AWSTemplateFormatVersion: "2010-09-09"
Transform: AWS::Serverless-2016-10-31
Description: >
  sh-openswe-traces — LangSmith Bulk Export destination. Storage-only:
  KMS-encrypted S3 bucket, a least-privilege IAM writer for LangSmith's
  export job, and a Secrets Manager holder for that writer's access key.
  No compute — the export schedule is configured on the LangSmith side.

Parameters:
  ExportPrefix:
    Type: String
    Default: langsmith/
    Description: S3 key prefix LangSmith writes exports under (also the lifecycle scope).

Resources:
  TracesKey:
    Type: AWS::KMS::Key
    Properties:
      Description: SSE-KMS CMK for sh-openswe-traces (LangSmith export archive).
      EnableKeyRotation: true
      KeyPolicy:
        Version: "2012-10-17"
        Statement:
          # Root-enable so IAM identity policies (below) govern access.
          - Sid: EnableIAMPolicies
            Effect: Allow
            Principal:
              AWS: !Sub "arn:aws:iam::${AWS::AccountId}:root"
            Action: "kms:*"
            Resource: "*"

  TracesKeyAlias:
    Type: AWS::KMS::Alias
    Properties:
      AliasName: alias/sh-openswe-traces
      TargetKeyId: !Ref TracesKey

  TracesBucket:
    Type: AWS::S3::Bucket
    DeletionPolicy: Retain
    UpdateReplacePolicy: Retain
    # Logging target policy must exist before S3 will accept LoggingConfiguration.
    DependsOn: TracesLogBucketPolicy
    Properties:
      BucketName: sh-openswe-traces
      PublicAccessBlockConfiguration:
        BlockPublicAcls: true
        BlockPublicPolicy: true
        IgnorePublicAcls: true
        RestrictPublicBuckets: true
      BucketEncryption:
        ServerSideEncryptionConfiguration:
          - ServerSideEncryptionByDefault:
              SSEAlgorithm: aws:kms
              KMSMasterKeyID: !Ref TracesKey
            BucketKeyEnabled: true
      OwnershipControls:
        Rules:
          - ObjectOwnership: BucketOwnerEnforced
      # Tamper recovery: the writer key is write-only (no DeleteObject / no
      # DeleteObjectVersion), so a malicious or buggy overwrite creates a noncurrent
      # version the prior bytes are recoverable from. Exports write new partitioned
      # keys, so noncurrent versions are rare — expire them after 90 days.
      VersioningConfiguration:
        Status: Enabled
      LifecycleConfiguration:
        Rules:
          - Id: archive-exports-to-deep-archive
            Status: Enabled
            Prefix: !Ref ExportPrefix
            Transitions:
              - StorageClass: DEEP_ARCHIVE
                TransitionInDays: 90
          - Id: expire-noncurrent-versions
            Status: Enabled
            NoncurrentVersionExpiration:
              NoncurrentDays: 90
          - Id: abort-incomplete-multipart
            Status: Enabled
            AbortIncompleteMultipartUpload:
              DaysAfterInitiation: 7
      LoggingConfiguration:
        DestinationBucketName: !Ref TracesLogBucket
        LogFilePrefix: s3-access/

  TracesBucketPolicy:
    Type: AWS::S3::BucketPolicy
    Properties:
      Bucket: !Ref TracesBucket
      PolicyDocument:
        Version: "2012-10-17"
        Statement:
          - Sid: DenyInsecureTransport
            Effect: Deny
            Principal: "*"
            Action: "s3:*"
            Resource:
              - !GetAtt TracesBucket.Arn
              - !Sub "${TracesBucket.Arn}/*"
            Condition:
              Bool:
                "aws:SecureTransport": "false"
          # No SSE-header enforcement Deny. LangSmith's exporter does not send an
          # "aws:kms" SSE header, so a "must be aws:kms" Deny blocks its writes — and
          # StringNotEqualsIfExists on a Deny also blocks header-less puts (absent key
          # evaluates true). Encryption is instead guaranteed by the bucket DEFAULT
          # (SSE-KMS with our CMK, applied to every header-less put) plus S3's baseline
          # (no object is ever stored unencrypted). If LangSmith explicitly requests
          # AES256, that object lands as SSE-S3 rather than CMK — verify post-write
          # (head-object) and decide CMK-vs-SSE-S3 if so.

