claude-flow-novice 1.6.5 → 1.6.6

package/config/docker/env.production

@@ -0,0 +1,83 @@
+# Docker Production Environment
+# Used by: docker-compose.production.yml
+
+# Environment
+NODE_ENV=production
+
+# Agent Configuration (Production: 500 agents)
+CFN_MAX_AGENTS=500
+CFN_SHARD_COUNT=32
+CFN_METRICS_ENABLED=true
+CFN_ALERTING_ENABLED=true
+CFN_LOG_LEVEL=warn
+CFN_CONSENSUS_THRESHOLD=0.95
+CFN_ALERT_COORD_TIME_MS=8000
+
+# Memory and Storage (tmpfs REQUIRED for production)
+CFN_BASE_DIR=/dev/shm/cfn
+CFN_AGENT_MEMORY_LIMIT_MB=100
+CFN_TOTAL_MEMORY_LIMIT_MB=51200
+
+# Performance
+CFN_AGENT_TIMEOUT_MS=30000
+CFN_CONSENSUS_TIMEOUT_MS=60000
+CFN_SWARM_INIT_TIMEOUT_MS=10000
+CFN_ENABLE_CACHING=true
+CFN_CACHE_TTL_SECONDS=600
+CFN_MAX_CONCURRENT_OPERATIONS=100
+
+# Resource Cleanup
+CFN_CLEANUP_INTERVAL_MS=60000
+CFN_CLEANUP_STALE_AGENTS_ENABLED=true
+
+# Monitoring
+CFN_METRICS_COLLECTION_INTERVAL_MS=5000
+CFN_METRICS_RETENTION_HOURS=168
+CFN_TRACK_COORDINATION_TIME=true
+CFN_TRACK_MEMORY_USAGE=true
+CFN_TRACK_AGENT_LIFECYCLE=true
+
+# Alerting Thresholds
+CFN_ALERT_MEMORY_THRESHOLD_PERCENT=80
+CFN_ALERT_AGENT_FAILURE_COUNT=3
+CFN_ALERT_CONSENSUS_FAILURE_THRESHOLD=0.70
+
+# Security (Production: REQUIRED)
+CFN_ENABLE_AGENT_AUTH=true
+CFN_AGENT_AUTH_TOKEN=${CFN_AGENT_AUTH_TOKEN}
+CFN_ENABLE_TLS=true
+CFN_TLS_CERT_PATH=/etc/cfn/certs/cert.pem
+CFN_TLS_KEY_PATH=/etc/cfn/certs/key.pem
+CFN_ENABLE_RATE_LIMITING=true
+CFN_RATE_LIMIT_REQUESTS_PER_MINUTE=1000
+
+# MCP Server
+CFN_MCP_SERVER_ENABLED=true
+CFN_MCP_SERVER_PORT=3000
+
+# Testing and Debugging (Production: DISABLED)
+CFN_TEST_MODE=false
+CFN_DEBUG_AGENT_SPAWN=false
+CFN_DEBUG_CONSENSUS=false
+CFN_DEBUG_MEMORY=false
+CFN_VERBOSE_LOGGING=false
+
+# Chaos Engineering (Production: DISABLED)
+CFN_CHAOS_ENABLED=false
+
+# Consensus Algorithm
+CFN_CONSENSUS_ALGORITHM=byzantine
+
+# Database (Production: PostgreSQL recommended)
+CFN_DB_ENABLED=true
+CFN_DB_TYPE=postgresql
+CFN_DB_HOST=${CFN_DB_HOST}
+CFN_DB_PORT=5432
+CFN_DB_NAME=cfn_metrics
+CFN_DB_USER=${CFN_DB_USER}
+CFN_DB_PASSWORD=${CFN_DB_PASSWORD}
+
+# Distributed Tracing
+CFN_TRACING_ENABLED=true
+CFN_TRACING_ENDPOINT=${CFN_TRACING_ENDPOINT}
+CFN_TRACING_SERVICE_NAME=claude-flow-novice

