriod = &d
+		}
 	}
 
 	// TODO: can service.tmpfs be handled as tmpfs volume mounts as well?
@@ -117,11 +139,61 @@ func ServiceSpecFromCompose(project *types.Project, serviceName string) (api.Ser
 	return spec, nil
 }
 
+func healthcheckFromCompose(hc *types.HealthCheckConfig) *api.HealthcheckSpec {
+	if hc == nil {
+		return nil
+	}
+	if hc.Disable {
+		return &api.HealthcheckSpec{Disable: true}
+	}
+
+	spec := &api.HealthcheckSpec{Test: hc.Test}
+	if hc.Interval != nil {
+		spec.Interval = time.Duration(*hc.Interval)
+	}
+	if hc.Timeout != nil {
+		spec.Timeout = time.Duration(*hc.Timeout)
+	}
+	if hc.StartPeriod != nil {
+		spec.StartPeriod = time.Duration(*hc.StartPeriod)
+	}
+	if hc.StartInterval != nil {
+		spec.StartInterval = time.Duration(*hc.StartInterval)
+	}
+	if hc.Retries != nil {
+		spec.Retries = uint(*hc.Retries)
+	}
+
+	return spec
+}
+
 func resourcesFromCompose(service types.ServiceConfig) api.ContainerResources {
 	resources := api.ContainerResources{
 		CPU:               int64(service.CPUS * 1e9),
 		Memory:            int64(service.MemLimit),
 		MemoryReservation: int64(service.MemReservation),
+		Ulimits:           ulimitsFromCompose(service.Ulimits),
+	}
+
+	// Convert device mappings, separating CDI devices from regular device mappings.
+	// CDI devices are identified when Source == Target and the source is a qualified CDI name.
+	var cdiDeviceNames []string
+	for _, dev := range service.Devices {
+		if dev.Source == dev.Target && cdi.IsQualifiedName(dev.Source) {
+			cdiDeviceNames = append(cdiDeviceNames, dev.Source)
+			continue
+		}
+		resources.Devices = append(resources.Devices, api.DeviceMapping{
+			HostPath:          dev.Source,
+			ContainerPath:     dev.Target,
+			CgroupPermissions: dev.Permissions,
+		})
+	}
+	if len(cdiDeviceNames) > 0 {
+		resources.DeviceReservations = append(resources.DeviceReservations, container.DeviceRequest{
+			Driver:    "cdi",
+			DeviceIDs: cdiDeviceNames,
+		})
 	}
 
 	// Convert GPU device requests from compose format, appending "gpu" capability.
@@ -290,6 +362,33 @@ func tmpfsVolumeSpecFromCompose(serviceVolume types.ServiceVolumeConfig) api.Vol
 	return spec
 }
 
+func ulimitsFromCompose(ulimits map[string]*types.UlimitsConfig) map[string]api.Ulimit {
+	if len(ulimits) == 0 {
+		return nil
+	}
+
+	res := make(map[string]api.Ulimit, len(ulimits))
+	for name, u := range ulimits {
+		soft := u.Soft
+		hard := u.Hard
+		if u.Single != 0 {
+			if soft == 0 {
+				soft = u.Single
+			}
+			if hard == 0 {
+				hard = u.Single
+			}
+		}
+
+		res[name] = api.Ulimit{
+			Soft: int64(soft),
+			Hard: int64(hard),
+		}
+	}
+
+	return res
+}
+
 // validateServicesExtensions validates extension combinations across all services in the project.
 func validateServicesExtensions(project *types.Project) error {
 	for _, service := range project.Services {

pkg/client/compose/service_test.go

@@ -8,6 +8,7 @@ import (
 	"slices"
 	"strings"
 	"testing"
+	"time"
 
 	composecli "github.com/compose-spec/compose-go/v2/cli"
 	"github.com/docker/docker/api/types/container"
@@ -93,13 +94,15 @@ func TestServiceSpecFromCompose(t *testing.T) {
 			},
 		},
 		{
-			name:     "full-spec",
+			name:     "full spec",
 			filename: "compose-full-spec.yaml",
 			want: map[string]api.ServiceSpec{
 				"test": {
 					Name: "test",
 					Mode: api.ServiceModeReplicated,
 					Container: api.ContainerSpec{
+						CapAdd:     []string{"NET_ADMIN"},
+						CapDrop:    []string{"ALL"},
 						Command:    []string{"nginx", "updated", "command"},
 						Entrypoint: []string{"/updated-docker-entrypoint.sh"},
 						Env: map[string]string{
@@ -107,6 +110,14 @@ func TestServiceSpecFromCompose(t *testing.T) {
 							"EMPTY": "",
 							"VAR":   "value",
 						},
+						Healthcheck: &api.HealthcheckSpec{
+							Test:          []string{"CMD", "curl", "-f", "http://localhost"},
+							Interval:      1*time.Minute + 30*time.Second,
+							Timeout:       10 * time.Second,
+							Retries:       5,
+							StartPeriod:   15 * time.Second,
+							StartInterval: 2 * time.Second,
+						},
 						Image: "nginx:latest",
 						Init:  &initTrue,
 						LogDriver: &api.LogDriver{
@@ -122,6 +133,20 @@ func TestServiceSpecFromCompose(t *testing.T) {
 							CPU:               0.5 * api.Core,
 							Memory:            100 * units.MiB,
 							MemoryReservation: 50 * units.MiB,
+							Ulimits: map[string]api.Ulimit{
+								"nofile": {Soft: 20000, Hard: 40000},
+								"nproc":  {Soft: 65535, Hard: 65535},
+							},
+							Devices: []api.DeviceMapping{
+								{HostPath: "/dev/ttyUSB0", ContainerPath: "/dev/ttyUSB0", CgroupPermissions: "rw"},
+								{HostPath: "/dev/sda", ContainerPath: "/dev/xvda", CgroupPermissions: "rwm"},
+							},
+							DeviceReservations: []container.DeviceRequest{
+								{Count: -1, Capabilities: [][]string{{"gpu"}}},
+							},
+						},
+						Sysctls: map[string]string{
+							"net.ipv4.ip_forward": "1",
 						},
 						User: "nginx:nginx",
 						VolumeMounts: []api.VolumeMount{
@@ -134,6 +159,15 @@ func TestServiceSpecFromCompose(t *testing.T) {
 								VolumeName:    "data1",
 								ContainerPath: "/data1",
 							},
+							{
+								VolumeName:    "bind-53f1acbf1de61e9e608c93effca23791674e463d02bb7aaca7c625804aef1926",
+								ContainerPath: "/path/in/container",
+								ReadOnly:      true,
+							},
+							{
+								VolumeName:    "data3-labeled",
+								ContainerPath: "/data3",
+							},
 							{
 								VolumeName:    "data2-alias",
 								ContainerPath: "/data2/long/syntax",
@@ -168,8 +202,24 @@ func TestServiceSpecFromCompose(t *testing.T) {
 							Mode:          api.PortModeHost,
 						},
 					},
+					Placement: api.Placement{
+						Machines: []string{"machine-1", "machine-2"},
+					},
 					Replicas: 3,
+					UpdateConfig: api.UpdateConfig{
+						Order:         api.UpdateOrderStopFirst,
+						MonitorPeriod: &api.DefaultHealthMonitorPeriod,
+					},
 					Volumes: []api.VolumeSpec{
+						{
+							Name: "bind-53f1acbf1de61e9e608c93effca23791674e463d02bb7aaca7c625804aef1926",
+							Type: api.VolumeTypeBind,
+							BindOptions: &api.BindOptions{
+								HostPath:       "/path/on/host",
+								CreateHostPath: true,
+								Propagation:    mount.Propagation("rprivate"),
+							},
+						},
 						{
 							Name: "bind-bb6aed1683cea1e0a1ae5cd227aacd0734f2f87f7a78fcf1baeff978ce300b90",
 							Type: api.VolumeTypeBind,
@@ -202,11 +252,22 @@ func TestServiceSpecFromCompose(t *testing.T) {
 								},
 							},
 						},
+						{
+							Name: "data3-labeled",
+							Type: api.VolumeTypeVolume,
+							VolumeOptions: &api.VolumeOptions{
+								Name:    "data3-labeled",
+								NoCopy:  true,
+								SubPath: "app/data",
+								Labels:  map[string]string{"env": "test"},
+							},
+						},
 						{
 							Name: "tmpfs-efa57ba8b6a1779674ac438de3af8729e2d55900b79eb929431cf9c5b0179542",
 							Type: api.VolumeTypeTmpfs,
 							TmpfsOptions: &mount.TmpfsOptions{
 								SizeBytes: 10 * units.MiB,
+								Mode:      os.FileMode(1770),
 							},
 						},
 					},
@@ -252,6 +313,8 @@ func TestServiceSpecFromCompose(t *testing.T) {
 }
 
 func TestServiceSpecFromCompose_Caddy(t *testing.T) {
+	t.Parallel()
+
 	tests := []struct {
 		name        string
 		composeYAML string
@@ -400,6 +463,8 @@ services:
 }
 
 func TestServiceSpecFromCompose_GPUs(t *testing.T) {
+	t.Parallel()
+
 	tests := []struct {
 		name               string
 		composeYAML        string
@@ -587,6 +652,8 @@ services:
 }
 
 func TestServiceSpecFromCompose_VolumeDriverOpts(t *testing.T) {
+	t.Parallel()
+
 	tests := []struct {
 		name           string
 		composeYAML    string
@@ -694,7 +761,269 @@ volumes:
 	}
 }
 
+func TestServiceSpecFromCompose_Ulimits(t *testing.T) {
+	t.Parallel()
+
+	tests := []struct {
+		name        string
+		composeYAML string
+		expected    map[string]api.Ulimit
+	}{
+		{
+			name: "single ulimit with soft and hard limits",
+			composeYAML: `
+services:
+  db:
+    image: postgres
+    ulimits:
+      nofile:
+        soft: 20000
+        hard: 40000
+`,
+			expected: map[string]api.Ulimit{
+				"nofile": {
+					Soft: 20000,
+					Hard: 40000,
+				},
+			},
+		},
+		{
+			name: "single ulimit with single value (soft=hard)",
+			composeYAML: `
+services:
+  db:
+    image: postgres
+    ulimits:
+      nproc: 65535
+`,
+			expected: map[string]api.Ulimit{
+				"nproc": {
+					Soft: 65535,
+					Hard: 65535,
+				},
+			},
+		},
+		{
+			name: "multiple ulimits",
+			composeYAML: `
+services:
+  db:
+    image: postgres
+    ulimits:
+      nofile:
+        soft: 20000
+        hard: 40000
+      nproc: 65535
+`,
+			expected: map[string]api.Ulimit{
+				"nofile": {
+					Soft: 20000,
+					Hard: 40000,
+				},
+				"nproc": {
+					Soft: 65535,
+					Hard: 65535,
+				},
+			},
+		},
+		{
+			name: "empty ulimits",
+			composeYAML: `
+services:
+  db:
+    image: postgres
+    ulimits: {}
+`,
+			expected: nil,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			project, err := LoadProjectFromContent(context.Background(), tt.composeYAML)
+			require.NoError(t, err)
+
+			spec, err := ServiceSpecFromCompose(project, "db")
+			require.NoError(t, err)
+
+			assert.Equal(t, tt.expected, spec.Container.Resources.Ulimits)
+		})
+	}
+}
+
+func TestServiceSpecFromCompose_UpdateConfig(t *testing.T) {
+	t.Parallel()
+
+	tests := []struct {
+		name        string
+		composeYAML string
+		expected    api.UpdateConfig
+		expectError bool
+	}{
+		{
+			name: "no update_config",
+			composeYAML: `
+services:
+  test:
+    image: nginx
+`,
+			expected: api.UpdateConfig{},
+		},
+		{
+			name: "empty update_config",
+			composeYAML: `
+services:
+  test:
+    image: nginx
+    deploy:
+      update_config: {}
+`,
+			expected: api.UpdateConfig{
+				MonitorPeriod: &api.DefaultHealthMonitorPeriod,
+			},
+		},
+		{
+			name: "update_config with unsupported attributes ignored",
+			composeYAML: `
+services:
+  test:
+    image: nginx
+    deploy:
+      update_config:
+        parallelism: 1
+`,
+			expected: api.UpdateConfig{
+				MonitorPeriod: &api.DefaultHealthMonitorPeriod,
+			},
+		},
+		{
+			name: "update_config with stop-first order",
+			composeYAML: `
+services:
+  test:
+    image: postgres
+    deploy:
+      update_config:
+        order: stop-first
+`,
+			expected: api.UpdateConfig{
+				Order:         api.UpdateOrderStopFirst,
+				MonitorPeriod: &api.DefaultHealthMonitorPeriod,
+			},
+		},
+		{
+			name: "update_config with start-first order",
+			composeYAML: `
+services:
+  test:
+    image: nginx
+    deploy:
+      update_config:
+        order: start-first
+`,
+			expected: api.UpdateConfig{
+				Order:         api.UpdateOrderStartFirst,
+				MonitorPeriod: &api.DefaultHealthMonitorPeriod,
+			},
+		},
+		{
+			name: "update_config with invalid order",
+			composeYAML: `
+services:
+  test:
+    image: nginx
+    deploy:
+      update_config:
+        order: invalid-order
+`,
+			expectError: true,
+		},
+		{
+			name: "update_config with replicas and order",
+			composeYAML: `
+services:
+  test:
+    image: nginx
+    deploy:
+      replicas: 3
+      update_config:
+        order: stop-first
+`,
+			expected: api.UpdateConfig{
+				Order:         api.UpdateOrderStopFirst,
+				MonitorPeriod: &api.DefaultHealthMonitorPeriod,
+			},
+		},
+		{
+			name: "update_config with custom monitor",
+			composeYAML: `
+services:
+  test:
+    image: nginx
+    deploy:
+      update_config:
+        monitor: 10s
+`,
+			expected: api.UpdateConfig{
+				MonitorPeriod: api.AsPtr(10 * time.Second),
+			},
+		},
+		{
+			name: "update_config with monitor and order",
+			composeYAML: `
+services:
+  test:
+    image: nginx
+    deploy:
+      update_config:
+        order: start-first
+        monitor: 30s
+`,
+			expected: api.UpdateConfig{
+				Order:         api.UpdateOrderStartFirst,
+				MonitorPeriod: api.AsPtr(30 * time.Second),
+			},
+		},
+		{
+			name: "update_config with zero monitor skips monitoring",
+			composeYAML: `
+services:
+  test:
+    image: nginx
+    deploy:
+      update_config:
+        monitor: 0s
+`,
+			expected: api.UpdateConfig{
+				MonitorPeriod: api.AsPtr(time.Duration(0)),
+			},
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			project, err := LoadProjectFromContent(context.Background(), tt.composeYAML)
+			if tt.expectError {
+				require.Error(t, err)
+				return
+			}
+			require.NoError(t, err)
+
+			spec, err := ServiceSpecFromCompose(project, "test")
+			if tt.expectError {
+				assert.Error(t, err)
+				return
+			}
+			require.NoError(t, err)
+
+			assert.Equal(t, tt.expected, spec.UpdateConfig)
+		})
+	}
+}
+
 func TestServiceSpecFromCompose_XMachinesPlacement(t *testing.T) {
+	t.Parallel()
+
 	tests := []struct {
 		name        string
 		composeYAML string
@@ -851,3 +1180,104 @@ services:
 		})
 	}
 }
+
+func TestServiceSpecFromCompose_Devices(t *testing.T) {
+	t.Parallel()
+
+	tests := []struct {
+		name                 string
+		composeYAML          string
+		expectedDevices      []api.DeviceMapping
+		expectedReservations []container.DeviceRequest
+	}{
+		{
+			name: "simple device",
+			composeYAML: `
+services:
+  test:
+    image: nginx
+    devices:
+      - /dev/dri
+`,
+			expectedDevices: []api.DeviceMapping{
+				{HostPath: "/dev/dri", ContainerPath: "/dev/dri", CgroupPermissions: "rwm"},
+			},
+		},
+		{
+			name: "device with target and permissions",
+			composeYAML: `
+services:
+  test:
+    image: nginx
+    devices:
+      - /dev/sda:/dev/xvda:r
+`,
+			expectedDevices: []api.DeviceMapping{
+				{HostPath: "/dev/sda", ContainerPath: "/dev/xvda", CgroupPermissions: "r"},
+			},
+		},
+		{
+			name: "multiple devices",
+			composeYAML: `
+services:
+  test:
+    image: nginx
+    devices:
+      - "/dev/ttyUSB0:/dev/ttyUSB0:rw"
+      - /dev/sda:/dev/xvda
+      - "/dev/dri"
+`,
+			expectedDevices: []api.DeviceMapping{
+				{HostPath: "/dev/ttyUSB0", ContainerPath: "/dev/ttyUSB0", CgroupPermissions: "rw"},
+				{HostPath: "/dev/sda", ContainerPath: "/dev/xvda", CgroupPermissions: "rwm"},
+				{HostPath: "/dev/dri", ContainerPath: "/dev/dri", CgroupPermissions: "rwm"},
+			},
+		},
+		{
+			name: "CDI device",
+			composeYAML: `
+services:
+  test:
+    image: nginx
+    devices:
+      - vendor.com/class=device1
+`,
+			expectedReservations: []container.DeviceRequest{
+				{Driver: "cdi", DeviceIDs: []string{"vendor.com/class=device1"}},
+			},
+		},
+		{
+			name: "mixed CDI and regular devices",
+			composeYAML: `
+services:
+  test:
+    image: nginx
+    devices:
+      - /dev/dri
+      - vendor.com/class=device1
+      - nvidia.com/gpu=0
+      - /dev/sda:/dev/xvda:r
+`,
+			expectedDevices: []api.DeviceMapping{
+				{HostPath: "/dev/dri", ContainerPath: "/dev/dri", CgroupPermissions: "rwm"},
+				{HostPath: "/dev/sda", ContainerPath: "/dev/xvda", CgroupPermissions: "r"},
+			},
+			expectedReservations: []container.DeviceRequest{
+				{Driver: "cdi", DeviceIDs: []string{"vendor.com/class=device1", "nvidia.com/gpu=0"}},
+			},
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			project, err := LoadProjectFromContent(context.Background(), tt.composeYAML)
+			require.NoError(t, err)
+
+			spec, err := ServiceSpecFromCompose(project, "test")
+			require.NoError(t, err)
+
+			assert.Equal(t, tt.expectedDevices, spec.Container.Resources.Devices)
+			assert.Equal(t, tt.expectedReservations, spec.Container.Resources.DeviceReservations)
+		})
+	}
+}

pkg/client/compose/testdata/compose-full-spec.yaml

@@ -1,12 +1,30 @@
 services:
   test:
+    cap_add:
+      - NET_ADMIN
+    cap_drop:
+      - ALL
     command: ["nginx", "updated", "command"]
     cpus: 0.5
+    deploy:
+      update_config:
+        order: stop-first
+    devices:
+      - /dev/ttyUSB0:/dev/ttyUSB0:rw
+      - /dev/sda:/dev/xvda
     entrypoint: ["/updated-docker-entrypoint.sh"]
     environment:
       BOOL: "true"
       EMPTY: ""
       VAR: value
+    gpus: all
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost"]
+      interval: 1m30s
+      timeout: 10s
+      retries: 5
+      start_period: 15s
+      start_interval: 2s
     image: nginx:latest
     init: true
     logging:
@@ -19,10 +37,30 @@ services:
     privileged: true
     pull_policy: always
     scale: 3
+    sysctls:
+      - net.ipv4.ip_forward=1
+    ulimits:
+      nofile:
+        soft: 20000
+        hard: 40000
+      nproc: 65535
     user: nginx:nginx
     volumes:
       - /etc/passwd:/host/etc/passwd:ro
       - data1:/data1
+      - type: bind
+        source: /path/on/host
+        target: /path/in/container
+        read_only: true
+        bind:
+          create_host_path: true
+          propagation: rprivate
+      - type: volume
+        source: data3-labeled
+        target: /data3
+        volume:
+          nocopy: true
+          subpath: app/data
       - type: volume
         source: data2-alias
         target: /data2/long/syntax
@@ -31,6 +69,8 @@ services:
         target: /tmpfs
         tmpfs:
           size: 10485760
+          mode: 1770
+    x-machines: ["machine-1", "machine-2"]
     x-ports:
       - test.example.com:80/https
       - 8000/http
@@ -49,5 +89,8 @@ volumes:
   data2-alias:
     name: data2
     driver: local
+  data3-labeled:
+    labels:
+      env: test
   data-external:
     external: true

pkg/client/connector/common.go

@@ -0,0 +1,30 @@
+package connector
+
+import (
+	"encoding/json"
+	"fmt"
+)
+
+// defaultServiceConfig defines the default gRPC service configuration including retry policy for transient failures.
+var defaultServiceConfig = mustMarshalJSON(map[string]any{
+	"methodConfig": []map[string]any{
+		{
+			"name": []map[string]string{{"service": ""}},
+			"retryPolicy": map[string]any{
+				"maxAttempts":          5, // 5 is the maximum allowed by gRPC
+				"initialBackoff":       "0.5s",
+				"maxBackoff":           "5s",
+				"backoffMultiplier":    2,
+				"retryableStatusCodes": []string{"UNAVAILABLE"},
+			},
+		},
+	},
+})
+
+func mustMarshalJSON(v any) string {
+	b, err := json.Marshal(v)
+	if err != nil {
+		panic(fmt.Sprintf("failed to marshal service config: %v", err))
+	}
+	return string(b)
+}

pkg/client/connector/ssh.go

@@ -24,6 +24,16 @@ type SSHConnectorConfig struct {
 	SockPath string
 }
 
+// Destination returns the destination string that can be passed to ssh CLI in the format [user@]host.
+func (cfg *SSHConnectorConfig) Destination() string {
+	dst := cfg.Host
+	if cfg.User != "" {
+		dst = fmt.Sprintf("%s@%s", cfg.User, dst)
+	}
+
+	return dst
+}
+
 // SSHConnector establishes a connection to the machine API through an SSH tunnel to the machine.
 type SSHConnector struct {
 	config SSHConnectorConfig
@@ -48,7 +58,11 @@ func (c *SSHConnector) Connect(ctx context.Context) (*grpc.ClientConn, error) {
 		var err error
 		c.client, err = sshexec.Connect(c.config.User, c.config.Host, c.config.Port, c.config.KeyPath)
 		if err != nil {
-			return nil, fmt.Errorf("SSH login to %s@%s:%d: %w", c.config.User, c.config.Host, c.config.Port, err)
+			dst := c.config.Destination()
+			if c.config.Port != 0 {
+				dst = fmt.Sprintf("%s:%d", dst, c.config.Port)
+			}
+			return nil, fmt.Errorf("SSH login to %s: %w", dst, err)
 		}
 	}
 
@@ -59,6 +73,7 @@ func (c *SSHConnector) Connect(ctx context.Context) (*grpc.ClientConn, error) {
 	conn, err := grpc.NewClient(
 		"unix://"+sockPath,
 		grpc.WithTransportCredentials(insecure.NewCredentials()),
+		grpc.WithDefaultServiceConfig(defaultServiceConfig),
 		grpc.WithContextDialer(
 			func(ctx context.Context, addr string) (net.Conn, error) {
 				addr = strings.TrimPrefix(addr, "unix://")

pkg/client/connector/sshcli.go

@@ -4,6 +4,8 @@ import (
 	"context"
 	"fmt"
 	"net"
+	"os"
+	"path/filepath"
 	"strconv"
 
