{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://volcano.sh/schemas/job.json",
  "title": "Volcano Job",
  "description": "Schema for the Volcano Job (vcjob) custom resource definition. A Volcano Job defines a batch workload with multiple task types, lifecycle policies, gang scheduling requirements, plugin integration, and queue assignment for Kubernetes batch processing.",
  "type": "object",
  "required": ["apiVersion", "kind", "metadata", "spec"],
  "properties": {
    "apiVersion": {
      "type": "string",
      "description": "API version of the Volcano Job resource.",
      "const": "batch.volcano.sh/v1alpha1"
    },
    "kind": {
      "type": "string",
      "description": "Resource kind.",
      "const": "Job"
    },
    "metadata": {
      "$ref": "#/$defs/ObjectMeta"
    },
    "spec": {
      "$ref": "#/$defs/JobSpec"
    },
    "status": {
      "$ref": "#/$defs/JobStatus"
    }
  },
  "$defs": {
    "JobSpec": {
      "type": "object",
      "description": "Specification of a Volcano Job defining workload structure, tasks, scheduling requirements, and lifecycle policies.",
      "properties": {
        "schedulerName": {
          "type": "string",
          "description": "Name of the scheduler responsible for this job. Defaults to 'volcano'.",
          "default": "volcano"
        },
        "minAvailable": {
          "type": "integer",
          "description": "Minimum number of pods that must be schedulable simultaneously for gang scheduling. If fewer pods are available, none are scheduled.",
          "minimum": 0
        },
        "tasks": {
          "type": "array",
          "description": "List of task groups composing the job. Each task defines a pod template, replica count, and task-level policies.",
          "items": {
            "$ref": "#/$defs/TaskSpec"
          }
        },
        "policies": {
          "type": "array",
          "description": "Job-level lifecycle policies controlling how the job reacts to events like pod failures or completions.",
          "items": {
            "$ref": "#/$defs/LifecyclePolicy"
          }
        },
        "plugins": {
          "type": "object",
          "description": "Map of plugin names to argument arrays. Plugins inject environment variables and sidecar containers for ML frameworks. Common plugins include 'tensorflow', 'pytorch', 'mpi', 'svc', and 'env'.",
          "additionalProperties": {
            "type": "array",
            "items": {
              "type": "string"
            }
          },
          "examples": [
            {"svc": [], "env": []},
            {"pytorch": ["--master=master", "--worker=worker"]},
            {"mpi": ["--master=mpimaster", "--worker=mpiworker"]}
          ]
        },
        "queue": {
          "type": "string",
          "description": "Name of the Volcano Queue to submit this job to. Determines scheduling priority and resource quota constraints."
        },
        "priorityClassName": {
          "type": "string",
          "description": "Kubernetes PriorityClass name controlling this job's scheduling priority."
        },
        "maxRetry": {
          "type": "integer",
          "description": "Maximum number of retry attempts before the job is permanently failed.",
          "minimum": 0
        },
        "ttlSecondsAfterFinished": {
          "type": "integer",
          "description": "Seconds after completion before the job is automatically garbage-collected. Omit to disable automatic cleanup.",
          "minimum": 0
        },
        "runningDuration": {
          "type": "string",
          "description": "Maximum allowed running duration for the job (e.g. '2h', '30m'). Job is terminated if it exceeds this duration.",
          "examples": ["1h", "30m", "2h30m"]
        },
        "volumes": {
          "type": "array",
          "description": "Volumes to be mounted into job task containers.",
          "items": {
            "type": "object"
          }
        }
      }
    },
    "TaskSpec": {
      "type": "object",
      "description": "A named task group within a Volcano Job, defining a set of pods with a shared pod template and optional task-level policies.",
      "required": ["name", "replicas", "template"],
      "properties": {
        "name": {
          "type": "string",
          "description": "Unique name of the task within the job. Used to reference the task in plugins and dependencies.",
          "maxLength": 63,
          "pattern": "^[a-z0-9][a-z0-9-]*[a-z0-9]$"
        },
        "replicas": {
          "type": "integer",
          "description": "Number of pod replicas for this task.",
          "minimum": 1
        },
        "template": {
          "type": "object",
          "description": "Kubernetes pod template spec for pods in this task."
        },
        "policies": {
          "type": "array",
          "description": "Lifecycle policies for this task, overriding job-level policies for events affecting this task's pods.",
          "items": {
            "$ref": "#/$defs/LifecyclePolicy"
          }
        },
        "topologyPolicy": {
          "type": "string",
          "description": "NUMA topology policy for resource allocation. Controls how CPU and memory are assigned relative to NUMA nodes.",
          "enum": ["none", "best-effort", "restricted", "single-numa-node"]
        },
        "maxRetry": {
          "type": "integer",
          "description": "Maximum retry attempts for this task before it is marked as failed.",
          "minimum": 0
        },
        "dependsOn": {
          "type": "object",
          "description": "Task dependency configuration controlling execution order within the job.",
          "properties": {
            "name": {
              "type": "array",
              "description": "Names of tasks that must successfully complete before this task starts.",
              "items": {
                "type": "string"
              }
            },
            "iteration": {
              "type": "string",
              "description": "Dependency evaluation strategy.",
              "enum": ["any", "all"]
            }
          }
        }
      }
    },
    "LifecyclePolicy": {
      "type": "object",
      "description": "A lifecycle policy rule defining an automated action to take when a specific event occurs during job or task execution.",
      "properties": {
        "action": {
          "type": "string",
          "description": "Action to execute when the policy condition is met.",
          "enum": [
            "AbortJob",
            "RestartJob",
            "RestartTask",
            "TerminateJob",
            "CompleteJob",
            "ResumeJob",
            "SyncJob",
            "EnqueueJob"
          ]
        },
        "event": {
          "type": "string",
          "description": "Single event type that triggers this policy.",
          "enum": [
            "PodFailed",
            "PodEvicted",
            "PodPending",
            "PodRunning",
            "PodSucceeded",
            "TaskCompleted",
            "AnyEvent",
            "CommandIssued",
            "JobUnknown",
            "JobUpdated",
            "OutOfSync"
          ]
        },
        "events": {
          "type": "array",
          "description": "Multiple event types that each independently trigger this policy.",
          "items": {
            "type": "string"
          }
        },
        "exitCode": {
          "type": "integer",
          "description": "Container exit code that triggers this policy when a pod exits with this code."