package/config/docker/env.staging

@@ -0,0 +1,70 @@
+# Docker Staging Environment
+# Used by: docker-compose.staging.yml
+
+# Environment
+NODE_ENV=staging
+
+# Agent Configuration (Staging: 100 agents)
+CFN_MAX_AGENTS=100
+CFN_SHARD_COUNT=16
+CFN_METRICS_ENABLED=true
+CFN_ALERTING_ENABLED=true
+CFN_LOG_LEVEL=info
+CFN_CONSENSUS_THRESHOLD=0.90
+CFN_ALERT_COORD_TIME_MS=5000
+
+# Memory and Storage (tmpfs recommended)
+CFN_BASE_DIR=/dev/shm/cfn
+CFN_AGENT_MEMORY_LIMIT_MB=100
+CFN_TOTAL_MEMORY_LIMIT_MB=10240
+
+# Performance
+CFN_AGENT_TIMEOUT_MS=30000
+CFN_CONSENSUS_TIMEOUT_MS=60000
+CFN_SWARM_INIT_TIMEOUT_MS=10000
+CFN_ENABLE_CACHING=true
+CFN_CACHE_TTL_SECONDS=300
+CFN_MAX_CONCURRENT_OPERATIONS=50
+
+# Monitoring
+CFN_METRICS_COLLECTION_INTERVAL_MS=5000
+CFN_METRICS_RETENTION_HOURS=168
+CFN_TRACK_COORDINATION_TIME=true
+CFN_TRACK_MEMORY_USAGE=true
+CFN_TRACK_AGENT_LIFECYCLE=true
+
+# Alerting Thresholds
+CFN_ALERT_MEMORY_THRESHOLD_PERCENT=80
+CFN_ALERT_AGENT_FAILURE_COUNT=3
+CFN_ALERT_CONSENSUS_FAILURE_THRESHOLD=0.70
+
+# Security (Staging: Enabled)
+CFN_ENABLE_AGENT_AUTH=true
+CFN_AGENT_AUTH_TOKEN=${CFN_AGENT_AUTH_TOKEN}
+CFN_ENABLE_TLS=false
+CFN_ENABLE_RATE_LIMITING=true
+CFN_RATE_LIMIT_REQUESTS_PER_MINUTE=500
+
+# MCP Server
+CFN_MCP_SERVER_ENABLED=true
+CFN_MCP_SERVER_PORT=3000
+
+# Testing and Debugging
+CFN_TEST_MODE=false
+CFN_DEBUG_AGENT_SPAWN=false
+CFN_DEBUG_CONSENSUS=false
+CFN_DEBUG_MEMORY=false
+CFN_VERBOSE_LOGGING=false
+
+# Chaos Engineering (Staging only)
+CFN_CHAOS_ENABLED=true
+CFN_CHAOS_FAILURE_RATE=0.05
+CFN_CHAOS_LATENCY_MS=100
+
+# Consensus Algorithm
+CFN_CONSENSUS_ALGORITHM=byzantine
+
+# Database (Optional)
+CFN_DB_ENABLED=true
+CFN_DB_TYPE=sqlite
+CFN_DB_PATH=/var/lib/cfn/metrics.db

package/config/k8s/configmap-development.yaml

@@ -0,0 +1,60 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: cfn-coordination-config-dev
+  namespace: claude-flow-novice
+  labels:
+    app: claude-flow-novice
+    environment: development
+    component: coordination
+data:
+  # Environment
+  NODE_ENV: "development"
+
+  # Agent Configuration (Development: 10 agents)
+  CFN_MAX_AGENTS: "10"
+  CFN_SHARD_COUNT: "4"
+  CFN_METRICS_ENABLED: "true"
+  CFN_ALERTING_ENABLED: "false"
+  CFN_LOG_LEVEL: "debug"
+  CFN_CONSENSUS_THRESHOLD: "0.90"
+  CFN_ALERT_COORD_TIME_MS: "3000"
+
+  # Memory and Storage
+  CFN_BASE_DIR: "/tmp/cfn"
+  CFN_AGENT_MEMORY_LIMIT_MB: "100"
+  CFN_TOTAL_MEMORY_LIMIT_MB: "2048"
+
+  # Performance
+  CFN_AGENT_TIMEOUT_MS: "30000"
+  CFN_CONSENSUS_TIMEOUT_MS: "60000"
+  CFN_SWARM_INIT_TIMEOUT_MS: "10000"
+  CFN_ENABLE_CACHING: "true"
+  CFN_CACHE_TTL_SECONDS: "300"
+  CFN_MAX_CONCURRENT_OPERATIONS: "10"
+
+  # Monitoring
+  CFN_METRICS_COLLECTION_INTERVAL_MS: "5000"
+  CFN_METRICS_RETENTION_HOURS: "24"
+  CFN_TRACK_COORDINATION_TIME: "true"
+  CFN_TRACK_MEMORY_USAGE: "true"
+  CFN_TRACK_AGENT_LIFECYCLE: "true"
+
+  # Security (Development: Disabled)
+  CFN_ENABLE_AGENT_AUTH: "false"
+  CFN_ENABLE_TLS: "false"
+  CFN_ENABLE_RATE_LIMITING: "false"
+
+  # MCP Server
+  CFN_MCP_SERVER_ENABLED: "true"
+  CFN_MCP_SERVER_PORT: "3000"
+
+  # Testing and Debugging
+  CFN_TEST_MODE: "false"
+  CFN_DEBUG_AGENT_SPAWN: "true"
+  CFN_DEBUG_CONSENSUS: "true"
+  CFN_DEBUG_MEMORY: "true"
+  CFN_VERBOSE_LOGGING: "true"
+
+  # Consensus Algorithm
+  CFN_CONSENSUS_ALGORITHM: "byzantine"

