docs: update generated docs (#981)

diff --git a/docs/dyn/dataflow_v1b3.projects.jobs.html b/docs/dyn/dataflow_v1b3.projects.jobs.html
index 8287947..df7d7bd 100644
--- a/docs/dyn/dataflow_v1b3.projects.jobs.html
+++ b/docs/dyn/dataflow_v1b3.projects.jobs.html
@@ -90,7 +90,7 @@
 <p class="firstline">Returns the workItems Resource.</p>
 
 <p class="toc_element">
-  <code><a href="#aggregated">aggregated(projectId, filter=None, location=None, pageToken=None, pageSize=None, view=None, x__xgafv=None)</a></code></p>
+  <code><a href="#aggregated">aggregated(projectId, pageSize=None, filter=None, location=None, pageToken=None, view=None, x__xgafv=None)</a></code></p>
 <p class="firstline">List the jobs of a project across all regions.</p>
 <p class="toc_element">
   <code><a href="#aggregated_next">aggregated_next(previous_request, previous_response)</a></code></p>
@@ -99,13 +99,13 @@
   <code><a href="#create">create(projectId, body=None, location=None, replaceJobId=None, view=None, x__xgafv=None)</a></code></p>
 <p class="firstline">Creates a Cloud Dataflow job.</p>
 <p class="toc_element">
-  <code><a href="#get">get(projectId, jobId, view=None, location=None, x__xgafv=None)</a></code></p>
+  <code><a href="#get">get(projectId, jobId, location=None, view=None, x__xgafv=None)</a></code></p>
 <p class="firstline">Gets the state of the specified Cloud Dataflow job.</p>
 <p class="toc_element">
   <code><a href="#getMetrics">getMetrics(projectId, jobId, startTime=None, location=None, x__xgafv=None)</a></code></p>
 <p class="firstline">Request the job status.</p>
 <p class="toc_element">
-  <code><a href="#list">list(projectId, filter=None, location=None, pageToken=None, pageSize=None, view=None, x__xgafv=None)</a></code></p>
+  <code><a href="#list">list(projectId, filter=None, pageSize=None, location=None, view=None, pageToken=None, x__xgafv=None)</a></code></p>
 <p class="firstline">List the jobs of a project.</p>
 <p class="toc_element">
   <code><a href="#list_next">list_next(previous_request, previous_response)</a></code></p>
@@ -118,20 +118,20 @@
 <p class="firstline">Updates the state of an existing Cloud Dataflow job.</p>
 <h3>Method Details</h3>
 <div class="method">
-    <code class="details" id="aggregated">aggregated(projectId, filter=None, location=None, pageToken=None, pageSize=None, view=None, x__xgafv=None)</code>
+    <code class="details" id="aggregated">aggregated(projectId, pageSize=None, filter=None, location=None, pageToken=None, view=None, x__xgafv=None)</code>
   <pre>List the jobs of a project across all regions.
 
 Args:
   projectId: string, The project which owns the jobs. (required)
+  pageSize: integer, If there are many jobs, limit response to at most this many.
+The actual number of jobs returned will be the lesser of max_responses
+and an unspecified server-defined limit.
   filter: string, The kind of filter to use.
   location: string, The [regional endpoint]
 (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that
 contains this job.
   pageToken: string, Set this to the &#x27;next_page_token&#x27; field of a previous response
 to request additional results in a long list.
-  pageSize: integer, If there are many jobs, limit response to at most this many.
-The actual number of jobs returned will be the lesser of max_responses
-and an unspecified server-defined limit.
   view: string, Level of information requested in response. Default is `JOB_VIEW_SUMMARY`.
   x__xgafv: string, V1 error format.
     Allowed values
@@ -148,243 +148,285 @@
       # body is empty {}.
     &quot;jobs&quot;: [ # A subset of the requested job information.
       { # Defines a job to be run by the Cloud Dataflow service.
-        &quot;clientRequestId&quot;: &quot;A String&quot;, # The client&#x27;s unique identifier of the job, re-used across retried attempts.
-            # If this field is set, the service will ensure its uniqueness.
-            # The request to create a job will fail if the service has knowledge of a
-            # previously submitted job with the same client&#x27;s ID and job name.
-            # The caller may use this field to ensure idempotence of job
-            # creation across retried attempts to create a job.
-            # By default, the field is empty and, in that case, the service ignores it.
-        &quot;id&quot;: &quot;A String&quot;, # The unique ID of this job.
-            #
-            # This field is set by the Cloud Dataflow service when the Job is
-            # created, and is immutable for the life of the job.
-        &quot;currentStateTime&quot;: &quot;A String&quot;, # The timestamp associated with the current state.
-        &quot;transformNameMapping&quot;: { # The map of transform name prefixes of the job to be replaced to the
-            # corresponding name prefixes of the new job.
-          &quot;a_key&quot;: &quot;A String&quot;,
-        },
-        &quot;environment&quot;: { # Describes the environment in which a Dataflow Job runs. # The environment for the job.
-          &quot;internalExperiments&quot;: { # Experimental settings.
-            &quot;a_key&quot;: &quot;&quot;, # Properties of the object. Contains field @type with type URL.
-          },
-          &quot;workerRegion&quot;: &quot;A String&quot;, # The Compute Engine region
-              # (https://cloud.google.com/compute/docs/regions-zones/regions-zones) in
-              # which worker processing should occur, e.g. &quot;us-west1&quot;. Mutually exclusive
-              # with worker_zone. If neither worker_region nor worker_zone is specified,
-              # default to the control plane&#x27;s region.
-          &quot;serviceKmsKeyName&quot;: &quot;A String&quot;, # If set, contains the Cloud KMS key identifier used to encrypt data
-              # at rest, AKA a Customer Managed Encryption Key (CMEK).
-              #
-              # Format:
-              #   projects/PROJECT_ID/locations/LOCATION/keyRings/KEY_RING/cryptoKeys/KEY
-          &quot;userAgent&quot;: { # A description of the process that generated the request.
-            &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
-          },
-          &quot;workerZone&quot;: &quot;A String&quot;, # The Compute Engine zone
-              # (https://cloud.google.com/compute/docs/regions-zones/regions-zones) in
-              # which worker processing should occur, e.g. &quot;us-west1-a&quot;. Mutually exclusive
-              # with worker_region. If neither worker_region nor worker_zone is specified,
-              # a zone in the control plane&#x27;s region is chosen based on available capacity.
-          &quot;clusterManagerApiService&quot;: &quot;A String&quot;, # The type of cluster manager API to use.  If unknown or
-              # unspecified, the service will attempt to choose a reasonable
-              # default.  This should be in the form of the API service name,
-              # e.g. &quot;compute.googleapis.com&quot;.
-          &quot;tempStoragePrefix&quot;: &quot;A String&quot;, # The prefix of the resources the system should use for temporary
-              # storage.  The system will append the suffix &quot;/temp-{JOBNAME} to
-              # this resource prefix, where {JOBNAME} is the value of the
-              # job_name field.  The resulting bucket and object prefix is used
-              # as the prefix of the resources used to store temporary data
-              # needed during the job execution.  NOTE: This will override the
-              # value in taskrunner_settings.
-              # The supported resource type is:
-              #
-              # Google Cloud Storage:
-              #
-              #   storage.googleapis.com/{bucket}/{object}
-              #   bucket.storage.googleapis.com/{object}
-          &quot;experiments&quot;: [ # The list of experiments to enable.
-            &quot;A String&quot;,
-          ],
-          &quot;version&quot;: { # A structure describing which components and their versions of the service
-              # are required in order to run the job.
-            &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
-          },
-          &quot;serviceAccountEmail&quot;: &quot;A String&quot;, # Identity to run virtual machines as. Defaults to the default account.
-          &quot;sdkPipelineOptions&quot;: { # The Cloud Dataflow SDK pipeline options specified by the user. These
-              # options are passed through the service and are used to recreate the
-              # SDK pipeline options on the worker in a language agnostic and platform
-              # independent way.
-            &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
-          },
-          &quot;flexResourceSchedulingGoal&quot;: &quot;A String&quot;, # Which Flexible Resource Scheduling mode to run in.
-          &quot;workerPools&quot;: [ # The worker pools. At least one &quot;harness&quot; worker pool must be
-              # specified in order for the job to have workers.
-            { # Describes one particular pool of Cloud Dataflow workers to be
-                # instantiated by the Cloud Dataflow service in order to perform the
-                # computations required by a job.  Note that a workflow job may use
-                # multiple pools, in order to match the various computational
-                # requirements of the various stages of the job.
-              &quot;numThreadsPerWorker&quot;: 42, # The number of threads per worker harness. If empty or unspecified, the
-                  # service will choose a number of threads (according to the number of cores
-                  # on the selected machine type for batch, or 1 by convention for streaming).
-              &quot;numWorkers&quot;: 42, # Number of Google Compute Engine workers in this pool needed to
-                  # execute the job.  If zero or unspecified, the service will
-                  # attempt to choose a reasonable default.
-              &quot;zone&quot;: &quot;A String&quot;, # Zone to run the worker pools in.  If empty or unspecified, the service
-                  # will attempt to choose a reasonable default.
-              &quot;diskSourceImage&quot;: &quot;A String&quot;, # Fully qualified source image for disks.
-              &quot;packages&quot;: [ # Packages to be installed on workers.
-                { # The packages that must be installed in order for a worker to run the
-                    # steps of the Cloud Dataflow job that will be assigned to its worker
-                    # pool.
-                    #
-                    # This is the mechanism by which the Cloud Dataflow SDK causes code to
-                    # be loaded onto the workers. For example, the Cloud Dataflow Java SDK
-                    # might use this to install jars containing the user&#x27;s code and all of the
-                    # various dependencies (libraries, data files, etc.) required in order
-                    # for that code to run.
-                  &quot;name&quot;: &quot;A String&quot;, # The name of the package.
-                  &quot;location&quot;: &quot;A String&quot;, # The resource to read the package from. The supported resource type is:
-                      #
-                      # Google Cloud Storage:
-                      #
-                      #   storage.googleapis.com/{bucket}
-                      #   bucket.storage.googleapis.com/
-                },
-              ],
-              &quot;teardownPolicy&quot;: &quot;A String&quot;, # Sets the policy for determining when to turndown worker pool.
-                  # Allowed values are: `TEARDOWN_ALWAYS`, `TEARDOWN_ON_SUCCESS`, and
-                  # `TEARDOWN_NEVER`.
-                  # `TEARDOWN_ALWAYS` means workers are always torn down regardless of whether
-                  # the job succeeds. `TEARDOWN_ON_SUCCESS` means workers are torn down
-                  # if the job succeeds. `TEARDOWN_NEVER` means the workers are never torn
-                  # down.
-                  #
-                  # If the workers are not torn down by the service, they will
-                  # continue to run and use Google Compute Engine VM resources in the
-                  # user&#x27;s project until they are explicitly terminated by the user.
-                  # Because of this, Google recommends using the `TEARDOWN_ALWAYS`
-                  # policy except for small, manually supervised test jobs.
-                  #
-                  # If unknown or unspecified, the service will attempt to choose a reasonable
-                  # default.
-              &quot;onHostMaintenance&quot;: &quot;A String&quot;, # The action to take on host maintenance, as defined by the Google
-                  # Compute Engine API.
-              &quot;poolArgs&quot;: { # Extra arguments for this worker pool.
-                &quot;a_key&quot;: &quot;&quot;, # Properties of the object. Contains field @type with type URL.
+          &quot;pipelineDescription&quot;: { # A descriptive representation of submitted pipeline as well as the executed # Preliminary field: The format of this data may change at any time.
+              # A description of the user pipeline and stages through which it is executed.
+              # Created by Cloud Dataflow service.  Only retrieved with
+              # JOB_VIEW_DESCRIPTION or JOB_VIEW_ALL.
+              # form.  This data is provided by the Dataflow service for ease of visualizing
+              # the pipeline and interpreting Dataflow provided metrics.
+            &quot;displayData&quot;: [ # Pipeline level display data.
+              { # Data provided with a pipeline or transform to provide descriptive info.
+                &quot;url&quot;: &quot;A String&quot;, # An optional full URL.
+                &quot;javaClassValue&quot;: &quot;A String&quot;, # Contains value if the data is of java class type.
+                &quot;timestampValue&quot;: &quot;A String&quot;, # Contains value if the data is of timestamp type.
+                &quot;durationValue&quot;: &quot;A String&quot;, # Contains value if the data is of duration type.
+                &quot;label&quot;: &quot;A String&quot;, # An optional label to display in a dax UI for the element.
+                &quot;key&quot;: &quot;A String&quot;, # The key identifying the display data.
+                    # This is intended to be used as a label for the display data
+                    # when viewed in a dax monitoring system.
+                &quot;namespace&quot;: &quot;A String&quot;, # The namespace for the key. This is usually a class name or programming
+                    # language namespace (i.e. python module) which defines the display data.
+                    # This allows a dax monitoring system to specially handle the data
+                    # and perform custom rendering.
+                &quot;floatValue&quot;: 3.14, # Contains value if the data is of float type.
+                &quot;strValue&quot;: &quot;A String&quot;, # Contains value if the data is of string type.
+                &quot;int64Value&quot;: &quot;A String&quot;, # Contains value if the data is of int64 type.
+                &quot;boolValue&quot;: True or False, # Contains value if the data is of a boolean type.
+                &quot;shortStrValue&quot;: &quot;A String&quot;, # A possible additional shorter value to display.
+                    # For example a java_class_name_value of com.mypackage.MyDoFn
+                    # will be stored with MyDoFn as the short_str_value and
+                    # com.mypackage.MyDoFn as the java_class_name value.
+                    # short_str_value can be displayed and java_class_name_value
+                    # will be displayed as a tooltip.
               },
-              &quot;diskSizeGb&quot;: 42, # Size of root disk for VMs, in GB.  If zero or unspecified, the service will
-                  # attempt to choose a reasonable default.
-              &quot;workerHarnessContainerImage&quot;: &quot;A String&quot;, # Required. Docker container image that executes the Cloud Dataflow worker
-                  # harness, residing in Google Container Registry.
-                  #
-                  # Deprecated for the Fn API path. Use sdk_harness_container_images instead.
-              &quot;diskType&quot;: &quot;A String&quot;, # Type of root disk for VMs.  If empty or unspecified, the service will
-                  # attempt to choose a reasonable default.
-              &quot;machineType&quot;: &quot;A String&quot;, # Machine type (e.g. &quot;n1-standard-1&quot;).  If empty or unspecified, the
-                  # service will attempt to choose a reasonable default.
-              &quot;kind&quot;: &quot;A String&quot;, # The kind of the worker pool; currently only `harness` and `shuffle`
-                  # are supported.
-              &quot;sdkHarnessContainerImages&quot;: [ # Set of SDK harness containers needed to execute this pipeline. This will
-                  # only be set in the Fn API path. For non-cross-language pipelines this
-                  # should have only one entry. Cross-language pipelines will have two or more
-                  # entries.
-                { # Defines a SDK harness container for executing Dataflow pipelines.
-                  &quot;containerImage&quot;: &quot;A String&quot;, # A docker container image that resides in Google Container Registry.
-                  &quot;useSingleCorePerContainer&quot;: True or False, # If true, recommends the Dataflow service to use only one core per SDK
-                      # container instance with this image. If false (or unset) recommends using
-                      # more than one core per SDK container instance with this image for
-                      # efficiency. Note that Dataflow service may choose to override this property
-                      # if needed.
-                },
-              ],
-              &quot;dataDisks&quot;: [ # Data disks that are used by a VM in this workflow.
-                { # Describes the data disk used by a workflow job.
-                  &quot;diskType&quot;: &quot;A String&quot;, # Disk storage type, as defined by Google Compute Engine.  This
-                      # must be a disk type appropriate to the project and zone in which
-                      # the workers will run.  If unknown or unspecified, the service
-                      # will attempt to choose a reasonable default.
-                      #
-                      # For example, the standard persistent disk type is a resource name
-                      # typically ending in &quot;pd-standard&quot;.  If SSD persistent disks are
-                      # available, the resource name typically ends with &quot;pd-ssd&quot;.  The
-                      # actual valid values are defined the Google Compute Engine API,
-                      # not by the Cloud Dataflow API; consult the Google Compute Engine
-                      # documentation for more information about determining the set of
-                      # available disk types for a particular project and zone.
-                      #
-                      # Google Compute Engine Disk types are local to a particular
-                      # project in a particular zone, and so the resource name will
-                      # typically look something like this:
-                      #
-                      # compute.googleapis.com/projects/project-id/zones/zone/diskTypes/pd-standard
-                  &quot;sizeGb&quot;: 42, # Size of disk in GB.  If zero or unspecified, the service will
-                      # attempt to choose a reasonable default.
-                  &quot;mountPoint&quot;: &quot;A String&quot;, # Directory in a VM where disk is mounted.
-                },
-              ],
-              &quot;subnetwork&quot;: &quot;A String&quot;, # Subnetwork to which VMs will be assigned, if desired.  Expected to be of
-                  # the form &quot;regions/REGION/subnetworks/SUBNETWORK&quot;.
-              &quot;ipConfiguration&quot;: &quot;A String&quot;, # Configuration for VM IPs.
-              &quot;taskrunnerSettings&quot;: { # Taskrunner configuration settings. # Settings passed through to Google Compute Engine workers when
-                  # using the standard Dataflow task runner.  Users should ignore
-                  # this field.
-                &quot;alsologtostderr&quot;: True or False, # Whether to also send taskrunner log info to stderr.
-                &quot;taskGroup&quot;: &quot;A String&quot;, # The UNIX group ID on the worker VM to use for tasks launched by
-                    # taskrunner; e.g. &quot;wheel&quot;.
-                &quot;harnessCommand&quot;: &quot;A String&quot;, # The command to launch the worker harness.
-                &quot;logDir&quot;: &quot;A String&quot;, # The directory on the VM to store logs.
-                &quot;oauthScopes&quot;: [ # The OAuth2 scopes to be requested by the taskrunner in order to
-                    # access the Cloud Dataflow API.
+            ],
+            &quot;originalPipelineTransform&quot;: [ # Description of each transform in the pipeline and collections between them.
+              { # Description of the type, names/ids, and input/outputs for a transform.
+                &quot;outputCollectionName&quot;: [ # User  names for all collection outputs to this transform.
                   &quot;A String&quot;,
                 ],
-                &quot;dataflowApiVersion&quot;: &quot;A String&quot;, # The API version of endpoint, e.g. &quot;v1b3&quot;
-                &quot;logUploadLocation&quot;: &quot;A String&quot;, # Indicates where to put logs.  If this is not specified, the logs
-                    # will not be uploaded.
-                    #
-                    # The supported resource type is:
-                    #
-                    # Google Cloud Storage:
-                    #   storage.googleapis.com/{bucket}/{object}
-                    #   bucket.storage.googleapis.com/{object}
-                &quot;streamingWorkerMainClass&quot;: &quot;A String&quot;, # The streaming worker main class name.
-                &quot;workflowFileName&quot;: &quot;A String&quot;, # The file to store the workflow in.
-                &quot;languageHint&quot;: &quot;A String&quot;, # The suggested backend language.
-                &quot;commandlinesFileName&quot;: &quot;A String&quot;, # The file to store preprocessing commands in.
-                &quot;baseTaskDir&quot;: &quot;A String&quot;, # The location on the worker for task-specific subdirectories.
-                &quot;tempStoragePrefix&quot;: &quot;A String&quot;, # The prefix of the resources the taskrunner should use for
-                    # temporary storage.
-                    #
-                    # The supported resource type is:
-                    #
-                    # Google Cloud Storage:
-                    #   storage.googleapis.com/{bucket}/{object}
-                    #   bucket.storage.googleapis.com/{object}
-                &quot;baseUrl&quot;: &quot;A String&quot;, # The base URL for the taskrunner to use when accessing Google Cloud APIs.
-                    #
-                    # When workers access Google Cloud APIs, they logically do so via
-                    # relative URLs.  If this field is specified, it supplies the base
-                    # URL to use for resolving these relative URLs.  The normative
-                    # algorithm used is defined by RFC 1808, &quot;Relative Uniform Resource
-                    # Locators&quot;.
-                    #
-                    # If not specified, the default value is &quot;http://www.googleapis.com/&quot;
-                &quot;logToSerialconsole&quot;: True or False, # Whether to send taskrunner log info to Google Compute Engine VM serial
-                    # console.
-                &quot;continueOnException&quot;: True or False, # Whether to continue taskrunner if an exception is hit.
-                &quot;parallelWorkerSettings&quot;: { # Provides data to pass through to the worker harness. # The settings to pass to the parallel worker harness.
-                  &quot;tempStoragePrefix&quot;: &quot;A String&quot;, # The prefix of the resources the system should use for temporary
-                      # storage.
+                &quot;displayData&quot;: [ # Transform-specific display data.
+                  { # Data provided with a pipeline or transform to provide descriptive info.
+                    &quot;url&quot;: &quot;A String&quot;, # An optional full URL.
+                    &quot;javaClassValue&quot;: &quot;A String&quot;, # Contains value if the data is of java class type.
+                    &quot;timestampValue&quot;: &quot;A String&quot;, # Contains value if the data is of timestamp type.
+                    &quot;durationValue&quot;: &quot;A String&quot;, # Contains value if the data is of duration type.
+                    &quot;label&quot;: &quot;A String&quot;, # An optional label to display in a dax UI for the element.
+                    &quot;key&quot;: &quot;A String&quot;, # The key identifying the display data.
+                        # This is intended to be used as a label for the display data
+                        # when viewed in a dax monitoring system.
+                    &quot;namespace&quot;: &quot;A String&quot;, # The namespace for the key. This is usually a class name or programming
+                        # language namespace (i.e. python module) which defines the display data.
+                        # This allows a dax monitoring system to specially handle the data
+                        # and perform custom rendering.
+                    &quot;floatValue&quot;: 3.14, # Contains value if the data is of float type.
+                    &quot;strValue&quot;: &quot;A String&quot;, # Contains value if the data is of string type.
+                    &quot;int64Value&quot;: &quot;A String&quot;, # Contains value if the data is of int64 type.
+                    &quot;boolValue&quot;: True or False, # Contains value if the data is of a boolean type.
+                    &quot;shortStrValue&quot;: &quot;A String&quot;, # A possible additional shorter value to display.
+                        # For example a java_class_name_value of com.mypackage.MyDoFn
+                        # will be stored with MyDoFn as the short_str_value and
+                        # com.mypackage.MyDoFn as the java_class_name value.
+                        # short_str_value can be displayed and java_class_name_value
+                        # will be displayed as a tooltip.
+                  },
+                ],
+                &quot;id&quot;: &quot;A String&quot;, # SDK generated id of this transform instance.
+                &quot;inputCollectionName&quot;: [ # User names for all collection inputs to this transform.
+                  &quot;A String&quot;,
+                ],
+                &quot;name&quot;: &quot;A String&quot;, # User provided name for this transform instance.
+                &quot;kind&quot;: &quot;A String&quot;, # Type of transform.
+              },
+            ],
+            &quot;executionPipelineStage&quot;: [ # Description of each stage of execution of the pipeline.
+              { # Description of the composing transforms, names/ids, and input/outputs of a
+                  # stage of execution.  Some composing transforms and sources may have been
+                  # generated by the Dataflow service during execution planning.
+                &quot;componentSource&quot;: [ # Collections produced and consumed by component transforms of this stage.
+                  { # Description of an interstitial value between transforms in an execution
+                      # stage.
+                    &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this transform; may be user or system generated.
+                    &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
+                    &quot;originalTransformOrCollection&quot;: &quot;A String&quot;, # User name for the original user transform or collection with which this
+                        # source is most closely associated.
+                  },
+                ],
+                &quot;inputSource&quot;: [ # Input sources for this stage.
+                  { # Description of an input or output of an execution stage.
+                    &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this source; may be user or system generated.
+                    &quot;originalTransformOrCollection&quot;: &quot;A String&quot;, # User name for the original user transform or collection with which this
+                        # source is most closely associated.
+                    &quot;sizeBytes&quot;: &quot;A String&quot;, # Size of the source, if measurable.
+                    &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
+                  },
+                ],
+                &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this stage.
+                &quot;componentTransform&quot;: [ # Transforms that comprise this execution stage.
+                  { # Description of a transform executed as part of an execution stage.
+                    &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
+                    &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this transform; may be user or system generated.
+                    &quot;originalTransform&quot;: &quot;A String&quot;, # User name for the original user transform with which this transform is
+                        # most closely associated.
+                  },
+                ],
+                &quot;id&quot;: &quot;A String&quot;, # Dataflow service generated id for this stage.
+                &quot;outputSource&quot;: [ # Output sources for this stage.
+                  { # Description of an input or output of an execution stage.
+                    &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this source; may be user or system generated.
+                    &quot;originalTransformOrCollection&quot;: &quot;A String&quot;, # User name for the original user transform or collection with which this
+                        # source is most closely associated.
+                    &quot;sizeBytes&quot;: &quot;A String&quot;, # Size of the source, if measurable.
+                    &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
+                  },
+                ],
+                &quot;kind&quot;: &quot;A String&quot;, # Type of tranform this stage is executing.
+              },
+            ],
+          },
+          &quot;labels&quot;: { # User-defined labels for this job.
+              #
+              # The labels map can contain no more than 64 entries.  Entries of the labels
+              # map are UTF8 strings that comply with the following restrictions:
+              #
+              # * Keys must conform to regexp:  \p{Ll}\p{Lo}{0,62}
+              # * Values must conform to regexp:  [\p{Ll}\p{Lo}\p{N}_-]{0,63}
+              # * Both keys and values are additionally constrained to be &lt;= 128 bytes in
+              # size.
+            &quot;a_key&quot;: &quot;A String&quot;,
+          },
+          &quot;projectId&quot;: &quot;A String&quot;, # The ID of the Cloud Platform project that the job belongs to.
+          &quot;environment&quot;: { # Describes the environment in which a Dataflow Job runs. # The environment for the job.
+            &quot;flexResourceSchedulingGoal&quot;: &quot;A String&quot;, # Which Flexible Resource Scheduling mode to run in.
+            &quot;workerRegion&quot;: &quot;A String&quot;, # The Compute Engine region
+                # (https://cloud.google.com/compute/docs/regions-zones/regions-zones) in
+                # which worker processing should occur, e.g. &quot;us-west1&quot;. Mutually exclusive
+                # with worker_zone. If neither worker_region nor worker_zone is specified,
+                # default to the control plane&#x27;s region.
+            &quot;userAgent&quot;: { # A description of the process that generated the request.
+              &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
+            },
+            &quot;serviceAccountEmail&quot;: &quot;A String&quot;, # Identity to run virtual machines as. Defaults to the default account.
+            &quot;version&quot;: { # A structure describing which components and their versions of the service
+                # are required in order to run the job.
+              &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
+            },
+            &quot;serviceKmsKeyName&quot;: &quot;A String&quot;, # If set, contains the Cloud KMS key identifier used to encrypt data
+                # at rest, AKA a Customer Managed Encryption Key (CMEK).
+                #
+                # Format:
+                #   projects/PROJECT_ID/locations/LOCATION/keyRings/KEY_RING/cryptoKeys/KEY
+            &quot;experiments&quot;: [ # The list of experiments to enable.
+              &quot;A String&quot;,
+            ],
+            &quot;workerZone&quot;: &quot;A String&quot;, # The Compute Engine zone
+                # (https://cloud.google.com/compute/docs/regions-zones/regions-zones) in
+                # which worker processing should occur, e.g. &quot;us-west1-a&quot;. Mutually exclusive
+                # with worker_region. If neither worker_region nor worker_zone is specified,
+                # a zone in the control plane&#x27;s region is chosen based on available capacity.
+            &quot;workerPools&quot;: [ # The worker pools. At least one &quot;harness&quot; worker pool must be
+                # specified in order for the job to have workers.
+              { # Describes one particular pool of Cloud Dataflow workers to be
+                  # instantiated by the Cloud Dataflow service in order to perform the
+                  # computations required by a job.  Note that a workflow job may use
+                  # multiple pools, in order to match the various computational
+                  # requirements of the various stages of the job.
+                &quot;onHostMaintenance&quot;: &quot;A String&quot;, # The action to take on host maintenance, as defined by the Google
+                    # Compute Engine API.
+                &quot;sdkHarnessContainerImages&quot;: [ # Set of SDK harness containers needed to execute this pipeline. This will
+                    # only be set in the Fn API path. For non-cross-language pipelines this
+                    # should have only one entry. Cross-language pipelines will have two or more
+                    # entries.
+                  { # Defines a SDK harness container for executing Dataflow pipelines.
+                    &quot;containerImage&quot;: &quot;A String&quot;, # A docker container image that resides in Google Container Registry.
+                    &quot;useSingleCorePerContainer&quot;: True or False, # If true, recommends the Dataflow service to use only one core per SDK
+                        # container instance with this image. If false (or unset) recommends using
+                        # more than one core per SDK container instance with this image for
+                        # efficiency. Note that Dataflow service may choose to override this property
+                        # if needed.
+                  },
+                ],
+                &quot;zone&quot;: &quot;A String&quot;, # Zone to run the worker pools in.  If empty or unspecified, the service
+                    # will attempt to choose a reasonable default.
+                &quot;kind&quot;: &quot;A String&quot;, # The kind of the worker pool; currently only `harness` and `shuffle`
+                    # are supported.
+                &quot;metadata&quot;: { # Metadata to set on the Google Compute Engine VMs.
+                  &quot;a_key&quot;: &quot;A String&quot;,
+                },
+                &quot;diskSourceImage&quot;: &quot;A String&quot;, # Fully qualified source image for disks.
+                &quot;dataDisks&quot;: [ # Data disks that are used by a VM in this workflow.
+                  { # Describes the data disk used by a workflow job.
+                    &quot;sizeGb&quot;: 42, # Size of disk in GB.  If zero or unspecified, the service will
+                        # attempt to choose a reasonable default.
+                    &quot;diskType&quot;: &quot;A String&quot;, # Disk storage type, as defined by Google Compute Engine.  This
+                        # must be a disk type appropriate to the project and zone in which
+                        # the workers will run.  If unknown or unspecified, the service
+                        # will attempt to choose a reasonable default.
+                        #
+                        # For example, the standard persistent disk type is a resource name
+                        # typically ending in &quot;pd-standard&quot;.  If SSD persistent disks are
+                        # available, the resource name typically ends with &quot;pd-ssd&quot;.  The
+                        # actual valid values are defined the Google Compute Engine API,
+                        # not by the Cloud Dataflow API; consult the Google Compute Engine
+                        # documentation for more information about determining the set of
+                        # available disk types for a particular project and zone.
