afterhours-shift-manager/template.yaml

AWSTemplateFormatVersion: "2010-09-09"
Transform: AWS::Serverless-2016-10-31
Description: After-Hours Shift Manager — Slack bot for managing on-call shifts with 3CX integration

Parameters:
  Timezone:
    Type: String
    Default: "America/New_York"
  ShiftChannel:
    Type: String
    Description: Slack channel ID for schedule posts and shift notifications
  QueueNumber:
    Type: String
    Default: "801"
    Description: 3CX queue extension number to update

Globals:
  Function:
    Runtime: python3.12
    Timeout: 30
    MemorySize: 1024
    Architectures:
      - arm64
    PermissionsBoundary: arn:aws:iam::328440206208:policy/seahaven-lambda-execution-boundary
  # Access logging + default throttling on the implicit HTTP API (audit M-18).
  HttpApi:
    AccessLogSettings:
      DestinationArn: !GetAtt ApiAccessLogGroup.Arn
      Format: '{"requestId":"$context.requestId","ip":"$context.identity.sourceIp","requestTime":"$context.requestTime","method":"$context.httpMethod","routeKey":"$context.routeKey","status":"$context.status","protocol":"$context.protocol","responseLength":"$context.responseLength","integrationError":"$context.integrationErrorMessage"}'
    DefaultRouteSettings:
      ThrottlingBurstLimit: 50
      ThrottlingRateLimit: 100

Resources:
  ApiAccessLogGroup:
    Type: AWS::Logs::LogGroup
    Properties:
      LogGroupName: /aws/apigateway/afterhours-shift-manager
      RetentionInDays: 90

  # --- Shared Lambda Layer ---
  SharedLayer:
    Type: AWS::Serverless::LayerVersion
    Properties:
      LayerName: afterhours-shared
      ContentUri: src/shared/
      CompatibleRuntimes:
        - python3.12
      CompatibleArchitectures:
        - arm64
    Metadata:
      BuildMethod: python3.12
      BuildArchitecture: arm64

  # --- DynamoDB ---
  ShiftTable:
    Type: AWS::DynamoDB::Table
    Properties:
      TableName: afterhours-shifts
      BillingMode: PAY_PER_REQUEST
      AttributeDefinitions:
        - AttributeName: PK
          AttributeType: S
        - AttributeName: SK
          AttributeType: S
      KeySchema:
        - AttributeName: PK
          KeyType: HASH
        - AttributeName: SK
          KeyType: RANGE
      TimeToLiveSpecification:
        AttributeName: expires_at
        Enabled: true

  # --- Slack Bot Lambda ---
  SlackBotFunction:
    Type: AWS::Serverless::Function
    Properties:
      FunctionName: afterhours-shift-manager
      Handler: handler.handler
      CodeUri: src/slack-bot/
      Layers:
        - !Ref SharedLayer
      Environment:
        Variables:
          SHIFT_TABLE: !Ref ShiftTable
          SLACK_BOT_TOKEN_SECRET: afterhours-shift-manager/slack-bot-token
          SLACK_SIGNING_SECRET: afterhours-shift-manager/slack-signing-secret
          SHIFT_CHANNEL: !Ref ShiftChannel
          TCX_SECRET_PREFIX: afterhours-shift-manager/3cx-
          QUEUE_NUMBER: !Ref QueueNumber
          TZ: !Ref Timezone
          # Holiday scheduling: per-holiday one-off schedules target the router,
          # passing the scheduler exec role; inline activation invokes it directly.
          HOLIDAY_ROUTER_ARN: !GetAtt HolidayRouterFunction.Arn
          HOLIDAY_SCHEDULER_ROLE_ARN: !GetAtt HolidaySchedulerExecutionRole.Arn
      Policies:
        - DynamoDBCrudPolicy:
            TableName: !Ref ShiftTable
        - Statement:
            - Effect: Allow
              Action:
                - secretsmanager:GetSecretValue
              Resource:
                - !Sub "arn:aws:secretsmanager:${AWS::Region}:${AWS::AccountId}:secret:afterhours-shift-manager/*"
            # Manage the per-holiday EventBridge Scheduler one-off schedules
            # (08:00 activate / 17:00 deactivate of the holiday router).
            - Effect: Allow
              Action:
                - scheduler:CreateSchedule
                - scheduler:DeleteSchedule
                - scheduler:GetSchedule
              # Predictable names (holiday-activate-/holiday-deactivate-<date>)
              # in the default group — scope to those rather than all schedules.
              Resource:
                - !Sub "arn:aws:scheduler:${AWS::Region}:${AWS::AccountId}:schedule/default/holiday-*"
            # PassRole only for the holiday scheduler exec role, and only when
            # handed to EventBridge Scheduler.
            - Effect: Allow
              Action: iam:PassRole
              Resource: !GetAtt HolidaySchedulerExecutionRole.Arn
              Condition:
                StringEquals:
                  iam:PassedToService: scheduler.amazonaws.com
            # Inline activation (holiday added mid-window) invokes the router now.
            # Unqualified ARN only — we invoke the base function, no alias/version.
            - Effect: Allow
              Action: lambda:InvokeFunction
              Resource: !GetAtt HolidayRouterFunction.Arn
      Events:
        SlackEvents:
          Type: HttpApi
          Properties:
            Path: /slack/events
            Method: POST