  # Server access logging target for TracesBucket — read attribution for the
  # secret-bearing archive (the org trail logs no S3 data events). SSE-S3 only:
  # S3 log delivery cannot write to an SSE-KMS bucket.
  TracesLogBucket:
    Type: AWS::S3::Bucket
    DeletionPolicy: Retain
    UpdateReplacePolicy: Retain
    Properties:
      BucketName: sh-openswe-traces-logs
      PublicAccessBlockConfiguration:
        BlockPublicAcls: true
        BlockPublicPolicy: true
        IgnorePublicAcls: true
        RestrictPublicBuckets: true
      BucketEncryption:
        ServerSideEncryptionConfiguration:
          - ServerSideEncryptionByDefault:
              SSEAlgorithm: AES256
      OwnershipControls:
        Rules:
          - ObjectOwnership: BucketOwnerEnforced
      LifecycleConfiguration:
        Rules:
          - Id: expire-access-logs
            Status: Enabled
            ExpirationInDays: 365

  TracesLogBucketPolicy:
    Type: AWS::S3::BucketPolicy
    Properties:
      Bucket: !Ref TracesLogBucket
      PolicyDocument:
        Version: "2012-10-17"
        Statement:
          - Sid: S3ServerAccessLogsWrite
            Effect: Allow
            Principal:
              Service: logging.s3.amazonaws.com
            Action: "s3:PutObject"
            Resource: !Sub "${TracesLogBucket.Arn}/s3-access/*"
            Condition:
              ArnLike:
                # literal (not !GetAtt) to avoid a cycle with TracesBucket's DependsOn
                "aws:SourceArn": "arn:aws:s3:::sh-openswe-traces"
              StringEquals:
                "aws:SourceAccount": !Ref "AWS::AccountId"
          - Sid: DenyInsecureTransport
            Effect: Deny
            Principal: "*"
            Action: "s3:*"
            Resource:
              - !GetAtt TracesLogBucket.Arn
              - !Sub "${TracesLogBucket.Arn}/*"
            Condition:
              Bool:
                "aws:SecureTransport": "false"

  # No explicit UserName: an IAM name would require CAPABILITY_NAMED_IAM, but the
  # standard cd-sam.yaml reusable workflow deploys with CAPABILITY_IAM only. The
  # principal is referenced by ARN (in the secret + LangSmith config), not by name;
  # the tag carries the human-facing identifier.
  LangSmithExportUser:
    Type: AWS::IAM::User
    Properties:
      Tags:
        - Key: Name
          Value: sh-openswe-langsmith-export
        - Key: purpose
          Value: langsmith-bulk-export-writer
      Policies:
        - PolicyName: langsmith-export-put
          PolicyDocument:
            Version: "2012-10-17"
            Statement:
              # Bucket-wide (not prefix-scoped): LangSmith's destination-creation
              # validation writes a test object whose key is NOT guaranteed to be
              # under ExportPrefix (docs reference a /tmp path), and its documented
              # policy scopes PutObject to the whole bucket. This bucket is
              # single-purpose, so bucket-wide write is still tightly bounded.
              # Deliberately NO s3:GetObject / s3:DeleteObject (both optional per
              # LangSmith): omitting them keeps the writer write-only (no exfil,
              # no delete). Trade-off: LangSmith skips post-write size verification
              # and leaves its small test object behind (harmless).
              - Sid: PutExportObjects
                Effect: Allow
                Action:
                  - "s3:PutObject"
                  - "s3:AbortMultipartUpload"
                Resource: !Sub "${TracesBucket.Arn}/*"
              - Sid: EncryptWithBucketKey
                Effect: Allow
                Action:
                  - "kms:GenerateDataKey"
                  - "kms:Encrypt"
                  # Required by S3 at CompleteMultipartUpload for SSE-KMS. Safe: the
                  # writer has no s3:GetObject, so there is no object to decrypt/exfil.
                  - "kms:Decrypt"
                Resource: !GetAtt TracesKey.Arn
                # Usable only through S3 — blocks a leaked key from calling kms:Decrypt
                # directly against arbitrary ciphertext under this CMK.
                Condition:
                  StringEquals:
                    "kms:ViaService": !Sub "s3.${AWS::Region}.amazonaws.com"

  # Holder only — the real access key is minted post-deploy and written in
  # with `aws secretsmanager put-secret-value` (see README). Never in the template.
  ExportKeySecret:
    Type: AWS::SecretsManager::Secret
    Properties:
      Name: sh-openswe/langsmith-export-s3
      Description: >
        Access key for the sh-openswe-langsmith-export IAM user, consumed by
        LangSmith Bulk Export. Populated out-of-band post-deploy; rotate quarterly.
      # Encrypted with the aws/secretsmanager managed key — deliberately NOT the
      # trace CMK, so the credential and the data it protects never share a key the
      # writer principal holds any KMS grant on.

Outputs:
  BucketName:
    Value: !Ref TracesBucket
  BucketArn:
    Value: !GetAtt TracesBucket.Arn
  KmsKeyArn:
    Value: !GetAtt TracesKey.Arn
  ExportUserName:
    Value: !Ref LangSmithExportUser
  ExportKeySecretName:
    Value: sh-openswe/langsmith-export-s3