KubeRay API Reference¶

{
  "$defs": {
    "AuthOptions": {
      "additionalProperties": true,
      "description": "[AuthOptions](https://ray-project.github.io/kuberay/reference/api/#authoptions) for the Ray cluster.\n\nEvery field the CRD supports is meant to be declared here. As an escape hatch for any that is missing, undeclared fields are passed through to the Kubernetes manifest, in either `snake_case` or `camelCase`. See [Extra Spec Fields](../tutorial/kuberay.md#extra-spec-fields).",
      "properties": {
        "mode": {
          "default": "token",
          "enum": [
            "token",
            "disabled"
          ],
          "title": "Mode",
          "type": "string"
        },
        "secret_name": {
          "anyOf": [
            {
              "type": "string"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "description": "Name of the `Secret` holding the authentication token. The `Secret` must have an `auth_token` data key. If set, KubeRay skips generating a per-`RayCluster` token `Secret`. Requires KubeRay 1.6.0.",
          "title": "Secret Name"
        },
        "enable_k8s_token_auth": {
          "anyOf": [
            {
              "type": "boolean"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "description": "Delegate authentication to the Kubernetes API server. Sets `RAY_ENABLE_K8S_TOKEN_AUTH=true` on all Ray pods; the ServiceAccount token mounted into Raylets must be granted the `ray:write` custom verb via RBAC. Requires `mode='token'`, Ray 2.55.0 or later, and KubeRay 1.6.0, and cannot be combined with `secret_name` \u2014 the token comes from the mounted ServiceAccount rather than a `Secret`. KubeRay rejects it for `RayJob` and `RayService`, so it cannot be used with [`KubeRayInteractiveJob`][dagster_ray.kuberay.KubeRayInteractiveJob] \u2014 use [`KubeRayCluster`][dagster_ray.kuberay.KubeRayCluster].",
          "title": "Enable K8S Token Auth"
        }
      },
      "title": "AuthOptions",
      "type": "object"
    },
    "ExecutionOptionsConfig": {
      "properties": {
        "cpu": {
          "anyOf": [
            {
              "type": "integer"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "title": "Cpu"
        },
        "gpu": {
          "anyOf": [
            {
              "type": "integer"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "title": "Gpu"
        },
        "object_store_memory": {
          "anyOf": [
            {
              "type": "integer"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "title": "Object Store Memory"
        }
      },
      "title": "ExecutionOptionsConfig",
      "type": "object"
    },
    "InteractiveRayJobConfig": {
      "description": "Same as [`RayJobConfig`][dagster_ray.kuberay.configs.RayJobConfig], but `spec.submission_mode` mode has to be `InteractiveMode`",
      "properties": {
        "kind": {
          "default": "RayJob",
          "title": "Kind",
          "type": "string"
        },
        "api_version": {
          "default": "ray.io/v1",
          "title": "Api Version",
          "type": "string"
        },
        "metadata": {
          "additionalProperties": true,
          "description": "Kubernetes metadata, except the name field can be omitted. In this case it will be generated by `dagster-ray`.",
          "title": "Metadata",
          "type": "object"
        },
        "spec": {
          "$ref": "#/$defs/InteractiveRayJobSpec"
        }
      },
      "title": "InteractiveRayJobConfig",
      "type": "object"
    },
    "InteractiveRayJobSpec": {
      "additionalProperties": true,
      "description": "Same as [`RayJobSpec`][dagster_ray.kuberay.configs.RayJobSpec], but `mode` has to be `InteractiveMode`",
      "properties": {
        "active_deadline_seconds": {
          "default": 86400,
          "title": "Active Deadline Seconds",
          "type": "integer"
        },
        "pre_running_deadline_seconds": {
          "anyOf": [
            {
              "type": "integer"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "description": "Deadline for the `RayJob` to reach the `Running` state, measured from `.status.startTime`. If it doesn't, KubeRay fails the job with reason `PreRunningDeadlineExceeded`. Useful for reaping jobs stuck in `Initializing` or `Waiting` \u2014 for example when the `RayCluster` can never be scheduled. Unset means no deadline. Requires KubeRay 1.6.0: older operators prune the field without an error.",
          "title": "Pre Running Deadline Seconds"
        },
        "backoff_limit": {
          "default": 0,
          "title": "Backoff Limit",
          "type": "integer"
        },
        "ray_cluster_spec": {
          "anyOf": [
            {
              "$ref": "#/$defs/RayClusterSpec"
            },
            {
              "type": "null"
            }
          ]
        },
        "submitter_pod_template": {
          "anyOf": [
            {
              "additionalProperties": true,
              "type": "object"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "title": "Submitter Pod Template"
        },
        "submitter_config": {
          "anyOf": [
            {
              "additionalProperties": true,
              "type": "object"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "title": "Submitter Config"
        },
        "metadata": {
          "anyOf": [
            {
              "additionalProperties": true,
              "type": "object"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "title": "Metadata"
        },
        "cluster_selector": {
          "anyOf": [
            {
              "additionalProperties": {
                "type": "string"
              },
              "type": "object"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "title": "Cluster Selector"
        },
        "managed_by": {
          "anyOf": [
            {
              "type": "string"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "title": "Managed By"