package/config/k8s/configmap-production.yaml

@@ -0,0 +1,85 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: cfn-coordination-config-prod
+  namespace: claude-flow-novice
+  labels:
+    app: claude-flow-novice
+    environment: production
+    component: coordination
+data:
+  # Environment
+  NODE_ENV: "production"
+
+  # Agent Configuration (Production: 500 agents)
+  CFN_MAX_AGENTS: "500"
+  CFN_SHARD_COUNT: "32"
+  CFN_METRICS_ENABLED: "true"
+  CFN_ALERTING_ENABLED: "true"
+  CFN_LOG_LEVEL: "warn"
+  CFN_CONSENSUS_THRESHOLD: "0.95"
+  CFN_ALERT_COORD_TIME_MS: "8000"
+
+  # Memory and Storage (tmpfs REQUIRED)
+  CFN_BASE_DIR: "/dev/shm/cfn"
+  CFN_AGENT_MEMORY_LIMIT_MB: "100"
+  CFN_TOTAL_MEMORY_LIMIT_MB: "51200"
+
+  # Performance
+  CFN_AGENT_TIMEOUT_MS: "30000"
+  CFN_CONSENSUS_TIMEOUT_MS: "60000"
+  CFN_SWARM_INIT_TIMEOUT_MS: "10000"
+  CFN_ENABLE_CACHING: "true"
+  CFN_CACHE_TTL_SECONDS: "600"
+  CFN_MAX_CONCURRENT_OPERATIONS: "100"
+
+  # Resource Cleanup
+  CFN_CLEANUP_INTERVAL_MS: "60000"
+  CFN_CLEANUP_STALE_AGENTS_ENABLED: "true"
+
+  # Monitoring
+  CFN_METRICS_COLLECTION_INTERVAL_MS: "5000"
+  CFN_METRICS_RETENTION_HOURS: "168"
+  CFN_TRACK_COORDINATION_TIME: "true"
+  CFN_TRACK_MEMORY_USAGE: "true"
+  CFN_TRACK_AGENT_LIFECYCLE: "true"
+
+  # Alerting Thresholds
+  CFN_ALERT_MEMORY_THRESHOLD_PERCENT: "80"
+  CFN_ALERT_AGENT_FAILURE_COUNT: "3"
+  CFN_ALERT_CONSENSUS_FAILURE_THRESHOLD: "0.70"
+
+  # Security (Production: REQUIRED)
+  CFN_ENABLE_AGENT_AUTH: "true"
+  CFN_ENABLE_TLS: "true"
+  CFN_TLS_CERT_PATH: "/etc/cfn/certs/cert.pem"
+  CFN_TLS_KEY_PATH: "/etc/cfn/certs/key.pem"
+  CFN_ENABLE_RATE_LIMITING: "true"
+  CFN_RATE_LIMIT_REQUESTS_PER_MINUTE: "1000"
+
+  # MCP Server
+  CFN_MCP_SERVER_ENABLED: "true"
+  CFN_MCP_SERVER_PORT: "3000"
+
+  # Testing and Debugging (Production: DISABLED)
+  CFN_TEST_MODE: "false"
+  CFN_DEBUG_AGENT_SPAWN: "false"
+  CFN_DEBUG_CONSENSUS: "false"
+  CFN_DEBUG_MEMORY: "false"
+  CFN_VERBOSE_LOGGING: "false"
+
+  # Chaos Engineering (Production: DISABLED)
+  CFN_CHAOS_ENABLED: "false"
+
+  # Consensus Algorithm
+  CFN_CONSENSUS_ALGORITHM: "byzantine"
+
+  # Database (Production: PostgreSQL)
+  CFN_DB_ENABLED: "true"
+  CFN_DB_TYPE: "postgresql"
+  CFN_DB_PORT: "5432"
+  CFN_DB_NAME: "cfn_metrics"
+
+  # Distributed Tracing
+  CFN_TRACING_ENABLED: "true"
+  CFN_TRACING_SERVICE_NAME: "claude-flow-novice"