  # --- Weekly Schedule Post (Monday 7am ET) ---
  WeeklyPostFunction:
    Type: AWS::Serverless::Function
    Properties:
      FunctionName: afterhours-weekly-post
      Handler: app.handler
      CodeUri: src/weekly-post/
      Layers:
        - !Ref SharedLayer
      Environment:
        Variables:
          SHIFT_TABLE: !Ref ShiftTable
          SLACK_BOT_TOKEN_SECRET: afterhours-shift-manager/slack-bot-token
          SHIFT_CHANNEL: !Ref ShiftChannel
          SES_SENDER: noreply@seahaven.com
          PAYROLL_RECIPIENTS: payroll@seahaven.com
          PAY_REPORT_USER: U0A3SC48T47
          TZ: !Ref Timezone
      Policies:
        - DynamoDBCrudPolicy:
            TableName: !Ref ShiftTable
        - Statement:
            # Least privilege: only the Slack bot token, not the whole namespace.
            - Effect: Allow
              Action:
                - secretsmanager:GetSecretValue
              Resource:
                - !Sub "arn:aws:secretsmanager:${AWS::Region}:${AWS::AccountId}:secret:afterhours-shift-manager/slack-bot-token-*"
            - Effect: Allow
              Action:
                - ses:SendEmail
              Resource:
                # Only the single sending identity (noreply@seahaven.com), not
                # every identity in the account.
                - !Sub "arn:aws:ses:${AWS::Region}:${AWS::AccountId}:identity/noreply@seahaven.com"
                # The sending identity has a default configuration set
                # (seahaven-email-events); SES authorizes SendEmail against the
                # config-set resource too, so it must be granted alongside the
                # identity or the send is denied. Scoped to the known set name.
                - !Sub "arn:aws:ses:${AWS::Region}:${AWS::AccountId}:configuration-set/seahaven-email-events"
      Events:
        # EST: 7am ET = 12:00 UTC (Nov-Mar)
        WeeklyPostEST:
          Type: Schedule
          Properties:
            Schedule: cron(0 12 ? * MON *)
            Description: "Post weekly schedule Monday 7am EST"
            Enabled: true
        # EDT: 7am ET = 11:00 UTC (Mar-Nov)
        WeeklyPostEDT:
          Type: Schedule
          Properties:
            Schedule: cron(0 11 ? * MON *)
            Description: "Post weekly schedule Monday 7am EDT"
            Enabled: true

  # --- Roster Sync Lambda (daily sync from 3CX) ---
  RosterSyncFunction:
    Type: AWS::Serverless::Function
    Properties:
      FunctionName: afterhours-roster-sync
      Handler: app.handler
      CodeUri: src/roster-sync/
      Layers:
        - !Ref SharedLayer
      Timeout: 60
      Environment:
        Variables:
          SHIFT_TABLE: !Ref ShiftTable
          TCX_SECRET_PREFIX: afterhours-shift-manager/3cx-
          SYNC_GROUP: DEFAULT
          TZ: !Ref Timezone
      Policies:
        - DynamoDBCrudPolicy:
            TableName: !Ref ShiftTable
        - Statement:
            # Least privilege: only the 3cx-* secrets this function reads.
            - Effect: Allow
              Action:
                - secretsmanager:GetSecretValue
              Resource:
                - !Sub "arn:aws:secretsmanager:${AWS::Region}:${AWS::AccountId}:secret:afterhours-shift-manager/3cx-*"
      Events:
        # Daily at 6am ET (before the 7am schedule post and 8am 3CX scheduler)
        # EST: 6am ET = 11:00 UTC (Nov-Mar)
        RosterSyncEST:
          Type: Schedule
          Properties:
            Schedule: cron(0 11 ? * * *)
            Description: "Sync roster from 3CX at 6am EST"
            Enabled: true
        # EDT: 6am ET = 10:00 UTC (Mar-Nov)
        RosterSyncEDT:
          Type: Schedule
          Properties:
            Schedule: cron(0 10 ? * * *)
            Description: "Sync roster from 3CX at 6am EDT"
            Enabled: true

