pangea 0.0.45 → 0.0.46

data/lib/pangea/components/global_traffic_manager/types.rb

@@ -1,282 +0,0 @@
-# frozen_string_literal: true
-# Copyright 2025 The Pangea Authors
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-
-require 'dry-struct'
-require 'pangea/resources/types'
-
-module Pangea
-  module Components
-    module GlobalTrafficManager
-      # Endpoint configuration for traffic management
-      class EndpointConfig < Dry::Struct
-        transform_keys(&:to_sym)
-        
-        attribute :region, Types::String
-        attribute :endpoint_id, Types::String
-        attribute :endpoint_type, Types::String.enum('ALB', 'NLB', 'INSTANCE', 'EIP', 'EC2').default('ALB')
-        attribute :weight, Types::Integer.default(100)
-        attribute :priority, Types::Integer.default(100)
-        attribute :enabled, Types::Bool.default(true)
-        attribute :health_check_enabled, Types::Bool.default(true)
-        attribute :client_ip_preservation, Types::Bool.default(false)
-        attribute :metadata, Types::Hash.default({}.freeze)
-      end
-      
-      # Traffic policy configuration
-      class TrafficPolicyConfig < Dry::Struct
-        transform_keys(&:to_sym)
-        
-        attribute :policy_name, Types::String
-        attribute :policy_type, Types::String.enum('latency', 'weighted', 'geoproximity', 'geolocation', 'failover', 'multivalue').default('latency')
-        attribute :health_check_interval, Types::Integer.default(30)
-        attribute :health_check_path, Types::String.default('/health')
-        attribute :health_check_protocol, Types::String.enum('HTTP', 'HTTPS', 'TCP').default('HTTP')
-        attribute :unhealthy_threshold, Types::Integer.default(3)
-        attribute :healthy_threshold, Types::Integer.default(2)
-        attribute :health_check_timeout, Types::Integer.default(5)
-      end
-      
-      # Geo-routing configuration
-      class GeoRoutingConfig < Dry::Struct
-        transform_keys(&:to_sym)
-        
-        attribute :enabled, Types::Bool.default(false)
-        attribute :default_location, Types::String.default('*')
-        attribute :location_rules, Types::Array.of(Types::Hash).default([].freeze)
-        attribute :bias_adjustments, Types::Hash.default({}.freeze)
-        attribute :continent_mapping, Types::Hash.default({}.freeze)
-      end
-      
-      # Performance optimization configuration
-      class PerformanceConfig < Dry::Struct
-        transform_keys(&:to_sym)
-        
-        attribute :tcp_optimization, Types::Bool.default(true)
-        attribute :flow_logs_enabled, Types::Bool.default(true)
-        attribute :flow_logs_s3_bucket, Types::String.optional
-        attribute :flow_logs_s3_prefix, Types::String.default('global-traffic-flow-logs/')
-        attribute :connection_draining_timeout, Types::Integer.default(30)
-        attribute :idle_timeout, Types::Integer.default(60)
-      end
-      
-      # Advanced routing features
-      class AdvancedRoutingConfig < Dry::Struct
-        transform_keys(&:to_sym)
-        
-        attribute :weighted_distribution, Types::Hash.default({}.freeze)
-        attribute :canary_deployment, Types::Hash.default({}.freeze)
-        attribute :blue_green_deployment, Types::Hash.default({}.freeze)
-        attribute :traffic_dials, Types::Hash.default({}.freeze)
-        attribute :custom_headers, Types::Array.of(Types::Hash).default([].freeze)
-        attribute :request_routing_rules, Types::Array.of(Types::Hash).default([].freeze)
-      end
-      
-      # Monitoring and observability configuration
-      class ObservabilityConfig < Dry::Struct
-        transform_keys(&:to_sym)
-        
-        attribute :cloudwatch_enabled, Types::Bool.default(true)
-        attribute :detailed_metrics, Types::Bool.default(true)
-        attribute :access_logs_enabled, Types::Bool.default(true)
-        attribute :distributed_tracing, Types::Bool.default(true)
-        attribute :real_user_monitoring, Types::Bool.default(false)