 	"github.com/docker/cli/cli/connhelper/commandconn"
@@ -17,100 +19,96 @@ import (
 // and running `uncloudd dial-stdio` on the remote machine.
 type SSHCLIConnector struct {
 	config SSHConnectorConfig
-	conn   net.Conn
+	// Path to SSH control socket for connection reuse.
+	controlSockPath string
 }
 
 func NewSSHCLIConnector(cfg *SSHConnectorConfig) *SSHCLIConnector {
-	return &SSHCLIConnector{config: *cfg}
+	return &SSHCLIConnector{
+		config:          *cfg,
+		controlSockPath: controlSocketPath(),
+	}
 }
 
-// sshCLIDialer implements proxy.ContextDialer by spawning SSH processes with -W flag.
-type sshCLIDialer struct {
-	config SSHConnectorConfig
-}
+// controlSocketPath returns a unique control socket path for the SSH connection.
+// Returns an empty string if unable to find or create a suitable path.
+func controlSocketPath() string {
+	// %C is expanded by `ssh` to a hash of user, local and remote hostnames, port, and the contents
+	// of the ProxyJump option. This ensures that shared connections are uniquely identified.
+	sockName := fmt.Sprintf("uc_control_%%C.sock")
 
-// buildDialArgs constructs SSH command arguments for -W flag dialing.
-func (d *sshCLIDialer) buildDialArgs(address string) []string {
-	args := []string{}
-
-	// Add connection timeout to fail fast when node is down.
-	args = append(args, "-o", "ConnectTimeout=5")
-
-	// Add port if non-standard.
-	if d.config.Port != 0 && d.config.Port != 22 {
-		args = append(args, "-p", strconv.Itoa(d.config.Port))
+	// Prefer XDG_RUNTIME_DIR if set, fall back to ~/.ssh if it exists.
+	if dir := os.Getenv("XDG_RUNTIME_DIR"); dir != "" {
+		return filepath.Join(dir, sockName)
+	}
+	if home, err := os.UserHomeDir(); err == nil {
+		sshDir := filepath.Join(home, ".ssh")
+		if fi, sErr := os.Stat(sshDir); sErr == nil && fi.IsDir() {
+			return filepath.Join(sshDir, sockName)
+		}
 	}
 
-	// Add identity file if specified.
-	if d.config.KeyPath != "" {
-		args = append(args, "-i", d.config.KeyPath)
+	// Last resort: create a subdirectory in temp with restricted permissions.
+	tmpDir := filepath.Join(os.TempDir(), fmt.Sprintf("uncloud-%d", os.Getuid()))
+	path := filepath.Join(tmpDir, sockName)
+	if len(path)-2+40 < 104 { // 40 chars for %C hash, 104 is typical UNIX socket path limit
+		if err := os.MkdirAll(tmpDir, 0o700); err == nil {
+			return path
+		}
 	}
 
-	// Add -W flag for stdin/stdout forwarding to target address.
-	args = append(args, "-W", address)
-
-	// Add user@host.
-	args = append(args, d.config.User+"@"+d.config.Host)
-
-	return args
-}
-
-// DialContext establishes a connection to the target address through an SSH tunnel using -W flag.
-func (d *sshCLIDialer) DialContext(ctx context.Context, network, address string) (net.Conn, error) {
-	// Only support TCP connections.
-	if network != "tcp" {
-		return nil, fmt.Errorf("unsupported network type: %s", network)
-	}
-
-	// Build SSH command arguments.
-	args := d.buildDialArgs(address)
-
-	// Create connection using commandconn.
-	conn, err := commandconn.New(ctx, "ssh", args...)
-	if err != nil {
-		return nil, fmt.Errorf("SSH connection to %s@%s for dialing %s: %w", d.config.User, d.config.Host, address, err)
-	}
-
-	return conn, nil
+	return ""
 }
 
 func (c *SSHCLIConnector) Connect(ctx context.Context) (*grpc.ClientConn, error) {
-	// Build SSH command arguments.
-	args := c.buildSSHArgs()
-
-	// Create connection using commandconn.
-	conn, err := commandconn.New(ctx, "ssh", args...)
-	if err != nil {
-		return nil, fmt.Errorf("SSH connection to %s@%s: %w", c.config.User, c.config.Host, err)
-	}
-	c.conn = conn
-
-	// Create gRPC client over the connection.
-	// Use a custom dialer that returns our existing connection.
+	// Create gRPC client with a dialer that spawns a new SSH connection on demand.
+	// Each dial attempt runs `ssh ... uncloudd dial-stdio`, reusing the control socket if available.
 	grpcConn, err := grpc.NewClient(
 		"passthrough:///", // Dummy target since we're using a custom dialer.
 		grpc.WithTransportCredentials(insecure.NewCredentials()),
+		grpc.WithDefaultServiceConfig(defaultServiceConfig),
 		grpc.WithContextDialer(func(ctx context.Context, _ string) (net.Conn, error) {
-			return c.conn, nil
+			args := c.buildSSHArgs()
+			conn, err := commandconn.New(ctx, "ssh", args...)
+			if err != nil {
+				return nil, fmt.Errorf("SSH connection to %s: %w", c.config.Destination(), err)
+			}
+			return conn, nil
 		}),
 	)
 	if err != nil {
-		c.conn.Close()
 		return nil, fmt.Errorf("create machine API client: %w", err)
 	}
 
 	return grpcConn, nil
 }
 
-// buildSSHArgs constructs the SSH command arguments.
+// buildSSHArgs constructs the SSH command arguments to run `uncloudd dial-stdio` on the remote machine reusing
+// the established connection via control socket.
 func (c *SSHCLIConnector) buildSSHArgs() []string {
-	args := []string{}
+	var args []string
+
+	// Add control socket options for connection reuse if available.
+	if c.controlSockPath != "" {
+		args = append(args, "-o", "ControlMaster=auto")
+		args = append(args, "-o", "ControlPath="+c.controlSockPath)
+
+		// Keep the established connection alive for a short duration after the last session closes to allow reuse.
+		controlPersist := "10m"
+		// Override the default duration with the UNCLOUD_SSH_CONTROL_PERSIST env variable.
+		if v := os.Getenv("UNCLOUD_SSH_CONTROL_PERSIST"); v != "" {
+			controlPersist = v
+		}
+		args = append(args, "-o", "ControlPersist="+controlPersist)
+	}
 
 	// Add connection timeout to fail fast when node is down.
 	args = append(args, "-o", "ConnectTimeout=5")
+	// Disable pseudo-terminal allocation to prevent SSH from executing as a login shell.
+	args = append(args, "-T")
 
-	// Add port if non-standard.
-	if c.config.Port != 0 && c.config.Port != 22 {
+	// Add port if specified.
+	if c.config.Port != 0 {
 		args = append(args, "-p", strconv.Itoa(c.config.Port))
 	}
 
@@ -119,8 +117,8 @@ func (c *SSHCLIConnector) buildSSHArgs() []string {
 		args = append(args, "-i", c.config.KeyPath)
 	}
 
-	// Add user@host.
-	args = append(args, c.config.User+"@"+c.config.Host)
+	// Add [user@]host destination.
+	args = append(args, c.config.Destination())
 
 	// Add remote command: uncloudd dial-stdio
 	args = append(args, "uncloudd", "dial-stdio")
@@ -140,15 +138,74 @@ func (c *SSHCLIConnector) Dialer() (proxy.ContextDialer, error) {
 	}
 
 	return &sshCLIDialer{
-		config: c.config,
+		config:          c.config,
+		controlSockPath: c.controlSockPath,
 	}, nil
 }
 
 func (c *SSHCLIConnector) Close() error {
-	if c.conn != nil {
-		err := c.conn.Close()
-		c.conn = nil
-		return err
-	}
+	// Individual connections are managed by gRPC and closed when the gRPC connection closes.
+	// The SSH control socket may persist for connection reuse across CLI invocations.
 	return nil
 }
+
+// sshCLIDialer implements proxy.ContextDialer by spawning SSH processes with -W flag.
+type sshCLIDialer struct {
+	config SSHConnectorConfig
+	// Shared control socket path from SSHCLIConnector for connection reuse.
+	controlSockPath string
+}
+
+// buildDialArgs constructs SSH command arguments for -W flag dialing.
+func (d *sshCLIDialer) buildDialArgs(address string) []string {
+	var args []string
+
+	if d.controlSockPath != "" {
+		// Try to reuse the existing control connection without initiating a new one.
+		// Falls back to direct connection if the control socket is not available.
+		args = append(args, "-o", "ControlMaster=no")
+		args = append(args, "-o", "ControlPath="+d.controlSockPath)
+	}
+
+	// Add connection timeout to fail fast when node is down.
+	args = append(args, "-o", "ConnectTimeout=5")
+	// Disable pseudo-terminal allocation to prevent SSH from executing as a login shell.
+	args = append(args, "-T")
+
+	// Add port if specified.
+	if d.config.Port != 0 {
+		args = append(args, "-p", strconv.Itoa(d.config.Port))
+	}
+
+	// Add identity file if specified.
+	if d.config.KeyPath != "" {
+		args = append(args, "-i", d.config.KeyPath)
+	}
+
+	// Add -W flag for stdin/stdout forwarding to target address.
+	args = append(args, "-W", address)
+
+	// Add [user@]host destination.
+	args = append(args, d.config.Destination())
+
+	return args
+}
+
+// DialContext establishes a connection to the target address through an SSH tunnel using -W flag.
+func (d *sshCLIDialer) DialContext(ctx context.Context, network, address string) (net.Conn, error) {
+	// Only support TCP connections.
+	if network != "tcp" {
+		return nil, fmt.Errorf("unsupported network type: %s", network)
+	}
+
+	// Build SSH command arguments.
+	args := d.buildDialArgs(address)
+
+	// Create connection using docker's commandconn.
+	conn, err := commandconn.New(ctx, "ssh", args...)
+	if err != nil {
+		return nil, fmt.Errorf("SSH connection to %s for dialing %s: %w", d.config.Destination(), address, err)
+	}
+
+	return conn, nil
+}

pkg/client/connector/sshcli_test.go

@@ -1,6 +1,7 @@
 package connector
 
 import (
+	"strings"
 	"testing"
 
 	"github.com/psviderski/uncloud/internal/machine"
@@ -11,17 +12,28 @@ func TestSSHCLIConnector_buildSSHArgs(t *testing.T) {
 	t.Parallel()
 
 	tests := []struct {
-		name     string
-		config   SSHConnectorConfig
-		expected []string
+		name            string
+		config          SSHConnectorConfig
+		controlSockPath string
+		expected        []string
 	}{
 		{
-			name: "basic connection",
+			name: "basic connection with control socket",
 			config: SSHConnectorConfig{
 				User: "root",
 				Host: "example.com",
 			},
-			expected: []string{"-o", "ConnectTimeout=5", "root@example.com", "uncloudd", "dial-stdio"},
+			controlSockPath: "/tmp/test.sock",
+			expected:        []string{"-o", "ControlMaster=auto", "-o", "ControlPath=/tmp/test.sock", "-o", "ControlPersist=10m", "-o", "ConnectTimeout=5", "-T", "root@example.com", "uncloudd", "dial-stdio"},
+		},
+		{
+			name: "basic connection without control socket",
+			config: SSHConnectorConfig{
+				User: "root",
+				Host: "example.com",
+			},
+			controlSockPath: "",
+			expected:        []string{"-o", "ConnectTimeout=5", "-T", "root@example.com", "uncloudd", "dial-stdio"},
 		},
 		{
 			name: "with custom port",
@@ -30,7 +42,8 @@ func TestSSHCLIConnector_buildSSHArgs(t *testing.T) {
 				Host: "example.com",
 				Port: 2222,
 			},
-			expected: []string{"-o", "ConnectTimeout=5", "-p", "2222", "root@example.com", "uncloudd", "dial-stdio"},
+			controlSockPath: "/tmp/test.sock",
+			expected:        []string{"-o", "ControlMaster=auto", "-o", "ControlPath=/tmp/test.sock", "-o", "ControlPersist=10m", "-o", "ConnectTimeout=5", "-T", "-p", "2222", "root@example.com", "uncloudd", "dial-stdio"},
 		},
 		{
 			name: "with identity file",
@@ -39,7 +52,8 @@ func TestSSHCLIConnector_buildSSHArgs(t *testing.T) {
 				Host:    "example.com",
 				KeyPath: "/path/to/key",
 			},
-			expected: []string{"-o", "ConnectTimeout=5", "-i", "/path/to/key", "root@example.com", "uncloudd", "dial-stdio"},
+			controlSockPath: "/tmp/test.sock",
+			expected:        []string{"-o", "ControlMaster=auto", "-o", "ControlPath=/tmp/test.sock", "-o", "ControlPersist=10m", "-o", "ConnectTimeout=5", "-T", "-i", "/path/to/key", "root@example.com", "uncloudd", "dial-stdio"},
 		},
 		{
 			name: "with custom socket path",
@@ -48,7 +62,8 @@ func TestSSHCLIConnector_buildSSHArgs(t *testing.T) {
 				Host:     "example.com",
 				SockPath: "/custom/path/uncloud.sock",
 			},
-			expected: []string{"-o", "ConnectTimeout=5", "root@example.com", "uncloudd", "dial-stdio", "--socket", "/custom/path/uncloud.sock"},
+			controlSockPath: "/tmp/test.sock",
+			expected:        []string{"-o", "ControlMaster=auto", "-o", "ControlPath=/tmp/test.sock", "-o", "ControlPersist=10m", "-o", "ConnectTimeout=5", "-T", "root@example.com", "uncloudd", "dial-stdio", "--socket", "/custom/path/uncloud.sock"},
 		},
 		{
 			name: "with default socket path (not included)",
@@ -57,7 +72,8 @@ func TestSSHCLIConnector_buildSSHArgs(t *testing.T) {
 				Host:     "example.com",
 				SockPath: machine.DefaultUncloudSockPath,
 			},
-			expected: []string{"-o", "ConnectTimeout=5", "root@example.com", "uncloudd", "dial-stdio"},
+			controlSockPath: "/tmp/test.sock",
+			expected:        []string{"-o", "ControlMaster=auto", "-o", "ControlPath=/tmp/test.sock", "-o", "ControlPersist=10m", "-o", "ConnectTimeout=5", "-T", "root@example.com", "uncloudd", "dial-stdio"},
 		},
 		{
 			name: "all options combined",
@@ -68,16 +84,28 @@ func TestSSHCLIConnector_buildSSHArgs(t *testing.T) {
 				KeyPath:  "/path/to/key",
 				SockPath: "/custom/path/uncloud.sock",
 			},
-			expected: []string{"-o", "ConnectTimeout=5", "-p", "2222", "-i", "/path/to/key", "root@example.com", "uncloudd", "dial-stdio", "--socket", "/custom/path/uncloud.sock"},
+			controlSockPath: "/tmp/test.sock",
+			expected:        []string{"-o", "ControlMaster=auto", "-o", "ControlPath=/tmp/test.sock", "-o", "ControlPersist=10m", "-o", "ConnectTimeout=5", "-T", "-p", "2222", "-i", "/path/to/key", "root@example.com", "uncloudd", "dial-stdio", "--socket", "/custom/path/uncloud.sock"},
 		},
 		{
-			name: "port 22 not included (default)",
+			name: "port 0 not included",
 			config: SSHConnectorConfig{
 				User: "root",
 				Host: "example.com",
 				Port: 0,
 			},
-			expected: []string{"-o", "ConnectTimeout=5", "root@example.com", "uncloudd", "dial-stdio"},
+			controlSockPath: "/tmp/test.sock",
+			expected:        []string{"-o", "ControlMaster=auto", "-o", "ControlPath=/tmp/test.sock", "-o", "ControlPersist=10m", "-o", "ConnectTimeout=5", "-T", "root@example.com", "uncloudd", "dial-stdio"},
+		},
+		{
+			name: "port 22 included when explicit",
+			config: SSHConnectorConfig{
+				User: "root",
+				Host: "example.com",
+				Port: 22,
+			},
+			controlSockPath: "/tmp/test.sock",
+			expected:        []string{"-o", "ControlMaster=auto", "-o", "ControlPath=/tmp/test.sock", "-o", "ControlPersist=10m", "-o", "ConnectTimeout=5", "-T", "-p", "22", "root@example.com", "uncloudd", "dial-stdio"},
 		},
 	}
 
@@ -85,7 +113,7 @@ func TestSSHCLIConnector_buildSSHArgs(t *testing.T) {
 		t.Run(tt.name, func(t *testing.T) {
 			t.Parallel()
 
-			c := &SSHCLIConnector{config: tt.config}
+			c := &SSHCLIConnector{config: tt.config, controlSockPath: tt.controlSockPath}
 			got := c.buildSSHArgs()
 			assert.Equal(t, tt.expected, got)
 		})
@@ -96,61 +124,77 @@ func TestSSHCLIDialer_buildDialArgs(t *testing.T) {
 	t.Parallel()
 
 	tests := []struct {
-		name     string
-		config   SSHConnectorConfig
-		address  string
-		expected []string
+		name            string
+		config          SSHConnectorConfig
+		controlSockPath string
+		address         string
+		expected        []string
 	}{
 		{
-			name: "basic connection",
+			name: "basic connection without control socket",
 			config: SSHConnectorConfig{
 				User: "root",
 				Host: "example.com",
 			},
-			address:  "10.210.1.1:5000",
-			expected: []string{"-o", "ConnectTimeout=5", "-W", "10.210.1.1:5000", "root@example.com"},
+			controlSockPath: "",
+			address:         "10.210.1.1:5000",
+			expected:        []string{"-o", "ConnectTimeout=5", "-T", "-W", "10.210.1.1:5000", "root@example.com"},
 		},
 		{
-			name: "custom port",
+			name: "basic connection with control socket",
+			config: SSHConnectorConfig{
+				User: "root",
+				Host: "example.com",
+			},
+			controlSockPath: "/tmp/test.sock",
+			address:         "10.210.1.1:5000",
+			expected:        []string{"-o", "ControlMaster=no", "-o", "ControlPath=/tmp/test.sock", "-o", "ConnectTimeout=5", "-T", "-W", "10.210.1.1:5000", "root@example.com"},
+		},
+		{
+			name: "custom port with control socket",
 			config: SSHConnectorConfig{
 				User: "root",
 				Host: "example.com",
 				Port: 2222,
 			},
-			address:  "10.210.1.1:5000",
-			expected: []string{"-o", "ConnectTimeout=5", "-p", "2222", "-W", "10.210.1.1:5000", "root@example.com"},
+			controlSockPath: "/tmp/test.sock",
+			address:         "10.210.1.1:5000",
+			expected:        []string{"-o", "ControlMaster=no", "-o", "ControlPath=/tmp/test.sock", "-o", "ConnectTimeout=5", "-T", "-p", "2222", "-W", "10.210.1.1:5000", "root@example.com"},
 		},
 		{
-			name: "with identity file",
+			name: "with identity file and control socket",
 			config: SSHConnectorConfig{
 				User:    "root",
 				Host:    "example.com",
 				Port:    22,
 				KeyPath: "/home/user/.ssh/id_rsa",
 			},
-			address:  "10.210.1.1:5000",
-			expected: []string{"-o", "ConnectTimeout=5", "-i", "/home/user/.ssh/id_rsa", "-W", "10.210.1.1:5000", "root@example.com"},
+			controlSockPath: "/tmp/test.sock",
+			address:         "10.210.1.1:5000",
+			expected:        []string{"-o", "ControlMaster=no", "-o", "ControlPath=/tmp/test.sock", "-o", "ConnectTimeout=5", "-T", "-p", "22", "-i", "/home/user/.ssh/id_rsa", "-W", "10.210.1.1:5000", "root@example.com"},
 		},
 		{
-			name: "custom port with identity file",
+			name: "custom port with identity file and control socket",
 			config: SSHConnectorConfig{
 				User:    "root",
 				Host:    "example.com",
 				Port:    2222,
 				KeyPath: "/home/user/.ssh/id_rsa",
 			},
-			address:  "10.210.1.1:5000",
-			expected: []string{"-o", "ConnectTimeout=5", "-p", "2222", "-i", "/home/user/.ssh/id_rsa", "-W", "10.210.1.1:5000", "root@example.com"},
+			controlSockPath: "/tmp/test.sock",
+			address:         "10.210.1.1:5000",
+			expected:        []string{"-o", "ControlMaster=no", "-o", "ControlPath=/tmp/test.sock", "-o", "ConnectTimeout=5", "-T", "-p", "2222", "-i", "/home/user/.ssh/id_rsa", "-W", "10.210.1.1:5000", "root@example.com"},
 		},
 		{
-			name: "zero port defaults to 22",
+			name: "port 0 not included",
 			config: SSHConnectorConfig{
 				User: "root",
 				Host: "example.com",
 				Port: 0,
 			},
-			address:  "10.210.1.1:5000",
-			expected: []string{"-o", "ConnectTimeout=5", "-W", "10.210.1.1:5000", "root@example.com"},
+			controlSockPath: "/tmp/test.sock",
+			address:         "10.210.1.1:5000",
+			expected:        []string{"-o", "ControlMaster=no", "-o", "ControlPath=/tmp/test.sock", "-o", "ConnectTimeout=5", "-T", "-W", "10.210.1.1:5000", "root@example.com"},
 		},
 	}
 
@@ -158,9 +202,28 @@ func TestSSHCLIDialer_buildDialArgs(t *testing.T) {
 		t.Run(tt.name, func(t *testing.T) {
 			t.Parallel()
 
-			d := &sshCLIDialer{config: tt.config}
+			d := &sshCLIDialer{config: tt.config, controlSockPath: tt.controlSockPath}
 			got := d.buildDialArgs(tt.address)
 			assert.Equal(t, tt.expected, got)
 		})
 	}
 }
+
+func TestControlSocketPath(t *testing.T) {
+	// Note: Cannot use t.Parallel() because a subtest uses t.Setenv().
+
+	path1 := controlSocketPath()
+	path2 := controlSocketPath()
+
+	assert.Equal(t, path1, path2)
+	assert.True(t, strings.HasSuffix(path1, ".sock"))
+	assert.Contains(t, path1, "%C")
+
+	t.Run("uses XDG_RUNTIME_DIR when set", func(t *testing.T) {
+		runDir := "/user/runtime/dir"
+		t.Setenv("XDG_RUNTIME_DIR", runDir)
+
+		path := controlSocketPath()
+		assert.True(t, strings.HasPrefix(path, runDir))
+	})
+}

pkg/client/connector/tcp.go

@@ -23,6 +23,7 @@ func (c *TCPConnector) Connect(_ context.Context) (*grpc.ClientConn, error) {
 	conn, err := grpc.NewClient(
 		c.apiAddr.String(),
 		grpc.WithTransportCredentials(insecure.NewCredentials()),
+		grpc.WithDefaultServiceConfig(defaultServiceConfig),
 	)
 	if err != nil {
 		return nil, fmt.Errorf("create machine API client: %w", err)

pkg/client/connector/unix.go

@@ -25,6 +25,7 @@ func (c *UnixConnector) Connect(_ context.Context) (*grpc.ClientConn, error) {
 	conn, err := grpc.NewClient(
 		target,
 		grpc.WithTransportCredentials(insecure.NewCredentials()),
+		grpc.WithDefaultServiceConfig(defaultServiceConfig),
 	)
 	if err != nil {
 		return nil, fmt.Errorf("create machine API client: %w", err)

pkg/client/connector/wireguard.go

@@ -66,6 +66,7 @@ func (c *WireGuardConnector) Connect(ctx context.Context) (*grpc.ClientConn, err
 	conn, err := grpc.NewClient(
 		machineAPIAddr,
 		grpc.WithTransportCredentials(insecure.NewCredentials()),
+		grpc.WithDefaultServiceConfig(defaultServiceConfig),
 		grpc.WithContextDialer(func(ctx context.Context, addr string) (net.Conn, error) {
 			return c.tun.DialContext(ctx, "tcp", addr)
 		}),

pkg/client/container.go

@@ -5,6 +5,7 @@ import (
 	"errors"
 	"fmt"
 	"strings"
+	"time"
 