  # --- Ring Scheduler (daily 3CX queue routing updates) ---
  RingSchedulerFunction:
    Type: AWS::Serverless::Function
    Properties:
      FunctionName: afterhours-ring-scheduler
      Handler: app.handler
      CodeUri: src/ring-scheduler/
      Layers:
        - !Ref SharedLayer
      Timeout: 60
      Environment:
        Variables:
          SHIFT_TABLE: !Ref ShiftTable
          TCX_SECRET_PREFIX: afterhours-shift-manager/3cx-
          QUEUE_NUMBER: !Ref QueueNumber
          TZ: !Ref Timezone
      Policies:
        - DynamoDBReadPolicy:
            TableName: !Ref ShiftTable
        - Statement:
            # Least privilege: only the 3cx-* secrets this function reads.
            - Effect: Allow
              Action:
                - secretsmanager:GetSecretValue
              Resource:
                - !Sub "arn:aws:secretsmanager:${AWS::Region}:${AWS::AccountId}:secret:afterhours-shift-manager/3cx-*"
      Events:
        # Daily at 8am ET — update after-hours routing
        DailyScheduleEST:
          Type: Schedule
          Properties:
            Schedule: cron(0 13 ? * * *)
            Description: "Update 3CX queue at 8am EST"
            Enabled: true
        DailyScheduleEDT:
          Type: Schedule
          Properties:
            Schedule: cron(0 12 ? * * *)
            Description: "Update 3CX queue at 8am EDT"
            Enabled: true
        # Weekends at 5pm ET — switch to night shift person
        WeekendEveningEST:
          Type: Schedule
          Properties:
            Schedule: cron(0 22 ? * SAT,SUN *)
            Description: "Update 3CX queue at 5pm EST weekends"
            Enabled: true
        WeekendEveningEDT:
          Type: Schedule
          Properties:
            Schedule: cron(0 21 ? * SAT,SUN *)
            Description: "Update 3CX queue at 5pm EDT weekends"
            Enabled: true

  # Lambda error alarm for the ring scheduler. Mirrors the account-wide
  # operational convention (Lambda-Errors-<fn>, threshold 1 over one 5-min
  # period, Sum, missing=notBreaching) and pages the same site-alerts SNS topic
  # → AWS Chatbot → Slack as the other afterhours-* functions.
  RingSchedulerErrorAlarm:
    Type: AWS::CloudWatch::Alarm
    Properties:
      AlarmName: !Sub "Lambda-Errors-${RingSchedulerFunction}"
      AlarmDescription: "Ring scheduler Lambda reported one or more errors"
      Namespace: AWS/Lambda
      MetricName: Errors
      Dimensions:
        - Name: FunctionName
          Value: !Ref RingSchedulerFunction
      Statistic: Sum
      Period: 300
      EvaluationPeriods: 1
      Threshold: 1
      ComparisonOperator: GreaterThanOrEqualToThreshold
      TreatMissingData: notBreaching
      AlarmActions:
        - !Sub "arn:aws:sns:${AWS::Region}:${AWS::AccountId}:site-alerts"

  # --- Holiday Router (repoints 3CX IVR/queue for a holiday day-shift) ---
  # Invoked with {"action": "activate"|"deactivate", "date": "<YYYY-MM-DD>"} at
  # 08:00 ET (activate) and 17:00 ET (deactivate) for each holiday date. Both
  # operations are idempotent. No standing schedule here — invocation is driven
  # per-holiday-date (the holiday record gates the work; off-days are no-ops).
  HolidayRouterFunction:
    Type: AWS::Serverless::Function
    Properties:
      FunctionName: afterhours-holiday-router
      Handler: app.handler
      CodeUri: src/holiday-router/
      Layers:
        - !Ref SharedLayer
      Timeout: 60
      Environment:
        Variables:
          SHIFT_TABLE: !Ref ShiftTable
          TCX_SECRET_PREFIX: afterhours-shift-manager/3cx-
          TZ: !Ref Timezone
      Policies:
        - DynamoDBCrudPolicy:
            TableName: !Ref ShiftTable
        - Statement:
            # Least privilege: only the 3cx-* secrets this function reads.
            - Effect: Allow
              Action:
                - secretsmanager:GetSecretValue
              Resource:
                - !Sub "arn:aws:secretsmanager:${AWS::Region}:${AWS::AccountId}:secret:afterhours-shift-manager/3cx-*"

  # Lambda error alarm for the holiday router. Mirrors the account-wide
  # operational convention (Lambda-Errors-<fn>, threshold 1 over one 5-min
  # period, Sum, missing=notBreaching) and pages the same site-alerts SNS topic
  # → AWS Chatbot → Slack as the other afterhours-* functions.
  HolidayRouterErrorAlarm:
    Type: AWS::CloudWatch::Alarm
    Properties:
      AlarmName: !Sub "Lambda-Errors-${HolidayRouterFunction}"
      AlarmDescription: "Holiday router Lambda reported one or more errors"
      Namespace: AWS/Lambda
      MetricName: Errors
      Dimensions:
        - Name: FunctionName
          Value: !Ref HolidayRouterFunction
      Statistic: Sum
      Period: 300
      EvaluationPeriods: 1
      Threshold: 1
      ComparisonOperator: GreaterThanOrEqualToThreshold
      TreatMissingData: notBreaching
      AlarmActions:
        - !Sub "arn:aws:sns:${AWS::Region}:${AWS::AccountId}:site-alerts"

