snapshot: NODE1 production state 2026-02-09

Complete snapshot of /opt/microdao-daarion/ from NODE1 (144.76.224.179).
This represents the actual running production code that has diverged
significantly from the previous main branch.

Key changes from old main:
- Gateway (http_api.py): expanded from ~40KB to 164KB with full agent support
- Router: new /v1/agents/{id}/infer endpoint with vision + DeepSeek routing
- Behavior Policy: SOWA v2.2 (3-level: FULL/ACK/SILENT)
- Agent Registry: config/agent_registry.yml as single source of truth
- 13 agents configured (was 3)
- Memory service integration
- CrewAI teams and roles

Excluded from snapshot: venv/, .env, data/, backups, .tgz archives

Co-authored-by: Cursor <cursoragent@cursor.com>

monitoring/grafana/dashboards/slo_dashboard.json

@@ -0,0 +1,100 @@
+{
+  "dashboard": {
+    "title": "SLO Dashboard - DAARION Platform",
+    "tags": ["slo", "production", "monitoring"],
+    "timezone": "browser",
+    "panels": [
+      {
+        "id": 1,
+        "title": "Availability SLO (99.9%)",
+        "type": "stat",
+        "targets": [
+          {
+            "expr": "sum(rate(http_requests_total{status=~\"2..\"}[5m])) / sum(rate(http_requests_total[5m])) * 100",
+            "legendFormat": "Success Rate"
+          }
+        ],
+        "fieldConfig": {
+          "defaults": {
+            "unit": "percent",
+            "thresholds": {
+              "steps": [
+                {"value": 0, "color": "red"},
+                {"value": 99.9, "color": "green"}
+              ]
+            }
+          }
+        }
+      },
+      {
+        "id": 2,
+        "title": "Latency SLO (p95 < 2s)",
+        "type": "graph",
+        "targets": [
+          {
+            "expr": "histogram_quantile(0.95, sum(rate(http_request_duration_seconds_bucket{service=\"router\"}[5m])) by (le))",
+            "legendFormat": "p95 Gateway→Router"
+          },
+          {
+            "expr": "histogram_quantile(0.95, sum(rate(nats_message_processing_duration_seconds_bucket[5m])) by (le))",
+            "legendFormat": "p95 E2E Async"
+          }
+        ],
+        "yaxes": [
+          {
+            "format": "s",
+            "label": "Latency"
+          }
+        ],
+        "gridPos": {"h": 8, "w": 12, "x": 0, "y": 1}
+      },
+      {
+        "id": 3,
+        "title": "Queue Time SLO (p95 < 5s)",
+        "type": "graph",
+        "targets": [
+          {
+            "expr": "histogram_quantile(0.95, sum(rate(nats_consumer_lag[5m])) by (consumer))",
+            "legendFormat": "{{consumer}}"
+          }
+        ],
+        "yaxes": [
+          {
+            "format": "s",
+            "label": "Queue Time"
+          }
+        ],
+        "gridPos": {"h": 8, "w": 12, "x": 12, "y": 1}
+      },
+      {
+        "id": 4,
+        "title": "Error Budget (30 days)",
+        "type": "stat",
+        "targets": [
+          {
+            "expr": "(1 - (sum(rate(http_requests_total{status=~\"5..\"}[30d])) / sum(rate(http_requests_total[30d])))) * 100",
+            "legendFormat": "Error Budget Remaining"
+          }
+        ],
+        "fieldConfig": {
+          "defaults": {
+            "unit": "percent",
+            "thresholds": {
+              "steps": [
+                {"value": 0, "color": "red"},
+                {"value": 50, "color": "yellow"},
+                {"value": 99, "color": "green"}
+              ]
+            }
+          }
+        },
+        "gridPos": {"h": 4, "w": 6, "x": 0, "y": 9}
+      }
+    ],
+    "refresh": "30s",
+    "time": {
+      "from": "now-1h",
+      "to": "now"
+    }
+  }
+}