agentic-qe 1.9.3 → 2.0.0

package/config/alerting-rules.yml

@@ -0,0 +1,518 @@
+# Prometheus Alerting Rules for Agentic QE Fleet
+# Phase 4: Autonomous Alerting & Feedback Loop System
+# Issue: #69
+# Version: 1.0.0
+# Date: 2025-11-29
+
+groups:
+  # =========================================================================
+  # QUALITY METRIC ALERTS
+  # =========================================================================
+  - name: quality_metrics
+    interval: 15s
+    rules:
+      # Test Failure Rate Alert
+      - alert: HighTestFailureRate
+        expr: |
+          (
+            sum(rate(aqe_quality_test_count{status="failed"}[5m]))
+            /
+            sum(rate(aqe_quality_test_count[5m]))
+          ) > 0.05
+        for: 5m
+        labels:
+          severity: error
+          component: quality
+          alert_type: test_failure
+          feedback_action: adjust_strategy
+        annotations:
+          summary: "Test failure rate exceeds 5%"
+          description: "Test failure rate is {{ $value | humanizePercentage }} (threshold: 5%). This indicates quality degradation."
+          feedback_strategy: "increase_test_isolation"
+          feedback_focus: "failing_tests"
+          runbook_url: "https://docs.agentic-qe.io/runbooks/high-test-failure-rate"
+
+      # Coverage Drop - Critical
+      - alert: CriticalCoverageDrop
+        expr: aqe_quality_coverage_line < 80
+        for: 1m
+        labels:
+          severity: critical
+          component: quality
+          alert_type: coverage_drop
+          feedback_action: auto_remediate
+          agent_scope: qe-coverage-analyzer
+        annotations:
+          summary: "Code coverage dropped below 80%"
+          description: "Line coverage is {{ $value }}% (threshold: 80%). Immediate action required."
+          feedback_action: "generate_additional_tests"
+          feedback_target_coverage: "85.0"
+          runbook_url: "https://docs.agentic-qe.io/runbooks/coverage-drop"
+
+      # Coverage Drop - Warning
+      - alert: WarningCoverageDrop
+        expr: aqe_quality_coverage_line < 85 and aqe_quality_coverage_line >= 80
+        for: 5m
+        labels:
+          severity: warning
+          component: quality
+          alert_type: coverage_drop
+          feedback_action: adjust_strategy
+        annotations:
+          summary: "Code coverage approaching threshold"
+          description: "Line coverage is {{ $value }}% (warning at 85%, critical at 80%)"
+          feedback_strategy: "proactive_test_generation"
+
+      # Branch Coverage Drop
+      - alert: BranchCoverageLow
+        expr: aqe_quality_coverage_branch < 75
+        for: 5m
+        labels:
+          severity: warning
+          component: quality
+          alert_type: coverage_drop
+          feedback_action: adjust_strategy
+        annotations:
+          summary: "Branch coverage below threshold"
+          description: "Branch coverage is {{ $value }}% (threshold: 75%)"
+          feedback_strategy: "focus_branch_coverage"
+
+      # Flaky Tests Increasing
+      - alert: FlakyTestsIncreasing
+        expr: aqe_quality_flaky_count > 5
+        for: 1h
+        labels:
+          severity: warning
+          component: quality
+          alert_type: flaky_tests
+          feedback_action: adjust_strategy
+          agent_scope: qe-flaky-detector
+        annotations:
+          summary: "Number of flaky tests is growing"
+          description: "{{ $value }} flaky tests detected (threshold: 5). Test stability degrading."
+          feedback_strategy: "stabilize_flaky_tests"
+          feedback_analysis_depth: "deep"
+          runbook_url: "https://docs.agentic-qe.io/runbooks/flaky-tests"
+
+      # Critical Flaky Test Count
+      - alert: CriticalFlakyTestCount
+        expr: aqe_quality_flaky_count > 10
+        for: 30m
+        labels:
+          severity: error
+          component: quality
+          alert_type: flaky_tests
+          feedback_action: escalate
+        annotations:
+          summary: "Critical number of flaky tests detected"
+          description: "{{ $value }} flaky tests (critical threshold: 10). Test suite reliability compromised."
