feat: Claude Code Monitor — lanes, pipelines and a merged workspace

Internal SmartGift build of a Claude Code monitoring dashboard.

Lanes: a durable unit of parallel agent work, one per working directory,
tracked across session restarts. Managed lanes are git worktrees the
dashboard provisions and can reset or remove behind a three-check destroy
guard and a counted preflight; adopted lanes are directories you already
own and are never destroyable.

Pipelines: a lane moves through pipeline stages. A stage the agent declares
with evidence renders green; a stage inferred from the tool-event stream
renders dashed amber and never counts as done. Detection is forward-only
within a 30-minute window, and never writes the declared stage.

Workspace: one page at /run with a lane grid, the selected lane's pipeline,
and a full Claude console behind a disclosure.

deployments/terraform/providers/aws/main.tf

@@ -0,0 +1,264 @@
+# ─────────────────────────────────────────────────────────────────────────────
+# AWS Provider – Full implementation for Claude Code Agent Monitor
+#
+# Composes the generic modules into a production-ready AWS stack:
+#   VPC → ECS Fargate → EFS → ALB → CloudWatch → ACM
+#
+# Features:
+#   - Multi-AZ deployment
+#   - Blue/green deployment slots
+#   - EFS for persistent SQLite storage
+#   - ALB with WebSocket support and sticky sessions
+#   - Auto-scaling with CPU/memory targets
+#   - CloudWatch monitoring, alarms, and dashboards
+#   - IAM least-privilege roles
+# ─────────────────────────────────────────────────────────────────────────────
+
+provider "aws" {
+  region = var.region
+
+  default_tags {
+    tags = local.common_tags
+  }
+}
+
+# ── Data sources ────────────────────────────────────────────────────────────
+
+data "aws_caller_identity" "current" {}
+data "aws_region" "current" {}
+
+data "aws_availability_zones" "available" {
+  state = "available"
+}
+
+# ── Locals ──────────────────────────────────────────────────────────────────
+
+locals {
+  name_prefix = lower(replace("${var.project_name}-${var.environment}", "_", "-"))
+
+  common_tags = merge(
+    {
+      project        = var.project_name
+      environment    = var.environment
+      managed_by     = "terraform"
+      cloud_provider = "aws"
+      repository     = "Claude-Code-Agent-Monitor"
+    },
+    var.tags,
+  )
+
+  # Use first 3 available AZs when none specified
+  availability_zones = length(var.availability_zones) > 0 ? var.availability_zones : slice(data.aws_availability_zones.available.names, 0, min(3, length(data.aws_availability_zones.available.names)))
+}
+
+# ─────────────────────────────────────────────────────────────────────────────
+# Networking
+# ─────────────────────────────────────────────────────────────────────────────
+
+module "networking" {
+  source = "../../modules/networking"
+
+  project_name         = var.project_name
+  environment          = var.environment
+  cloud_provider       = "aws"
+  region               = var.region
+  vpc_cidr             = var.vpc_cidr
+  availability_zones   = local.availability_zones
+  public_subnet_cidrs  = var.public_subnet_cidrs
+  private_subnet_cidrs = var.private_subnet_cidrs
+  app_port             = var.app_port
+  mcp_port             = var.mcp_port
+  tags                 = local.common_tags
+}
+
+# ─────────────────────────────────────────────────────────────────────────────
+# Database (EFS for SQLite persistence)
+# ─────────────────────────────────────────────────────────────────────────────
+
+module "database" {
+  source = "../../modules/database"
+
+  project_name               = var.project_name
+  environment                = var.environment
+  cloud_provider             = "aws"
+  region                     = var.region
+  storage_size_gb            = var.storage_size_gb
+  enable_backup              = var.enable_storage_backup
+  private_subnet_ids         = module.networking.private_subnet_ids
+  vpc_id                     = module.networking.vpc_id
+  allowed_security_group_ids = module.networking.storage_security_group_ids
+  tags                       = local.common_tags
+}
+
+# ─────────────────────────────────────────────────────────────────────────────
+# Compute – Blue slot
+# ─────────────────────────────────────────────────────────────────────────────
+
+module "compute_blue" {
+  source = "../../modules/compute"
+
+  project_name          = var.project_name
+  environment           = var.environment
+  cloud_provider        = "aws"
+  region                = var.region
+  deployment_slot       = "blue"
+  container_image       = var.app_container_image
+  mcp_container_image   = var.mcp_container_image
+  app_port              = var.app_port
+  mcp_port              = var.mcp_port
+  cpu                   = var.cpu
+  memory                = var.memory
+  desired_count         = var.active_deployment_slot == "blue" ? var.desired_replicas : 0
+  min_count             = var.active_deployment_slot == "blue" ? var.min_replicas : 0
+  max_count             = var.active_deployment_slot == "blue" ? var.max_replicas : 0
+  environment_variables = var.environment_variables
+  health_check_path     = var.health_check_path
+  vpc_id                = module.networking.vpc_id
+  private_subnet_ids    = module.networking.private_subnet_ids
+  security_group_ids    = module.networking.private_security_group_ids
+  storage_filesystem_id = module.database.filesystem_id