 	"github.com/containerd/errdefs"
 	"github.com/docker/compose/v2/pkg/progress"
@@ -17,6 +18,9 @@ import (
 	"google.golang.org/grpc/status"
 )
 
+// TODO: format container and machine IDs in 'Container %s on %s' events as bold.
+//  Consider formatting containers as <service_name>/<short-container-id>.
+
 // CreateContainer creates a new container for the given service on the specified machine.
 func (cli *Client) CreateContainer(
 	ctx context.Context, serviceID string, spec api.ServiceSpec, machineID string,
@@ -354,3 +358,150 @@ func (cli *Client) ExecContainer(
 
 	return exitCode, nil
 }
+
+// WaitContainerHealthy polls the container until it is considered running and healthy.
+//
+// For containers without a health check, it waits for the monitor period and then verifies the container
+// is still running and not restarting.
+//
+// For containers with a health check, it waits until Docker reports healthy or unhealthy. During the monitor period,
+// unhealthy status is treated as retryable (the container may be recovering from a transient crash).
+// After the monitor period, unhealthy becomes a permanent failure.
+func (cli *Client) WaitContainerHealthy(
+	ctx context.Context, serviceNameOrID, containerNameOrID string, opts api.WaitContainerHealthyOptions,
+) error {
+	// First inspect to get container info, machine name, and health check config.
+	mc, err := cli.InspectContainer(ctx, serviceNameOrID, containerNameOrID)
+	if err != nil {
+		return fmt.Errorf("inspect container: %w", err)
+	}
+
+	machine, err := cli.InspectMachine(ctx, mc.MachineID)
+	if err != nil {
+		return fmt.Errorf("inspect machine '%s': %w", mc.MachineID, err)
+	}
+
+	pw := progress.ContextWriter(ctx)
+	eventID := fmt.Sprintf("Container %s on %s", mc.Container.Name, machine.Machine.Name)
+
+	var monitor time.Duration
+	if opts.MonitorPeriod == nil {
+		monitor = api.DefaultHealthMonitorPeriod
+	} else {
+		monitor = *opts.MonitorPeriod
+	}
+	pw.Event(progress.NewEvent(eventID, progress.Working, fmt.Sprintf("Monitoring (%s)", monitor)))
+
+	// For containers without a health check, just wait for the monitor period and then check the container
+	// is still running and not restarting.
+	if !mc.Container.HasHealthcheck() {
+		select {
+		case <-ctx.Done():
+			return ctx.Err()
+		case <-time.After(monitor):
+		}
+
+		mc, err := cli.InspectContainer(ctx, serviceNameOrID, containerNameOrID)
+		if err != nil {
+			return fmt.Errorf("inspect container: %w", err)
+		}
+
+		if mc.Container.Healthy() {
+			pw.Event(progress.RunningEvent(eventID))
+			return nil
+		}
+
+		humanState, _ := mc.Container.HumanState()
+		pw.Event(progress.ErrorMessageEvent(eventID, fmt.Sprintf("Unhealthy (%s)", humanState)))
+
+		if mc.Container.State.Restarting {
+			return fmt.Errorf("container is restarting after monitor period (%s): exit_code=%d",
+				monitor, mc.Container.State.ExitCode)
+		}
+		return fmt.Errorf("container is unhealthy after monitor period (%s): %s", monitor, humanState)
+	}
+
+	// For containers with a health check, wait until Docker reports healthy or unhealthy.
+	mctx := proxyToMachine(ctx, machine.Machine)
+	mctx, cancel := context.WithTimeout(mctx, healthcheckTimeout(mc.Container.Config.Healthcheck))
+	defer cancel()
+	ticker := time.NewTicker(1 * time.Second)
+	defer ticker.Stop()
+	monitorDeadline := time.Now().Add(monitor)
+
+	for {
+		select {
+		case <-mctx.Done():
+			return mctx.Err()
+		case <-ticker.C:
+			ctr, err := cli.Docker.InspectServiceContainer(mctx, mc.Container.ID)
+			if err != nil {
+				pw.Event(progress.NewEvent(eventID, progress.Working,
+					fmt.Sprintf("Health checking (failed to inspect container: %v)", err)))
+				continue
+			}
+
+			// Reset the event status if previous inspect failed.
+			eventStatus := fmt.Sprintf("Monitoring (%s)", monitor)
+			if time.Now().After(monitorDeadline) {
+				// TODO: provide more details about running checks or waiting so the user can see what's going on.
+				eventStatus = "Health checking"
+			}
+			pw.Event(progress.NewEvent(eventID, progress.Working, eventStatus))
+
+			if ctr.Healthy() {
+				pw.Event(progress.Healthy(eventID))
+				return nil
+			}
+			if time.Now().Before(monitorDeadline) {
+				continue
+			}
+
+			if ctr.State.Health.Status == container.Unhealthy {
+				humanState, _ := ctr.HumanState()
+				pw.Event(progress.ErrorMessageEvent(eventID, fmt.Sprintf("Unhealthy (%s)", humanState)))
+
+				if ctr.State.Restarting {
+					return fmt.Errorf("container is restarting after monitor period (%s): exit_code=%d",
+						monitor, ctr.State.ExitCode)
+				}
+				return fmt.Errorf("container is unhealthy after monitor period (%s): %s", monitor, humanState)
+			}
+		}
+	}
+}
+
+const (
+	// defaultDockerHealthcheckInterval is the default Docker interval between health check runs.
+	defaultDockerHealthcheckInterval = 30 * time.Second
+	// defaultDockerHealthcheckTimeout is the default Docker timeout for each health check run.
+	defaultDockerHealthcheckTimeout = 30 * time.Second
+	// defaultDockerHealthcheckRetries is the default Docker number of consecutive failures needed
+	// to consider the container unhealthy.
+	defaultDockerHealthcheckRetries = 3
+)
+
+// healthcheckTimeout computes the maximum time to wait for a container to become healthy based on
+// its health check config. This is the worst case timeout to stop polling in case something goes wrong and Docker
+// doesn't report the container as unhealthy after it should.
+func healthcheckTimeout(hc *container.HealthConfig) time.Duration {
+	if hc == nil {
+		return 0
+	}
+
+	interval := hc.Interval
+	if interval <= 0 {
+		interval = defaultDockerHealthcheckInterval
+	}
+	timeout := hc.Timeout
+	if timeout <= 0 {
+		timeout = defaultDockerHealthcheckTimeout
+	}
+	retries := hc.Retries
+	if retries <= 0 {
+		retries = defaultDockerHealthcheckRetries
+	}
+
+	// 5s is a buffer to account for scheduling delays.
+	return hc.StartPeriod + time.Duration(retries)*(interval+timeout) + 5*time.Second
+}

pkg/client/deploy/container.go

@@ -83,10 +83,17 @@ func EvalContainerSpecChange(current api.ServiceSpec, new api.ServiceSpec) Conta
 		}
 	}
 
-	// Device reservations are immutable, so we'll need to recreate if any have changed
+	// Device reservations and mappings are immutable, so we'll need to recreate if any have changed
 	if !reflect.DeepEqual(current.Container.Resources.DeviceReservations, newResources.DeviceReservations) {
 		return ContainerNeedsRecreate
 	}
+	if !reflect.DeepEqual(current.Container.Resources.Devices, newResources.Devices) {
+		return ContainerNeedsRecreate
+	}
+	// Ulimits are immutable, so we'll need to recreate if any have changed.
+	if !reflect.DeepEqual(current.Container.Resources.Ulimits, newResources.Ulimits) {
+		return ContainerNeedsRecreate
+	}
 
 	// Check if any mutable properties changed.
 	if !current.Caddy.Equals(new.Caddy) {

pkg/client/deploy/container_test.go

@@ -9,6 +9,44 @@ import (
 	"github.com/stretchr/testify/assert"
 )
 
+func TestEvalContainerSpecChange_ContainerCapAdd(t *testing.T) {
+	t.Parallel()
+
+	currentSpec := api.ServiceSpec{
+		Container: api.ContainerSpec{
+			Image: "nginx:latest",
+		},
+	}
+	newSpec := api.ServiceSpec{
+		Container: api.ContainerSpec{
+			Image:  "nginx:latest",
+			CapAdd: []string{"NET_ADMIN"},
+		},
+	}
+
+	assert.Equal(t, ContainerNeedsRecreate, EvalContainerSpecChange(currentSpec, newSpec))
+	assert.Equal(t, ContainerNeedsRecreate, EvalContainerSpecChange(newSpec, currentSpec))
+}
+
+func TestEvalContainerSpecChange_ContainerCapDrop(t *testing.T) {
+	t.Parallel()
+
+	currentSpec := api.ServiceSpec{
+		Container: api.ContainerSpec{
+			Image: "nginx:latest",
+		},
+	}
+	newSpec := api.ServiceSpec{
+		Container: api.ContainerSpec{
+			Image:   "nginx:latest",
+			CapDrop: []string{"ALL"},
+		},
+	}
+
+	assert.Equal(t, ContainerNeedsRecreate, EvalContainerSpecChange(currentSpec, newSpec))
+	assert.Equal(t, ContainerNeedsRecreate, EvalContainerSpecChange(newSpec, currentSpec))
+}
+
 func TestEvalContainerSpecChange_ContainerResources(t *testing.T) {
 	t.Parallel()
 
@@ -325,6 +363,27 @@ func TestEvalContainerSpecChange_ContainerPrivileged(t *testing.T) {
 	assert.Equal(t, ContainerNeedsRecreate, EvalContainerSpecChange(newSpec, currentSpec))
 }
 
+func TestEvalContainerSpecChange_ContainerSysctls(t *testing.T) {
+	t.Parallel()
+
+	currentSpec := api.ServiceSpec{
+		Container: api.ContainerSpec{
+			Image: "nginx:latest",
+		},
+	}
+	newSpec := api.ServiceSpec{
+		Container: api.ContainerSpec{
+			Image: "nginx:latest",
+			Sysctls: map[string]string{
+				"net.ipv4.ip_forward": "1",
+			},
+		},
+	}
+
+	assert.Equal(t, ContainerNeedsRecreate, EvalContainerSpecChange(currentSpec, newSpec))
+	assert.Equal(t, ContainerNeedsRecreate, EvalContainerSpecChange(newSpec, currentSpec))
+}
+
 func TestEvalContainerSpecChange_PullPolicy(t *testing.T) {
 	t.Parallel()
 
@@ -1351,6 +1410,68 @@ func TestEvalContainerSpecChange_Volumes(t *testing.T) {
 	}
 }
 
+func TestEvalContainerSpecChange_Devices(t *testing.T) {
+	t.Parallel()
+
+	tests := []struct {
+		name    string
+		current api.ContainerResources
+		new     api.ContainerResources
+		want    ContainerSpecStatus
+	}{
+		{
+			name:    "empty",
+			current: api.ContainerResources{},
+			new:     api.ContainerResources{},
+			want:    ContainerUpToDate,
+		},
+		{
+			name:    "identical mapping",
+			current: api.ContainerResources{Devices: []api.DeviceMapping{{HostPath: "/dev/foo", ContainerPath: "/dev/foo", CgroupPermissions: "rwm"}}},
+			new:     api.ContainerResources{Devices: []api.DeviceMapping{{HostPath: "/dev/foo", ContainerPath: "/dev/foo", CgroupPermissions: "rwm"}}},
+			want:    ContainerUpToDate,
+		},
+		{
+			name:    "add mapping",
+			current: api.ContainerResources{},
+			new:     api.ContainerResources{Devices: []api.DeviceMapping{{HostPath: "/dev/foo", ContainerPath: "/dev/foo", CgroupPermissions: "rwm"}}},
+			want:    ContainerNeedsRecreate,
+		},
+		{
+			name:    "remove mapping",
+			current: api.ContainerResources{Devices: []api.DeviceMapping{{HostPath: "/dev/foo", ContainerPath: "/dev/foo", CgroupPermissions: "rwm"}}},
+			new:     api.ContainerResources{},
+			want:    ContainerNeedsRecreate,
+		},
+		{
+			name:    "change mapping path",
+			current: api.ContainerResources{Devices: []api.DeviceMapping{{HostPath: "/dev/foo", ContainerPath: "/dev/foo", CgroupPermissions: "rwm"}}},
+			new:     api.ContainerResources{Devices: []api.DeviceMapping{{HostPath: "/dev/foo", ContainerPath: "/dev/bar", CgroupPermissions: "rwm"}}},
+			want:    ContainerNeedsRecreate,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			currentSpec := api.ServiceSpec{
+				Container: api.ContainerSpec{
+					Image:     "nginx:latest",
+					Resources: tt.current,
+				},
+			}
+			newSpec := api.ServiceSpec{
+				Container: api.ContainerSpec{
+					Image:     "nginx:latest",
+					Resources: tt.new,
+				},
+			}
+
+			result := EvalContainerSpecChange(currentSpec, newSpec)
+			assert.Equal(t, tt.want, result)
+		})
+	}
+}
+
 func TestEvalContainerSpecChange_DeviceReservations(t *testing.T) {
 	t.Parallel()
 
@@ -1743,6 +1864,85 @@ func TestEvalContainerSpecChange_DeviceReservations(t *testing.T) {
 	}
 }
 
+func TestEvalContainerSpecChange_Ulimits(t *testing.T) {
+	t.Parallel()
+
+	tests := []struct {
+		name    string
+		current api.ContainerResources
+		new     api.ContainerResources
+		want    ContainerSpecStatus
+	}{
+		{
+			name:    "empty",
+			current: api.ContainerResources{},
+			new:     api.ContainerResources{},
+			want:    ContainerUpToDate,
+		},
+		{
+			name:    "identical single ulimit",
+			current: api.ContainerResources{Ulimits: map[string]api.Ulimit{"nofile": {Soft: 20000, Hard: 40000}}},
+			new:     api.ContainerResources{Ulimits: map[string]api.Ulimit{"nofile": {Soft: 20000, Hard: 40000}}},
+			want:    ContainerUpToDate,
+		},
+		{
+			name:    "set ulimit",
+			current: api.ContainerResources{},
+			new:     api.ContainerResources{Ulimits: map[string]api.Ulimit{"nofile": {Soft: 20000, Hard: 40000}}},
+			want:    ContainerNeedsRecreate,
+		},
+		{
+			name:    "remove ulimit",
+			current: api.ContainerResources{Ulimits: map[string]api.Ulimit{"nofile": {Soft: 20000, Hard: 40000}}},
+			new:     api.ContainerResources{},
+			want:    ContainerNeedsRecreate,
+		},
+		{
+			name:    "change ulimit soft value",
+			current: api.ContainerResources{Ulimits: map[string]api.Ulimit{"nofile": {Soft: 20000, Hard: 40000}}},
+			new:     api.ContainerResources{Ulimits: map[string]api.Ulimit{"nofile": {Soft: 30000, Hard: 40000}}},
+			want:    ContainerNeedsRecreate,
+		},
+		{
+			name:    "change ulimit hard value",
+			current: api.ContainerResources{Ulimits: map[string]api.Ulimit{"nofile": {Soft: 20000, Hard: 40000}}},
+			new:     api.ContainerResources{Ulimits: map[string]api.Ulimit{"nofile": {Soft: 20000, Hard: 80000}}},
+			want:    ContainerNeedsRecreate,
+		},
+		{
+			name: "add ulimit",
+			current: api.ContainerResources{Ulimits: map[string]api.Ulimit{
+				"nofile": {Soft: 20000, Hard: 40000},
+			}},
+			new: api.ContainerResources{Ulimits: map[string]api.Ulimit{
+				"nofile": {Soft: 20000, Hard: 40000},
+				"nproc":  {Soft: 65535, Hard: 65535},
+			}},
+			want: ContainerNeedsRecreate,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			currentSpec := api.ServiceSpec{
+				Container: api.ContainerSpec{
+					Image:     "nginx:latest",
+					Resources: tt.current,
+				},
+			}
+			newSpec := api.ServiceSpec{
+				Container: api.ContainerSpec{
+					Image:     "nginx:latest",
+					Resources: tt.new,
+				},
+			}
+
+			result := EvalContainerSpecChange(currentSpec, newSpec)
+			assert.Equal(t, tt.want, result)
+		})
+	}
+}
+
 func TestEvalContainerSpecChange_Mixed(t *testing.T) {
 	t.Parallel()
 

pkg/client/deploy/deploy.go

@@ -6,6 +6,7 @@ import (
 	"fmt"
 
 	"github.com/psviderski/uncloud/pkg/api"
+	"github.com/psviderski/uncloud/pkg/client/deploy/operation"
 	"github.com/psviderski/uncloud/pkg/client/deploy/scheduler"
 )
 
@@ -33,7 +34,7 @@ type Deployment struct {
 type Plan struct {
 	ServiceID   string
 	ServiceName string
-	SequenceOperation
+	operation.SequenceOperation
 }
 
 // NewDeployment creates a new deployment for the given service specification.

pkg/client/deploy/operation.go

@@ -1,191 +0,0 @@
-package deploy
-
-import (
-	"context"
-	"fmt"
-	"strings"
-
-	"github.com/docker/docker/api/types/container"
-	"github.com/docker/docker/api/types/volume"
-	"github.com/psviderski/uncloud/pkg/api"
-)
-
-// Operation represents a single atomic operation in a deployment process.
-// Operations can be composed to form complex deployment strategies.
-type Operation interface {
-	// Execute performs the operation using the provided client.
-	// TODO: Encapsulate the client in the operation as otherwise it gives an impression that different clients
-	//  can be provided. But in reality, the operation is tightly coupled with the client that was used to create it.
-	Execute(ctx context.Context, cli Client) error
-	// Format returns a human-readable representation of the operation.
-	// TODO: get rid of the resolver and assign the required names for formatting in the operation itself.
-	Format(resolver NameResolver) string
-	String() string
-}
-
-// NameResolver resolves machine and container IDs to their names.
-type NameResolver interface {
-	MachineName(machineID string) string
-	ContainerName(containerID string) string
-}
-
-// TODO: pass api.ServiceContainer to operations to simplify operation formatting in the plan.
-
-// RunContainerOperation creates and starts a new container on a specific machine.
-type RunContainerOperation struct {
-	ServiceID string
-	Spec      api.ServiceSpec
-	MachineID string
-}
-
-func (o *RunContainerOperation) Execute(ctx context.Context, cli Client) error {
-	resp, err := cli.CreateContainer(ctx, o.ServiceID, o.Spec, o.MachineID)
-	if err != nil {
-		return fmt.Errorf("create container: %w", err)
-	}
-	if err = cli.StartContainer(ctx, o.ServiceID, resp.ID); err != nil {
-		return fmt.Errorf("start container: %w", err)
-	}
-
-	// TODO: wait for the container to become healthy
-
-	return nil
-}
-
-func (o *RunContainerOperation) Format(resolver NameResolver) string {
-	machineName := resolver.MachineName(o.MachineID)
-	return fmt.Sprintf("%s: Run container [image=%s]", machineName, o.Spec.Container.Image)
-}
-
-func (o *RunContainerOperation) String() string {
-	return fmt.Sprintf("RunContainerOperation[machine_id=%s service_id=%s image=%s]",
-		o.MachineID, o.ServiceID, o.Spec.Container.Image)
-}
-
-// StopContainerOperation stops a container on a specific machine.
-type StopContainerOperation struct {
-	ServiceID   string
-	ContainerID string
-	MachineID   string
-}
-
-func (o *StopContainerOperation) Execute(ctx context.Context, cli Client) error {
-	if err := cli.StopContainer(ctx, o.ServiceID, o.ContainerID, container.StopOptions{}); err != nil {
-		return fmt.Errorf("stop container: %w", err)
-	}
-	return nil
-}
-
-func (o *StopContainerOperation) Format(resolver NameResolver) string {
-	machineName := resolver.MachineName(o.MachineID)
-	return fmt.Sprintf("%s: Stop container [id=%s name=%s]", machineName,
-		o.ContainerID[:12], resolver.ContainerName(o.ContainerID))
-}
-
-func (o *StopContainerOperation) String() string {
-	return fmt.Sprintf("StopContainerOperation[machine_id=%s service_id=%s container_id=%s]",
-		o.MachineID, o.ServiceID, o.ContainerID)
-}
-
-// RemoveContainerOperation stops and removes a container from a specific machine.
-type RemoveContainerOperation struct {
-	MachineID string
-	Container api.ServiceContainer
-}
-
-func (o *RemoveContainerOperation) Execute(ctx context.Context, cli Client) error {
-	if err := cli.StopContainer(ctx, o.Container.ServiceID(), o.Container.ID, container.StopOptions{}); err != nil {
-		return fmt.Errorf("stop container: %w", err)
-	}
-	if err := cli.RemoveContainer(ctx, o.Container.ServiceID(), o.Container.ID, container.RemoveOptions{
-		// Remove anonymous volumes created by the container.
-		RemoveVolumes: true,
-	}); err != nil {
-		return fmt.Errorf("remove container: %w", err)
-	}
-
-	return nil
-}
-
-func (o *RemoveContainerOperation) Format(resolver NameResolver) string {
-	machineName := resolver.MachineName(o.MachineID)
-	return fmt.Sprintf("%s: Remove container [id=%s image=%s]",
-		machineName, o.Container.ShortID(), o.Container.Config.Image)
-}
-
-func (o *RemoveContainerOperation) String() string {
-	return fmt.Sprintf("RemoveContainerOperation[machine_id=%s service_id=%s container_id=%s]",
-		o.MachineID, o.Container.ServiceID(), o.Container.ID)
-}
-
-// CreateVolumeOperation creates a volume on a specific machine.
-type CreateVolumeOperation struct {
-	VolumeSpec api.VolumeSpec
-	MachineID  string
-	// MachineName is used for formatting the operation output only.
-	MachineName string
-}
-
-func (o *CreateVolumeOperation) Execute(ctx context.Context, cli Client) error {
-	if o.VolumeSpec.Type != api.VolumeTypeVolume {
-		return fmt.Errorf("invalid volume type: '%s', expected '%s'", o.VolumeSpec.Type, api.VolumeTypeVolume)
-	}
-
-	opts := volume.CreateOptions{
-		Name: o.VolumeSpec.DockerVolumeName(),
-	}
-	if o.VolumeSpec.VolumeOptions != nil {
-		if o.VolumeSpec.VolumeOptions.Driver != nil {
-			opts.Driver = o.VolumeSpec.VolumeOptions.Driver.Name
-			opts.DriverOpts = o.VolumeSpec.VolumeOptions.Driver.Options
-		}
-		opts.Labels = o.VolumeSpec.VolumeOptions.Labels
-	}
-
-	if _, err := cli.CreateVolume(ctx, o.MachineID, opts); err != nil {
-		return fmt.Errorf("create volume: %w", err)
-	}
-
-	return nil
-}
-
-func (o *CreateVolumeOperation) Format(_ NameResolver) string {
-	return fmt.Sprintf("%s: Create volume [name=%s]", o.MachineName, o.VolumeSpec.DockerVolumeName())
-}
-
-func (o *CreateVolumeOperation) String() string {
-	return fmt.Sprintf("CreateVolumeOperation[machine_id=%s volume=%s]",
-		o.MachineID, o.VolumeSpec.DockerVolumeName())
-}
-
-// SequenceOperation is a composite operation that executes a sequence of operations in order.
-type SequenceOperation struct {
-	Operations []Operation
-}
-
-func (o *SequenceOperation) Execute(ctx context.Context, cli Client) error {
-	for _, op := range o.Operations {
-		if err := op.Execute(ctx, cli); err != nil {
-			return err
-		}
-	}
-	return nil
-}
-
-func (o *SequenceOperation) Format(resolver NameResolver) string {
-	ops := make([]string, len(o.Operations))
-	for i, op := range o.Operations {
-		ops[i] = "- " + op.Format(resolver)
-	}
-
-	return strings.Join(ops, "\n")
-}
-
-func (o *SequenceOperation) String() string {
-	ops := make([]string, len(o.Operations))
-	for i, op := range o.Operations {
-		ops[i] = op.String()
-	}
-
-	return fmt.Sprintf("SequenceOperation[%s]", strings.Join(ops, ", "))
-}