+                        #
+                        # Google Compute Engine Disk types are local to a particular
+                        # project in a particular zone, and so the resource name will
+                        # typically look something like this:
+                        #
+                        # compute.googleapis.com/projects/project-id/zones/zone/diskTypes/pd-standard
+                    &quot;mountPoint&quot;: &quot;A String&quot;, # Directory in a VM where disk is mounted.
+                  },
+                ],
+                &quot;packages&quot;: [ # Packages to be installed on workers.
+                  { # The packages that must be installed in order for a worker to run the
+                      # steps of the Cloud Dataflow job that will be assigned to its worker
+                      # pool.
                       #
-                      # The supported resource type is:
-                      #
-                      # Google Cloud Storage:
-                      #
-                      #   storage.googleapis.com/{bucket}/{object}
-                      #   bucket.storage.googleapis.com/{object}
-                  &quot;reportingEnabled&quot;: True or False, # Whether to send work progress updates to the service.
-                  &quot;baseUrl&quot;: &quot;A String&quot;, # The base URL for accessing Google Cloud APIs.
+                      # This is the mechanism by which the Cloud Dataflow SDK causes code to
+                      # be loaded onto the workers. For example, the Cloud Dataflow Java SDK
+                      # might use this to install jars containing the user&#x27;s code and all of the
+                      # various dependencies (libraries, data files, etc.) required in order
+                      # for that code to run.
+                    &quot;name&quot;: &quot;A String&quot;, # The name of the package.
+                    &quot;location&quot;: &quot;A String&quot;, # The resource to read the package from. The supported resource type is:
+                        #
+                        # Google Cloud Storage:
+                        #
+                        #   storage.googleapis.com/{bucket}
+                        #   bucket.storage.googleapis.com/
+                  },
+                ],
+                &quot;teardownPolicy&quot;: &quot;A String&quot;, # Sets the policy for determining when to turndown worker pool.
+                    # Allowed values are: `TEARDOWN_ALWAYS`, `TEARDOWN_ON_SUCCESS`, and
+                    # `TEARDOWN_NEVER`.
+                    # `TEARDOWN_ALWAYS` means workers are always torn down regardless of whether
+                    # the job succeeds. `TEARDOWN_ON_SUCCESS` means workers are torn down
+                    # if the job succeeds. `TEARDOWN_NEVER` means the workers are never torn
+                    # down.
+                    #
+                    # If the workers are not torn down by the service, they will
+                    # continue to run and use Google Compute Engine VM resources in the
+                    # user&#x27;s project until they are explicitly terminated by the user.
+                    # Because of this, Google recommends using the `TEARDOWN_ALWAYS`
+                    # policy except for small, manually supervised test jobs.
+                    #
+                    # If unknown or unspecified, the service will attempt to choose a reasonable
+                    # default.
+                &quot;network&quot;: &quot;A String&quot;, # Network to which VMs will be assigned.  If empty or unspecified,
+                    # the service will use the network &quot;default&quot;.
+                &quot;ipConfiguration&quot;: &quot;A String&quot;, # Configuration for VM IPs.
+                &quot;diskSizeGb&quot;: 42, # Size of root disk for VMs, in GB.  If zero or unspecified, the service will
+                    # attempt to choose a reasonable default.
+                &quot;autoscalingSettings&quot;: { # Settings for WorkerPool autoscaling. # Settings for autoscaling of this WorkerPool.
+                  &quot;maxNumWorkers&quot;: 42, # The maximum number of workers to cap scaling at.
+                  &quot;algorithm&quot;: &quot;A String&quot;, # The algorithm to use for autoscaling.
+                },
+                &quot;poolArgs&quot;: { # Extra arguments for this worker pool.
+                  &quot;a_key&quot;: &quot;&quot;, # Properties of the object. Contains field @type with type URL.
+                },
+                &quot;subnetwork&quot;: &quot;A String&quot;, # Subnetwork to which VMs will be assigned, if desired.  Expected to be of
+                    # the form &quot;regions/REGION/subnetworks/SUBNETWORK&quot;.
+                &quot;numWorkers&quot;: 42, # Number of Google Compute Engine workers in this pool needed to
+                    # execute the job.  If zero or unspecified, the service will
+                    # attempt to choose a reasonable default.
+                &quot;numThreadsPerWorker&quot;: 42, # The number of threads per worker harness. If empty or unspecified, the
+                    # service will choose a number of threads (according to the number of cores
+                    # on the selected machine type for batch, or 1 by convention for streaming).
+                &quot;workerHarnessContainerImage&quot;: &quot;A String&quot;, # Required. Docker container image that executes the Cloud Dataflow worker
+                    # harness, residing in Google Container Registry.
+                    #
+                    # Deprecated for the Fn API path. Use sdk_harness_container_images instead.
+                &quot;taskrunnerSettings&quot;: { # Taskrunner configuration settings. # Settings passed through to Google Compute Engine workers when
+                    # using the standard Dataflow task runner.  Users should ignore
+                    # this field.
+                  &quot;dataflowApiVersion&quot;: &quot;A String&quot;, # The API version of endpoint, e.g. &quot;v1b3&quot;
+                  &quot;oauthScopes&quot;: [ # The OAuth2 scopes to be requested by the taskrunner in order to
+                      # access the Cloud Dataflow API.
+                    &quot;A String&quot;,
+                  ],
+                  &quot;baseUrl&quot;: &quot;A String&quot;, # The base URL for the taskrunner to use when accessing Google Cloud APIs.
                       #
                       # When workers access Google Cloud APIs, they logically do so via
                       # relative URLs.  If this field is specified, it supplies the base
@@ -393,340 +435,299 @@
                       # Locators&quot;.
                       #
                       # If not specified, the default value is &quot;http://www.googleapis.com/&quot;
-                  &quot;servicePath&quot;: &quot;A String&quot;, # The Cloud Dataflow service path relative to the root URL, for example,
-                      # &quot;dataflow/v1b3/projects&quot;.
-                  &quot;shuffleServicePath&quot;: &quot;A String&quot;, # The Shuffle service path relative to the root URL, for example,
-                      # &quot;shuffle/v1beta1&quot;.
-                  &quot;workerId&quot;: &quot;A String&quot;, # The ID of the worker running this pipeline.
+                  &quot;workflowFileName&quot;: &quot;A String&quot;, # The file to store the workflow in.
+                  &quot;logToSerialconsole&quot;: True or False, # Whether to send taskrunner log info to Google Compute Engine VM serial
+                      # console.
+                  &quot;baseTaskDir&quot;: &quot;A String&quot;, # The location on the worker for task-specific subdirectories.
+                  &quot;taskUser&quot;: &quot;A String&quot;, # The UNIX user ID on the worker VM to use for tasks launched by
+                      # taskrunner; e.g. &quot;root&quot;.
+                  &quot;vmId&quot;: &quot;A String&quot;, # The ID string of the VM.
+                  &quot;alsologtostderr&quot;: True or False, # Whether to also send taskrunner log info to stderr.
+                  &quot;parallelWorkerSettings&quot;: { # Provides data to pass through to the worker harness. # The settings to pass to the parallel worker harness.
+                    &quot;shuffleServicePath&quot;: &quot;A String&quot;, # The Shuffle service path relative to the root URL, for example,
+                        # &quot;shuffle/v1beta1&quot;.
+                    &quot;tempStoragePrefix&quot;: &quot;A String&quot;, # The prefix of the resources the system should use for temporary
+                        # storage.
+                        #
+                        # The supported resource type is:
+                        #
+                        # Google Cloud Storage:
+                        #
+                        #   storage.googleapis.com/{bucket}/{object}
+                        #   bucket.storage.googleapis.com/{object}
+                    &quot;reportingEnabled&quot;: True or False, # Whether to send work progress updates to the service.
+                    &quot;servicePath&quot;: &quot;A String&quot;, # The Cloud Dataflow service path relative to the root URL, for example,
+                        # &quot;dataflow/v1b3/projects&quot;.
+                    &quot;baseUrl&quot;: &quot;A String&quot;, # The base URL for accessing Google Cloud APIs.
+                        #
+                        # When workers access Google Cloud APIs, they logically do so via
+                        # relative URLs.  If this field is specified, it supplies the base
+                        # URL to use for resolving these relative URLs.  The normative
+                        # algorithm used is defined by RFC 1808, &quot;Relative Uniform Resource
+                        # Locators&quot;.
+                        #
+                        # If not specified, the default value is &quot;http://www.googleapis.com/&quot;
+                    &quot;workerId&quot;: &quot;A String&quot;, # The ID of the worker running this pipeline.
+                  },
+                  &quot;harnessCommand&quot;: &quot;A String&quot;, # The command to launch the worker harness.
+                  &quot;logDir&quot;: &quot;A String&quot;, # The directory on the VM to store logs.
+                  &quot;streamingWorkerMainClass&quot;: &quot;A String&quot;, # The streaming worker main class name.
+                  &quot;languageHint&quot;: &quot;A String&quot;, # The suggested backend language.
+                  &quot;taskGroup&quot;: &quot;A String&quot;, # The UNIX group ID on the worker VM to use for tasks launched by
+                      # taskrunner; e.g. &quot;wheel&quot;.
+                  &quot;logUploadLocation&quot;: &quot;A String&quot;, # Indicates where to put logs.  If this is not specified, the logs
+                      # will not be uploaded.
+                      #
+                      # The supported resource type is:
+                      #
+                      # Google Cloud Storage:
+                      #   storage.googleapis.com/{bucket}/{object}
+                      #   bucket.storage.googleapis.com/{object}
+                  &quot;commandlinesFileName&quot;: &quot;A String&quot;, # The file to store preprocessing commands in.
+                  &quot;continueOnException&quot;: True or False, # Whether to continue taskrunner if an exception is hit.
+                  &quot;tempStoragePrefix&quot;: &quot;A String&quot;, # The prefix of the resources the taskrunner should use for
+                      # temporary storage.
+                      #
+                      # The supported resource type is:
+                      #
+                      # Google Cloud Storage:
+                      #   storage.googleapis.com/{bucket}/{object}
+                      #   bucket.storage.googleapis.com/{object}
                 },
-                &quot;taskUser&quot;: &quot;A String&quot;, # The UNIX user ID on the worker VM to use for tasks launched by
-                    # taskrunner; e.g. &quot;root&quot;.
-                &quot;vmId&quot;: &quot;A String&quot;, # The ID string of the VM.
+                &quot;diskType&quot;: &quot;A String&quot;, # Type of root disk for VMs.  If empty or unspecified, the service will
+                    # attempt to choose a reasonable default.
+                &quot;defaultPackageSet&quot;: &quot;A String&quot;, # The default package set to install.  This allows the service to
+                    # select a default set of packages which are useful to worker
+                    # harnesses written in a particular language.
+                &quot;machineType&quot;: &quot;A String&quot;, # Machine type (e.g. &quot;n1-standard-1&quot;).  If empty or unspecified, the
+                    # service will attempt to choose a reasonable default.
               },
-              &quot;autoscalingSettings&quot;: { # Settings for WorkerPool autoscaling. # Settings for autoscaling of this WorkerPool.
-                &quot;algorithm&quot;: &quot;A String&quot;, # The algorithm to use for autoscaling.
-                &quot;maxNumWorkers&quot;: 42, # The maximum number of workers to cap scaling at.
-              },
-              &quot;metadata&quot;: { # Metadata to set on the Google Compute Engine VMs.
-                &quot;a_key&quot;: &quot;A String&quot;,
-              },
-              &quot;defaultPackageSet&quot;: &quot;A String&quot;, # The default package set to install.  This allows the service to
-                  # select a default set of packages which are useful to worker
-                  # harnesses written in a particular language.
-              &quot;network&quot;: &quot;A String&quot;, # Network to which VMs will be assigned.  If empty or unspecified,
-                  # the service will use the network &quot;default&quot;.
+            ],
+            &quot;tempStoragePrefix&quot;: &quot;A String&quot;, # The prefix of the resources the system should use for temporary
+                # storage.  The system will append the suffix &quot;/temp-{JOBNAME} to
+                # this resource prefix, where {JOBNAME} is the value of the
+                # job_name field.  The resulting bucket and object prefix is used
+                # as the prefix of the resources used to store temporary data
+                # needed during the job execution.  NOTE: This will override the
+                # value in taskrunner_settings.
+                # The supported resource type is:
+                #
+                # Google Cloud Storage:
+                #
+                #   storage.googleapis.com/{bucket}/{object}
+                #   bucket.storage.googleapis.com/{object}
+            &quot;internalExperiments&quot;: { # Experimental settings.
+              &quot;a_key&quot;: &quot;&quot;, # Properties of the object. Contains field @type with type URL.
             },
-          ],
-          &quot;dataset&quot;: &quot;A String&quot;, # The dataset for the current project where various workflow
-              # related tables are stored.
-              #
-              # The supported resource type is:
-              #
-              # Google BigQuery:
-              #   bigquery.googleapis.com/{dataset}
-        },
-        &quot;stageStates&quot;: [ # This field may be mutated by the Cloud Dataflow service;
-            # callers cannot mutate it.
-          { # A message describing the state of a particular execution stage.
-            &quot;currentStateTime&quot;: &quot;A String&quot;, # The time at which the stage transitioned to this state.
-            &quot;executionStageState&quot;: &quot;A String&quot;, # Executions stage states allow the same set of values as JobState.
-            &quot;executionStageName&quot;: &quot;A String&quot;, # The name of the execution stage.
-          },
-        ],
-        &quot;jobMetadata&quot;: { # Metadata available primarily for filtering jobs. Will be included in the # This field is populated by the Dataflow service to support filtering jobs
-            # by the metadata values provided here. Populated for ListJobs and all GetJob
-            # views SUMMARY and higher.
-            # ListJob response and Job SUMMARY view.
-          &quot;datastoreDetails&quot;: [ # Identification of a Datastore source used in the Dataflow job.
-            { # Metadata for a Datastore connector used by the job.
-              &quot;namespace&quot;: &quot;A String&quot;, # Namespace used in the connection.
-              &quot;projectId&quot;: &quot;A String&quot;, # ProjectId accessed in the connection.
-            },
-          ],
-          &quot;sdkVersion&quot;: { # The version of the SDK used to run the job. # The SDK version used to run the job.
-            &quot;version&quot;: &quot;A String&quot;, # The version of the SDK used to run the job.
-            &quot;sdkSupportStatus&quot;: &quot;A String&quot;, # The support status for this SDK version.
-            &quot;versionDisplayName&quot;: &quot;A String&quot;, # A readable string describing the version of the SDK.
-          },
-          &quot;bigqueryDetails&quot;: [ # Identification of a BigQuery source used in the Dataflow job.
-            { # Metadata for a BigQuery connector used by the job.
-              &quot;table&quot;: &quot;A String&quot;, # Table accessed in the connection.
-              &quot;dataset&quot;: &quot;A String&quot;, # Dataset accessed in the connection.
-              &quot;query&quot;: &quot;A String&quot;, # Query used to access data in the connection.
-              &quot;projectId&quot;: &quot;A String&quot;, # Project accessed in the connection.
-            },
-          ],
-          &quot;fileDetails&quot;: [ # Identification of a File source used in the Dataflow job.
-            { # Metadata for a File connector used by the job.
-              &quot;filePattern&quot;: &quot;A String&quot;, # File Pattern used to access files by the connector.
-            },
-          ],
-          &quot;pubsubDetails&quot;: [ # Identification of a PubSub source used in the Dataflow job.
-            { # Metadata for a PubSub connector used by the job.
-              &quot;topic&quot;: &quot;A String&quot;, # Topic accessed in the connection.
-              &quot;subscription&quot;: &quot;A String&quot;, # Subscription used in the connection.
-            },
-          ],
-          &quot;bigTableDetails&quot;: [ # Identification of a BigTable source used in the Dataflow job.
-            { # Metadata for a BigTable connector used by the job.
-              &quot;projectId&quot;: &quot;A String&quot;, # ProjectId accessed in the connection.
-              &quot;instanceId&quot;: &quot;A String&quot;, # InstanceId accessed in the connection.
-              &quot;tableId&quot;: &quot;A String&quot;, # TableId accessed in the connection.
-            },
-          ],
-          &quot;spannerDetails&quot;: [ # Identification of a Spanner source used in the Dataflow job.
-            { # Metadata for a Spanner connector used by the job.
-              &quot;instanceId&quot;: &quot;A String&quot;, # InstanceId accessed in the connection.
-              &quot;projectId&quot;: &quot;A String&quot;, # ProjectId accessed in the connection.
-              &quot;databaseId&quot;: &quot;A String&quot;, # DatabaseId accessed in the connection.
-            },
-          ],
-        },
-        &quot;type&quot;: &quot;A String&quot;, # The type of Cloud Dataflow job.
-        &quot;projectId&quot;: &quot;A String&quot;, # The ID of the Cloud Platform project that the job belongs to.
-        &quot;createdFromSnapshotId&quot;: &quot;A String&quot;, # If this is specified, the job&#x27;s initial state is populated from the given
-            # snapshot.
-        &quot;pipelineDescription&quot;: { # A descriptive representation of submitted pipeline as well as the executed # Preliminary field: The format of this data may change at any time.
-            # A description of the user pipeline and stages through which it is executed.
-            # Created by Cloud Dataflow service.  Only retrieved with
-            # JOB_VIEW_DESCRIPTION or JOB_VIEW_ALL.
-            # form.  This data is provided by the Dataflow service for ease of visualizing
-            # the pipeline and interpreting Dataflow provided metrics.
-          &quot;executionPipelineStage&quot;: [ # Description of each stage of execution of the pipeline.
-            { # Description of the composing transforms, names/ids, and input/outputs of a
-                # stage of execution.  Some composing transforms and sources may have been
-                # generated by the Dataflow service during execution planning.
-              &quot;outputSource&quot;: [ # Output sources for this stage.
-                { # Description of an input or output of an execution stage.
-                  &quot;sizeBytes&quot;: &quot;A String&quot;, # Size of the source, if measurable.
-                  &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
-                  &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this source; may be user or system generated.
-                  &quot;originalTransformOrCollection&quot;: &quot;A String&quot;, # User name for the original user transform or collection with which this
-                      # source is most closely associated.
-                },
-              ],
-              &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this stage.
-              &quot;inputSource&quot;: [ # Input sources for this stage.
-                { # Description of an input or output of an execution stage.
-                  &quot;sizeBytes&quot;: &quot;A String&quot;, # Size of the source, if measurable.
-                  &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
-                  &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this source; may be user or system generated.
-                  &quot;originalTransformOrCollection&quot;: &quot;A String&quot;, # User name for the original user transform or collection with which this
-                      # source is most closely associated.
-                },
-              ],
-              &quot;id&quot;: &quot;A String&quot;, # Dataflow service generated id for this stage.
-              &quot;componentTransform&quot;: [ # Transforms that comprise this execution stage.
-                { # Description of a transform executed as part of an execution stage.
-                  &quot;originalTransform&quot;: &quot;A String&quot;, # User name for the original user transform with which this transform is
-                      # most closely associated.
-                  &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
-                  &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this transform; may be user or system generated.
-                },
-              ],
-              &quot;componentSource&quot;: [ # Collections produced and consumed by component transforms of this stage.
-                { # Description of an interstitial value between transforms in an execution
-                    # stage.
-                  &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
-                  &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this transform; may be user or system generated.
-                  &quot;originalTransformOrCollection&quot;: &quot;A String&quot;, # User name for the original user transform or collection with which this
-                      # source is most closely associated.
-                },
-              ],
-              &quot;kind&quot;: &quot;A String&quot;, # Type of tranform this stage is executing.
-            },
-          ],
-          &quot;originalPipelineTransform&quot;: [ # Description of each transform in the pipeline and collections between them.
-            { # Description of the type, names/ids, and input/outputs for a transform.
-              &quot;kind&quot;: &quot;A String&quot;, # Type of transform.
-              &quot;inputCollectionName&quot;: [ # User names for all collection inputs to this transform.
-                &quot;A String&quot;,
-              ],
-              &quot;name&quot;: &quot;A String&quot;, # User provided name for this transform instance.
-              &quot;id&quot;: &quot;A String&quot;, # SDK generated id of this transform instance.
-              &quot;displayData&quot;: [ # Transform-specific display data.
-                { # Data provided with a pipeline or transform to provide descriptive info.
-                  &quot;durationValue&quot;: &quot;A String&quot;, # Contains value if the data is of duration type.
-                  &quot;int64Value&quot;: &quot;A String&quot;, # Contains value if the data is of int64 type.
-                  &quot;namespace&quot;: &quot;A String&quot;, # The namespace for the key. This is usually a class name or programming
-                      # language namespace (i.e. python module) which defines the display data.
-                      # This allows a dax monitoring system to specially handle the data
-                      # and perform custom rendering.
-                  &quot;floatValue&quot;: 3.14, # Contains value if the data is of float type.
-                  &quot;key&quot;: &quot;A String&quot;, # The key identifying the display data.
-                      # This is intended to be used as a label for the display data
-                      # when viewed in a dax monitoring system.
-                  &quot;shortStrValue&quot;: &quot;A String&quot;, # A possible additional shorter value to display.
-                      # For example a java_class_name_value of com.mypackage.MyDoFn
-                      # will be stored with MyDoFn as the short_str_value and
-                      # com.mypackage.MyDoFn as the java_class_name value.
-                      # short_str_value can be displayed and java_class_name_value
-                      # will be displayed as a tooltip.
-                  &quot;url&quot;: &quot;A String&quot;, # An optional full URL.
-                  &quot;label&quot;: &quot;A String&quot;, # An optional label to display in a dax UI for the element.
-                  &quot;timestampValue&quot;: &quot;A String&quot;, # Contains value if the data is of timestamp type.
-                  &quot;boolValue&quot;: True or False, # Contains value if the data is of a boolean type.
-                  &quot;javaClassValue&quot;: &quot;A String&quot;, # Contains value if the data is of java class type.
-                  &quot;strValue&quot;: &quot;A String&quot;, # Contains value if the data is of string type.
-                },
-              ],
-              &quot;outputCollectionName&quot;: [ # User  names for all collection outputs to this transform.
-                &quot;A String&quot;,
-              ],
-            },
-          ],
-          &quot;displayData&quot;: [ # Pipeline level display data.
-            { # Data provided with a pipeline or transform to provide descriptive info.
-              &quot;durationValue&quot;: &quot;A String&quot;, # Contains value if the data is of duration type.
-              &quot;int64Value&quot;: &quot;A String&quot;, # Contains value if the data is of int64 type.
-              &quot;namespace&quot;: &quot;A String&quot;, # The namespace for the key. This is usually a class name or programming
-                  # language namespace (i.e. python module) which defines the display data.
-                  # This allows a dax monitoring system to specially handle the data
-                  # and perform custom rendering.
-              &quot;floatValue&quot;: 3.14, # Contains value if the data is of float type.
-              &quot;key&quot;: &quot;A String&quot;, # The key identifying the display data.
-                  # This is intended to be used as a label for the display data
-                  # when viewed in a dax monitoring system.
-              &quot;shortStrValue&quot;: &quot;A String&quot;, # A possible additional shorter value to display.
-                  # For example a java_class_name_value of com.mypackage.MyDoFn
-                  # will be stored with MyDoFn as the short_str_value and
-                  # com.mypackage.MyDoFn as the java_class_name value.
-                  # short_str_value can be displayed and java_class_name_value
-                  # will be displayed as a tooltip.
-              &quot;url&quot;: &quot;A String&quot;, # An optional full URL.
-              &quot;label&quot;: &quot;A String&quot;, # An optional label to display in a dax UI for the element.
-              &quot;timestampValue&quot;: &quot;A String&quot;, # Contains value if the data is of timestamp type.
-              &quot;boolValue&quot;: True or False, # Contains value if the data is of a boolean type.
-              &quot;javaClassValue&quot;: &quot;A String&quot;, # Contains value if the data is of java class type.
-              &quot;strValue&quot;: &quot;A String&quot;, # Contains value if the data is of string type.
-            },
-          ],
-        },
-        &quot;replaceJobId&quot;: &quot;A String&quot;, # If this job is an update of an existing job, this field is the job ID
-            # of the job it replaced.
-            #
-            # When sending a `CreateJobRequest`, you can update a job by specifying it
-            # here. The job named here is stopped, and its intermediate state is
-            # transferred to this job.
-        &quot;tempFiles&quot;: [ # A set of files the system should be aware of that are used
-            # for temporary storage. These temporary files will be
-            # removed on job completion.
-            # No duplicates are allowed.
-            # No file patterns are supported.
-            #
-            # The supported files are:
-            #
-            # Google Cloud Storage:
-            #
-            #    storage.googleapis.com/{bucket}/{object}
-            #    bucket.storage.googleapis.com/{object}
-          &quot;A String&quot;,
-        ],
-        &quot;name&quot;: &quot;A String&quot;, # The user-specified Cloud Dataflow job name.
-            #
-            # Only one Job with a given name may exist in a project at any
-            # given time. If a caller attempts to create a Job with the same
-            # name as an already-existing Job, the attempt returns the
-            # existing Job.
-            #
-            # The name must match the regular expression
-            # `[a-z]([-a-z0-9]{0,38}[a-z0-9])?`
-        &quot;steps&quot;: [ # Exactly one of step or steps_location should be specified.
-            #
-            # The top-level steps that constitute the entire job.
-          { # Defines a particular step within a Cloud Dataflow job.
-              #
-              # A job consists of multiple steps, each of which performs some
-              # specific operation as part of the overall job.  Data is typically
-              # passed from one step to another as part of the job.
-              #
-              # Here&#x27;s an example of a sequence of steps which together implement a
-              # Map-Reduce job:
-              #
-              #   * Read a collection of data from some source, parsing the
-              #     collection&#x27;s elements.
-              #
-              #   * Validate the elements.
-              #
-              #   * Apply a user-defined function to map each element to some value
-              #     and extract an element-specific key value.
-              #
-              #   * Group elements with the same key into a single element with
-              #     that key, transforming a multiply-keyed collection into a
-              #     uniquely-keyed collection.
-              #
-              #   * Write the elements out to some data sink.
-              #
-              # Note that the Cloud Dataflow service may be used to run many different
-              # types of jobs, not just Map-Reduce.
-            &quot;name&quot;: &quot;A String&quot;, # The name that identifies the step. This must be unique for each
-                # step with respect to all other steps in the Cloud Dataflow job.
-            &quot;kind&quot;: &quot;A String&quot;, # The kind of step in the Cloud Dataflow job.
-            &quot;properties&quot;: { # Named properties associated with the step. Each kind of
-                # predefined step has its own required set of properties.
-                # Must be provided on Create.  Only retrieved with JOB_VIEW_ALL.
+            &quot;sdkPipelineOptions&quot;: { # The Cloud Dataflow SDK pipeline options specified by the user. These
+                # options are passed through the service and are used to recreate the
+                # SDK pipeline options on the worker in a language agnostic and platform
+                # independent way.
               &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
             },
+            &quot;dataset&quot;: &quot;A String&quot;, # The dataset for the current project where various workflow
+                # related tables are stored.
+                #
+                # The supported resource type is:
+                #
+                # Google BigQuery:
+                #   bigquery.googleapis.com/{dataset}
+            &quot;clusterManagerApiService&quot;: &quot;A String&quot;, # The type of cluster manager API to use.  If unknown or
+                # unspecified, the service will attempt to choose a reasonable
+                # default.  This should be in the form of the API service name,
+                # e.g. &quot;compute.googleapis.com&quot;.
           },
-        ],
-        &quot;replacedByJobId&quot;: &quot;A String&quot;, # If another job is an update of this job (and thus, this job is in
-            # `JOB_STATE_UPDATED`), this field contains the ID of that job.
-        &quot;executionInfo&quot;: { # Additional information about how a Cloud Dataflow job will be executed that # Deprecated.
-            # isn&#x27;t contained in the submitted job.
-          &quot;stages&quot;: { # A mapping from each stage to the information about that stage.
-            &quot;a_key&quot;: { # Contains information about how a particular
-                # google.dataflow.v1beta3.Step will be executed.
-              &quot;stepName&quot;: [ # The steps associated with the execution stage.
-                  # Note that stages may have several steps, and that a given step
-                  # might be run by more than one stage.
-                &quot;A String&quot;,
-              ],
+          &quot;stepsLocation&quot;: &quot;A String&quot;, # The GCS location where the steps are stored.
+          &quot;steps&quot;: [ # Exactly one of step or steps_location should be specified.
+              #
+              # The top-level steps that constitute the entire job.
+            { # Defines a particular step within a Cloud Dataflow job.
+                #
+                # A job consists of multiple steps, each of which performs some
+                # specific operation as part of the overall job.  Data is typically
+                # passed from one step to another as part of the job.
+                #
+                # Here&#x27;s an example of a sequence of steps which together implement a
+                # Map-Reduce job:
+                #
+                #   * Read a collection of data from some source, parsing the
+                #     collection&#x27;s elements.
+                #
+                #   * Validate the elements.
+                #
+                #   * Apply a user-defined function to map each element to some value
+                #     and extract an element-specific key value.
+                #
+                #   * Group elements with the same key into a single element with
+                #     that key, transforming a multiply-keyed collection into a
+                #     uniquely-keyed collection.
+                #
+                #   * Write the elements out to some data sink.
+                #
+                # Note that the Cloud Dataflow service may be used to run many different
+                # types of jobs, not just Map-Reduce.
+              &quot;kind&quot;: &quot;A String&quot;, # The kind of step in the Cloud Dataflow job.
+              &quot;properties&quot;: { # Named properties associated with the step. Each kind of
+                  # predefined step has its own required set of properties.
+                  # Must be provided on Create.  Only retrieved with JOB_VIEW_ALL.
+                &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
+              },
+              &quot;name&quot;: &quot;A String&quot;, # The name that identifies the step. This must be unique for each
+                  # step with respect to all other steps in the Cloud Dataflow job.
+            },
+          ],
+          &quot;stageStates&quot;: [ # This field may be mutated by the Cloud Dataflow service;
+              # callers cannot mutate it.
+            { # A message describing the state of a particular execution stage.
+              &quot;executionStageState&quot;: &quot;A String&quot;, # Executions stage states allow the same set of values as JobState.
+              &quot;executionStageName&quot;: &quot;A String&quot;, # The name of the execution stage.
+              &quot;currentStateTime&quot;: &quot;A String&quot;, # The time at which the stage transitioned to this state.
+            },
+          ],
+          &quot;replacedByJobId&quot;: &quot;A String&quot;, # If another job is an update of this job (and thus, this job is in
+              # `JOB_STATE_UPDATED`), this field contains the ID of that job.