-        attribute :synthetic_checks, Types::Array.of(Types::Hash).default([].freeze)
-        attribute :alerting_enabled, Types::Bool.default(true)
-        attribute :notification_topic_ref, Types::ResourceReference.optional
-      end
-      
-      # Security configuration
-      class SecurityConfig < Dry::Struct
-        transform_keys(&:to_sym)
-        
-        attribute :ddos_protection, Types::Bool.default(true)
-        attribute :waf_enabled, Types::Bool.default(false)
-        attribute :waf_acl_ref, Types::ResourceReference.optional
-        attribute :allowed_countries, Types::Array.of(Types::String).default([].freeze)
-        attribute :blocked_countries, Types::Array.of(Types::String).default([].freeze)
-        attribute :rate_limiting, Types::Hash.default({}.freeze)
-        attribute :ip_allowlist, Types::Array.of(Types::String).default([].freeze)
-        attribute :ip_blocklist, Types::Array.of(Types::String).default([].freeze)
-      end
-      
-      # CloudFront distribution configuration
-      class CloudFrontConfig < Dry::Struct
-        transform_keys(&:to_sym)
-        
-        attribute :enabled, Types::Bool.default(true)
-        attribute :price_class, Types::String.default('PriceClass_All')
-        attribute :cache_behaviors, Types::Array.of(Types::Hash).default([].freeze)
-        attribute :origin_shield_enabled, Types::Bool.default(false)
-        attribute :origin_shield_region, Types::String.optional
-        attribute :compress, Types::Bool.default(true)
-        attribute :viewer_protocol_policy, Types::String.default('redirect-to-https')
-        attribute :custom_error_responses, Types::Array.of(Types::Hash).default([].freeze)
-      end
-      
-      # Main component attributes
-      class GlobalTrafficManagerAttributes < Dry::Struct
-        transform_keys(&:to_sym)
-        
-        # Core configuration
-        attribute :manager_name, Types::String
-        attribute :manager_description, Types::String.default("Global traffic management infrastructure")
-        attribute :domain_name, Types::String
-        attribute :certificate_arn, Types::String.optional
-        
-        # Endpoints to manage
-        attribute :endpoints, Types::Array.of(EndpointConfig).constrained(min_size: 1)
-        
-        # Traffic policies
-        attribute :traffic_policies, Types::Array.of(TrafficPolicyConfig).default([].freeze)
-        attribute :default_policy, Types::String.enum('latency', 'weighted', 'geoproximity').default('latency')
-        
-        # Geo-routing configuration
-        attribute :geo_routing, GeoRoutingConfig.default { GeoRoutingConfig.new({}) }
-        
-        # Performance optimization
-        attribute :performance, PerformanceConfig.default { PerformanceConfig.new({}) }
-        
-        # Advanced routing
-        attribute :advanced_routing, AdvancedRoutingConfig.default { AdvancedRoutingConfig.new({}) }
-        
-        # Observability
-        attribute :observability, ObservabilityConfig.default { ObservabilityConfig.new({}) }
-        
-        # Security
-        attribute :security, SecurityConfig.default { SecurityConfig.new({}) }
-        
-        # CloudFront configuration
-        attribute :cloudfront, CloudFrontConfig.default { CloudFrontConfig.new({}) }
-        
-        # Global Accelerator configuration
-        attribute :enable_global_accelerator, Types::Bool.default(true)
-        attribute :global_accelerator_attributes, Types::Hash.default({}.freeze)
-        
-        # Route 53 configuration
-        attribute :enable_route53_policies, Types::Bool.default(true)
-        attribute :route53_hosted_zone_ref, Types::ResourceReference.optional
-        
-        # Multi-CDN strategy
-        attribute :enable_multi_cdn, Types::Bool.default(false)
-        attribute :cdn_providers, Types::Array.of(Types::String).default(['cloudfront'].freeze)
-        
-        # Tags
-        attribute :tags, Types::Hash.default({}.freeze)
-        
-        # Custom validations
-        def validate!
