feat(api): add prometheus metric coderd_workspace_builds_total (#6314)

This PR adds the prometheus metric coderd_workspace_builds_total.
It measures the total number of workspace builds, along with a number of labels intended to be useful for an operator debugging a failed workspace build trying to discover the scope of the issue.

provisionerd/provisionerd.go

@@ -157,6 +157,12 @@ func NewMetrics(reg prometheus.Registerer) Metrics {
 					60 * 60, // 1hr
 				},
 			}, []string{"provisioner", "status"}),
+			WorkspaceBuilds: auto.NewCounterVec(prometheus.CounterOpts{
+				Namespace: "coderd",
+				Subsystem: "", // Explicitly empty to make this a top-level metric.
+				Name:      "workspace_builds_total",
+				Help:      "The number of workspaces started, updated, or deleted.",
+			}, []string{"owner_email", "workspace_name", "template_name", "template_version", "action", "status"}),
 		},
 	}
 }

provisionerd/runner/runner.go

@@ -77,6 +77,8 @@ type Metrics struct {
 	ConcurrentJobs *prometheus.GaugeVec
 	// JobTimings also counts the total amount of jobs.
 	JobTimings *prometheus.HistogramVec
+	// WorkspaceBuilds counts workspace build successes and failures.
+	WorkspaceBuilds *prometheus.CounterVec
 }
 
 type JobUpdater interface {
@@ -161,6 +163,16 @@ func (r *Runner) Run() {
 		}
 
 		concurrentGauge.Dec()
+		if build := r.job.GetWorkspaceBuild(); build != nil {
+			r.metrics.WorkspaceBuilds.WithLabelValues(
+				build.Metadata.WorkspaceOwnerEmail,
+				build.Metadata.WorkspaceName,
+				build.Metadata.TemplateName,
+				build.Metadata.TemplateVersion,
+				build.Metadata.WorkspaceTransition.String(),
+				status,
+			).Inc()
+		}
 		r.metrics.JobTimings.WithLabelValues(r.job.Provisioner, status).Observe(time.Since(start).Seconds())
 	}()