+          &quot;jobMetadata&quot;: { # Metadata available primarily for filtering jobs. Will be included in the # This field is populated by the Dataflow service to support filtering jobs
+              # by the metadata values provided here. Populated for ListJobs and all GetJob
+              # views SUMMARY and higher.
+              # ListJob response and Job SUMMARY view.
+            &quot;sdkVersion&quot;: { # The version of the SDK used to run the job. # The SDK version used to run the job.
+              &quot;sdkSupportStatus&quot;: &quot;A String&quot;, # The support status for this SDK version.
+              &quot;versionDisplayName&quot;: &quot;A String&quot;, # A readable string describing the version of the SDK.
+              &quot;version&quot;: &quot;A String&quot;, # The version of the SDK used to run the job.
+            },
+            &quot;bigTableDetails&quot;: [ # Identification of a BigTable source used in the Dataflow job.
+              { # Metadata for a BigTable connector used by the job.
+                &quot;instanceId&quot;: &quot;A String&quot;, # InstanceId accessed in the connection.
+                &quot;tableId&quot;: &quot;A String&quot;, # TableId accessed in the connection.
+                &quot;projectId&quot;: &quot;A String&quot;, # ProjectId accessed in the connection.
+              },
+            ],
+            &quot;pubsubDetails&quot;: [ # Identification of a PubSub source used in the Dataflow job.
+              { # Metadata for a PubSub connector used by the job.
+                &quot;subscription&quot;: &quot;A String&quot;, # Subscription used in the connection.
+                &quot;topic&quot;: &quot;A String&quot;, # Topic accessed in the connection.
+              },
+            ],
+            &quot;bigqueryDetails&quot;: [ # Identification of a BigQuery source used in the Dataflow job.
+              { # Metadata for a BigQuery connector used by the job.
+                &quot;dataset&quot;: &quot;A String&quot;, # Dataset accessed in the connection.
+                &quot;projectId&quot;: &quot;A String&quot;, # Project accessed in the connection.
+                &quot;query&quot;: &quot;A String&quot;, # Query used to access data in the connection.
+                &quot;table&quot;: &quot;A String&quot;, # Table accessed in the connection.
+              },
+            ],
+            &quot;fileDetails&quot;: [ # Identification of a File source used in the Dataflow job.
+              { # Metadata for a File connector used by the job.
+                &quot;filePattern&quot;: &quot;A String&quot;, # File Pattern used to access files by the connector.
+              },
+            ],
+            &quot;datastoreDetails&quot;: [ # Identification of a Datastore source used in the Dataflow job.
+              { # Metadata for a Datastore connector used by the job.
+                &quot;namespace&quot;: &quot;A String&quot;, # Namespace used in the connection.
+                &quot;projectId&quot;: &quot;A String&quot;, # ProjectId accessed in the connection.
+              },
+            ],
+            &quot;spannerDetails&quot;: [ # Identification of a Spanner source used in the Dataflow job.
+              { # Metadata for a Spanner connector used by the job.
+                &quot;instanceId&quot;: &quot;A String&quot;, # InstanceId accessed in the connection.
+                &quot;databaseId&quot;: &quot;A String&quot;, # DatabaseId accessed in the connection.
+                &quot;projectId&quot;: &quot;A String&quot;, # ProjectId accessed in the connection.
+              },
+            ],
+          },
+          &quot;location&quot;: &quot;A String&quot;, # The [regional endpoint]
+              # (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that
+              # contains this job.
+          &quot;transformNameMapping&quot;: { # The map of transform name prefixes of the job to be replaced to the
+              # corresponding name prefixes of the new job.
+            &quot;a_key&quot;: &quot;A String&quot;,
+          },
+          &quot;startTime&quot;: &quot;A String&quot;, # The timestamp when the job was started (transitioned to JOB_STATE_PENDING).
+              # Flexible resource scheduling jobs are started with some delay after job
+              # creation, so start_time is unset before start and is updated when the
+              # job is started by the Cloud Dataflow service. For other jobs, start_time
+              # always equals to create_time and is immutable and set by the Cloud Dataflow
+              # service.
+          &quot;clientRequestId&quot;: &quot;A String&quot;, # The client&#x27;s unique identifier of the job, re-used across retried attempts.
+              # If this field is set, the service will ensure its uniqueness.
+              # The request to create a job will fail if the service has knowledge of a
+              # previously submitted job with the same client&#x27;s ID and job name.
+              # The caller may use this field to ensure idempotence of job
+              # creation across retried attempts to create a job.
+              # By default, the field is empty and, in that case, the service ignores it.
+          &quot;executionInfo&quot;: { # Additional information about how a Cloud Dataflow job will be executed that # Deprecated.
+              # isn&#x27;t contained in the submitted job.
+            &quot;stages&quot;: { # A mapping from each stage to the information about that stage.
+              &quot;a_key&quot;: { # Contains information about how a particular
+                  # google.dataflow.v1beta3.Step will be executed.
+                &quot;stepName&quot;: [ # The steps associated with the execution stage.
+                    # Note that stages may have several steps, and that a given step
+                    # might be run by more than one stage.
+                  &quot;A String&quot;,
+                ],
+              },
             },
           },
+          &quot;type&quot;: &quot;A String&quot;, # The type of Cloud Dataflow job.
+          &quot;createTime&quot;: &quot;A String&quot;, # The timestamp when the job was initially created. Immutable and set by the
+              # Cloud Dataflow service.
+          &quot;tempFiles&quot;: [ # A set of files the system should be aware of that are used
+              # for temporary storage. These temporary files will be
+              # removed on job completion.
+              # No duplicates are allowed.
+              # No file patterns are supported.
+              #
+              # The supported files are:
+              #
+              # Google Cloud Storage:
+              #
+              #    storage.googleapis.com/{bucket}/{object}
+              #    bucket.storage.googleapis.com/{object}
+            &quot;A String&quot;,
+          ],
+          &quot;id&quot;: &quot;A String&quot;, # The unique ID of this job.
+              #
+              # This field is set by the Cloud Dataflow service when the Job is
+              # created, and is immutable for the life of the job.
+          &quot;requestedState&quot;: &quot;A String&quot;, # The job&#x27;s requested state.
+              #
+              # `UpdateJob` may be used to switch between the `JOB_STATE_STOPPED` and
+              # `JOB_STATE_RUNNING` states, by setting requested_state.  `UpdateJob` may
+              # also be used to directly set a job&#x27;s requested state to
+              # `JOB_STATE_CANCELLED` or `JOB_STATE_DONE`, irrevocably terminating the
+              # job if it has not already reached a terminal state.
+          &quot;replaceJobId&quot;: &quot;A String&quot;, # If this job is an update of an existing job, this field is the job ID
+              # of the job it replaced.
+              #
+              # When sending a `CreateJobRequest`, you can update a job by specifying it
+              # here. The job named here is stopped, and its intermediate state is
+              # transferred to this job.
+          &quot;createdFromSnapshotId&quot;: &quot;A String&quot;, # If this is specified, the job&#x27;s initial state is populated from the given
+              # snapshot.
+          &quot;currentState&quot;: &quot;A String&quot;, # The current state of the job.
+              #
+              # Jobs are created in the `JOB_STATE_STOPPED` state unless otherwise
+              # specified.
+              #
+              # A job in the `JOB_STATE_RUNNING` state may asynchronously enter a
+              # terminal state. After a job has reached a terminal state, no
+              # further state updates may be made.
+              #
+              # This field may be mutated by the Cloud Dataflow service;
+              # callers cannot mutate it.
+          &quot;name&quot;: &quot;A String&quot;, # The user-specified Cloud Dataflow job name.
+              #
+              # Only one Job with a given name may exist in a project at any
+              # given time. If a caller attempts to create a Job with the same
+              # name as an already-existing Job, the attempt returns the
+              # existing Job.
+              #
+              # The name must match the regular expression
+              # `[a-z]([-a-z0-9]{0,38}[a-z0-9])?`
+          &quot;currentStateTime&quot;: &quot;A String&quot;, # The timestamp associated with the current state.
         },
-        &quot;currentState&quot;: &quot;A String&quot;, # The current state of the job.
-            #
-            # Jobs are created in the `JOB_STATE_STOPPED` state unless otherwise
-            # specified.
-            #
-            # A job in the `JOB_STATE_RUNNING` state may asynchronously enter a
-            # terminal state. After a job has reached a terminal state, no
-            # further state updates may be made.
-            #
-            # This field may be mutated by the Cloud Dataflow service;
-            # callers cannot mutate it.
-        &quot;location&quot;: &quot;A String&quot;, # The [regional endpoint]
-            # (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that
-            # contains this job.
-        &quot;startTime&quot;: &quot;A String&quot;, # The timestamp when the job was started (transitioned to JOB_STATE_PENDING).
-            # Flexible resource scheduling jobs are started with some delay after job
-            # creation, so start_time is unset before start and is updated when the
-            # job is started by the Cloud Dataflow service. For other jobs, start_time
-            # always equals to create_time and is immutable and set by the Cloud Dataflow
-            # service.
-        &quot;stepsLocation&quot;: &quot;A String&quot;, # The GCS location where the steps are stored.
-        &quot;labels&quot;: { # User-defined labels for this job.
-            #
-            # The labels map can contain no more than 64 entries.  Entries of the labels
-            # map are UTF8 strings that comply with the following restrictions:
-            #
-            # * Keys must conform to regexp:  \p{Ll}\p{Lo}{0,62}
-            # * Values must conform to regexp:  [\p{Ll}\p{Lo}\p{N}_-]{0,63}
-            # * Both keys and values are additionally constrained to be &lt;= 128 bytes in
-            # size.
-          &quot;a_key&quot;: &quot;A String&quot;,
-        },
-        &quot;createTime&quot;: &quot;A String&quot;, # The timestamp when the job was initially created. Immutable and set by the
-            # Cloud Dataflow service.
-        &quot;requestedState&quot;: &quot;A String&quot;, # The job&#x27;s requested state.
-            #
-            # `UpdateJob` may be used to switch between the `JOB_STATE_STOPPED` and
-            # `JOB_STATE_RUNNING` states, by setting requested_state.  `UpdateJob` may
-            # also be used to directly set a job&#x27;s requested state to
-            # `JOB_STATE_CANCELLED` or `JOB_STATE_DONE`, irrevocably terminating the
-            # job if it has not already reached a terminal state.
-      },
     ],
+    &quot;nextPageToken&quot;: &quot;A String&quot;, # Set if there may be more results than fit in this response.
     &quot;failedLocation&quot;: [ # Zero or more messages describing the [regional endpoints]
         # (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that
         # failed to respond.
@@ -738,7 +739,6 @@
             # failed to respond.
       },
     ],
-    &quot;nextPageToken&quot;: &quot;A String&quot;, # Set if there may be more results than fit in this response.
   }</pre>
 </div>
 
@@ -772,243 +772,285 @@
     The object takes the form of:
 
 { # Defines a job to be run by the Cloud Dataflow service.
-  &quot;clientRequestId&quot;: &quot;A String&quot;, # The client&#x27;s unique identifier of the job, re-used across retried attempts.
-      # If this field is set, the service will ensure its uniqueness.
-      # The request to create a job will fail if the service has knowledge of a
-      # previously submitted job with the same client&#x27;s ID and job name.
-      # The caller may use this field to ensure idempotence of job
-      # creation across retried attempts to create a job.
-      # By default, the field is empty and, in that case, the service ignores it.
-  &quot;id&quot;: &quot;A String&quot;, # The unique ID of this job.
-      # 
-      # This field is set by the Cloud Dataflow service when the Job is
-      # created, and is immutable for the life of the job.
-  &quot;currentStateTime&quot;: &quot;A String&quot;, # The timestamp associated with the current state.
-  &quot;transformNameMapping&quot;: { # The map of transform name prefixes of the job to be replaced to the
-      # corresponding name prefixes of the new job.
-    &quot;a_key&quot;: &quot;A String&quot;,
-  },
-  &quot;environment&quot;: { # Describes the environment in which a Dataflow Job runs. # The environment for the job.
-    &quot;internalExperiments&quot;: { # Experimental settings.
-      &quot;a_key&quot;: &quot;&quot;, # Properties of the object. Contains field @type with type URL.
-    },
-    &quot;workerRegion&quot;: &quot;A String&quot;, # The Compute Engine region
-        # (https://cloud.google.com/compute/docs/regions-zones/regions-zones) in
-        # which worker processing should occur, e.g. &quot;us-west1&quot;. Mutually exclusive
-        # with worker_zone. If neither worker_region nor worker_zone is specified,
-        # default to the control plane&#x27;s region.
-    &quot;serviceKmsKeyName&quot;: &quot;A String&quot;, # If set, contains the Cloud KMS key identifier used to encrypt data
-        # at rest, AKA a Customer Managed Encryption Key (CMEK).
-        #
-        # Format:
-        #   projects/PROJECT_ID/locations/LOCATION/keyRings/KEY_RING/cryptoKeys/KEY
-    &quot;userAgent&quot;: { # A description of the process that generated the request.
-      &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
-    },
-    &quot;workerZone&quot;: &quot;A String&quot;, # The Compute Engine zone
-        # (https://cloud.google.com/compute/docs/regions-zones/regions-zones) in
-        # which worker processing should occur, e.g. &quot;us-west1-a&quot;. Mutually exclusive
-        # with worker_region. If neither worker_region nor worker_zone is specified,
-        # a zone in the control plane&#x27;s region is chosen based on available capacity.
-    &quot;clusterManagerApiService&quot;: &quot;A String&quot;, # The type of cluster manager API to use.  If unknown or
-        # unspecified, the service will attempt to choose a reasonable
-        # default.  This should be in the form of the API service name,
-        # e.g. &quot;compute.googleapis.com&quot;.
-    &quot;tempStoragePrefix&quot;: &quot;A String&quot;, # The prefix of the resources the system should use for temporary
-        # storage.  The system will append the suffix &quot;/temp-{JOBNAME} to
-        # this resource prefix, where {JOBNAME} is the value of the
-        # job_name field.  The resulting bucket and object prefix is used
-        # as the prefix of the resources used to store temporary data
-        # needed during the job execution.  NOTE: This will override the
-        # value in taskrunner_settings.
-        # The supported resource type is:
-        #
-        # Google Cloud Storage:
-        #
-        #   storage.googleapis.com/{bucket}/{object}
-        #   bucket.storage.googleapis.com/{object}
-    &quot;experiments&quot;: [ # The list of experiments to enable.
-      &quot;A String&quot;,
-    ],
-    &quot;version&quot;: { # A structure describing which components and their versions of the service
-        # are required in order to run the job.
-      &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
-    },
-    &quot;serviceAccountEmail&quot;: &quot;A String&quot;, # Identity to run virtual machines as. Defaults to the default account.
-    &quot;sdkPipelineOptions&quot;: { # The Cloud Dataflow SDK pipeline options specified by the user. These
-        # options are passed through the service and are used to recreate the
-        # SDK pipeline options on the worker in a language agnostic and platform
-        # independent way.
-      &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
-    },
-    &quot;flexResourceSchedulingGoal&quot;: &quot;A String&quot;, # Which Flexible Resource Scheduling mode to run in.
-    &quot;workerPools&quot;: [ # The worker pools. At least one &quot;harness&quot; worker pool must be
-        # specified in order for the job to have workers.
-      { # Describes one particular pool of Cloud Dataflow workers to be
-          # instantiated by the Cloud Dataflow service in order to perform the
-          # computations required by a job.  Note that a workflow job may use
-          # multiple pools, in order to match the various computational
-          # requirements of the various stages of the job.
-        &quot;numThreadsPerWorker&quot;: 42, # The number of threads per worker harness. If empty or unspecified, the
-            # service will choose a number of threads (according to the number of cores
-            # on the selected machine type for batch, or 1 by convention for streaming).
-        &quot;numWorkers&quot;: 42, # Number of Google Compute Engine workers in this pool needed to
-            # execute the job.  If zero or unspecified, the service will
-            # attempt to choose a reasonable default.
-        &quot;zone&quot;: &quot;A String&quot;, # Zone to run the worker pools in.  If empty or unspecified, the service
-            # will attempt to choose a reasonable default.
-        &quot;diskSourceImage&quot;: &quot;A String&quot;, # Fully qualified source image for disks.
-        &quot;packages&quot;: [ # Packages to be installed on workers.
-          { # The packages that must be installed in order for a worker to run the
-              # steps of the Cloud Dataflow job that will be assigned to its worker
-              # pool.
-              #
-              # This is the mechanism by which the Cloud Dataflow SDK causes code to
-              # be loaded onto the workers. For example, the Cloud Dataflow Java SDK
-              # might use this to install jars containing the user&#x27;s code and all of the
-              # various dependencies (libraries, data files, etc.) required in order
-              # for that code to run.
-            &quot;name&quot;: &quot;A String&quot;, # The name of the package.
-            &quot;location&quot;: &quot;A String&quot;, # The resource to read the package from. The supported resource type is:
-                #
-                # Google Cloud Storage:
-                #
-                #   storage.googleapis.com/{bucket}
-                #   bucket.storage.googleapis.com/
-          },
-        ],
-        &quot;teardownPolicy&quot;: &quot;A String&quot;, # Sets the policy for determining when to turndown worker pool.
-            # Allowed values are: `TEARDOWN_ALWAYS`, `TEARDOWN_ON_SUCCESS`, and
-            # `TEARDOWN_NEVER`.
-            # `TEARDOWN_ALWAYS` means workers are always torn down regardless of whether
-            # the job succeeds. `TEARDOWN_ON_SUCCESS` means workers are torn down
-            # if the job succeeds. `TEARDOWN_NEVER` means the workers are never torn
-            # down.
-            #
-            # If the workers are not torn down by the service, they will
-            # continue to run and use Google Compute Engine VM resources in the
-            # user&#x27;s project until they are explicitly terminated by the user.
-            # Because of this, Google recommends using the `TEARDOWN_ALWAYS`
-            # policy except for small, manually supervised test jobs.
-            #
-            # If unknown or unspecified, the service will attempt to choose a reasonable
-            # default.
-        &quot;onHostMaintenance&quot;: &quot;A String&quot;, # The action to take on host maintenance, as defined by the Google
-            # Compute Engine API.
-        &quot;poolArgs&quot;: { # Extra arguments for this worker pool.
-          &quot;a_key&quot;: &quot;&quot;, # Properties of the object. Contains field @type with type URL.
+    &quot;pipelineDescription&quot;: { # A descriptive representation of submitted pipeline as well as the executed # Preliminary field: The format of this data may change at any time.
+        # A description of the user pipeline and stages through which it is executed.
+        # Created by Cloud Dataflow service.  Only retrieved with
+        # JOB_VIEW_DESCRIPTION or JOB_VIEW_ALL.
+        # form.  This data is provided by the Dataflow service for ease of visualizing
+        # the pipeline and interpreting Dataflow provided metrics.
+      &quot;displayData&quot;: [ # Pipeline level display data.
+        { # Data provided with a pipeline or transform to provide descriptive info.
+          &quot;url&quot;: &quot;A String&quot;, # An optional full URL.
+          &quot;javaClassValue&quot;: &quot;A String&quot;, # Contains value if the data is of java class type.
+          &quot;timestampValue&quot;: &quot;A String&quot;, # Contains value if the data is of timestamp type.
+          &quot;durationValue&quot;: &quot;A String&quot;, # Contains value if the data is of duration type.
+          &quot;label&quot;: &quot;A String&quot;, # An optional label to display in a dax UI for the element.
+          &quot;key&quot;: &quot;A String&quot;, # The key identifying the display data.
+              # This is intended to be used as a label for the display data
+              # when viewed in a dax monitoring system.
+          &quot;namespace&quot;: &quot;A String&quot;, # The namespace for the key. This is usually a class name or programming
+              # language namespace (i.e. python module) which defines the display data.
+              # This allows a dax monitoring system to specially handle the data
+              # and perform custom rendering.
+          &quot;floatValue&quot;: 3.14, # Contains value if the data is of float type.
+          &quot;strValue&quot;: &quot;A String&quot;, # Contains value if the data is of string type.
+          &quot;int64Value&quot;: &quot;A String&quot;, # Contains value if the data is of int64 type.
+          &quot;boolValue&quot;: True or False, # Contains value if the data is of a boolean type.
+          &quot;shortStrValue&quot;: &quot;A String&quot;, # A possible additional shorter value to display.
+              # For example a java_class_name_value of com.mypackage.MyDoFn
+              # will be stored with MyDoFn as the short_str_value and
+              # com.mypackage.MyDoFn as the java_class_name value.
+              # short_str_value can be displayed and java_class_name_value
+              # will be displayed as a tooltip.
         },
-        &quot;diskSizeGb&quot;: 42, # Size of root disk for VMs, in GB.  If zero or unspecified, the service will
-            # attempt to choose a reasonable default.
-        &quot;workerHarnessContainerImage&quot;: &quot;A String&quot;, # Required. Docker container image that executes the Cloud Dataflow worker
-            # harness, residing in Google Container Registry.
-            #
-            # Deprecated for the Fn API path. Use sdk_harness_container_images instead.
-        &quot;diskType&quot;: &quot;A String&quot;, # Type of root disk for VMs.  If empty or unspecified, the service will
-            # attempt to choose a reasonable default.
-        &quot;machineType&quot;: &quot;A String&quot;, # Machine type (e.g. &quot;n1-standard-1&quot;).  If empty or unspecified, the
-            # service will attempt to choose a reasonable default.
-        &quot;kind&quot;: &quot;A String&quot;, # The kind of the worker pool; currently only `harness` and `shuffle`
-            # are supported.
-        &quot;sdkHarnessContainerImages&quot;: [ # Set of SDK harness containers needed to execute this pipeline. This will
-            # only be set in the Fn API path. For non-cross-language pipelines this
-            # should have only one entry. Cross-language pipelines will have two or more
-            # entries.
-          { # Defines a SDK harness container for executing Dataflow pipelines.
-            &quot;containerImage&quot;: &quot;A String&quot;, # A docker container image that resides in Google Container Registry.
-            &quot;useSingleCorePerContainer&quot;: True or False, # If true, recommends the Dataflow service to use only one core per SDK
-                # container instance with this image. If false (or unset) recommends using
-                # more than one core per SDK container instance with this image for
-                # efficiency. Note that Dataflow service may choose to override this property
-                # if needed.
-          },
-        ],
-        &quot;dataDisks&quot;: [ # Data disks that are used by a VM in this workflow.
-          { # Describes the data disk used by a workflow job.
-            &quot;diskType&quot;: &quot;A String&quot;, # Disk storage type, as defined by Google Compute Engine.  This
-                # must be a disk type appropriate to the project and zone in which
-                # the workers will run.  If unknown or unspecified, the service
-                # will attempt to choose a reasonable default.
-                #
-                # For example, the standard persistent disk type is a resource name
-                # typically ending in &quot;pd-standard&quot;.  If SSD persistent disks are
-                # available, the resource name typically ends with &quot;pd-ssd&quot;.  The
-                # actual valid values are defined the Google Compute Engine API,
-                # not by the Cloud Dataflow API; consult the Google Compute Engine
-                # documentation for more information about determining the set of
-                # available disk types for a particular project and zone.
-                #
-                # Google Compute Engine Disk types are local to a particular
-                # project in a particular zone, and so the resource name will
-                # typically look something like this:
-                #
-                # compute.googleapis.com/projects/project-id/zones/zone/diskTypes/pd-standard
-            &quot;sizeGb&quot;: 42, # Size of disk in GB.  If zero or unspecified, the service will
-                # attempt to choose a reasonable default.
-            &quot;mountPoint&quot;: &quot;A String&quot;, # Directory in a VM where disk is mounted.
-          },
-        ],
-        &quot;subnetwork&quot;: &quot;A String&quot;, # Subnetwork to which VMs will be assigned, if desired.  Expected to be of
-            # the form &quot;regions/REGION/subnetworks/SUBNETWORK&quot;.
-        &quot;ipConfiguration&quot;: &quot;A String&quot;, # Configuration for VM IPs.
-        &quot;taskrunnerSettings&quot;: { # Taskrunner configuration settings. # Settings passed through to Google Compute Engine workers when
-            # using the standard Dataflow task runner.  Users should ignore
-            # this field.
-          &quot;alsologtostderr&quot;: True or False, # Whether to also send taskrunner log info to stderr.
-          &quot;taskGroup&quot;: &quot;A String&quot;, # The UNIX group ID on the worker VM to use for tasks launched by
-              # taskrunner; e.g. &quot;wheel&quot;.
-          &quot;harnessCommand&quot;: &quot;A String&quot;, # The command to launch the worker harness.
-          &quot;logDir&quot;: &quot;A String&quot;, # The directory on the VM to store logs.
-          &quot;oauthScopes&quot;: [ # The OAuth2 scopes to be requested by the taskrunner in order to
-              # access the Cloud Dataflow API.
+      ],
+      &quot;originalPipelineTransform&quot;: [ # Description of each transform in the pipeline and collections between them.
+        { # Description of the type, names/ids, and input/outputs for a transform.
+          &quot;outputCollectionName&quot;: [ # User  names for all collection outputs to this transform.
             &quot;A String&quot;,
           ],
-          &quot;dataflowApiVersion&quot;: &quot;A String&quot;, # The API version of endpoint, e.g. &quot;v1b3&quot;
-          &quot;logUploadLocation&quot;: &quot;A String&quot;, # Indicates where to put logs.  If this is not specified, the logs
-              # will not be uploaded.
-              #
-              # The supported resource type is:
-              #
-              # Google Cloud Storage:
-              #   storage.googleapis.com/{bucket}/{object}
-              #   bucket.storage.googleapis.com/{object}
-          &quot;streamingWorkerMainClass&quot;: &quot;A String&quot;, # The streaming worker main class name.
-          &quot;workflowFileName&quot;: &quot;A String&quot;, # The file to store the workflow in.
-          &quot;languageHint&quot;: &quot;A String&quot;, # The suggested backend language.
-          &quot;commandlinesFileName&quot;: &quot;A String&quot;, # The file to store preprocessing commands in.
-          &quot;baseTaskDir&quot;: &quot;A String&quot;, # The location on the worker for task-specific subdirectories.
-          &quot;tempStoragePrefix&quot;: &quot;A String&quot;, # The prefix of the resources the taskrunner should use for
-              # temporary storage.
-              #
-              # The supported resource type is:
-              #
-              # Google Cloud Storage:
-              #   storage.googleapis.com/{bucket}/{object}
-              #   bucket.storage.googleapis.com/{object}
-          &quot;baseUrl&quot;: &quot;A String&quot;, # The base URL for the taskrunner to use when accessing Google Cloud APIs.
-              #
-              # When workers access Google Cloud APIs, they logically do so via
-              # relative URLs.  If this field is specified, it supplies the base
-              # URL to use for resolving these relative URLs.  The normative
-              # algorithm used is defined by RFC 1808, &quot;Relative Uniform Resource
-              # Locators&quot;.
-              #
-              # If not specified, the default value is &quot;http://www.googleapis.com/&quot;
-          &quot;logToSerialconsole&quot;: True or False, # Whether to send taskrunner log info to Google Compute Engine VM serial
-              # console.
-          &quot;continueOnException&quot;: True or False, # Whether to continue taskrunner if an exception is hit.
-          &quot;parallelWorkerSettings&quot;: { # Provides data to pass through to the worker harness. # The settings to pass to the parallel worker harness.
-            &quot;tempStoragePrefix&quot;: &quot;A String&quot;, # The prefix of the resources the system should use for temporary
-                # storage.
+          &quot;displayData&quot;: [ # Transform-specific display data.
+            { # Data provided with a pipeline or transform to provide descriptive info.
+              &quot;url&quot;: &quot;A String&quot;, # An optional full URL.
+              &quot;javaClassValue&quot;: &quot;A String&quot;, # Contains value if the data is of java class type.
+              &quot;timestampValue&quot;: &quot;A String&quot;, # Contains value if the data is of timestamp type.
+              &quot;durationValue&quot;: &quot;A String&quot;, # Contains value if the data is of duration type.
+              &quot;label&quot;: &quot;A String&quot;, # An optional label to display in a dax UI for the element.
+              &quot;key&quot;: &quot;A String&quot;, # The key identifying the display data.
+                  # This is intended to be used as a label for the display data
+                  # when viewed in a dax monitoring system.
+              &quot;namespace&quot;: &quot;A String&quot;, # The namespace for the key. This is usually a class name or programming
+                  # language namespace (i.e. python module) which defines the display data.
+                  # This allows a dax monitoring system to specially handle the data
+                  # and perform custom rendering.
+              &quot;floatValue&quot;: 3.14, # Contains value if the data is of float type.
+              &quot;strValue&quot;: &quot;A String&quot;, # Contains value if the data is of string type.
+              &quot;int64Value&quot;: &quot;A String&quot;, # Contains value if the data is of int64 type.
+              &quot;boolValue&quot;: True or False, # Contains value if the data is of a boolean type.
+              &quot;shortStrValue&quot;: &quot;A String&quot;, # A possible additional shorter value to display.
+                  # For example a java_class_name_value of com.mypackage.MyDoFn
+                  # will be stored with MyDoFn as the short_str_value and
+                  # com.mypackage.MyDoFn as the java_class_name value.
+                  # short_str_value can be displayed and java_class_name_value
+                  # will be displayed as a tooltip.
+            },
+          ],
+          &quot;id&quot;: &quot;A String&quot;, # SDK generated id of this transform instance.
+          &quot;inputCollectionName&quot;: [ # User names for all collection inputs to this transform.
+            &quot;A String&quot;,
+          ],
+          &quot;name&quot;: &quot;A String&quot;, # User provided name for this transform instance.
+          &quot;kind&quot;: &quot;A String&quot;, # Type of transform.
+        },
+      ],
+      &quot;executionPipelineStage&quot;: [ # Description of each stage of execution of the pipeline.
+        { # Description of the composing transforms, names/ids, and input/outputs of a
+            # stage of execution.  Some composing transforms and sources may have been
+            # generated by the Dataflow service during execution planning.
+          &quot;componentSource&quot;: [ # Collections produced and consumed by component transforms of this stage.
+            { # Description of an interstitial value between transforms in an execution
+                # stage.
+              &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this transform; may be user or system generated.
+              &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
+              &quot;originalTransformOrCollection&quot;: &quot;A String&quot;, # User name for the original user transform or collection with which this
+                  # source is most closely associated.
+            },
+          ],
+          &quot;inputSource&quot;: [ # Input sources for this stage.
+            { # Description of an input or output of an execution stage.
+              &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this source; may be user or system generated.
+              &quot;originalTransformOrCollection&quot;: &quot;A String&quot;, # User name for the original user transform or collection with which this
+                  # source is most closely associated.