+  storage_mount_targets = module.database.mount_target_ids
+  autoscaling_cpu_target    = var.autoscaling_cpu_target
+  autoscaling_memory_target = var.autoscaling_memory_target
+  tags                  = local.common_tags
+}
+
+# ─────────────────────────────────────────────────────────────────────────────
+# Compute – Green slot
+# ─────────────────────────────────────────────────────────────────────────────
+
+module "compute_green" {
+  source = "../../modules/compute"
+
+  project_name          = var.project_name
+  environment           = var.environment
+  cloud_provider        = "aws"
+  region                = var.region
+  deployment_slot       = "green"
+  container_image       = var.app_container_image
+  mcp_container_image   = var.mcp_container_image
+  app_port              = var.app_port
+  mcp_port              = var.mcp_port
+  cpu                   = var.cpu
+  memory                = var.memory
+  desired_count         = var.active_deployment_slot == "green" ? var.desired_replicas : 0
+  min_count             = var.active_deployment_slot == "green" ? var.min_replicas : 0
+  max_count             = var.active_deployment_slot == "green" ? var.max_replicas : 0
+  environment_variables = var.environment_variables
+  health_check_path     = var.health_check_path
+  vpc_id                = module.networking.vpc_id
+  private_subnet_ids    = module.networking.private_subnet_ids
+  security_group_ids    = module.networking.private_security_group_ids
+  storage_filesystem_id = module.database.filesystem_id
+  storage_mount_targets = module.database.mount_target_ids
+  autoscaling_cpu_target    = var.autoscaling_cpu_target
+  autoscaling_memory_target = var.autoscaling_memory_target
+  tags                  = local.common_tags
+}
+
+# ─────────────────────────────────────────────────────────────────────────────
+# ACM Certificate (optional – when domain_name is specified)
+# ─────────────────────────────────────────────────────────────────────────────
+
+resource "aws_acm_certificate" "main" {
+  count = var.domain_name != "" && var.tls_certificate_arn == "" ? 1 : 0
+
+  domain_name       = var.domain_name
+  validation_method = "DNS"
+
+  tags = merge(local.common_tags, {
+    Name = "${local.name_prefix}-cert"
+  })
+
+  lifecycle {
+    create_before_destroy = true
+  }
+}
+
+locals {
+  tls_cert_arn = var.tls_certificate_arn != "" ? var.tls_certificate_arn : (
+    length(aws_acm_certificate.main) > 0 ? aws_acm_certificate.main[0].arn : ""
+  )
+}
+
+# ─────────────────────────────────────────────────────────────────────────────
+# Load Balancer
+# ─────────────────────────────────────────────────────────────────────────────
+
+module "loadbalancer" {
+  source = "../../modules/loadbalancer"
+
+  project_name        = var.project_name
+  environment         = var.environment
+  cloud_provider      = "aws"
+  region              = var.region
+  vpc_id              = module.networking.vpc_id
+  public_subnet_ids   = module.networking.public_subnet_ids
+  security_group_ids  = module.networking.public_security_group_ids
+  app_port            = var.app_port
+  mcp_port            = var.mcp_port
+  tls_certificate_arn = local.tls_cert_arn
+  domain_name         = var.domain_name
+
+  blue_target_group_arn  = module.compute_blue.target_group_arn
+  green_target_group_arn = module.compute_green.target_group_arn
+  blue_weight            = var.blue_weight
+  green_weight           = var.green_weight
+
+  health_check_path                = var.health_check_path
+  health_check_interval            = var.health_check_interval
+  health_check_timeout             = var.health_check_timeout
+  health_check_healthy_threshold   = var.health_check_healthy_threshold
+  health_check_unhealthy_threshold = var.health_check_unhealthy_threshold
+
+  enable_deletion_protection = var.environment == "production"
+
+  tags = local.common_tags
+}
+
+# ─────────────────────────────────────────────────────────────────────────────
+# Monitoring
+# ─────────────────────────────────────────────────────────────────────────────
+
+module "monitoring" {
+  source = "../../modules/monitoring"
+  count  = var.enable_monitoring ? 1 : 0
+
+  project_name       = var.project_name
+  environment        = var.environment
+  cloud_provider     = "aws"
+  region             = var.region
+  alert_email        = var.alert_email
+  log_retention_days = var.log_retention_days
+
+  loadbalancer_arn     = module.loadbalancer.loadbalancer_arn
+  target_group_arns    = [module.compute_blue.target_group_arn, module.compute_green.target_group_arn]
+  compute_cluster_name = module.compute_blue.cluster_name
+  filesystem_id        = module.database.filesystem_id
+
+  tags = local.common_tags
+}
+
+# ─────────────────────────────────────────────────────────────────────────────
+# Route53 DNS record (optional)
+# ─────────────────────────────────────────────────────────────────────────────
+
+data "aws_route53_zone" "main" {
+  count = var.domain_name != "" && var.route53_zone_id != "" ? 1 : 0
+
+  zone_id = var.route53_zone_id
+}
+
+resource "aws_route53_record" "app" {
+  count = var.domain_name != "" && var.route53_zone_id != "" ? 1 : 0
+
+  zone_id = data.aws_route53_zone.main[0].zone_id
+  name    = var.domain_name
+  type    = "A"
+
+  alias {
+    name                   = module.loadbalancer.dns_name
+    zone_id                = module.loadbalancer.zone_id
+    evaluate_target_health = true
+  }
+}

