# Comprehensive config for the SageMaker Pipeline module.
# Creates a SageMaker Pipeline via CfnPipeline (pure CDK) with
# preprocessing, training, evaluation, conditional model
# registration, VPC isolation, and cross-account model registry.

# SageMaker project name used in resource naming
projectName: test-pipeline-project

# (Optional) SageMaker domain ID for Studio integration tagging
# Often created by the SageMaker Studio Domain module.
# Example SSM: ssm:/{{org}}/{{domain}}/<sm_studio_domain_module_name>/domain-id
domainId: d-test123

# (Optional) SageMaker domain ARN for Studio integration tagging
# Often created by the SageMaker Studio Domain module.
# Example SSM: ssm:/{{org}}/{{domain}}/<sm_studio_domain_module_name>/domain-arn
domainArn: arn:{{partition}}:sagemaker:{{region}}:{{account}}:domain/d-test123

# (Optional) Model Package Group name for model registration
modelPackageGroupName: test-mpg

# (Optional) Pre-prod account ID for cross-account model
# registry access
preProdAccountId: '{{context:account-2}}'

# (Optional) Prod account ID for cross-account model
# registry access
prodAccountId: '{{context:account-3}}'

pipeline:
  # (Optional) Pipeline parameters — configurable at execution
  parameters:
    - name: ProcessingInstanceType
      type: String
      defaultValue: ml.m5.xlarge
    - name: TrainingInstanceType
      type: String
      defaultValue: ml.m5.xlarge
    - name: InputDataUrl
      type: String
      defaultValue: s3://test-bucket/dataset/data.csv

  # (Optional) Network configuration for pipeline steps
  networkConfig:
    enableNetworkIsolation: true
    encryptInterContainerTraffic: true
    # Often created by your VPC/networking stack.
    # Example SSM: ssm:/path/to/subnet/id
    subnetIds:
      - subnet-abc
      - subnet-def
    # Often created by your VPC/networking stack.
    # Example SSM: ssm:/path/to/security-group/id
    securityGroupIds:
      - sg-123

  # Pipeline steps — define the ML workflow
  steps:
    - name: PreprocessData
      type: Processing
      processing:
        imageUri: "123456789012.dkr.ecr.us-east-1.amazonaws.com/preprocess:latest"
        instanceType: ml.m5.xlarge
        scriptS3Uri: s3://test-bucket/scripts/preprocessing.py
        inputs:
          - inputName: input-data
            s3Uri: s3://test-bucket/dataset/data.csv
        outputs:
          - outputName: train
          - outputName: validation
          - outputName: test
        enableNetworkIsolation: false

    - name: TrainModel
      type: Training
      training:
        imageUri: "123456789012.dkr.ecr.us-east-1.amazonaws.com/train:latest"
        instanceType: ml.m5.xlarge
        hyperparameters:
          objective: "reg:linear"
          num_round: "50"
          max_depth: "5"
          eta: "0.2"
        inputChannels:
          - channelName: train
            stepOutput: "PreprocessData.train"
            contentType: text/csv
          - channelName: validation
            stepOutput: "PreprocessData.validation"
            contentType: text/csv
        outputPath: s3://test-bucket/output

    - name: EvaluateModel
      type: Processing
      processing:
        imageUri: "123456789012.dkr.ecr.us-east-1.amazonaws.com/train:latest"
        instanceType: ml.m5.xlarge
        scriptS3Uri: s3://test-bucket/scripts/evaluate.py
        inputs:
          - inputName: model
            stepOutput: "TrainModel.modelArtifacts"
          - inputName: test
            stepOutput: "PreprocessData.test"
        outputs:
          - outputName: evaluation
        propertyFiles:
          - propertyFileName: EvaluationReport
            outputName: evaluation
            filePath: evaluation.json

    - name: RegisterModel
      type: RegisterModel
      register:
        imageUri: "123456789012.dkr.ecr.us-east-1.amazonaws.com/inference:latest"
        modelDataStep: TrainModel
        modelPackageGroupName: test-mpg
        approvalStatus: PendingManualApproval
        contentTypes: ["text/csv"]
        responseTypes: ["text/csv"]
        inferenceInstanceTypes: ["ml.t2.medium", "ml.m5.large"]
        transformInstanceTypes: ["ml.m5.large"]

    - name: CheckMSE
      type: Condition
      condition:
        conditions:
          - operator: LessThanOrEqualTo
            stepName: EvaluateModel
            propertyFile: EvaluationReport
            jsonPath: regression_metrics.mse.value
            threshold: 6.0
        ifSteps:
          - RegisterModel