-          errors = []
-          
-          # Validate endpoints
-          endpoint_regions = endpoints.map(&:region)
-          if endpoint_regions.uniq.length != endpoint_regions.length
-            errors << "Duplicate regions found in endpoints"
-          end
-          
-          # Validate weights sum to reasonable value for weighted routing
-          if traffic_policies.any? { |p| p.policy_type == 'weighted' }
-            total_weight = endpoints.sum(&:weight)
-            if total_weight == 0
-              errors << "Total endpoint weight must be greater than 0 for weighted routing"
-            end
-          end
-          
-          # Validate health check configuration
-          traffic_policies.each do |policy|
-            if policy.health_check_interval < 10 || policy.health_check_interval > 300
-              errors << "Health check interval must be between 10 and 300 seconds"
-            end
-            
-            if policy.health_check_timeout >= policy.health_check_interval
-              errors << "Health check timeout must be less than interval"
-            end
-            
-            if policy.unhealthy_threshold < 2 || policy.unhealthy_threshold > 10
-              errors << "Unhealthy threshold must be between 2 and 10"
-            end
-          end
-          
-          # Validate geo-routing configuration
-          if geo_routing.enabled
-            if geo_routing.location_rules.empty?
-              errors << "Geo-routing enabled but no location rules defined"
-            end
-            
-            geo_routing.location_rules.each do |rule|
-              unless rule[:location] && rule[:endpoint_region]
-                errors << "Geo-routing rules must specify location and endpoint_region"
-              end
-            end
-          end
-          
-          # Validate performance configuration
-          if performance.flow_logs_enabled && !performance.flow_logs_s3_bucket
-            errors << "Flow logs enabled but S3 bucket not specified"
-          end
-          
-          if performance.connection_draining_timeout < 0 || performance.connection_draining_timeout > 3600
-            errors << "Connection draining timeout must be between 0 and 3600 seconds"
-          end
-          
-          # Validate security configuration
-          if security.waf_enabled && !security.waf_acl_ref
-            errors << "WAF enabled but no ACL reference provided"
-          end
-          
-          if security.allowed_countries.any? && security.blocked_countries.any?
-            overlap = security.allowed_countries & security.blocked_countries
-            if overlap.any?
-              errors << "Countries cannot be both allowed and blocked: #{overlap.join(', ')}"
-            end
-          end
-          
-          # Validate CloudFront configuration
-          if cloudfront.enabled
-            if cloudfront.origin_shield_enabled && !cloudfront.origin_shield_region
-              errors << "Origin Shield enabled but region not specified"
-            end
-            
-            valid_price_classes = ['PriceClass_All', 'PriceClass_200', 'PriceClass_100']
-            unless valid_price_classes.include?(cloudfront.price_class)
-              errors << "Invalid CloudFront price class"
-            end
-          end
-          
-          # Validate advanced routing
-          if advanced_routing.canary_deployment.any?
-            canary_percentage = advanced_routing.canary_deployment[:percentage] || 0
-            if canary_percentage < 0 || canary_percentage > 50
-              errors << "Canary deployment percentage must be between 0 and 50"
-            end
-          end
-          
-          # Validate multi-CDN configuration
-          if enable_multi_cdn
-            valid_providers = ['cloudfront', 'fastly', 'cloudflare', 'akamai']
-            invalid_providers = cdn_providers - valid_providers
-            if invalid_providers.any?
-              errors << "Invalid CDN providers: #{invalid_providers.join(', ')}"
-            end
-          end
-          
-          raise ArgumentError, errors.join(", ") unless errors.empty?
