agentic-qe 1.9.3 → 1.9.4

package/config/grafana/dashboards/agentic-qe-overview.json

@@ -0,0 +1,286 @@
+{
+  "annotations": {
+    "list": [
+      {
+        "builtIn": 1,
+        "datasource": {
+          "type": "grafana",
+          "uid": "-- Grafana --"
+        },
+        "enable": true,
+        "hide": true,
+        "iconColor": "rgba(0, 211, 255, 1)",
+        "name": "Annotations & Alerts",
+        "type": "dashboard"
+      }
+    ]
+  },
+  "editable": true,
+  "fiscalYearStartMonth": 0,
+  "graphTooltip": 0,
+  "id": null,
+  "links": [],
+  "liveNow": false,
+  "panels": [
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prometheus"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "",
+            "axisPlacement": "auto",
+            "barAlignment": 0,
+            "drawStyle": "line",
+            "fillOpacity": 10,
+            "gradientMode": "none",
+            "hideFrom": {
+              "tooltip": false,
+              "viz": false,
+              "legend": false
+            },
+            "lineInterpolation": "linear",
+            "lineWidth": 1,
+            "pointSize": 5,
+            "scaleDistribution": {
+              "type": "linear"
+            },
+            "showPoints": "never",
+            "spanNulls": false,
+            "stacking": {
+              "group": "A",
+              "mode": "none"
+            },
+            "thresholdsStyle": {
+              "mode": "off"
+            }
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "red",
+                "value": 80
+              }
+            ]
+          },
+          "unit": "short"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 0
+      },
+      "id": 1,
+      "options": {
+        "legend": {
+          "calcs": [],
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "single",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prometheus"
+          },
+          "expr": "rate(aqe_requests_total[5m])",
+          "refId": "A",
+          "legendFormat": "Request Rate"
+        }
+      ],
+      "title": "Request Rate",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prometheus"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "thresholds"
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "yellow",
+                "value": 500
+              },
+              {
+                "color": "red",
+                "value": 1000
+              }
+            ]
+          },
+          "unit": "ms"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 0
+      },
+      "id": 2,
+      "options": {
+        "orientation": "auto",
+        "reduceOptions": {
+          "values": false,
+          "calcs": [
+            "lastNotNull"
+          ],
+          "fields": ""
+        },
+        "showThresholdLabels": false,
+        "showThresholdMarkers": true
+      },
+      "pluginVersion": "10.0.0",
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prometheus"
+          },
+          "expr": "histogram_quantile(0.95, rate(aqe_request_duration_bucket[5m]))",
+          "refId": "A",
+          "legendFormat": "P95 Latency"
+        }
+      ],
+      "title": "P95 Response Time",
+      "type": "gauge"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prometheus"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "",
+            "axisPlacement": "auto",
+            "barAlignment": 0,
+            "drawStyle": "line",
+            "fillOpacity": 10,
+            "gradientMode": "none",
+            "hideFrom": {
+              "tooltip": false,
+              "viz": false,
+              "legend": false
+            },
+            "lineInterpolation": "linear",
+            "lineWidth": 1,
+            "pointSize": 5,
+            "scaleDistribution": {
+              "type": "linear"
+            },
+            "showPoints": "never",
+            "spanNulls": false,
+            "stacking": {
+              "group": "A",
+              "mode": "none"
+            },
+            "thresholdsStyle": {
+              "mode": "off"
+            }
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              }
+            ]
+          },
+          "unit": "short"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 24,
+        "x": 0,
+        "y": 8
+      },
+      "id": 3,
+      "options": {
+        "legend": {
+          "calcs": [],
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "single",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prometheus"
+          },
+          "expr": "sum by (agent_type) (rate(aqe_agent_tasks_total[5m]))",
+          "refId": "A",
+          "legendFormat": "{{agent_type}}"
+        }
+      ],
+      "title": "Agent Activity by Type",
+      "type": "timeseries"
+    }
+  ],
+  "schemaVersion": 38,
+  "style": "dark",
+  "tags": ["agentic-qe", "overview"],
+  "templating": {
+    "list": []
+  },
+  "time": {
+    "from": "now-1h",
+    "to": "now"
+  },
+  "timepicker": {},
+  "timezone": "",
+  "title": "Agentic QE Fleet - Overview",
+  "uid": "aqe-overview",
+  "version": 1,
+  "weekStart": ""
+}

package/config/grafana/provisioning/dashboards/dashboards.yml

@@ -0,0 +1,19 @@
+# Grafana Dashboard Provisioning
+# Agentic QE Fleet - Issue #71
+#
+# This file configures where Grafana should look for dashboard JSON files
+
+apiVersion: 1
+
+providers:
+  # Dashboard provider for Agentic QE Fleet
+  - name: 'Agentic QE Fleet'
+    orgId: 1
+    folder: 'Agentic QE Fleet'
+    type: file
+    disableDeletion: false
+    updateIntervalSeconds: 10
+    allowUiUpdates: true
+    options:
+      path: /var/lib/grafana/dashboards
+      foldersFromFilesStructure: true

