# Infrastructure Audit Workflow Template
# Physical server and SBC health check, connectivity, and OOB management
#
# Usage:
#   Provide host IPs/hostnames to audit.
#   Workflow checks connectivity, hardware health, and OOB access.

name: infrastructure-audit
version: '1.0.0'
description: |
  Infrastructure audit workflow for physical servers and SBCs.
  Checks SSH connectivity, OOB management access (iDRAC/iLO/IPMI),
  hardware health sensors, disk status, and generates a status report
  with recovery recommendations.

inputs:
  - name: hosts
    type: array
    description: List of host IPs or hostnames to audit
    required: true

  - name: oobHosts
    type: array
    description: List of OOB management IPs (iDRAC/iLO/IPMI) to check
    default: []

  - name: checkDocker
    type: boolean
    description: Check Docker daemon and container status on each host
    default: true

steps:
  # Step 1: SSH connectivity check
  - id: connectivity
    agent: infrastructure_expert
    action: check_ssh_connectivity
    description: |
      Tests SSH access to each host:
      - Key-based authentication
      - Password fallback detection
      - Connection timeout (2s per host)
      - Uptime and load average
    inputs:
      hosts: ${{ inputs.hosts }}
    timeout: 60000
    retries: 1

  # Step 2: OOB management check (runs in parallel)
  - id: oob_check
    agent: infrastructure_expert
    action: check_oob_management
    description: |
      Tests out-of-band management access:
      - iDRAC REST API reachability
      - IPMI over LAN connectivity
      - Power state query
      - Firmware version detection
    inputs:
      oobHosts: ${{ inputs.oobHosts }}
    parallel: true
    timeout: 60000
    retries: 1

  # Step 3: Hardware health (runs in parallel)
  - id: hardware_health
    agent: infrastructure_expert
    action: check_hardware_health
    description: |
      Queries hardware sensors on reachable hosts:
      - CPU temperature
      - Disk SMART status
      - Memory usage
      - Fan status (via OOB if available)
      - System Event Log entries
    inputs:
      hosts: ${{ inputs.hosts }}
      oobHosts: ${{ inputs.oobHosts }}
    parallel: true
    timeout: 120000
    retries: 1

  # Step 4: Docker status check (runs in parallel)
  - id: docker_check
    agent: infrastructure_expert
    action: check_docker_status
    description: |
      Checks Docker daemon and container health:
      - Daemon running status
      - Container count and state
      - Swarm membership (if applicable)
      - Disk usage for Docker volumes
    inputs:
      hosts: ${{ inputs.hosts }}
      checkDocker: ${{ inputs.checkDocker }}
    parallel: true
    timeout: 60000
    retries: 1

  # Step 5: Generate infrastructure report
  - id: report
    agent: infrastructure_expert
    action: generate_infrastructure_report
    description: |
      Generates infrastructure status report:
      - Host reachability matrix
      - Hardware health summary
      - OOB management status
      - Docker/service status
      - Boot time estimates per host type
      - Recovery recommendations for unreachable hosts
    inputs:
      connectivity: ${{ steps.connectivity.output }}
      oob_check: ${{ steps.oob_check.output }}
      hardware_health: ${{ steps.hardware_health.output }}
      docker_check: ${{ steps.docker_check.output }}
    dependsOn:
      - connectivity
      - oob_check
      - hardware_health
      - docker_check
    timeout: 60000

timeout: 600000