+          feedback_action: "quarantine_flaky_tests"
+
+      # Security Vulnerabilities - Critical
+      - alert: CriticalSecurityVulnerabilities
+        expr: aqe_quality_security_vulnerability_count{severity="critical"} > 0
+        for: 0s
+        labels:
+          severity: critical
+          component: security
+          alert_type: vulnerability
+          feedback_action: escalate
+          agent_scope: qe-security-scanner
+        annotations:
+          summary: "Critical security vulnerabilities detected"
+          description: "{{ $value }} critical vulnerabilities found. Deployment must be blocked."
+          feedback_notify: "security_team"
+          feedback_block_deployment: "true"
+          runbook_url: "https://docs.agentic-qe.io/runbooks/security-vulnerabilities"
+
+      # Security Vulnerabilities - High
+      - alert: HighSecurityVulnerabilities
+        expr: aqe_quality_security_vulnerability_count{severity="high"} > 0
+        for: 0s
+        labels:
+          severity: error
+          component: security
+          alert_type: vulnerability
+          feedback_action: escalate
+          agent_scope: qe-security-scanner
+        annotations:
+          summary: "High severity security vulnerabilities detected"
+          description: "{{ $value }} high severity vulnerabilities found. Immediate remediation required."
+          feedback_notify: "security_team"
+          feedback_block_deployment: "true"
+
+      # Security Vulnerabilities - Medium (with threshold)
+      - alert: MediumSecurityVulnerabilities
+        expr: aqe_quality_security_vulnerability_count{severity="medium"} > 5
+        for: 5m
+        labels:
+          severity: warning
+          component: security
+          alert_type: vulnerability
+          feedback_action: auto_remediate
+        annotations:
+          summary: "Multiple medium severity vulnerabilities"
+          description: "{{ $value }} medium severity vulnerabilities (threshold: 5)"
+          feedback_action: "schedule_security_remediation"
+
+      # Quality Gate Failure
+      - alert: QualityGateFailed
+        expr: aqe_quality_gate_pass_rate < 1.0
+        for: 1m
+        labels:
+          severity: error
+          component: quality
+          alert_type: quality_gate
+          feedback_action: adjust_strategy
+          agent_scope: qe-quality-gate
+        annotations:
+          summary: "Quality gate evaluation failed"
+          description: "Quality gate pass rate: {{ $value | humanizePercentage }} (expected: 100%)"
+          feedback_strategy: "incremental_improvement"
+          feedback_focus_areas: "coverage,complexity,security"
+          runbook_url: "https://docs.agentic-qe.io/runbooks/quality-gate-failure"
+
+  # =========================================================================
+  # PERFORMANCE METRIC ALERTS
+  # =========================================================================
+  - name: performance_metrics
+    interval: 15s
+    rules:
+      # Test Execution Slow
+      - alert: TestExecutionSlow
+        expr: |
+          histogram_quantile(0.95,
+            rate(aqe_quality_test_duration_bucket[5m])
+          ) > 30000
+        for: 5m
+        labels:
+          severity: warning
+          component: performance
+          alert_type: execution_slow
+          feedback_action: adjust_strategy
+          agent_scope: qe-test-executor
+        annotations:
+          summary: "Test execution time degraded"
+          description: "P95 test execution time is {{ $value | humanizeDuration }} (threshold: 30s)"
+          feedback_strategy: "optimize_test_suite"
+          feedback_action: "parallel_execution"
+          runbook_url: "https://docs.agentic-qe.io/runbooks/slow-tests"
+
+      # Critical Test Execution Time
+      - alert: CriticalTestExecutionTime
+        expr: |
+          histogram_quantile(0.95,
+            rate(aqe_quality_test_duration_bucket[5m])
+          ) > 60000
+        for: 3m
+        labels:
+          severity: error
+          component: performance
+          alert_type: execution_slow
+          feedback_action: auto_remediate
+        annotations:
+          summary: "Test execution critically slow"
+          description: "P95 test execution time is {{ $value | humanizeDuration }} (critical threshold: 60s)"
+          feedback_action: "emergency_test_optimization"
+
+      # Agent Task Timeout
+      - alert: AgentTaskTimeout
+        expr: |
+          histogram_quantile(0.95,
+            rate(aqe_agent_task_duration_bucket[10m])
+          ) > 120000
+        for: 10m
+        labels:
+          severity: error
+          component: performance
+          alert_type: task_timeout
+          feedback_action: retrain_model
+        annotations:
+          summary: "Agent tasks timing out frequently"