+              &quot;sizeBytes&quot;: &quot;A String&quot;, # Size of the source, if measurable.
+              &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
+            },
+          ],
+          &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this stage.
+          &quot;componentTransform&quot;: [ # Transforms that comprise this execution stage.
+            { # Description of a transform executed as part of an execution stage.
+              &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
+              &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this transform; may be user or system generated.
+              &quot;originalTransform&quot;: &quot;A String&quot;, # User name for the original user transform with which this transform is
+                  # most closely associated.
+            },
+          ],
+          &quot;id&quot;: &quot;A String&quot;, # Dataflow service generated id for this stage.
+          &quot;outputSource&quot;: [ # Output sources for this stage.
+            { # Description of an input or output of an execution stage.
+              &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this source; may be user or system generated.
+              &quot;originalTransformOrCollection&quot;: &quot;A String&quot;, # User name for the original user transform or collection with which this
+                  # source is most closely associated.
+              &quot;sizeBytes&quot;: &quot;A String&quot;, # Size of the source, if measurable.
+              &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
+            },
+          ],
+          &quot;kind&quot;: &quot;A String&quot;, # Type of tranform this stage is executing.
+        },
+      ],
+    },
+    &quot;labels&quot;: { # User-defined labels for this job.
+        # 
+        # The labels map can contain no more than 64 entries.  Entries of the labels
+        # map are UTF8 strings that comply with the following restrictions:
+        # 
+        # * Keys must conform to regexp:  \p{Ll}\p{Lo}{0,62}
+        # * Values must conform to regexp:  [\p{Ll}\p{Lo}\p{N}_-]{0,63}
+        # * Both keys and values are additionally constrained to be &lt;= 128 bytes in
+        # size.
+      &quot;a_key&quot;: &quot;A String&quot;,
+    },
+    &quot;projectId&quot;: &quot;A String&quot;, # The ID of the Cloud Platform project that the job belongs to.
+    &quot;environment&quot;: { # Describes the environment in which a Dataflow Job runs. # The environment for the job.
+      &quot;flexResourceSchedulingGoal&quot;: &quot;A String&quot;, # Which Flexible Resource Scheduling mode to run in.
+      &quot;workerRegion&quot;: &quot;A String&quot;, # The Compute Engine region
+          # (https://cloud.google.com/compute/docs/regions-zones/regions-zones) in
+          # which worker processing should occur, e.g. &quot;us-west1&quot;. Mutually exclusive
+          # with worker_zone. If neither worker_region nor worker_zone is specified,
+          # default to the control plane&#x27;s region.
+      &quot;userAgent&quot;: { # A description of the process that generated the request.
+        &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
+      },
+      &quot;serviceAccountEmail&quot;: &quot;A String&quot;, # Identity to run virtual machines as. Defaults to the default account.
+      &quot;version&quot;: { # A structure describing which components and their versions of the service
+          # are required in order to run the job.
+        &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
+      },
+      &quot;serviceKmsKeyName&quot;: &quot;A String&quot;, # If set, contains the Cloud KMS key identifier used to encrypt data
+          # at rest, AKA a Customer Managed Encryption Key (CMEK).
+          #
+          # Format:
+          #   projects/PROJECT_ID/locations/LOCATION/keyRings/KEY_RING/cryptoKeys/KEY
+      &quot;experiments&quot;: [ # The list of experiments to enable.
+        &quot;A String&quot;,
+      ],
+      &quot;workerZone&quot;: &quot;A String&quot;, # The Compute Engine zone
+          # (https://cloud.google.com/compute/docs/regions-zones/regions-zones) in
+          # which worker processing should occur, e.g. &quot;us-west1-a&quot;. Mutually exclusive
+          # with worker_region. If neither worker_region nor worker_zone is specified,
+          # a zone in the control plane&#x27;s region is chosen based on available capacity.
+      &quot;workerPools&quot;: [ # The worker pools. At least one &quot;harness&quot; worker pool must be
+          # specified in order for the job to have workers.
+        { # Describes one particular pool of Cloud Dataflow workers to be
+            # instantiated by the Cloud Dataflow service in order to perform the
+            # computations required by a job.  Note that a workflow job may use
+            # multiple pools, in order to match the various computational
+            # requirements of the various stages of the job.
+          &quot;onHostMaintenance&quot;: &quot;A String&quot;, # The action to take on host maintenance, as defined by the Google
+              # Compute Engine API.
+          &quot;sdkHarnessContainerImages&quot;: [ # Set of SDK harness containers needed to execute this pipeline. This will
+              # only be set in the Fn API path. For non-cross-language pipelines this
+              # should have only one entry. Cross-language pipelines will have two or more
+              # entries.
+            { # Defines a SDK harness container for executing Dataflow pipelines.
+              &quot;containerImage&quot;: &quot;A String&quot;, # A docker container image that resides in Google Container Registry.
+              &quot;useSingleCorePerContainer&quot;: True or False, # If true, recommends the Dataflow service to use only one core per SDK
+                  # container instance with this image. If false (or unset) recommends using
+                  # more than one core per SDK container instance with this image for
+                  # efficiency. Note that Dataflow service may choose to override this property
+                  # if needed.
+            },
+          ],
+          &quot;zone&quot;: &quot;A String&quot;, # Zone to run the worker pools in.  If empty or unspecified, the service
+              # will attempt to choose a reasonable default.
+          &quot;kind&quot;: &quot;A String&quot;, # The kind of the worker pool; currently only `harness` and `shuffle`
+              # are supported.
+          &quot;metadata&quot;: { # Metadata to set on the Google Compute Engine VMs.
+            &quot;a_key&quot;: &quot;A String&quot;,
+          },
+          &quot;diskSourceImage&quot;: &quot;A String&quot;, # Fully qualified source image for disks.
+          &quot;dataDisks&quot;: [ # Data disks that are used by a VM in this workflow.
+            { # Describes the data disk used by a workflow job.
+              &quot;sizeGb&quot;: 42, # Size of disk in GB.  If zero or unspecified, the service will
+                  # attempt to choose a reasonable default.
+              &quot;diskType&quot;: &quot;A String&quot;, # Disk storage type, as defined by Google Compute Engine.  This
+                  # must be a disk type appropriate to the project and zone in which
+                  # the workers will run.  If unknown or unspecified, the service
+                  # will attempt to choose a reasonable default.
+                  #
+                  # For example, the standard persistent disk type is a resource name
+                  # typically ending in &quot;pd-standard&quot;.  If SSD persistent disks are
+                  # available, the resource name typically ends with &quot;pd-ssd&quot;.  The
+                  # actual valid values are defined the Google Compute Engine API,
+                  # not by the Cloud Dataflow API; consult the Google Compute Engine
+                  # documentation for more information about determining the set of
+                  # available disk types for a particular project and zone.
+                  #
+                  # Google Compute Engine Disk types are local to a particular
+                  # project in a particular zone, and so the resource name will
+                  # typically look something like this:
+                  #
+                  # compute.googleapis.com/projects/project-id/zones/zone/diskTypes/pd-standard
+              &quot;mountPoint&quot;: &quot;A String&quot;, # Directory in a VM where disk is mounted.
+            },
+          ],
+          &quot;packages&quot;: [ # Packages to be installed on workers.
+            { # The packages that must be installed in order for a worker to run the
+                # steps of the Cloud Dataflow job that will be assigned to its worker
+                # pool.
                 #
-                # The supported resource type is:
-                #
-                # Google Cloud Storage:
-                #
-                #   storage.googleapis.com/{bucket}/{object}
-                #   bucket.storage.googleapis.com/{object}
-            &quot;reportingEnabled&quot;: True or False, # Whether to send work progress updates to the service.
-            &quot;baseUrl&quot;: &quot;A String&quot;, # The base URL for accessing Google Cloud APIs.
+                # This is the mechanism by which the Cloud Dataflow SDK causes code to
+                # be loaded onto the workers. For example, the Cloud Dataflow Java SDK
+                # might use this to install jars containing the user&#x27;s code and all of the
+                # various dependencies (libraries, data files, etc.) required in order
+                # for that code to run.
+              &quot;name&quot;: &quot;A String&quot;, # The name of the package.
+              &quot;location&quot;: &quot;A String&quot;, # The resource to read the package from. The supported resource type is:
+                  #
+                  # Google Cloud Storage:
+                  #
+                  #   storage.googleapis.com/{bucket}
+                  #   bucket.storage.googleapis.com/
+            },
+          ],
+          &quot;teardownPolicy&quot;: &quot;A String&quot;, # Sets the policy for determining when to turndown worker pool.
+              # Allowed values are: `TEARDOWN_ALWAYS`, `TEARDOWN_ON_SUCCESS`, and
+              # `TEARDOWN_NEVER`.
+              # `TEARDOWN_ALWAYS` means workers are always torn down regardless of whether
+              # the job succeeds. `TEARDOWN_ON_SUCCESS` means workers are torn down
+              # if the job succeeds. `TEARDOWN_NEVER` means the workers are never torn
+              # down.
+              #
+              # If the workers are not torn down by the service, they will
+              # continue to run and use Google Compute Engine VM resources in the
+              # user&#x27;s project until they are explicitly terminated by the user.
+              # Because of this, Google recommends using the `TEARDOWN_ALWAYS`
+              # policy except for small, manually supervised test jobs.
+              #
+              # If unknown or unspecified, the service will attempt to choose a reasonable
+              # default.
+          &quot;network&quot;: &quot;A String&quot;, # Network to which VMs will be assigned.  If empty or unspecified,
+              # the service will use the network &quot;default&quot;.
+          &quot;ipConfiguration&quot;: &quot;A String&quot;, # Configuration for VM IPs.
+          &quot;diskSizeGb&quot;: 42, # Size of root disk for VMs, in GB.  If zero or unspecified, the service will
+              # attempt to choose a reasonable default.
+          &quot;autoscalingSettings&quot;: { # Settings for WorkerPool autoscaling. # Settings for autoscaling of this WorkerPool.
+            &quot;maxNumWorkers&quot;: 42, # The maximum number of workers to cap scaling at.
+            &quot;algorithm&quot;: &quot;A String&quot;, # The algorithm to use for autoscaling.
+          },
+          &quot;poolArgs&quot;: { # Extra arguments for this worker pool.
+            &quot;a_key&quot;: &quot;&quot;, # Properties of the object. Contains field @type with type URL.
+          },
+          &quot;subnetwork&quot;: &quot;A String&quot;, # Subnetwork to which VMs will be assigned, if desired.  Expected to be of
+              # the form &quot;regions/REGION/subnetworks/SUBNETWORK&quot;.
+          &quot;numWorkers&quot;: 42, # Number of Google Compute Engine workers in this pool needed to
+              # execute the job.  If zero or unspecified, the service will
+              # attempt to choose a reasonable default.
+          &quot;numThreadsPerWorker&quot;: 42, # The number of threads per worker harness. If empty or unspecified, the
+              # service will choose a number of threads (according to the number of cores
+              # on the selected machine type for batch, or 1 by convention for streaming).
+          &quot;workerHarnessContainerImage&quot;: &quot;A String&quot;, # Required. Docker container image that executes the Cloud Dataflow worker
+              # harness, residing in Google Container Registry.
+              #
+              # Deprecated for the Fn API path. Use sdk_harness_container_images instead.
+          &quot;taskrunnerSettings&quot;: { # Taskrunner configuration settings. # Settings passed through to Google Compute Engine workers when
+              # using the standard Dataflow task runner.  Users should ignore
+              # this field.
+            &quot;dataflowApiVersion&quot;: &quot;A String&quot;, # The API version of endpoint, e.g. &quot;v1b3&quot;
+            &quot;oauthScopes&quot;: [ # The OAuth2 scopes to be requested by the taskrunner in order to
+                # access the Cloud Dataflow API.
+              &quot;A String&quot;,
+            ],
+            &quot;baseUrl&quot;: &quot;A String&quot;, # The base URL for the taskrunner to use when accessing Google Cloud APIs.
                 #
                 # When workers access Google Cloud APIs, they logically do so via
                 # relative URLs.  If this field is specified, it supplies the base
@@ -1017,339 +1059,297 @@
                 # Locators&quot;.
                 #
                 # If not specified, the default value is &quot;http://www.googleapis.com/&quot;
-            &quot;servicePath&quot;: &quot;A String&quot;, # The Cloud Dataflow service path relative to the root URL, for example,
-                # &quot;dataflow/v1b3/projects&quot;.
-            &quot;shuffleServicePath&quot;: &quot;A String&quot;, # The Shuffle service path relative to the root URL, for example,
-                # &quot;shuffle/v1beta1&quot;.
-            &quot;workerId&quot;: &quot;A String&quot;, # The ID of the worker running this pipeline.
+            &quot;workflowFileName&quot;: &quot;A String&quot;, # The file to store the workflow in.
+            &quot;logToSerialconsole&quot;: True or False, # Whether to send taskrunner log info to Google Compute Engine VM serial
+                # console.
+            &quot;baseTaskDir&quot;: &quot;A String&quot;, # The location on the worker for task-specific subdirectories.
+            &quot;taskUser&quot;: &quot;A String&quot;, # The UNIX user ID on the worker VM to use for tasks launched by
+                # taskrunner; e.g. &quot;root&quot;.
+            &quot;vmId&quot;: &quot;A String&quot;, # The ID string of the VM.
+            &quot;alsologtostderr&quot;: True or False, # Whether to also send taskrunner log info to stderr.
+            &quot;parallelWorkerSettings&quot;: { # Provides data to pass through to the worker harness. # The settings to pass to the parallel worker harness.
+              &quot;shuffleServicePath&quot;: &quot;A String&quot;, # The Shuffle service path relative to the root URL, for example,
+                  # &quot;shuffle/v1beta1&quot;.
+              &quot;tempStoragePrefix&quot;: &quot;A String&quot;, # The prefix of the resources the system should use for temporary
+                  # storage.
+                  #
+                  # The supported resource type is:
+                  #
+                  # Google Cloud Storage:
+                  #
+                  #   storage.googleapis.com/{bucket}/{object}
+                  #   bucket.storage.googleapis.com/{object}
+              &quot;reportingEnabled&quot;: True or False, # Whether to send work progress updates to the service.
+              &quot;servicePath&quot;: &quot;A String&quot;, # The Cloud Dataflow service path relative to the root URL, for example,
+                  # &quot;dataflow/v1b3/projects&quot;.
+              &quot;baseUrl&quot;: &quot;A String&quot;, # The base URL for accessing Google Cloud APIs.
+                  #
+                  # When workers access Google Cloud APIs, they logically do so via
+                  # relative URLs.  If this field is specified, it supplies the base
+                  # URL to use for resolving these relative URLs.  The normative
+                  # algorithm used is defined by RFC 1808, &quot;Relative Uniform Resource
+                  # Locators&quot;.
+                  #
+                  # If not specified, the default value is &quot;http://www.googleapis.com/&quot;
+              &quot;workerId&quot;: &quot;A String&quot;, # The ID of the worker running this pipeline.
+            },
+            &quot;harnessCommand&quot;: &quot;A String&quot;, # The command to launch the worker harness.
+            &quot;logDir&quot;: &quot;A String&quot;, # The directory on the VM to store logs.
+            &quot;streamingWorkerMainClass&quot;: &quot;A String&quot;, # The streaming worker main class name.
+            &quot;languageHint&quot;: &quot;A String&quot;, # The suggested backend language.
+            &quot;taskGroup&quot;: &quot;A String&quot;, # The UNIX group ID on the worker VM to use for tasks launched by
+                # taskrunner; e.g. &quot;wheel&quot;.
+            &quot;logUploadLocation&quot;: &quot;A String&quot;, # Indicates where to put logs.  If this is not specified, the logs
+                # will not be uploaded.
+                #
+                # The supported resource type is:
+                #
+                # Google Cloud Storage:
+                #   storage.googleapis.com/{bucket}/{object}
+                #   bucket.storage.googleapis.com/{object}
+            &quot;commandlinesFileName&quot;: &quot;A String&quot;, # The file to store preprocessing commands in.
+            &quot;continueOnException&quot;: True or False, # Whether to continue taskrunner if an exception is hit.
+            &quot;tempStoragePrefix&quot;: &quot;A String&quot;, # The prefix of the resources the taskrunner should use for
+                # temporary storage.
+                #
+                # The supported resource type is:
+                #
+                # Google Cloud Storage:
+                #   storage.googleapis.com/{bucket}/{object}
+                #   bucket.storage.googleapis.com/{object}
           },
-          &quot;taskUser&quot;: &quot;A String&quot;, # The UNIX user ID on the worker VM to use for tasks launched by
-              # taskrunner; e.g. &quot;root&quot;.
-          &quot;vmId&quot;: &quot;A String&quot;, # The ID string of the VM.
+          &quot;diskType&quot;: &quot;A String&quot;, # Type of root disk for VMs.  If empty or unspecified, the service will
+              # attempt to choose a reasonable default.
+          &quot;defaultPackageSet&quot;: &quot;A String&quot;, # The default package set to install.  This allows the service to
+              # select a default set of packages which are useful to worker
+              # harnesses written in a particular language.
+          &quot;machineType&quot;: &quot;A String&quot;, # Machine type (e.g. &quot;n1-standard-1&quot;).  If empty or unspecified, the
+              # service will attempt to choose a reasonable default.
         },
-        &quot;autoscalingSettings&quot;: { # Settings for WorkerPool autoscaling. # Settings for autoscaling of this WorkerPool.
-          &quot;algorithm&quot;: &quot;A String&quot;, # The algorithm to use for autoscaling.
-          &quot;maxNumWorkers&quot;: 42, # The maximum number of workers to cap scaling at.
-        },
-        &quot;metadata&quot;: { # Metadata to set on the Google Compute Engine VMs.
-          &quot;a_key&quot;: &quot;A String&quot;,
-        },
-        &quot;defaultPackageSet&quot;: &quot;A String&quot;, # The default package set to install.  This allows the service to
-            # select a default set of packages which are useful to worker
-            # harnesses written in a particular language.
-        &quot;network&quot;: &quot;A String&quot;, # Network to which VMs will be assigned.  If empty or unspecified,
-            # the service will use the network &quot;default&quot;.
+      ],
+      &quot;tempStoragePrefix&quot;: &quot;A String&quot;, # The prefix of the resources the system should use for temporary
+          # storage.  The system will append the suffix &quot;/temp-{JOBNAME} to
+          # this resource prefix, where {JOBNAME} is the value of the
+          # job_name field.  The resulting bucket and object prefix is used
+          # as the prefix of the resources used to store temporary data
+          # needed during the job execution.  NOTE: This will override the
+          # value in taskrunner_settings.
+          # The supported resource type is:
+          #
+          # Google Cloud Storage:
+          #
+          #   storage.googleapis.com/{bucket}/{object}
+          #   bucket.storage.googleapis.com/{object}
+      &quot;internalExperiments&quot;: { # Experimental settings.
+        &quot;a_key&quot;: &quot;&quot;, # Properties of the object. Contains field @type with type URL.
       },
-    ],
-    &quot;dataset&quot;: &quot;A String&quot;, # The dataset for the current project where various workflow
-        # related tables are stored.
-        #
-        # The supported resource type is:
-        #
-        # Google BigQuery:
-        #   bigquery.googleapis.com/{dataset}
-  },
-  &quot;stageStates&quot;: [ # This field may be mutated by the Cloud Dataflow service;
-      # callers cannot mutate it.
-    { # A message describing the state of a particular execution stage.
-      &quot;currentStateTime&quot;: &quot;A String&quot;, # The time at which the stage transitioned to this state.
-      &quot;executionStageState&quot;: &quot;A String&quot;, # Executions stage states allow the same set of values as JobState.
-      &quot;executionStageName&quot;: &quot;A String&quot;, # The name of the execution stage.
-    },
-  ],
-  &quot;jobMetadata&quot;: { # Metadata available primarily for filtering jobs. Will be included in the # This field is populated by the Dataflow service to support filtering jobs
-      # by the metadata values provided here. Populated for ListJobs and all GetJob
-      # views SUMMARY and higher.
-      # ListJob response and Job SUMMARY view.
-    &quot;datastoreDetails&quot;: [ # Identification of a Datastore source used in the Dataflow job.
-      { # Metadata for a Datastore connector used by the job.
-        &quot;namespace&quot;: &quot;A String&quot;, # Namespace used in the connection.
-        &quot;projectId&quot;: &quot;A String&quot;, # ProjectId accessed in the connection.
-      },
-    ],
-    &quot;sdkVersion&quot;: { # The version of the SDK used to run the job. # The SDK version used to run the job.
-      &quot;version&quot;: &quot;A String&quot;, # The version of the SDK used to run the job.
-      &quot;sdkSupportStatus&quot;: &quot;A String&quot;, # The support status for this SDK version.
-      &quot;versionDisplayName&quot;: &quot;A String&quot;, # A readable string describing the version of the SDK.
-    },
-    &quot;bigqueryDetails&quot;: [ # Identification of a BigQuery source used in the Dataflow job.
-      { # Metadata for a BigQuery connector used by the job.
-        &quot;table&quot;: &quot;A String&quot;, # Table accessed in the connection.
-        &quot;dataset&quot;: &quot;A String&quot;, # Dataset accessed in the connection.
-        &quot;query&quot;: &quot;A String&quot;, # Query used to access data in the connection.
-        &quot;projectId&quot;: &quot;A String&quot;, # Project accessed in the connection.
-      },
-    ],
-    &quot;fileDetails&quot;: [ # Identification of a File source used in the Dataflow job.
-      { # Metadata for a File connector used by the job.
-        &quot;filePattern&quot;: &quot;A String&quot;, # File Pattern used to access files by the connector.
-      },
-    ],
-    &quot;pubsubDetails&quot;: [ # Identification of a PubSub source used in the Dataflow job.
-      { # Metadata for a PubSub connector used by the job.
-        &quot;topic&quot;: &quot;A String&quot;, # Topic accessed in the connection.
-        &quot;subscription&quot;: &quot;A String&quot;, # Subscription used in the connection.
-      },
-    ],
-    &quot;bigTableDetails&quot;: [ # Identification of a BigTable source used in the Dataflow job.
-      { # Metadata for a BigTable connector used by the job.
-        &quot;projectId&quot;: &quot;A String&quot;, # ProjectId accessed in the connection.
-        &quot;instanceId&quot;: &quot;A String&quot;, # InstanceId accessed in the connection.
-        &quot;tableId&quot;: &quot;A String&quot;, # TableId accessed in the connection.
-      },
-    ],
-    &quot;spannerDetails&quot;: [ # Identification of a Spanner source used in the Dataflow job.
-      { # Metadata for a Spanner connector used by the job.
-        &quot;instanceId&quot;: &quot;A String&quot;, # InstanceId accessed in the connection.
-        &quot;projectId&quot;: &quot;A String&quot;, # ProjectId accessed in the connection.
-        &quot;databaseId&quot;: &quot;A String&quot;, # DatabaseId accessed in the connection.
-      },
-    ],
-  },
-  &quot;type&quot;: &quot;A String&quot;, # The type of Cloud Dataflow job.
-  &quot;projectId&quot;: &quot;A String&quot;, # The ID of the Cloud Platform project that the job belongs to.
-  &quot;createdFromSnapshotId&quot;: &quot;A String&quot;, # If this is specified, the job&#x27;s initial state is populated from the given
-      # snapshot.
-  &quot;pipelineDescription&quot;: { # A descriptive representation of submitted pipeline as well as the executed # Preliminary field: The format of this data may change at any time.
-      # A description of the user pipeline and stages through which it is executed.
-      # Created by Cloud Dataflow service.  Only retrieved with
-      # JOB_VIEW_DESCRIPTION or JOB_VIEW_ALL.
-      # form.  This data is provided by the Dataflow service for ease of visualizing
-      # the pipeline and interpreting Dataflow provided metrics.
-    &quot;executionPipelineStage&quot;: [ # Description of each stage of execution of the pipeline.
-      { # Description of the composing transforms, names/ids, and input/outputs of a
-          # stage of execution.  Some composing transforms and sources may have been
-          # generated by the Dataflow service during execution planning.
-        &quot;outputSource&quot;: [ # Output sources for this stage.
-          { # Description of an input or output of an execution stage.
-            &quot;sizeBytes&quot;: &quot;A String&quot;, # Size of the source, if measurable.
-            &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
-            &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this source; may be user or system generated.
-            &quot;originalTransformOrCollection&quot;: &quot;A String&quot;, # User name for the original user transform or collection with which this
-                # source is most closely associated.
-          },
-        ],
-        &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this stage.
-        &quot;inputSource&quot;: [ # Input sources for this stage.
-          { # Description of an input or output of an execution stage.
-            &quot;sizeBytes&quot;: &quot;A String&quot;, # Size of the source, if measurable.
-            &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
-            &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this source; may be user or system generated.
-            &quot;originalTransformOrCollection&quot;: &quot;A String&quot;, # User name for the original user transform or collection with which this
-                # source is most closely associated.
-          },
-        ],
-        &quot;id&quot;: &quot;A String&quot;, # Dataflow service generated id for this stage.
-        &quot;componentTransform&quot;: [ # Transforms that comprise this execution stage.
-          { # Description of a transform executed as part of an execution stage.
-            &quot;originalTransform&quot;: &quot;A String&quot;, # User name for the original user transform with which this transform is
-                # most closely associated.
-            &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
-            &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this transform; may be user or system generated.
-          },
-        ],
-        &quot;componentSource&quot;: [ # Collections produced and consumed by component transforms of this stage.
-          { # Description of an interstitial value between transforms in an execution
-              # stage.
-            &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
-            &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this transform; may be user or system generated.
-            &quot;originalTransformOrCollection&quot;: &quot;A String&quot;, # User name for the original user transform or collection with which this
-                # source is most closely associated.
-          },
-        ],
-        &quot;kind&quot;: &quot;A String&quot;, # Type of tranform this stage is executing.
-      },
-    ],
-    &quot;originalPipelineTransform&quot;: [ # Description of each transform in the pipeline and collections between them.
-      { # Description of the type, names/ids, and input/outputs for a transform.
-        &quot;kind&quot;: &quot;A String&quot;, # Type of transform.
-        &quot;inputCollectionName&quot;: [ # User names for all collection inputs to this transform.
-          &quot;A String&quot;,
-        ],
-        &quot;name&quot;: &quot;A String&quot;, # User provided name for this transform instance.
-        &quot;id&quot;: &quot;A String&quot;, # SDK generated id of this transform instance.
-        &quot;displayData&quot;: [ # Transform-specific display data.
-          { # Data provided with a pipeline or transform to provide descriptive info.
-            &quot;durationValue&quot;: &quot;A String&quot;, # Contains value if the data is of duration type.
-            &quot;int64Value&quot;: &quot;A String&quot;, # Contains value if the data is of int64 type.
-            &quot;namespace&quot;: &quot;A String&quot;, # The namespace for the key. This is usually a class name or programming
-                # language namespace (i.e. python module) which defines the display data.
-                # This allows a dax monitoring system to specially handle the data
-                # and perform custom rendering.
-            &quot;floatValue&quot;: 3.14, # Contains value if the data is of float type.
-            &quot;key&quot;: &quot;A String&quot;, # The key identifying the display data.
-                # This is intended to be used as a label for the display data
-                # when viewed in a dax monitoring system.
-            &quot;shortStrValue&quot;: &quot;A String&quot;, # A possible additional shorter value to display.
-                # For example a java_class_name_value of com.mypackage.MyDoFn
-                # will be stored with MyDoFn as the short_str_value and
-                # com.mypackage.MyDoFn as the java_class_name value.
-                # short_str_value can be displayed and java_class_name_value
-                # will be displayed as a tooltip.
-            &quot;url&quot;: &quot;A String&quot;, # An optional full URL.
-            &quot;label&quot;: &quot;A String&quot;, # An optional label to display in a dax UI for the element.
-            &quot;timestampValue&quot;: &quot;A String&quot;, # Contains value if the data is of timestamp type.
-            &quot;boolValue&quot;: True or False, # Contains value if the data is of a boolean type.
-            &quot;javaClassValue&quot;: &quot;A String&quot;, # Contains value if the data is of java class type.
-            &quot;strValue&quot;: &quot;A String&quot;, # Contains value if the data is of string type.
-          },
-        ],
-        &quot;outputCollectionName&quot;: [ # User  names for all collection outputs to this transform.
-          &quot;A String&quot;,
-        ],
-      },
-    ],
-    &quot;displayData&quot;: [ # Pipeline level display data.
-      { # Data provided with a pipeline or transform to provide descriptive info.
-        &quot;durationValue&quot;: &quot;A String&quot;, # Contains value if the data is of duration type.
-        &quot;int64Value&quot;: &quot;A String&quot;, # Contains value if the data is of int64 type.
-        &quot;namespace&quot;: &quot;A String&quot;, # The namespace for the key. This is usually a class name or programming
-            # language namespace (i.e. python module) which defines the display data.
-            # This allows a dax monitoring system to specially handle the data
-            # and perform custom rendering.
-        &quot;floatValue&quot;: 3.14, # Contains value if the data is of float type.
-        &quot;key&quot;: &quot;A String&quot;, # The key identifying the display data.
-            # This is intended to be used as a label for the display data
-            # when viewed in a dax monitoring system.
-        &quot;shortStrValue&quot;: &quot;A String&quot;, # A possible additional shorter value to display.
-            # For example a java_class_name_value of com.mypackage.MyDoFn
-            # will be stored with MyDoFn as the short_str_value and
-            # com.mypackage.MyDoFn as the java_class_name value.
-            # short_str_value can be displayed and java_class_name_value
-            # will be displayed as a tooltip.
-        &quot;url&quot;: &quot;A String&quot;, # An optional full URL.
-        &quot;label&quot;: &quot;A String&quot;, # An optional label to display in a dax UI for the element.
-        &quot;timestampValue&quot;: &quot;A String&quot;, # Contains value if the data is of timestamp type.
-        &quot;boolValue&quot;: True or False, # Contains value if the data is of a boolean type.
-        &quot;javaClassValue&quot;: &quot;A String&quot;, # Contains value if the data is of java class type.
-        &quot;strValue&quot;: &quot;A String&quot;, # Contains value if the data is of string type.
-      },
-    ],
-  },
-  &quot;replaceJobId&quot;: &quot;A String&quot;, # If this job is an update of an existing job, this field is the job ID
-      # of the job it replaced.
-      # 
-      # When sending a `CreateJobRequest`, you can update a job by specifying it
-      # here. The job named here is stopped, and its intermediate state is
-      # transferred to this job.
-  &quot;tempFiles&quot;: [ # A set of files the system should be aware of that are used
-      # for temporary storage. These temporary files will be
-      # removed on job completion.
-      # No duplicates are allowed.
-      # No file patterns are supported.
