From ef31ef70a5b145c984780c895a27570c90765af3 Mon Sep 17 00:00:00 2001
From: rock <locartrock@gmail.com>
Date: Sun, 13 Sep 2026 21:49:30 +0900
Subject: [PATCH] feat(O11): Grafana dashboard for memory-observability

- 12 panels: rates, latency, errors, embedding, DB, health, relevance
- Covers all O1-O9 metrics in visual form
- Import via Grafana UI or provisioning
- Dashboard UID: poimen-memory-obs
---
 k8s/infra/grafana-dashboard.json | 131 +++++++++++++++++++++++++++++++
 1 file changed, 131 insertions(+)
 create mode 100644 k8s/infra/grafana-dashboard.json

diff --git a/k8s/infra/grafana-dashboard.json b/k8s/infra/grafana-dashboard.json
new file mode 100644
index 0000000..90f30a0
--- /dev/null
+++ b/k8s/infra/grafana-dashboard.json
@@ -0,0 +1,131 @@
+{
+  "annotations": { "list": [] },
+  "editable": true,
+  "fiscalYearStartMonth": 0,
+  "graphTooltip": 0,
+  "id": null,
+  "links": [],
+  "panels": [
+    {
+      "title": "Ingest Rate (req/s)",
+      "type": "timeseries",
+      "gridPos": { "h": 8, "w": 12, "x": 0, "y": 0 },
+      "targets": [
+        { "expr": "rate(memory_ingest_requests_total[5m])", "legendFormat": "ingest req/s" }
+      ]
+    },
+    {
+      "title": "Query Rate (req/s)",
+      "type": "timeseries",
+      "gridPos": { "h": 8, "w": 12, "x": 12, "y": 0 },
+      "targets": [
+        { "expr": "rate(memory_query_requests_total[5m])", "legendFormat": "query req/s" }
+      ]
+    },
+    {
+      "title": "Ingest Latency (p50/p95/p99)",
+      "type": "timeseries",
+      "gridPos": { "h": 8, "w": 12, "x": 0, "y": 8 },
+      "targets": [
+        { "expr": "histogram_quantile(0.5, rate(memory_ingest_duration_seconds_bucket[5m]))", "legendFormat": "p50" },
+        { "expr": "histogram_quantile(0.95, rate(memory_ingest_duration_seconds_bucket[5m]))", "legendFormat": "p95" },
+        { "expr": "histogram_quantile(0.99, rate(memory_ingest_duration_seconds_bucket[5m]))", "legendFormat": "p99" }
+      ]
+    },
+    {
+      "title": "Query Latency (p50/p95/p99)",
+      "type": "timeseries",
+      "gridPos": { "h": 8, "w": 12, "x": 12, "y": 8 },
+      "targets": [
+        { "expr": "histogram_quantile(0.5, rate(memory_query_duration_seconds_bucket[5m]))", "legendFormat": "p50" },
+        { "expr": "histogram_quantile(0.95, rate(memory_query_duration_seconds_bucket[5m]))", "legendFormat": "p95" },
+        { "expr": "histogram_quantile(0.99, rate(memory_query_duration_seconds_bucket[5m]))", "legendFormat": "p99" }
+      ]
+    },
+    {
+      "title": "Error Rates",
+      "type": "timeseries",
+      "gridPos": { "h": 8, "w": 12, "x": 0, "y": 16 },
+      "targets": [
+        { "expr": "rate(memory_ingest_errors_total[5m])", "legendFormat": "ingest errors" },
+        { "expr": "rate(memory_query_errors_total[5m])", "legendFormat": "query errors" },
+        { "expr": "rate(memory_query_embedding_failures_total[5m])", "legendFormat": "embedding failures" }
+      ]
+    },
+    {
+      "title": "Embedding Latency",
+      "type": "timeseries",
+      "gridPos": { "h": 8, "w": 12, "x": 12, "y": 16 },
+      "targets": [
+        { "expr": "histogram_quantile(0.5, rate(memory_query_embedding_duration_seconds_bucket[5m]))", "legendFormat": "p50" },
+        { "expr": "histogram_quantile(0.95, rate(memory_query_embedding_duration_seconds_bucket[5m]))", "legendFormat": "p95" }
+      ]
+    },
+    {
+      "title": "DB Row Counts",
+      "type": "stat",
+      "gridPos": { "h": 4, "w": 12, "x": 0, "y": 24 },
+      "targets": [
+        { "expr": "memory_db_table_entity_rows", "legendFormat": "entities" },
+        { "expr": "memory_db_table_edge_rows", "legendFormat": "edges" },
+        { "expr": "memory_db_table_chunk_rows", "legendFormat": "chunks" }
+      ]
+    },
+    {
+      "title": "Dependency Health",
+      "type": "stat",
+      "gridPos": { "h": 4, "w": 12, "x": 12, "y": 24 },
+      "targets": [
+        { "expr": "memory_dependency_db_up", "legendFormat": "DB" },
+        { "expr": "memory_dependency_embedding_up", "legendFormat": "Embedding" },
+        { "expr": "memory_dependency_opensearch_up", "legendFormat": "OpenSearch" },
+        { "expr": "memory_dependency_llm_up", "legendFormat": "LLM" }
+      ]
+    },
+    {
+      "title": "DB Pool Stats",
+      "type": "timeseries",
+      "gridPos": { "h": 8, "w": 12, "x": 0, "y": 28 },
+      "targets": [
+        { "expr": "memory_db_pool_size", "legendFormat": "pool size" },
+        { "expr": "memory_db_pool_idle", "legendFormat": "idle" },
+        { "expr": "memory_db_pool_active", "legendFormat": "active" }
+      ]
+    },
+    {
+      "title": "Relevance Metrics",
+      "type": "timeseries",
+      "gridPos": { "h": 8, "w": 12, "x": 12, "y": 28 },
+      "targets": [
+        { "expr": "memory_relevance_precision", "legendFormat": "precision" },
+        { "expr": "memory_relevance_recall", "legendFormat": "recall" },
+        { "expr": "memory_relevance_f1_score", "legendFormat": "F1" }
+      ]
+    },
+    {
+      "title": "In-Flight Operations",
+      "type": "timeseries",
+      "gridPos": { "h": 8, "w": 12, "x": 0, "y": 36 },
+      "targets": [
+        { "expr": "memory_ingest_in_flight", "legendFormat": "ingest" },
+        { "expr": "memory_query_in_flight", "legendFormat": "query" }
+      ]
+    },
+    {
+      "title": "Write Volume",
+      "type": "timeseries",
+      "gridPos": { "h": 8, "w": 12, "x": 12, "y": 36 },
+      "targets": [
+        { "expr": "rate(memory_write_entities_total[5m])", "legendFormat": "entities/s" },
+        { "expr": "rate(memory_write_edges_total[5m])", "legendFormat": "edges/s" },
+        { "expr": "rate(memory_write_chunks_total[5m])", "legendFormat": "chunks/s" }
+      ]
+    }
+  ],
+  "schemaVersion": 39,
+  "tags": ["poimen", "memory", "observability"],
+  "templating": { "list": [] },
+  "time": { "from": "now-1h", "to": "now" },
+  "title": "Poimen Memory Observability",
+  "uid": "poimen-memory-obs"
+}