+          description: "P95 task duration is {{ $value | humanizeDuration }} (threshold: 2m)"
+          feedback_focus: "task_complexity_estimation"
+          feedback_learning_rate: "0.2"
+          runbook_url: "https://docs.agentic-qe.io/runbooks/agent-timeout"
+
+      # Memory Usage High
+      - alert: HighMemoryUsage
+        expr: aqe_system_memory_usage > 500000000
+        for: 1m
+        labels:
+          severity: warning
+          component: system
+          alert_type: resource_usage
+          feedback_action: auto_remediate
+        annotations:
+          summary: "Agent memory consumption exceeds threshold"
+          description: "Memory usage is {{ $value | humanize1024 }}B (threshold: 500MB)"
+          feedback_action: "garbage_collect"
+          feedback_optimize_batch_size: "true"
+          runbook_url: "https://docs.agentic-qe.io/runbooks/high-memory"
+
+      # Critical Memory Usage
+      - alert: CriticalMemoryUsage
+        expr: aqe_system_memory_usage > 800000000
+        for: 30s
+        labels:
+          severity: critical
+          component: system
+          alert_type: resource_usage
+          feedback_action: escalate
+        annotations:
+          summary: "Critical memory usage detected"
+          description: "Memory usage is {{ $value | humanize1024 }}B (critical threshold: 800MB). OOM risk."
+          feedback_action: "emergency_memory_cleanup"
+
+      # CPU Usage High
+      - alert: HighCPUUsage
+        expr: aqe_system_cpu_usage > 80
+        for: 5m
+        labels:
+          severity: warning
+          component: system
+          alert_type: resource_usage
+          feedback_action: adjust_strategy
+        annotations:
+          summary: "High CPU utilization detected"
+          description: "CPU usage is {{ $value }}% (threshold: 80%)"
+          feedback_strategy: "reduce_concurrent_tasks"
+
+  # =========================================================================
+  # LEARNING & ADAPTATION ALERTS
+  # =========================================================================
+  - name: learning_metrics
+    interval: 30s
+    rules:
+      # Low Agent Success Rate
+      - alert: LowAgentSuccessRate
+        expr: aqe_agent_success_rate < 0.90
+        for: 1h
+        labels:
+          severity: warning
+          component: learning
+          alert_type: success_rate
+          feedback_action: retrain_model
+        annotations:
+          summary: "Agent success rate below target"
+          description: "Agent {{ $labels.agent_type }} success rate is {{ $value | humanizePercentage }} (threshold: 90%)"
+          feedback_exploration_rate: "0.3"
+          feedback_focus: "failed_task_patterns"
+          runbook_url: "https://docs.agentic-qe.io/runbooks/low-success-rate"
+
+      # Critical Agent Success Rate
+      - alert: CriticalAgentSuccessRate
+        expr: aqe_agent_success_rate < 0.70
+        for: 30m
+        labels:
+          severity: error
+          component: learning
+          alert_type: success_rate
+          feedback_action: escalate
+        annotations:
+          summary: "Critical agent success rate"
+          description: "Agent {{ $labels.agent_type }} success rate is {{ $value | humanizePercentage }} (critical: 70%)"
+          feedback_action: "emergency_retraining"
+
+      # Defect Density High
+      - alert: HighDefectDensity
+        expr: aqe_quality_defect_density > 2.0
+        for: 24h
+        labels:
+          severity: error
+          component: quality
+          alert_type: defect_density
+          feedback_action: adjust_strategy
+          agent_scope: qe-quality-analyzer
+        annotations:
+          summary: "Defect density exceeds threshold"
+          description: "Defect density is {{ $value }} per KLOC (threshold: 2.0)"
+          feedback_strategy: "increase_review_depth"
+          feedback_static_analysis: "true"
+          runbook_url: "https://docs.agentic-qe.io/runbooks/high-defect-density"
+
+      # Agent Task Failure Spike
+      - alert: AgentTaskFailureSpike
+        expr: |
+          (
+            sum(rate(aqe_agent_task_count{status="failed"}[5m])) by (agent_type)
+            /
+            sum(rate(aqe_agent_task_count[5m])) by (agent_type)
+          ) > 0.20
+        for: 10m
+        labels:
+          severity: warning
+          component: learning
+          alert_type: failure_spike
+          feedback_action: retrain_model
+        annotations:
+          summary: "Agent experiencing task failure spike"
+          description: "Agent {{ $labels.agent_type }} failure rate is {{ $value | humanizePercentage }} (threshold: 20%)"
+          feedback_action: "analyze_failure_patterns"
+
+  # =========================================================================