-          
-          true
-        end
-      end
-    end
-  end
-end

data/lib/pangea/components/green_data_lifecycle/CLAUDE.md

@@ -1,353 +0,0 @@
-# Green Data Lifecycle - Architecture Documentation
-
-## Component Purpose
-
-The Green Data Lifecycle component addresses a critical sustainability challenge in cloud computing: the carbon footprint of data storage. While compute workloads are transient, data persists indefinitely, continuously consuming energy for storage, cooling, and redundancy. This component transforms passive data storage into an active sustainability practice by intelligently managing data lifecycle based on access patterns and carbon intensity of different storage tiers.
-
-## The Carbon Cost of Data Storage
-
-### Understanding Storage Carbon Footprint
-
-Different storage technologies have vastly different carbon footprints:
-
-1. **SSD/NVMe (STANDARD)**: High-performance storage requires constant power for controllers, wear leveling, and cooling. Carbon intensity: ~0.55 gCO2/GB/month
-
-2. **HDD (STANDARD_IA)**: Spinning disks can spin down when not accessed, reducing power consumption. Carbon intensity: ~0.35 gCO2/GB/month
-
-3. **Tape (GLACIER/DEEP_ARCHIVE)**: Tape storage requires power only during read/write operations. Carbon intensity: ~0.05-0.15 gCO2/GB/month
-
-4. **Redundancy Factor**: All storage includes replication overhead, typically 3x for durability, impacting total carbon footprint
-
-## Architecture Decisions
-
-### 1. Multi-Tier Storage Strategy
-
-**Decision**: Implement automatic progression through storage tiers based on access patterns.
-
-**Rationale**:
-- 90% of data becomes cold within 90 days
-- Cold data on hot storage wastes energy continuously
-- Intelligent tiering can reduce carbon footprint by 80%+
-- Access pattern analysis prevents premature archival
-
-**Implementation**:
-```
-STANDARD (Hot) → INTELLIGENT_TIERING (Warm) → STANDARD_IA (Cool) → GLACIER_IR (Cold) → DEEP_ARCHIVE (Frozen)
-```
-
-### 2. Access Pattern Intelligence
-
-**Decision**: Use Lambda-based access pattern analysis rather than relying solely on S3's built-in analytics.
-
-**Rationale**:
-- Custom analysis allows carbon-weighted decisions
-- Can incorporate business logic and compliance rules
-- Enables predictive modeling for seasonal data
-- Provides granular control over transitions
-
-**Trade-offs**:
-- Additional Lambda execution costs
-- Complexity vs. native S3 lifecycle rules
-- Requires periodic analysis runs
-
-### 3. Carbon-First Optimization
-
-**Decision**: Default to carbon-optimized strategy over cost-optimized.
-
-**Rationale**:
-- Aligns with sustainability goals
-- Carbon and cost optimization often align (cold storage is cheaper)
-- Demonstrates environmental commitment
-- Future carbon pricing makes this economically sound
-
-**Implementation**:
-- Calculate carbon intensity per storage class
-- Weight transition decisions by carbon reduction
-- Track and report carbon savings metrics
-
-### 4. Compliance and Governance Integration
-
-**Decision**: Build compliance features directly into lifecycle management.
-
-**Rationale**:
-- Prevents accidental deletion of regulated data
-- Enables audit trails for data lifecycle
-- Supports legal hold and retention policies
-- Satisfies regulatory requirements (GDPR, HIPAA, SOX)
-
-**Features**:
-- Legal hold tags prevent transitions/deletions
-- Compliance mode enforces minimum retention
-- Audit logging for all lifecycle events
-- Deletion protection with override controls
-
-### 5. Intelligent Tiering as Default
-
-**Decision**: Enable S3 Intelligent-Tiering by default for unpredictable access patterns.