-      # 
-      # The supported files are:
-      # 
-      # Google Cloud Storage:
-      # 
-      #    storage.googleapis.com/{bucket}/{object}
-      #    bucket.storage.googleapis.com/{object}
-    &quot;A String&quot;,
-  ],
-  &quot;name&quot;: &quot;A String&quot;, # The user-specified Cloud Dataflow job name.
-      # 
-      # Only one Job with a given name may exist in a project at any
-      # given time. If a caller attempts to create a Job with the same
-      # name as an already-existing Job, the attempt returns the
-      # existing Job.
-      # 
-      # The name must match the regular expression
-      # `[a-z]([-a-z0-9]{0,38}[a-z0-9])?`
-  &quot;steps&quot;: [ # Exactly one of step or steps_location should be specified.
-      # 
-      # The top-level steps that constitute the entire job.
-    { # Defines a particular step within a Cloud Dataflow job.
-        #
-        # A job consists of multiple steps, each of which performs some
-        # specific operation as part of the overall job.  Data is typically
-        # passed from one step to another as part of the job.
-        #
-        # Here&#x27;s an example of a sequence of steps which together implement a
-        # Map-Reduce job:
-        #
-        #   * Read a collection of data from some source, parsing the
-        #     collection&#x27;s elements.
-        #
-        #   * Validate the elements.
-        #
-        #   * Apply a user-defined function to map each element to some value
-        #     and extract an element-specific key value.
-        #
-        #   * Group elements with the same key into a single element with
-        #     that key, transforming a multiply-keyed collection into a
-        #     uniquely-keyed collection.
-        #
-        #   * Write the elements out to some data sink.
-        #
-        # Note that the Cloud Dataflow service may be used to run many different
-        # types of jobs, not just Map-Reduce.
-      &quot;name&quot;: &quot;A String&quot;, # The name that identifies the step. This must be unique for each
-          # step with respect to all other steps in the Cloud Dataflow job.
-      &quot;kind&quot;: &quot;A String&quot;, # The kind of step in the Cloud Dataflow job.
-      &quot;properties&quot;: { # Named properties associated with the step. Each kind of
-          # predefined step has its own required set of properties.
-          # Must be provided on Create.  Only retrieved with JOB_VIEW_ALL.
+      &quot;sdkPipelineOptions&quot;: { # The Cloud Dataflow SDK pipeline options specified by the user. These
+          # options are passed through the service and are used to recreate the
+          # SDK pipeline options on the worker in a language agnostic and platform
+          # independent way.
         &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
       },
+      &quot;dataset&quot;: &quot;A String&quot;, # The dataset for the current project where various workflow
+          # related tables are stored.
+          #
+          # The supported resource type is:
+          #
+          # Google BigQuery:
+          #   bigquery.googleapis.com/{dataset}
+      &quot;clusterManagerApiService&quot;: &quot;A String&quot;, # The type of cluster manager API to use.  If unknown or
+          # unspecified, the service will attempt to choose a reasonable
+          # default.  This should be in the form of the API service name,
+          # e.g. &quot;compute.googleapis.com&quot;.
     },
-  ],
-  &quot;replacedByJobId&quot;: &quot;A String&quot;, # If another job is an update of this job (and thus, this job is in
-      # `JOB_STATE_UPDATED`), this field contains the ID of that job.
-  &quot;executionInfo&quot;: { # Additional information about how a Cloud Dataflow job will be executed that # Deprecated.
-      # isn&#x27;t contained in the submitted job.
-    &quot;stages&quot;: { # A mapping from each stage to the information about that stage.
-      &quot;a_key&quot;: { # Contains information about how a particular
-          # google.dataflow.v1beta3.Step will be executed.
-        &quot;stepName&quot;: [ # The steps associated with the execution stage.
-            # Note that stages may have several steps, and that a given step
-            # might be run by more than one stage.
-          &quot;A String&quot;,
-        ],
+    &quot;stepsLocation&quot;: &quot;A String&quot;, # The GCS location where the steps are stored.
+    &quot;steps&quot;: [ # Exactly one of step or steps_location should be specified.
+        # 
+        # The top-level steps that constitute the entire job.
+      { # Defines a particular step within a Cloud Dataflow job.
+          #
+          # A job consists of multiple steps, each of which performs some
+          # specific operation as part of the overall job.  Data is typically
+          # passed from one step to another as part of the job.
+          #
+          # Here&#x27;s an example of a sequence of steps which together implement a
+          # Map-Reduce job:
+          #
+          #   * Read a collection of data from some source, parsing the
+          #     collection&#x27;s elements.
+          #
+          #   * Validate the elements.
+          #
+          #   * Apply a user-defined function to map each element to some value
+          #     and extract an element-specific key value.
+          #
+          #   * Group elements with the same key into a single element with
+          #     that key, transforming a multiply-keyed collection into a
+          #     uniquely-keyed collection.
+          #
+          #   * Write the elements out to some data sink.
+          #
+          # Note that the Cloud Dataflow service may be used to run many different
+          # types of jobs, not just Map-Reduce.
+        &quot;kind&quot;: &quot;A String&quot;, # The kind of step in the Cloud Dataflow job.
+        &quot;properties&quot;: { # Named properties associated with the step. Each kind of
+            # predefined step has its own required set of properties.
+            # Must be provided on Create.  Only retrieved with JOB_VIEW_ALL.
+          &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
+        },
+        &quot;name&quot;: &quot;A String&quot;, # The name that identifies the step. This must be unique for each
+            # step with respect to all other steps in the Cloud Dataflow job.
+      },
+    ],
+    &quot;stageStates&quot;: [ # This field may be mutated by the Cloud Dataflow service;
+        # callers cannot mutate it.
+      { # A message describing the state of a particular execution stage.
+        &quot;executionStageState&quot;: &quot;A String&quot;, # Executions stage states allow the same set of values as JobState.
+        &quot;executionStageName&quot;: &quot;A String&quot;, # The name of the execution stage.
+        &quot;currentStateTime&quot;: &quot;A String&quot;, # The time at which the stage transitioned to this state.
+      },
+    ],
+    &quot;replacedByJobId&quot;: &quot;A String&quot;, # If another job is an update of this job (and thus, this job is in
+        # `JOB_STATE_UPDATED`), this field contains the ID of that job.
+    &quot;jobMetadata&quot;: { # Metadata available primarily for filtering jobs. Will be included in the # This field is populated by the Dataflow service to support filtering jobs
+        # by the metadata values provided here. Populated for ListJobs and all GetJob
+        # views SUMMARY and higher.
+        # ListJob response and Job SUMMARY view.
+      &quot;sdkVersion&quot;: { # The version of the SDK used to run the job. # The SDK version used to run the job.
+        &quot;sdkSupportStatus&quot;: &quot;A String&quot;, # The support status for this SDK version.
+        &quot;versionDisplayName&quot;: &quot;A String&quot;, # A readable string describing the version of the SDK.
+        &quot;version&quot;: &quot;A String&quot;, # The version of the SDK used to run the job.
+      },
+      &quot;bigTableDetails&quot;: [ # Identification of a BigTable source used in the Dataflow job.
+        { # Metadata for a BigTable connector used by the job.
+          &quot;instanceId&quot;: &quot;A String&quot;, # InstanceId accessed in the connection.
+          &quot;tableId&quot;: &quot;A String&quot;, # TableId accessed in the connection.
+          &quot;projectId&quot;: &quot;A String&quot;, # ProjectId accessed in the connection.
+        },
+      ],
+      &quot;pubsubDetails&quot;: [ # Identification of a PubSub source used in the Dataflow job.
+        { # Metadata for a PubSub connector used by the job.
+          &quot;subscription&quot;: &quot;A String&quot;, # Subscription used in the connection.
+          &quot;topic&quot;: &quot;A String&quot;, # Topic accessed in the connection.
+        },
+      ],
+      &quot;bigqueryDetails&quot;: [ # Identification of a BigQuery source used in the Dataflow job.
+        { # Metadata for a BigQuery connector used by the job.
+          &quot;dataset&quot;: &quot;A String&quot;, # Dataset accessed in the connection.
+          &quot;projectId&quot;: &quot;A String&quot;, # Project accessed in the connection.
+          &quot;query&quot;: &quot;A String&quot;, # Query used to access data in the connection.
+          &quot;table&quot;: &quot;A String&quot;, # Table accessed in the connection.
+        },
+      ],
+      &quot;fileDetails&quot;: [ # Identification of a File source used in the Dataflow job.
+        { # Metadata for a File connector used by the job.
+          &quot;filePattern&quot;: &quot;A String&quot;, # File Pattern used to access files by the connector.
+        },
+      ],
+      &quot;datastoreDetails&quot;: [ # Identification of a Datastore source used in the Dataflow job.
+        { # Metadata for a Datastore connector used by the job.
+          &quot;namespace&quot;: &quot;A String&quot;, # Namespace used in the connection.
+          &quot;projectId&quot;: &quot;A String&quot;, # ProjectId accessed in the connection.
+        },
+      ],
+      &quot;spannerDetails&quot;: [ # Identification of a Spanner source used in the Dataflow job.
+        { # Metadata for a Spanner connector used by the job.
+          &quot;instanceId&quot;: &quot;A String&quot;, # InstanceId accessed in the connection.
+          &quot;databaseId&quot;: &quot;A String&quot;, # DatabaseId accessed in the connection.
+          &quot;projectId&quot;: &quot;A String&quot;, # ProjectId accessed in the connection.
+        },
+      ],
+    },
+    &quot;location&quot;: &quot;A String&quot;, # The [regional endpoint]
+        # (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that
+        # contains this job.
+    &quot;transformNameMapping&quot;: { # The map of transform name prefixes of the job to be replaced to the
+        # corresponding name prefixes of the new job.
+      &quot;a_key&quot;: &quot;A String&quot;,
+    },
+    &quot;startTime&quot;: &quot;A String&quot;, # The timestamp when the job was started (transitioned to JOB_STATE_PENDING).
+        # Flexible resource scheduling jobs are started with some delay after job
+        # creation, so start_time is unset before start and is updated when the
+        # job is started by the Cloud Dataflow service. For other jobs, start_time
+        # always equals to create_time and is immutable and set by the Cloud Dataflow
+        # service.
+    &quot;clientRequestId&quot;: &quot;A String&quot;, # The client&#x27;s unique identifier of the job, re-used across retried attempts.
+        # If this field is set, the service will ensure its uniqueness.
+        # The request to create a job will fail if the service has knowledge of a
+        # previously submitted job with the same client&#x27;s ID and job name.
+        # The caller may use this field to ensure idempotence of job
+        # creation across retried attempts to create a job.
+        # By default, the field is empty and, in that case, the service ignores it.
+    &quot;executionInfo&quot;: { # Additional information about how a Cloud Dataflow job will be executed that # Deprecated.
+        # isn&#x27;t contained in the submitted job.
+      &quot;stages&quot;: { # A mapping from each stage to the information about that stage.
+        &quot;a_key&quot;: { # Contains information about how a particular
+            # google.dataflow.v1beta3.Step will be executed.
+          &quot;stepName&quot;: [ # The steps associated with the execution stage.
+              # Note that stages may have several steps, and that a given step
+              # might be run by more than one stage.
+            &quot;A String&quot;,
+          ],
+        },
       },
     },
-  },
-  &quot;currentState&quot;: &quot;A String&quot;, # The current state of the job.
-      # 
-      # Jobs are created in the `JOB_STATE_STOPPED` state unless otherwise
-      # specified.
-      # 
-      # A job in the `JOB_STATE_RUNNING` state may asynchronously enter a
-      # terminal state. After a job has reached a terminal state, no
-      # further state updates may be made.
-      # 
-      # This field may be mutated by the Cloud Dataflow service;
-      # callers cannot mutate it.
-  &quot;location&quot;: &quot;A String&quot;, # The [regional endpoint]
-      # (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that
-      # contains this job.
-  &quot;startTime&quot;: &quot;A String&quot;, # The timestamp when the job was started (transitioned to JOB_STATE_PENDING).
-      # Flexible resource scheduling jobs are started with some delay after job
-      # creation, so start_time is unset before start and is updated when the
-      # job is started by the Cloud Dataflow service. For other jobs, start_time
-      # always equals to create_time and is immutable and set by the Cloud Dataflow
-      # service.
-  &quot;stepsLocation&quot;: &quot;A String&quot;, # The GCS location where the steps are stored.
-  &quot;labels&quot;: { # User-defined labels for this job.
-      # 
-      # The labels map can contain no more than 64 entries.  Entries of the labels
-      # map are UTF8 strings that comply with the following restrictions:
-      # 
-      # * Keys must conform to regexp:  \p{Ll}\p{Lo}{0,62}
-      # * Values must conform to regexp:  [\p{Ll}\p{Lo}\p{N}_-]{0,63}
-      # * Both keys and values are additionally constrained to be &lt;= 128 bytes in
-      # size.
-    &quot;a_key&quot;: &quot;A String&quot;,
-  },
-  &quot;createTime&quot;: &quot;A String&quot;, # The timestamp when the job was initially created. Immutable and set by the
-      # Cloud Dataflow service.
-  &quot;requestedState&quot;: &quot;A String&quot;, # The job&#x27;s requested state.
-      # 
-      # `UpdateJob` may be used to switch between the `JOB_STATE_STOPPED` and
-      # `JOB_STATE_RUNNING` states, by setting requested_state.  `UpdateJob` may
-      # also be used to directly set a job&#x27;s requested state to
-      # `JOB_STATE_CANCELLED` or `JOB_STATE_DONE`, irrevocably terminating the
-      # job if it has not already reached a terminal state.
-}
+    &quot;type&quot;: &quot;A String&quot;, # The type of Cloud Dataflow job.
+    &quot;createTime&quot;: &quot;A String&quot;, # The timestamp when the job was initially created. Immutable and set by the
+        # Cloud Dataflow service.
+    &quot;tempFiles&quot;: [ # A set of files the system should be aware of that are used
+        # for temporary storage. These temporary files will be
+        # removed on job completion.
+        # No duplicates are allowed.
+        # No file patterns are supported.
+        # 
+        # The supported files are:
+        # 
+        # Google Cloud Storage:
+        # 
+        #    storage.googleapis.com/{bucket}/{object}
+        #    bucket.storage.googleapis.com/{object}
+      &quot;A String&quot;,
+    ],
+    &quot;id&quot;: &quot;A String&quot;, # The unique ID of this job.
+        # 
+        # This field is set by the Cloud Dataflow service when the Job is
+        # created, and is immutable for the life of the job.
+    &quot;requestedState&quot;: &quot;A String&quot;, # The job&#x27;s requested state.
+        # 
+        # `UpdateJob` may be used to switch between the `JOB_STATE_STOPPED` and
+        # `JOB_STATE_RUNNING` states, by setting requested_state.  `UpdateJob` may
+        # also be used to directly set a job&#x27;s requested state to
+        # `JOB_STATE_CANCELLED` or `JOB_STATE_DONE`, irrevocably terminating the
+        # job if it has not already reached a terminal state.
+    &quot;replaceJobId&quot;: &quot;A String&quot;, # If this job is an update of an existing job, this field is the job ID
+        # of the job it replaced.
+        # 
+        # When sending a `CreateJobRequest`, you can update a job by specifying it
+        # here. The job named here is stopped, and its intermediate state is
+        # transferred to this job.
+    &quot;createdFromSnapshotId&quot;: &quot;A String&quot;, # If this is specified, the job&#x27;s initial state is populated from the given
+        # snapshot.
+    &quot;currentState&quot;: &quot;A String&quot;, # The current state of the job.
+        # 
+        # Jobs are created in the `JOB_STATE_STOPPED` state unless otherwise
+        # specified.
+        # 
+        # A job in the `JOB_STATE_RUNNING` state may asynchronously enter a
+        # terminal state. After a job has reached a terminal state, no
+        # further state updates may be made.
+        # 
+        # This field may be mutated by the Cloud Dataflow service;
+        # callers cannot mutate it.
+    &quot;name&quot;: &quot;A String&quot;, # The user-specified Cloud Dataflow job name.
+        # 
+        # Only one Job with a given name may exist in a project at any
+        # given time. If a caller attempts to create a Job with the same
+        # name as an already-existing Job, the attempt returns the
+        # existing Job.
+        # 
+        # The name must match the regular expression
+        # `[a-z]([-a-z0-9]{0,38}[a-z0-9])?`
+    &quot;currentStateTime&quot;: &quot;A String&quot;, # The timestamp associated with the current state.
+  }
 
   location: string, The [regional endpoint]
 (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that
@@ -1365,243 +1365,285 @@
   An object of the form:
 
     { # Defines a job to be run by the Cloud Dataflow service.
-    &quot;clientRequestId&quot;: &quot;A String&quot;, # The client&#x27;s unique identifier of the job, re-used across retried attempts.
-        # If this field is set, the service will ensure its uniqueness.
-        # The request to create a job will fail if the service has knowledge of a
-        # previously submitted job with the same client&#x27;s ID and job name.
-        # The caller may use this field to ensure idempotence of job
-        # creation across retried attempts to create a job.
-        # By default, the field is empty and, in that case, the service ignores it.
-    &quot;id&quot;: &quot;A String&quot;, # The unique ID of this job.
-        #
-        # This field is set by the Cloud Dataflow service when the Job is
-        # created, and is immutable for the life of the job.
-    &quot;currentStateTime&quot;: &quot;A String&quot;, # The timestamp associated with the current state.
-    &quot;transformNameMapping&quot;: { # The map of transform name prefixes of the job to be replaced to the
-        # corresponding name prefixes of the new job.
-      &quot;a_key&quot;: &quot;A String&quot;,
-    },
-    &quot;environment&quot;: { # Describes the environment in which a Dataflow Job runs. # The environment for the job.
-      &quot;internalExperiments&quot;: { # Experimental settings.
-        &quot;a_key&quot;: &quot;&quot;, # Properties of the object. Contains field @type with type URL.
-      },
-      &quot;workerRegion&quot;: &quot;A String&quot;, # The Compute Engine region
-          # (https://cloud.google.com/compute/docs/regions-zones/regions-zones) in
-          # which worker processing should occur, e.g. &quot;us-west1&quot;. Mutually exclusive
-          # with worker_zone. If neither worker_region nor worker_zone is specified,
-          # default to the control plane&#x27;s region.
-      &quot;serviceKmsKeyName&quot;: &quot;A String&quot;, # If set, contains the Cloud KMS key identifier used to encrypt data
-          # at rest, AKA a Customer Managed Encryption Key (CMEK).
-          #
-          # Format:
-          #   projects/PROJECT_ID/locations/LOCATION/keyRings/KEY_RING/cryptoKeys/KEY
-      &quot;userAgent&quot;: { # A description of the process that generated the request.
-        &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
-      },
-      &quot;workerZone&quot;: &quot;A String&quot;, # The Compute Engine zone
-          # (https://cloud.google.com/compute/docs/regions-zones/regions-zones) in
-          # which worker processing should occur, e.g. &quot;us-west1-a&quot;. Mutually exclusive
-          # with worker_region. If neither worker_region nor worker_zone is specified,
-          # a zone in the control plane&#x27;s region is chosen based on available capacity.
-      &quot;clusterManagerApiService&quot;: &quot;A String&quot;, # The type of cluster manager API to use.  If unknown or
-          # unspecified, the service will attempt to choose a reasonable
-          # default.  This should be in the form of the API service name,
-          # e.g. &quot;compute.googleapis.com&quot;.
-      &quot;tempStoragePrefix&quot;: &quot;A String&quot;, # The prefix of the resources the system should use for temporary
-          # storage.  The system will append the suffix &quot;/temp-{JOBNAME} to
-          # this resource prefix, where {JOBNAME} is the value of the
-          # job_name field.  The resulting bucket and object prefix is used
-          # as the prefix of the resources used to store temporary data
-          # needed during the job execution.  NOTE: This will override the
-          # value in taskrunner_settings.
-          # The supported resource type is:
-          #
-          # Google Cloud Storage:
-          #
-          #   storage.googleapis.com/{bucket}/{object}
-          #   bucket.storage.googleapis.com/{object}
-      &quot;experiments&quot;: [ # The list of experiments to enable.
-        &quot;A String&quot;,
-      ],
-      &quot;version&quot;: { # A structure describing which components and their versions of the service
-          # are required in order to run the job.
-        &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
-      },
-      &quot;serviceAccountEmail&quot;: &quot;A String&quot;, # Identity to run virtual machines as. Defaults to the default account.
-      &quot;sdkPipelineOptions&quot;: { # The Cloud Dataflow SDK pipeline options specified by the user. These
-          # options are passed through the service and are used to recreate the
-          # SDK pipeline options on the worker in a language agnostic and platform
-          # independent way.
-        &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
-      },
-      &quot;flexResourceSchedulingGoal&quot;: &quot;A String&quot;, # Which Flexible Resource Scheduling mode to run in.
-      &quot;workerPools&quot;: [ # The worker pools. At least one &quot;harness&quot; worker pool must be
-          # specified in order for the job to have workers.
-        { # Describes one particular pool of Cloud Dataflow workers to be
-            # instantiated by the Cloud Dataflow service in order to perform the
-            # computations required by a job.  Note that a workflow job may use
-            # multiple pools, in order to match the various computational
-            # requirements of the various stages of the job.
-          &quot;numThreadsPerWorker&quot;: 42, # The number of threads per worker harness. If empty or unspecified, the
-              # service will choose a number of threads (according to the number of cores
-              # on the selected machine type for batch, or 1 by convention for streaming).
-          &quot;numWorkers&quot;: 42, # Number of Google Compute Engine workers in this pool needed to
-              # execute the job.  If zero or unspecified, the service will
-              # attempt to choose a reasonable default.
-          &quot;zone&quot;: &quot;A String&quot;, # Zone to run the worker pools in.  If empty or unspecified, the service
-              # will attempt to choose a reasonable default.
-          &quot;diskSourceImage&quot;: &quot;A String&quot;, # Fully qualified source image for disks.
-          &quot;packages&quot;: [ # Packages to be installed on workers.
-            { # The packages that must be installed in order for a worker to run the
-                # steps of the Cloud Dataflow job that will be assigned to its worker
-                # pool.
-                #
-                # This is the mechanism by which the Cloud Dataflow SDK causes code to
-                # be loaded onto the workers. For example, the Cloud Dataflow Java SDK
-                # might use this to install jars containing the user&#x27;s code and all of the
-                # various dependencies (libraries, data files, etc.) required in order
-                # for that code to run.
-              &quot;name&quot;: &quot;A String&quot;, # The name of the package.
-              &quot;location&quot;: &quot;A String&quot;, # The resource to read the package from. The supported resource type is:
-                  #
-                  # Google Cloud Storage:
-                  #
-                  #   storage.googleapis.com/{bucket}
-                  #   bucket.storage.googleapis.com/
-            },
-          ],
-          &quot;teardownPolicy&quot;: &quot;A String&quot;, # Sets the policy for determining when to turndown worker pool.
-              # Allowed values are: `TEARDOWN_ALWAYS`, `TEARDOWN_ON_SUCCESS`, and
-              # `TEARDOWN_NEVER`.
-              # `TEARDOWN_ALWAYS` means workers are always torn down regardless of whether
-              # the job succeeds. `TEARDOWN_ON_SUCCESS` means workers are torn down
-              # if the job succeeds. `TEARDOWN_NEVER` means the workers are never torn
-              # down.
-              #
-              # If the workers are not torn down by the service, they will
-              # continue to run and use Google Compute Engine VM resources in the
-              # user&#x27;s project until they are explicitly terminated by the user.
-              # Because of this, Google recommends using the `TEARDOWN_ALWAYS`
-              # policy except for small, manually supervised test jobs.
-              #
-              # If unknown or unspecified, the service will attempt to choose a reasonable
-              # default.
-          &quot;onHostMaintenance&quot;: &quot;A String&quot;, # The action to take on host maintenance, as defined by the Google
-              # Compute Engine API.
-          &quot;poolArgs&quot;: { # Extra arguments for this worker pool.
-            &quot;a_key&quot;: &quot;&quot;, # Properties of the object. Contains field @type with type URL.
+      &quot;pipelineDescription&quot;: { # A descriptive representation of submitted pipeline as well as the executed # Preliminary field: The format of this data may change at any time.
+          # A description of the user pipeline and stages through which it is executed.
+          # Created by Cloud Dataflow service.  Only retrieved with
+          # JOB_VIEW_DESCRIPTION or JOB_VIEW_ALL.
+          # form.  This data is provided by the Dataflow service for ease of visualizing
+          # the pipeline and interpreting Dataflow provided metrics.
+        &quot;displayData&quot;: [ # Pipeline level display data.
+          { # Data provided with a pipeline or transform to provide descriptive info.
+            &quot;url&quot;: &quot;A String&quot;, # An optional full URL.
+            &quot;javaClassValue&quot;: &quot;A String&quot;, # Contains value if the data is of java class type.
+            &quot;timestampValue&quot;: &quot;A String&quot;, # Contains value if the data is of timestamp type.
+            &quot;durationValue&quot;: &quot;A String&quot;, # Contains value if the data is of duration type.
+            &quot;label&quot;: &quot;A String&quot;, # An optional label to display in a dax UI for the element.
+            &quot;key&quot;: &quot;A String&quot;, # The key identifying the display data.
+                # This is intended to be used as a label for the display data
+                # when viewed in a dax monitoring system.
+            &quot;namespace&quot;: &quot;A String&quot;, # The namespace for the key. This is usually a class name or programming
+                # language namespace (i.e. python module) which defines the display data.
+                # This allows a dax monitoring system to specially handle the data
+                # and perform custom rendering.
+            &quot;floatValue&quot;: 3.14, # Contains value if the data is of float type.
+            &quot;strValue&quot;: &quot;A String&quot;, # Contains value if the data is of string type.
+            &quot;int64Value&quot;: &quot;A String&quot;, # Contains value if the data is of int64 type.
+            &quot;boolValue&quot;: True or False, # Contains value if the data is of a boolean type.
+            &quot;shortStrValue&quot;: &quot;A String&quot;, # A possible additional shorter value to display.
+                # For example a java_class_name_value of com.mypackage.MyDoFn
+                # will be stored with MyDoFn as the short_str_value and
+                # com.mypackage.MyDoFn as the java_class_name value.
+                # short_str_value can be displayed and java_class_name_value
+                # will be displayed as a tooltip.
           },
-          &quot;diskSizeGb&quot;: 42, # Size of root disk for VMs, in GB.  If zero or unspecified, the service will
-              # attempt to choose a reasonable default.
-          &quot;workerHarnessContainerImage&quot;: &quot;A String&quot;, # Required. Docker container image that executes the Cloud Dataflow worker
-              # harness, residing in Google Container Registry.
-              #
-              # Deprecated for the Fn API path. Use sdk_harness_container_images instead.
-          &quot;diskType&quot;: &quot;A String&quot;, # Type of root disk for VMs.  If empty or unspecified, the service will
-              # attempt to choose a reasonable default.
-          &quot;machineType&quot;: &quot;A String&quot;, # Machine type (e.g. &quot;n1-standard-1&quot;).  If empty or unspecified, the
-              # service will attempt to choose a reasonable default.
-          &quot;kind&quot;: &quot;A String&quot;, # The kind of the worker pool; currently only `harness` and `shuffle`
-              # are supported.
-          &quot;sdkHarnessContainerImages&quot;: [ # Set of SDK harness containers needed to execute this pipeline. This will
-              # only be set in the Fn API path. For non-cross-language pipelines this
-              # should have only one entry. Cross-language pipelines will have two or more
-              # entries.
-            { # Defines a SDK harness container for executing Dataflow pipelines.
-              &quot;containerImage&quot;: &quot;A String&quot;, # A docker container image that resides in Google Container Registry.
-              &quot;useSingleCorePerContainer&quot;: True or False, # If true, recommends the Dataflow service to use only one core per SDK
-                  # container instance with this image. If false (or unset) recommends using
-                  # more than one core per SDK container instance with this image for
-                  # efficiency. Note that Dataflow service may choose to override this property
-                  # if needed.
-            },
-          ],
-          &quot;dataDisks&quot;: [ # Data disks that are used by a VM in this workflow.
-            { # Describes the data disk used by a workflow job.
-              &quot;diskType&quot;: &quot;A String&quot;, # Disk storage type, as defined by Google Compute Engine.  This
-                  # must be a disk type appropriate to the project and zone in which
-                  # the workers will run.  If unknown or unspecified, the service
-                  # will attempt to choose a reasonable default.
-                  #
-                  # For example, the standard persistent disk type is a resource name
-                  # typically ending in &quot;pd-standard&quot;.  If SSD persistent disks are
-                  # available, the resource name typically ends with &quot;pd-ssd&quot;.  The
-                  # actual valid values are defined the Google Compute Engine API,
-                  # not by the Cloud Dataflow API; consult the Google Compute Engine
-                  # documentation for more information about determining the set of
-                  # available disk types for a particular project and zone.
-                  #
-                  # Google Compute Engine Disk types are local to a particular
-                  # project in a particular zone, and so the resource name will
-                  # typically look something like this:
-                  #
-                  # compute.googleapis.com/projects/project-id/zones/zone/diskTypes/pd-standard
-              &quot;sizeGb&quot;: 42, # Size of disk in GB.  If zero or unspecified, the service will
-                  # attempt to choose a reasonable default.
-              &quot;mountPoint&quot;: &quot;A String&quot;, # Directory in a VM where disk is mounted.
-            },
-          ],
-          &quot;subnetwork&quot;: &quot;A String&quot;, # Subnetwork to which VMs will be assigned, if desired.  Expected to be of
-              # the form &quot;regions/REGION/subnetworks/SUBNETWORK&quot;.
-          &quot;ipConfiguration&quot;: &quot;A String&quot;, # Configuration for VM IPs.
-          &quot;taskrunnerSettings&quot;: { # Taskrunner configuration settings. # Settings passed through to Google Compute Engine workers when
-              # using the standard Dataflow task runner.  Users should ignore
-              # this field.
-            &quot;alsologtostderr&quot;: True or False, # Whether to also send taskrunner log info to stderr.
-            &quot;taskGroup&quot;: &quot;A String&quot;, # The UNIX group ID on the worker VM to use for tasks launched by
-                # taskrunner; e.g. &quot;wheel&quot;.
-            &quot;harnessCommand&quot;: &quot;A String&quot;, # The command to launch the worker harness.
-            &quot;logDir&quot;: &quot;A String&quot;, # The directory on the VM to store logs.
-            &quot;oauthScopes&quot;: [ # The OAuth2 scopes to be requested by the taskrunner in order to
-                # access the Cloud Dataflow API.