        },
        "deletion_strategy": {
          "anyOf": [
            {
              "additionalProperties": true,
              "type": "object"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "description": "`RayJob` cleanup policy. Unset by default: cleanup is governed by `shutdown_after_job_finishes`, which deletes the `RayCluster` once the job succeeds or fails. Requires KubeRay 1.5.0 (the field was named `deletionPolicy` before that) **and** the `RayJobDeletionPolicy` feature gate \u2014 the KubeRay controller fails the `RayJob` with `ValidationFailed` if the gate is off. The gate is alpha in 1.5.x (off by default) and beta in 1.6.x (on by default). See [Deletion Strategy](../tutorial/kuberay.md#deletion-strategy).",
          "title": "Deletion Strategy"
        },
        "runtime_env_yaml": {
          "anyOf": [
            {
              "type": "string"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "title": "Runtime Env Yaml"
        },
        "job_id": {
          "anyOf": [
            {
              "type": "string"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "title": "Job Id"
        },
        "submission_mode": {
          "const": "InteractiveMode",
          "default": "InteractiveMode",
          "title": "Submission Mode",
          "type": "string"
        },
        "entrypoint_resources": {
          "anyOf": [
            {
              "type": "string"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "title": "Entrypoint Resources"
        },
        "entrypoint_num_cpus": {
          "anyOf": [
            {
              "type": "number"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "title": "Entrypoint Num Cpus"
        },
        "entrypoint_memory": {
          "anyOf": [
            {
              "type": "number"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "title": "Entrypoint Memory"
        },
        "entrypoint_num_gpus": {
          "anyOf": [
            {
              "type": "number"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "title": "Entrypoint Num Gpus"
        },
        "ttl_seconds_after_finished": {
          "anyOf": [
            {
              "type": "integer"
            },
            {
              "type": "null"
            }
          ],
          "default": 300,
          "title": "Ttl Seconds After Finished"
        },
        "shutdown_after_job_finishes": {
          "default": true,
          "title": "Shutdown After Job Finishes",
          "type": "boolean"
        },
        "suspend": {
          "anyOf": [
            {
              "type": "boolean"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "title": "Suspend"
        }
      },
      "title": "InteractiveRayJobSpec",
      "type": "object"
    },
    "Lifecycle": {
      "properties": {
        "create": {
          "default": true,
          "description": "Whether to create the resource. If set to `False`, the user can manually call `.create` instead.",
          "title": "Create",
          "type": "boolean"
        },
        "wait": {
          "default": true,
          "description": "Whether to wait for the remote Ray cluster to become ready to accept connections. If set to `False`, the user can manually call `.wait` instead.",
          "title": "Wait",
          "type": "boolean"
        },
        "connect": {
          "default": true,
          "description": "Whether to run `ray.init` against the remote Ray cluster. If set to `False`, the user can manually call `.connect` instead.",
          "title": "Connect",
          "type": "boolean"
        },
        "cleanup": {
          "default": "always",
          "description": "Resource cleanup policy. Determines when the resource should be deleted after Dagster step execution or during interruption.",
          "enum": [
            "never",
            "always",
            "on_exception"
          ],
          "title": "Cleanup",
          "type": "string"
        }
      },
      "title": "Lifecycle",
      "type": "object"
    },
    "RayClusterSpec": {
      "additionalProperties": true,
      "description": "[RayCluster spec](https://ray-project.github.io/kuberay/reference/api/#rayclusterspec) configuration options. A few sensible defaults are provided for convenience.\n\nEvery field the CRD supports is meant to be declared here. As an escape hatch for any that is missing, undeclared fields are passed through to the Kubernetes manifest, in either `snake_case` or `camelCase`. See [Extra Spec Fields](../tutorial/kuberay.md#extra-spec-fields).",
      "properties": {
        "suspend": {
          "anyOf": [
            {
              "type": "boolean"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "title": "Suspend"
        },
        "managed_by": {
          "anyOf": [
            {
              "type": "string"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "title": "Managed By"
        },
        "autoscaler_options": {
          "additionalProperties": true,
          "default": {
            "upscalingMode": "Default",
            "idleTimeoutSeconds": 60,
            "env": [],
            "envFrom": [],
            "resources": {
              "limits": {
                "cpu": "50m",
                "memory": "0.1Gi"
              },
              "requests": {
                "cpu": "50m",
                "memory": "0.1Gi"
              }
            }
          },
          "title": "Autoscaler Options",
          "type": "object"
        },
        "head_service_annotations": {
          "anyOf": [
            {
              "additionalProperties": {
                "type": "string"
              },
              "type": "object"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "title": "Head Service Annotations"
        },
        "enable_in_tree_autoscaling": {
          "default": false,
          "title": "Enable In Tree Autoscaling",
          "type": "boolean"
        },
        "gcs_fault_tolerance_options": {