  # EventBridge Scheduler execution role. The slack-bot creates one-off
  # schedules per holiday date (08:00 activate / 17:00 deactivate); Scheduler
  # assumes this role to invoke the holiday router. Auto-named (no RoleName) so
  # the deploy's CAPABILITY_IAM suffices — cd-sam does not pass
  # CAPABILITY_NAMED_IAM. The permissions boundary is REQUIRED: the scoped
  # github-cfn-execution-role gates iam:CreateRole/PutRolePolicy on roles
  # carrying exactly this boundary, so the CI deploy is denied without it.
  HolidaySchedulerExecutionRole:
    Type: AWS::IAM::Role
    Properties:
      PermissionsBoundary: arn:aws:iam::328440206208:policy/seahaven-lambda-execution-boundary
      AssumeRolePolicyDocument:
        Version: "2012-10-17"
        Statement:
          - Effect: Allow
            Principal:
              Service: scheduler.amazonaws.com
            Action: sts:AssumeRole
            Condition:
              StringEquals:
                aws:SourceAccount: !Ref AWS::AccountId
              # Only schedules this stack creates (holiday-* in the default group)
              # may assume the role — not any schedule in the account.
              ArnLike:
                aws:SourceArn: !Sub "arn:aws:scheduler:${AWS::Region}:${AWS::AccountId}:schedule/default/holiday-*"
      Policies:
        - PolicyName: invoke-holiday-router
          PolicyDocument:
            Version: "2012-10-17"
            Statement:
              - Effect: Allow
                Action: lambda:InvokeFunction
                Resource: !GetAtt HolidayRouterFunction.Arn

  # --- Release Notifier (invoked by release.yaml on minor/major releases) ---
  ReleaseNotifierFunction:
    Type: AWS::Serverless::Function
    Properties:
      FunctionName: afterhours-release-notifier
      Handler: app.handler
      CodeUri: src/release-notifier/
      Layers:
        - !Ref SharedLayer
      Environment:
        Variables:
          SLACK_BOT_TOKEN_SECRET: afterhours-shift-manager/slack-bot-token
          SHIFT_CHANNEL: !Ref ShiftChannel
          TZ: !Ref Timezone
      Policies:
        # Least privilege: only the Slack bot token, not the whole namespace.
        - Statement:
            - Effect: Allow
              Action:
                - secretsmanager:GetSecretValue
              Resource:
                - !Sub "arn:aws:secretsmanager:${AWS::Region}:${AWS::AccountId}:secret:afterhours-shift-manager/slack-bot-token-*"

  # GitHub-OIDC role assumed by release.yaml to invoke the notifier. Auto-named
  # (no RoleName) so the deploy's CAPABILITY_IAM is sufficient — cd-sam does not
  # pass CAPABILITY_NAMED_IAM. Trust + permission are scoped to the minimum: this
  # repo's main ref + release workflow, and InvokeFunction on the notifier alone.
  # Its ARN is surfaced as a stack output and set once as the
  # RELEASE_NOTIFY_INVOKE_ROLE_ARN repo variable (see README).
  #
  # The permissions boundary is REQUIRED, not optional: the scoped
  # github-cfn-execution-role's IAM policy gates iam:CreateRole/PutRolePolicy on
  # the role carrying exactly this boundary, so the CI deploy is denied without
  # it. The boundary itself permits lambda:InvokeFunction (Sid LambdaInvoke), so
  # it does not restrict this role's one job.
  ReleaseNotifyInvokeRole:
    Type: AWS::IAM::Role
    Properties:
      PermissionsBoundary: arn:aws:iam::328440206208:policy/seahaven-lambda-execution-boundary
      AssumeRolePolicyDocument:
        Version: "2012-10-17"
        Statement:
          - Effect: Allow
            Principal:
              Federated: !Sub "arn:aws:iam::${AWS::AccountId}:oidc-provider/token.actions.githubusercontent.com"
            Action: sts:AssumeRoleWithWebIdentity
            Condition:
              StringEquals:
                token.actions.githubusercontent.com:aud: sts.amazonaws.com
              StringLike:
                token.actions.githubusercontent.com:sub: "repo:Sea-Haven-Industries/afterhours-shift-manager:ref:refs/heads/main"
                # Defense-in-depth: only the Deploy workflow's release job may assume
                # this role, not any workflow running on main. (The release job lives
                # in deploy.yaml; this must match that workflow's path.)
                token.actions.githubusercontent.com:job_workflow_ref: "Sea-Haven-Industries/afterhours-shift-manager/.github/workflows/deploy.yaml@refs/heads/main"
      Policies:
        - PolicyName: invoke-release-notifier
          PolicyDocument:
            Version: "2012-10-17"
            Statement:
              - Effect: Allow
                Action: lambda:InvokeFunction
                Resource: !GetAtt ReleaseNotifierFunction.Arn

  # ===========================================================================
  # CloudWatch alarm coverage (Wave 1 PR A). All alarms page the same
  # site-alerts SNS topic → AWS Chatbot → Slack as the existing Errors alarms.
  # No OKActions by design (the existing Errors alarms have none either).
  # Naming follows the in-template convention: Lambda-<Metric>-${Fn}.
  # ===========================================================================

  # --- Lambda Errors alarms (clone of HolidayRouterErrorAlarm) ---
  # Errors for ring-scheduler + holiday-router already exist above.

