feat: Collect Windows services as workloads

2026-08-13 11:52:08 +00:00
parent c3075fd743
commit d764eb2c6f
3 changed files with 258 additions and 0 deletions
@@ -0,0 +1,42 @@
+package workloads
+
+import (
+	"context"
+	"os"
+	"time"
+
+	"gitea.hostxtra.co.uk/mrhid6/vantage/agent/internal/winexec"
+)
+
+const servicesTimeout = 60 * time.Second
+
+const servicesScript = `
+$ErrorActionPreference = 'Stop'
+$svcs = Get-CimInstance Win32_Service |
+  Select-Object Name,DisplayName,State,StartMode,PathName,ExitCode
+ConvertTo-Json -InputObject @($svcs) -Depth 3 -Compress
+`
+
+// collectUnits enumerates Windows services. The bool and string it returns are
+// the same SystemdOK / SystemdError pair the Linux collector fills: the wire
+// shape is shared, and the UI words it per platform.
+func collectUnits(ctx context.Context) ([]Workload, bool, string) {
+	ctx, cancel := context.WithTimeout(ctx, servicesTimeout)
+	defer cancel()
+
+	out, err := winexec.Run(ctx, servicesScript)
+	if err != nil {
+		return nil, false, "Win32_Service query failed: " + err.Error()
+	}
+
+	systemRoot := os.Getenv("SystemRoot")
+	if systemRoot == "" {
+		systemRoot = `C:\Windows`
+	}
+
+	wls, err := parseServices(out, systemRoot)
+	if err != nil {
+		return nil, false, "Win32_Service output could not be read: " + err.Error()
+	}
+	return wls, true, ""
+}
@@ -0,0 +1,117 @@
+package workloads
+
+import (
+	"encoding/json"
+	"strings"
+)
+
+// winService is one row of Get-CimInstance Win32_Service.
+//
+// Win32_Service rather than Get-Service: Get-Service exposes neither PathName
+// nor StartMode, and the filter below needs both.
+type winService struct {
+	Name        string `json:"Name"`
+	DisplayName string `json:"DisplayName"`
+	State       string `json:"State"`
+	StartMode   string `json:"StartMode"`
+	PathName    string `json:"PathName"`
+	ExitCode    int    `json:"ExitCode"`
+}
+
+// exitCodeNeverStarted is ERROR_SERVICE_NEVER_STARTED. A stopped service
+// carrying it has not failed — it has not run since boot — and painting that
+// red would cry wolf on every host.
+const exitCodeNeverStarted = 1077
+
+// servicePath extracts the executable from a Win32_Service PathName.
+//
+// A naive split on whitespace misfiles a substantial share of a real fleet:
+// `"C:\Program Files\X\x.exe" -service` is one path and one argument.
+func servicePath(pathName string) string {
+	s := strings.TrimSpace(pathName)
+	if s == "" {
+		return ""
+	}
+	if s[0] == '"' {
+		if end := strings.IndexByte(s[1:], '"'); end >= 0 {
+			return s[1 : 1+end]
+		}
+		return strings.TrimPrefix(s, `"`)
+	}
+	if i := strings.Index(strings.ToLower(s), ".exe"); i >= 0 {
+		return s[:i+len(".exe")]
+	}
+	if i := strings.IndexAny(s, " \t"); i >= 0 {
+		return s[:i]
+	}
+	return s
+}
+
+// parseServices turns the collector's JSON into workloads.
+//
+// systemRoot is a parameter rather than an environment read so this is testable
+// off Windows. The caller passes %SystemRoot%.
+//
+// The filter mirrors the systemd collector's intent: show what an operator
+// installed, and show what is meant to be up but is not. Services under
+// %SystemRoot%\System32 are the platform's own, and a typical host has well
+// over a hundred of them.
+func parseServices(jsonText, systemRoot string) ([]Workload, error) {
+	s := strings.TrimSpace(jsonText)
+	if s == "" || s == "null" {
+		return nil, nil
+	}
+
+	var rows []winService
+	if err := json.Unmarshal([]byte(s), &rows); err != nil {
+		var one winService
+		if err2 := json.Unmarshal([]byte(s), &one); err2 != nil {
+			return nil, err
+		}
+		rows = []winService{one}
+	}
+
+	sys32 := strings.ToLower(strings.TrimRight(systemRoot, `\`) + `\system32\`)
+
+	var wls []Workload
+	for _, r := range rows {
+		if p := strings.ToLower(servicePath(r.PathName)); p != "" && strings.HasPrefix(p, sys32) {
+			continue
+		}
+
+		running := strings.EqualFold(r.State, "Running")
+		failed := !running && r.ExitCode != 0 && r.ExitCode != exitCodeNeverStarted
+		auto := strings.HasPrefix(strings.ToLower(r.StartMode), "auto")
+		if !running && !failed && !auto {
+			continue
+		}
+
+		state := "stopped"
+		switch {
+		case running:
+			state = "running"
+		case failed:
+			state = "failed"
+		}
+
+		name := r.DisplayName
+		if name == "" {
+			name = r.Name
+		}
+
+		wls = append(wls, Workload{
+			Kind:  "unit",
+			ID:    r.Name,
+			Name:  name,
+			State: state,
+		})
+	}
+	return wls, nil
+}
+
+// psQuote renders a Go string as a PowerShell single-quoted literal. Single
+// quotes suppress every form of expansion, so the only character needing an
+// escape is the quote itself, which is doubled.