package/config/k8s/configmap-staging.yaml

@@ -0,0 +1,76 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: cfn-coordination-config-staging
+  namespace: claude-flow-novice
+  labels:
+    app: claude-flow-novice
+    environment: staging
+    component: coordination
+data:
+  # Environment
+  NODE_ENV: "staging"
+
+  # Agent Configuration (Staging: 100 agents)
+  CFN_MAX_AGENTS: "100"
+  CFN_SHARD_COUNT: "16"
+  CFN_METRICS_ENABLED: "true"
+  CFN_ALERTING_ENABLED: "true"
+  CFN_LOG_LEVEL: "info"
+  CFN_CONSENSUS_THRESHOLD: "0.90"
+  CFN_ALERT_COORD_TIME_MS: "5000"
+
+  # Memory and Storage (tmpfs)
+  CFN_BASE_DIR: "/dev/shm/cfn"
+  CFN_AGENT_MEMORY_LIMIT_MB: "100"
+  CFN_TOTAL_MEMORY_LIMIT_MB: "10240"
+
+  # Performance
+  CFN_AGENT_TIMEOUT_MS: "30000"
+  CFN_CONSENSUS_TIMEOUT_MS: "60000"
+  CFN_SWARM_INIT_TIMEOUT_MS: "10000"
+  CFN_ENABLE_CACHING: "true"
+  CFN_CACHE_TTL_SECONDS: "300"
+  CFN_MAX_CONCURRENT_OPERATIONS: "50"
+
+  # Monitoring
+  CFN_METRICS_COLLECTION_INTERVAL_MS: "5000"
+  CFN_METRICS_RETENTION_HOURS: "168"
+  CFN_TRACK_COORDINATION_TIME: "true"
+  CFN_TRACK_MEMORY_USAGE: "true"
+  CFN_TRACK_AGENT_LIFECYCLE: "true"
+
+  # Alerting Thresholds
+  CFN_ALERT_MEMORY_THRESHOLD_PERCENT: "80"
+  CFN_ALERT_AGENT_FAILURE_COUNT: "3"
+  CFN_ALERT_CONSENSUS_FAILURE_THRESHOLD: "0.70"
+
+  # Security (Staging: Enabled)
+  CFN_ENABLE_AGENT_AUTH: "true"
+  CFN_ENABLE_TLS: "false"
+  CFN_ENABLE_RATE_LIMITING: "true"
+  CFN_RATE_LIMIT_REQUESTS_PER_MINUTE: "500"
+
+  # MCP Server
+  CFN_MCP_SERVER_ENABLED: "true"
+  CFN_MCP_SERVER_PORT: "3000"
+
+  # Testing and Debugging
+  CFN_TEST_MODE: "false"
+  CFN_DEBUG_AGENT_SPAWN: "false"
+  CFN_DEBUG_CONSENSUS: "false"
+  CFN_DEBUG_MEMORY: "false"
+  CFN_VERBOSE_LOGGING: "false"
+
+  # Chaos Engineering (Staging only)
+  CFN_CHAOS_ENABLED: "true"
+  CFN_CHAOS_FAILURE_RATE: "0.05"
+  CFN_CHAOS_LATENCY_MS: "100"
+
+  # Consensus Algorithm
+  CFN_CONSENSUS_ALGORITHM: "byzantine"
+
+  # Database
+  CFN_DB_ENABLED: "true"
+  CFN_DB_TYPE: "sqlite"
+  CFN_DB_PATH: "/var/lib/cfn/metrics.db"