pkg/client/deploy/operation/container.go

@@ -0,0 +1,211 @@
+package operation
+
+import (
+	"context"
+	"fmt"
+
+	"github.com/docker/compose/v2/pkg/progress"
+	"github.com/docker/docker/api/types/container"
+	"github.com/docker/docker/pkg/stringid"
+	"github.com/psviderski/uncloud/pkg/api"
+)
+
+// RunContainerOperation creates and starts a new container on a specific machine.
+type RunContainerOperation struct {
+	ServiceID string
+	Spec      api.ServiceSpec
+	MachineID string
+	// SkipHealthMonitor skips the monitoring period and health checks after starting a container.
+	SkipHealthMonitor bool
+}
+
+func (o *RunContainerOperation) Execute(ctx context.Context, cli Client) error {
+	resp, err := cli.CreateContainer(ctx, o.ServiceID, o.Spec, o.MachineID)
+	if err != nil {
+		return fmt.Errorf("create container: %w", err)
+	}
+	if err = cli.StartContainer(ctx, o.ServiceID, resp.ID); err != nil {
+		return fmt.Errorf("start container: %w", err)
+	}
+
+	if o.SkipHealthMonitor {
+		return nil
+	}
+
+	opts := api.WaitContainerHealthyOptions{MonitorPeriod: o.Spec.UpdateConfig.MonitorPeriod}
+	if err = cli.WaitContainerHealthy(ctx, o.ServiceID, resp.ID, opts); err != nil {
+		return fmt.Errorf("container '%s/%s' failed to become healthy: %w",
+			o.Spec.Name, stringid.TruncateID(resp.ID), err)
+	}
+
+	return nil
+}
+
+func (o *RunContainerOperation) Format(resolver NameResolver) string {
+	machineName := resolver.MachineName(o.MachineID)
+	return fmt.Sprintf("%s: Run container [image=%s]", machineName, o.Spec.Container.Image)
+}
+
+func (o *RunContainerOperation) String() string {
+	return fmt.Sprintf("RunContainerOperation[machine_id=%s service_id=%s image=%s]",
+		o.MachineID, o.ServiceID, o.Spec.Container.Image)
+}
+
+// StopContainerOperation stops a container on a specific machine.
+type StopContainerOperation struct {
+	ServiceID   string
+	ContainerID string
+	MachineID   string
+}
+
+func (o *StopContainerOperation) Execute(ctx context.Context, cli Client) error {
+	if err := cli.StopContainer(ctx, o.ServiceID, o.ContainerID, container.StopOptions{}); err != nil {
+		return fmt.Errorf("stop container: %w", err)
+	}
+	return nil
+}
+
+func (o *StopContainerOperation) Format(resolver NameResolver) string {
+	machineName := resolver.MachineName(o.MachineID)
+	return fmt.Sprintf("%s: Stop container [id=%s name=%s]", machineName,
+		o.ContainerID[:12], resolver.ContainerName(o.ContainerID))
+}
+
+func (o *StopContainerOperation) String() string {
+	return fmt.Sprintf("StopContainerOperation[machine_id=%s service_id=%s container_id=%s]",
+		o.MachineID, o.ServiceID, o.ContainerID)
+}
+
+// RemoveContainerOperation stops and removes a container from a specific machine.
+type RemoveContainerOperation struct {
+	MachineID string
+	Container api.ServiceContainer
+}
+
+func (o *RemoveContainerOperation) Execute(ctx context.Context, cli Client) error {
+	if err := cli.StopContainer(ctx, o.Container.ServiceID(), o.Container.ID, container.StopOptions{}); err != nil {
+		return fmt.Errorf("stop container: %w", err)
+	}
+	if err := cli.RemoveContainer(ctx, o.Container.ServiceID(), o.Container.ID, container.RemoveOptions{
+		// Remove anonymous volumes created by the container.
+		RemoveVolumes: true,
+	}); err != nil {
+		return fmt.Errorf("remove container: %w", err)
+	}
+
+	return nil
+}
+
+func (o *RemoveContainerOperation) Format(resolver NameResolver) string {
+	machineName := resolver.MachineName(o.MachineID)
+	return fmt.Sprintf("%s: Remove container [id=%s image=%s]",
+		machineName, o.Container.ShortID(), o.Container.Config.Image)
+}
+
+func (o *RemoveContainerOperation) String() string {
+	return fmt.Sprintf("RemoveContainerOperation[machine_id=%s service_id=%s container_id=%s]",
+		o.MachineID, o.Container.ServiceID(), o.Container.ID)
+}
+
+// ReplaceContainerOperation replaces an old container with a new one based on the specified update order.
+// For start-first: starts new container, then removes old container.
+// For stop-first: stops old container, starts new container, then removes old container.
+type ReplaceContainerOperation struct {
+	ServiceID    string
+	Spec         api.ServiceSpec
+	MachineID    string
+	OldContainer api.ServiceContainer
+	// Order specifies the update order: "start-first" or "stop-first".
+	Order string
+	// SkipHealthMonitor skips the monitoring period and health checks after starting a new container.
+	SkipHealthMonitor bool
+}
+
+func (o *ReplaceContainerOperation) Execute(ctx context.Context, cli Client) error {
+	stopFirst := o.Order == api.UpdateOrderStopFirst
+
+	wasRunning := false
+	if stopFirst {
+		// Inspect the old container to remember its running state before stopping.
+		ctr, err := cli.InspectContainer(ctx, o.ServiceID, o.OldContainer.ID)
+		if err != nil {
+			return fmt.Errorf("inspect old container: %w", err)
+		}
+		wasRunning = ctr.Container.State.Running
+		if wasRunning {
+			if err = cli.StopContainer(ctx, o.ServiceID, o.OldContainer.ID, container.StopOptions{}); err != nil {
+				return fmt.Errorf("stop old container: %w", err)
+			}
+		}
+	}
+
+	resp, err := cli.CreateContainer(ctx, o.ServiceID, o.Spec, o.MachineID)
+	if err != nil {
+		return fmt.Errorf("create new container: %w", err)
+	}
+	if err = cli.StartContainer(ctx, o.ServiceID, resp.ID); err != nil {
+		return fmt.Errorf("start new container: %w", err)
+	}
+
+	if !o.SkipHealthMonitor {
+		opts := api.WaitContainerHealthyOptions{MonitorPeriod: o.Spec.UpdateConfig.MonitorPeriod}
+		if err = cli.WaitContainerHealthy(ctx, o.ServiceID, resp.ID, opts); err != nil {
+			// New container failed to become healthy. Stop it and roll back to the previous container.
+			// Don't remove the new stopped container to allow users to inspect logs and state.
+			// TODO: collect logs from the new container and include in the error message to speed up debugging.
+
+			// Use context without progress to not overwrite the container Unhealthy status with Stopped.
+			ctxWithoutProgress := progress.WithContextWriter(ctx, nil)
+			_ = cli.StopContainer(ctxWithoutProgress, o.ServiceID, resp.ID, container.StopOptions{})
+
+			newCtr := fmt.Sprintf("%s/%s", o.Spec.Name, stringid.TruncateID(resp.ID))
+			healthErr := fmt.Errorf(
+				"new container '%s' failed to become healthy: %w. "+
+					"It's stopped and available for inspection. Fetch logs with 'uc logs %s'",
+				newCtr, err, o.Spec.Name,
+			)
+
+			if stopFirst && wasRunning {
+				// Restart the old container only if it was running before we stopped it.
+				oldCtr := fmt.Sprintf("%s/%s", o.OldContainer.ServiceSpec.Name, o.OldContainer.ShortID())
+				if rollbackErr := cli.StartContainer(ctx, o.ServiceID, o.OldContainer.ID); rollbackErr != nil {
+					return fmt.Errorf("%w. Rolled back to old container '%s' but failed to restart it: %w",
+						healthErr, oldCtr, rollbackErr)
+				}
+				return fmt.Errorf("%w. Rolled back to old container '%s'", healthErr, oldCtr)
+			}
+
+			return healthErr
+		}
+	}
+
+	// For start-first, we need to stop before removing.
+	// For stop-first, the container is already stopped.
+	if !stopFirst {
+		// TODO: the new container is propagated to Caddy upstreams through the cluster store asynchronously.
+		//  There still might be a brief downtime (for a 1 replica service) when Caddy doesn't know about
+		//  the new container but we're stopping the old container. We should somehow ensure Caddy is updated
+		//  with the new container before we stop the old one to avoid this downtime.
+		if err := cli.StopContainer(ctx, o.ServiceID, o.OldContainer.ID, container.StopOptions{}); err != nil {
+			return fmt.Errorf("stop old container: %w", err)
+		}
+	}
+
+	if err := cli.RemoveContainer(ctx, o.ServiceID, o.OldContainer.ID, container.RemoveOptions{
+		RemoveVolumes: true,
+	}); err != nil {
+		return fmt.Errorf("remove old container: %w", err)
+	}
+
+	return nil
+}
+
+func (o *ReplaceContainerOperation) Format(resolver NameResolver) string {
+	return fmt.Sprintf("%s: Replace container [id=%s image=%s order=%s]",
+		resolver.MachineName(o.MachineID), o.OldContainer.ShortID(), o.Spec.Container.Image, o.Order)
+}
+
+func (o *ReplaceContainerOperation) String() string {
+	return fmt.Sprintf("ReplaceContainerOperation[machine_id=%s service_id=%s old_container_id=%s order=%s]",
+		o.MachineID, o.ServiceID, o.OldContainer.ID, o.Order)
+}

pkg/client/deploy/operation/operation.go

@@ -0,0 +1,30 @@
+package operation
+
+import (
+	"context"
+
+	"github.com/psviderski/uncloud/pkg/api"
+)
+
+// Operation represents a single atomic operation in a deployment process.
+// Operations can be composed to form complex deployment strategies.
+type Operation interface {
+	// Execute performs the operation using the provided client.
+	Execute(ctx context.Context, cli Client) error
+	// Format returns a human-readable representation of the operation.
+	// TODO: get rid of the resolver and assign the required names for formatting in the operation itself.
+	Format(resolver NameResolver) string
+	String() string
+}
+
+// Client defines the interface required to execute deployment operations.
+type Client interface {
+	api.ContainerClient
+	api.VolumeClient
+}
+
+// NameResolver resolves machine and container IDs to their names.
+type NameResolver interface {
+	MachineName(machineID string) string
+	ContainerName(containerID string) string
+}

pkg/client/deploy/operation/sequence.go

@@ -0,0 +1,39 @@
+package operation
+
+import (
+	"context"
+	"fmt"
+	"strings"
+)
+
+// SequenceOperation is a composite operation that executes a sequence of operations in order.
+type SequenceOperation struct {
+	Operations []Operation
+}
+
+func (o *SequenceOperation) Execute(ctx context.Context, cli Client) error {
+	for _, op := range o.Operations {
+		if err := op.Execute(ctx, cli); err != nil {
+			return err
+		}
+	}
+	return nil
+}
+
+func (o *SequenceOperation) Format(resolver NameResolver) string {
+	ops := make([]string, len(o.Operations))
+	for i, op := range o.Operations {
+		ops[i] = "- " + op.Format(resolver)
+	}
+
+	return strings.Join(ops, "\n")
+}
+
+func (o *SequenceOperation) String() string {
+	ops := make([]string, len(o.Operations))
+	for i, op := range o.Operations {
+		ops[i] = op.String()
+	}
+
+	return fmt.Sprintf("SequenceOperation[%s]", strings.Join(ops, ", "))
+}

pkg/client/deploy/operation/volume.go

@@ -0,0 +1,49 @@
+package operation
+
+import (
+	"context"
+	"fmt"
+
+	"github.com/docker/docker/api/types/volume"
+	"github.com/psviderski/uncloud/pkg/api"
+)
+
+// CreateVolumeOperation creates a volume on a specific machine.
+type CreateVolumeOperation struct {
+	VolumeSpec api.VolumeSpec
+	MachineID  string
+	// MachineName is used for formatting the operation output only.
+	MachineName string
+}
+
+func (o *CreateVolumeOperation) Execute(ctx context.Context, cli Client) error {
+	if o.VolumeSpec.Type != api.VolumeTypeVolume {
+		return fmt.Errorf("invalid volume type: '%s', expected '%s'", o.VolumeSpec.Type, api.VolumeTypeVolume)
+	}
+
+	opts := volume.CreateOptions{
+		Name: o.VolumeSpec.DockerVolumeName(),
+	}
+	if o.VolumeSpec.VolumeOptions != nil {
+		if o.VolumeSpec.VolumeOptions.Driver != nil {
+			opts.Driver = o.VolumeSpec.VolumeOptions.Driver.Name
+			opts.DriverOpts = o.VolumeSpec.VolumeOptions.Driver.Options
+		}
+		opts.Labels = o.VolumeSpec.VolumeOptions.Labels
+	}
+
+	if _, err := cli.CreateVolume(ctx, o.MachineID, opts); err != nil {
+		return fmt.Errorf("create volume: %w", err)
+	}
+
+	return nil
+}
+
+func (o *CreateVolumeOperation) Format(_ NameResolver) string {
+	return fmt.Sprintf("%s: Create volume [name=%s]", o.MachineName, o.VolumeSpec.DockerVolumeName())
+}
+
+func (o *CreateVolumeOperation) String() string {
+	return fmt.Sprintf("CreateVolumeOperation[machine_id=%s volume=%s]",
+		o.MachineID, o.VolumeSpec.DockerVolumeName())
+}

pkg/client/deploy/scheduler/volume.go

@@ -11,6 +11,7 @@ import (
 
 // VolumeScheduler determines what missing volumes should be created and where for a multi-service deployment.
 // It satisfies the following constraints:
+//   - Volumes used by global services will be created on all eligible machines.
 //   - Services that share a volume must be placed on the same machine where the volume is located.
 //     If the volume is located on multiple machines, services can be placed on any of them.
 //   - Services must respect their individual placement constraints.
@@ -128,12 +129,20 @@ func (s *VolumeScheduler) Schedule() (map[string][]api.VolumeSpec, error) {
 		serviceEligibleMachines[spec.Name] = machineIDs
 	}
 
-	// For each volume that exists on any machine(s) (which shouldn't be created), intersect each service's
+	// For each volume that exists on any machine(s), intersect each non-global service's
 	// eligible machines that use the volume with the machines the volume is located on.
+	// Global services skip this constraint as they need the volume on ALL eligible machines,
+	// and the volume will be created on machines that don't have it.
 	//
 	// Service name -> list of processed volume names (quoted) to format the error message.
 	quotedServiceVolumes := make(map[string][]string)
 	for volumeName, volumeMachines := range s.existingVolumeMachines {
+		// Skip constraint narrowing for global services - they don't need to be constrained
+		// to machines that already have the volume.
+		if s.isVolumeForGlobalService(volumeName) {
+			continue
+		}
+
 		for _, serviceName := range s.volumeServices[volumeName] {
 			quotedServiceVolumes[serviceName] = append(quotedServiceVolumes[serviceName],
 				fmt.Sprintf("'%s'", volumeName))
@@ -147,52 +156,97 @@ func (s *VolumeScheduler) Schedule() (map[string][]api.VolumeSpec, error) {
 		}
 	}
 
-	// Skip constraints propagation for volumes that already exist on machines as the propagation only works
-	// for missing volumes.
+	// Skip constraints propagation for:
+	// 1. Volumes that already exist on machines (for replicated services) as the propagation only works
+	//    for missing volumes. Global service volumes are NOT marked as placed here since they still need
+	//    to be scheduled on machines that don't have them.
+	// 2. Volumes only used by global services - these need UNION of eligible machines, not intersection.
 	placedVolumes := make(map[string]struct{})
 	for volumeName := range s.existingVolumeMachines {
-		placedVolumes[volumeName] = struct{}{}
+		if !s.isVolumeForGlobalService(volumeName) {
+			placedVolumes[volumeName] = struct{}{}
+		}
+	}
+	// Skip constraint propagation for volumes used by global services.
+	// Also check for invalid configuration: volume shared between global and replicated services.
+	for volumeName := range s.volumeSpecs {
+		if s.isVolumeSharedBetweenGlobalAndReplicated(volumeName) {
+			return nil, fmt.Errorf("volume '%s' cannot be shared between global and replicated services: "+
+				"global services require the volume on all machines while replicated services require "+
+				"co-location with the volume", volumeName)
+		}
+		if s.isVolumeForGlobalService(volumeName) {
+			placedVolumes[volumeName] = struct{}{}
+		}
 	}
 
 	if err := s.propagateConstraintsUntilConvergence(serviceEligibleMachines, placedVolumes); err != nil {
 		return nil, err
 	}
 
-	// Schedule each missing volume on one of its eligible machines.
+	// Schedule each missing volume on eligible machines.
+	// For global services: schedule on ALL eligible machines that don't already have the volume.
+	// For replicated services: schedule on ONE eligible machine (skip if volume exists anywhere).
 	scheduledVolumes := make(map[string][]api.VolumeSpec)
-	for missingVolumeName, missingVolumeSpec := range s.volumeSpecs {
-		// Skip volumes that already exist on machines.
-		if _, ok := s.existingVolumeMachines[missingVolumeName]; ok {
-			continue
-		}
-
-		serviceNames := s.volumeServices[missingVolumeName]
+	for volumeName, volumeSpec := range s.volumeSpecs {
+		existingMachines := s.existingVolumeMachines[volumeName]
+		serviceNames := s.volumeServices[volumeName]
 		if len(serviceNames) == 0 {
-			return nil, fmt.Errorf("bug detected: no services using volume '%s'", missingVolumeName)
+			return nil, fmt.Errorf("bug detected: no services using volume '%s'", volumeName)
 		}
 
-		// Get the current eligible machines (any service using the volume will have the same set after convergence).
-		eligibleMachines := serviceEligibleMachines[serviceNames[0]]
+		// Get the eligible machines for this volume.
+		// For volumes used by global services: compute UNION of all services' eligible machines.
+		// For other volumes: any service will have the same set after constraint convergence.
+		var eligibleMachines mapset.Set[string]
+		if s.isVolumeForGlobalService(volumeName) {
+			// Compute union of eligible machines for all global services using this volume.
+			eligibleMachines = mapset.NewSet[string]()
+			for _, serviceName := range serviceNames {
+				eligibleMachines = eligibleMachines.Union(serviceEligibleMachines[serviceName])
+			}
+		} else {
+			eligibleMachines = serviceEligibleMachines[serviceNames[0]]
+		}
 		if eligibleMachines.Cardinality() == 0 {
-			return nil, fmt.Errorf("bug detected: no eligible machines for volume '%s'", missingVolumeName)
+			return nil, fmt.Errorf("bug detected: no eligible machines for volume '%s'", volumeName)
 		}
 
-		// Choose the first machine in the sorted eligible machines to schedule the volume on.
 		// Sort the eligible machines to ensure deterministic behavior.
 		sortedEligibleMachines := eligibleMachines.ToSlice()
 		slices.Sort(sortedEligibleMachines)
-		machineID := sortedEligibleMachines[0]
-		// Update constraints for all services that use this volume to be placed on the selected machine.
-		for _, serviceName := range serviceNames {
-			serviceEligibleMachines[serviceName] = mapset.NewSet(machineID)
-		}
-		placedVolumes[missingVolumeName] = struct{}{}
-		scheduledVolumes[machineID] = append(scheduledVolumes[machineID], missingVolumeSpec)
 
-		// Propagate the updated constraints.
-		if err := s.propagateConstraintsUntilConvergence(serviceEligibleMachines, placedVolumes); err != nil {
-			return nil, fmt.Errorf("unexpected error while propagating constraints after "+
-				"scheduling volume '%s' on machine '%s': %w", missingVolumeName, machineID, err)
+		if s.isVolumeForGlobalService(volumeName) {
+			// Global service: schedule volume on eligible machines that don't already have it.
+			for _, machineID := range sortedEligibleMachines {
+				if existingMachines != nil && existingMachines.Contains(machineID) {
+					// Volume already exists on this machine, skip it.
+					continue
+				}
+				scheduledVolumes[machineID] = append(scheduledVolumes[machineID], volumeSpec)
+			}
+			// Mark volume as placed - no constraint propagation needed since volume will be on all machines.
+			placedVolumes[volumeName] = struct{}{}
+		} else {
+			// Replicated service: skip if volume already exists on any machine (services will use that location).
+			if existingMachines != nil && existingMachines.Cardinality() > 0 {
+				continue
+			}
+
+			// Schedule volume on ONE machine (first in sorted order).
+			machineID := sortedEligibleMachines[0]
+			// Update constraints for all services that use this volume to be placed on the selected machine.
+			for _, serviceName := range serviceNames {
+				serviceEligibleMachines[serviceName] = mapset.NewSet(machineID)
+			}
+			placedVolumes[volumeName] = struct{}{}
+			scheduledVolumes[machineID] = append(scheduledVolumes[machineID], volumeSpec)
+
+			// Propagate the updated constraints.
+			if err := s.propagateConstraintsUntilConvergence(serviceEligibleMachines, placedVolumes); err != nil {
+				return nil, fmt.Errorf("unexpected error while propagating constraints after "+
+					"scheduling volume '%s' on machine '%s': %w", volumeName, machineID, err)
+			}
 		}
 	}
 