+func psQuote(s string) string {
+	return "'" + strings.ReplaceAll(s, "'", "''") + "'"
+}
@@ -0,0 +1,99 @@
+package workloads
+
+import "testing"
+
+func TestServicePath(t *testing.T) {
+	cases := []struct{ in, want string }{
+		{`"C:\Program Files\Contoso\svc.exe" -service`, `C:\Program Files\Contoso\svc.exe`},
+		{`C:\WINDOWS\system32\svchost.exe -k netsvcs`, `C:\WINDOWS\system32\svchost.exe`},
+		{`C:\Vantage\vantage-agent.exe`, `C:\Vantage\vantage-agent.exe`},
+		{`"C:\no\args.exe"`, `C:\no\args.exe`},
+		{``, ``},
+	}
+	for _, c := range cases {
+		if got := servicePath(c.in); got != c.want {
+			t.Errorf("servicePath(%q) = %q, want %q", c.in, got, c.want)
+		}
+	}
+}
+
+func TestParseServicesFilters(t *testing.T) {
+	in := `[
+	  {"Name":"Contoso","DisplayName":"Contoso Broker","State":"Running","StartMode":"Auto","PathName":"\"C:\\Program Files\\Contoso\\svc.exe\" -service","ExitCode":0},
+	  {"Name":"Themes","DisplayName":"Themes","State":"Running","StartMode":"Auto","PathName":"C:\\WINDOWS\\system32\\svchost.exe -k netsvcs","ExitCode":0},
+	  {"Name":"Fabrikam","DisplayName":"Fabrikam Sync","State":"Stopped","StartMode":"Auto","PathName":"C:\\Fabrikam\\sync.exe","ExitCode":0},
+	  {"Name":"Northwind","DisplayName":"Northwind Poller","State":"Stopped","StartMode":"Manual","PathName":"C:\\Northwind\\poll.exe","ExitCode":0},
+	  {"Name":"Crashed","DisplayName":"Crashed Thing","State":"Stopped","StartMode":"Auto","PathName":"C:\\Crashed\\c.exe","ExitCode":1067}
+	]`
+
+	got, err := parseServices(in, `C:\WINDOWS`)
+	if err != nil {
+		t.Fatalf("parseServices: %v", err)
+	}
+
+	byID := map[string]Workload{}
+	for _, w := range got {
+		byID[w.ID] = w
+	}
+
+	// The OS's own svchost service is dropped; a manual, stopped, never-failed
+	// service is nobody's business either.
+	if _, ok := byID["Themes"]; ok {
+		t.Error("Themes (under %SystemRoot%) should be filtered out")
+	}
+	if _, ok := byID["Northwind"]; ok {
+		t.Error("stopped Manual service should be filtered out")
+	}
+	if len(got) != 3 {
+		t.Fatalf("got %d workloads, want 3: %+v", len(got), got)
+	}
+
+	if w := byID["Contoso"]; w.Kind != "unit" || w.Name != "Contoso Broker" || w.State != "running" {
+		t.Errorf("Contoso = %+v", w)
+	}
+	// Enabled but not running is exactly the row worth seeing.
+	if byID["Fabrikam"].State != "stopped" {
+		t.Errorf("Fabrikam state = %q, want stopped", byID["Fabrikam"].State)
+	}
+	// A non-zero exit code on a stopped service is a crash, not a clean stop.
+	if byID["Crashed"].State != "failed" {
+		t.Errorf("Crashed state = %q, want failed", byID["Crashed"].State)
+	}
+}
+
+// 1077 means "no attempt to start since boot" — a clean stopped service, not a
+// failure, and reporting it red would cry wolf on every host.
+func TestParseServicesExitCode1077(t *testing.T) {
+	in := `[{"Name":"Idle","DisplayName":"Idle","State":"Stopped","StartMode":"Auto","PathName":"C:\\Idle\\i.exe","ExitCode":1077}]`
+	got, err := parseServices(in, `C:\WINDOWS`)
+	if err != nil {
+		t.Fatalf("parseServices: %v", err)
+	}
+	if len(got) != 1 || got[0].State != "stopped" {
+		t.Fatalf("got %+v, want one stopped workload", got)
+	}
+}
+
+func TestParseServicesSingleObjectAndEmpty(t *testing.T) {
+	one := `{"Name":"Solo","DisplayName":"Solo","State":"Running","StartMode":"Auto","PathName":"C:\\Solo\\s.exe","ExitCode":0}`
+	got, err := parseServices(one, `C:\WINDOWS`)
+	if err != nil || len(got) != 1 {
+		t.Fatalf("single object: got %+v, err %v", got, err)
+	}
+
+	for _, in := range []string{"", "[]", "null"} {
+		got, err := parseServices(in, `C:\WINDOWS`)
+		if err != nil || len(got) != 0 {
+			t.Fatalf("parseServices(%q) = %+v, err %v", in, got, err)
+		}
+	}
+}
+
+func TestPSQuote(t *testing.T) {
+	if got := psQuote(`it's`); got != `'it''s'` {
+		t.Fatalf("psQuote = %s", got)
+	}
+	if got := psQuote(`plain`); got != `'plain'` {
+		t.Fatalf("psQuote = %s", got)
+	}
+}