+  # FLEET COORDINATION ALERTS
+  # =========================================================================
+  - name: fleet_coordination
+    interval: 30s
+    rules:
+      # Agent Queue Depth High
+      - alert: HighAgentQueueDepth
+        expr: aqe_system_queue_depth > 50
+        for: 5m
+        labels:
+          severity: warning
+          component: coordination
+          alert_type: queue_depth
+          feedback_action: adjust_strategy
+        annotations:
+          summary: "Agent task queue is backing up"
+          description: "Queue depth is {{ $value }} tasks (threshold: 50)"
+          feedback_strategy: "scale_agents"
+          runbook_url: "https://docs.agentic-qe.io/runbooks/queue-backup"
+
+      # Agent Queue Depth Critical
+      - alert: CriticalAgentQueueDepth
+        expr: aqe_system_queue_depth > 100
+        for: 2m
+        labels:
+          severity: error
+          component: coordination
+          alert_type: queue_depth
+          feedback_action: auto_remediate
+        annotations:
+          summary: "Critical agent queue backlog"
+          description: "Queue depth is {{ $value }} tasks (critical: 100). System overloaded."
+          feedback_action: "emergency_queue_drain"
+
+      # Database Query Slow
+      - alert: SlowDatabaseQueries
+        expr: |
+          histogram_quantile(0.95,
+            rate(aqe_system_db_query_duration_bucket[5m])
+          ) > 1000
+        for: 5m
+        labels:
+          severity: warning
+          component: system
+          alert_type: database_slow
+          feedback_action: adjust_strategy
+        annotations:
+          summary: "Database queries are slow"
+          description: "P95 query duration is {{ $value | humanizeDuration }} (threshold: 1s)"
+          feedback_strategy: "optimize_database_access"
+          runbook_url: "https://docs.agentic-qe.io/runbooks/slow-database"
+
+      # Event Bus Latency High
+      - alert: HighEventBusLatency
+        expr: |
+          rate(aqe_system_eventbus_latency_sum[5m])
+          /
+          rate(aqe_system_eventbus_latency_count[5m])
+          > 500
+        for: 5m
+        labels:
+          severity: warning
+          component: coordination
+          alert_type: event_latency
+          feedback_action: adjust_strategy
+        annotations:
+          summary: "Event bus experiencing high latency"
+          description: "Average event latency is {{ $value | humanizeDuration }} (threshold: 500ms)"
+          feedback_strategy: "optimize_event_handling"
+
+  # =========================================================================
+  # TOKEN COST & EFFICIENCY ALERTS
+  # =========================================================================
+  - name: cost_efficiency
+    interval: 1m
+    rules:
+      # High Token Cost Rate
+      - alert: HighTokenCostRate
+        expr: |
+          rate(aqe_agent_cost_sum[1h])
+          > 10.0
+        for: 15m
+        labels:
+          severity: warning
+          component: cost
+          alert_type: token_cost
+          feedback_action: adjust_strategy
+        annotations:
+          summary: "Token costs increasing rapidly"
+          description: "Cost rate is ${{ $value }}/hour (threshold: $10/hour)"
+          feedback_strategy: "optimize_token_usage"
+          runbook_url: "https://docs.agentic-qe.io/runbooks/high-token-cost"
+
+      # Inefficient Agent Token Usage
+      - alert: InefficientAgentTokenUsage
+        expr: |
+          (
+            rate(aqe_agent_token_usage_sum[1h]) by (agent_type)
+            /
+            rate(aqe_agent_task_count{status="success"}[1h]) by (agent_type)
+          ) > 10000
+        for: 30m
+        labels:
+          severity: warning
+          component: efficiency
+          alert_type: token_efficiency
+          feedback_action: retrain_model
+        annotations:
+          summary: "Agent using excessive tokens per successful task"
+          description: "Agent {{ $labels.agent_type }} uses {{ $value }} tokens per success (threshold: 10k)"
+          feedback_strategy: "optimize_prompt_efficiency"
+
+  # =========================================================================
+  # ALERTING SYSTEM HEALTH
+  # =========================================================================
+  - name: alerting_system_health
+    interval: 30s
+    rules:
+      # High Alert Fire Rate (Alert Fatigue)
+      - alert: AlertFatigueDetected
+        expr: |
+          sum(rate(aqe_alerting_alerts_fired[1h])) > 20
+        for: 1h
+        labels:
+          severity: warning
+          component: alerting
+          alert_type: alert_fatigue
+        annotations:
+          summary: "Excessive alerts being fired"
+          description: "{{ $value }} alerts fired in the last hour. Potential alert fatigue."