@@ -298,3 +352,42 @@ func (s *VolumeScheduler) propagateConstraintsUntilConvergence(
 
 	return nil
 }
+
+// isVolumeForGlobalService returns true if any service using this volume is a global service.
+func (s *VolumeScheduler) isVolumeForGlobalService(volumeName string) bool {
+	serviceNames := s.volumeServices[volumeName]
+	for _, serviceName := range serviceNames {
+		for _, spec := range s.serviceSpecs {
+			if spec.Name == serviceName && spec.Mode == api.ServiceModeGlobal {
+				return true
+			}
+		}
+	}
+	return false
+}
+
+// isVolumeSharedBetweenGlobalAndReplicated returns true if a volume is used by both
+// global and replicated services, which is an invalid configuration.
+func (s *VolumeScheduler) isVolumeSharedBetweenGlobalAndReplicated(volumeName string) bool {
+	serviceNames := s.volumeServices[volumeName]
+	hasGlobal := false
+	hasReplicated := false
+
+	for _, serviceName := range serviceNames {
+		for _, spec := range s.serviceSpecs {
+			if spec.Name == serviceName {
+				mode := spec.Mode
+				if mode == "" {
+					mode = api.ServiceModeReplicated
+				}
+				if mode == api.ServiceModeGlobal {
+					hasGlobal = true
+				} else {
+					hasReplicated = true
+				}
+			}
+		}
+	}
+
+	return hasGlobal && hasReplicated
+}

pkg/client/deploy/scheduler/volume_test.go

@@ -802,6 +802,396 @@ func TestVolumeScheduler_Schedule(t *testing.T) {
 				},
 			},
 		},
+		{
+			name: "global service with missing volume schedules on all machines",
+			machines: []*Machine{
+				{
+					Info: &pb.MachineInfo{
+						Id: "machine1",
+					},
+				},
+				{
+					Info: &pb.MachineInfo{
+						Id: "machine2",
+					},
+				},
+				{
+					Info: &pb.MachineInfo{
+						Id: "machine3",
+					},
+				},
+			},
+			serviceSpecs: []api.ServiceSpec{
+				{
+					Name: "global-service",
+					Mode: api.ServiceModeGlobal,
+					Container: api.ContainerSpec{
+						Image: "portainer/pause:latest",
+						VolumeMounts: []api.VolumeMount{
+							{
+								VolumeName:    "vol1",
+								ContainerPath: "/data",
+							},
+						},
+					},
+					Volumes: []api.VolumeSpec{
+						{
+							Name: "vol1",
+							Type: api.VolumeTypeVolume,
+						},
+					},
+				},
+			},
+			want: map[string][]api.VolumeSpec{
+				"machine1": {
+					{
+						Name: "vol1",
+						Type: api.VolumeTypeVolume,
+					},
+				},
+				"machine2": {
+					{
+						Name: "vol1",
+						Type: api.VolumeTypeVolume,
+					},
+				},
+				"machine3": {
+					{
+						Name: "vol1",
+						Type: api.VolumeTypeVolume,
+					},
+				},
+			},
+		},
+		{
+			name: "global service with volume on some machines schedules remaining",
+			machines: []*Machine{
+				{
+					Info: &pb.MachineInfo{
+						Id: "machine1",
+					},
+					Volumes: []volume.Volume{
+						{
+							Name: "vol1",
+						},
+					},
+				},
+				{
+					Info: &pb.MachineInfo{
+						Id: "machine2",
+					},
+				},
+				{
+					Info: &pb.MachineInfo{
+						Id: "machine3",
+					},
+				},
+			},
+			serviceSpecs: []api.ServiceSpec{
+				{
+					Name: "global-service",
+					Mode: api.ServiceModeGlobal,
+					Container: api.ContainerSpec{
+						Image: "portainer/pause:latest",
+						VolumeMounts: []api.VolumeMount{
+							{
+								VolumeName:    "vol1",
+								ContainerPath: "/data",
+							},
+						},
+					},
+					Volumes: []api.VolumeSpec{
+						{
+							Name: "vol1",
+							Type: api.VolumeTypeVolume,
+						},
+					},
+				},
+			},
+			want: map[string][]api.VolumeSpec{
+				"machine2": {
+					{
+						Name: "vol1",
+						Type: api.VolumeTypeVolume,
+					},
+				},
+				"machine3": {
+					{
+						Name: "vol1",
+						Type: api.VolumeTypeVolume,
+					},
+				},
+			},
+		},
+		{
+			name: "global service with placement constraint",
+			machines: []*Machine{
+				{
+					Info: &pb.MachineInfo{
+						Id: "machine1",
+					},
+				},
+				{
+					Info: &pb.MachineInfo{
+						Id: "machine2",
+					},
+				},
+				{
+					Info: &pb.MachineInfo{
+						Id: "machine3",
+					},
+				},
+			},
+			serviceSpecs: []api.ServiceSpec{
+				{
+					Name: "global-service",
+					Mode: api.ServiceModeGlobal,
+					Placement: api.Placement{
+						Machines: []string{"machine1", "machine3"},
+					},
+					Container: api.ContainerSpec{
+						Image: "portainer/pause:latest",
+						VolumeMounts: []api.VolumeMount{
+							{
+								VolumeName:    "vol1",
+								ContainerPath: "/data",
+							},
+						},
+					},
+					Volumes: []api.VolumeSpec{
+						{
+							Name: "vol1",
+							Type: api.VolumeTypeVolume,
+						},
+					},
+				},
+			},
+			want: map[string][]api.VolumeSpec{
+				"machine1": {
+					{
+						Name: "vol1",
+						Type: api.VolumeTypeVolume,
+					},
+				},
+				"machine3": {
+					{
+						Name: "vol1",
+						Type: api.VolumeTypeVolume,
+					},
+				},
+			},
+		},
+		{
+			name: "volume shared between global and replicated fails",
+			machines: []*Machine{
+				{
+					Info: &pb.MachineInfo{
+						Id: "machine1",
+					},
+				},
+				{
+					Info: &pb.MachineInfo{
+						Id: "machine2",
+					},
+				},
+			},
+			serviceSpecs: []api.ServiceSpec{
+				{
+					Name: "global-service",
+					Mode: api.ServiceModeGlobal,
+					Container: api.ContainerSpec{
+						Image: "portainer/pause:latest",
+						VolumeMounts: []api.VolumeMount{
+							{
+								VolumeName:    "shared-vol",
+								ContainerPath: "/data",
+							},
+						},
+					},
+					Volumes: []api.VolumeSpec{
+						{
+							Name: "shared-vol",
+							Type: api.VolumeTypeVolume,
+						},
+					},
+				},
+				{
+					Name: "replicated-service",
+					Mode: api.ServiceModeReplicated,
+					Container: api.ContainerSpec{
+						Image: "portainer/pause:latest",
+						VolumeMounts: []api.VolumeMount{
+							{
+								VolumeName:    "shared-vol",
+								ContainerPath: "/data",
+							},
+						},
+					},
+					Volumes: []api.VolumeSpec{
+						{
+							Name: "shared-vol",
+							Type: api.VolumeTypeVolume,
+						},
+					},
+				},
+			},
+			wantErr: "volume 'shared-vol' cannot be shared between global and replicated services",
+		},
+		{
+			name: "multiple global services sharing same volume",
+			machines: []*Machine{
+				{
+					Info: &pb.MachineInfo{
+						Id: "machine1",
+					},
+				},
+				{
+					Info: &pb.MachineInfo{
+						Id: "machine2",
+					},
+				},
+			},
+			serviceSpecs: []api.ServiceSpec{
+				{
+					Name: "global-service-1",
+					Mode: api.ServiceModeGlobal,
+					Container: api.ContainerSpec{
+						Image: "portainer/pause:latest",
+						VolumeMounts: []api.VolumeMount{
+							{
+								VolumeName:    "shared-vol",
+								ContainerPath: "/data1",
+							},
+						},
+					},
+					Volumes: []api.VolumeSpec{
+						{
+							Name: "shared-vol",
+							Type: api.VolumeTypeVolume,
+						},
+					},
+				},
+				{
+					Name: "global-service-2",
+					Mode: api.ServiceModeGlobal,
+					Container: api.ContainerSpec{
+						Image: "portainer/pause:latest",
+						VolumeMounts: []api.VolumeMount{
+							{
+								VolumeName:    "shared-vol",
+								ContainerPath: "/data2",
+							},
+						},
+					},
+					Volumes: []api.VolumeSpec{
+						{
+							Name: "shared-vol",
+							Type: api.VolumeTypeVolume,
+						},
+					},
+				},
+			},
+			want: map[string][]api.VolumeSpec{
+				"machine1": {
+					{
+						Name: "shared-vol",
+						Type: api.VolumeTypeVolume,
+					},
+				},
+				"machine2": {
+					{
+						Name: "shared-vol",
+						Type: api.VolumeTypeVolume,
+					},
+				},
+			},
+		},
+		{
+			name: "multiple global services sharing same volume with different placement constraints",
+			machines: []*Machine{
+				{
+					Info: &pb.MachineInfo{
+						Id: "machine1",
+					},
+				},
+				{
+					Info: &pb.MachineInfo{
+						Id: "machine2",
+					},
+				},
+				{
+					Info: &pb.MachineInfo{
+						Id: "machine3",
+					},
+				},
+			},
+			serviceSpecs: []api.ServiceSpec{
+				{
+					Name: "global-service-1",
+					Mode: api.ServiceModeGlobal,
+					Placement: api.Placement{
+						Machines: []string{"machine1", "machine2"},
+					},
+					Container: api.ContainerSpec{
+						Image: "portainer/pause:latest",
+						VolumeMounts: []api.VolumeMount{
+							{
+								VolumeName:    "shared-vol",
+								ContainerPath: "/data1",
+							},
+						},
+					},
+					Volumes: []api.VolumeSpec{
+						{
+							Name: "shared-vol",
+							Type: api.VolumeTypeVolume,
+						},
+					},
+				},
+				{
+					Name: "global-service-2",
+					Mode: api.ServiceModeGlobal,
+					Placement: api.Placement{
+						Machines: []string{"machine2", "machine3"},
+					},
+					Container: api.ContainerSpec{
+						Image: "portainer/pause:latest",
+						VolumeMounts: []api.VolumeMount{
+							{
+								VolumeName:    "shared-vol",
+								ContainerPath: "/data2",
+							},
+						},
+					},
+					Volumes: []api.VolumeSpec{
+						{
+							Name: "shared-vol",
+							Type: api.VolumeTypeVolume,
+						},
+					},
+				},
+			},
+			want: map[string][]api.VolumeSpec{
+				"machine1": {
+					{
+						Name: "shared-vol",
+						Type: api.VolumeTypeVolume,
+					},
+				},
+				"machine2": {
+					{
+						Name: "shared-vol",
+						Type: api.VolumeTypeVolume,
+					},
+				},
+				"machine3": {
+					{
+						Name: "shared-vol",
+						Type: api.VolumeTypeVolume,
+					},
+				},
+			},
+		},
 	}
 
 	for _, tt := range tests {

pkg/client/deploy/strategy.go

@@ -8,6 +8,7 @@ import (
 	"github.com/psviderski/uncloud/internal/machine/api/pb"
 	"github.com/psviderski/uncloud/internal/secret"
 	"github.com/psviderski/uncloud/pkg/api"
+	"github.com/psviderski/uncloud/pkg/client/deploy/operation"
 	"github.com/psviderski/uncloud/pkg/client/deploy/scheduler"
 )
 
@@ -28,6 +29,8 @@ type RollingStrategy struct {
 	// ForceRecreate indicates whether all containers should be recreated during the deployment,
 	// regardless of whether their specifications have changed.
 	ForceRecreate bool
+	// SkipHealthMonitor skips the monitoring period and health checks for faster emergency deployments.
+	SkipHealthMonitor bool
 
 	// state is the current and planned state of the cluster used for scheduling decisions.
 	state *scheduler.ClusterState
@@ -144,10 +147,11 @@ func (s *RollingStrategy) planReplicated(svc *api.Service, spec api.ServiceSpec)
 
 		if len(containers) == 0 {
 			// No more existing containers on this machine, create a new one.
-			plan.Operations = append(plan.Operations, &RunContainerOperation{
-				ServiceID: plan.ServiceID,
-				Spec:      spec,
-				MachineID: m.Id,
+			plan.Operations = append(plan.Operations, &operation.RunContainerOperation{
+				ServiceID:         plan.ServiceID,
+				Spec:              spec,
+				MachineID:         m.Id,
+				SkipHealthMonitor: s.SkipHealthMonitor,
 			})
 			continue
 		}
@@ -160,36 +164,24 @@ func (s *RollingStrategy) planReplicated(svc *api.Service, spec api.ServiceSpec)
 				continue
 			}
 			// TODO: handle ContainerNeedsUpdate when update of mutable fields on a container is supported.
-
-			conflictingPorts, portsErr := ctr.ConflictingServicePorts(spec.Ports)
-			if portsErr != nil || len(conflictingPorts) > 0 {
-				// Stop the malformed container or the container with conflicting ports.
-				plan.Operations = append(plan.Operations, &StopContainerOperation{
-					ServiceID:   plan.ServiceID,
-					ContainerID: ctr.ID,
-					MachineID:   m.Id,
-				})
-			}
 		}
 
-		// Run a new container.
-		plan.Operations = append(plan.Operations, &RunContainerOperation{
-			ServiceID: plan.ServiceID,
-			Spec:      spec,
-			MachineID: m.Id,
-		})
-
-		// Remove the old container.
-		plan.Operations = append(plan.Operations, &RemoveContainerOperation{
-			MachineID: m.Id,
-			Container: ctr,
+		// Replace the old container with a new one.
+		order := determineUpdateOrder(ctr, spec)
+		plan.Operations = append(plan.Operations, &operation.ReplaceContainerOperation{
+			ServiceID:         plan.ServiceID,
+			Spec:              spec,
+			MachineID:         m.Id,
+			OldContainer:      ctr,
+			Order:             order,
+			SkipHealthMonitor: s.SkipHealthMonitor,
 		})
 	}
 
 	// Remove any remaining containers that are not needed.
 	for mid, containers := range containersOnMachine {
 		for _, c := range containers {
-			plan.Operations = append(plan.Operations, &RemoveContainerOperation{
+			plan.Operations = append(plan.Operations, &operation.RemoveContainerOperation{
 				MachineID: mid,
 				Container: c,
 			})
@@ -228,7 +220,8 @@ func (s *RollingStrategy) planGlobal(svc *api.Service, spec api.ServiceSpec) (Pl
 
 	for _, m := range availableMachines {
 		containers := containersOnMachine[m.Info.Id]
-		ops, err := reconcileGlobalContainer(containers, spec, plan.ServiceID, m.Info.Id, s.ForceRecreate)
+		ops, err := reconcileGlobalContainer(
+			containers, spec, plan.ServiceID, m.Info.Id, s.ForceRecreate, s.SkipHealthMonitor)
 		if err != nil {
 			return plan, err
 		}
@@ -240,7 +233,7 @@ func (s *RollingStrategy) planGlobal(svc *api.Service, spec api.ServiceSpec) (Pl
 	// Remove any remaining containers on machines that don't match the new placement constraints.
 	for _, containers := range containersOnMachine {
 		for _, c := range containers {
-			plan.Operations = append(plan.Operations, &RemoveContainerOperation{
+			plan.Operations = append(plan.Operations, &operation.RemoveContainerOperation{
 				MachineID: c.MachineID,
 				Container: c.Container,
 			})
@@ -254,16 +247,18 @@ func (s *RollingStrategy) planGlobal(svc *api.Service, spec api.ServiceSpec) (Pl
 // It ensures exactly one container with the desired spec is running on the machine by creating a new container and
 // removing old ones. If there is a host port conflict, it stops the old container before starting a new one.
 func reconcileGlobalContainer(
-	containers []api.MachineServiceContainer, spec api.ServiceSpec, serviceID, machineID string, forceRecreate bool,
-) ([]Operation, error) {
-	var ops []Operation
+	containers []api.MachineServiceContainer, spec api.ServiceSpec, serviceID, machineID string,
+	forceRecreate, skipHealthCheck bool,
+) ([]operation.Operation, error) {
+	var ops []operation.Operation
 
 	if len(containers) == 0 {
 		// No containers on this machine, create a new one.
-		ops = append(ops, &RunContainerOperation{
-			ServiceID: serviceID,
-			Spec:      spec,
-			MachineID: machineID,
+		ops = append(ops, &operation.RunContainerOperation{
+			ServiceID:         serviceID,
+			Spec:              spec,
+			MachineID:         machineID,
+			SkipHealthMonitor: skipHealthCheck,
 		})
 		return ops, nil
 	}
@@ -290,7 +285,7 @@ func reconcileGlobalContainer(
 				if i == j {
 					continue
 				}
-				ops = append(ops, &RemoveContainerOperation{
+				ops = append(ops, &operation.RemoveContainerOperation{
 					MachineID: old.MachineID,
 					Container: old.Container,
 				})
@@ -304,43 +299,102 @@ func reconcileGlobalContainer(
 	}
 
 	// The machine has containers but none of them match the new spec.
-	// Stop the old running containers that have conflicting ports with the new spec before running a new one.
-	for _, c := range containers {
+	// Find the first running container to replace (there should typically be only one).
+	var containerToReplace *api.MachineServiceContainer
+	for i, c := range containers {
 		if c.Container.State.Running {
-			conflictingPorts, err := c.Container.ConflictingServicePorts(spec.Ports)
-			if err != nil {
-				return nil, fmt.Errorf("check conflicting ports: %w", err)
-			}
-
-			if len(conflictingPorts) > 0 {
-				// Stop the running container with conflicting ports.
-				ops = append(ops, &StopContainerOperation{
-					ServiceID:   serviceID,
-					ContainerID: c.Container.ID,
-					MachineID:   c.MachineID,
-				})
-			}
+			containerToReplace = &containers[i]
+			break
 		}
 	}
 
-	// Run a new container.
-	ops = append(ops, &RunContainerOperation{
-		ServiceID: serviceID,
-		Spec:      spec,
-		MachineID: machineID,
-	})
+	if containerToReplace != nil {
+		// Stop any other running containers that have conflicting ports before replacing the container.
+		// This handles the edge case where multiple running containers exist (due to bugs or interrupted deployments)
+		// and more than one has ports that conflict with the new spec.
+		for _, c := range containers {
+			if c.Container.ID == containerToReplace.Container.ID || !c.Container.State.Running {
+				continue
+			}
+			conflictingPorts, err := c.Container.ConflictingServicePorts(spec.Ports)
+			if err != nil || len(conflictingPorts) > 0 {
+				ops = append(ops, &operation.StopContainerOperation{
+					ServiceID:   serviceID,
+					ContainerID: c.Container.ID,
+					MachineID:   machineID,
+				})
+			}
+		}
 
-	// Remove the old containers.
-	for _, c := range containers {
-		ops = append(ops, &RemoveContainerOperation{
-			MachineID: c.MachineID,
-			Container: c.Container,
+		// Replace the running container with a new one.
+		order := determineUpdateOrder(containerToReplace.Container, spec)
+		ops = append(ops, &operation.ReplaceContainerOperation{
+			ServiceID:         serviceID,
+			Spec:              spec,
+			MachineID:         machineID,
+			OldContainer:      containerToReplace.Container,
+			Order:             order,
+			SkipHealthMonitor: skipHealthCheck,
 		})
+
+		// Remove any other containers (there shouldn't be any in normal operation).
+		for _, c := range containers {
+			if c.Container.ID == containerToReplace.Container.ID {
+				continue
+			}
+			ops = append(ops, &operation.RemoveContainerOperation{
+				MachineID: c.MachineID,
+				Container: c.Container,
+			})
+		}
+	} else {
+		// No running containers, create a new one and remove all stopped containers.
+		ops = append(ops, &operation.RunContainerOperation{
+			ServiceID:         serviceID,
+			Spec:              spec,
+			MachineID:         machineID,
+			SkipHealthMonitor: skipHealthCheck,
+		})
+		for _, c := range containers {
+			ops = append(ops, &operation.RemoveContainerOperation{
+				MachineID: c.MachineID,
+				Container: c.Container,
+			})
+		}
 	}
 
 	return ops, nil
 }
 
+// determineUpdateOrder determines the update order for replacing a container based on the service spec
+// and current container state. The order can be explicitly set in UpdateConfig, or automatically determined:
+// - If the user explicitly set order, respect it
+// - Services with port conflicts require stop-first (ports must be freed first)
+// - Single-replica services with data volumes default to stop-first (prevents data corruption)
+// - Multi-replica services use start-first (concurrent access already happening)
+// - All other services default to start-first (minimizes downtime)
+func determineUpdateOrder(oldContainer api.ServiceContainer, spec api.ServiceSpec) string {
+	// User explicitly set order - respect it
+	if spec.UpdateConfig.Order != "" {
+		return spec.UpdateConfig.Order
+	}
+
+	// Port conflicts require stop-first
+	conflictingPorts, err := oldContainer.ConflictingServicePorts(spec.Ports)
+	if err != nil || len(conflictingPorts) > 0 {
+		return api.UpdateOrderStopFirst
+	}
+
+	// Single-replica services with data volumes default to stop-first to prevent data corruption.
+	// Multi-replica services already have concurrent access, so start-first is safe.
+	if spec.Replicas <= 1 && len(spec.MountedDockerVolumes()) > 0 {
+		return api.UpdateOrderStopFirst
+	}
+
+	// Default: start-first for minimal downtime
+	return api.UpdateOrderStartFirst
+}
+
 // newEmptyPlan creates a new empty plan for a service deployment with initialised service ID and name.
 func newEmptyPlan(svc *api.Service, spec api.ServiceSpec) (Plan, error) {
 	var plan Plan