+        ],
+        &quot;originalPipelineTransform&quot;: [ # Description of each transform in the pipeline and collections between them.
+          { # Description of the type, names/ids, and input/outputs for a transform.
+            &quot;outputCollectionName&quot;: [ # User  names for all collection outputs to this transform.
               &quot;A String&quot;,
             ],
-            &quot;dataflowApiVersion&quot;: &quot;A String&quot;, # The API version of endpoint, e.g. &quot;v1b3&quot;
-            &quot;logUploadLocation&quot;: &quot;A String&quot;, # Indicates where to put logs.  If this is not specified, the logs
-                # will not be uploaded.
-                #
-                # The supported resource type is:
-                #
-                # Google Cloud Storage:
-                #   storage.googleapis.com/{bucket}/{object}
-                #   bucket.storage.googleapis.com/{object}
-            &quot;streamingWorkerMainClass&quot;: &quot;A String&quot;, # The streaming worker main class name.
-            &quot;workflowFileName&quot;: &quot;A String&quot;, # The file to store the workflow in.
-            &quot;languageHint&quot;: &quot;A String&quot;, # The suggested backend language.
-            &quot;commandlinesFileName&quot;: &quot;A String&quot;, # The file to store preprocessing commands in.
-            &quot;baseTaskDir&quot;: &quot;A String&quot;, # The location on the worker for task-specific subdirectories.
-            &quot;tempStoragePrefix&quot;: &quot;A String&quot;, # The prefix of the resources the taskrunner should use for
-                # temporary storage.
-                #
-                # The supported resource type is:
-                #
-                # Google Cloud Storage:
-                #   storage.googleapis.com/{bucket}/{object}
-                #   bucket.storage.googleapis.com/{object}
-            &quot;baseUrl&quot;: &quot;A String&quot;, # The base URL for the taskrunner to use when accessing Google Cloud APIs.
-                #
-                # When workers access Google Cloud APIs, they logically do so via
-                # relative URLs.  If this field is specified, it supplies the base
-                # URL to use for resolving these relative URLs.  The normative
-                # algorithm used is defined by RFC 1808, &quot;Relative Uniform Resource
-                # Locators&quot;.
-                #
-                # If not specified, the default value is &quot;http://www.googleapis.com/&quot;
-            &quot;logToSerialconsole&quot;: True or False, # Whether to send taskrunner log info to Google Compute Engine VM serial
-                # console.
-            &quot;continueOnException&quot;: True or False, # Whether to continue taskrunner if an exception is hit.
-            &quot;parallelWorkerSettings&quot;: { # Provides data to pass through to the worker harness. # The settings to pass to the parallel worker harness.
-              &quot;tempStoragePrefix&quot;: &quot;A String&quot;, # The prefix of the resources the system should use for temporary
-                  # storage.
+            &quot;displayData&quot;: [ # Transform-specific display data.
+              { # Data provided with a pipeline or transform to provide descriptive info.
+                &quot;url&quot;: &quot;A String&quot;, # An optional full URL.
+                &quot;javaClassValue&quot;: &quot;A String&quot;, # Contains value if the data is of java class type.
+                &quot;timestampValue&quot;: &quot;A String&quot;, # Contains value if the data is of timestamp type.
+                &quot;durationValue&quot;: &quot;A String&quot;, # Contains value if the data is of duration type.
+                &quot;label&quot;: &quot;A String&quot;, # An optional label to display in a dax UI for the element.
+                &quot;key&quot;: &quot;A String&quot;, # The key identifying the display data.
+                    # This is intended to be used as a label for the display data
+                    # when viewed in a dax monitoring system.
+                &quot;namespace&quot;: &quot;A String&quot;, # The namespace for the key. This is usually a class name or programming
+                    # language namespace (i.e. python module) which defines the display data.
+                    # This allows a dax monitoring system to specially handle the data
+                    # and perform custom rendering.
+                &quot;floatValue&quot;: 3.14, # Contains value if the data is of float type.
+                &quot;strValue&quot;: &quot;A String&quot;, # Contains value if the data is of string type.
+                &quot;int64Value&quot;: &quot;A String&quot;, # Contains value if the data is of int64 type.
+                &quot;boolValue&quot;: True or False, # Contains value if the data is of a boolean type.
+                &quot;shortStrValue&quot;: &quot;A String&quot;, # A possible additional shorter value to display.
+                    # For example a java_class_name_value of com.mypackage.MyDoFn
+                    # will be stored with MyDoFn as the short_str_value and
+                    # com.mypackage.MyDoFn as the java_class_name value.
+                    # short_str_value can be displayed and java_class_name_value
+                    # will be displayed as a tooltip.
+              },
+            ],
+            &quot;id&quot;: &quot;A String&quot;, # SDK generated id of this transform instance.
+            &quot;inputCollectionName&quot;: [ # User names for all collection inputs to this transform.
+              &quot;A String&quot;,
+            ],
+            &quot;name&quot;: &quot;A String&quot;, # User provided name for this transform instance.
+            &quot;kind&quot;: &quot;A String&quot;, # Type of transform.
+          },
+        ],
+        &quot;executionPipelineStage&quot;: [ # Description of each stage of execution of the pipeline.
+          { # Description of the composing transforms, names/ids, and input/outputs of a
+              # stage of execution.  Some composing transforms and sources may have been
+              # generated by the Dataflow service during execution planning.
+            &quot;componentSource&quot;: [ # Collections produced and consumed by component transforms of this stage.
+              { # Description of an interstitial value between transforms in an execution
+                  # stage.
+                &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this transform; may be user or system generated.
+                &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
+                &quot;originalTransformOrCollection&quot;: &quot;A String&quot;, # User name for the original user transform or collection with which this
+                    # source is most closely associated.
+              },
+            ],
+            &quot;inputSource&quot;: [ # Input sources for this stage.
+              { # Description of an input or output of an execution stage.
+                &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this source; may be user or system generated.
+                &quot;originalTransformOrCollection&quot;: &quot;A String&quot;, # User name for the original user transform or collection with which this
+                    # source is most closely associated.
+                &quot;sizeBytes&quot;: &quot;A String&quot;, # Size of the source, if measurable.
+                &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
+              },
+            ],
+            &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this stage.
+            &quot;componentTransform&quot;: [ # Transforms that comprise this execution stage.
+              { # Description of a transform executed as part of an execution stage.
+                &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
+                &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this transform; may be user or system generated.
+                &quot;originalTransform&quot;: &quot;A String&quot;, # User name for the original user transform with which this transform is
+                    # most closely associated.
+              },
+            ],
+            &quot;id&quot;: &quot;A String&quot;, # Dataflow service generated id for this stage.
+            &quot;outputSource&quot;: [ # Output sources for this stage.
+              { # Description of an input or output of an execution stage.
+                &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this source; may be user or system generated.
+                &quot;originalTransformOrCollection&quot;: &quot;A String&quot;, # User name for the original user transform or collection with which this
+                    # source is most closely associated.
+                &quot;sizeBytes&quot;: &quot;A String&quot;, # Size of the source, if measurable.
+                &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
+              },
+            ],
+            &quot;kind&quot;: &quot;A String&quot;, # Type of tranform this stage is executing.
+          },
+        ],
+      },
+      &quot;labels&quot;: { # User-defined labels for this job.
+          #
+          # The labels map can contain no more than 64 entries.  Entries of the labels
+          # map are UTF8 strings that comply with the following restrictions:
+          #
+          # * Keys must conform to regexp:  \p{Ll}\p{Lo}{0,62}
+          # * Values must conform to regexp:  [\p{Ll}\p{Lo}\p{N}_-]{0,63}
+          # * Both keys and values are additionally constrained to be &lt;= 128 bytes in
+          # size.
+        &quot;a_key&quot;: &quot;A String&quot;,
+      },
+      &quot;projectId&quot;: &quot;A String&quot;, # The ID of the Cloud Platform project that the job belongs to.
+      &quot;environment&quot;: { # Describes the environment in which a Dataflow Job runs. # The environment for the job.
+        &quot;flexResourceSchedulingGoal&quot;: &quot;A String&quot;, # Which Flexible Resource Scheduling mode to run in.
+        &quot;workerRegion&quot;: &quot;A String&quot;, # The Compute Engine region
+            # (https://cloud.google.com/compute/docs/regions-zones/regions-zones) in
+            # which worker processing should occur, e.g. &quot;us-west1&quot;. Mutually exclusive
+            # with worker_zone. If neither worker_region nor worker_zone is specified,
+            # default to the control plane&#x27;s region.
+        &quot;userAgent&quot;: { # A description of the process that generated the request.
+          &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
+        },
+        &quot;serviceAccountEmail&quot;: &quot;A String&quot;, # Identity to run virtual machines as. Defaults to the default account.
+        &quot;version&quot;: { # A structure describing which components and their versions of the service
+            # are required in order to run the job.
+          &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
+        },
+        &quot;serviceKmsKeyName&quot;: &quot;A String&quot;, # If set, contains the Cloud KMS key identifier used to encrypt data
+            # at rest, AKA a Customer Managed Encryption Key (CMEK).
+            #
+            # Format:
+            #   projects/PROJECT_ID/locations/LOCATION/keyRings/KEY_RING/cryptoKeys/KEY
+        &quot;experiments&quot;: [ # The list of experiments to enable.
+          &quot;A String&quot;,
+        ],
+        &quot;workerZone&quot;: &quot;A String&quot;, # The Compute Engine zone
+            # (https://cloud.google.com/compute/docs/regions-zones/regions-zones) in
+            # which worker processing should occur, e.g. &quot;us-west1-a&quot;. Mutually exclusive
+            # with worker_region. If neither worker_region nor worker_zone is specified,
+            # a zone in the control plane&#x27;s region is chosen based on available capacity.
+        &quot;workerPools&quot;: [ # The worker pools. At least one &quot;harness&quot; worker pool must be
+            # specified in order for the job to have workers.
+          { # Describes one particular pool of Cloud Dataflow workers to be
+              # instantiated by the Cloud Dataflow service in order to perform the
+              # computations required by a job.  Note that a workflow job may use
+              # multiple pools, in order to match the various computational
+              # requirements of the various stages of the job.
+            &quot;onHostMaintenance&quot;: &quot;A String&quot;, # The action to take on host maintenance, as defined by the Google
+                # Compute Engine API.
+            &quot;sdkHarnessContainerImages&quot;: [ # Set of SDK harness containers needed to execute this pipeline. This will
+                # only be set in the Fn API path. For non-cross-language pipelines this
+                # should have only one entry. Cross-language pipelines will have two or more
+                # entries.
+              { # Defines a SDK harness container for executing Dataflow pipelines.
+                &quot;containerImage&quot;: &quot;A String&quot;, # A docker container image that resides in Google Container Registry.
+                &quot;useSingleCorePerContainer&quot;: True or False, # If true, recommends the Dataflow service to use only one core per SDK
+                    # container instance with this image. If false (or unset) recommends using
+                    # more than one core per SDK container instance with this image for
+                    # efficiency. Note that Dataflow service may choose to override this property
+                    # if needed.
+              },
+            ],
+            &quot;zone&quot;: &quot;A String&quot;, # Zone to run the worker pools in.  If empty or unspecified, the service
+                # will attempt to choose a reasonable default.
+            &quot;kind&quot;: &quot;A String&quot;, # The kind of the worker pool; currently only `harness` and `shuffle`
+                # are supported.
+            &quot;metadata&quot;: { # Metadata to set on the Google Compute Engine VMs.
+              &quot;a_key&quot;: &quot;A String&quot;,
+            },
+            &quot;diskSourceImage&quot;: &quot;A String&quot;, # Fully qualified source image for disks.
+            &quot;dataDisks&quot;: [ # Data disks that are used by a VM in this workflow.
+              { # Describes the data disk used by a workflow job.
+                &quot;sizeGb&quot;: 42, # Size of disk in GB.  If zero or unspecified, the service will
+                    # attempt to choose a reasonable default.
+                &quot;diskType&quot;: &quot;A String&quot;, # Disk storage type, as defined by Google Compute Engine.  This
+                    # must be a disk type appropriate to the project and zone in which
+                    # the workers will run.  If unknown or unspecified, the service
+                    # will attempt to choose a reasonable default.
+                    #
+                    # For example, the standard persistent disk type is a resource name
+                    # typically ending in &quot;pd-standard&quot;.  If SSD persistent disks are
+                    # available, the resource name typically ends with &quot;pd-ssd&quot;.  The
+                    # actual valid values are defined the Google Compute Engine API,
+                    # not by the Cloud Dataflow API; consult the Google Compute Engine
+                    # documentation for more information about determining the set of
+                    # available disk types for a particular project and zone.
+                    #
+                    # Google Compute Engine Disk types are local to a particular
+                    # project in a particular zone, and so the resource name will
+                    # typically look something like this:
+                    #
+                    # compute.googleapis.com/projects/project-id/zones/zone/diskTypes/pd-standard
+                &quot;mountPoint&quot;: &quot;A String&quot;, # Directory in a VM where disk is mounted.
+              },
+            ],
+            &quot;packages&quot;: [ # Packages to be installed on workers.
+              { # The packages that must be installed in order for a worker to run the
+                  # steps of the Cloud Dataflow job that will be assigned to its worker
+                  # pool.
                   #
-                  # The supported resource type is:
-                  #
-                  # Google Cloud Storage:
-                  #
-                  #   storage.googleapis.com/{bucket}/{object}
-                  #   bucket.storage.googleapis.com/{object}
-              &quot;reportingEnabled&quot;: True or False, # Whether to send work progress updates to the service.
-              &quot;baseUrl&quot;: &quot;A String&quot;, # The base URL for accessing Google Cloud APIs.
+                  # This is the mechanism by which the Cloud Dataflow SDK causes code to
+                  # be loaded onto the workers. For example, the Cloud Dataflow Java SDK
+                  # might use this to install jars containing the user&#x27;s code and all of the
+                  # various dependencies (libraries, data files, etc.) required in order
+                  # for that code to run.
+                &quot;name&quot;: &quot;A String&quot;, # The name of the package.
+                &quot;location&quot;: &quot;A String&quot;, # The resource to read the package from. The supported resource type is:
+                    #
+                    # Google Cloud Storage:
+                    #
+                    #   storage.googleapis.com/{bucket}
+                    #   bucket.storage.googleapis.com/
+              },
+            ],
+            &quot;teardownPolicy&quot;: &quot;A String&quot;, # Sets the policy for determining when to turndown worker pool.
+                # Allowed values are: `TEARDOWN_ALWAYS`, `TEARDOWN_ON_SUCCESS`, and
+                # `TEARDOWN_NEVER`.
+                # `TEARDOWN_ALWAYS` means workers are always torn down regardless of whether
+                # the job succeeds. `TEARDOWN_ON_SUCCESS` means workers are torn down
+                # if the job succeeds. `TEARDOWN_NEVER` means the workers are never torn
+                # down.
+                #
+                # If the workers are not torn down by the service, they will
+                # continue to run and use Google Compute Engine VM resources in the
+                # user&#x27;s project until they are explicitly terminated by the user.
+                # Because of this, Google recommends using the `TEARDOWN_ALWAYS`
+                # policy except for small, manually supervised test jobs.
+                #
+                # If unknown or unspecified, the service will attempt to choose a reasonable
+                # default.
+            &quot;network&quot;: &quot;A String&quot;, # Network to which VMs will be assigned.  If empty or unspecified,
+                # the service will use the network &quot;default&quot;.
+            &quot;ipConfiguration&quot;: &quot;A String&quot;, # Configuration for VM IPs.
+            &quot;diskSizeGb&quot;: 42, # Size of root disk for VMs, in GB.  If zero or unspecified, the service will
+                # attempt to choose a reasonable default.
+            &quot;autoscalingSettings&quot;: { # Settings for WorkerPool autoscaling. # Settings for autoscaling of this WorkerPool.
+              &quot;maxNumWorkers&quot;: 42, # The maximum number of workers to cap scaling at.
+              &quot;algorithm&quot;: &quot;A String&quot;, # The algorithm to use for autoscaling.
+            },
+            &quot;poolArgs&quot;: { # Extra arguments for this worker pool.
+              &quot;a_key&quot;: &quot;&quot;, # Properties of the object. Contains field @type with type URL.
+            },
+            &quot;subnetwork&quot;: &quot;A String&quot;, # Subnetwork to which VMs will be assigned, if desired.  Expected to be of
+                # the form &quot;regions/REGION/subnetworks/SUBNETWORK&quot;.
+            &quot;numWorkers&quot;: 42, # Number of Google Compute Engine workers in this pool needed to
+                # execute the job.  If zero or unspecified, the service will
+                # attempt to choose a reasonable default.
+            &quot;numThreadsPerWorker&quot;: 42, # The number of threads per worker harness. If empty or unspecified, the
+                # service will choose a number of threads (according to the number of cores
+                # on the selected machine type for batch, or 1 by convention for streaming).
+            &quot;workerHarnessContainerImage&quot;: &quot;A String&quot;, # Required. Docker container image that executes the Cloud Dataflow worker
+                # harness, residing in Google Container Registry.
+                #
+                # Deprecated for the Fn API path. Use sdk_harness_container_images instead.
+            &quot;taskrunnerSettings&quot;: { # Taskrunner configuration settings. # Settings passed through to Google Compute Engine workers when
+                # using the standard Dataflow task runner.  Users should ignore
+                # this field.
+              &quot;dataflowApiVersion&quot;: &quot;A String&quot;, # The API version of endpoint, e.g. &quot;v1b3&quot;
+              &quot;oauthScopes&quot;: [ # The OAuth2 scopes to be requested by the taskrunner in order to
+                  # access the Cloud Dataflow API.
+                &quot;A String&quot;,
+              ],
+              &quot;baseUrl&quot;: &quot;A String&quot;, # The base URL for the taskrunner to use when accessing Google Cloud APIs.
                   #
                   # When workers access Google Cloud APIs, they logically do so via
                   # relative URLs.  If this field is specified, it supplies the base
@@ -1610,343 +1652,301 @@
                   # Locators&quot;.
                   #
                   # If not specified, the default value is &quot;http://www.googleapis.com/&quot;
-              &quot;servicePath&quot;: &quot;A String&quot;, # The Cloud Dataflow service path relative to the root URL, for example,
-                  # &quot;dataflow/v1b3/projects&quot;.
-              &quot;shuffleServicePath&quot;: &quot;A String&quot;, # The Shuffle service path relative to the root URL, for example,
-                  # &quot;shuffle/v1beta1&quot;.
-              &quot;workerId&quot;: &quot;A String&quot;, # The ID of the worker running this pipeline.
+              &quot;workflowFileName&quot;: &quot;A String&quot;, # The file to store the workflow in.
+              &quot;logToSerialconsole&quot;: True or False, # Whether to send taskrunner log info to Google Compute Engine VM serial
+                  # console.
+              &quot;baseTaskDir&quot;: &quot;A String&quot;, # The location on the worker for task-specific subdirectories.
+              &quot;taskUser&quot;: &quot;A String&quot;, # The UNIX user ID on the worker VM to use for tasks launched by
+                  # taskrunner; e.g. &quot;root&quot;.
+              &quot;vmId&quot;: &quot;A String&quot;, # The ID string of the VM.
+              &quot;alsologtostderr&quot;: True or False, # Whether to also send taskrunner log info to stderr.
+              &quot;parallelWorkerSettings&quot;: { # Provides data to pass through to the worker harness. # The settings to pass to the parallel worker harness.
+                &quot;shuffleServicePath&quot;: &quot;A String&quot;, # The Shuffle service path relative to the root URL, for example,
+                    # &quot;shuffle/v1beta1&quot;.
+                &quot;tempStoragePrefix&quot;: &quot;A String&quot;, # The prefix of the resources the system should use for temporary
+                    # storage.
+                    #
+                    # The supported resource type is:
+                    #
+                    # Google Cloud Storage:
+                    #
+                    #   storage.googleapis.com/{bucket}/{object}
+                    #   bucket.storage.googleapis.com/{object}
+                &quot;reportingEnabled&quot;: True or False, # Whether to send work progress updates to the service.
+                &quot;servicePath&quot;: &quot;A String&quot;, # The Cloud Dataflow service path relative to the root URL, for example,
+                    # &quot;dataflow/v1b3/projects&quot;.
+                &quot;baseUrl&quot;: &quot;A String&quot;, # The base URL for accessing Google Cloud APIs.
+                    #
+                    # When workers access Google Cloud APIs, they logically do so via
+                    # relative URLs.  If this field is specified, it supplies the base
+                    # URL to use for resolving these relative URLs.  The normative
+                    # algorithm used is defined by RFC 1808, &quot;Relative Uniform Resource
+                    # Locators&quot;.
+                    #
+                    # If not specified, the default value is &quot;http://www.googleapis.com/&quot;
+                &quot;workerId&quot;: &quot;A String&quot;, # The ID of the worker running this pipeline.
+              },
+              &quot;harnessCommand&quot;: &quot;A String&quot;, # The command to launch the worker harness.
+              &quot;logDir&quot;: &quot;A String&quot;, # The directory on the VM to store logs.
+              &quot;streamingWorkerMainClass&quot;: &quot;A String&quot;, # The streaming worker main class name.
+              &quot;languageHint&quot;: &quot;A String&quot;, # The suggested backend language.
+              &quot;taskGroup&quot;: &quot;A String&quot;, # The UNIX group ID on the worker VM to use for tasks launched by
+                  # taskrunner; e.g. &quot;wheel&quot;.
+              &quot;logUploadLocation&quot;: &quot;A String&quot;, # Indicates where to put logs.  If this is not specified, the logs
+                  # will not be uploaded.
+                  #
+                  # The supported resource type is:
+                  #
+                  # Google Cloud Storage:
+                  #   storage.googleapis.com/{bucket}/{object}
+                  #   bucket.storage.googleapis.com/{object}
+              &quot;commandlinesFileName&quot;: &quot;A String&quot;, # The file to store preprocessing commands in.
+              &quot;continueOnException&quot;: True or False, # Whether to continue taskrunner if an exception is hit.
+              &quot;tempStoragePrefix&quot;: &quot;A String&quot;, # The prefix of the resources the taskrunner should use for
+                  # temporary storage.
+                  #
+                  # The supported resource type is:
+                  #
+                  # Google Cloud Storage:
+                  #   storage.googleapis.com/{bucket}/{object}
+                  #   bucket.storage.googleapis.com/{object}
             },
-            &quot;taskUser&quot;: &quot;A String&quot;, # The UNIX user ID on the worker VM to use for tasks launched by
-                # taskrunner; e.g. &quot;root&quot;.
-            &quot;vmId&quot;: &quot;A String&quot;, # The ID string of the VM.
+            &quot;diskType&quot;: &quot;A String&quot;, # Type of root disk for VMs.  If empty or unspecified, the service will
+                # attempt to choose a reasonable default.
+            &quot;defaultPackageSet&quot;: &quot;A String&quot;, # The default package set to install.  This allows the service to
+                # select a default set of packages which are useful to worker
+                # harnesses written in a particular language.
+            &quot;machineType&quot;: &quot;A String&quot;, # Machine type (e.g. &quot;n1-standard-1&quot;).  If empty or unspecified, the
+                # service will attempt to choose a reasonable default.
           },
-          &quot;autoscalingSettings&quot;: { # Settings for WorkerPool autoscaling. # Settings for autoscaling of this WorkerPool.
-            &quot;algorithm&quot;: &quot;A String&quot;, # The algorithm to use for autoscaling.
-            &quot;maxNumWorkers&quot;: 42, # The maximum number of workers to cap scaling at.
-          },
-          &quot;metadata&quot;: { # Metadata to set on the Google Compute Engine VMs.
-            &quot;a_key&quot;: &quot;A String&quot;,
-          },
-          &quot;defaultPackageSet&quot;: &quot;A String&quot;, # The default package set to install.  This allows the service to
-              # select a default set of packages which are useful to worker
-              # harnesses written in a particular language.
-          &quot;network&quot;: &quot;A String&quot;, # Network to which VMs will be assigned.  If empty or unspecified,
-              # the service will use the network &quot;default&quot;.
+        ],
+        &quot;tempStoragePrefix&quot;: &quot;A String&quot;, # The prefix of the resources the system should use for temporary
+            # storage.  The system will append the suffix &quot;/temp-{JOBNAME} to
+            # this resource prefix, where {JOBNAME} is the value of the
+            # job_name field.  The resulting bucket and object prefix is used
+            # as the prefix of the resources used to store temporary data
+            # needed during the job execution.  NOTE: This will override the
+            # value in taskrunner_settings.
+            # The supported resource type is:
+            #
+            # Google Cloud Storage:
+            #
+            #   storage.googleapis.com/{bucket}/{object}
+            #   bucket.storage.googleapis.com/{object}
+        &quot;internalExperiments&quot;: { # Experimental settings.
+          &quot;a_key&quot;: &quot;&quot;, # Properties of the object. Contains field @type with type URL.
         },
-      ],
-      &quot;dataset&quot;: &quot;A String&quot;, # The dataset for the current project where various workflow
-          # related tables are stored.
-          #
-          # The supported resource type is:
-          #
-          # Google BigQuery:
-          #   bigquery.googleapis.com/{dataset}
-    },
-    &quot;stageStates&quot;: [ # This field may be mutated by the Cloud Dataflow service;
-        # callers cannot mutate it.
-      { # A message describing the state of a particular execution stage.
-        &quot;currentStateTime&quot;: &quot;A String&quot;, # The time at which the stage transitioned to this state.
-        &quot;executionStageState&quot;: &quot;A String&quot;, # Executions stage states allow the same set of values as JobState.
-        &quot;executionStageName&quot;: &quot;A String&quot;, # The name of the execution stage.
-      },
-    ],
-    &quot;jobMetadata&quot;: { # Metadata available primarily for filtering jobs. Will be included in the # This field is populated by the Dataflow service to support filtering jobs
-        # by the metadata values provided here. Populated for ListJobs and all GetJob
-        # views SUMMARY and higher.
-        # ListJob response and Job SUMMARY view.
-      &quot;datastoreDetails&quot;: [ # Identification of a Datastore source used in the Dataflow job.
-        { # Metadata for a Datastore connector used by the job.
-          &quot;namespace&quot;: &quot;A String&quot;, # Namespace used in the connection.
-          &quot;projectId&quot;: &quot;A String&quot;, # ProjectId accessed in the connection.
-        },
-      ],
-      &quot;sdkVersion&quot;: { # The version of the SDK used to run the job. # The SDK version used to run the job.
-        &quot;version&quot;: &quot;A String&quot;, # The version of the SDK used to run the job.
-        &quot;sdkSupportStatus&quot;: &quot;A String&quot;, # The support status for this SDK version.
-        &quot;versionDisplayName&quot;: &quot;A String&quot;, # A readable string describing the version of the SDK.
-      },
-      &quot;bigqueryDetails&quot;: [ # Identification of a BigQuery source used in the Dataflow job.
-        { # Metadata for a BigQuery connector used by the job.
-          &quot;table&quot;: &quot;A String&quot;, # Table accessed in the connection.
-          &quot;dataset&quot;: &quot;A String&quot;, # Dataset accessed in the connection.
-          &quot;query&quot;: &quot;A String&quot;, # Query used to access data in the connection.
-          &quot;projectId&quot;: &quot;A String&quot;, # Project accessed in the connection.
-        },
-      ],
-      &quot;fileDetails&quot;: [ # Identification of a File source used in the Dataflow job.
-        { # Metadata for a File connector used by the job.
-          &quot;filePattern&quot;: &quot;A String&quot;, # File Pattern used to access files by the connector.
-        },
-      ],
-      &quot;pubsubDetails&quot;: [ # Identification of a PubSub source used in the Dataflow job.
-        { # Metadata for a PubSub connector used by the job.
-          &quot;topic&quot;: &quot;A String&quot;, # Topic accessed in the connection.
-          &quot;subscription&quot;: &quot;A String&quot;, # Subscription used in the connection.
-        },
-      ],
-      &quot;bigTableDetails&quot;: [ # Identification of a BigTable source used in the Dataflow job.
-        { # Metadata for a BigTable connector used by the job.
-          &quot;projectId&quot;: &quot;A String&quot;, # ProjectId accessed in the connection.
-          &quot;instanceId&quot;: &quot;A String&quot;, # InstanceId accessed in the connection.
-          &quot;tableId&quot;: &quot;A String&quot;, # TableId accessed in the connection.
-        },
-      ],
-      &quot;spannerDetails&quot;: [ # Identification of a Spanner source used in the Dataflow job.
-        { # Metadata for a Spanner connector used by the job.
-          &quot;instanceId&quot;: &quot;A String&quot;, # InstanceId accessed in the connection.
-          &quot;projectId&quot;: &quot;A String&quot;, # ProjectId accessed in the connection.
-          &quot;databaseId&quot;: &quot;A String&quot;, # DatabaseId accessed in the connection.
-        },
-      ],
-    },
-    &quot;type&quot;: &quot;A String&quot;, # The type of Cloud Dataflow job.
-    &quot;projectId&quot;: &quot;A String&quot;, # The ID of the Cloud Platform project that the job belongs to.
-    &quot;createdFromSnapshotId&quot;: &quot;A String&quot;, # If this is specified, the job&#x27;s initial state is populated from the given
-        # snapshot.
-    &quot;pipelineDescription&quot;: { # A descriptive representation of submitted pipeline as well as the executed # Preliminary field: The format of this data may change at any time.
-        # A description of the user pipeline and stages through which it is executed.
-        # Created by Cloud Dataflow service.  Only retrieved with
-        # JOB_VIEW_DESCRIPTION or JOB_VIEW_ALL.
-        # form.  This data is provided by the Dataflow service for ease of visualizing
-        # the pipeline and interpreting Dataflow provided metrics.
-      &quot;executionPipelineStage&quot;: [ # Description of each stage of execution of the pipeline.
-        { # Description of the composing transforms, names/ids, and input/outputs of a
-            # stage of execution.  Some composing transforms and sources may have been
-            # generated by the Dataflow service during execution planning.
-          &quot;outputSource&quot;: [ # Output sources for this stage.
-            { # Description of an input or output of an execution stage.
-              &quot;sizeBytes&quot;: &quot;A String&quot;, # Size of the source, if measurable.
-              &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
-              &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this source; may be user or system generated.
-              &quot;originalTransformOrCollection&quot;: &quot;A String&quot;, # User name for the original user transform or collection with which this
-                  # source is most closely associated.
-            },
-          ],
-          &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this stage.
-          &quot;inputSource&quot;: [ # Input sources for this stage.
-            { # Description of an input or output of an execution stage.
-              &quot;sizeBytes&quot;: &quot;A String&quot;, # Size of the source, if measurable.
-              &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
-              &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this source; may be user or system generated.