deployments/terraform/providers/aws/outputs.tf

@@ -0,0 +1,58 @@
+# ─────────────────────────────────────────────────────────────────────────────
+# AWS provider outputs
+# ─────────────────────────────────────────────────────────────────────────────
+
+output "application_url" {
+  description = "Public URL of the Claude Code Agent Monitor dashboard"
+  value       = module.loadbalancer.application_url
+}
+
+output "alb_dns_name" {
+  description = "DNS name of the Application Load Balancer"
+  value       = module.loadbalancer.dns_name
+}
+
+output "vpc_id" {
+  description = "ID of the VPC"
+  value       = module.networking.vpc_id
+}
+
+output "ecs_cluster_name" {
+  description = "Name of the ECS cluster"
+  value       = module.compute_blue.cluster_name
+}
+
+output "blue_service_name" {
+  description = "Name of the blue ECS service"
+  value       = module.compute_blue.service_name
+}
+
+output "green_service_name" {
+  description = "Name of the green ECS service"
+  value       = module.compute_green.service_name
+}
+
+output "efs_filesystem_id" {
+  description = "ID of the EFS file system"
+  value       = module.database.filesystem_id
+}
+
+output "acm_certificate_arn" {
+  description = "ARN of the ACM certificate (if auto-created)"
+  value       = length(aws_acm_certificate.main) > 0 ? aws_acm_certificate.main[0].arn : var.tls_certificate_arn
+}
+
+output "monitoring_dashboard_url" {
+  description = "CloudWatch dashboard URL"
+  value       = var.enable_monitoring ? module.monitoring[0].dashboard_url : "monitoring disabled"
+}
+
+output "account_id" {
+  description = "AWS account ID"
+  value       = data.aws_caller_identity.current.account_id
+}
+
+output "region" {
+  description = "AWS region"
+  value       = data.aws_region.current.name
+}