+          action: "Review and tune alert thresholds"
+          runbook_url: "https://docs.agentic-qe.io/runbooks/alert-fatigue"
+
+      # High Alert Suppression Rate
+      - alert: HighAlertSuppressionRate
+        expr: |
+          (
+            rate(aqe_alerting_alerts_suppressed[1h])
+            /
+            rate(aqe_alerting_alerts_fired[1h])
+          ) > 0.5
+        for: 1h
+        labels:
+          severity: info
+          component: alerting
+          alert_type: suppression_rate
+        annotations:
+          summary: "High alert suppression rate"
+          description: "{{ $value | humanizePercentage }} of alerts are being suppressed. Review cooldown settings."
+
+      # Feedback Processing Slow
+      - alert: SlowFeedbackProcessing
+        expr: |
+          histogram_quantile(0.95,
+            rate(aqe_alerting_feedback_duration_bucket[5m])
+          ) > 5000
+        for: 5m
+        labels:
+          severity: warning
+          component: alerting
+          alert_type: feedback_slow
+        annotations:
+          summary: "Feedback loop processing is slow"
+          description: "P95 feedback processing time is {{ $value | humanizeDuration }} (threshold: 5s)"
+          action: "Investigate feedback router performance"

package/config/docker-compose.otel.yml

@@ -0,0 +1,187 @@
+version: '3.8'
+
+# OTEL Observability Stack for Agentic QE Fleet
+# Issue #71: Complete OTEL Stack Docker Compose Configuration
+#
+# This compose file sets up a complete observability stack:
+# - OTEL Collector: Receives telemetry via OTLP (gRPC:4317, HTTP:4318)
+# - Prometheus: Scrapes metrics from OTEL Collector (port 9090)
+# - Jaeger: Distributed tracing backend (UI on port 16686)
+# - Grafana: Visualization and dashboards (port 3001)
+#
+# Usage:
+#   docker-compose -f config/docker-compose.otel.yml up -d
+#   docker-compose -f docker-compose.yml -f config/docker-compose.otel.yml up -d
+
+services:
+  # OpenTelemetry Collector
+  otel-collector:
+    image: otel/opentelemetry-collector-contrib:latest
+    container_name: agentic-qe-otel-collector
+    command: ["--config=/etc/otel-collector-config.yaml"]
+    volumes:
+      - ./otel-collector-config.yaml.example:/etc/otel-collector-config.yaml:ro
+      - otel-data:/var/log/otel
+    ports:
+      # OTLP gRPC receiver
+      - "4317:4317"
+      # OTLP HTTP receiver
+      - "4318:4318"
+      # Prometheus exporter
+      - "8889:8889"
+      # Collector metrics (self-monitoring)
+      - "8888:8888"
+      # Health check endpoint
+      - "13133:13133"
+      # pprof profiling (development only)
+      - "1777:1777"
+      # zpages debug interface (development only)
+      - "55679:55679"
+    environment:
+      - DEPLOYMENT_ENVIRONMENT=${DEPLOYMENT_ENVIRONMENT:-development}
+    networks:
+      - agentic-qe-otel
+    restart: unless-stopped
+    healthcheck:
+      test: ["CMD", "wget", "--spider", "-q", "http://localhost:13133/health"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 40s
+
+  # Prometheus - Metrics storage and querying
+  prometheus:
+    image: prom/prometheus:latest
+    container_name: agentic-qe-prometheus
+    command:
+      - '--config.file=/etc/prometheus/prometheus.yml'
+      - '--storage.tsdb.path=/prometheus'
+      - '--storage.tsdb.retention.time=15d'
+      - '--storage.tsdb.retention.size=10GB'
+      - '--web.console.libraries=/usr/share/prometheus/console_libraries'
+      - '--web.console.templates=/usr/share/prometheus/consoles'
+      - '--web.enable-lifecycle'
+    volumes:
+      - ./prometheus.yml.example:/etc/prometheus/prometheus.yml:ro
+      - prometheus-data:/prometheus
+      # Optionally mount alerting rules
+      # - ./prometheus-rules:/etc/prometheus/rules:ro
+    ports:
+      - "9090:9090"
+    networks:
+      - agentic-qe-otel
+    restart: unless-stopped
+    depends_on:
+      otel-collector:
+        condition: service_healthy
+    healthcheck:
+      test: ["CMD", "wget", "--spider", "-q", "http://localhost:9090/-/healthy"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 30s
+
+  # Jaeger - Distributed tracing backend
+  jaeger:
+    image: jaegertracing/all-in-one:latest
+    container_name: agentic-qe-jaeger
+    environment:
+      # Collector settings
+      - COLLECTOR_OTLP_ENABLED=true
+      - COLLECTOR_ZIPKIN_HOST_PORT=:9411
+      # Storage settings (in-memory for development)
+      - SPAN_STORAGE_TYPE=badger
+      - BADGER_EPHEMERAL=false
+      - BADGER_DIRECTORY_VALUE=/badger/data
+      - BADGER_DIRECTORY_KEY=/badger/key
+      # Query settings
+      - QUERY_BASE_PATH=/
+      # Metrics backend
+      - METRICS_BACKEND=prometheus
+      - METRICS_HTTP_ROUTE=/metrics
+    volumes:
+      - jaeger-data:/badger
+    ports:
+      # Jaeger UI
+      - "16686:16686"
+      # OTLP gRPC receiver
+      - "4327:4317"
+      # OTLP HTTP receiver
+      - "4328:4318"
+      # Zipkin compatible endpoint
+      - "9411:9411"
+      # Admin port (health check, metrics)
+      - "14269:14269"
+      # Jaeger Thrift compact
+      - "6831:6831/udp"
+      # Jaeger Thrift binary
+      - "6832:6832/udp"
+      # Jaeger gRPC
+      - "14250:14250"
+    networks:
+      - agentic-qe-otel
+    restart: unless-stopped
+    healthcheck:
+      test: ["CMD", "wget", "--spider", "-q", "http://localhost:14269/"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 30s
+
+  # Grafana - Visualization and dashboards
+  grafana:
+    image: grafana/grafana:latest
+    container_name: agentic-qe-grafana
+    environment:
+      # Admin credentials (change in production!)
+      - GF_SECURITY_ADMIN_USER=${GRAFANA_ADMIN_USER:-admin}
+      - GF_SECURITY_ADMIN_PASSWORD=${GRAFANA_ADMIN_PASSWORD:-admin}
+      # Server settings
+      - GF_SERVER_ROOT_URL=http://localhost:3001
+      - GF_SERVER_SERVE_FROM_SUB_PATH=false
+      # Enable anonymous access (development only)
+      - GF_AUTH_ANONYMOUS_ENABLED=false
+      # Provisioning
+      - GF_PATHS_PROVISIONING=/etc/grafana/provisioning
+      # Plugins
+      - GF_INSTALL_PLUGINS=grafana-clock-panel,grafana-simple-json-datasource
+    volumes:
+      # Datasource provisioning
+      - ./grafana/provisioning/datasources:/etc/grafana/provisioning/datasources:ro
+      # Dashboard provisioning
+      - ./grafana/provisioning/dashboards:/etc/grafana/provisioning/dashboards:ro
+      # Dashboard JSON files
+      - ./grafana/dashboards:/var/lib/grafana/dashboards:ro
+      # Persistent storage
+      - grafana-data:/var/lib/grafana
+    ports:
+      - "3001:3000"
+    networks:
+      - agentic-qe-otel
+    restart: unless-stopped
+    depends_on:
+      prometheus:
+        condition: service_healthy
+      jaeger:
+        condition: service_healthy
+    healthcheck:
+      test: ["CMD", "wget", "--spider", "-q", "http://localhost:3000/api/health"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 40s
+
+volumes:
+  otel-data:
+    driver: local
+  prometheus-data:
+    driver: local
+  jaeger-data:
+    driver: local
+  grafana-data:
+    driver: local
+
+networks:
+  agentic-qe-otel:
+    driver: bridge
+    name: agentic-qe-otel