        },
        "timeout": {
          "type": "string",
          "description": "Duration after which the policy fires if the triggering condition persists.",
          "examples": ["30s", "5m", "1h"]
        }
      }
    },
    "JobStatus": {
      "type": "object",
      "description": "Observed status of a Volcano Job including its lifecycle phase, retry count, and per-task pod counts.",
      "properties": {
        "state": {
          "type": "object",
          "description": "Current phase and transition details of the job.",
          "properties": {
            "phase": {
              "type": "string",
              "description": "Current lifecycle phase of the job.",
              "enum": [
                "Pending",
                "Aborting",
                "Aborted",
                "Running",
                "Restarting",
                "Completing",
                "Completed",
                "Terminating",
                "Terminated",
                "Failed"
              ]
            },
            "reason": {
              "type": "string",
              "description": "Machine-readable reason for the current phase."
            },
            "message": {
              "type": "string",
              "description": "Human-readable description of the current state."
            },
            "lastTransitionTime": {
              "type": "string",
              "format": "date-time",
              "description": "Timestamp of the most recent phase transition."
            }
          }
        },
        "minAvailable": {
          "type": "integer",
          "description": "Minimum pod count required for this job."
        },
        "retryCount": {
          "type": "integer",
          "format": "int32",
          "description": "Number of times the job has been retried so far."
        },
        "runningDuration": {
          "type": "string",
          "description": "Duration the job has been in the Running phase."
        },
        "taskStatusCount": {
          "type": "object",
          "description": "Per-task breakdown of pod counts by Kubernetes pod phase.",
          "additionalProperties": {
            "type": "object",
            "properties": {
              "phase": {
                "type": "object",
                "description": "Map of Kubernetes pod phase names to pod counts.",
                "additionalProperties": {
                  "type": "integer"
                }
              }
            }
          }
        },
        "conditions": {
          "type": "array",
          "description": "Detailed conditions describing the current state of the job.",
          "items": {
            "type": "object",
            "properties": {
              "type": {
                "type": "string"
              },
              "status": {
                "type": "string",
                "enum": ["True", "False", "Unknown"]
              },
              "transitionID": {
                "type": "string"
              },
              "lastTransitionTime": {
                "type": "string",
                "format": "date-time"
              },
              "reason": {
                "type": "string"
              },
              "message": {
                "type": "string"
              }
            }
          }
        }
      }
    },
    "ObjectMeta": {
      "type": "object",
      "description": "Standard Kubernetes object metadata.",
      "required": ["name"],
      "properties": {
        "name": {
          "type": "string",
          "description": "Name of the job, unique within its namespace.",
          "maxLength": 253,
          "pattern": "^[a-z0-9][a-z0-9.-]*[a-z0-9]$"
        },
        "namespace": {
          "type": "string",
          "description": "Namespace the job belongs to."
        },
        "labels": {
          "type": "object",
          "description": "Labels for organizing and selecting the job.",
          "additionalProperties": {
            "type": "string"
          }
        },
        "annotations": {
          "type": "object",
          "description": "Non-identifying metadata for the job.",
          "additionalProperties": {
            "type": "string"
          }
        }
      }
    }
  },
  "examples": [
    {
      "apiVersion": "batch.volcano.sh/v1alpha1",
      "kind": "Job",
      "metadata": {
        "name": "pytorch-training",
        "namespace": "default"
      },
      "spec": {
        "minAvailable": 3,
        "schedulerName": "volcano",
        "queue": "training",
        "plugins": {
          "pytorch": ["--master=master", "--worker=worker"],
          "svc": [],
          "env": []
        },
        "policies": [
          {
            "event": "PodEvicted",
            "action": "RestartJob"
          }
        ],
        "maxRetry": 3,
        "tasks": [
          {
            "name": "master",
            "replicas": 1,
            "template": {
              "spec": {
                "containers": [
                  {
                    "name": "pytorch",
                    "image": "pytorch/pytorch:2.0.0-cuda11.7-cudnn8-runtime",
                    "resources": {
                      "requests": {"cpu": "4", "memory": "8Gi"},
                      "limits": {"cpu": "4", "memory": "8Gi", "nvidia.com/gpu": "1"}
                    }
                  }
                ]
              }
            }
          },
          {
            "name": "worker",
            "replicas": 2,
            "template": {
              "spec": {
                "containers": [
                  {
                    "name": "pytorch",
                    "image": "pytorch/pytorch:2.0.0-cuda11.7-cudnn8-runtime",
                    "resources": {
                      "requests": {"cpu": "4", "memory": "8Gi"},
                      "limits": {"cpu": "4", "memory": "8Gi", "nvidia.com/gpu": "2"}
                    }
                  }
                ]
              }
            }
          }
        ]
      }
    }
  ]
}