deployments/terraform/providers/aws/terraform.tf

@@ -0,0 +1,14 @@
+# ─────────────────────────────────────────────────────────────────────────────
+# AWS provider – Terraform and provider constraints
+# ─────────────────────────────────────────────────────────────────────────────
+
+terraform {
+  required_version = ">= 1.5.0"
+
+  required_providers {
+    aws = {
+      source  = "hashicorp/aws"
+      version = "~> 5.0"
+    }
+  }
+}

deployments/terraform/providers/aws/variables.tf

@@ -0,0 +1,254 @@
+# ─────────────────────────────────────────────────────────────────────────────
+# AWS provider variables
+# ─────────────────────────────────────────────────────────────────────────────
+
+# ── Core ────────────────────────────────────────────────────────────────────
+
+variable "project_name" {
+  description = "Project identifier used in resource naming and tagging"
+  type        = string
+  default     = "claude-agent-monitor"
+}
+
+variable "environment" {
+  description = "Deployment environment: dev, staging, or production"
+  type        = string
+  validation {
+    condition     = contains(["dev", "staging", "production"], var.environment)
+    error_message = "environment must be one of: dev, staging, production."
+  }
+}
+
+variable "region" {
+  description = "AWS region for resource deployment"
+  type        = string
+  default     = "us-east-1"
+}
+
+variable "tags" {
+  description = "Additional tags to apply to all resources"
+  type        = map(string)
+  default     = {}
+}
+
+# ── Networking ──────────────────────────────────────────────────────────────
+
+variable "vpc_cidr" {
+  description = "CIDR block for the VPC"
+  type        = string
+  default     = "10.0.0.0/16"
+}
+
+variable "availability_zones" {
+  description = "List of AZs (auto-detected if empty)"
+  type        = list(string)
+  default     = []
+}
+
+variable "public_subnet_cidrs" {
+  description = "CIDR blocks for public subnets"
+  type        = list(string)
+  default     = ["10.0.1.0/24", "10.0.2.0/24", "10.0.3.0/24"]
+}
+
+variable "private_subnet_cidrs" {
+  description = "CIDR blocks for private subnets"
+  type        = list(string)
+  default     = ["10.0.11.0/24", "10.0.12.0/24", "10.0.13.0/24"]
+}
+
+# ── Compute ─────────────────────────────────────────────────────────────────
+
+variable "app_container_image" {
+  description = "Docker image URI for the main application"
+  type        = string
+}
+
+variable "mcp_container_image" {
+  description = "Docker image URI for the MCP sidecar (empty to disable)"
+  type        = string
+  default     = ""
+}
+
+variable "app_port" {
+  description = "Application container port"
+  type        = number
+  default     = 4820
+}
+
+variable "mcp_port" {
+  description = "MCP sidecar container port"
+  type        = number
+  default     = 8819
+}
+
+variable "cpu" {
+  description = "CPU units for Fargate tasks (256, 512, 1024, 2048, 4096)"
+  type        = number
+  default     = 512
+}
+
+variable "memory" {
+  description = "Memory in MiB for Fargate tasks"
+  type        = number
+  default     = 1024
+}
+
+variable "min_replicas" {
+  description = "Minimum number of ECS tasks"
+  type        = number
+  default     = 1
+}
+
+variable "max_replicas" {
+  description = "Maximum number of ECS tasks for auto-scaling"
+  type        = number
+  default     = 3
+}
+
+variable "desired_replicas" {
+  description = "Desired number of ECS tasks at steady state"
+  type        = number
+  default     = 1
+}
+
+variable "environment_variables" {
+  description = "Environment variables for the application container"
+  type        = map(string)
+  default = {
+    NODE_ENV       = "production"