          "anyOf": [
            {
              "additionalProperties": true,
              "type": "object"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "title": "Gcs Fault Tolerance Options"
        },
        "head_group_spec": {
          "additionalProperties": true,
          "default": {
            "serviceType": "ClusterIP",
            "rayStartParams": {},
            "metadata": {
              "annotations": {},
              "labels": {}
            },
            "template": {
              "spec": {
                "affinity": {},
                "containers": [
                  {
                    "imagePullPolicy": "Always",
                    "name": "head",
                    "volumeMounts": [
                      {
                        "mountPath": "/tmp/ray",
                        "name": "ray-logs"
                      }
                    ]
                  }
                ],
                "imagePullSecrets": [],
                "nodeSelector": {},
                "tolerations": [],
                "volumes": [
                  {
                    "emptyDir": {},
                    "name": "ray-logs"
                  }
                ]
              }
            }
          },
          "title": "Head Group Spec",
          "type": "object"
        },
        "ray_version": {
          "anyOf": [
            {
              "type": "string"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "title": "Ray Version"
        },
        "worker_group_specs": {
          "default": [
            {
              "groupName": "workers",
              "replicas": 0,
              "minReplicas": 0,
              "maxReplicas": 1,
              "rayStartParams": {},
              "template": {
                "metadata": {
                  "annotations": {},
                  "labels": {}
                },
                "spec": {
                  "affinity": {},
                  "containers": [
                    {
                      "imagePullPolicy": "Always",
                      "name": "worker",
                      "volumeMounts": [
                        {
                          "mountPath": "/tmp/ray",
                          "name": "ray-logs"
                        }
                      ]
                    }
                  ],
                  "imagePullSecrets": [],
                  "nodeSelector": {},
                  "tolerations": [],
                  "volumes": [
                    {
                      "emptyDir": {},
                      "name": "ray-logs"
                    }
                  ]
                }
              }
            }
          ],
          "items": {
            "additionalProperties": true,
            "type": "object"
          },
          "title": "Worker Group Specs",
          "type": "array"
        },
        "auth_options": {
          "anyOf": [
            {
              "$ref": "#/$defs/AuthOptions"
            },
            {
              "type": "null"
            }
          ],
          "default": null
        },
        "upgrade_strategy": {
          "anyOf": [
            {
              "$ref": "#/$defs/RayClusterUpgradeStrategy"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "description": "Scaling policy used when upgrading the `RayCluster`. See [RayClusterUpgradeStrategy](https://ray-project.github.io/kuberay/reference/api/#rayclusterupgradestrategy). Requires KubeRay 1.6.0: older operators prune the field without an error."
        }
      },
      "title": "RayClusterSpec",
      "type": "object"
    },
    "RayClusterUpgradeStrategy": {
      "additionalProperties": true,
      "description": "[RayClusterUpgradeStrategy](https://ray-project.github.io/kuberay/reference/api/#rayclusterupgradestrategy) for the Ray cluster.\n\nEvery field the CRD supports is meant to be declared here. As an escape hatch for any that is missing, undeclared fields are passed through to the Kubernetes manifest, in either `snake_case` or `camelCase`. See [Extra Spec Fields](../tutorial/kuberay.md#extra-spec-fields).",
      "properties": {
        "type": {
          "description": "Strategy used when upgrading the `RayCluster` pods. `Recreate` deletes all existing pods before creating new ones; the string `\"None\"` creates no new pods. Note that `\"None\"` is a KubeRay strategy name, distinct from leaving `upgrade_strategy` itself unset.",
          "enum": [
            "Recreate",
            "None"
          ],
          "title": "Type",
          "type": "string"
        }
      },
      "required": [
        "type"
      ],
      "title": "RayClusterUpgradeStrategy",
      "type": "object"
    },
    "RayDataExecutionOptions": {
      "properties": {
        "execution_options": {
          "$ref": "#/$defs/ExecutionOptionsConfig"
        },
        "cpu_limit": {
          "default": 5000,
          "title": "Cpu Limit",
          "type": "integer"
        },
        "gpu_limit": {
          "default": 0,
          "title": "Gpu Limit",
          "type": "integer"
        },
        "verbose_progress": {
          "default": true,
          "title": "Verbose Progress",
          "type": "boolean"
        },
        "use_polars": {
          "default": true,
          "title": "Use Polars",
          "type": "boolean"
        }
      },
      "title": "RayDataExecutionOptions",
      "type": "object"
    }
  },
  "description": "Provides a Ray Job for Dagster steps.\n\nIs the recommended way to run Ray workloads with automatic cluster management. It creates a Ray Job, connects to it in client mode and sets the `jobId` field. Cleanup is handled by the KubeRay controller or by the resource lifecycle logic.\n\nInfo:\n    Image defaults to `dagster/image` run tag.\n\nTip:\n    Make sure `ray[full]` is available in the image.",
  "properties": {
    "lifecycle": {
      "$ref": "#/$defs/Lifecycle",
      "description": "Actions to perform during resource setup."