-
-**Rationale**:
-- Automatically optimizes storage costs
-- No retrieval fees for access
-- Handles varying access patterns
-- Reduces manual optimization needs
-
-**Configuration**:
-- Archive Access tier after 90 days
-- Deep Archive Access tier after 180 days
-- Automatic restoration on access
-
-## Security Architecture
-
-### 1. Encryption Throughout Lifecycle
-
-- All storage tiers use SSE-S3 or SSE-KMS
-- Encryption keys rotate automatically
-- No decryption during tier transitions
-- Compliance with data-at-rest requirements
-
-### 2. Access Control Preservation
-
-- IAM policies remain consistent across tiers
-- Bucket policies apply to all storage classes
-- Object ACLs preserved during transitions
-- VPC endpoints for private access
-
-### 3. Audit and Compliance
-
-- CloudTrail logs all lifecycle transitions
-- S3 Inventory provides storage class reporting
-- Compliance tags prevent unauthorized changes
-- Automated compliance validation
-
-## Scalability Patterns
-
-### 1. Massive Scale Optimization
-
-**Challenge**: Analyzing millions of objects efficiently
-
-**Solution**:
-- S3 Inventory for bulk analysis
-- Parallel Lambda processing
-- DynamoDB for access pattern tracking
-- Incremental analysis with checkpointing
-
-### 2. Multi-Region Considerations
-
-**Pattern**: Regional carbon optimization
-
-```ruby
-# Deploy to regions with renewable energy
-renewable_regions = ["us-west-2", "eu-north-1", "ca-central-1"]
-renewable_regions.each do |region|
-  deploy_green_lifecycle(region)
-end
-```
-
-### 3. Organizational Scale
-
-**Pattern**: Centralized lifecycle management
-
-```ruby
-# Organization-wide lifecycle policies
-aws_organizations_policy(:green_storage_policy, {
-  content: lifecycle_policy_document,
-  type: "LIFECYCLE_POLICY"
-})
-```
-
-## Cost Architecture
-
-### 1. Storage Cost Optimization
-
-| Transition | Cost Reduction | Carbon Reduction |
-|------------|---------------|------------------|
-| STANDARD → STANDARD_IA | 54% | 36% |
-| STANDARD → GLACIER_IR | 82% | 73% |
-| STANDARD → DEEP_ARCHIVE | 95% | 91% |
-
-### 2. Operational Cost Considerations
-
-**Lambda Costs**:
-- Access analyzer: ~$0.10/million objects/month
-- Carbon optimizer: ~$0.05/million objects/month
-- Lifecycle manager: ~$0.08/million objects/month
-
-**S3 API Costs**:
-- Lifecycle transitions: $0.01/1000 requests
-- Tagging operations: $0.01/10000 tags
-- Inventory reports: $0.0025/million objects
-
-### 3. ROI Calculation
-
-```
-Monthly Savings = (Storage Cost Reduction) + (Carbon Credit Value) - (Operational Costs)
-Typical ROI: 300-500% within 6 months
-```
-
-## Monitoring Strategy
-
-### 1. Carbon Metrics
-
-**Real-time Tracking**:
-- Carbon footprint per storage class
-- Carbon intensity trends
-- Carbon savings vs. baseline
-- Regional carbon optimization
-
-**Dashboard Widgets**:
-```json
-{
-  "CarbonFootprint": {
-    "metric": "TotalCarbonFootprint",
-    "stat": "Average",
-    "period": 86400
-  },
-  "StorageEfficiency": {
-    "metric": "CarbonPerGB",
-    "stat": "Average",
-    "period": 86400
-  }
-}
-```
-
-### 2. Access Pattern Intelligence
-
-**Pattern Recognition**:
-- Hot data identification (accessed > 1x/day)
-- Warm data patterns (accessed > 1x/week)
-- Cool data trends (accessed > 1x/month)
-- Cold data detection (accessed < 1x/quarter)
-
-### 3. Compliance Monitoring
-
-**Automated Checks**:
-- Legal hold compliance
-- Retention policy adherence
-- Deletion protection status
-- Audit trail completeness
-
-## Integration Patterns
-
-### 1. Event-Driven Transitions
-
-```ruby
-# Trigger analysis on upload
-s3_event = aws_s3_bucket_notification(bucket, {
-  lambda_function_arn: green_lifecycle.access_analyzer_function.arn,
-  events: ["s3:ObjectCreated:*"]
-})
-```
-
-### 2. Scheduled Optimization
-
-```ruby
-# Daily carbon optimization
-schedule = aws_eventbridge_schedule(:daily_optimization, {
-  schedule_expression: "cron(0 2 * * ? *)",  # 2 AM daily
-  target: {
-    arn: green_lifecycle.carbon_optimizer_function.arn
-  }
-})
-```
-
-### 3. Cross-Component Integration
-
-```ruby
-# Integrate with Carbon Aware Compute
-carbon_compute = CarbonAwareCompute.build(...)
