Run guest updates outside agent sandbox

agent_actions.go

@@ -8,7 +8,6 @@ import (
 	"io"
 	"net"
 	"net/http"
-	"os"
 	"os/exec"
 	"path/filepath"
 	"regexp"
@@ -72,7 +71,7 @@ func (s *Store) QueueAgentAction(agentID, action, target string) (AgentAction, e
 				}
 			}
 		}
-	case "updates-refresh", "system-update":
+	case "updates-refresh", "system-update", "system-reboot":
 		valid = target == ""
 	}
 	if !valid {
@@ -172,6 +171,8 @@ func executeAgentCommand(command AgentCommand) AgentActionResult {
 		output = removeAgentContainer(command.Target)
 	case "system-update":
 		output = updateAgentSystem()
+	case "system-reboot":
+		output = scheduleAgentReboot()
 	case "updates-refresh":
 		guestInventory.Lock()
 		guestInventory.value.CollectedAt = time.Time{}
@@ -210,25 +211,59 @@ func removeAgentContainer(target string) string {
 }
 
 func updateAgentSystem() string {
-	if output := runAgentCombinedCommand(3*time.Minute, "apt-get", "update"); strings.HasPrefix(output, "ERROR: ") {
-		return output
-	}
-	ctx, cancel := context.WithTimeout(context.Background(), 30*time.Minute)
-	defer cancel()
-	command := exec.CommandContext(ctx, "apt-get", "-y", "upgrade")
-	command.Env = append(os.Environ(), "DEBIAN_FRONTEND=noninteractive")
-	output, err := command.CombinedOutput()
-	message := strings.TrimSpace(string(output))
-	if len(message) > 3500 {
-		message = message[len(message)-3500:]
-	}
+	aptGet, err := exec.LookPath("apt-get")
 	if err != nil {
-		return "ERROR: " + err.Error() + ": " + message
+		return "ERROR: apt-get не найден; обновление поддерживается для Debian/Ubuntu"
+	}
+	if output := runPrivilegedTransient(5*time.Minute, "update-lists", aptGet, "update"); strings.HasPrefix(output, "ERROR: ") {
+		return explainSystemUpdateError(output)
+	}
+	message := runPrivilegedTransient(30*time.Minute, "upgrade", aptGet, "-y", "upgrade")
+	if strings.HasPrefix(message, "ERROR: ") {
+		return explainSystemUpdateError(message)
 	}
 	guestInventory.Lock()
 	guestInventory.value.CollectedAt = time.Time{}
 	guestInventory.Unlock()
-	return firstNonEmpty(message, "Обновления системы установлены")
+	return "Обновления системы установлены; список пакетов будет обновлён в следующем отчёте агента"
+}
+
+func explainSystemUpdateError(message string) string {
+	if strings.Contains(strings.ToLower(message), "read-only file system") {
+		return "ERROR: файловая система агента доступна только для чтения. Обновите Dashboard и агент до v0.19.2 или новее, затем повторите операцию."
+	}
+	if len(message) > 1800 {
+		message = message[len(message)-1800:]
+	}
+	return message
+}
+
+func runPrivilegedTransient(timeout time.Duration, suffix, name string, args ...string) string {
+	systemdRun, err := exec.LookPath("systemd-run")
+	if err != nil {
+		return "ERROR: systemd-run не найден; невозможно безопасно выйти из read-only sandbox агента"
+	}
+	unit := fmt.Sprintf("proxmox-dashboard-%s-%d", suffix, time.Now().UnixNano())
+	commandArgs := []string{"--quiet", "--wait", "--collect", "--pipe", "--unit=" + unit, "--setenv=DEBIAN_FRONTEND=noninteractive", name}
+	commandArgs = append(commandArgs, args...)
+	return runAgentCombinedCommand(timeout, systemdRun, commandArgs...)
+}
+
+func scheduleAgentReboot() string {
+	systemdRun, err := exec.LookPath("systemd-run")
+	if err != nil {
+		return "ERROR: systemd-run не найден"
+	}
+	systemctl, err := exec.LookPath("systemctl")
+	if err != nil {
+		return "ERROR: systemctl не найден"
+	}
+	unit := fmt.Sprintf("proxmox-dashboard-reboot-%d", time.Now().UnixNano())
+	output := runAgentCombinedCommand(15*time.Second, systemdRun, "--quiet", "--collect", "--unit="+unit, "--on-active=20s", systemctl, "reboot")
+	if strings.HasPrefix(output, "ERROR: ") {
+		return output
+	}
+	return "Перезагрузка запланирована через 20 секунд; кратковременный offline агента ожидаем"
 }
 
 func updateAgentContainer(target string, recreate bool) string {

agent_actions_test.go

@@ -2,6 +2,7 @@ package main
 
 import (
 	"encoding/json"
+	"strings"
 	"testing"
 	"time"
 )
@@ -42,6 +43,12 @@ func TestAgentActionAllowlistAndLifecycle(t *testing.T) {
 	if err != nil || len(items) != 3 || items[0].Status != "completed" {
 		t.Fatalf("items=%#v err=%v", items, err)
 	}
+	if _, err = store.QueueAgentAction("a", "system-reboot", ""); err != nil {
+		t.Fatalf("system reboot rejected: %v", err)
+	}
+	if _, err = store.QueueAgentAction("a", "system-reboot", "now"); err == nil {
+		t.Fatal("system reboot with unexpected target accepted")
+	}
 }
 
 func TestManualServiceLinkGroupsOfflineAlerts(t *testing.T) {
@@ -61,3 +68,10 @@ func TestManualServiceLinkGroupsOfflineAlerts(t *testing.T) {
 		t.Fatalf("group alert missing: %#v", grouped)
 	}
 }
+
+func TestExplainReadOnlySystemUpdateError(t *testing.T) {
+	message := explainSystemUpdateError("ERROR: apt failed: Read-only file system")
+	if !strings.Contains(message, "v0.19.2") {
+		t.Fatalf("read-only failure is not actionable: %s", message)
+	}
+}