-              &quot;originalTransformOrCollection&quot;: &quot;A String&quot;, # User name for the original user transform or collection with which this
-                  # source is most closely associated.
-            },
-          ],
-          &quot;id&quot;: &quot;A String&quot;, # Dataflow service generated id for this stage.
-          &quot;componentTransform&quot;: [ # Transforms that comprise this execution stage.
-            { # Description of a transform executed as part of an execution stage.
-              &quot;originalTransform&quot;: &quot;A String&quot;, # User name for the original user transform with which this transform is
-                  # most closely associated.
-              &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
-              &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this transform; may be user or system generated.
-            },
-          ],
-          &quot;componentSource&quot;: [ # Collections produced and consumed by component transforms of this stage.
-            { # Description of an interstitial value between transforms in an execution
-                # stage.
-              &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
-              &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this transform; may be user or system generated.
-              &quot;originalTransformOrCollection&quot;: &quot;A String&quot;, # User name for the original user transform or collection with which this
-                  # source is most closely associated.
-            },
-          ],
-          &quot;kind&quot;: &quot;A String&quot;, # Type of tranform this stage is executing.
-        },
-      ],
-      &quot;originalPipelineTransform&quot;: [ # Description of each transform in the pipeline and collections between them.
-        { # Description of the type, names/ids, and input/outputs for a transform.
-          &quot;kind&quot;: &quot;A String&quot;, # Type of transform.
-          &quot;inputCollectionName&quot;: [ # User names for all collection inputs to this transform.
-            &quot;A String&quot;,
-          ],
-          &quot;name&quot;: &quot;A String&quot;, # User provided name for this transform instance.
-          &quot;id&quot;: &quot;A String&quot;, # SDK generated id of this transform instance.
-          &quot;displayData&quot;: [ # Transform-specific display data.
-            { # Data provided with a pipeline or transform to provide descriptive info.
-              &quot;durationValue&quot;: &quot;A String&quot;, # Contains value if the data is of duration type.
-              &quot;int64Value&quot;: &quot;A String&quot;, # Contains value if the data is of int64 type.
-              &quot;namespace&quot;: &quot;A String&quot;, # The namespace for the key. This is usually a class name or programming
-                  # language namespace (i.e. python module) which defines the display data.
-                  # This allows a dax monitoring system to specially handle the data
-                  # and perform custom rendering.
-              &quot;floatValue&quot;: 3.14, # Contains value if the data is of float type.
-              &quot;key&quot;: &quot;A String&quot;, # The key identifying the display data.
-                  # This is intended to be used as a label for the display data
-                  # when viewed in a dax monitoring system.
-              &quot;shortStrValue&quot;: &quot;A String&quot;, # A possible additional shorter value to display.
-                  # For example a java_class_name_value of com.mypackage.MyDoFn
-                  # will be stored with MyDoFn as the short_str_value and
-                  # com.mypackage.MyDoFn as the java_class_name value.
-                  # short_str_value can be displayed and java_class_name_value
-                  # will be displayed as a tooltip.
-              &quot;url&quot;: &quot;A String&quot;, # An optional full URL.
-              &quot;label&quot;: &quot;A String&quot;, # An optional label to display in a dax UI for the element.
-              &quot;timestampValue&quot;: &quot;A String&quot;, # Contains value if the data is of timestamp type.
-              &quot;boolValue&quot;: True or False, # Contains value if the data is of a boolean type.
-              &quot;javaClassValue&quot;: &quot;A String&quot;, # Contains value if the data is of java class type.
-              &quot;strValue&quot;: &quot;A String&quot;, # Contains value if the data is of string type.
-            },
-          ],
-          &quot;outputCollectionName&quot;: [ # User  names for all collection outputs to this transform.
-            &quot;A String&quot;,
-          ],
-        },
-      ],
-      &quot;displayData&quot;: [ # Pipeline level display data.
-        { # Data provided with a pipeline or transform to provide descriptive info.
-          &quot;durationValue&quot;: &quot;A String&quot;, # Contains value if the data is of duration type.
-          &quot;int64Value&quot;: &quot;A String&quot;, # Contains value if the data is of int64 type.
-          &quot;namespace&quot;: &quot;A String&quot;, # The namespace for the key. This is usually a class name or programming
-              # language namespace (i.e. python module) which defines the display data.
-              # This allows a dax monitoring system to specially handle the data
-              # and perform custom rendering.
-          &quot;floatValue&quot;: 3.14, # Contains value if the data is of float type.
-          &quot;key&quot;: &quot;A String&quot;, # The key identifying the display data.
-              # This is intended to be used as a label for the display data
-              # when viewed in a dax monitoring system.
-          &quot;shortStrValue&quot;: &quot;A String&quot;, # A possible additional shorter value to display.
-              # For example a java_class_name_value of com.mypackage.MyDoFn
-              # will be stored with MyDoFn as the short_str_value and
-              # com.mypackage.MyDoFn as the java_class_name value.
-              # short_str_value can be displayed and java_class_name_value
-              # will be displayed as a tooltip.
-          &quot;url&quot;: &quot;A String&quot;, # An optional full URL.
-          &quot;label&quot;: &quot;A String&quot;, # An optional label to display in a dax UI for the element.
-          &quot;timestampValue&quot;: &quot;A String&quot;, # Contains value if the data is of timestamp type.
-          &quot;boolValue&quot;: True or False, # Contains value if the data is of a boolean type.
-          &quot;javaClassValue&quot;: &quot;A String&quot;, # Contains value if the data is of java class type.
-          &quot;strValue&quot;: &quot;A String&quot;, # Contains value if the data is of string type.
-        },
-      ],
-    },
-    &quot;replaceJobId&quot;: &quot;A String&quot;, # If this job is an update of an existing job, this field is the job ID
-        # of the job it replaced.
-        #
-        # When sending a `CreateJobRequest`, you can update a job by specifying it
-        # here. The job named here is stopped, and its intermediate state is
-        # transferred to this job.
-    &quot;tempFiles&quot;: [ # A set of files the system should be aware of that are used
-        # for temporary storage. These temporary files will be
-        # removed on job completion.
-        # No duplicates are allowed.
-        # No file patterns are supported.
-        #
-        # The supported files are:
-        #
-        # Google Cloud Storage:
-        #
-        #    storage.googleapis.com/{bucket}/{object}
-        #    bucket.storage.googleapis.com/{object}
-      &quot;A String&quot;,
-    ],
-    &quot;name&quot;: &quot;A String&quot;, # The user-specified Cloud Dataflow job name.
-        #
-        # Only one Job with a given name may exist in a project at any
-        # given time. If a caller attempts to create a Job with the same
-        # name as an already-existing Job, the attempt returns the
-        # existing Job.
-        #
-        # The name must match the regular expression
-        # `[a-z]([-a-z0-9]{0,38}[a-z0-9])?`
-    &quot;steps&quot;: [ # Exactly one of step or steps_location should be specified.
-        #
-        # The top-level steps that constitute the entire job.
-      { # Defines a particular step within a Cloud Dataflow job.
-          #
-          # A job consists of multiple steps, each of which performs some
-          # specific operation as part of the overall job.  Data is typically
-          # passed from one step to another as part of the job.
-          #
-          # Here&#x27;s an example of a sequence of steps which together implement a
-          # Map-Reduce job:
-          #
-          #   * Read a collection of data from some source, parsing the
-          #     collection&#x27;s elements.
-          #
-          #   * Validate the elements.
-          #
-          #   * Apply a user-defined function to map each element to some value
-          #     and extract an element-specific key value.
-          #
-          #   * Group elements with the same key into a single element with
-          #     that key, transforming a multiply-keyed collection into a
-          #     uniquely-keyed collection.
-          #
-          #   * Write the elements out to some data sink.
-          #
-          # Note that the Cloud Dataflow service may be used to run many different
-          # types of jobs, not just Map-Reduce.
-        &quot;name&quot;: &quot;A String&quot;, # The name that identifies the step. This must be unique for each
-            # step with respect to all other steps in the Cloud Dataflow job.
-        &quot;kind&quot;: &quot;A String&quot;, # The kind of step in the Cloud Dataflow job.
-        &quot;properties&quot;: { # Named properties associated with the step. Each kind of
-            # predefined step has its own required set of properties.
-            # Must be provided on Create.  Only retrieved with JOB_VIEW_ALL.
+        &quot;sdkPipelineOptions&quot;: { # The Cloud Dataflow SDK pipeline options specified by the user. These
+            # options are passed through the service and are used to recreate the
+            # SDK pipeline options on the worker in a language agnostic and platform
+            # independent way.
           &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
         },
+        &quot;dataset&quot;: &quot;A String&quot;, # The dataset for the current project where various workflow
+            # related tables are stored.
+            #
+            # The supported resource type is:
+            #
+            # Google BigQuery:
+            #   bigquery.googleapis.com/{dataset}
+        &quot;clusterManagerApiService&quot;: &quot;A String&quot;, # The type of cluster manager API to use.  If unknown or
+            # unspecified, the service will attempt to choose a reasonable
+            # default.  This should be in the form of the API service name,
+            # e.g. &quot;compute.googleapis.com&quot;.
       },
-    ],
-    &quot;replacedByJobId&quot;: &quot;A String&quot;, # If another job is an update of this job (and thus, this job is in
-        # `JOB_STATE_UPDATED`), this field contains the ID of that job.
-    &quot;executionInfo&quot;: { # Additional information about how a Cloud Dataflow job will be executed that # Deprecated.
-        # isn&#x27;t contained in the submitted job.
-      &quot;stages&quot;: { # A mapping from each stage to the information about that stage.
-        &quot;a_key&quot;: { # Contains information about how a particular
-            # google.dataflow.v1beta3.Step will be executed.
-          &quot;stepName&quot;: [ # The steps associated with the execution stage.
-              # Note that stages may have several steps, and that a given step
-              # might be run by more than one stage.
-            &quot;A String&quot;,
-          ],
+      &quot;stepsLocation&quot;: &quot;A String&quot;, # The GCS location where the steps are stored.
+      &quot;steps&quot;: [ # Exactly one of step or steps_location should be specified.
+          #
+          # The top-level steps that constitute the entire job.
+        { # Defines a particular step within a Cloud Dataflow job.
+            #
+            # A job consists of multiple steps, each of which performs some
+            # specific operation as part of the overall job.  Data is typically
+            # passed from one step to another as part of the job.
+            #
+            # Here&#x27;s an example of a sequence of steps which together implement a
+            # Map-Reduce job:
+            #
+            #   * Read a collection of data from some source, parsing the
+            #     collection&#x27;s elements.
+            #
+            #   * Validate the elements.
+            #
+            #   * Apply a user-defined function to map each element to some value
+            #     and extract an element-specific key value.
+            #
+            #   * Group elements with the same key into a single element with
+            #     that key, transforming a multiply-keyed collection into a
+            #     uniquely-keyed collection.
+            #
+            #   * Write the elements out to some data sink.
+            #
+            # Note that the Cloud Dataflow service may be used to run many different
+            # types of jobs, not just Map-Reduce.
+          &quot;kind&quot;: &quot;A String&quot;, # The kind of step in the Cloud Dataflow job.
+          &quot;properties&quot;: { # Named properties associated with the step. Each kind of
+              # predefined step has its own required set of properties.
+              # Must be provided on Create.  Only retrieved with JOB_VIEW_ALL.
+            &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
+          },
+          &quot;name&quot;: &quot;A String&quot;, # The name that identifies the step. This must be unique for each
+              # step with respect to all other steps in the Cloud Dataflow job.
+        },
+      ],
+      &quot;stageStates&quot;: [ # This field may be mutated by the Cloud Dataflow service;
+          # callers cannot mutate it.
+        { # A message describing the state of a particular execution stage.
+          &quot;executionStageState&quot;: &quot;A String&quot;, # Executions stage states allow the same set of values as JobState.
+          &quot;executionStageName&quot;: &quot;A String&quot;, # The name of the execution stage.
+          &quot;currentStateTime&quot;: &quot;A String&quot;, # The time at which the stage transitioned to this state.
+        },
+      ],
+      &quot;replacedByJobId&quot;: &quot;A String&quot;, # If another job is an update of this job (and thus, this job is in
+          # `JOB_STATE_UPDATED`), this field contains the ID of that job.
+      &quot;jobMetadata&quot;: { # Metadata available primarily for filtering jobs. Will be included in the # This field is populated by the Dataflow service to support filtering jobs
+          # by the metadata values provided here. Populated for ListJobs and all GetJob
+          # views SUMMARY and higher.
+          # ListJob response and Job SUMMARY view.
+        &quot;sdkVersion&quot;: { # The version of the SDK used to run the job. # The SDK version used to run the job.
+          &quot;sdkSupportStatus&quot;: &quot;A String&quot;, # The support status for this SDK version.
+          &quot;versionDisplayName&quot;: &quot;A String&quot;, # A readable string describing the version of the SDK.
+          &quot;version&quot;: &quot;A String&quot;, # The version of the SDK used to run the job.
+        },
+        &quot;bigTableDetails&quot;: [ # Identification of a BigTable source used in the Dataflow job.
+          { # Metadata for a BigTable connector used by the job.
+            &quot;instanceId&quot;: &quot;A String&quot;, # InstanceId accessed in the connection.
+            &quot;tableId&quot;: &quot;A String&quot;, # TableId accessed in the connection.
+            &quot;projectId&quot;: &quot;A String&quot;, # ProjectId accessed in the connection.
+          },
+        ],
+        &quot;pubsubDetails&quot;: [ # Identification of a PubSub source used in the Dataflow job.
+          { # Metadata for a PubSub connector used by the job.
+            &quot;subscription&quot;: &quot;A String&quot;, # Subscription used in the connection.
+            &quot;topic&quot;: &quot;A String&quot;, # Topic accessed in the connection.
+          },
+        ],
+        &quot;bigqueryDetails&quot;: [ # Identification of a BigQuery source used in the Dataflow job.
+          { # Metadata for a BigQuery connector used by the job.
+            &quot;dataset&quot;: &quot;A String&quot;, # Dataset accessed in the connection.
+            &quot;projectId&quot;: &quot;A String&quot;, # Project accessed in the connection.
+            &quot;query&quot;: &quot;A String&quot;, # Query used to access data in the connection.
+            &quot;table&quot;: &quot;A String&quot;, # Table accessed in the connection.
+          },
+        ],
+        &quot;fileDetails&quot;: [ # Identification of a File source used in the Dataflow job.
+          { # Metadata for a File connector used by the job.
+            &quot;filePattern&quot;: &quot;A String&quot;, # File Pattern used to access files by the connector.
+          },
+        ],
+        &quot;datastoreDetails&quot;: [ # Identification of a Datastore source used in the Dataflow job.
+          { # Metadata for a Datastore connector used by the job.
+            &quot;namespace&quot;: &quot;A String&quot;, # Namespace used in the connection.
+            &quot;projectId&quot;: &quot;A String&quot;, # ProjectId accessed in the connection.
+          },
+        ],
+        &quot;spannerDetails&quot;: [ # Identification of a Spanner source used in the Dataflow job.
+          { # Metadata for a Spanner connector used by the job.
+            &quot;instanceId&quot;: &quot;A String&quot;, # InstanceId accessed in the connection.
+            &quot;databaseId&quot;: &quot;A String&quot;, # DatabaseId accessed in the connection.
+            &quot;projectId&quot;: &quot;A String&quot;, # ProjectId accessed in the connection.
+          },
+        ],
+      },
+      &quot;location&quot;: &quot;A String&quot;, # The [regional endpoint]
+          # (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that
+          # contains this job.
+      &quot;transformNameMapping&quot;: { # The map of transform name prefixes of the job to be replaced to the
+          # corresponding name prefixes of the new job.
+        &quot;a_key&quot;: &quot;A String&quot;,
+      },
+      &quot;startTime&quot;: &quot;A String&quot;, # The timestamp when the job was started (transitioned to JOB_STATE_PENDING).
+          # Flexible resource scheduling jobs are started with some delay after job
+          # creation, so start_time is unset before start and is updated when the
+          # job is started by the Cloud Dataflow service. For other jobs, start_time
+          # always equals to create_time and is immutable and set by the Cloud Dataflow
+          # service.
+      &quot;clientRequestId&quot;: &quot;A String&quot;, # The client&#x27;s unique identifier of the job, re-used across retried attempts.
+          # If this field is set, the service will ensure its uniqueness.
+          # The request to create a job will fail if the service has knowledge of a
+          # previously submitted job with the same client&#x27;s ID and job name.
+          # The caller may use this field to ensure idempotence of job
+          # creation across retried attempts to create a job.
+          # By default, the field is empty and, in that case, the service ignores it.
+      &quot;executionInfo&quot;: { # Additional information about how a Cloud Dataflow job will be executed that # Deprecated.
+          # isn&#x27;t contained in the submitted job.
+        &quot;stages&quot;: { # A mapping from each stage to the information about that stage.
+          &quot;a_key&quot;: { # Contains information about how a particular
+              # google.dataflow.v1beta3.Step will be executed.
+            &quot;stepName&quot;: [ # The steps associated with the execution stage.
+                # Note that stages may have several steps, and that a given step
+                # might be run by more than one stage.
+              &quot;A String&quot;,
+            ],
+          },
         },
       },
-    },
-    &quot;currentState&quot;: &quot;A String&quot;, # The current state of the job.
-        #
-        # Jobs are created in the `JOB_STATE_STOPPED` state unless otherwise
-        # specified.
-        #
-        # A job in the `JOB_STATE_RUNNING` state may asynchronously enter a
-        # terminal state. After a job has reached a terminal state, no
-        # further state updates may be made.
-        #
-        # This field may be mutated by the Cloud Dataflow service;
-        # callers cannot mutate it.
-    &quot;location&quot;: &quot;A String&quot;, # The [regional endpoint]
-        # (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that
-        # contains this job.
-    &quot;startTime&quot;: &quot;A String&quot;, # The timestamp when the job was started (transitioned to JOB_STATE_PENDING).
-        # Flexible resource scheduling jobs are started with some delay after job
-        # creation, so start_time is unset before start and is updated when the
-        # job is started by the Cloud Dataflow service. For other jobs, start_time
-        # always equals to create_time and is immutable and set by the Cloud Dataflow
-        # service.
-    &quot;stepsLocation&quot;: &quot;A String&quot;, # The GCS location where the steps are stored.
-    &quot;labels&quot;: { # User-defined labels for this job.
-        #
-        # The labels map can contain no more than 64 entries.  Entries of the labels
-        # map are UTF8 strings that comply with the following restrictions:
-        #
-        # * Keys must conform to regexp:  \p{Ll}\p{Lo}{0,62}
-        # * Values must conform to regexp:  [\p{Ll}\p{Lo}\p{N}_-]{0,63}
-        # * Both keys and values are additionally constrained to be &lt;= 128 bytes in
-        # size.
-      &quot;a_key&quot;: &quot;A String&quot;,
-    },
-    &quot;createTime&quot;: &quot;A String&quot;, # The timestamp when the job was initially created. Immutable and set by the
-        # Cloud Dataflow service.
-    &quot;requestedState&quot;: &quot;A String&quot;, # The job&#x27;s requested state.
-        #
-        # `UpdateJob` may be used to switch between the `JOB_STATE_STOPPED` and
-        # `JOB_STATE_RUNNING` states, by setting requested_state.  `UpdateJob` may
-        # also be used to directly set a job&#x27;s requested state to
-        # `JOB_STATE_CANCELLED` or `JOB_STATE_DONE`, irrevocably terminating the
-        # job if it has not already reached a terminal state.
-  }</pre>
+      &quot;type&quot;: &quot;A String&quot;, # The type of Cloud Dataflow job.
+      &quot;createTime&quot;: &quot;A String&quot;, # The timestamp when the job was initially created. Immutable and set by the
+          # Cloud Dataflow service.
+      &quot;tempFiles&quot;: [ # A set of files the system should be aware of that are used
+          # for temporary storage. These temporary files will be
+          # removed on job completion.
+          # No duplicates are allowed.
+          # No file patterns are supported.
+          #
+          # The supported files are:
+          #
+          # Google Cloud Storage:
+          #
+          #    storage.googleapis.com/{bucket}/{object}
+          #    bucket.storage.googleapis.com/{object}
+        &quot;A String&quot;,
+      ],
+      &quot;id&quot;: &quot;A String&quot;, # The unique ID of this job.
+          #
+          # This field is set by the Cloud Dataflow service when the Job is
+          # created, and is immutable for the life of the job.
+      &quot;requestedState&quot;: &quot;A String&quot;, # The job&#x27;s requested state.
+          #
+          # `UpdateJob` may be used to switch between the `JOB_STATE_STOPPED` and
+          # `JOB_STATE_RUNNING` states, by setting requested_state.  `UpdateJob` may
+          # also be used to directly set a job&#x27;s requested state to
+          # `JOB_STATE_CANCELLED` or `JOB_STATE_DONE`, irrevocably terminating the
+          # job if it has not already reached a terminal state.
+      &quot;replaceJobId&quot;: &quot;A String&quot;, # If this job is an update of an existing job, this field is the job ID
+          # of the job it replaced.
+          #
+          # When sending a `CreateJobRequest`, you can update a job by specifying it
+          # here. The job named here is stopped, and its intermediate state is
+          # transferred to this job.
+      &quot;createdFromSnapshotId&quot;: &quot;A String&quot;, # If this is specified, the job&#x27;s initial state is populated from the given
+          # snapshot.
+      &quot;currentState&quot;: &quot;A String&quot;, # The current state of the job.
+          #
+          # Jobs are created in the `JOB_STATE_STOPPED` state unless otherwise
+          # specified.
+          #
+          # A job in the `JOB_STATE_RUNNING` state may asynchronously enter a
+          # terminal state. After a job has reached a terminal state, no
+          # further state updates may be made.
+          #
+          # This field may be mutated by the Cloud Dataflow service;
+          # callers cannot mutate it.
+      &quot;name&quot;: &quot;A String&quot;, # The user-specified Cloud Dataflow job name.
+          #
+          # Only one Job with a given name may exist in a project at any
+          # given time. If a caller attempts to create a Job with the same
+          # name as an already-existing Job, the attempt returns the
+          # existing Job.
+          #
+          # The name must match the regular expression
+          # `[a-z]([-a-z0-9]{0,38}[a-z0-9])?`
+      &quot;currentStateTime&quot;: &quot;A String&quot;, # The timestamp associated with the current state.
+    }</pre>
 </div>
 
 <div class="method">
-    <code class="details" id="get">get(projectId, jobId, view=None, location=None, x__xgafv=None)</code>
+    <code class="details" id="get">get(projectId, jobId, location=None, view=None, x__xgafv=None)</code>
   <pre>Gets the state of the specified Cloud Dataflow job.
 
 To get the state of a job, we recommend using `projects.locations.jobs.get`
@@ -1958,10 +1958,10 @@
 Args:
   projectId: string, The ID of the Cloud Platform project that the job belongs to. (required)
   jobId: string, The job ID. (required)
-  view: string, The level of information requested in response.
   location: string, The [regional endpoint]
 (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that
 contains this job.
+  view: string, The level of information requested in response.
   x__xgafv: string, V1 error format.
     Allowed values
       1 - v1 error format
@@ -1971,243 +1971,285 @@
   An object of the form:
 
     { # Defines a job to be run by the Cloud Dataflow service.
-    &quot;clientRequestId&quot;: &quot;A String&quot;, # The client&#x27;s unique identifier of the job, re-used across retried attempts.
-        # If this field is set, the service will ensure its uniqueness.
-        # The request to create a job will fail if the service has knowledge of a
-        # previously submitted job with the same client&#x27;s ID and job name.
-        # The caller may use this field to ensure idempotence of job
-        # creation across retried attempts to create a job.
-        # By default, the field is empty and, in that case, the service ignores it.
-    &quot;id&quot;: &quot;A String&quot;, # The unique ID of this job.
-        #
-        # This field is set by the Cloud Dataflow service when the Job is
-        # created, and is immutable for the life of the job.
-    &quot;currentStateTime&quot;: &quot;A String&quot;, # The timestamp associated with the current state.
-    &quot;transformNameMapping&quot;: { # The map of transform name prefixes of the job to be replaced to the
-        # corresponding name prefixes of the new job.
-      &quot;a_key&quot;: &quot;A String&quot;,
-    },
-    &quot;environment&quot;: { # Describes the environment in which a Dataflow Job runs. # The environment for the job.
-      &quot;internalExperiments&quot;: { # Experimental settings.
-        &quot;a_key&quot;: &quot;&quot;, # Properties of the object. Contains field @type with type URL.
-      },
-      &quot;workerRegion&quot;: &quot;A String&quot;, # The Compute Engine region
-          # (https://cloud.google.com/compute/docs/regions-zones/regions-zones) in
-          # which worker processing should occur, e.g. &quot;us-west1&quot;. Mutually exclusive
-          # with worker_zone. If neither worker_region nor worker_zone is specified,
-          # default to the control plane&#x27;s region.
-      &quot;serviceKmsKeyName&quot;: &quot;A String&quot;, # If set, contains the Cloud KMS key identifier used to encrypt data
-          # at rest, AKA a Customer Managed Encryption Key (CMEK).
-          #
-          # Format:
-          #   projects/PROJECT_ID/locations/LOCATION/keyRings/KEY_RING/cryptoKeys/KEY
-      &quot;userAgent&quot;: { # A description of the process that generated the request.
-        &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
-      },
-      &quot;workerZone&quot;: &quot;A String&quot;, # The Compute Engine zone
-          # (https://cloud.google.com/compute/docs/regions-zones/regions-zones) in
-          # which worker processing should occur, e.g. &quot;us-west1-a&quot;. Mutually exclusive
-          # with worker_region. If neither worker_region nor worker_zone is specified,
-          # a zone in the control plane&#x27;s region is chosen based on available capacity.
-      &quot;clusterManagerApiService&quot;: &quot;A String&quot;, # The type of cluster manager API to use.  If unknown or
-          # unspecified, the service will attempt to choose a reasonable
-          # default.  This should be in the form of the API service name,
-          # e.g. &quot;compute.googleapis.com&quot;.
-      &quot;tempStoragePrefix&quot;: &quot;A String&quot;, # The prefix of the resources the system should use for temporary
-          # storage.  The system will append the suffix &quot;/temp-{JOBNAME} to
-          # this resource prefix, where {JOBNAME} is the value of the
-          # job_name field.  The resulting bucket and object prefix is used
-          # as the prefix of the resources used to store temporary data
-          # needed during the job execution.  NOTE: This will override the
-          # value in taskrunner_settings.
-          # The supported resource type is:
-          #
-          # Google Cloud Storage:
-          #
-          #   storage.googleapis.com/{bucket}/{object}
-          #   bucket.storage.googleapis.com/{object}
-      &quot;experiments&quot;: [ # The list of experiments to enable.
-        &quot;A String&quot;,
-      ],
-      &quot;version&quot;: { # A structure describing which components and their versions of the service
-          # are required in order to run the job.
-        &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
-      },
-      &quot;serviceAccountEmail&quot;: &quot;A String&quot;, # Identity to run virtual machines as. Defaults to the default account.
-      &quot;sdkPipelineOptions&quot;: { # The Cloud Dataflow SDK pipeline options specified by the user. These
-          # options are passed through the service and are used to recreate the
-          # SDK pipeline options on the worker in a language agnostic and platform
-          # independent way.
-        &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
-      },
-      &quot;flexResourceSchedulingGoal&quot;: &quot;A String&quot;, # Which Flexible Resource Scheduling mode to run in.
-      &quot;workerPools&quot;: [ # The worker pools. At least one &quot;harness&quot; worker pool must be
-          # specified in order for the job to have workers.
-        { # Describes one particular pool of Cloud Dataflow workers to be
-            # instantiated by the Cloud Dataflow service in order to perform the
-            # computations required by a job.  Note that a workflow job may use
-            # multiple pools, in order to match the various computational
-            # requirements of the various stages of the job.
-          &quot;numThreadsPerWorker&quot;: 42, # The number of threads per worker harness. If empty or unspecified, the
-              # service will choose a number of threads (according to the number of cores
-              # on the selected machine type for batch, or 1 by convention for streaming).
-          &quot;numWorkers&quot;: 42, # Number of Google Compute Engine workers in this pool needed to
-              # execute the job.  If zero or unspecified, the service will
-              # attempt to choose a reasonable default.
-          &quot;zone&quot;: &quot;A String&quot;, # Zone to run the worker pools in.  If empty or unspecified, the service
-              # will attempt to choose a reasonable default.
-          &quot;diskSourceImage&quot;: &quot;A String&quot;, # Fully qualified source image for disks.
-          &quot;packages&quot;: [ # Packages to be installed on workers.
-            { # The packages that must be installed in order for a worker to run the
-                # steps of the Cloud Dataflow job that will be assigned to its worker
-                # pool.
-                #
-                # This is the mechanism by which the Cloud Dataflow SDK causes code to
-                # be loaded onto the workers. For example, the Cloud Dataflow Java SDK
-                # might use this to install jars containing the user&#x27;s code and all of the
-                # various dependencies (libraries, data files, etc.) required in order
-                # for that code to run.
-              &quot;name&quot;: &quot;A String&quot;, # The name of the package.
-              &quot;location&quot;: &quot;A String&quot;, # The resource to read the package from. The supported resource type is:
-                  #
-                  # Google Cloud Storage:
-                  #
-                  #   storage.googleapis.com/{bucket}
-                  #   bucket.storage.googleapis.com/
-            },
-          ],
-          &quot;teardownPolicy&quot;: &quot;A String&quot;, # Sets the policy for determining when to turndown worker pool.
-              # Allowed values are: `TEARDOWN_ALWAYS`, `TEARDOWN_ON_SUCCESS`, and
-              # `TEARDOWN_NEVER`.
-              # `TEARDOWN_ALWAYS` means workers are always torn down regardless of whether
-              # the job succeeds. `TEARDOWN_ON_SUCCESS` means workers are torn down
-              # if the job succeeds. `TEARDOWN_NEVER` means the workers are never torn
-              # down.
-              #
-              # If the workers are not torn down by the service, they will
-              # continue to run and use Google Compute Engine VM resources in the
-              # user&#x27;s project until they are explicitly terminated by the user.
-              # Because of this, Google recommends using the `TEARDOWN_ALWAYS`
-              # policy except for small, manually supervised test jobs.
-              #
-              # If unknown or unspecified, the service will attempt to choose a reasonable
-              # default.
-          &quot;onHostMaintenance&quot;: &quot;A String&quot;, # The action to take on host maintenance, as defined by the Google
-              # Compute Engine API.
-          &quot;poolArgs&quot;: { # Extra arguments for this worker pool.