  RosterSyncErrorAlarm:
    Type: AWS::CloudWatch::Alarm
    Properties:
      AlarmName: !Sub "Lambda-Errors-${RosterSyncFunction}"
      AlarmDescription: "Roster sync Lambda reported one or more errors"
      Namespace: AWS/Lambda
      MetricName: Errors
      Dimensions:
        - Name: FunctionName
          Value: !Ref RosterSyncFunction
      Statistic: Sum
      Period: 300
      EvaluationPeriods: 1
      Threshold: 1
      ComparisonOperator: GreaterThanOrEqualToThreshold
      TreatMissingData: notBreaching
      AlarmActions:
        - !Sub "arn:aws:sns:${AWS::Region}:${AWS::AccountId}:site-alerts"

  ReleaseNotifierErrorAlarm:
    Type: AWS::CloudWatch::Alarm
    Properties:
      AlarmName: !Sub "Lambda-Errors-${ReleaseNotifierFunction}"
      AlarmDescription: "Release notifier Lambda reported one or more errors"
      Namespace: AWS/Lambda
      MetricName: Errors
      Dimensions:
        - Name: FunctionName
          Value: !Ref ReleaseNotifierFunction
      Statistic: Sum
      Period: 300
      EvaluationPeriods: 1
      Threshold: 1
      ComparisonOperator: GreaterThanOrEqualToThreshold
      TreatMissingData: notBreaching
      AlarmActions:
        - !Sub "arn:aws:sns:${AWS::Region}:${AWS::AccountId}:site-alerts"

  # ORPHAN ADOPTION: live alarms named Lambda-Errors-afterhours-shift-manager
  # and Lambda-Errors-afterhours-weekly-post already exist OUTSIDE the stack.
  # They MUST be deleted immediately before this stack deploys, or CloudFormation
  # will fail to create these resources (AlarmName collision). See PR body.
  SlackBotErrorAlarm:
    Type: AWS::CloudWatch::Alarm
    Properties:
      AlarmName: !Sub "Lambda-Errors-${SlackBotFunction}"
      AlarmDescription: "Slack bot Lambda reported one or more errors"
      Namespace: AWS/Lambda
      MetricName: Errors
      Dimensions:
        - Name: FunctionName
          Value: !Ref SlackBotFunction
      Statistic: Sum
      Period: 300
      EvaluationPeriods: 1
      Threshold: 1
      ComparisonOperator: GreaterThanOrEqualToThreshold
      TreatMissingData: notBreaching
      AlarmActions:
        - !Sub "arn:aws:sns:${AWS::Region}:${AWS::AccountId}:site-alerts"

  WeeklyPostErrorAlarm:
    Type: AWS::CloudWatch::Alarm
    Properties:
      AlarmName: !Sub "Lambda-Errors-${WeeklyPostFunction}"
      AlarmDescription: "Weekly post Lambda reported one or more errors"
      Namespace: AWS/Lambda
      MetricName: Errors
      Dimensions:
        - Name: FunctionName
          Value: !Ref WeeklyPostFunction
      Statistic: Sum
      Period: 300
      EvaluationPeriods: 1
      Threshold: 1
      ComparisonOperator: GreaterThanOrEqualToThreshold
      TreatMissingData: notBreaching
      AlarmActions:
        - !Sub "arn:aws:sns:${AWS::Region}:${AWS::AccountId}:site-alerts"

  # --- Lambda Duration alarms (Maximum, ms; 2-of-3 evaluation) ---
  # Thresholds set to ~80% of each function's timeout, with 2-of-3 evaluation.
  # Timeouts: slack-bot/weekly-post/release-notifier = 30s (global default);
  # roster-sync/ring-scheduler/holiday-router = 60s.
  SlackBotDurationAlarm:
    Type: AWS::CloudWatch::Alarm
    Properties:
      AlarmName: !Sub "Lambda-Duration-${SlackBotFunction}"
      AlarmDescription: "Slack bot Lambda duration approaching its 30s timeout (>=24s)"
      Namespace: AWS/Lambda
      MetricName: Duration
      Dimensions:
        - Name: FunctionName
          Value: !Ref SlackBotFunction
      Statistic: Maximum
      Period: 300
      EvaluationPeriods: 3
      DatapointsToAlarm: 2
      Threshold: 24000
      ComparisonOperator: GreaterThanOrEqualToThreshold
      TreatMissingData: notBreaching
      AlarmActions:
        - !Sub "arn:aws:sns:${AWS::Region}:${AWS::AccountId}:site-alerts"

  WeeklyPostDurationAlarm:
    Type: AWS::CloudWatch::Alarm
    Properties:
      AlarmName: !Sub "Lambda-Duration-${WeeklyPostFunction}"
      AlarmDescription: "Weekly post Lambda duration approaching its 30s timeout (>=24s)"
      Namespace: AWS/Lambda
      MetricName: Duration
      Dimensions:
        - Name: FunctionName
          Value: !Ref WeeklyPostFunction
      Statistic: Maximum
      Period: 300
      EvaluationPeriods: 3
      DatapointsToAlarm: 2
      Threshold: 24000
      ComparisonOperator: GreaterThanOrEqualToThreshold
      TreatMissingData: notBreaching
      AlarmActions:
        - !Sub "arn:aws:sns:${AWS::Region}:${AWS::AccountId}:site-alerts"

