feat: agent enumerates systemd services

agent/internal/workloads/systemd.go

@@ -0,0 +1,94 @@
+package workloads
+
+import (
+	"context"
+	"os/exec"
+	"strings"
+	"time"
+)
+
+const systemdTimeout = 30 * time.Second
+
+// excludedPrefixes drops the platform's own units. A typical host carries 300+
+// units and systemd accounts for most of them; listing all of them buries the
+// ten anyone cares about.
+var excludedPrefixes = []string{"systemd-", "user@", "user-", "session-", "init.scope"}
+
+// collectSystemd enumerates services in two passes, because "running or
+// failed" and "enabled but stopped" are different questions — and an enabled
+// unit that is not running is exactly the one worth seeing.
+func collectSystemd(ctx context.Context) ([]Workload, bool, string) {
+	if _, err := exec.LookPath("systemctl"); err != nil {
+		return nil, false, ""
+	}
+
+	ctx, cancel := context.WithTimeout(ctx, systemdTimeout)
+	defer cancel()
+
+	// Column output rather than --output=json: the JSON flag needs systemd
+	// 246+, and this fleet includes older stable distributions. The columns
+	// have been stable considerably longer than the JSON has existed.
+	unitsOut, err := exec.CommandContext(ctx, "systemctl",
+		"list-units", "--type=service", "--state=running,failed",
+		"--no-legend", "--plain", "--no-pager").Output()
+	if err != nil {
+		return nil, false, "systemctl list-units failed: " + errText(err)
+	}
+
+	seen := map[string]bool{}
+	var wls []Workload
+
+	for _, line := range strings.Split(string(unitsOut), "\n") {
+		f := strings.Fields(line)
+		// UNIT LOAD ACTIVE SUB DESCRIPTION…
+		if len(f) < 4 {
+			continue
+		}
+		name := f[0]
+		if excluded(name) || seen[name] {
+			continue
+		}
+		seen[name] = true
+		wls = append(wls, Workload{
+			Kind:  "unit",
+			ID:    name,
+			Name:  strings.TrimSuffix(name, ".service"),
+			State: f[2], // ACTIVE: active | failed | activating | inactive
+		})
+	}
+
+	filesOut, err := exec.CommandContext(ctx, "systemctl",
+		"list-unit-files", "--type=service", "--state=enabled",
+		"--no-legend", "--plain", "--no-pager").Output()
+	if err == nil {
+		for _, line := range strings.Split(string(filesOut), "\n") {
+			f := strings.Fields(line)
+			// UNIT FILE  STATE  [PRESET]
+			if len(f) < 2 {
+				continue
+			}
+			name := f[0]
+			if excluded(name) || seen[name] {
+				continue
+			}
+			seen[name] = true
+			wls = append(wls, Workload{
+				Kind:  "unit",
+				ID:    name,
+				Name:  strings.TrimSuffix(name, ".service"),
+				State: "inactive", // enabled but not currently running
+			})
+		}
+	}
+
+	return wls, true, ""
+}
+
+func excluded(name string) bool {
+	for _, p := range excludedPrefixes {
+		if strings.HasPrefix(name, p) {
+			return true
+		}
+	}
+	return false
+}

agent/internal/workloads/workloads.go

@@ -0,0 +1,68 @@
+package workloads
+
+import (
+	"context"
+	"crypto/sha256"
+	"encoding/hex"
+	"runtime"
+	"sort"
+	"strconv"
+	"strings"
+)
+
+// Result is one collection pass.
+type Result struct {
+	Workloads    []Workload
+	DockerOK     bool
+	DockerError  string
+	SystemdOK    bool
+	SystemdError string
+}
+
+// Collect enumerates every workload on this host. Linux only.
+func Collect(ctx context.Context) Result {
+	if runtime.GOOS != "linux" {
+		return Result{}
+	}
+
+	var r Result
+	containers, dockerOK, dockerErr := collectDocker(ctx)
+	units, systemdOK, systemdErr := collectSystemd(ctx)
+
+	r.DockerOK, r.DockerError = dockerOK, dockerErr
+	r.SystemdOK, r.SystemdError = systemdOK, systemdErr
+	r.Workloads = append(append([]Workload{}, containers...), units...)
+
+	markProtected(r.Workloads)
+	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
+// ordering-sensitive hash would resend the full list every 60 seconds forever
+// — a cost visible only as traffic.
+//
+// StartedAt is deliberately excluded: it does not change while a container
+// runs, and including it would add nothing. Restarts IS included, because a
+// container cycling is exactly the change worth reporting.
+func Hash(wls []Workload) string {
+	lines := make([]string, 0, len(wls))
+	for _, w := range wls {
+		lines = append(lines, strings.Join([]string{
+			w.Kind, w.ID, w.Name, w.State, w.Health, w.Image, w.Stack,
+			strconv.Itoa(w.Restarts),
+		}, "\x00"))
+	}
+	sort.Strings(lines)
+	h := sha256.New()
+	for _, l := range lines {
+		h.Write([]byte(l))
+		h.Write([]byte("\n"))
+	}
+	return hex.EncodeToString(h.Sum(nil))
+}