    },
    "timeout": {
      "default": 600.0,
      "description": "Timeout for Ray readiness in seconds",
      "title": "Timeout",
      "type": "number"
    },
    "ray_init_options": {
      "additionalProperties": true,
      "description": "Additional keyword arguments to pass to `ray.init()` call, such as `runtime_env`, `num_cpus`, etc. Dagster's `EnvVar` is supported. More details in [Ray docs](https://docs.ray.io/en/latest/ray-core/api/doc/ray.init.html).",
      "title": "Ray Init Options",
      "type": "object"
    },
    "data_execution_options": {
      "$ref": "#/$defs/RayDataExecutionOptions"
    },
    "redis_port": {
      "default": 10001,
      "description": "Redis port for connection. Make sure to match with the actual available port.",
      "title": "Redis Port",
      "type": "integer"
    },
    "dashboard_port": {
      "default": 8265,
      "description": "Dashboard port for connection. Make sure to match with the actual available port.",
      "title": "Dashboard Port",
      "type": "integer"
    },
    "env_vars": {
      "anyOf": [
        {
          "additionalProperties": {
            "type": "string"
          },
          "type": "object"
        },
        {
          "type": "null"
        }
      ],
      "description": "Environment variables to pass to the Ray cluster.",
      "title": "Env Vars"
    },
    "enable_tracing": {
      "default": false,
      "description": "Enable tracing: inject `RAY_PROFILING=1` and `RAY_task_events_report_interval_ms=0` into the Ray cluster configuration. This allows using `ray.timeline()` to fetch recorded task events. Learn more: [KubeRay docs](https://docs.ray.io/en/latest/ray-core/api/doc/ray.timeline.html#ray-timeline)",
      "title": "Enable Tracing",
      "type": "boolean"
    },
    "enable_actor_task_logging": {
      "default": false,
      "description": "Enable actor task logging: inject `RAY_ENABLE_RECORD_ACTOR_TASK_LOGGING=1` into the Ray cluster configuration.",
      "title": "Enable Actor Task Logging",
      "type": "boolean"
    },
    "enable_debug_post_mortem": {
      "default": false,
      "description": "Enable post-mortem debugging: inject `RAY_DEBUG_POST_MORTEM=1` into the Ray cluster configuration. Learn more: [KubeRay docs](https://docs.ray.io/en/latest/ray-observability/ray-distributed-debugger.html)",
      "title": "Enable Debug Post Mortem",
      "type": "boolean"
    },
    "enable_legacy_debugger": {
      "default": false,
      "description": "Enable legacy debugger: inject `RAY_DEBUG=legacy` into the Ray cluster configuration. Learn more: [KubeRay docs](https://docs.ray.io/en/latest/ray-observability/user-guides/debug-apps/ray-debugging.html#using-the-ray-debugger)",
      "title": "Enable Legacy Debugger",
      "type": "boolean"
    },
    "image": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Image to inject into the `RayCluster` spec. Defaults to `dagster/image` run tag. Images already provided in the `RayCluster` spec won't be overridden.",
      "title": "Image"
    },
    "deployment_name": {
      "default": "dev",
      "description": "Dagster deployment name. Is used as a prefix for the Kubernetes resource name. Dagster Cloud variables are used to determine the default value.",
      "title": "Deployment Name",
      "type": "string"
    },
    "failure_tolerance_timeout": {
      "default": 0.0,
      "description": "The period in seconds to wait for the cluster to transition out of `failed` state if it reaches it. This state can be transient under certain conditions. With the default value of 0, the first `failed` state appearance will raise an exception immediately.",
      "title": "Failure Tolerance Timeout",
      "type": "number"
    },
    "poll_interval": {
      "default": 1.0,
      "description": "Poll interval for various API requests",
      "title": "Poll Interval",
      "type": "number"
    },
    "ray_job": {
      "$ref": "#/$defs/InteractiveRayJobConfig",
      "description": "Configuration for the Kubernetes `RayJob` CR"
    },
    "client": {
      "description": "Kubernetes `RayJob` client",
      "title": "Client"
    },
    "log_cluster_conditions": {
      "default": true,
      "description": "Whether to log `RayCluster` conditions while waiting for the RayCluster to become ready. Learn more: [KubeRay docs](https://docs.ray.io/en/latest/cluster/kubernetes/user-guides/observability.html#raycluster-status-conditions).",
      "title": "Log Cluster Conditions",
      "type": "boolean"
    }
  },
  "title": "KubeRayInteractiveJob",
  "type": "object"
}

{
  "$defs": {
    "AuthOptions": {
      "additionalProperties": true,
      "description": "[AuthOptions](https://ray-project.github.io/kuberay/reference/api/#authoptions) for the Ray cluster.\n\nEvery field the CRD supports is meant to be declared here. As an escape hatch for any that is missing, undeclared fields are passed through to the Kubernetes manifest, in either `snake_case` or `camelCase`. See [Extra Spec Fields](../tutorial/kuberay.md#extra-spec-fields).",
      "properties": {
        "mode": {
          "default": "token",
          "enum": [
            "token",
            "disabled"
          ],
          "title": "Mode",
          "type": "string"
        },
        "secret_name": {
          "anyOf": [
            {