pkg/client/deploy/strategy_test.go

@@ -0,0 +1,425 @@
+package deploy
+
+import (
+	"testing"
+
+	"github.com/docker/docker/api/types/container"
+	"github.com/google/go-cmp/cmp"
+	"github.com/google/go-cmp/cmp/cmpopts"
+	"github.com/psviderski/uncloud/pkg/api"
+	"github.com/psviderski/uncloud/pkg/client/deploy/operation"
+	"github.com/stretchr/testify/assert"
+)
+
+func TestDetermineUpdateOrder(t *testing.T) {
+	tests := []struct {
+		name         string
+		oldContainer api.ServiceContainer
+		spec         api.ServiceSpec
+		expected     string
+	}{
+		{
+			name: "explicit stop-first order",
+			oldContainer: api.ServiceContainer{
+				Container: api.Container{
+					InspectResponse: container.InspectResponse{
+						Config: &container.Config{Labels: map[string]string{}},
+					},
+				},
+			},
+			spec: api.ServiceSpec{
+				UpdateConfig: api.UpdateConfig{
+					Order: api.UpdateOrderStopFirst,
+				},
+			},
+			expected: api.UpdateOrderStopFirst,
+		},
+		{
+			name: "explicit start-first order",
+			oldContainer: api.ServiceContainer{
+				Container: api.Container{
+					InspectResponse: container.InspectResponse{
+						Config: &container.Config{Labels: map[string]string{}},
+					},
+				},
+			},
+			spec: api.ServiceSpec{
+				UpdateConfig: api.UpdateConfig{
+					Order: api.UpdateOrderStartFirst,
+				},
+			},
+			expected: api.UpdateOrderStartFirst,
+		},
+		{
+			name: "explicit start-first overrides volume default",
+			oldContainer: api.ServiceContainer{
+				Container: api.Container{
+					InspectResponse: container.InspectResponse{
+						Config: &container.Config{Labels: map[string]string{}},
+					},
+				},
+			},
+			spec: api.ServiceSpec{
+				UpdateConfig: api.UpdateConfig{
+					Order: api.UpdateOrderStartFirst,
+				},
+				Volumes: []api.VolumeSpec{
+					{
+						Name: "data",
+						Type: api.VolumeTypeVolume,
+						VolumeOptions: &api.VolumeOptions{
+							Name: "data",
+						},
+					},
+				},
+				Container: api.ContainerSpec{
+					VolumeMounts: []api.VolumeMount{
+						{
+							VolumeName:    "data",
+							ContainerPath: "/data",
+						},
+					},
+				},
+			},
+			expected: api.UpdateOrderStartFirst,
+		},
+		{
+			name: "single-replica service with volume defaults to stop-first",
+			oldContainer: api.ServiceContainer{
+				Container: api.Container{
+					InspectResponse: container.InspectResponse{
+						Config: &container.Config{Labels: map[string]string{}},
+					},
+				},
+			},
+			spec: api.ServiceSpec{
+				Replicas: 1,
+				Volumes: []api.VolumeSpec{
+					{
+						Name: "db-data",
+						Type: api.VolumeTypeVolume,
+						VolumeOptions: &api.VolumeOptions{
+							Name: "db-data",
+						},
+					},
+				},
+				Container: api.ContainerSpec{
+					VolumeMounts: []api.VolumeMount{
+						{
+							VolumeName:    "db-data",
+							ContainerPath: "/var/lib/postgresql/data",
+						},
+					},
+				},
+			},
+			expected: api.UpdateOrderStopFirst,
+		},
+		{
+			name: "multi-replica service with volume defaults to start-first",
+			oldContainer: api.ServiceContainer{
+				Container: api.Container{
+					InspectResponse: container.InspectResponse{
+						Config: &container.Config{Labels: map[string]string{}},
+					},
+				},
+			},
+			spec: api.ServiceSpec{
+				Replicas: 3,
+				Volumes: []api.VolumeSpec{
+					{
+						Name: "app-data",
+						Type: api.VolumeTypeVolume,
+						VolumeOptions: &api.VolumeOptions{
+							Name: "app-data",
+						},
+					},
+				},
+				Container: api.ContainerSpec{
+					VolumeMounts: []api.VolumeMount{
+						{
+							VolumeName:    "app-data",
+							ContainerPath: "/data",
+						},
+					},
+				},
+			},
+			expected: api.UpdateOrderStartFirst,
+		},
+		{
+			name: "service with bind mount defaults to start-first",
+			oldContainer: api.ServiceContainer{
+				Container: api.Container{
+					InspectResponse: container.InspectResponse{
+						Config: &container.Config{Labels: map[string]string{}},
+					},
+				},
+			},
+			spec: api.ServiceSpec{
+				Volumes: []api.VolumeSpec{
+					{
+						Name: "config",
+						Type: api.VolumeTypeBind,
+						BindOptions: &api.BindOptions{
+							HostPath: "/etc/app/config",
+						},
+					},
+				},
+				Container: api.ContainerSpec{
+					VolumeMounts: []api.VolumeMount{
+						{
+							VolumeName:    "config",
+							ContainerPath: "/config",
+						},
+					},
+				},
+			},
+			expected: api.UpdateOrderStartFirst,
+		},
+		{
+			name: "service with tmpfs mount defaults to start-first",
+			oldContainer: api.ServiceContainer{
+				Container: api.Container{
+					InspectResponse: container.InspectResponse{
+						Config: &container.Config{Labels: map[string]string{}},
+					},
+				},
+			},
+			spec: api.ServiceSpec{
+				Volumes: []api.VolumeSpec{
+					{
+						Name: "tmp",
+						Type: api.VolumeTypeTmpfs,
+					},
+				},
+				Container: api.ContainerSpec{
+					VolumeMounts: []api.VolumeMount{
+						{
+							VolumeName:    "tmp",
+							ContainerPath: "/tmp",
+						},
+					},
+				},
+			},
+			expected: api.UpdateOrderStartFirst,
+		},
+		{
+			name: "stateless service defaults to start-first",
+			oldContainer: api.ServiceContainer{
+				Container: api.Container{
+					InspectResponse: container.InspectResponse{
+						Config: &container.Config{Labels: map[string]string{}},
+					},
+				},
+			},
+			spec: api.ServiceSpec{
+				Container: api.ContainerSpec{
+					Image: "nginx:latest",
+				},
+			},
+			expected: api.UpdateOrderStartFirst,
+		},
+		{
+			name: "port conflict forces stop-first",
+			oldContainer: api.ServiceContainer{
+				Container: api.Container{
+					InspectResponse: container.InspectResponse{
+						Config: &container.Config{
+							Labels: map[string]string{
+								api.LabelServicePorts: `[{"container_port":8080,"published_port":8080,"protocol":"tcp","mode":"host"}]`,
+							},
+						},
+					},
+				},
+			},
+			spec: api.ServiceSpec{
+				Ports: []api.PortSpec{
+					{
+						ContainerPort: 8080,
+						PublishedPort: 8080,
+						Protocol:      "tcp",
+						Mode:          api.PortModeHost,
+					},
+				},
+			},
+			expected: api.UpdateOrderStopFirst,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			result := determineUpdateOrder(tt.oldContainer, tt.spec)
+			assert.Equal(t, tt.expected, result)
+		})
+	}
+}
+
+func TestReconcileGlobalContainer(t *testing.T) {
+	container1 := api.ServiceContainer{
+		Container: api.Container{
+			InspectResponse: container.InspectResponse{
+				ContainerJSONBase: &container.ContainerJSONBase{
+					ID:    "container-1",
+					State: &container.State{Running: true},
+				},
+				Config: &container.Config{
+					Labels: map[string]string{
+						api.LabelServicePorts: "8080:8080/tcp@host",
+					},
+				},
+			},
+		},
+	}
+	container2WithPort9090 := api.ServiceContainer{
+		Container: api.Container{
+			InspectResponse: container.InspectResponse{
+				ContainerJSONBase: &container.ContainerJSONBase{
+					ID:    "container-2",
+					State: &container.State{Running: true},
+				},
+				Config: &container.Config{
+					Labels: map[string]string{
+						api.LabelServicePorts: "9090:9090/tcp@host",
+					},
+				},
+			},
+		},
+	}
+	container2WithPort3000 := api.ServiceContainer{
+		Container: api.Container{
+			InspectResponse: container.InspectResponse{
+				ContainerJSONBase: &container.ContainerJSONBase{
+					ID:    "container-2",
+					State: &container.State{Running: true},
+				},
+				Config: &container.Config{
+					Labels: map[string]string{
+						api.LabelServicePorts: "3000:3000/tcp@host",
+					},
+				},
+			},
+		},
+	}
+
+	tests := []struct {
+		name          string
+		containers    []api.MachineServiceContainer
+		spec          api.ServiceSpec
+		forceRecreate bool
+		expectedOps   []operation.Operation
+	}{
+		{
+			name:       "no containers creates new",
+			containers: nil,
+			spec: api.ServiceSpec{
+				Container: api.ContainerSpec{Image: "nginx:latest"},
+			},
+			expectedOps: []operation.Operation{
+				&operation.RunContainerOperation{
+					ServiceID: "service-1",
+					MachineID: "machine-1",
+				},
+			},
+		},
+		{
+			name: "single running container with port conflict uses replace",
+			containers: []api.MachineServiceContainer{
+				{MachineID: "machine-1", Container: container1},
+			},
+			spec: api.ServiceSpec{
+				Container: api.ContainerSpec{Image: "nginx:latest"},
+				Ports: []api.PortSpec{
+					{ContainerPort: 8080, PublishedPort: 8080, Protocol: "tcp", Mode: api.PortModeHost},
+				},
+			},
+			expectedOps: []operation.Operation{
+				&operation.ReplaceContainerOperation{
+					ServiceID:    "service-1",
+					MachineID:    "machine-1",
+					OldContainer: container1,
+					Order:        api.UpdateOrderStopFirst,
+				},
+			},
+		},
+		{
+			name: "multiple running containers with different conflicting ports stops extras before replace",
+			containers: []api.MachineServiceContainer{
+				{MachineID: "machine-1", Container: container1},
+				{MachineID: "machine-1", Container: container2WithPort9090},
+			},
+			spec: api.ServiceSpec{
+				Container: api.ContainerSpec{Image: "nginx:latest"},
+				Ports: []api.PortSpec{
+					{ContainerPort: 8080, PublishedPort: 8080, Protocol: "tcp", Mode: api.PortModeHost},
+					{ContainerPort: 9090, PublishedPort: 9090, Protocol: "tcp", Mode: api.PortModeHost},
+				},
+			},
+			expectedOps: []operation.Operation{
+				&operation.StopContainerOperation{
+					ServiceID:   "service-1",
+					ContainerID: "container-2",
+					MachineID:   "machine-1",
+				},
+				&operation.ReplaceContainerOperation{
+					ServiceID:    "service-1",
+					MachineID:    "machine-1",
+					OldContainer: container1,
+					Order:        api.UpdateOrderStopFirst,
+				},
+				&operation.RemoveContainerOperation{
+					MachineID: "machine-1",
+					Container: container2WithPort9090,
+				},
+			},
+		},
+		{
+			name: "multiple running containers but only one has port conflict",
+			containers: []api.MachineServiceContainer{
+				{MachineID: "machine-1", Container: container1},
+				{MachineID: "machine-1", Container: container2WithPort3000},
+			},
+			spec: api.ServiceSpec{
+				Container: api.ContainerSpec{Image: "nginx:latest"},
+				Ports: []api.PortSpec{
+					{ContainerPort: 8080, PublishedPort: 8080, Protocol: "tcp", Mode: api.PortModeHost},
+				},
+			},
+			// Container-2 has no conflicting ports, so no StopContainerOperation for it.
+			expectedOps: []operation.Operation{
+				&operation.ReplaceContainerOperation{
+					ServiceID:    "service-1",
+					MachineID:    "machine-1",
+					OldContainer: container1,
+					Order:        api.UpdateOrderStopFirst,
+				},
+				&operation.RemoveContainerOperation{
+					MachineID: "machine-1",
+					Container: container2WithPort3000,
+				},
+			},
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			ops, err := reconcileGlobalContainer(
+				tt.containers, tt.spec, "service-1", "machine-1", tt.forceRecreate, false,
+			)
+			assert.NoError(t, err)
+			assertOperationsEqual(t, tt.expectedOps, ops)
+		})
+	}
+}
+
+// assertOperationsEqual compares expected and actual operations, ignoring the Spec field
+// which is passed separately to the function and not the focus of these tests.
+func assertOperationsEqual(t *testing.T, expected, actual []operation.Operation) {
+	t.Helper()
+	opts := cmp.Options{
+		cmpopts.IgnoreFields(operation.RunContainerOperation{}, "Spec"),
+		cmpopts.IgnoreFields(operation.ReplaceContainerOperation{}, "Spec"),
+		cmpopts.IgnoreUnexported(api.Container{}),
+	}
+	if diff := cmp.Diff(expected, actual, opts); diff != "" {
+		t.Errorf("operations mismatch (-expected +actual):\n%s", diff)
+	}
+}

pkg/client/dns.go

@@ -5,7 +5,9 @@ import (
 	"errors"
 	"fmt"
 	"io"
+	"net"
 	"net/http"
+	"net/netip"
 	"sync"
 	"time"
 
@@ -61,14 +63,11 @@ func (cli *Client) CreateIngressRecords(ctx context.Context, serviceID string) (
 			continue
 		}
 
-		wg.Add(1)
-		go func() {
-			defer wg.Done()
-
+		wg.Go(func() {
 			if err = verifyCaddyReachable(ctx, m.Machine); err == nil {
 				reachableMachines <- m.Machine
 			}
-		}()
+		})
 	}
 
 	go func() {
@@ -111,8 +110,7 @@ func verifyCaddyReachable(ctx context.Context, m *pb.MachineInfo) error {
 	eventID := fmt.Sprintf("Machine %s (%s)", m.Name, publicIP)
 	pw.Event(progress.NewEvent(eventID, progress.Working, "Querying"))
 
-	verifyURL := fmt.Sprintf("http://%s%s", publicIP, caddyconfig.VerifyPath)
-
+	verifyURL := getVerifyURL(publicIP)
 	req, err := http.NewRequestWithContext(ctx, http.MethodGet, verifyURL, nil)
 	if err != nil {
 		pw.Event(progress.NewEvent(eventID, progress.Error, err.Error()))
@@ -173,6 +171,11 @@ func verifyCaddyReachable(ctx context.Context, m *pb.MachineInfo) error {
 	}
 }
 
+func getVerifyURL(publicIP netip.Addr) string {
+	httpFormattedIP := net.JoinHostPort(publicIP.String(), "")
+	return fmt.Sprintf("http://%s%s", httpFormattedIP, caddyconfig.VerifyPath)
+}
+
 // unreachable creates a new Unreachable error event.
 func unreachable(id string) progress.Event {
 	return progress.NewEvent(

pkg/client/dns_internal_test.go

@@ -0,0 +1,30 @@
+package client
+
+import (
+	"net/netip"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+)
+
+func TestGetVerifyURL(t *testing.T) {
+	tests := map[string]struct {
+		given netip.Addr
+		want  string
+	}{
+		"IPv4": {
+			given: netip.MustParseAddr("93.184.216.34"),
+			want:  "http://93.184.216.34:/.uncloud-verify",
+		},
+		"IPv6": {
+			given: netip.MustParseAddr("2001:db8::1"),
+			want:  "http://[2001:db8::1]:/.uncloud-verify",
+		},
+	}
+	for name, tt := range tests {
+		t.Run(name, func(t *testing.T) {
+			got := getVerifyURL(tt.given)
+			assert.Equal(t, tt.want, got)
+		})
+	}
+}

pkg/client/image.go

@@ -6,6 +6,7 @@ import (
 	"errors"
 	"fmt"
 	"net"
+	"runtime"
 	"strconv"
 	"strings"
 	"sync"
@@ -363,14 +364,25 @@ func newUnregistryProxy(
 	return p, nil
 }
 
-// isDockerVirtualised checks if Docker is running in a virtualised environment like Docker Desktop on macOS.
+// isDockerVirtualised checks if Docker is running in a virtualised environment like Docker/Rancher Desktop or Colima.
+// On macOS, Docker always requires a VM, so it returns true unless OrbStack is detected (which handles host networking
+// natively). On other platforms, it checks for known virtualised Docker hostnames.
 func isDockerVirtualised(ctx context.Context, dockerCli *docker.Client) (bool, error) {
 	info, err := dockerCli.Info(ctx)
 	if err != nil {
 		return false, fmt.Errorf("get Docker info: %w", err)
 	}
 
-	virtualisedHostnames := []string{"docker-desktop", "colima"}
+	// On macOS, Docker always runs in a VM. OrbStack is the only known exception that doesn't need a proxy.
+	if runtime.GOOS == "darwin" {
+		if info.Name == "orbstack" {
+			return false, nil
+		}
+		return true, nil
+	}
+
+	// On other platforms, check for known virtualised Docker environments.
+	virtualisedHostnames := []string{"docker-desktop", "rancher-desktop", "colima"}
 	for _, name := range virtualisedHostnames {
 		if strings.Contains(strings.ToLower(info.Name), name) {
 			return true, nil
@@ -406,6 +418,9 @@ func runDockerVMProxyContainer(ctx context.Context, dockerCli *docker.Client, ta
 		ExposedPorts: nat.PortSet{
 			containerPort: {},
 		},
+		Labels: map[string]string{
+			api.LabelManaged: "",
+		},
 	}
 
 	// Get an available port on localhost to bind the container port to by creating a temporary listener and closing it.

pkg/client/machine.go

@@ -4,7 +4,9 @@ import (
 	"context"
 	"fmt"
 	"strings"
+	"time"
 
+	"github.com/cenkalti/backoff/v4"
 	"github.com/psviderski/uncloud/internal/machine/api/pb"
 	"github.com/psviderski/uncloud/pkg/api"
 	"google.golang.org/grpc/codes"
@@ -13,6 +15,7 @@ import (
 )
 
 func (cli *Client) InspectMachine(ctx context.Context, nameOrID string) (*pb.MachineMember, error) {
+	// TODO: refactor to use MachineClient.InspectMachine.
 	machines, err := cli.ListMachines(ctx, nil)
 	if err != nil {
 		return nil, err
@@ -99,3 +102,48 @@ func (cli *Client) RenameMachine(ctx context.Context, nameOrID, newName string)
 
 	return cli.UpdateMachine(ctx, req)
 }
+
+// WaitMachineReady waits for the machine API on the connected machine to respond.
+func (cli *Client) WaitMachineReady(ctx context.Context, timeout time.Duration) error {
+	boff := backoff.WithContext(backoff.NewExponentialBackOff(
+		backoff.WithInitialInterval(100*time.Millisecond),
+		backoff.WithMaxInterval(1*time.Second),
+		backoff.WithMaxElapsedTime(timeout),
+	), ctx)
+
+	inspect := func() error {
+		if _, err := cli.Inspect(ctx, &emptypb.Empty{}); err != nil {
+			return fmt.Errorf("inspect machine: %w", err)
+		}
+		return nil
+	}
+	return backoff.Retry(inspect, boff)
+}
+
+// WaitClusterReady waits for the connected machine to be ready to server cluster requests.
+func (cli *Client) WaitClusterReady(ctx context.Context, timeout time.Duration) error {
+	// Backoff is not really needed here as the default service config for the gRPC client is already
+	// doing retries with backoff for Unavailable errors. However, it's still convenient to use backoff
+	// to control the overall timeout for the operation.
+	boff := backoff.WithContext(backoff.NewExponentialBackOff(
+		backoff.WithInitialInterval(100*time.Millisecond),
+		backoff.WithMaxInterval(1*time.Second),
+		backoff.WithMaxElapsedTime(timeout),
+	), ctx)
+
+	listMachines := func() error {
+		_, err := cli.ListMachines(ctx, nil)
+		if err != nil {
+			if s, ok := status.FromError(err); ok &&
+				// TODO: remove FailedPrecondition after releading 0.17.
+				(s.Code() == codes.Unavailable || s.Code() == codes.FailedPrecondition) {
+				// Machine is not ready yet, retry.
+				return err
+			}
+			// Other non-Unavailable errors should not be retried.
+			return backoff.Permanent(err)
+		}
+		return nil
+	}
+	return backoff.Retry(listMachines, boff)
+}

pkg/client/service.go

@@ -240,11 +240,7 @@ func (cli *Client) RemoveService(ctx context.Context, id string) error {
 
 	// Remove all containers on all machines that belong to the service.
 	for _, mc := range svc.Containers {
-		wg.Add(1)
-
-		go func() {
-			defer wg.Done()
-
+		wg.Go(func() {
 			err := cli.StopContainer(ctx, svc.ID, mc.Container.ID, container.StopOptions{})
 			if err != nil {
 				errCh <- fmt.Errorf("stop container '%s': %w", mc.Container.ID, err)
@@ -258,7 +254,7 @@ func (cli *Client) RemoveService(ctx context.Context, id string) error {
 			if err != nil && !errors.Is(err, api.ErrNotFound) {
 				errCh <- fmt.Errorf("remove container '%s': %w", mc.Container.ID, err)
 			}
-		}()
+		})
 	}
 
 	go func() {
@@ -286,16 +282,12 @@ func (cli *Client) StopService(ctx context.Context, id string, opts container.St
 
 	// Stop all containers on all machines that belong to the service.
 	for _, mc := range svc.Containers {
-		wg.Add(1)
-
-		go func() {
-			defer wg.Done()
-
+		wg.Go(func() {
 			err := cli.StopContainer(ctx, svc.ID, mc.Container.ID, opts)
 			if err != nil {
 				errCh <- fmt.Errorf("stop container '%s': %w", mc.Container.ID, err)
 			}
-		}()
+		})
 	}
 
 	go func() {
@@ -323,16 +315,12 @@ func (cli *Client) StartService(ctx context.Context, id string) error {
 
 	// Start all containers on all machines that belong to the service.
 	for _, mc := range svc.Containers {
-		wg.Add(1)
-
-		go func() {
-			defer wg.Done()
-
+		wg.Go(func() {
 			err := cli.StartContainer(ctx, svc.ID, mc.Container.ID)
 			if err != nil {
 				errCh <- fmt.Errorf("start container '%s': %w", mc.Container.ID, err)
 			}
-		}()
+		})
 	}
 
 	go func() {

scripts/install.sh

@@ -338,7 +338,7 @@ if [ "$DOCKER_ALREADY_INSTALLED" = "true" ] && [ "$CONTAINERD_IMAGE_STORE_ENABLE
     echo ""
     warning "Docker was already installed on the machine but it doesn't use the containerd"
     warning "image store. Uncloud works best with the containerd image store enabled in Docker."
-    warning "It allows Docker to directly use the images stores in containerd (pushed with"
+    warning "It allows Docker to directly use the images stored in containerd (pushed with"
     warning "'uc image push') without duplicating them in Docker. This saves disk space and"
     warning "makes image management more efficient."
     echo ""

test/e2e/assert.go

@@ -58,6 +58,36 @@ func assertContainerMatchesSpec(t *testing.T, ctr api.ServiceContainer, spec api
 		assert.Contains(t, ctr.Config.Env, env)
 	}
 
+	// Healthcheck can only be compared if set in the spec. Otherwise, the container inherits it from the image.
+	if spec.Container.Healthcheck != nil {
+		hc := spec.Container.Healthcheck
+		require.NotNil(t, ctr.Config.Healthcheck)
+		if hc.Disable {
+			assert.Equal(t, []string{"NONE"}, ctr.Config.Healthcheck.Test)
+		} else {
+			// Only compare fields that are explicitly set in the spec as unset fields inherit their values
+			// from the image.
+			if hc.Test != nil {
+				assert.EqualValues(t, hc.Test, ctr.Config.Healthcheck.Test)
+			}
+			if hc.Interval != 0 {
+				assert.Equal(t, hc.Interval, ctr.Config.Healthcheck.Interval)
+			}
+			if hc.Timeout != 0 {
+				assert.Equal(t, hc.Timeout, ctr.Config.Healthcheck.Timeout)
+			}
+			if hc.StartPeriod != 0 {
+				assert.Equal(t, hc.StartPeriod, ctr.Config.Healthcheck.StartPeriod)
+			}
+			if hc.StartInterval != 0 {
+				assert.Equal(t, hc.StartInterval, ctr.Config.Healthcheck.StartInterval)
+			}
+			if hc.Retries != 0 {
+				assert.Equal(t, int(hc.Retries), ctr.Config.Healthcheck.Retries)
+			}
+		}
+	}
+
 	assert.Equal(t, spec.Container.Image, ctr.Config.Image)
 	assert.Equal(t, spec.Container.Init, ctr.HostConfig.Init)
 	assert.True(t, strings.HasPrefix(ctr.Name, spec.Name+"-"))

test/e2e/cluster_test.go

@@ -55,7 +55,7 @@ func createTestCluster(
 	})
 
 	if waitReady {
-		require.NoError(t, p.WaitClusterReady(ctx, c, 15*time.Second))
+		require.NoError(t, p.WaitClusterReady(ctx, c, 30*time.Second))
 	}
 
 	return c, p
@@ -73,7 +73,6 @@ func TestClusterLifecycle(t *testing.T) {
 		// Create a client for each machine and wait for it to be ready.
 		clients := make([]*client.Client, len(c.Machines))
 		for i, m := range c.Machines {
-			require.NoError(t, ucind.WaitMachineReady(ctx, m, 5*time.Second))
 			clients[i], err = m.Connect(ctx)
 			require.NoError(t, err)
 			//goland:noinspection GoDeferInLoop
@@ -86,11 +85,10 @@ func TestClusterLifecycle(t *testing.T) {
 			require.Eventually(t, func() bool {
 				machines, err := cli.ListMachines(ctx, nil)
 				if err != nil {
-					// FailedPrecondition "cluster is not initialised" is expected until the store is reconciled.
-					if s, ok := status.FromError(err); ok {
-						if s.Code() == codes.FailedPrecondition {
-							return false
-						}
+					// Unavailable "machine is not ready to serve cluster requests" is expected until
+					// the store is reconciled.
+					if s, ok := status.FromError(err); ok && s.Code() == codes.Unavailable {
+						return false
 					}
 					require.NoError(t, err)
 				}

test/e2e/compose_configs_test.go

@@ -66,6 +66,11 @@ func TestComposeConfigs(t *testing.T) {
 						Gid:           "1000",
 						Mode:          func() *os.FileMode { m := os.FileMode(0o600); return &m }(),
 					},
+					{
+						ConfigName:    "from-file",
+						ContainerPath: "/etc/new-dir/config-from-file.conf",
+						Mode:          func() *os.FileMode { m := os.FileMode(0o644); return &m }(),
+					},
 				},
 			},
 			Configs: []api.ConfigSpec{
@@ -110,5 +115,14 @@ func TestComposeConfigs(t *testing.T) {
 			userId:      1000,
 			groupId:     1000,
 		}, configContentSecond)
+
+		configContentThird, err := readFileInfoInContainer(t, cli, name, containerName, "/etc/new-dir/config-from-file.conf")
+		require.NoError(t, err)
+		assert.Equal(t, fileInfo{
+			permissions: 0o644,
+			content:     "this is file config\n",
+			userId:      0,
+			groupId:     0,
+		}, configContentThird, "Same config should be mountable to multiple paths, including nested directories")
 	})
 }

test/e2e/compose_deploy_test.go

@@ -558,4 +558,45 @@ volumes:
 
 		assert.Len(t, plan.Operations, 2, "Expected 1 volume creation and 1 service to deploy")
 	})
+
+	t.Run("global service auto-creates volumes on all machines", func(t *testing.T) {
+		t.Parallel()
+
+		serviceName := "test-compose-global-volume"
+		volumeName := serviceName
+		t.Cleanup(func() {
+			removeServices(t, cli, serviceName)
+			for _, machine := range c.Machines {
+				_ = cli.RemoveVolume(ctx, machine.Name, volumeName, false)
+			}
+		})
+
+		project, err := compose.LoadProject(ctx, []string{"fixtures/compose-global-volume.yaml"})
+		require.NoError(t, err)
+
+		deployment, err := compose.NewDeployment(ctx, cli, project)
+		require.NoError(t, err)
+
+		err = deployment.Run(ctx)
+		require.NoError(t, err, "Global deployment should auto-create volumes on all machines")
+
+		// Verify volumes were created on all machines.
+		volumes, err := cli.ListVolumes(ctx, &api.VolumeFilter{Names: []string{volumeName}})
+		require.NoError(t, err)
+		assert.Len(t, volumes, len(c.Machines), "Volume should be created on all machines")
+
+		// Verify containers are running on all machines.
+		svc, err := cli.InspectService(ctx, serviceName)
+		require.NoError(t, err)
+		assert.Equal(t, api.ServiceModeGlobal, svc.Mode)
+		assert.Len(t, svc.Containers, len(c.Machines), "Container should be running on all machines")
+
+		machines := serviceMachines(svc)
+		expectedMachines := make([]string, len(c.Machines))
+		for i, m := range c.Machines {
+			expectedMachines[i] = m.ID
+		}
+		assert.ElementsMatch(t, machines.ToSlice(), expectedMachines,
+			"Containers should be distributed across all machines")
+	})
 }

test/e2e/fixtures/compose-configs.yaml

@@ -11,6 +11,10 @@ services:
         uid: "1000"
         gid: "1000"
         mode: 0600
+      # Writing a config to a new, non-existent directory
+      - source: from-file
+        target: /etc/new-dir/config-from-file.conf
+        mode: 0644
     deploy:
       replicas: 1
 configs:

test/e2e/fixtures/compose-global-volume.yaml

@@ -0,0 +1,10 @@
+services:
+  test-compose-global-volume:
+    image: portainer/pause:latest
+    deploy:
+      mode: global
+    volumes:
+      - test-compose-global-volume:/data
+
+volumes:
+  test-compose-global-volume:

test/e2e/helpers.go

@@ -71,7 +71,6 @@ func readFileInfoInContainer(t *testing.T, cli *client.Client, serviceNameOrID,
 