-green_storage = GreenDataLifecycle.build(...)
-
-# Store compute results sustainably
-configure_compute_output(carbon_compute, green_storage.primary_bucket)
-```
-
-## Advanced Features
-
-### 1. Predictive Lifecycle Management
-
-**ML-Based Predictions**:
-- Analyze historical access patterns
-- Predict future access likelihood
-- Preemptive tier optimization
-- Seasonal pattern recognition
-
-### 2. Carbon-Aware Replication
-
-**Strategy**: Replicate to low-carbon regions
-
-```ruby
-replication_config = {
-  rules: [{
-    destination: {
-      bucket: renewable_region_bucket,
-      storage_class: "GLACIER_IR"  # Low carbon storage
-    },
-    filter: {
-      tag: {
-        key: "ReplicationStrategy",
-        value: "carbon-optimized"
-      }
-    }
-  }]
-}
-```
-
-### 3. Lifecycle Simulation
-
-**What-If Analysis**:
-- Simulate different lifecycle strategies
-- Predict carbon and cost impact
-- A/B test transition timings
-- Optimize for specific goals
-
-## Performance Characteristics
-
-### 1. Transition Performance
-
-- STANDARD → STANDARD_IA: < 24 hours
-- STANDARD_IA → GLACIER_IR: < 24 hours
-- Any → INTELLIGENT_TIERING: Immediate
-- Bulk transitions: Up to 1 billion objects/day
-
-### 2. Retrieval Latencies
-
-| Storage Class | Retrieval Time | Use Case |
-|--------------|----------------|----------|
-| STANDARD | Milliseconds | Active data |
-| STANDARD_IA | Milliseconds | Backup data |
-| GLACIER_IR | 1-5 minutes | Archived data |
-| GLACIER | 1-12 hours | Cold archives |
-| DEEP_ARCHIVE | 12-48 hours | Compliance |
-
-### 3. Analysis Performance
-
-- Access pattern analysis: 1M objects/minute
-- Carbon calculation: 10M objects/hour
-- Lifecycle execution: 100K transitions/hour
-
-## Future Enhancements
-
-### 1. AI-Powered Optimization
-
-- GPT-based access prediction
-- Anomaly detection for unusual access
-- Natural language lifecycle policies
-- Automated optimization suggestions
-
-### 2. Blockchain Integration
-
-- Immutable audit trails
-- Carbon credit tokenization
-- Decentralized storage verification
-- Smart contract lifecycle rules
-
-### 3. Quantum-Ready Architecture
-
-- Post-quantum encryption preparation
-- Quantum-safe hash algorithms
-- Future-proof security architecture
-- Quantum computing optimization
-
-## Conclusion
-
-The Green Data Lifecycle component demonstrates that sustainable data storage is not only possible but economically advantageous. By intelligently managing data lifecycle based on access patterns and carbon intensity, organizations can reduce their storage carbon footprint by up to 91% while simultaneously reducing costs by up to 95%. This component proves that environmental responsibility and business efficiency are complementary goals in modern cloud architecture.