              "type": "string"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "description": "Name of the `Secret` holding the authentication token. The `Secret` must have an `auth_token` data key. If set, KubeRay skips generating a per-`RayCluster` token `Secret`. Requires KubeRay 1.6.0.",
          "title": "Secret Name"
        },
        "enable_k8s_token_auth": {
          "anyOf": [
            {
              "type": "boolean"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "description": "Delegate authentication to the Kubernetes API server. Sets `RAY_ENABLE_K8S_TOKEN_AUTH=true` on all Ray pods; the ServiceAccount token mounted into Raylets must be granted the `ray:write` custom verb via RBAC. Requires `mode='token'`, Ray 2.55.0 or later, and KubeRay 1.6.0, and cannot be combined with `secret_name` \u2014 the token comes from the mounted ServiceAccount rather than a `Secret`. KubeRay rejects it for `RayJob` and `RayService`, so it cannot be used with [`KubeRayInteractiveJob`][dagster_ray.kuberay.KubeRayInteractiveJob] \u2014 use [`KubeRayCluster`][dagster_ray.kuberay.KubeRayCluster].",
          "title": "Enable K8S Token Auth"
        }
      },
      "title": "AuthOptions",
      "type": "object"
    },
    "ClusterSharing": {
      "description": "Defines the strategy for sharing `RayCluster` resources with other Dagster steps.\n\nBy default, the cluster is expected to be created by Dagster during one of the previously executed steps.\n\n!!!note\n\n    Cluster sharing uses the Kubernetes Lease API (`coordination.k8s.io`) for leader election\n    to coordinate cluster creation across parallel steps. The Dagster ServiceAccount must have\n    `create`, `get`, and `delete` permissions on `leases` in the `coordination.k8s.io` API group.",
      "properties": {
        "enabled": {
          "default": false,
          "description": "Whether to enable sharing of RayClusters.",
          "title": "Enabled",
          "type": "boolean"
        },
        "match_dagster_labels": {
          "$ref": "#/$defs/MatchDagsterLabels",
          "description": "Configuration for matching on Dagster-generated labels."
        },
        "match_labels": {
          "anyOf": [
            {
              "additionalProperties": {
                "type": "string"
              },
              "type": "object"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "description": "Additional user-provided labels to match on.",
          "title": "Match Labels"
        },
        "ttl_seconds": {
          "default": 1800.0,
          "description": "Time to live for the lock placed on the `RayCluster` resource, marking it as in use by the current Dagster step. The lock is renewed periodically while the step is running (see `heartbeat`), so this only needs to cover the gap between renewals.",
          "title": "Ttl Seconds",
          "type": "number"
        },
        "heartbeat": {
          "$ref": "#/$defs/ClusterSharingHeartbeat",
          "description": "Configuration for background renewal of the cluster sharing lock while the Dagster step is running."
        }
      },
      "title": "ClusterSharing",
      "type": "object"
    },
    "ClusterSharingHeartbeat": {
      "description": "Controls background renewal of the cluster sharing lock while the Dagster step is running.\n\nWithout renewal, the lock expires `ttl_seconds` after step start and the garbage collection\nsensor may delete the cluster while the step is still using it. With renewal, `ttl_seconds`\ncan stay short: idle clusters are reaped promptly, active steps survive.\n\nEach renewal updates the lock's `heartbeat_at` timestamp; `created_at` always points at the\ninitial lock placement. A hanging step renews its lock indefinitely \u2014 set the\n`dagster/max_runtime` tag on runs to bound step runtime.",
      "properties": {
        "enabled": {
          "default": true,
          "description": "Whether to renew the cluster sharing lock in the background while the Dagster step is running.",
          "title": "Enabled",
          "type": "boolean"
        },
        "refresh_seconds": {
          "default": 10.0,
          "description": "How often to renew the lock. Must be well below `ClusterSharing.ttl_seconds` \u2014 if a renewal is missed, the lock must not have expired yet, or the cluster can be deleted mid-step.",
          "title": "Refresh Seconds",
          "type": "number"
        }
      },
      "title": "ClusterSharingHeartbeat",
      "type": "object"
    },
    "ExecutionOptionsConfig": {
      "properties": {
        "cpu": {
          "anyOf": [
            {
              "type": "integer"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "title": "Cpu"
        },
        "gpu": {
          "anyOf": [
            {
              "type": "integer"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "title": "Gpu"
        },
        "object_store_memory": {
          "anyOf": [
            {
              "type": "integer"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "title": "Object Store Memory"
        }
      },
      "title": "ExecutionOptionsConfig",
      "type": "object"
    },
    "Lifecycle": {
      "properties": {
        "create": {
          "default": true,
          "description": "Whether to create the resource. If set to `False`, the user can manually call `.create` instead.",
          "title": "Create",
          "type": "boolean"
        },
        "wait": {
          "default": true,