  RosterSyncDurationAlarm:
    Type: AWS::CloudWatch::Alarm
    Properties:
      AlarmName: !Sub "Lambda-Duration-${RosterSyncFunction}"
      AlarmDescription: "Roster sync Lambda duration approaching its 60s timeout (>=48s)"
      Namespace: AWS/Lambda
      MetricName: Duration
      Dimensions:
        - Name: FunctionName
          Value: !Ref RosterSyncFunction
      Statistic: Maximum
      Period: 300
      EvaluationPeriods: 3
      DatapointsToAlarm: 2
      Threshold: 48000
      ComparisonOperator: GreaterThanOrEqualToThreshold
      TreatMissingData: notBreaching
      AlarmActions:
        - !Sub "arn:aws:sns:${AWS::Region}:${AWS::AccountId}:site-alerts"

  RingSchedulerDurationAlarm:
    Type: AWS::CloudWatch::Alarm
    Properties:
      AlarmName: !Sub "Lambda-Duration-${RingSchedulerFunction}"
      AlarmDescription: "Ring scheduler Lambda duration approaching its 60s timeout (>=48s)"
      Namespace: AWS/Lambda
      MetricName: Duration
      Dimensions:
        - Name: FunctionName
          Value: !Ref RingSchedulerFunction
      Statistic: Maximum
      Period: 300
      EvaluationPeriods: 3
      DatapointsToAlarm: 2
      Threshold: 48000
      ComparisonOperator: GreaterThanOrEqualToThreshold
      TreatMissingData: notBreaching
      AlarmActions:
        - !Sub "arn:aws:sns:${AWS::Region}:${AWS::AccountId}:site-alerts"

  HolidayRouterDurationAlarm:
    Type: AWS::CloudWatch::Alarm
    Properties:
      AlarmName: !Sub "Lambda-Duration-${HolidayRouterFunction}"
      AlarmDescription: "Holiday router Lambda duration approaching its 60s timeout (>=48s)"
      Namespace: AWS/Lambda
      MetricName: Duration
      Dimensions:
        - Name: FunctionName
          Value: !Ref HolidayRouterFunction
      Statistic: Maximum
      Period: 300
      EvaluationPeriods: 3
      DatapointsToAlarm: 2
      Threshold: 48000
      ComparisonOperator: GreaterThanOrEqualToThreshold
      TreatMissingData: notBreaching
      AlarmActions:
        - !Sub "arn:aws:sns:${AWS::Region}:${AWS::AccountId}:site-alerts"

  ReleaseNotifierDurationAlarm:
    Type: AWS::CloudWatch::Alarm
    Properties:
      AlarmName: !Sub "Lambda-Duration-${ReleaseNotifierFunction}"
      AlarmDescription: "Release notifier Lambda duration approaching its 30s timeout (>=24s)"
      Namespace: AWS/Lambda
      MetricName: Duration
      Dimensions:
        - Name: FunctionName
          Value: !Ref ReleaseNotifierFunction
      Statistic: Maximum
      Period: 300
      EvaluationPeriods: 3
      DatapointsToAlarm: 2
      Threshold: 24000
      ComparisonOperator: GreaterThanOrEqualToThreshold
      TreatMissingData: notBreaching
      AlarmActions:
        - !Sub "arn:aws:sns:${AWS::Region}:${AWS::AccountId}:site-alerts"

  # --- Lambda Throttles alarms (Sum; threshold 1 over one 5-min period) ---
  SlackBotThrottlesAlarm:
    Type: AWS::CloudWatch::Alarm
    Properties:
      AlarmName: !Sub "Lambda-Throttles-${SlackBotFunction}"
      AlarmDescription: "Slack bot Lambda was throttled (concurrency limit hit)"
      Namespace: AWS/Lambda
      MetricName: Throttles
      Dimensions:
        - Name: FunctionName
          Value: !Ref SlackBotFunction
      Statistic: Sum
      Period: 300
      EvaluationPeriods: 1
      Threshold: 1
      ComparisonOperator: GreaterThanOrEqualToThreshold
      TreatMissingData: notBreaching
      AlarmActions:
        - !Sub "arn:aws:sns:${AWS::Region}:${AWS::AccountId}:site-alerts"

  WeeklyPostThrottlesAlarm:
    Type: AWS::CloudWatch::Alarm
    Properties:
      AlarmName: !Sub "Lambda-Throttles-${WeeklyPostFunction}"
      AlarmDescription: "Weekly post Lambda was throttled (concurrency limit hit)"
      Namespace: AWS/Lambda
      MetricName: Throttles
      Dimensions:
        - Name: FunctionName
          Value: !Ref WeeklyPostFunction
      Statistic: Sum
      Period: 300
      EvaluationPeriods: 1
      Threshold: 1
      ComparisonOperator: GreaterThanOrEqualToThreshold
      TreatMissingData: notBreaching
      AlarmActions:
        - !Sub "arn:aws:sns:${AWS::Region}:${AWS::AccountId}:site-alerts"