 	// Parse permissions
 	permissions := strings.TrimSpace(permOutput)
-	fmt.Printf("Permissions output: %s\n", permissions)
 
 	// Parse three numbers: permissions, uid, gid
 	var permissionsOctal, uid, gid int

test/e2e/main_test.go

@@ -0,0 +1,15 @@
+package e2e
+
+import (
+	"os"
+	"testing"
+
+	"github.com/psviderski/uncloud/pkg/api"
+)
+
+func TestMain(m *testing.M) {
+	// Disable the default health monitor period to speed up tests. Tests that need a non-zero monitor period
+	// should set it explicitly via UpdateConfig.MonitorPeriod in their service spec.
+	api.DefaultHealthMonitorPeriod = 0
+	os.Exit(m.Run())
+}

test/e2e/service_test.go

@@ -56,11 +56,16 @@ func TestDeployment(t *testing.T) {
 			require.ErrorIs(t, err, api.ErrNotFound)
 		})
 
+		// Explicit short period as the default 5s is disabled in tests for faster test execution.
+		monitorPeriod := 1 * time.Second
 		spec := api.ServiceSpec{
 			Mode: api.ServiceModeGlobal,
 			Container: api.ContainerSpec{
 				Image: "portainer/pause:latest",
 			},
+			UpdateConfig: api.UpdateConfig{
+				MonitorPeriod: &monitorPeriod,
+			},
 		}
 		deployment := cli.NewDeployment(spec, nil)
 
@@ -73,7 +78,9 @@ func TestDeployment(t *testing.T) {
 		assert.NotEmpty(t, plan.ServiceName)
 		assert.Len(t, plan.SequenceOperation.Operations, 3) // 3 run
 
+		start := time.Now()
 		runPlan, err := deployment.Run(ctx)
+		duration := time.Since(start)
 		require.NoError(t, err)
 		assert.Equal(t, plan, runPlan)
 
@@ -88,6 +95,13 @@ func TestDeployment(t *testing.T) {
 		machines := serviceMachines(svc)
 		assert.Len(t, machines.ToSlice(), 3, "Expected 1 container on each machine")
 
+		for _, ctr := range svc.Containers {
+			assert.True(t, ctr.Container.Healthy(), "Expected deployed containers to be healthy")
+		}
+		assert.True(t, duration >= 3*monitorPeriod,
+			"Expected deployment to wait for at least the health monitor period for each container "+
+				"before checking health")
+
 		// Deploy a published port.
 		initialContainers := serviceContainerIDs(svc)
 
@@ -105,14 +119,19 @@ func TestDeployment(t *testing.T) {
 					Mode:          api.PortModeHost,
 				},
 			},
+			UpdateConfig: api.UpdateConfig{
+				MonitorPeriod: &monitorPeriod,
+			},
 		}
 		deployment = cli.NewDeployment(specWithPort, nil)
 
 		plan, err = deployment.Plan(ctx)
 		require.NoError(t, err)
-		assert.Len(t, plan.SequenceOperation.Operations, 6) // 3 run + 3 remove
+		assert.Len(t, plan.SequenceOperation.Operations, 3) // 3 replace
 
+		start = time.Now()
 		_, err = deployment.Run(ctx)
+		duration = time.Since(start)
 		require.NoError(t, err)
 
 		svc, err = cli.InspectService(ctx, name)
@@ -126,6 +145,13 @@ func TestDeployment(t *testing.T) {
 		assert.Empty(t, initialContainers.Intersect(containers).ToSlice(),
 			"All existing containers should be replaced")
 
+		for _, ctr := range svc.Containers {
+			assert.True(t, ctr.Container.Healthy(), "Expected redeployed containers to be healthy")
+		}
+		assert.True(t, duration >= 3*monitorPeriod,
+			"Expected deployment to wait for at least the health monitor period for each container "+
+				"before checking health")
+
 		// Deploy the same conflicting port but with container spec changes
 		initialContainers = containers
 
@@ -150,7 +176,7 @@ func TestDeployment(t *testing.T) {
 
 		plan, err = deployment.Plan(ctx)
 		require.NoError(t, err)
-		assert.Len(t, plan.SequenceOperation.Operations, 9) // 3 stop + 3 run + 3 remove
+		assert.Len(t, plan.SequenceOperation.Operations, 3) // 3 replace (stop-first due to port conflicts)
 
 		_, err = deployment.Run(ctx)
 		require.NoError(t, err)
@@ -293,7 +319,7 @@ func TestDeployment(t *testing.T) {
 		config, err := cli.Caddy.GetConfig(ctx, nil)
 		require.NoError(t, err)
 
-		assert.Contains(t, config.Caddyfile, "# This file is autogenerated by Uncloud")
+		assert.Contains(t, config.Caddyfile, "# Caddyfile autogenerated by Uncloud")
 		assert.Contains(t, config.Caddyfile, "handle /.uncloud-verify")
 	})
 
@@ -423,7 +449,7 @@ myapp.example.com {
 		}, 5*time.Second, 100*time.Millisecond,
 			"Expected both custom configs to be included in the Caddyfile")
 
-		assert.Contains(t, config.Caddyfile, "# This file is autogenerated by Uncloud")
+		assert.Contains(t, config.Caddyfile, "# Caddyfile autogenerated by Uncloud")
 		assert.Contains(t, config.Caddyfile, "handle /.uncloud-verify")
 		assert.Contains(t, config.Caddyfile, caddyCaddyfile,
 			"Expected user-defined global Caddy config to be included in the Caddyfile")
@@ -480,7 +506,11 @@ myapp.example.com {
 		// Check that the Caddy config hasn't changed.
 		newConfig, err := cli.Caddy.GetConfig(ctx, nil)
 		require.NoError(t, err)
-		assert.Equal(t, validConfig, newConfig.Caddyfile,
+
+		// Compare stable parts of the Caddyfile only (skip autogenerated comment with timestamp).
+		_, stableValidConfig, _ := strings.Cut(validConfig, "\n")
+		_, stableNewConfig, _ := strings.Cut(newConfig.Caddyfile, "\n")
+		assert.Equal(t, stableValidConfig, stableNewConfig,
 			"Caddy config should not change when an invalid user-defined Caddy config is deployed")
 	})
 
@@ -496,6 +526,8 @@ myapp.example.com {
 		})
 
 		// 1. Create a basic replicated service with 2 replicas.
+		// Explicit short period as the default 5s is disabled in tests for faster test execution.
+		monitorPeriod := 1 * time.Second
 		spec := api.ServiceSpec{
 			Name: name,
 			Mode: api.ServiceModeReplicated,
@@ -503,6 +535,9 @@ myapp.example.com {
 				Image: "portainer/pause:latest",
 			},
 			Replicas: 2,
+			UpdateConfig: api.UpdateConfig{
+				MonitorPeriod: &monitorPeriod,
+			},
 		}
 		deployment := cli.NewDeployment(spec, nil)
 
@@ -515,7 +550,9 @@ myapp.example.com {
 		assert.Equal(t, name, plan.ServiceName)
 		assert.Len(t, plan.SequenceOperation.Operations, 2) // 2 run operations for 2 replicas
 
+		start := time.Now()
 		runPlan, err := deployment.Run(ctx)
+		duration := time.Since(start)
 		require.NoError(t, err)
 		assert.Equal(t, plan, runPlan)
 
@@ -529,6 +566,13 @@ myapp.example.com {
 		assert.Len(t, initialMachines.ToSlice(), 2, "Expected 2 containers on 2 different machines")
 		initialContainers := serviceContainerIDs(svc)
 
+		for _, ctr := range svc.Containers {
+			assert.True(t, ctr.Container.Healthy(), "Expected deployed containers to be healthy")
+		}
+		assert.True(t, duration >= 2*monitorPeriod,
+			"Expected deployment to wait for at least the health monitor period for each container "+
+				"before checking health")
+
 		// 2. Update the service with a new configuration.
 		init := true
 		updatedSpec := spec
@@ -537,9 +581,11 @@ myapp.example.com {
 
 		plan, err = deployment.Plan(ctx)
 		require.NoError(t, err)
-		assert.Len(t, plan.Operations, 4, "Expected 2 run + 2 remove operations")
+		assert.Len(t, plan.Operations, 2, "Expected 2 replace operations")
 
+		start = time.Now()
 		_, err = deployment.Run(ctx)
+		duration = time.Since(start)
 		require.NoError(t, err)
 
 		svc, err = cli.InspectService(ctx, name)
@@ -554,6 +600,13 @@ myapp.example.com {
 		assert.Empty(t, initialContainers.Intersect(containers).ToSlice(),
 			"All existing containers should be replaced")
 
+		for _, ctr := range svc.Containers {
+			assert.True(t, ctr.Container.Healthy(), "Expected deployed containers to be healthy")
+		}
+		assert.True(t, duration >= 2*monitorPeriod,
+			"Expected deployment to wait for at least the health monitor period for each container "+
+				"before checking health")
+
 		// 3. Scale to 3 replicas.
 		initialMachines = machines
 		initialContainers = containers // Reset container tracking.
@@ -589,7 +642,7 @@ myapp.example.com {
 
 		plan, err = deployment.Plan(ctx)
 		require.NoError(t, err)
-		assert.Len(t, plan.Operations, 8, "Expected 5 run + 3 remove operations")
+		assert.Len(t, plan.Operations, 5, "Expected 3 replace + 2 run operations")
 
 		_, err = deployment.Run(ctx)
 		require.NoError(t, err)
@@ -1209,6 +1262,9 @@ myapp.example.com {
 			Container: api.ContainerSpec{
 				Image: uniqueImage,
 			},
+			Placement: api.Placement{
+				Machines: []string{c.Machines[0].Name, c.Machines[1].Name},
+			},
 			Replicas: 2,
 		}
 
@@ -1260,6 +1316,168 @@ myapp.example.com {
 		}
 	})
 
+	t.Run("healthcheck becomes healthy", func(t *testing.T) {
+		t.Parallel()
+
+		name := "test-health-ok"
+		t.Cleanup(func() {
+			err := cli.RemoveService(ctx, name)
+			if !errors.Is(err, api.ErrNotFound) {
+				require.NoError(t, err)
+			}
+		})
+
+		monitorPeriod := 60 * time.Second
+		spec := api.ServiceSpec{
+			Name: name,
+			Mode: api.ServiceModeReplicated,
+			Container: api.ContainerSpec{
+				Image:   "busybox:1.37.0-musl",
+				Command: []string{"sh", "-c", "sleep 3600"},
+				Healthcheck: &api.HealthcheckSpec{
+					Test:     []string{"CMD-SHELL", "exit 0"},
+					Interval: 1 * time.Second,
+					Retries:  2,
+				},
+			},
+			UpdateConfig: api.UpdateConfig{
+				MonitorPeriod: &monitorPeriod,
+			},
+		}
+		deployment := cli.NewDeployment(spec, nil)
+
+		start := time.Now()
+		_, err := deployment.Run(ctx)
+		duration := time.Since(start)
+		require.NoError(t, err)
+
+		svc, err := cli.InspectService(ctx, name)
+		require.NoError(t, err)
+		assertServiceMatchesSpec(t, svc, spec)
+
+		assert.True(t, svc.Containers[0].Container.Healthy())
+		assert.True(t, duration >= 1*time.Second,
+			"Deployment should wait for at least one health check interval before marking container as healthy")
+		assert.True(t, duration < monitorPeriod,
+			"Deployment should mark container as healthy after first successful health check "+
+				"and not wait for the entire monitor period")
+	})
+
+	t.Run("healthcheck becomes unhealthy", func(t *testing.T) {
+		t.Parallel()
+
+		name := "test-health-fail"
+		t.Cleanup(func() {
+			err := cli.RemoveService(ctx, name)
+			if !errors.Is(err, api.ErrNotFound) {
+				require.NoError(t, err)
+			}
+		})
+
+		monitorPeriod := 1 * time.Second
+		spec := api.ServiceSpec{
+			Name: name,
+			Mode: api.ServiceModeReplicated,
+			Container: api.ContainerSpec{
+				Image:   "busybox:1.37.0-musl",
+				Command: []string{"sh", "-c", "sleep 3600"},
+				Healthcheck: &api.HealthcheckSpec{
+					Test:     []string{"CMD-SHELL", "exit 1"},
+					Interval: 1 * time.Second,
+					Retries:  2,
+				},
+			},
+			UpdateConfig: api.UpdateConfig{
+				MonitorPeriod: &monitorPeriod,
+			},
+		}
+		deployment := cli.NewDeployment(spec, nil)
+
+		start := time.Now()
+		_, err := deployment.Run(ctx)
+		duration := time.Since(start)
+		require.Error(t, err)
+
+		assert.ErrorContains(t, err, "unhealthy")
+		assert.True(t, duration >= monitorPeriod,
+			"Deployment should wait for at least the monitor period before checking health status")
+	})
+
+	t.Run("container crashes on startup with healthcheck", func(t *testing.T) {
+		t.Parallel()
+
+		name := "test-crash-startup-healthcheck"
+		t.Cleanup(func() {
+			err := cli.RemoveService(ctx, name)
+			if !errors.Is(err, api.ErrNotFound) {
+				require.NoError(t, err)
+			}
+		})
+
+		monitorPeriod := 1 * time.Second
+		spec := api.ServiceSpec{
+			Name: name,
+			Mode: api.ServiceModeReplicated,
+			Container: api.ContainerSpec{
+				Image:   "busybox:1.37.0-musl",
+				Command: []string{"false"},
+				Healthcheck: &api.HealthcheckSpec{
+					Test:     []string{"CMD-SHELL", "exit 0"},
+					Interval: 1 * time.Second,
+					Retries:  2,
+				},
+			},
+			UpdateConfig: api.UpdateConfig{
+				MonitorPeriod: &monitorPeriod,
+			},
+		}
+		deployment := cli.NewDeployment(spec, nil)
+
+		start := time.Now()
+		_, err := deployment.Run(ctx)
+		duration := time.Since(start)
+		require.Error(t, err)
+
+		assert.ErrorContains(t, err, "restarting")
+		assert.True(t, duration >= monitorPeriod,
+			"Deployment should wait for at least the monitor period before marking container as unhealthy")
+	})
+
+	t.Run("container crashes on startup without healthcheck", func(t *testing.T) {
+		t.Parallel()
+
+		name := "test-crash-startup-no-healthcheck"
+		t.Cleanup(func() {
+			err := cli.RemoveService(ctx, name)
+			if !errors.Is(err, api.ErrNotFound) {
+				require.NoError(t, err)
+			}
+		})
+
+		monitorPeriod := 1 * time.Second
+		spec := api.ServiceSpec{
+			Name: name,
+			Mode: api.ServiceModeReplicated,
+			Container: api.ContainerSpec{
+				Image:   "busybox:1.37.0-musl",
+				Command: []string{"false"},
+			},
+			UpdateConfig: api.UpdateConfig{
+				MonitorPeriod: &monitorPeriod,
+			},
+		}
+		deployment := cli.NewDeployment(spec, nil)
+
+		start := time.Now()
+		_, err := deployment.Run(ctx)
+		duration := time.Since(start)
+		require.Error(t, err)
+
+		assert.ErrorContains(t, err, "restarting")
+		assert.True(t, duration >= monitorPeriod,
+			"Deployment should wait for at least the monitor period before marking container as unhealthy")
+	})
+
 	// TODO: test deployments with unreachable machines. See https://github.com/psviderski/uncloud/issues/29.
 }
 
@@ -1311,6 +1529,7 @@ func TestServiceLifecycle(t *testing.T) {
 			Name: "container-spec-full",
 			Mode: api.ServiceModeGlobal,
 			Container: api.ContainerSpec{
+				// TODO: Add the latest implemented fields to this spec and update assertContainerMatchesSpec.
 				Command: []string{"sleep", "infinity"},
 				// Extra slashes is not a typo, it changes the spec but Linux ignores them and uses the default /pause.
 				Entrypoint: []string{"///pause"},
@@ -1320,6 +1539,14 @@ func TestServiceLifecycle(t *testing.T) {
 					"BOOL":  "true",
 					"":      "ignored",
 				},
+				Healthcheck: &api.HealthcheckSpec{
+					Test:          []string{"CMD-SHELL", "exit 0"},
+					Interval:      1*time.Minute + 30*time.Second,
+					Timeout:       10 * time.Second,
+					Retries:       5,
+					StartPeriod:   15 * time.Second,
+					StartInterval: 2 * time.Second,
+				},
 				Image: "portainer/pause:latest",
 				Init:  &init,
 				LogDriver: &api.LogDriver{

website/compose.yaml

@@ -20,3 +20,6 @@ services:
           log
       }
     scale: 2
+    x-machines:
+      - uc-prod-us2
+      - uc-prod-ap1

website/docs/2-getting-started/2-deploy-demo-app.md

@@ -4,6 +4,14 @@ In this guide, we'll deploy [Excalidraw](https://excalidraw.com) — a popular s
 Linux server. You'll learn the **basics of Uncloud** and see how simple it is to **run web apps** on your own
 infrastructure with secure internet access.
 
+:::info NOTE
+To give you a chance to play with Uncloud without even leaving your browser or needing your own servers, we're providing interactive tutorials and playgrounds on the [iximiuz Labs](https://labs.iximiuz.com/) platform.
+
+You can follow [this tutorial](https://labs.iximiuz.com/tutorials/uncloud-create-cluster-ebebf72b) which walks you through creating a new cluster with two machines and then deploying a simple web service to it.
+
+You can also launch the [Uncloud playground](https://labs.iximiuz.com/playgrounds/uncloud-cluster-64523f7c) where you can play with an already initialized Uncloud cluster.
+:::
+
 ## Prerequisites
 
 Before you begin, you'll need:

website/docs/3-concepts/1-ingress/1-overview.md

@@ -10,7 +10,7 @@ with [Let's Encrypt](https://letsencrypt.org/), and route requests to your servi
 ## How it works
 
 By default, Caddy runs as a global service `caddy` on every machine in your cluster, listening on the host ports 80
-(HTTP) and 443 (HTTPS).
+(HTTP), 443 (HTTPS), and 443/UDP (HTTP/3).
 