package/config/k8s/secret-production.yaml

@@ -0,0 +1,62 @@
+apiVersion: v1
+kind: Secret
+metadata:
+  name: cfn-coordination-secrets-prod
+  namespace: claude-flow-novice
+  labels:
+    app: claude-flow-novice
+    environment: production
+    component: coordination
+type: Opaque
+stringData:
+  # Agent Authentication Token
+  # Generate with: openssl rand -base64 32
+  CFN_AGENT_AUTH_TOKEN: "REPLACE_WITH_PRODUCTION_TOKEN"
+
+  # Database Credentials (PostgreSQL)
+  CFN_DB_HOST: "cfn-postgres.database.svc.cluster.local"
+  CFN_DB_USER: "cfn_production"
+  CFN_DB_PASSWORD: "REPLACE_WITH_DB_PASSWORD"
+
+  # GitHub Integration (optional)
+  CFN_GITHUB_TOKEN: "REPLACE_WITH_GITHUB_TOKEN"
+
+  # Distributed Tracing Endpoint
+  CFN_TRACING_ENDPOINT: "http://jaeger-collector.monitoring.svc.cluster.local:9411"
+
+  # Neural API Key (experimental features)
+  CFN_NEURAL_API_KEY: "REPLACE_WITH_NEURAL_API_KEY"
+---
+# Production Secret Management Best Practices:
+#
+# 1. DO NOT commit actual secrets to git
+# 2. Use external secret management:
+#    - AWS Secrets Manager
+#    - Azure Key Vault
+#    - HashiCorp Vault
+#    - Google Secret Manager
+#
+# 3. Create secrets using kubectl with --dry-run:
+#    kubectl create secret generic cfn-coordination-secrets-prod \
+#      --from-literal=CFN_AGENT_AUTH_TOKEN="$(openssl rand -base64 32)" \
+#      --from-literal=CFN_DB_PASSWORD="your-secure-password" \
+#      --dry-run=client -o yaml | kubectl apply -f -
+#
+# 4. Use External Secrets Operator for GitOps:
+#    apiVersion: external-secrets.io/v1beta1
+#    kind: ExternalSecret
+#    metadata:
+#      name: cfn-coordination-secrets-prod
+#    spec:
+#      secretStoreRef:
+#        name: aws-secrets-manager
+#      target:
+#        name: cfn-coordination-secrets-prod
+#      data:
+#        - secretKey: CFN_AGENT_AUTH_TOKEN
+#          remoteRef:
+#            key: prod/cfn/auth-token
+#
+# 5. Rotate secrets regularly (every 90 days minimum)
+# 6. Use RBAC to restrict secret access
+# 7. Enable audit logging for secret access

package/config/k8s/secret-staging.yaml

@@ -0,0 +1,36 @@
+apiVersion: v1
+kind: Secret
+metadata:
+  name: cfn-coordination-secrets-staging
+  namespace: claude-flow-novice
+  labels:
+    app: claude-flow-novice
+    environment: staging
+    component: coordination
+type: Opaque
+stringData:
+  # Agent Authentication Token
+  # Generate with: openssl rand -base64 32
+  CFN_AGENT_AUTH_TOKEN: "REPLACE_WITH_STAGING_TOKEN"
+
+  # Database Credentials (if using external DB)
+  CFN_DB_USER: "cfn_staging"
+  CFN_DB_PASSWORD: "REPLACE_WITH_DB_PASSWORD"
+
+  # GitHub Integration (optional)
+  CFN_GITHUB_TOKEN: "REPLACE_WITH_GITHUB_TOKEN"
+
+  # Neural API Key (experimental features)
+  CFN_NEURAL_API_KEY: "REPLACE_WITH_NEURAL_API_KEY"
+---
+# Usage Instructions:
+# 1. Create secret: kubectl apply -f secret-staging.yaml
+# 2. Verify: kubectl get secret cfn-coordination-secrets-staging -n claude-flow-novice
+# 3. Update deployment to reference secret values:
+#
+# env:
+#   - name: CFN_AGENT_AUTH_TOKEN
+#     valueFrom:
+#       secretKeyRef:
+#         name: cfn-coordination-secrets-staging
+#         key: CFN_AGENT_AUTH_TOKEN