+    DASHBOARD_PORT = "4820"
+  }
+}
+
+# ── Deployment ──────────────────────────────────────────────────────────────
+
+variable "active_deployment_slot" {
+  description = "Active deployment slot: blue or green"
+  type        = string
+  default     = "blue"
+  validation {
+    condition     = contains(["blue", "green"], var.active_deployment_slot)
+    error_message = "active_deployment_slot must be blue or green."
+  }
+}
+
+variable "blue_weight" {
+  description = "Traffic weight for blue target group (0-100)"
+  type        = number
+  default     = 100
+  validation {
+    condition     = var.blue_weight >= 0 && var.blue_weight <= 100
+    error_message = "blue_weight must be between 0 and 100."
+  }
+}
+
+variable "green_weight" {
+  description = "Traffic weight for green target group (0-100)"
+  type        = number
+  default     = 0
+  validation {
+    condition     = var.green_weight >= 0 && var.green_weight <= 100
+    error_message = "green_weight must be between 0 and 100."
+  }
+}
+
+# ── TLS / Domain ────────────────────────────────────────────────────────────
+
+variable "domain_name" {
+  description = "FQDN for the application (empty to skip DNS/TLS)"
+  type        = string
+  default     = ""
+}
+
+variable "tls_certificate_arn" {
+  description = "ARN of an existing ACM certificate (auto-created if domain_name set)"
+  type        = string
+  default     = ""
+}
+
+variable "route53_zone_id" {
+  description = "Route53 hosted zone ID for DNS records (empty to skip)"
+  type        = string
+  default     = ""
+}
+
+# ── Storage ─────────────────────────────────────────────────────────────────
+
+variable "storage_size_gb" {
+  description = "EFS storage does not require pre-provisioning; kept for interface compatibility"
+  type        = number
+  default     = 20
+}
+
+variable "enable_storage_backup" {
+  description = "Enable AWS Backup for EFS"
+  type        = bool
+  default     = true
+}
+
+# ── Health check ────────────────────────────────────────────────────────────
+
+variable "health_check_path" {
+  description = "HTTP path for health checks"
+  type        = string
+  default     = "/api/health"
+}
+
+variable "health_check_interval" {
+  description = "Seconds between health checks"
+  type        = number
+  default     = 30
+}
+
+variable "health_check_timeout" {
+  description = "Seconds before a health check request times out"
+  type        = number
+  default     = 5
+}
+
+variable "health_check_healthy_threshold" {
+  description = "Consecutive successes to mark target healthy"
+  type        = number
+  default     = 2
+}
+
+variable "health_check_unhealthy_threshold" {
+  description = "Consecutive failures to mark target unhealthy"
+  type        = number
+  default     = 3
+}
+
+# ── Auto-scaling ────────────────────────────────────────────────────────────
+
+variable "autoscaling_cpu_target" {
+  description = "Target CPU utilization percentage for auto-scaling"
+  type        = number
+  default     = 70
+}
+
+variable "autoscaling_memory_target" {
+  description = "Target memory utilization percentage for auto-scaling"
+  type        = number
+  default     = 80
+}
+
+# ── Monitoring ──────────────────────────────────────────────────────────────
+
+variable "enable_monitoring" {
+  description = "Enable CloudWatch monitoring, alarms, and dashboards"
+  type        = bool
+  default     = true
+}
+
+variable "alert_email" {
+  description = "Email address for SNS alert notifications"
+  type        = string
+  default     = ""
+}
+
+variable "log_retention_days" {
+  description = "CloudWatch log retention in days"
+  type        = number
+  default     = 30
+}