harden article generation reliability

server/internal/tenant/app/monitoring_metrics_prometheus.go

@@ -14,7 +14,7 @@ import (
 )
 
 func MonitoringSchedulerMetricsPrometheusHandler() http.Handler {
-	return monitoringPrometheusHandler(true, monitoringDailyTaskMetricsCollector{}, cache.MetricsCollector{})
+	return monitoringPrometheusHandler(true, monitoringDailyTaskMetricsCollector{}, generationTaskMetricsCollector{}, cache.MetricsCollector{})
 }
 
 func MonitoringDailyTaskMetricsPrometheus() string {
@@ -41,6 +41,14 @@ func MonitoringHeartbeatSnapshotMetricsPrometheusHandler() http.Handler {
 	return monitoringPrometheusHandler(false, monitoringHeartbeatSnapshotMetricsCollector{})
 }
 
+func GenerationTaskMetricsPrometheus() string {
+	return renderMonitoringPrometheus(monitoringPrometheusRegistry(false, generationTaskMetricsCollector{}))
+}
+
+func GenerationTaskMetricsPrometheusHandler() http.Handler {
+	return monitoringPrometheusHandler(false, generationTaskMetricsCollector{})
+}
+
 func monitoringPrometheusHandler(includeRuntime bool, metricCollectors ...prometheus.Collector) http.Handler {
 	return promhttp.HandlerFor(monitoringPrometheusRegistry(includeRuntime, metricCollectors...), promhttp.HandlerOpts{})
 }
@@ -155,6 +163,33 @@ func (monitoringHeartbeatSnapshotMetricsCollector) Collect(ch chan<- prometheus.
 	}
 }
 
+type generationTaskMetricsCollector struct{}
+
+func (generationTaskMetricsCollector) Describe(chan<- *prometheus.Desc) {}
+
+func (generationTaskMetricsCollector) Collect(ch chan<- prometheus.Metric) {
+	snapshot := GenerationTaskMetricsSnapshotValue()
+	monitoringCounter(ch, "article_generation_task_transitions_total", "Total article generation task state transition attempts.", float64(snapshot.TransitionTotal), nil)
+	monitoringCounter(ch, "article_generation_task_failures_total", "Total article generation task failures recorded by business stage.", float64(snapshot.FailureTotal), nil)
+	monitoringCounter(ch, "article_generation_task_cleanup_failures_total", "Total article generation failure-cleanup errors that need operator attention.", float64(snapshot.CleanupFailureTotal), nil)
+	monitoringCounter(ch, "article_generation_task_queue_failures_total", "Total article generation task queue publish or delivery errors.", float64(snapshot.QueueFailureTotal), nil)
+	monitoringCounter(ch, "article_generation_task_recovery_total", "Total article generation recovery actions by action.", float64(snapshot.RecoveryRequeueTotal), []string{"action"}, "requeue")
+	monitoringCounter(ch, "article_generation_task_recovery_total", "Total article generation recovery actions by action.", float64(snapshot.RecoveryFinalizeTotal), []string{"action"}, "finalize")
+	monitoringCounter(ch, "article_generation_task_state_anomalies_total", "Total article generation task/article state anomalies detected by bounded consistency checks.", float64(snapshot.StateAnomalyTotal), nil)
+	monitoringCounter(ch, "article_generation_task_state_check_failures_total", "Total article generation state consistency check failures.", float64(snapshot.StateCheckFailureTotal), nil)
+	if snapshot.LastEvent != "" {
+		monitoringGauge(ch, "article_generation_task_last_event_info", "Last article generation task observability event.", 1, []string{"event", "task_type", "stage", "result", "anomaly_type", "severity"},
+			snapshot.LastEvent,
+			snapshot.LastTaskType,
+			snapshot.LastStage,
+			snapshot.LastResult,
+			snapshot.LastAnomalyType,
+			snapshot.LastSeverity,
+		)
+	}
+	monitoringGauge(ch, "article_generation_task_last_event_timestamp_seconds", "Unix timestamp of the last article generation task observability event.", monitoringDailyTimeSeconds(snapshot.LastEventAt), nil)
+}
+
 func monitoringCounter(ch chan<- prometheus.Metric, name, help string, value float64, labelNames []string, labelValues ...string) {
 	monitoringMetric(ch, name, help, prometheus.CounterValue, value, labelNames, labelValues...)
 }