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "claude-flow-novice",
-  "version": "1.6.5",
+  "version": "1.6.6",
   "description": "Standalone Claude Flow for beginners - AI agent orchestration made easy with enhanced TDD testing pipeline, memory safety protection, and automated hooks. Enhanced init command creates complete agent system, MCP configuration with 30 essential tools, and automated hooks with single-file testing, real-time coverage analysis, and advanced validation. Features memory leak prevention for WSL/Windows environments and pre-tool safety validation. Fully standalone with zero external dependencies, complete project setup in one command.",
   "mcpName": "io.github.ruvnet/claude-flow",
   "main": ".claude-flow-novice/dist/index.js",

package/scripts/monitoring/dashboards/rate-limiting-dashboard.json

@@ -0,0 +1,211 @@
+{
+  "dashboard": {
+    "title": "CFN Rate Limiting & Backpressure Monitoring",
+    "description": "Real-time monitoring of message inbox utilization, backpressure events, and overflow alerts",
+    "version": "1.0.0",
+    "tags": ["rate-limiting", "backpressure", "inbox", "coordination"],
+    "timezone": "UTC",
+    "refresh": "10s",
+    "panels": [
+      {
+        "id": 1,
+        "title": "Inbox Utilization by Agent",
+        "type": "timeseries",
+        "gridPos": { "x": 0, "y": 0, "w": 12, "h": 8 },
+        "targets": [
+          {
+            "metric": "inbox.utilization",
+            "legend": "{{agent}}",
+            "unit": "percent"
+          }
+        ],
+        "thresholds": [
+          { "value": 75, "color": "yellow", "label": "Warning" },
+          { "value": 90, "color": "red", "label": "Critical" }
+        ],
+        "description": "Message inbox utilization percentage per agent (max 100 messages)"
+      },
+      {
+        "id": 2,
+        "title": "Inbox Message Count",
+        "type": "timeseries",
+        "gridPos": { "x": 12, "y": 0, "w": 12, "h": 8 },
+        "targets": [
+          {
+            "metric": "inbox.size",
+            "legend": "{{agent}}",
+            "unit": "count"
+          }
+        ],
+        "thresholds": [
+          { "value": 75, "color": "yellow", "label": "Warning (75 msgs)" },
+          { "value": 90, "color": "red", "label": "Critical (90 msgs)" }
+        ],
+        "description": "Absolute message count in agent inboxes"
+      },
+      {
+        "id": 3,
+        "title": "Backpressure Events Rate",
+        "type": "timeseries",
+        "gridPos": { "x": 0, "y": 8, "w": 12, "h": 8 },
+        "targets": [
+          {
+            "metric": "backpressure.events_per_min",
+            "legend": "Backpressure events/min",
+            "unit": "count"
+          }
+        ],
+        "thresholds": [
+          { "value": 100, "color": "yellow", "label": "Warning threshold" }
+        ],
+        "description": "Rate of backpressure wait events (high rate indicates system load)"
+      },
+      {
+        "id": 4,
+        "title": "Message Send Failures",
+        "type": "timeseries",
+        "gridPos": { "x": 12, "y": 8, "w": 12, "h": 8 },
+        "targets": [
+          {
+            "metric": "coordination.send_failures_per_min",
+            "legend": "Send failures/min",
+            "unit": "count"
+          }
+        ],
+        "thresholds": [
+          { "value": 10, "color": "red", "label": "Critical threshold" }
+        ],
+        "description": "Message delivery failure rate (critical if >10/min)"
+      },
+      {
+        "id": 5,
+        "title": "Inbox Overflow Events",
+        "type": "timeseries",
+        "gridPos": { "x": 0, "y": 16, "w": 12, "h": 8 },
+        "targets": [
+          {
+            "metric": "inbox.overflow_events_per_min",
+            "legend": "Overflow events/min",
+            "unit": "count"
+          }
+        ],
+        "thresholds": [
+          { "value": 1, "color": "red", "label": "Any overflow is critical" }