package/config/grafana/provisioning/datasources/datasources.yml

@@ -0,0 +1,53 @@
+# Grafana Datasource Provisioning
+# Agentic QE Fleet - Issue #71
+#
+# This file configures datasources for Prometheus and Jaeger
+# Grafana will automatically import these on startup
+
+apiVersion: 1
+
+datasources:
+  # Prometheus datasource for metrics
+  - name: Prometheus
+    type: prometheus
+    access: proxy
+    url: http://prometheus:9090
+    isDefault: true
+    editable: false
+    jsonData:
+      timeInterval: 15s
+      queryTimeout: 60s
+      httpMethod: POST
+    version: 1
+
+  # Jaeger datasource for distributed tracing
+  - name: Jaeger
+    type: jaeger
+    access: proxy
+    url: http://jaeger:16686
+    editable: false
+    jsonData:
+      # Trace query configuration
+      tracesToLogs:
+        datasourceUid: 'loki'
+        tags: ['job', 'instance', 'pod', 'namespace']
+        mappedTags: [{ key: 'service.name', value: 'service' }]
+        mapTagNamesEnabled: true
+        spanStartTimeShift: '1h'
+        spanEndTimeShift: '1h'
+      # Node graph configuration
+      nodeGraph:
+        enabled: true
+    version: 1
+
+  # OTEL Collector Prometheus endpoint (for collector metrics)
+  - name: OTEL Collector Metrics
+    type: prometheus
+    access: proxy
+    url: http://otel-collector:8889
+    editable: false
+    jsonData:
+      timeInterval: 15s
+      queryTimeout: 60s
+      httpMethod: POST
+    version: 1

package/config/otel-collector-config.yaml.example

@@ -0,0 +1,145 @@
+# OpenTelemetry Collector Configuration
+# Agentic QE Fleet - Issues #69 & #71
+#
+# This configuration defines the OTEL Collector pipeline for receiving,
+# processing, and exporting telemetry data from the Agentic QE Fleet.
+#
+# Usage: Copy to otel-collector-config.yaml and customize as needed
+
+receivers:
+  # OTLP receiver - accepts traces and metrics via gRPC and HTTP
+  otlp:
+    protocols:
+      grpc:
+        endpoint: 0.0.0.0:4317
+        # TLS configuration for production
+        # tls:
+        #   cert_file: /etc/otel/certs/server.crt
+        #   key_file: /etc/otel/certs/server.key
+
+      http:
+        endpoint: 0.0.0.0:4318
+        # CORS configuration if needed
+        # cors:
+        #   allowed_origins:
+        #     - http://localhost:3000
+        #     - https://*.example.com
+
+processors:
+  # Batch processor - groups spans/metrics for efficient export
+  batch:
+    timeout: 10s
+    send_batch_size: 1024
+    send_batch_max_size: 2048
+
+  # Memory limiter - prevents OOM issues
+  memory_limiter:
+    check_interval: 1s
+    limit_mib: 512
+    spike_limit_mib: 128
+
+  # Resource processor - adds service metadata
+  resource:
+    attributes:
+      - key: service.namespace
+        value: agentic-qe
+        action: upsert
+      - key: deployment.environment
+        from_attribute: deployment.environment
+        action: upsert
+
+  # Attributes processor - enriches telemetry data
+  attributes:
+    actions:
+      - key: environment
+        from_attribute: deployment.environment
+        action: upsert
+      # Sanitize sensitive data
+      - key: db.password
+        action: delete
+      - key: api.key
+        action: delete
+      - key: jwt.token
+        action: delete
+
+  # Transform processor - modify spans/metrics (optional)
+  # transform:
+  #   traces:
+  #     statements:
+  #       - set(status.code, 1) where attributes["http.status_code"] < 400
+
+exporters:
+  # Prometheus exporter - exposes metrics endpoint
+  prometheus:
+    endpoint: "0.0.0.0:8889"
+    namespace: aqe
+    const_labels:
+      service: agentic-qe-fleet
+    # Metric resource to telemetry conversion
+    resource_to_telemetry_conversion:
+      enabled: true
+
+  # Jaeger exporter - sends traces to Jaeger
+  otlp/jaeger:
+    endpoint: jaeger:4317
+    tls:
+      insecure: true
+    # For production with TLS
+    # tls:
+    #   insecure: false
+    #   cert_file: /etc/otel/certs/client.crt
+    #   key_file: /etc/otel/certs/client.key
+    #   ca_file: /etc/otel/certs/ca.crt
+
+  # Logging exporter - debug output (disable in production)
+  logging:
+    verbosity: detailed
+    sampling_initial: 5
+    sampling_thereafter: 200
+
+  # File exporter - local backup (optional)
+  # file:
+  #   path: /var/log/otel/telemetry.json
+
+service:
+  # Telemetry pipelines
+  pipelines:
+    # Trace pipeline
+    traces:
+      receivers: [otlp]
+      processors: [memory_limiter, batch, resource, attributes]
+      exporters: [otlp/jaeger, logging]
+
+    # Metrics pipeline
+    metrics:
+      receivers: [otlp]
+      processors: [memory_limiter, batch, resource, attributes]
+      exporters: [prometheus, logging]
+
+  # Collector telemetry (self-monitoring)
+  telemetry:
+    logs:
+      level: info
+      # Development: debug, Production: info
+      # level: debug
+
+    metrics:
+      # Expose collector's own metrics
+      address: 0.0.0.0:8888
+
+  # Extensions
+  extensions: [health_check, pprof, zpages]
+
+# Extensions configuration
+extensions:
+  # Health check endpoint
+  health_check:
+    endpoint: 0.0.0.0:13133
+
+  # Performance profiling (development only)
+  pprof:
+    endpoint: 0.0.0.0:1777
+
+  # ZPages debug interface (development only)
+  zpages:
+    endpoint: 0.0.0.0:55679

