feat(observability): add the Scrabble — Messages Grafana dashboard

Visualises the chat read-receipt metrics added with the read-receipt feature (the dashboard was deferred there per the owner): posted rate by kind, the unread backlog (chat_unread_messages gauge), and the publish-to-read latency (chat_read_duration — average by kind plus overall p50/p95). Mirrors the game-domain dashboard's structure; the file provider auto-discovers it.
2026-06-17 12:00:58 +02:00
parent b71f006ddf
commit c3b3cafcdd
3 changed files with 50 additions and 2 deletions
@@ -0,0 +1,47 @@
+{
+  "uid": "scrabble-messages",
+  "title": "Scrabble — Messages",
+  "tags": ["scrabble"],
+  "timezone": "",
+  "schemaVersion": 39,
+  "version": 1,
+  "refresh": "30s",
+  "time": { "from": "now-24h", "to": "now" },
+  "panels": [
+    {
+      "type": "timeseries",
+      "title": "Chat entries posted (rate by kind)",
+      "gridPos": { "h": 8, "w": 12, "x": 0, "y": 0 },
+      "datasource": { "type": "prometheus", "uid": "prometheus" },
+      "targets": [{ "refId": "A", "expr": "sum(rate(chat_messages_total[15m])) by (kind)", "legendFormat": "{{kind}}" }]
+    },
+    {
+      "type": "timeseries",
+      "title": "Unread chat entries (backlog)",
+      "description": "Chat entries with at least one recipient seat that has not read them yet (chat_unread_messages gauge).",
+      "gridPos": { "h": 8, "w": 12, "x": 12, "y": 0 },
+      "datasource": { "type": "prometheus", "uid": "prometheus" },
+      "targets": [{ "refId": "A", "expr": "sum(chat_unread_messages)", "legendFormat": "unread" }]
+    },
+    {
+      "type": "timeseries",
+      "title": "Publish → read latency (avg by kind)",
+      "description": "Mean time from a chat entry being posted to a recipient reading it (move-history / chat open, or a nudge answered by moving). A born-read message to a robot records no read, so it does not enter this average.",
+      "gridPos": { "h": 8, "w": 12, "x": 0, "y": 8 },
+      "fieldConfig": { "defaults": { "unit": "s" }, "overrides": [] },
+      "datasource": { "type": "prometheus", "uid": "prometheus" },
+      "targets": [{ "refId": "A", "expr": "sum(rate(chat_read_duration_sum[15m])) by (kind) / sum(rate(chat_read_duration_count[15m])) by (kind)", "legendFormat": "{{kind}}" }]
+    },
+    {
+      "type": "timeseries",
+      "title": "Publish → read latency (p50 / p95)",
+      "gridPos": { "h": 8, "w": 12, "x": 12, "y": 8 },
+      "fieldConfig": { "defaults": { "unit": "s" }, "overrides": [] },
+      "datasource": { "type": "prometheus", "uid": "prometheus" },
+      "targets": [
+        { "refId": "A", "expr": "histogram_quantile(0.5, sum(rate(chat_read_duration_bucket[15m])) by (le))", "legendFormat": "p50" },
+        { "refId": "B", "expr": "histogram_quantile(0.95, sum(rate(chat_read_duration_bucket[15m])) by (le))", "legendFormat": "p95" }
+      ]
+    }
+  ]
+}