feat: agent control actions with self-protection

agent/internal/workloads/control.go

@@ -0,0 +1,105 @@
+package workloads
+
+import (
+	"context"
+	"errors"
+	"fmt"
+	"os"
+	"os/exec"
+	"regexp"
+	"strings"
+	"time"
+)
+
+// ErrProtected is returned for a workload the agent will not act on.
+var ErrProtected = errors.New("workload is protected")
+
+// AgentUnit is the systemd unit this agent runs as.
+const AgentUnit = "vantage-agent.service"
+
+// controlTimeout bounds a stop that may never finish on its own. `docker stop`
+// waits on a container that may ignore SIGTERM, and `systemctl stop` on a unit
+// with a long TimeoutStopSec blocks for exactly as long as that says. A
+// timeout must return a real error rather than an ack implying success.
+const controlTimeout = 90 * time.Second
+
+// ownContainerID is read once: the container this agent runs in, if any.
+var ownContainerID = detectOwnContainer()
+
+var cgroupContainerRe = regexp.MustCompile(`[0-9a-f]{64}`)
+
+// detectOwnContainer returns this process's container ID, or "" on a host
+// install. The agent is normally a systemd service, so "" is the common case;
+// this exists so containerising it later cannot silently remove the guard.
+func detectOwnContainer() string {
+	b, err := os.ReadFile("/proc/self/cgroup")
+	if err != nil {
+		return ""
+	}
+	if m := cgroupContainerRe.FindString(string(b)); m != "" {
+		return m
+	}
+	return ""
+}
+
+// isProtected reports whether the agent refuses to act on this workload.
+//
+// The refusal lives here, in the agent, and not in the control plane. As with
+// the console relay hardcoding 127.0.0.1 agent-side: the control plane may name
+// a target, but the agent decides what it will do to itself. A server-side
+// denylist alone would be bypassed by the next dispatch path someone adds.
+func isProtected(kind, id, name string) bool {
+	if kind == "unit" {
+		return id == AgentUnit || name == strings.TrimSuffix(AgentUnit, ".service")
+	}
+	if ownContainerID == "" {
+		return false
+	}
+	// Container IDs are commonly abbreviated to 12 characters; compare on the
+	// shorter of the two so a short id still matches a full one.
+	return strings.HasPrefix(ownContainerID, id) || strings.HasPrefix(id, ownContainerID)
+}
+
+// markProtected stamps the flag onto a collected list so the UI can render the
+// action disabled with a reason.
+func markProtected(wls []Workload) {
+	for i := range wls {
+		wls[i].Protected = isProtected(wls[i].Kind, wls[i].ID, wls[i].Name)
+	}
+}
+
+// Control starts, stops or restarts a workload.
+func Control(ctx context.Context, kind, id, action string) error {
+	switch action {
+	case "start", "stop", "restart":
+	default:
+		return fmt.Errorf("unknown action %q", action)
+	}
+
+	// Checked before anything else happens, and checked here rather than only
+	// on the server. See isProtected.
+	if isProtected(kind, id, strings.TrimSuffix(id, ".service")) {
+		return fmt.Errorf("%w: %s", ErrProtected, id)
+	}
+
+	ctx, cancel := context.WithTimeout(ctx, controlTimeout)
+	defer cancel()
+
+	var cmd *exec.Cmd
+	switch kind {
+	case "container":
+		cmd = exec.CommandContext(ctx, "docker", action, id)
+	case "unit":
+		cmd = exec.CommandContext(ctx, "systemctl", action, id)
+	default:
+		return fmt.Errorf("unknown workload kind %q", kind)
+	}
+
+	if out, err := cmd.CombinedOutput(); err != nil {
+		if ctx.Err() == context.DeadlineExceeded {
+			return fmt.Errorf("%s %s timed out after %s", action, id, controlTimeout)
+		}
+		return fmt.Errorf("%s %s: %s", action, id, strings.TrimSpace(string(out)))
+	}
+	return nil
+}

agent/internal/workloads/workloads.go

@@ -37,10 +37,6 @@ func Collect(ctx context.Context) Result {
 	return r
 }
 
-// markProtected is a temporary stub; the real implementation lands with the
-// control layer in control.go.
-func markProtected(_ []Workload) {}
-
 // Hash fingerprints a workload set so an unchanged set never has to be sent.
 //
 // It sorts first: `docker ps` output ordering is not stable, and an