+        ],
+        "description": "Inbox overflow events (messages dropped due to full inbox)"
+      },
+      {
+        "id": 6,
+        "title": "Alert Summary",
+        "type": "stat",
+        "gridPos": { "x": 12, "y": 16, "w": 6, "h": 8 },
+        "targets": [
+          {
+            "query": "count_alerts_by_severity",
+            "fields": ["critical", "warning", "info"]
+          }
+        ],
+        "description": "Alert counts by severity level (last hour)"
+      },
+      {
+        "id": 7,
+        "title": "Top Utilized Agents",
+        "type": "table",
+        "gridPos": { "x": 18, "y": 16, "w": 6, "h": 8 },
+        "targets": [
+          {
+            "query": "top_inbox_utilization",
+            "fields": ["agent", "utilization", "message_count"],
+            "limit": 10,
+            "order": "desc"
+          }
+        ],
+        "description": "Agents with highest inbox utilization"
+      }
+    ],
+    "annotations": [
+      {
+        "name": "Rate Limiting Alerts",
+        "datasource": "cfn-alerts",
+        "filter": {
+          "tags": ["inbox_high_utilization", "backpressure_high_rate", "inbox_overflow_detected"]
+        },
+        "color": "red"
+      }
+    ],
+    "variables": [
+      {
+        "name": "agent",
+        "type": "query",
+        "query": "SELECT DISTINCT agent FROM inbox_metrics",
+        "description": "Filter by specific agent",
+        "multi": true,
+        "includeAll": true
+      },
+      {
+        "name": "timeRange",
+        "type": "interval",
+        "options": ["5m", "15m", "1h", "6h", "24h"],
+        "default": "1h",
+        "description": "Time range for metrics"
+      }
+    ]
+  },
+  "queries": {
+    "count_alerts_by_severity": {
+      "description": "Count alerts grouped by severity",
+      "source": "/dev/shm/cfn-alerts.jsonl",
+      "aggregation": "GROUP BY severity, COUNT(*)",
+      "timeWindow": "1h"
+    },
+    "top_inbox_utilization": {
+      "description": "Rank agents by inbox utilization",
+      "source": "/dev/shm/cfn-metrics.jsonl",
+      "query": "SELECT agent, MAX(value) as utilization FROM metrics WHERE metric='inbox.utilization' GROUP BY agent ORDER BY utilization DESC LIMIT 10",
+      "timeWindow": "5m"
+    }
+  },
+  "alertRules": [
+    {
+      "name": "Inbox Critical Utilization",
+      "condition": "inbox.utilization >= 90",
+      "severity": "critical",
+      "message": "Agent {{agent}} inbox at {{value}}% utilization (critical threshold: 90%)",
+      "actions": ["emit_alert", "notify_oncall"]
+    },
+    {
+      "name": "Inbox Warning Utilization",
+      "condition": "inbox.utilization >= 75 AND inbox.utilization < 90",
+      "severity": "warning",
+      "message": "Agent {{agent}} inbox at {{value}}% utilization (warning threshold: 75%)",
+      "actions": ["emit_alert"]
+    },
+    {
+      "name": "Backpressure High Rate",
+      "condition": "backpressure.events_per_min > 100",
+      "severity": "warning",
+      "message": "Backpressure events exceeding threshold: {{value}} events/min (threshold: 100/min)",
+      "actions": ["emit_alert"]
+    },
+    {
+      "name": "Message Send Failures Critical",
+      "condition": "coordination.send_failures_per_min > 10",
+      "severity": "critical",
+      "message": "Message send failures critical: {{value}} failures/min (threshold: 10/min)",
+      "actions": ["emit_alert", "notify_oncall", "trigger_incident"]
+    },
+    {
+      "name": "Inbox Overflow Detected",
+      "condition": "inbox.overflow_events_per_min > 0",
+      "severity": "critical",
+      "message": "Inbox overflow detected: {{value}} overflow events in last minute",
+      "actions": ["emit_alert", "notify_oncall", "trigger_incident"]
+    }
+  ],
+  "metadata": {
+    "createdBy": "devops-engineer",
+    "phase": "1",
+    "sprint": "1.5",
+    "lastUpdated": "2025-10-06T19:35:00Z"
+  }
+}