# Comprehensive config for the SageMaker Model Monitoring module.
# Deploys all four monitor types (data quality, model quality,
# model bias, model explainability) with VPC isolation, KMS
# encryption, and automated baselining.
#
# NOTE: ECR image URIs below are region-specific (us-east-1). Replace the account ID
# and region with values appropriate for your deployment region. See:
# https://docs.aws.amazon.com/sagemaker/latest/dg/sagemaker-algo-docker-registry-paths.html

# Name of the SageMaker endpoint to monitor
# Often created by the SageMaker Endpoint module.
# Example SSM: ssm:/{{org}}/{{domain}}/<endpoint_module_name>/endpoint-name
endpointName: test-endpoint

# Monitor configurations — at least one type must be enabled
monitors:
  dataQuality:
    enabled: true
    schedule: "cron(0 * ? * * *)"
    instanceType: ml.m5.xlarge
    instanceCount: 1
    volumeSizeInGb: 30
    maxRuntimeInSeconds: 3600
    imageUri: "156813124566.dkr.ecr.us-east-1.amazonaws.com/sagemaker-model-monitor-analyzer"
    # (Optional) Pre-computed baseline references
    baselineDatasetUri: s3://test-model-bucket/baselines/data-quality/dataset.csv
    baselineConstraintsUri: s3://test-model-bucket/baselines/data-quality/constraints.json
    baselineStatisticsUri: s3://test-model-bucket/baselines/data-quality/statistics.json
  modelQuality:
    enabled: true
    schedule: "cron(0 */6 ? * * *)"
    instanceType: ml.m5.xlarge
    imageUri: "156813124566.dkr.ecr.us-east-1.amazonaws.com/sagemaker-model-monitor-analyzer"
    problemType: BinaryClassification
    groundTruthS3Uri: s3://test-model-bucket/ground-truth/
    inferenceAttribute: prediction
    probabilityAttribute: probability
    probabilityThreshold: 0.5
  modelBias:
    enabled: true
    schedule: "cron(0 0 ? * MON *)"
    instanceType: ml.m5.xlarge
    imageUri: "246618743249.dkr.ecr.us-east-1.amazonaws.com/sagemaker-clarify-processing:1.0"
    groundTruthS3Uri: s3://test-model-bucket/ground-truth/
    featuresAttribute: features
  modelExplainability:
    enabled: true
    schedule: "cron(0 0 ? * MON *)"
    instanceType: ml.m5.xlarge
    imageUri: "246618743249.dkr.ecr.us-east-1.amazonaws.com/sagemaker-clarify-processing:1.0"
    featuresAttribute: features

# (Optional) VPC ID for monitoring jobs
# Often created by your VPC/networking stack.
# Example SSM: ssm:/path/to/vpc/id
vpcId: vpc-0123456789abcdef0

# (Optional) Subnet IDs for monitoring jobs
# Often created by your VPC/networking stack.
# Example SSM: ssm:/path/to/subnet/id
subnetIds:
  - subnet-0123456789abcdef0
  - subnet-0123456789abcdef1

# (Optional) Security group IDs for monitoring jobs
# Often created by your VPC/networking stack.
# Example SSM: ssm:/path/to/security-group/id
securityGroupIds:
  - sg-0123456789abcdef0

# (Optional) S3 bucket ARN for model artifacts access
modelBucketArn: arn:{{partition}}:s3:::test-model-bucket

# (Optional) Enable network isolation for monitoring jobs
# (default: false)
networkIsolation: false

# (Optional) KMS key ARN for encryption. If omitted, a new
# customer-managed key is created.
kmsKeyArn: arn:{{partition}}:kms:{{region}}:{{account}}:key/test-key-id

# (Optional) Automated baselining configuration
baselineTrainingDataS3Uri: s3://test-model-bucket/baselines/training-data.csv
baselineOutputDataS3Uri: s3://test-model-bucket/baselines/output/
baselineSchedule: "cron(0 0 1 * ? *)"
baselineDatasetFormat: '{"csv": {"header": true}}'