          "description": "Whether to wait for the remote Ray cluster to become ready to accept connections. If set to `False`, the user can manually call `.wait` instead.",
          "title": "Wait",
          "type": "boolean"
        },
        "connect": {
          "default": true,
          "description": "Whether to run `ray.init` against the remote Ray cluster. If set to `False`, the user can manually call `.connect` instead.",
          "title": "Connect",
          "type": "boolean"
        },
        "cleanup": {
          "default": "always",
          "description": "Resource cleanup policy. Determines when the resource should be deleted after Dagster step execution or during interruption.",
          "enum": [
            "never",
            "always",
            "on_exception"
          ],
          "title": "Cleanup",
          "type": "string"
        }
      },
      "title": "Lifecycle",
      "type": "object"
    },
    "MatchDagsterLabels": {
      "properties": {
        "cluster_sharing": {
          "default": true,
          "description": "Whether to match on `dagster/cluster-sharing=true` label.",
          "title": "Cluster Sharing",
          "type": "boolean"
        },
        "code_location": {
          "default": true,
          "description": "Whether to match on `dagster/code-location` label. The value will be taken from the current Dagster code location.",
          "title": "Code Location",
          "type": "boolean"
        },
        "resource_key": {
          "default": true,
          "description": "Whether to match on `dagster/resource-key` label. The value will be taken from the current Dagster resource key.",
          "title": "Resource Key",
          "type": "boolean"
        },
        "git_sha": {
          "default": true,
          "description": "Whether to match on `dagster/git-sha` label. The value will be taken from `DAGSTER_CLOUD_GIT_SHA` environment variable.",
          "title": "Git Sha",
          "type": "boolean"
        },
        "run_id": {
          "default": false,
          "description": "Whether to match on `dagster/run-id` label. The value will be taken from the current Dagster run ID.",
          "title": "Run Id",
          "type": "boolean"
        }
      },
      "title": "MatchDagsterLabels",
      "type": "object"
    },
    "RayClusterConfig": {
      "properties": {
        "kind": {
          "default": "RayCluster",
          "title": "Kind",
          "type": "string"
        },
        "api_version": {
          "default": "ray.io/v1",
          "title": "Api Version",
          "type": "string"
        },
        "metadata": {
          "additionalProperties": true,
          "description": "Kubernetes metadata, except the name field can be omitted. In this case it will be generated by `dagster-ray`.",
          "title": "Metadata",
          "type": "object"
        },
        "spec": {
          "$ref": "#/$defs/RayClusterSpec"
        }
      },
      "title": "RayClusterConfig",
      "type": "object"
    },
    "RayClusterSpec": {
      "additionalProperties": true,
      "description": "[RayCluster spec](https://ray-project.github.io/kuberay/reference/api/#rayclusterspec) configuration options. A few sensible defaults are provided for convenience.\n\nEvery field the CRD supports is meant to be declared here. As an escape hatch for any that is missing, undeclared fields are passed through to the Kubernetes manifest, in either `snake_case` or `camelCase`. See [Extra Spec Fields](../tutorial/kuberay.md#extra-spec-fields).",
      "properties": {
        "suspend": {
          "anyOf": [
            {
              "type": "boolean"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "title": "Suspend"
        },
        "managed_by": {
          "anyOf": [
            {
              "type": "string"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "title": "Managed By"
        },
        "autoscaler_options": {
          "additionalProperties": true,
          "default": {
            "upscalingMode": "Default",
            "idleTimeoutSeconds": 60,
            "env": [],
            "envFrom": [],
            "resources": {
              "limits": {
                "cpu": "50m",
                "memory": "0.1Gi"
              },
              "requests": {
                "cpu": "50m",
                "memory": "0.1Gi"
              }
            }
          },
          "title": "Autoscaler Options",
          "type": "object"
        },
        "head_service_annotations": {
          "anyOf": [
            {
              "additionalProperties": {
                "type": "string"
              },
              "type": "object"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "title": "Head Service Annotations"
        },
        "enable_in_tree_autoscaling": {
          "default": false,
          "title": "Enable In Tree Autoscaling",
          "type": "boolean"
        },
        "gcs_fault_tolerance_options": {
          "anyOf": [
            {
              "additionalProperties": true,
              "type": "object"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "title": "Gcs Fault Tolerance Options"
        },
        "head_group_spec": {
          "additionalProperties": true,
          "default": {
            "serviceType": "ClusterIP",
            "rayStartParams": {},
            "metadata": {
              "annotations": {},
              "labels": {}