 It's deployed during cluster initialisation (`uc machine init`) unless you use the `--no-caddy` flag.
 See [Managing Caddy](3-managing-caddy.md) for deployment and customisation instructions.

website/docs/3-concepts/1-ingress/2-publishing-services.md

@@ -197,8 +197,9 @@ debugging and verifying your `x-caddy` configs.
 Example output:
 
 ```caddyfile
-# This file is autogenerated by Uncloud based on the configuration of running services.
-# Do not edit manually. Any manual changes will be overwritten on the next update.
+# Caddyfile autogenerated by Uncloud (DO NOT EDIT): 2025-12-20T22:43:56Z
+# Automatically updated on service or health status changes.
+# Docs: https://uncloud.run/docs/concepts/ingress/overview
 
 # User-defined global config from service 'caddy'.
 *.example.com {

website/docs/3-concepts/1-ingress/3-managing-caddy.md

@@ -94,6 +94,7 @@ services:
     x-ports:
       - 80:80@host
       - 443:443@host
+      - 443:443/udp@host
     x-caddy: Caddyfile
     deploy:
       mode: global
@@ -138,7 +139,8 @@ internal.example.com {
 :::info note
 
 The specified `command`, `environment`, `volumes`, and `x-ports` properties are essential for Caddy to function
-correctly in the Uncloud cluster.
+correctly in the Uncloud cluster. Do not change the source paths of the volume mounts as the Uncloud daemon relies on
+them to communicate with Caddy and update its configuration.
 
 :::
 
@@ -160,8 +162,9 @@ uc caddy config
 Example output:
 
 ```caddyfile
-# This file is autogenerated by Uncloud based on the configuration of running services.
-# Do not edit manually. Any manual changes will be overwritten on the next update.
+# Caddyfile autogenerated by Uncloud (DO NOT EDIT): 2025-12-22T10:30:12Z
+# Automatically updated on service or health status changes.
+# Docs: https://uncloud.run/docs/concepts/ingress/overview
 
 # User-defined global config from service 'caddy'.
 # Global options.

website/docs/4-guides/1-deployments/2-deploy-specific-machines.md

@@ -78,7 +78,7 @@ See [Push local images to cluster machines](1-deploy-app.md#push-local-images-to
 
 ## See also
 
-- [Deploy an app](1-deploy-app.md): Deploy from source code or prebuilt images
+- [Deploy an app](1-deploy-app.md): Build and deploy from source code or prebuilt images
 - [Deploy a global service](3-deploy-global-services.md): Deploy one service replica on each cluster machine
 - [Compose support matrix](../../8-compose-file-reference/1-support-matrix.md): Supported Compose features and Uncloud
   extensions

website/docs/4-guides/1-deployments/4-rolling-deployments.md

@@ -0,0 +1,173 @@
+# Rolling deployments
+
+How `uc deploy` updates your services without downtime and automatically rolls back on failure.
+
+Uncloud uses a rolling deployment to update your service by replacing its containers **one at a time**. Before moving on
+to the next container, Uncloud waits for the new one to pass [health monitoring](#health-monitoring). If it fails to
+become healthy, Uncloud stops the deployment and rolls back that container to the old one. This keeps your service
+available throughout the update.
+
+For a service with three replicas and the default `start-first` [update order](#update-order), the deployment looks like
+this:
+
+1. Start new container #1, wait until healthy
+2. Stop and remove old container #1
+3. Start new container #2, wait until healthy
+4. Stop and remove old container #2
+5. Start new container #3, wait until healthy
+6. Stop and remove old container #3
+
+At every step, at least three containers are serving traffic.
+
+## Update order
+
+The **update order** controls whether Uncloud starts the new container before or after stopping the old one.
+
+| Order         | What happens                                                                | Best for                            |
+|---------------|-----------------------------------------------------------------------------|-------------------------------------|
+| `start-first` | Start new container, then stop old<br/>(running containers briefly overlap) | Stateless services (web apps, APIs) |
+| `stop-first`  | Stop old container, then start new                                          | Stateful services (databases)       |
+
+The default is `start-first` so there's **no downtime**. But it automatically switches to `stop-first` in two cases:
+
+- **Host port conflicts**: the old container must free the port before the new one can bind to it.
+- **Single-replica service with a volume**: two containers simultaneously writing to the same volume can
+  **corrupt data**, so Uncloud stops the old container first to prevent this.
+
+`stop-first` can cause a **brief downtime** while the old container stops and the new one starts in these cases. The
+deployment plan printed by `uc deploy` indicates which containers will be replaced with `stop-first`.
+
+A multiple-replica service with a volume doesn't automatically switch to `stop-first` as Uncloud assumes that the
+concurrent access is desired and safe. Host path and tmpfs mounts don't trigger the switch either.
+
+### Override update order
+
+You can override the update order with `deploy.update_config.order`:
+
+```yaml title="compose.yaml"
+services:
+  app:
+    image: myapp
+    volumes:
+      - data:/data
+    deploy:
+      update_config:
+        order: start-first
+
+volumes:
+  data:
+```
+
+This single-replica service uses a volume, so Uncloud would normally use `stop-first`. Setting `order: start-first`
+overrides that.
+
+This is useful if your app handles concurrent access to data safely and you want to avoid downtime. For example, the app
+uses an SQLite database in WAL mode on the volume.
+
+## Health monitoring
+
+After starting each new container, Uncloud **monitors** it for failures for **5 seconds** to make sure it keeps running
+and not crashing. If it keeps restarting after this period, the deployment fails and Uncloud
+[rolls back](#rollback-on-failure) that container to the old one.
+
+This is a safeguard to prevent you from deploying broken code or misconfiguration that would cause downtime. 5 seconds
+is typically enough for a process in a container to initialise all its dependencies and start.
+
+You can change the monitoring period for a service with `deploy.update_config.monitor`. For example, increase it if your
+app takes longer to start or if you want to give it more time to recover from transient errors on startup.
+
+Set it to `0s` to skip monitoring entirely if you are confident the new containers will start correctly and want to
+speed up the deployment.
+
+```yaml title="compose.yaml"
+services:
+  app:
+    image: myapp
+    deploy:
+      update_config:
+        # Specified as duration: 500ms, 20s, 1m30s, 0s (skip)
+        monitor: 10s
+```
+
+You can also change the default monitoring period (`5s`) for all services globally with an environment variable
+`UNCLOUD_HEALTH_MONITOR_PERIOD`:
+
+```shell
+export UNCLOUD_HEALTH_MONITOR_PERIOD=10s
+
+# or skip monitoring for all services
+export UNCLOUD_HEALTH_MONITOR_PERIOD=0s
+```
+
+`deploy.update_config.monitor` overrides the global default for each service.
+
+### Health checks
+
+If your container has a [`healthcheck`](https://github.com/compose-spec/compose-spec/blob/main/spec.md#healthcheck)
+configured, Uncloud also checks its health status during and after the monitoring period.
+
+If the container becomes `healthy` before the monitoring period ends, the deployment succeeds early and moves on to the
+next container. If the container is `unhealthy` after the monitoring period, Uncloud
+[rolls it back](#rollback-on-failure) and fails the deployment. Transient `unhealthy` states during the monitoring
+period are tolerated to give the container time to recover from startup issues.
+
+To make deployments **safer** and **faster**, it's recommended to configure a health check that can quickly notify
+Uncloud when containers start successfully and become ready to serve traffic. You can configure it with
+[`healthcheck`](https://github.com/compose-spec/compose-spec/blob/main/spec.md#healthcheck) in your Compose file or
+[`HEALTHCHECK`](https://docs.docker.com/reference/dockerfile#healthcheck) in your image `Dockerfile`:
+
+```yaml title="compose.yaml"
+services:
+  app:
+    image: myapp
+    healthcheck:
+      test: curl -f http://localhost:8000/health
+      interval: 5s
+      retries: 3
+      start_period: 10s
+      start_interval: 1s
+```
+
+:::info important
+
+If a health check fails after the deployment, Uncloud automatically removes the unhealthy container from the
+[Caddy](../../3-concepts/1-ingress/1-overview.md) configuration to prevent routing traffic to that container. But it
+doesn't automatically restart or roll it back.
+
+Uncloud automatically adds it back to Caddy when it recovers and becomes healthy again. You can inspect the health
+status of your containers with [`uc ps`](../../9-cli-reference/uc_ps.md) or
+[`uc inspect`](../../9-cli-reference/uc_inspect.md) and check their logs with
+[`uc logs`](../../9-cli-reference/uc_logs.md).
+
+:::
+
+### Skip health monitoring
+
+To skip health monitoring for **faster emergency deployments**, use `uc deploy --skip-health`.
+
+:::warning
+
+`--skip-health` won't detect containers that crash on startup or become unhealthy so won't roll them back or stop the
+deployment. Use this only for emergency deployments when you are confident the new containers will start correctly.
+
+:::
+
+## Rollback on failure
+
+If a new container fails health monitoring during a deployment, Uncloud stops it but keeps it around so you can inspect
+its state and logs. For `stop-first` order, Uncloud also restarts the old container. The deployment then stops and the
+remaining containers are left untouched.
+
+For example, if the first container in a rolling update succeeds but the second one fails, the first replacement stays
+in place.
+
+## Retry after failure
+
+You can retry the deployment by running `uc deploy` again. Uncloud will skip the successfully deployed containers if the
+configuration hasn't changed and only redeploy the remaining ones.
+
+## See also
+
+- [Deploy an app](1-deploy-app.md): Build and deploy from source code or pre-built images
+- [Compose support matrix](../../8-compose-file-reference/1-support-matrix.md): Supported Compose features and Uncloud
+  extensions

website/docs/8-compose-file-reference/1-support-matrix.md

@@ -3,63 +3,68 @@
 Uncloud supports a subset of the [Compose specification](https://compose-spec.io/) with some extensions and limitations.
 The following table shows the support status for main Compose features:
 
-| Feature            | Support Status     | Notes                                                                                 |
-|--------------------|--------------------|---------------------------------------------------------------------------------------|
-| **Services**       |                    |                                                                                       |
-| `build`            | ⚠️ Limited         | Build context and Dockerfile                                                          |
-| `command`          | ✅ Supported        | Override container command                                                            |
-| `configs`          | ✅ Supported        | File-based and inline configs                                                         |
-| `cpus`             | ✅ Supported        | CPU limit                                                                             |
-| `depends_on`       | ⚠️ Limited         | Services deployed in order but conditions not checked                                 |
-| `dns`              | ❌ Not supported    | Built-in service discovery                                                            |
-| `dns_search`       | ❌ Not supported    | Built-in service discovery                                                            |
-| `entrypoint`       | ✅ Supported        | Override container entrypoint                                                         |
-| `env_file`         | ✅ Supported        | Environment file                                                                      |
-| `environment`      | ✅ Supported        | Environment variables                                                                 |
-| `gpus`             | ✅ Supported        | GPU device access                                                                     |
-| `image`            | ✅ Supported        | Container image specification                                                         |
-| `init`             | ✅ Supported        | Run init process in container                                                         |
-| `labels`           | ❌ Not supported    |                                                                                       |
-| `links`            | ❌ Not supported    | Use service names for communication                                                   |
-| `logging`          | ✅ Supported        | Defaults to [local](https://docs.docker.com/engine/logging/drivers/local/) log driver |
-| `mem_limit`        | ✅ Supported        | Memory limit                                                                          |
-| `mem_reservation`  | ✅ Supported        | Memory reservation                                                                    |
-| `mem_swappiness`   | ❌ Not supported    |                                                                                       |
-| `memswap_limit`    | ❌ Not supported    |                                                                                       |
-| `networks`         | ❌ Not supported    | All containers share cluster network                                                  |
-| `ports`            | ⚠️ Limited         | `mode: host` only, use `x-ports` for HTTP/HTTPS                                       |
-| `privileged`       | ✅ Supported        | Run containers in privileged mode                                                     |
-| `pull_policy`      | ✅ Supported        | `always`, `missing`, `never`                                                          |
-| `secrets`          | ❌ Not supported    | Use configs or environment variables                                                  |
-| `security_opt`     | ❌ Not supported    |                                                                                       |
-| `storage_opt`      | ❌ Not supported    |                                                                                       |
-| `user`             | ✅ Supported        | Set container user                                                                    |
-| `volumes`          | ✅ Supported        | Named volumes, bind mounts, tmpfs                                                     |
-| **Deploy**         |                    |                                                                                       |
-| `labels`           | ❌ Not supported    |                                                                                       |
-| `mode`             | ✅ Supported        | Either `global` or `replicated`                                                       |
-| `placement`        | ❌ Not supported    | Use `x-machines` extension                                                            |
-| `replicas`         | ✅ Supported        | Number of container replicas                                                          |
-| `resources`        | ⚠️ Limited         | CPU, memory limits and device reservations                                            |
-| `restart_policy`   | ❌ Not supported    | Defaults to `unless-stopped`                                                          |
-| `rollback_config`  | ❌ Not supported    | See [#151](https://github.com/psviderski/uncloud/issues/151)                          |
-| `update_config`    | ❌ Not supported    | See [#151](https://github.com/psviderski/uncloud/issues/151)                          |
-| **Volumes**        |                    |                                                                                       |
-| Named volumes      | ✅ Supported        | Docker volumes                                                                        |
-| Bind mounts        | ✅ Supported        | Host path binding                                                                     |
-| Tmpfs mounts       | ✅ Supported        | In-memory filesystems                                                                 |
-| Volume labels      | ✅ Supported        | Custom labels                                                                         |
-| External volumes   | ✅ Supported        | Must exist before deployment                                                          |
-| Volume drivers     | ⚠️ Limited         | Local driver only                                                                     |
-| **Configs**        |                    |                                                                                       |
-| File-based configs | ✅ Supported        | Read from file                                                                        |
-| Inline configs     | ✅ Supported        | Defined in compose file                                                               |
-| External configs   | ❌ Not supported    | Not supported                                                                         |
-| Short syntax       | ❌ Not supported    | Use long syntax only                                                                  |
-| **Extensions**     |                    |                                                                                       |
-| `x-caddy`          | ✅ Uncloud-specific | Custom Caddy configuration                                                            |
-| `x-machines`       | ✅ Uncloud-specific | Machine placement constraints                                                         |
-| `x-ports`          | ✅ Uncloud-specific | Service port publishing                                                               |
+| Feature            | Support Status     | Notes                                                                                                          |
+|--------------------|--------------------|----------------------------------------------------------------------------------------------------------------|
+| **Services**       |                    |                                                                                                                |
+| `build`            | ✅ Supported        | Build context and Dockerfile                                                                                   |
+| `cap_add`          | ✅ Supported        | Additional kernel [capabilities](https://man7.org/linux/man-pages/man7/capabilities.7.html)                    |
+| `cap_drop`         | ✅ Supported        | Which kernel [capabilities](https://man7.org/linux/man-pages/man7/capabilities.7.html) to drop                 |
+| `command`          | ✅ Supported        | Override container command                                                                                     |
+| `configs`          | ✅ Supported        | File-based and inline configs                                                                                  |
+| `cpus`             | ✅ Supported        | CPU limit                                                                                                      |
+| `depends_on`       | ⚠️ Limited         | Services deployed in order but conditions not checked                                                          |
+| `devices`          | ✅ Supported        | Device mappings                                                                                                |
+| `dns`              | ❌ Not supported    | Built-in service discovery                                                                                     |
+| `dns_search`       | ❌ Not supported    | Built-in service discovery                                                                                     |
+| `entrypoint`       | ✅ Supported        | Override container entrypoint                                                                                  |
+| `env_file`         | ✅ Supported        | Environment file                                                                                               |
+| `environment`      | ✅ Supported        | Environment variables                                                                                          |
+| `gpus`             | ✅ Supported        | GPU device access                                                                                              |
+| `healthcheck`      | ✅ Supported        | Health check configuration                                                                                     |
+| `image`            | ✅ Supported        | Container image specification                                                                                  |
+| `init`             | ✅ Supported        | Run init process in container                                                                                  |
+| `labels`           | ❌ Not supported    |                                                                                                                |
+| `links`            | ❌ Not supported    | Use service names for communication                                                                            |
+| `logging`          | ✅ Supported        | Defaults to [local](https://docs.docker.com/engine/logging/drivers/local/) log driver                          |
+| `mem_limit`        | ✅ Supported        | Memory limit                                                                                                   |
+| `mem_reservation`  | ✅ Supported        | Memory reservation                                                                                             |
+| `mem_swappiness`   | ❌ Not supported    |                                                                                                                |
+| `memswap_limit`    | ❌ Not supported    |                                                                                                                |
+| `networks`         | ❌ Not supported    | All containers share cluster network                                                                           |
+| `ports`            | ⚠️ Limited         | `mode: host` only, use [`x-ports`](#x-ports) for HTTP/HTTPS                                                    |
+| `privileged`       | ✅ Supported        | Run containers in privileged mode                                                                              |
+| `pull_policy`      | ✅ Supported        | `always`, `missing`, `never`                                                                                   |
+| `secrets`          | ❌ Not supported    | Use configs or environment variables                                                                           |
+| `security_opt`     | ❌ Not supported    |                                                                                                                |
+| `storage_opt`      | ❌ Not supported    |                                                                                                                |
+| `sysctls`          | ✅ Supported        | Namespaced kernel parameters                                                                                   |
+| `user`             | ✅ Supported        | Set container user                                                                                             |
+| `volumes`          | ✅ Supported        | Named volumes, bind mounts, tmpfs                                                                              |
+| **Deploy**         |                    |                                                                                                                |
+| `labels`           | ❌ Not supported    |                                                                                                                |
+| `mode`             | ✅ Supported        | Either `global` or `replicated`                                                                                |
+| `placement`        | ❌ Not supported    | Use [`x-machines`](#x-machines) extension                                                                      |
+| `replicas`         | ✅ Supported        | Number of container replicas                                                                                   |
+| `resources`        | ⚠️ Limited         | CPU, memory limits and device reservations                                                                     |
+| `restart_policy`   | ❌ Not supported    | Defaults to `unless-stopped`                                                                                   |
+| `rollback_config`  | ❌ Not supported    | See [#151](https://github.com/psviderski/uncloud/issues/151)                                                   |
+| `update_config`    | ⚠️ Limited         | `order` and `monitor` supported. See [rolling deployments](../4-guides/1-deployments/4-rolling-deployments.md) |
+| **Volumes**        |                    |                                                                                                                |
+| Named volumes      | ✅ Supported        | Docker volumes                                                                                                 |
+| Bind mounts        | ✅ Supported        | Host path binding                                                                                              |
+| Tmpfs mounts       | ✅ Supported        | In-memory filesystems                                                                                          |
+| Volume labels      | ✅ Supported        | Custom labels                                                                                                  |
+| External volumes   | ✅ Supported        | Must exist before deployment                                                                                   |
+| Volume drivers     | ⚠️ Limited         | Local driver only                                                                                              |
+| **Configs**        |                    |                                                                                                                |
+| File-based configs | ✅ Supported        | Read from file                                                                                                 |
+| Inline configs     | ✅ Supported        | Defined in compose file                                                                                        |
+| External configs   | ❌ Not supported    | Not supported                                                                                                  |
+| Short syntax       | ❌ Not supported    | Use long syntax only                                                                                           |
+| **Extensions**     |                    |                                                                                                                |
+| `x-caddy`          | ✅ Uncloud-specific | Custom Caddy configuration                                                                                     |
+| `x-machines`       | ✅ Uncloud-specific | Machine placement constraints                                                                                  |
+| `x-ports`          | ✅ Uncloud-specific | Service port publishing                                                                                        |
 
 ### Legend
 

website/docs/8-compose-file-reference/2-image-tag-template.md

@@ -14,8 +14,8 @@ Git repository state. You can customise the image name and tag format for the bu
 If you **don't specify** an `image` attribute for a service with a `build` section, Uncloud uses the following Go
 template for tagging the built image:
 
-```go
-{{.Project}}/{{.Service}}:{{if.Git.IsRepo}}{{gitdate "2006-01-02-150405"}}.{{gitsha 7}}{{if.Git.IsDirty}}.dirty{{end}}{{else}}{{date "2006-01-02-150405"}}{{end}}
+```
+{{.Project}}/{{.Service}}:{{if .Git.IsRepo}}{{gitdate "2006-01-02-150405"}}.{{gitsha 7}}{{if .Git.IsDirty}}.dirty{{end}}{{else}}{{date "2006-01-02-150405"}}{{end}}
 ```
 
 ```yaml title="compose.yaml"
@@ -92,8 +92,7 @@ image: myapp:{{date "20060102-150405" "Local"}}   # → myapp:20251031-220651
 
 ### Date format reference
 
-Go uses a reference time (`Mon Jan 2 15:04:05 MST 2006`) for formatting. Replace reference components with desired
-format:
+Go uses a reference time `Mon Jan 2 15:04:05 MST 2006` for formatting. Replace reference components with desired format:
 
 | Component | Reference | Example     |
 |-----------|-----------|-------------|

website/docs/9-cli-reference/uc.md

@@ -19,17 +19,20 @@ A CLI tool for managing Uncloud resources such as machines, services, and volume
 * [uc ctx](uc_ctx.md)	 - Switch between different cluster contexts. Contains subcommands to manage contexts.
 * [uc deploy](uc_deploy.md)	 - Deploy services from a Compose file.
 * [uc dns](uc_dns.md)	 - Manage cluster domain in Uncloud DNS.
-* [uc exec](uc_exec.md)	 - Execute a command in a running service container
+* [uc exec](uc_exec.md)	 - Execute a command in a running service container.
 * [uc image](uc_image.md)	 - Manage images on machines in the cluster.
 * [uc images](uc_images.md)	 - List images on machines in the cluster.
 * [uc inspect](uc_inspect.md)	 - Display detailed information on a service.
 * [uc logs](uc_logs.md)	 - View service logs.
 * [uc ls](uc_ls.md)	 - List services.
 * [uc machine](uc_machine.md)	 - Manage machines in the cluster.
-* [uc ps](uc_ps.md)	 - List all service containers in the cluster
+* [uc ps](uc_ps.md)	 - List all service containers.
 * [uc rm](uc_rm.md)	 - Remove one or more services.
 * [uc run](uc_run.md)	 - Run a service.
 * [uc scale](uc_scale.md)	 - Scale a replicated service by changing the number of replicas.
 * [uc service](uc_service.md)	 - Manage services in the cluster.
+* [uc start](uc_start.md)	 - Start one or more services.
+* [uc stop](uc_stop.md)	 - Stop one or more services.
 * [uc volume](uc_volume.md)	 - Manage volumes in the cluster.
+* [uc wg](uc_wg.md)	 - Inspect WireGuard network
 

website/docs/9-cli-reference/uc_deploy.md

@@ -18,6 +18,8 @@ uc deploy [FLAGS] [SERVICE...] [flags]
       --no-cache                Do not use cache when building images.
   -p, --profile strings         One or more Compose profiles to enable.
       --recreate                Recreate containers even if their configuration and image haven't changed.
+      --skip-health             Skip the monitoring period and health checks after starting new containers. Useful for faster emergency deployments.
+                                Warning: This may cause downtime if new containers fail to start properly.
   -y, --yes                     Auto-confirm deployment plan. Should be explicitly set when running non-interactively,
                                 e.g., in CI/CD pipelines. [$UNCLOUD_AUTO_CONFIRM]
 ```

website/docs/9-cli-reference/uc_exec.md

@@ -1,6 +1,6 @@
 # uc exec
 
-Execute a command in a running service container
+Execute a command in a running service container.
 
 ## Synopsis
 

website/docs/9-cli-reference/uc_machine_add.md

@@ -24,6 +24,8 @@ uc machine add [USER@]HOST[:PORT] [flags]
       --public-ip string   Public IP address of the machine for ingress configuration. Use 'auto' for automatic detection, blank '' or 'none' to disable ingress on this machine, or specify an IP address. (default "auto")
   -i, --ssh-key string     Path to SSH private key for remote login (if not already added to SSH agent). (default "~/.ssh/id_ed25519")
       --version string     Version of the Uncloud daemon to install on the machine. (default "latest")
+  -y, --yes                Auto-confirm prompts (e.g., resetting an already initialised machine).
+                           Should be explicitly set when running non-interactively, e.g., in CI/CD pipelines. [$UNCLOUD_AUTO_CONFIRM]
 ```
 
 ## Options inherited from parent commands

website/docs/9-cli-reference/uc_machine_init.md

@@ -12,7 +12,7 @@ Connection methods:
   ssh+cli://user@host   - Use system SSH command (supports ProxyJump, SSH config)
 
 ```
-uc machine init [USER@HOST:PORT] [flags]
+uc machine init [schema://]USER@HOST[:PORT] [flags]
 ```
 
 ## Examples
@@ -46,6 +46,8 @@ uc machine init [USER@HOST:PORT] [flags]
       --public-ip string      Public IP address of the machine for ingress configuration. Use 'auto' for automatic detection, blank '' or 'none' to disable ingress on this machine, or specify an IP address. (default "auto")
   -i, --ssh-key string        Path to SSH private key for remote login (if not already added to SSH agent). (default "~/.ssh/id_ed25519")
       --version string        Version of the Uncloud daemon to install on the machine. (default "latest")
+  -y, --yes                   Auto-confirm prompts (e.g., resetting an already initialised machine).
+                              Should be explicitly set when running non-interactively, e.g., in CI/CD pipelines. [$UNCLOUD_AUTO_CONFIRM]
 ```
 
 ## Options inherited from parent commands

website/docs/9-cli-reference/uc_ps.md

@@ -1,6 +1,6 @@
 # uc ps
 
-List all service containers in the cluster
+List all service containers.
 
 ## Synopsis
 
@@ -17,7 +17,7 @@ uc ps [flags]
 
 ```
   -h, --help          help for ps
-  -s, --sort string   Sort containers by 'service', 'machine' or 'health' (default "service")
+  -s, --sort string   Sort containers by 'service', 'machine', or 'health'. (default "service")
 ```
 
 ## Options inherited from parent commands