  RosterSyncThrottlesAlarm:
    Type: AWS::CloudWatch::Alarm
    Properties:
      AlarmName: !Sub "Lambda-Throttles-${RosterSyncFunction}"
      AlarmDescription: "Roster sync Lambda was throttled (concurrency limit hit)"
      Namespace: AWS/Lambda
      MetricName: Throttles
      Dimensions:
        - Name: FunctionName
          Value: !Ref RosterSyncFunction
      Statistic: Sum
      Period: 300
      EvaluationPeriods: 1
      Threshold: 1
      ComparisonOperator: GreaterThanOrEqualToThreshold
      TreatMissingData: notBreaching
      AlarmActions:
        - !Sub "arn:aws:sns:${AWS::Region}:${AWS::AccountId}:site-alerts"

  RingSchedulerThrottlesAlarm:
    Type: AWS::CloudWatch::Alarm
    Properties:
      AlarmName: !Sub "Lambda-Throttles-${RingSchedulerFunction}"
      AlarmDescription: "Ring scheduler Lambda was throttled (concurrency limit hit)"
      Namespace: AWS/Lambda
      MetricName: Throttles
      Dimensions:
        - Name: FunctionName
          Value: !Ref RingSchedulerFunction
      Statistic: Sum
      Period: 300
      EvaluationPeriods: 1
      Threshold: 1
      ComparisonOperator: GreaterThanOrEqualToThreshold
      TreatMissingData: notBreaching
      AlarmActions:
        - !Sub "arn:aws:sns:${AWS::Region}:${AWS::AccountId}:site-alerts"

  HolidayRouterThrottlesAlarm:
    Type: AWS::CloudWatch::Alarm
    Properties:
      AlarmName: !Sub "Lambda-Throttles-${HolidayRouterFunction}"
      AlarmDescription: "Holiday router Lambda was throttled (concurrency limit hit)"
      Namespace: AWS/Lambda
      MetricName: Throttles
      Dimensions:
        - Name: FunctionName
          Value: !Ref HolidayRouterFunction
      Statistic: Sum
      Period: 300
      EvaluationPeriods: 1
      Threshold: 1
      ComparisonOperator: GreaterThanOrEqualToThreshold
      TreatMissingData: notBreaching
      AlarmActions:
        - !Sub "arn:aws:sns:${AWS::Region}:${AWS::AccountId}:site-alerts"

  ReleaseNotifierThrottlesAlarm:
    Type: AWS::CloudWatch::Alarm
    Properties:
      AlarmName: !Sub "Lambda-Throttles-${ReleaseNotifierFunction}"
      AlarmDescription: "Release notifier Lambda was throttled (concurrency limit hit)"
      Namespace: AWS/Lambda
      MetricName: Throttles
      Dimensions:
        - Name: FunctionName
          Value: !Ref ReleaseNotifierFunction
      Statistic: Sum
      Period: 300
      EvaluationPeriods: 1
      Threshold: 1
      ComparisonOperator: GreaterThanOrEqualToThreshold
      TreatMissingData: notBreaching
      AlarmActions:
        - !Sub "arn:aws:sns:${AWS::Region}:${AWS::AccountId}:site-alerts"

  # --- DynamoDB alarms (afterhours-shifts table) ---
  # ReadThrottleEvents / WriteThrottleEvents are the table-level throttle
  # signals: AWS/DynamoDB emits them at the TableName dimension, so these
  # alarms transition normally. (ThrottledRequests and SystemErrors are NOT
  # emitted at TableName-only granularity — only at TableName+Operation — so
  # alarms on them sit permanently in INSUFFICIENT_DATA and never fire.)
  ShiftTableReadThrottleAlarm:
    Type: AWS::CloudWatch::Alarm
    Properties:
      AlarmName: !Sub "DDB-ReadThrottle-${ShiftTable}"
      AlarmDescription: "afterhours-shifts table had one or more read throttle events"
      Namespace: AWS/DynamoDB
      MetricName: ReadThrottleEvents
      Dimensions:
        - Name: TableName
          Value: !Ref ShiftTable
      Statistic: Sum
      Period: 300
      EvaluationPeriods: 1
      Threshold: 0
      ComparisonOperator: GreaterThanThreshold
      TreatMissingData: notBreaching
      AlarmActions:
        - !Sub "arn:aws:sns:${AWS::Region}:${AWS::AccountId}:site-alerts"

  ShiftTableWriteThrottleAlarm:
    Type: AWS::CloudWatch::Alarm
    Properties:
      AlarmName: !Sub "DDB-WriteThrottle-${ShiftTable}"
      AlarmDescription: "afterhours-shifts table had one or more write throttle events"
      Namespace: AWS/DynamoDB
      MetricName: WriteThrottleEvents
      Dimensions:
        - Name: TableName
          Value: !Ref ShiftTable
      Statistic: Sum
      Period: 300
      EvaluationPeriods: 1
      Threshold: 0
      ComparisonOperator: GreaterThanThreshold
      TreatMissingData: notBreaching
      AlarmActions:
        - !Sub "arn:aws:sns:${AWS::Region}:${AWS::AccountId}:site-alerts"