            },
            "template": {
              "spec": {
                "affinity": {},
                "containers": [
                  {
                    "imagePullPolicy": "Always",
                    "name": "head",
                    "volumeMounts": [
                      {
                        "mountPath": "/tmp/ray",
                        "name": "ray-logs"
                      }
                    ]
                  }
                ],
                "imagePullSecrets": [],
                "nodeSelector": {},
                "tolerations": [],
                "volumes": [
                  {
                    "emptyDir": {},
                    "name": "ray-logs"
                  }
                ]
              }
            }
          },
          "title": "Head Group Spec",
          "type": "object"
        },
        "ray_version": {
          "anyOf": [
            {
              "type": "string"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "title": "Ray Version"
        },
        "worker_group_specs": {
          "default": [
            {
              "groupName": "workers",
              "replicas": 0,
              "minReplicas": 0,
              "maxReplicas": 1,
              "rayStartParams": {},
              "template": {
                "metadata": {
                  "annotations": {},
                  "labels": {}
                },
                "spec": {
                  "affinity": {},
                  "containers": [
                    {
                      "imagePullPolicy": "Always",
                      "name": "worker",
                      "volumeMounts": [
                        {
                          "mountPath": "/tmp/ray",
                          "name": "ray-logs"
                        }
                      ]
                    }
                  ],
                  "imagePullSecrets": [],
                  "nodeSelector": {},
                  "tolerations": [],
                  "volumes": [
                    {
                      "emptyDir": {},
                      "name": "ray-logs"
                    }
                  ]
                }
              }
            }
          ],
          "items": {
            "additionalProperties": true,
            "type": "object"
          },
          "title": "Worker Group Specs",
          "type": "array"
        },
        "auth_options": {
          "anyOf": [
            {
              "$ref": "#/$defs/AuthOptions"
            },
            {
              "type": "null"
            }
          ],
          "default": null
        },
        "upgrade_strategy": {
          "anyOf": [
            {
              "$ref": "#/$defs/RayClusterUpgradeStrategy"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "description": "Scaling policy used when upgrading the `RayCluster`. See [RayClusterUpgradeStrategy](https://ray-project.github.io/kuberay/reference/api/#rayclusterupgradestrategy). Requires KubeRay 1.6.0: older operators prune the field without an error."
        }
      },
      "title": "RayClusterSpec",
      "type": "object"
    },
    "RayClusterUpgradeStrategy": {
      "additionalProperties": true,
      "description": "[RayClusterUpgradeStrategy](https://ray-project.github.io/kuberay/reference/api/#rayclusterupgradestrategy) for the Ray cluster.\n\nEvery field the CRD supports is meant to be declared here. As an escape hatch for any that is missing, undeclared fields are passed through to the Kubernetes manifest, in either `snake_case` or `camelCase`. See [Extra Spec Fields](../tutorial/kuberay.md#extra-spec-fields).",
      "properties": {
        "type": {
          "description": "Strategy used when upgrading the `RayCluster` pods. `Recreate` deletes all existing pods before creating new ones; the string `\"None\"` creates no new pods. Note that `\"None\"` is a KubeRay strategy name, distinct from leaving `upgrade_strategy` itself unset.",
          "enum": [
            "Recreate",
            "None"
          ],
          "title": "Type",
          "type": "string"
        }
      },
      "required": [
        "type"
      ],
      "title": "RayClusterUpgradeStrategy",
      "type": "object"
    },
    "RayDataExecutionOptions": {
      "properties": {
        "execution_options": {
          "$ref": "#/$defs/ExecutionOptionsConfig"
        },
        "cpu_limit": {
          "default": 5000,
          "title": "Cpu Limit",
          "type": "integer"
        },
        "gpu_limit": {
          "default": 0,
          "title": "Gpu Limit",
          "type": "integer"
        },
        "verbose_progress": {
          "default": true,
          "title": "Verbose Progress",
          "type": "boolean"
        },
        "use_polars": {
          "default": true,
          "title": "Use Polars",
          "type": "boolean"
        }
      },
      "title": "RayDataExecutionOptions",
      "type": "object"
    }
  },
  "description": "Provides a Ray Cluster for Dagster steps.\n\nIt is advised to use [`KubeRayInteractiveJob`][dagster_ray.kuberay.resources.KubeRayInteractiveJob] with KubeRay >= 1.3.0 instead.\n\nInfo:\n    Image defaults to `dagster/image` run tag.\n\nTip:\n    Make sure `ray[full]` is available in the image.",
  "properties": {
    "lifecycle": {
      "$ref": "#/$defs/Lifecycle",
      "description": "Actions to perform during resource setup."
