Detect and alert on stuck jobs

internal/store/jobs.go

@@ -27,6 +27,52 @@ type Job struct {
 	CreatedAt     time.Time
 }
 
+// RunningJobActivity is the persisted activity summary used to detect jobs
+// whose terminal message was lost. LastActivity is the newer of started_at and
+// the most recent persisted log line; ephemeral progress events deliberately
+// do not extend it.
+type RunningJobActivity struct {
+	JobID        string
+	HostID       string
+	Kind         string
+	StartedAt    time.Time
+	LastActivity time.Time
+}
+
+// ListRunningJobActivity returns every running job with its latest persisted
+// activity. Jobs without started_at are excluded because they have not actually
+// entered the running state coherently and cannot be aged safely here.
+func (s *Store) ListRunningJobActivity(ctx context.Context) ([]RunningJobActivity, error) {
+	rows, err := s.db.QueryContext(ctx, `
+		SELECT j.id, j.host_id, j.kind, j.started_at,
+		       COALESCE(MAX(l.ts), j.started_at) AS last_activity
+		FROM jobs j
+		LEFT JOIN job_logs l ON l.job_id = j.id
+		WHERE j.status = 'running' AND j.started_at IS NOT NULL
+		GROUP BY j.id, j.host_id, j.kind, j.started_at
+		ORDER BY j.started_at`)
+	if err != nil {
+		return nil, fmt.Errorf("store: list running job activity: %w", err)
+	}
+	defer func() { _ = rows.Close() }()
+
+	var out []RunningJobActivity
+	for rows.Next() {
+		var item RunningJobActivity
+		var started, activity string
+		if err := rows.Scan(&item.JobID, &item.HostID, &item.Kind, &started, &activity); err != nil {
+			return nil, fmt.Errorf("store: scan running job activity: %w", err)
+		}
+		item.StartedAt, _ = time.Parse(time.RFC3339Nano, started)
+		item.LastActivity, _ = time.Parse(time.RFC3339Nano, activity)
+		out = append(out, item)
+	}
+	if err := rows.Err(); err != nil {
+		return nil, fmt.Errorf("store: iterate running job activity: %w", err)
+	}
+	return out, nil
+}
+
 // CreateJob inserts a queued job. The agent will mark it running
 // when it actually starts work. ScheduledID is set when the job
 // originates from a cron fire (actor_kind="schedule"); nil for

internal/store/jobs_test.go

@@ -7,6 +7,48 @@ import (
 	"time"
 )
 
+func TestListRunningJobActivity(t *testing.T) {
+	t.Parallel()
+	s := openTestStore(t)
+	ctx := context.Background()
+	hostID := makeSchedHost(t, s)
+	started := time.Now().UTC().Add(-8 * time.Hour).Truncate(time.Second)
+
+	for _, id := range []string{"running-idle", "running-active", "finished"} {
+		if err := s.CreateJob(ctx, Job{ID: id, HostID: hostID, Kind: "backup", ActorKind: "user", CreatedAt: started}); err != nil {
+			t.Fatalf("create %s: %v", id, err)
+		}
+		if err := s.MarkJobStarted(ctx, id, started); err != nil {
+			t.Fatalf("start %s: %v", id, err)
+		}
+	}
+	activity := started.Add(7 * time.Hour)
+	if err := s.AppendJobLog(ctx, "running-active", 1, activity, "stdout", "still working"); err != nil {
+		t.Fatalf("append log: %v", err)
+	}
+	if err := s.MarkJobFinished(ctx, "finished", "succeeded", 0, nil, "", activity); err != nil {
+		t.Fatalf("finish: %v", err)
+	}
+
+	got, err := s.ListRunningJobActivity(ctx)
+	if err != nil {
+		t.Fatalf("list activity: %v", err)
+	}
+	if len(got) != 2 {
+		t.Fatalf("got %d rows, want 2: %+v", len(got), got)
+	}
+	byID := make(map[string]RunningJobActivity, len(got))
+	for _, row := range got {
+		byID[row.JobID] = row
+	}
+	if !byID["running-idle"].LastActivity.Equal(started) {
+		t.Errorf("idle last activity = %s, want %s", byID["running-idle"].LastActivity, started)
+	}
+	if !byID["running-active"].LastActivity.Equal(activity) {
+		t.Errorf("active last activity = %s, want %s", byID["running-active"].LastActivity, activity)
+	}
+}
+
 func TestLatestJobByKind(t *testing.T) {
 	t.Parallel()
 	s := openTestStore(t)