  # --- API Gateway v2 (HTTP API) alarms on the implicit ServerlessHttpApi ---
  # AWS::ApiGatewayV2 metric names: 4xx, 5xx, Latency; dimension ApiId.
  ApiGateway4xxAlarm:
    Type: AWS::CloudWatch::Alarm
    Properties:
      AlarmName: !Sub "ApiGateway-4xx-${ServerlessHttpApi}"
      AlarmDescription: "Elevated 4xx responses on the Slack events HTTP API"
      Namespace: AWS/ApiGateway
      MetricName: 4xx
      Dimensions:
        - Name: ApiId
          Value: !Ref ServerlessHttpApi
      Statistic: Sum
      Period: 300
      EvaluationPeriods: 1
      Threshold: 5
      ComparisonOperator: GreaterThanOrEqualToThreshold
      TreatMissingData: notBreaching
      AlarmActions:
        - !Sub "arn:aws:sns:${AWS::Region}:${AWS::AccountId}:site-alerts"

  ApiGateway5xxAlarm:
    Type: AWS::CloudWatch::Alarm
    Properties:
      AlarmName: !Sub "ApiGateway-5xx-${ServerlessHttpApi}"
      AlarmDescription: "5xx responses on the Slack events HTTP API"
      Namespace: AWS/ApiGateway
      MetricName: 5xx
      Dimensions:
        - Name: ApiId
          Value: !Ref ServerlessHttpApi
      Statistic: Sum
      Period: 300
      EvaluationPeriods: 1
      Threshold: 1
      ComparisonOperator: GreaterThanOrEqualToThreshold
      TreatMissingData: notBreaching
      AlarmActions:
        - !Sub "arn:aws:sns:${AWS::Region}:${AWS::AccountId}:site-alerts"

  # Latency p99 via ExtendedStatistic. ~3000ms target chosen alongside the
  # Lambda Duration thresholds (Slack requires a fast 3s ack).
  ApiGatewayLatencyAlarm:
    Type: AWS::CloudWatch::Alarm
    Properties:
      AlarmName: !Sub "ApiGateway-Latency-${ServerlessHttpApi}"
      AlarmDescription: "p99 latency on the Slack events HTTP API exceeded 3s"
      Namespace: AWS/ApiGateway
      MetricName: Latency
      Dimensions:
        - Name: ApiId
          Value: !Ref ServerlessHttpApi
      ExtendedStatistic: p99
      Period: 300
      EvaluationPeriods: 3
      DatapointsToAlarm: 2
      Threshold: 3000
      ComparisonOperator: GreaterThanOrEqualToThreshold
      TreatMissingData: notBreaching
      AlarmActions:
        - !Sub "arn:aws:sns:${AWS::Region}:${AWS::AccountId}:site-alerts"

  # --- CloudWatch Log Groups (explicit 60-day retention) ---
  SlackBotLogGroup:
    Type: AWS::Logs::LogGroup
    Properties:
      LogGroupName: !Sub "/aws/lambda/${SlackBotFunction}"
      RetentionInDays: 60

  WeeklyPostLogGroup:
    Type: AWS::Logs::LogGroup
    Properties:
      LogGroupName: !Sub "/aws/lambda/${WeeklyPostFunction}"
      RetentionInDays: 60

  RosterSyncLogGroup:
    Type: AWS::Logs::LogGroup
    Properties:
      LogGroupName: !Sub "/aws/lambda/${RosterSyncFunction}"
      RetentionInDays: 60

  RingSchedulerLogGroup:
    Type: AWS::Logs::LogGroup
    Properties:
      LogGroupName: !Sub "/aws/lambda/${RingSchedulerFunction}"
      RetentionInDays: 60

  HolidayRouterLogGroup:
    Type: AWS::Logs::LogGroup
    Properties:
      LogGroupName: !Sub "/aws/lambda/${HolidayRouterFunction}"
      RetentionInDays: 60

  ReleaseNotifierLogGroup:
    Type: AWS::Logs::LogGroup
    Properties:
      LogGroupName: !Sub "/aws/lambda/${ReleaseNotifierFunction}"
      RetentionInDays: 60

Outputs:
  SlackBotApiUrl:
    Description: URL for Slack app Request URL configuration
    Value: !Sub "https://${ServerlessHttpApi}.execute-api.${AWS::Region}.amazonaws.com/slack/events"
  ShiftTableName:
    Value: !Ref ShiftTable
  SlackBotFunctionArn:
    Value: !GetAtt SlackBotFunction.Arn
  WeeklyPostFunctionArn:
    Value: !GetAtt WeeklyPostFunction.Arn
  RosterSyncFunctionArn:
    Value: !GetAtt RosterSyncFunction.Arn
  RingSchedulerFunctionArn:
    Value: !GetAtt RingSchedulerFunction.Arn
  HolidayRouterFunctionArn:
    Value: !GetAtt HolidayRouterFunction.Arn
  HolidaySchedulerExecutionRoleArn:
    Description: Role EventBridge Scheduler assumes to invoke the holiday router; the slack-bot passes this when creating per-holiday schedules
    Value: !GetAtt HolidaySchedulerExecutionRole.Arn
  ReleaseNotifierFunctionArn:
    Value: !GetAtt ReleaseNotifierFunction.Arn
  ReleaseNotifyInvokeRoleArn:
    Description: Set this as the RELEASE_NOTIFY_INVOKE_ROLE_ARN repo variable for release.yaml
    Value: !GetAtt ReleaseNotifyInvokeRole.Arn