    },
    "timeout": {
      "default": 600.0,
      "description": "Timeout for Ray readiness in seconds",
      "title": "Timeout",
      "type": "number"
    },
    "ray_init_options": {
      "additionalProperties": true,
      "description": "Additional keyword arguments to pass to `ray.init()` call, such as `runtime_env`, `num_cpus`, etc. Dagster's `EnvVar` is supported. More details in [Ray docs](https://docs.ray.io/en/latest/ray-core/api/doc/ray.init.html).",
      "title": "Ray Init Options",
      "type": "object"
    },
    "data_execution_options": {
      "$ref": "#/$defs/RayDataExecutionOptions"
    },
    "redis_port": {
      "default": 10001,
      "description": "Redis port for connection. Make sure to match with the actual available port.",
      "title": "Redis Port",
      "type": "integer"
    },
    "dashboard_port": {
      "default": 8265,
      "description": "Dashboard port for connection. Make sure to match with the actual available port.",
      "title": "Dashboard Port",
      "type": "integer"
    },
    "env_vars": {
      "anyOf": [
        {
          "additionalProperties": {
            "type": "string"
          },
          "type": "object"
        },
        {
          "type": "null"
        }
      ],
      "description": "Environment variables to pass to the Ray cluster.",
      "title": "Env Vars"
    },
    "enable_tracing": {
      "default": false,
      "description": "Enable tracing: inject `RAY_PROFILING=1` and `RAY_task_events_report_interval_ms=0` into the Ray cluster configuration. This allows using `ray.timeline()` to fetch recorded task events. Learn more: [KubeRay docs](https://docs.ray.io/en/latest/ray-core/api/doc/ray.timeline.html#ray-timeline)",
      "title": "Enable Tracing",
      "type": "boolean"
    },
    "enable_actor_task_logging": {
      "default": false,
      "description": "Enable actor task logging: inject `RAY_ENABLE_RECORD_ACTOR_TASK_LOGGING=1` into the Ray cluster configuration.",
      "title": "Enable Actor Task Logging",
      "type": "boolean"
    },
    "enable_debug_post_mortem": {
      "default": false,
      "description": "Enable post-mortem debugging: inject `RAY_DEBUG_POST_MORTEM=1` into the Ray cluster configuration. Learn more: [KubeRay docs](https://docs.ray.io/en/latest/ray-observability/ray-distributed-debugger.html)",
      "title": "Enable Debug Post Mortem",
      "type": "boolean"
    },
    "enable_legacy_debugger": {
      "default": false,
      "description": "Enable legacy debugger: inject `RAY_DEBUG=legacy` into the Ray cluster configuration. Learn more: [KubeRay docs](https://docs.ray.io/en/latest/ray-observability/user-guides/debug-apps/ray-debugging.html#using-the-ray-debugger)",
      "title": "Enable Legacy Debugger",
      "type": "boolean"
    },
    "image": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Image to inject into the `RayCluster` spec. Defaults to `dagster/image` run tag. Images already provided in the `RayCluster` spec won't be overridden.",
      "title": "Image"
    },
    "deployment_name": {
      "default": "dev",
      "description": "Dagster deployment name. Is used as a prefix for the Kubernetes resource name. Dagster Cloud variables are used to determine the default value.",
      "title": "Deployment Name",
      "type": "string"
    },
    "failure_tolerance_timeout": {
      "default": 0.0,
      "description": "The period in seconds to wait for the cluster to transition out of `failed` state if it reaches it. This state can be transient under certain conditions. With the default value of 0, the first `failed` state appearance will raise an exception immediately.",
      "title": "Failure Tolerance Timeout",
      "type": "number"
    },
    "poll_interval": {
      "default": 1.0,
      "description": "Poll interval for various API requests",
      "title": "Poll Interval",
      "type": "number"
    },
    "cluster_sharing": {
      "$ref": "#/$defs/ClusterSharing",
      "description": "Configuration for sharing the `RayCluster` across Dagster steps. Existing clusters matching this configuration will be reused without recreating them. A `dagster/sharing=true` label will be applied to the `RayCluster`, and a `dagster/lock-<run-id>-<step-id>=<lock>` annotation will be placed on the `RayCluster` to mark it as being used by this step. Cleanup will only proceed if the `RayCluster` is not being used by any other steps, therefore cluster sharing should be used in conjunction with [dagster_ray.kuberay.sensors.cleanup_expired_kuberay_clusters][] sensor."
    },
    "ray_cluster": {
      "$ref": "#/$defs/RayClusterConfig",
      "description": "Kubernetes `RayCluster` CR configuration."
    },
    "client": {
      "description": "Kubernetes `RayCluster` client",
      "title": "Client"
    },
    "log_cluster_conditions": {
      "default": true,
      "description": "Whether to log RayCluster conditions while waiting for the RayCluster to become ready. Learn more: [KubeRay docs](https://docs.ray.io/en/latest/cluster/kubernetes/user-guides/observability.html#raycluster-status-conditions).",
      "title": "Log Cluster Conditions",
      "type": "boolean"
    }
  },
  "title": "KubeRayCluster",
  "type": "object"
}