monitoring: add signage marquee Grafana alerts

apps/monitoring/noc-monitoring.yaml

@@ -3362,6 +3362,92 @@ data:
                 relativeTimeRange: {from: 120, to: 0}
                 datasourceUid: __expr__
                 model: {type: threshold, expression: B, conditions: [{evaluator: {params: [600], type: gt}}], refId: C}
+      - orgId: 1
+        name: Signage Marquee
+        folder: AI Stack Alerts
+        interval: 1m
+        rules:
+          - uid: marquee-dropped-frames-high
+            title: MarqueeDroppedFramesHigh
+            condition: C
+            for: 5m
+            noDataState: OK
+            execErrState: OK
+            annotations:
+              summary: Marquee dropped-frame rate above 5%
+              description: "Dropped frames exceeded the IR-21 budget for a renderer/phase/node tuple. Grafana owns alert delivery to IRC #alerts; Prometheus rules remain only the visibility source."
+              runbook: "1. Open /d/fc-marquee-perf/marquee-animation-performance 2. Filter renderer/node/phase 3. Compare latest AAT baseline diff 4. Restart only the affected player if the issue is node-local"
+            labels:
+              severity: warning
+              service: signage
+              alert_channel: irc
+            data:
+              - refId: A
+                relativeTimeRange: {from: 300, to: 0}
+                datasourceUid: prometheus
+                model: {expr: '(sum by (renderer, node_id, phase) (rate(marquee_dropped_frames_total[5m])) / sum by (renderer, node_id, phase) (rate(marquee_render_latency_ms_count[5m]))) * 100', instant: true, refId: A}
+              - refId: B
+                relativeTimeRange: {from: 300, to: 0}
+                datasourceUid: __expr__
+                model: {type: reduce, expression: A, reducer: last, refId: B}
+              - refId: C
+                relativeTimeRange: {from: 300, to: 0}
+                datasourceUid: __expr__
+                model: {type: threshold, expression: B, conditions: [{evaluator: {params: [5], type: gt}}], refId: C}
+          - uid: marquee-render-latency-p99-high
+            title: MarqueeRenderLatencyP99High
+            condition: C
+            for: 5m
+            noDataState: OK
+            execErrState: OK
+            annotations:
+              summary: Marquee render latency p99 above 16ms
+              description: "Renderer p99 latency exceeded the Pi-class 16ms budget. Grafana delivers this alert to IRC #alerts."
+              runbook: "1. Open /d/fc-marquee-perf/marquee-animation-performance 2. Check render latency p99 by renderer/node/phase 3. Compare with dropped frames and node CPU 4. If isolated to WPF, capture current Player.Wpf frame set before restart"
+            labels:
+              severity: warning
+              service: signage
+              alert_channel: irc
+            data:
+              - refId: A
+                relativeTimeRange: {from: 300, to: 0}
+                datasourceUid: prometheus
+                model: {expr: 'histogram_quantile(0.99, sum by (renderer, node_id, phase, le) (rate(marquee_render_latency_ms_bucket[5m])))', instant: true, refId: A}
+              - refId: B
+                relativeTimeRange: {from: 300, to: 0}
+                datasourceUid: __expr__
+                model: {type: reduce, expression: A, reducer: last, refId: B}
+              - refId: C
+                relativeTimeRange: {from: 300, to: 0}
+                datasourceUid: __expr__
+                model: {type: threshold, expression: B, conditions: [{evaluator: {params: [16], type: gt}}], refId: C}
+          - uid: marquee-animation-duration-drift
+            title: MarqueeAnimationDurationDrift
+            condition: C
+            for: 10m
+            noDataState: OK
+            execErrState: OK
+            annotations:
+              summary: Marquee animation duration drift above 10%
+              description: "Observed cycle duration has drifted more than 10% from target for a renderer/phase pair. Grafana delivers this alert to IRC #alerts."
+              runbook: "1. Open /d/fc-marquee-perf/marquee-animation-performance 2. Compare observed vs target duration 3. Check recent theme/preset changes 4. Re-run MarqueeHolidayBrandTrajectoryTests before promoting a baseline"
+            labels:
+              severity: warning
+              service: signage
+              alert_channel: irc
+            data:
+              - refId: A
+                relativeTimeRange: {from: 900, to: 0}
+                datasourceUid: prometheus
+                model: {expr: 'abs((histogram_quantile(0.5, sum by (renderer, phase, le) (rate(marquee_animation_duration_ms_bucket[15m]))) - avg by (renderer, phase) (marquee_animation_duration_target_ms)) / avg by (renderer, phase) (marquee_animation_duration_target_ms))', instant: true, refId: A}
+              - refId: B
+                relativeTimeRange: {from: 900, to: 0}
+                datasourceUid: __expr__
+                model: {type: reduce, expression: A, reducer: last, refId: B}
+              - refId: C
+                relativeTimeRange: {from: 900, to: 0}
+                datasourceUid: __expr__
+                model: {type: threshold, expression: B, conditions: [{evaluator: {params: [0.1], type: gt}}], refId: C}
       - orgId: 1
         name: Infrastructure
         folder: AI Stack Alerts