package/config/prometheus.yml.example

@@ -0,0 +1,106 @@
+# Prometheus Configuration
+# Agentic QE Fleet - Issues #69 & #71
+#
+# This configuration defines scrape targets and alerting rules
+# for the Agentic QE Fleet observability stack.
+#
+# Usage: Copy to prometheus.yml and customize as needed
+
+global:
+  scrape_interval: 15s
+  scrape_timeout: 10s
+  evaluation_interval: 15s
+
+  # External labels attached to all metrics
+  external_labels:
+    cluster: 'agentic-qe-fleet'
+    environment: 'development'
+    region: 'us-east-1'
+
+# Scrape configurations
+scrape_configs:
+  # OTEL Collector metrics (from Prometheus exporter)
+  - job_name: 'otel-collector'
+    static_configs:
+      - targets: ['otel-collector:8889']
+        labels:
+          service: 'otel-collector'
+          component: 'telemetry'
+
+  # OTEL Collector self-monitoring
+  - job_name: 'otel-collector-internal'
+    static_configs:
+      - targets: ['otel-collector:8888']
+        labels:
+          service: 'otel-collector-internal'
+          component: 'telemetry'
+
+  # Agentic QE Fleet application metrics (if exposed directly)
+  - job_name: 'agentic-qe-fleet'
+    static_configs:
+      - targets: ['agentic-qe-fleet:3000']
+        labels:
+          service: 'agentic-qe-fleet'
+          component: 'application'
+    metrics_path: '/metrics'
+    scrape_interval: 30s
+
+  # Prometheus self-monitoring
+  - job_name: 'prometheus'
+    static_configs:
+      - targets: ['localhost:9090']
+        labels:
+          service: 'prometheus'
+          component: 'telemetry'
+
+  # Jaeger metrics (optional)
+  - job_name: 'jaeger'
+    static_configs:
+      - targets: ['jaeger:14269']
+        labels:
+          service: 'jaeger'
+          component: 'telemetry'
+    metrics_path: '/metrics'
+
+  # PostgreSQL metrics (optional, requires postgres_exporter)
+  # - job_name: 'postgres'
+  #   static_configs:
+  #     - targets: ['postgres-exporter:9187']
+  #       labels:
+  #         service: 'postgres'
+  #         component: 'database'
+
+  # Redis metrics (optional, requires redis_exporter)
+  # - job_name: 'redis'
+  #   static_configs:
+  #     - targets: ['redis-exporter:9121']
+  #       labels:
+  #         service: 'redis'
+  #         component: 'cache'
+
+# Alerting configuration
+alerting:
+  alertmanagers:
+    - static_configs:
+        - targets: []
+          # Uncomment when Alertmanager is deployed
+          # - targets: ['alertmanager:9093']
+
+# Rule files for recording and alerting rules
+rule_files:
+  - '/etc/prometheus/rules/*.yml'
+
+# Storage configuration
+storage:
+  tsdb:
+    # Retention period
+    retention.time: 15d
+    # Maximum storage size
+    retention.size: 10GB
+
+# Remote write configuration (optional, for long-term storage)
+# remote_write:
+#   - url: "https://prometheus-remote-write.example.com/api/v1/write"
+#     basic_auth:
+#       username: "user"
+#       password: "password"