-            &quot;a_key&quot;: &quot;&quot;, # Properties of the object. Contains field @type with type URL.
+      &quot;pipelineDescription&quot;: { # A descriptive representation of submitted pipeline as well as the executed # Preliminary field: The format of this data may change at any time.
+          # A description of the user pipeline and stages through which it is executed.
+          # Created by Cloud Dataflow service.  Only retrieved with
+          # JOB_VIEW_DESCRIPTION or JOB_VIEW_ALL.
+          # form.  This data is provided by the Dataflow service for ease of visualizing
+          # the pipeline and interpreting Dataflow provided metrics.
+        &quot;displayData&quot;: [ # Pipeline level display data.
+          { # Data provided with a pipeline or transform to provide descriptive info.
+            &quot;url&quot;: &quot;A String&quot;, # An optional full URL.
+            &quot;javaClassValue&quot;: &quot;A String&quot;, # Contains value if the data is of java class type.
+            &quot;timestampValue&quot;: &quot;A String&quot;, # Contains value if the data is of timestamp type.
+            &quot;durationValue&quot;: &quot;A String&quot;, # Contains value if the data is of duration type.
+            &quot;label&quot;: &quot;A String&quot;, # An optional label to display in a dax UI for the element.
+            &quot;key&quot;: &quot;A String&quot;, # The key identifying the display data.
+                # This is intended to be used as a label for the display data
+                # when viewed in a dax monitoring system.
+            &quot;namespace&quot;: &quot;A String&quot;, # The namespace for the key. This is usually a class name or programming
+                # language namespace (i.e. python module) which defines the display data.
+                # This allows a dax monitoring system to specially handle the data
+                # and perform custom rendering.
+            &quot;floatValue&quot;: 3.14, # Contains value if the data is of float type.
+            &quot;strValue&quot;: &quot;A String&quot;, # Contains value if the data is of string type.
+            &quot;int64Value&quot;: &quot;A String&quot;, # Contains value if the data is of int64 type.
+            &quot;boolValue&quot;: True or False, # Contains value if the data is of a boolean type.
+            &quot;shortStrValue&quot;: &quot;A String&quot;, # A possible additional shorter value to display.
+                # For example a java_class_name_value of com.mypackage.MyDoFn
+                # will be stored with MyDoFn as the short_str_value and
+                # com.mypackage.MyDoFn as the java_class_name value.
+                # short_str_value can be displayed and java_class_name_value
+                # will be displayed as a tooltip.
           },
-          &quot;diskSizeGb&quot;: 42, # Size of root disk for VMs, in GB.  If zero or unspecified, the service will
-              # attempt to choose a reasonable default.
-          &quot;workerHarnessContainerImage&quot;: &quot;A String&quot;, # Required. Docker container image that executes the Cloud Dataflow worker
-              # harness, residing in Google Container Registry.
-              #
-              # Deprecated for the Fn API path. Use sdk_harness_container_images instead.
-          &quot;diskType&quot;: &quot;A String&quot;, # Type of root disk for VMs.  If empty or unspecified, the service will
-              # attempt to choose a reasonable default.
-          &quot;machineType&quot;: &quot;A String&quot;, # Machine type (e.g. &quot;n1-standard-1&quot;).  If empty or unspecified, the
-              # service will attempt to choose a reasonable default.
-          &quot;kind&quot;: &quot;A String&quot;, # The kind of the worker pool; currently only `harness` and `shuffle`
-              # are supported.
-          &quot;sdkHarnessContainerImages&quot;: [ # Set of SDK harness containers needed to execute this pipeline. This will
-              # only be set in the Fn API path. For non-cross-language pipelines this
-              # should have only one entry. Cross-language pipelines will have two or more
-              # entries.
-            { # Defines a SDK harness container for executing Dataflow pipelines.
-              &quot;containerImage&quot;: &quot;A String&quot;, # A docker container image that resides in Google Container Registry.
-              &quot;useSingleCorePerContainer&quot;: True or False, # If true, recommends the Dataflow service to use only one core per SDK
-                  # container instance with this image. If false (or unset) recommends using
-                  # more than one core per SDK container instance with this image for
-                  # efficiency. Note that Dataflow service may choose to override this property
-                  # if needed.
-            },
-          ],
-          &quot;dataDisks&quot;: [ # Data disks that are used by a VM in this workflow.
-            { # Describes the data disk used by a workflow job.
-              &quot;diskType&quot;: &quot;A String&quot;, # Disk storage type, as defined by Google Compute Engine.  This
-                  # must be a disk type appropriate to the project and zone in which
-                  # the workers will run.  If unknown or unspecified, the service
-                  # will attempt to choose a reasonable default.
-                  #
-                  # For example, the standard persistent disk type is a resource name
-                  # typically ending in &quot;pd-standard&quot;.  If SSD persistent disks are
-                  # available, the resource name typically ends with &quot;pd-ssd&quot;.  The
-                  # actual valid values are defined the Google Compute Engine API,
-                  # not by the Cloud Dataflow API; consult the Google Compute Engine
-                  # documentation for more information about determining the set of
-                  # available disk types for a particular project and zone.
-                  #
-                  # Google Compute Engine Disk types are local to a particular
-                  # project in a particular zone, and so the resource name will
-                  # typically look something like this:
-                  #
-                  # compute.googleapis.com/projects/project-id/zones/zone/diskTypes/pd-standard
-              &quot;sizeGb&quot;: 42, # Size of disk in GB.  If zero or unspecified, the service will
-                  # attempt to choose a reasonable default.
-              &quot;mountPoint&quot;: &quot;A String&quot;, # Directory in a VM where disk is mounted.
-            },
-          ],
-          &quot;subnetwork&quot;: &quot;A String&quot;, # Subnetwork to which VMs will be assigned, if desired.  Expected to be of
-              # the form &quot;regions/REGION/subnetworks/SUBNETWORK&quot;.
-          &quot;ipConfiguration&quot;: &quot;A String&quot;, # Configuration for VM IPs.
-          &quot;taskrunnerSettings&quot;: { # Taskrunner configuration settings. # Settings passed through to Google Compute Engine workers when
-              # using the standard Dataflow task runner.  Users should ignore
-              # this field.
-            &quot;alsologtostderr&quot;: True or False, # Whether to also send taskrunner log info to stderr.
-            &quot;taskGroup&quot;: &quot;A String&quot;, # The UNIX group ID on the worker VM to use for tasks launched by
-                # taskrunner; e.g. &quot;wheel&quot;.
-            &quot;harnessCommand&quot;: &quot;A String&quot;, # The command to launch the worker harness.
-            &quot;logDir&quot;: &quot;A String&quot;, # The directory on the VM to store logs.
-            &quot;oauthScopes&quot;: [ # The OAuth2 scopes to be requested by the taskrunner in order to
-                # access the Cloud Dataflow API.
+        ],
+        &quot;originalPipelineTransform&quot;: [ # Description of each transform in the pipeline and collections between them.
+          { # Description of the type, names/ids, and input/outputs for a transform.
+            &quot;outputCollectionName&quot;: [ # User  names for all collection outputs to this transform.
               &quot;A String&quot;,
             ],
-            &quot;dataflowApiVersion&quot;: &quot;A String&quot;, # The API version of endpoint, e.g. &quot;v1b3&quot;
-            &quot;logUploadLocation&quot;: &quot;A String&quot;, # Indicates where to put logs.  If this is not specified, the logs
-                # will not be uploaded.
-                #
-                # The supported resource type is:
-                #
-                # Google Cloud Storage:
-                #   storage.googleapis.com/{bucket}/{object}
-                #   bucket.storage.googleapis.com/{object}
-            &quot;streamingWorkerMainClass&quot;: &quot;A String&quot;, # The streaming worker main class name.
-            &quot;workflowFileName&quot;: &quot;A String&quot;, # The file to store the workflow in.
-            &quot;languageHint&quot;: &quot;A String&quot;, # The suggested backend language.
-            &quot;commandlinesFileName&quot;: &quot;A String&quot;, # The file to store preprocessing commands in.
-            &quot;baseTaskDir&quot;: &quot;A String&quot;, # The location on the worker for task-specific subdirectories.
-            &quot;tempStoragePrefix&quot;: &quot;A String&quot;, # The prefix of the resources the taskrunner should use for
-                # temporary storage.
-                #
-                # The supported resource type is:
-                #
-                # Google Cloud Storage:
-                #   storage.googleapis.com/{bucket}/{object}
-                #   bucket.storage.googleapis.com/{object}
-            &quot;baseUrl&quot;: &quot;A String&quot;, # The base URL for the taskrunner to use when accessing Google Cloud APIs.
-                #
-                # When workers access Google Cloud APIs, they logically do so via
-                # relative URLs.  If this field is specified, it supplies the base
-                # URL to use for resolving these relative URLs.  The normative
-                # algorithm used is defined by RFC 1808, &quot;Relative Uniform Resource
-                # Locators&quot;.
-                #
-                # If not specified, the default value is &quot;http://www.googleapis.com/&quot;
-            &quot;logToSerialconsole&quot;: True or False, # Whether to send taskrunner log info to Google Compute Engine VM serial
-                # console.
-            &quot;continueOnException&quot;: True or False, # Whether to continue taskrunner if an exception is hit.
-            &quot;parallelWorkerSettings&quot;: { # Provides data to pass through to the worker harness. # The settings to pass to the parallel worker harness.
-              &quot;tempStoragePrefix&quot;: &quot;A String&quot;, # The prefix of the resources the system should use for temporary
-                  # storage.
+            &quot;displayData&quot;: [ # Transform-specific display data.
+              { # Data provided with a pipeline or transform to provide descriptive info.
+                &quot;url&quot;: &quot;A String&quot;, # An optional full URL.
+                &quot;javaClassValue&quot;: &quot;A String&quot;, # Contains value if the data is of java class type.
+                &quot;timestampValue&quot;: &quot;A String&quot;, # Contains value if the data is of timestamp type.
+                &quot;durationValue&quot;: &quot;A String&quot;, # Contains value if the data is of duration type.
+                &quot;label&quot;: &quot;A String&quot;, # An optional label to display in a dax UI for the element.
+                &quot;key&quot;: &quot;A String&quot;, # The key identifying the display data.
+                    # This is intended to be used as a label for the display data
+                    # when viewed in a dax monitoring system.
+                &quot;namespace&quot;: &quot;A String&quot;, # The namespace for the key. This is usually a class name or programming
+                    # language namespace (i.e. python module) which defines the display data.
+                    # This allows a dax monitoring system to specially handle the data
+                    # and perform custom rendering.
+                &quot;floatValue&quot;: 3.14, # Contains value if the data is of float type.
+                &quot;strValue&quot;: &quot;A String&quot;, # Contains value if the data is of string type.
+                &quot;int64Value&quot;: &quot;A String&quot;, # Contains value if the data is of int64 type.
+                &quot;boolValue&quot;: True or False, # Contains value if the data is of a boolean type.
+                &quot;shortStrValue&quot;: &quot;A String&quot;, # A possible additional shorter value to display.
+                    # For example a java_class_name_value of com.mypackage.MyDoFn
+                    # will be stored with MyDoFn as the short_str_value and
+                    # com.mypackage.MyDoFn as the java_class_name value.
+                    # short_str_value can be displayed and java_class_name_value
+                    # will be displayed as a tooltip.
+              },
+            ],
+            &quot;id&quot;: &quot;A String&quot;, # SDK generated id of this transform instance.
+            &quot;inputCollectionName&quot;: [ # User names for all collection inputs to this transform.
+              &quot;A String&quot;,
+            ],
+            &quot;name&quot;: &quot;A String&quot;, # User provided name for this transform instance.
+            &quot;kind&quot;: &quot;A String&quot;, # Type of transform.
+          },
+        ],
+        &quot;executionPipelineStage&quot;: [ # Description of each stage of execution of the pipeline.
+          { # Description of the composing transforms, names/ids, and input/outputs of a
+              # stage of execution.  Some composing transforms and sources may have been
+              # generated by the Dataflow service during execution planning.
+            &quot;componentSource&quot;: [ # Collections produced and consumed by component transforms of this stage.
+              { # Description of an interstitial value between transforms in an execution
+                  # stage.
+                &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this transform; may be user or system generated.
+                &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
+                &quot;originalTransformOrCollection&quot;: &quot;A String&quot;, # User name for the original user transform or collection with which this
+                    # source is most closely associated.
+              },
+            ],
+            &quot;inputSource&quot;: [ # Input sources for this stage.
+              { # Description of an input or output of an execution stage.
+                &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this source; may be user or system generated.
+                &quot;originalTransformOrCollection&quot;: &quot;A String&quot;, # User name for the original user transform or collection with which this
+                    # source is most closely associated.
+                &quot;sizeBytes&quot;: &quot;A String&quot;, # Size of the source, if measurable.
+                &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
+              },
+            ],
+            &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this stage.
+            &quot;componentTransform&quot;: [ # Transforms that comprise this execution stage.
+              { # Description of a transform executed as part of an execution stage.
+                &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
+                &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this transform; may be user or system generated.
+                &quot;originalTransform&quot;: &quot;A String&quot;, # User name for the original user transform with which this transform is
+                    # most closely associated.
+              },
+            ],
+            &quot;id&quot;: &quot;A String&quot;, # Dataflow service generated id for this stage.
+            &quot;outputSource&quot;: [ # Output sources for this stage.
+              { # Description of an input or output of an execution stage.
+                &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this source; may be user or system generated.
+                &quot;originalTransformOrCollection&quot;: &quot;A String&quot;, # User name for the original user transform or collection with which this
+                    # source is most closely associated.
+                &quot;sizeBytes&quot;: &quot;A String&quot;, # Size of the source, if measurable.
+                &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
+              },
+            ],
+            &quot;kind&quot;: &quot;A String&quot;, # Type of tranform this stage is executing.
+          },
+        ],
+      },
+      &quot;labels&quot;: { # User-defined labels for this job.
+          #
+          # The labels map can contain no more than 64 entries.  Entries of the labels
+          # map are UTF8 strings that comply with the following restrictions:
+          #
+          # * Keys must conform to regexp:  \p{Ll}\p{Lo}{0,62}
+          # * Values must conform to regexp:  [\p{Ll}\p{Lo}\p{N}_-]{0,63}
+          # * Both keys and values are additionally constrained to be &lt;= 128 bytes in
+          # size.
+        &quot;a_key&quot;: &quot;A String&quot;,
+      },
+      &quot;projectId&quot;: &quot;A String&quot;, # The ID of the Cloud Platform project that the job belongs to.
+      &quot;environment&quot;: { # Describes the environment in which a Dataflow Job runs. # The environment for the job.
+        &quot;flexResourceSchedulingGoal&quot;: &quot;A String&quot;, # Which Flexible Resource Scheduling mode to run in.
+        &quot;workerRegion&quot;: &quot;A String&quot;, # The Compute Engine region
+            # (https://cloud.google.com/compute/docs/regions-zones/regions-zones) in
+            # which worker processing should occur, e.g. &quot;us-west1&quot;. Mutually exclusive
+            # with worker_zone. If neither worker_region nor worker_zone is specified,
+            # default to the control plane&#x27;s region.
+        &quot;userAgent&quot;: { # A description of the process that generated the request.
+          &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
+        },
+        &quot;serviceAccountEmail&quot;: &quot;A String&quot;, # Identity to run virtual machines as. Defaults to the default account.
+        &quot;version&quot;: { # A structure describing which components and their versions of the service
+            # are required in order to run the job.
+          &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
+        },
+        &quot;serviceKmsKeyName&quot;: &quot;A String&quot;, # If set, contains the Cloud KMS key identifier used to encrypt data
+            # at rest, AKA a Customer Managed Encryption Key (CMEK).
+            #
+            # Format:
+            #   projects/PROJECT_ID/locations/LOCATION/keyRings/KEY_RING/cryptoKeys/KEY
+        &quot;experiments&quot;: [ # The list of experiments to enable.
+          &quot;A String&quot;,
+        ],
+        &quot;workerZone&quot;: &quot;A String&quot;, # The Compute Engine zone
+            # (https://cloud.google.com/compute/docs/regions-zones/regions-zones) in
+            # which worker processing should occur, e.g. &quot;us-west1-a&quot;. Mutually exclusive
+            # with worker_region. If neither worker_region nor worker_zone is specified,
+            # a zone in the control plane&#x27;s region is chosen based on available capacity.
+        &quot;workerPools&quot;: [ # The worker pools. At least one &quot;harness&quot; worker pool must be
+            # specified in order for the job to have workers.
+          { # Describes one particular pool of Cloud Dataflow workers to be
+              # instantiated by the Cloud Dataflow service in order to perform the
+              # computations required by a job.  Note that a workflow job may use
+              # multiple pools, in order to match the various computational
+              # requirements of the various stages of the job.
+            &quot;onHostMaintenance&quot;: &quot;A String&quot;, # The action to take on host maintenance, as defined by the Google
+                # Compute Engine API.
+            &quot;sdkHarnessContainerImages&quot;: [ # Set of SDK harness containers needed to execute this pipeline. This will
+                # only be set in the Fn API path. For non-cross-language pipelines this
+                # should have only one entry. Cross-language pipelines will have two or more
+                # entries.
+              { # Defines a SDK harness container for executing Dataflow pipelines.
+                &quot;containerImage&quot;: &quot;A String&quot;, # A docker container image that resides in Google Container Registry.
+                &quot;useSingleCorePerContainer&quot;: True or False, # If true, recommends the Dataflow service to use only one core per SDK
+                    # container instance with this image. If false (or unset) recommends using
+                    # more than one core per SDK container instance with this image for
+                    # efficiency. Note that Dataflow service may choose to override this property
+                    # if needed.
+              },
+            ],
+            &quot;zone&quot;: &quot;A String&quot;, # Zone to run the worker pools in.  If empty or unspecified, the service
+                # will attempt to choose a reasonable default.
+            &quot;kind&quot;: &quot;A String&quot;, # The kind of the worker pool; currently only `harness` and `shuffle`
+                # are supported.
+            &quot;metadata&quot;: { # Metadata to set on the Google Compute Engine VMs.
+              &quot;a_key&quot;: &quot;A String&quot;,
+            },
+            &quot;diskSourceImage&quot;: &quot;A String&quot;, # Fully qualified source image for disks.
+            &quot;dataDisks&quot;: [ # Data disks that are used by a VM in this workflow.
+              { # Describes the data disk used by a workflow job.
+                &quot;sizeGb&quot;: 42, # Size of disk in GB.  If zero or unspecified, the service will
+                    # attempt to choose a reasonable default.
+                &quot;diskType&quot;: &quot;A String&quot;, # Disk storage type, as defined by Google Compute Engine.  This
+                    # must be a disk type appropriate to the project and zone in which
+                    # the workers will run.  If unknown or unspecified, the service
+                    # will attempt to choose a reasonable default.
+                    #
+                    # For example, the standard persistent disk type is a resource name
+                    # typically ending in &quot;pd-standard&quot;.  If SSD persistent disks are
+                    # available, the resource name typically ends with &quot;pd-ssd&quot;.  The
+                    # actual valid values are defined the Google Compute Engine API,
+                    # not by the Cloud Dataflow API; consult the Google Compute Engine
+                    # documentation for more information about determining the set of
+                    # available disk types for a particular project and zone.
+                    #
+                    # Google Compute Engine Disk types are local to a particular
+                    # project in a particular zone, and so the resource name will
+                    # typically look something like this:
+                    #
+                    # compute.googleapis.com/projects/project-id/zones/zone/diskTypes/pd-standard
+                &quot;mountPoint&quot;: &quot;A String&quot;, # Directory in a VM where disk is mounted.
+              },
+            ],
+            &quot;packages&quot;: [ # Packages to be installed on workers.
+              { # The packages that must be installed in order for a worker to run the
+                  # steps of the Cloud Dataflow job that will be assigned to its worker
+                  # pool.
                   #
-                  # The supported resource type is:
-                  #
-                  # Google Cloud Storage:
-                  #
-                  #   storage.googleapis.com/{bucket}/{object}
-                  #   bucket.storage.googleapis.com/{object}
-              &quot;reportingEnabled&quot;: True or False, # Whether to send work progress updates to the service.
-              &quot;baseUrl&quot;: &quot;A String&quot;, # The base URL for accessing Google Cloud APIs.
+                  # This is the mechanism by which the Cloud Dataflow SDK causes code to
+                  # be loaded onto the workers. For example, the Cloud Dataflow Java SDK
+                  # might use this to install jars containing the user&#x27;s code and all of the
+                  # various dependencies (libraries, data files, etc.) required in order
+                  # for that code to run.
+                &quot;name&quot;: &quot;A String&quot;, # The name of the package.
+                &quot;location&quot;: &quot;A String&quot;, # The resource to read the package from. The supported resource type is:
+                    #
+                    # Google Cloud Storage:
+                    #
+                    #   storage.googleapis.com/{bucket}
+                    #   bucket.storage.googleapis.com/
+              },
+            ],
+            &quot;teardownPolicy&quot;: &quot;A String&quot;, # Sets the policy for determining when to turndown worker pool.
+                # Allowed values are: `TEARDOWN_ALWAYS`, `TEARDOWN_ON_SUCCESS`, and
+                # `TEARDOWN_NEVER`.
+                # `TEARDOWN_ALWAYS` means workers are always torn down regardless of whether
+                # the job succeeds. `TEARDOWN_ON_SUCCESS` means workers are torn down
+                # if the job succeeds. `TEARDOWN_NEVER` means the workers are never torn
+                # down.
+                #
+                # If the workers are not torn down by the service, they will
+                # continue to run and use Google Compute Engine VM resources in the
+                # user&#x27;s project until they are explicitly terminated by the user.
+                # Because of this, Google recommends using the `TEARDOWN_ALWAYS`
+                # policy except for small, manually supervised test jobs.
+                #
+                # If unknown or unspecified, the service will attempt to choose a reasonable
+                # default.
+            &quot;network&quot;: &quot;A String&quot;, # Network to which VMs will be assigned.  If empty or unspecified,
+                # the service will use the network &quot;default&quot;.
+            &quot;ipConfiguration&quot;: &quot;A String&quot;, # Configuration for VM IPs.
+            &quot;diskSizeGb&quot;: 42, # Size of root disk for VMs, in GB.  If zero or unspecified, the service will
+                # attempt to choose a reasonable default.
+            &quot;autoscalingSettings&quot;: { # Settings for WorkerPool autoscaling. # Settings for autoscaling of this WorkerPool.
+              &quot;maxNumWorkers&quot;: 42, # The maximum number of workers to cap scaling at.
+              &quot;algorithm&quot;: &quot;A String&quot;, # The algorithm to use for autoscaling.
+            },
+            &quot;poolArgs&quot;: { # Extra arguments for this worker pool.
+              &quot;a_key&quot;: &quot;&quot;, # Properties of the object. Contains field @type with type URL.
+            },
+            &quot;subnetwork&quot;: &quot;A String&quot;, # Subnetwork to which VMs will be assigned, if desired.  Expected to be of
+                # the form &quot;regions/REGION/subnetworks/SUBNETWORK&quot;.
+            &quot;numWorkers&quot;: 42, # Number of Google Compute Engine workers in this pool needed to
+                # execute the job.  If zero or unspecified, the service will
+                # attempt to choose a reasonable default.
+            &quot;numThreadsPerWorker&quot;: 42, # The number of threads per worker harness. If empty or unspecified, the
+                # service will choose a number of threads (according to the number of cores
+                # on the selected machine type for batch, or 1 by convention for streaming).
+            &quot;workerHarnessContainerImage&quot;: &quot;A String&quot;, # Required. Docker container image that executes the Cloud Dataflow worker
+                # harness, residing in Google Container Registry.
+                #
+                # Deprecated for the Fn API path. Use sdk_harness_container_images instead.
+            &quot;taskrunnerSettings&quot;: { # Taskrunner configuration settings. # Settings passed through to Google Compute Engine workers when
+                # using the standard Dataflow task runner.  Users should ignore
+                # this field.
+              &quot;dataflowApiVersion&quot;: &quot;A String&quot;, # The API version of endpoint, e.g. &quot;v1b3&quot;
+              &quot;oauthScopes&quot;: [ # The OAuth2 scopes to be requested by the taskrunner in order to
+                  # access the Cloud Dataflow API.
+                &quot;A String&quot;,
+              ],
+              &quot;baseUrl&quot;: &quot;A String&quot;, # The base URL for the taskrunner to use when accessing Google Cloud APIs.
                   #
                   # When workers access Google Cloud APIs, they logically do so via
                   # relative URLs.  If this field is specified, it supplies the base
@@ -2216,339 +2258,297 @@
                   # Locators&quot;.
                   #
                   # If not specified, the default value is &quot;http://www.googleapis.com/&quot;
-              &quot;servicePath&quot;: &quot;A String&quot;, # The Cloud Dataflow service path relative to the root URL, for example,
-                  # &quot;dataflow/v1b3/projects&quot;.
-              &quot;shuffleServicePath&quot;: &quot;A String&quot;, # The Shuffle service path relative to the root URL, for example,
-                  # &quot;shuffle/v1beta1&quot;.
-              &quot;workerId&quot;: &quot;A String&quot;, # The ID of the worker running this pipeline.
+              &quot;workflowFileName&quot;: &quot;A String&quot;, # The file to store the workflow in.
+              &quot;logToSerialconsole&quot;: True or False, # Whether to send taskrunner log info to Google Compute Engine VM serial
+                  # console.
+              &quot;baseTaskDir&quot;: &quot;A String&quot;, # The location on the worker for task-specific subdirectories.
+              &quot;taskUser&quot;: &quot;A String&quot;, # The UNIX user ID on the worker VM to use for tasks launched by
+                  # taskrunner; e.g. &quot;root&quot;.
+              &quot;vmId&quot;: &quot;A String&quot;, # The ID string of the VM.
+              &quot;alsologtostderr&quot;: True or False, # Whether to also send taskrunner log info to stderr.
+              &quot;parallelWorkerSettings&quot;: { # Provides data to pass through to the worker harness. # The settings to pass to the parallel worker harness.
+                &quot;shuffleServicePath&quot;: &quot;A String&quot;, # The Shuffle service path relative to the root URL, for example,
+                    # &quot;shuffle/v1beta1&quot;.
+                &quot;tempStoragePrefix&quot;: &quot;A String&quot;, # The prefix of the resources the system should use for temporary
+                    # storage.
+                    #
+                    # The supported resource type is:
+                    #
+                    # Google Cloud Storage:
+                    #
+                    #   storage.googleapis.com/{bucket}/{object}
+                    #   bucket.storage.googleapis.com/{object}
+                &quot;reportingEnabled&quot;: True or False, # Whether to send work progress updates to the service.
+                &quot;servicePath&quot;: &quot;A String&quot;, # The Cloud Dataflow service path relative to the root URL, for example,
+                    # &quot;dataflow/v1b3/projects&quot;.
+                &quot;baseUrl&quot;: &quot;A String&quot;, # The base URL for accessing Google Cloud APIs.
+                    #
+                    # When workers access Google Cloud APIs, they logically do so via
+                    # relative URLs.  If this field is specified, it supplies the base
+                    # URL to use for resolving these relative URLs.  The normative
+                    # algorithm used is defined by RFC 1808, &quot;Relative Uniform Resource
+                    # Locators&quot;.
+                    #
+                    # If not specified, the default value is &quot;http://www.googleapis.com/&quot;
+                &quot;workerId&quot;: &quot;A String&quot;, # The ID of the worker running this pipeline.
+              },
+              &quot;harnessCommand&quot;: &quot;A String&quot;, # The command to launch the worker harness.
+              &quot;logDir&quot;: &quot;A String&quot;, # The directory on the VM to store logs.
+              &quot;streamingWorkerMainClass&quot;: &quot;A String&quot;, # The streaming worker main class name.
+              &quot;languageHint&quot;: &quot;A String&quot;, # The suggested backend language.
+              &quot;taskGroup&quot;: &quot;A String&quot;, # The UNIX group ID on the worker VM to use for tasks launched by
+                  # taskrunner; e.g. &quot;wheel&quot;.
+              &quot;logUploadLocation&quot;: &quot;A String&quot;, # Indicates where to put logs.  If this is not specified, the logs
+                  # will not be uploaded.
+                  #
+                  # The supported resource type is:
+                  #
+                  # Google Cloud Storage:
+                  #   storage.googleapis.com/{bucket}/{object}
+                  #   bucket.storage.googleapis.com/{object}
+              &quot;commandlinesFileName&quot;: &quot;A String&quot;, # The file to store preprocessing commands in.
+              &quot;continueOnException&quot;: True or False, # Whether to continue taskrunner if an exception is hit.
+              &quot;tempStoragePrefix&quot;: &quot;A String&quot;, # The prefix of the resources the taskrunner should use for
+                  # temporary storage.
+                  #
+                  # The supported resource type is:
+                  #
+                  # Google Cloud Storage:
+                  #   storage.googleapis.com/{bucket}/{object}
+                  #   bucket.storage.googleapis.com/{object}
             },
-            &quot;taskUser&quot;: &quot;A String&quot;, # The UNIX user ID on the worker VM to use for tasks launched by
-                # taskrunner; e.g. &quot;root&quot;.
-            &quot;vmId&quot;: &quot;A String&quot;, # The ID string of the VM.
+            &quot;diskType&quot;: &quot;A String&quot;, # Type of root disk for VMs.  If empty or unspecified, the service will
+                # attempt to choose a reasonable default.
+            &quot;defaultPackageSet&quot;: &quot;A String&quot;, # The default package set to install.  This allows the service to
+                # select a default set of packages which are useful to worker
+                # harnesses written in a particular language.
+            &quot;machineType&quot;: &quot;A String&quot;, # Machine type (e.g. &quot;n1-standard-1&quot;).  If empty or unspecified, the
+                # service will attempt to choose a reasonable default.
           },
-          &quot;autoscalingSettings&quot;: { # Settings for WorkerPool autoscaling. # Settings for autoscaling of this WorkerPool.
-            &quot;algorithm&quot;: &quot;A String&quot;, # The algorithm to use for autoscaling.
-            &quot;maxNumWorkers&quot;: 42, # The maximum number of workers to cap scaling at.
-          },
-          &quot;metadata&quot;: { # Metadata to set on the Google Compute Engine VMs.
-            &quot;a_key&quot;: &quot;A String&quot;,
-          },
-          &quot;defaultPackageSet&quot;: &quot;A String&quot;, # The default package set to install.  This allows the service to
-              # select a default set of packages which are useful to worker
-              # harnesses written in a particular language.
-          &quot;network&quot;: &quot;A String&quot;, # Network to which VMs will be assigned.  If empty or unspecified,
-              # the service will use the network &quot;default&quot;.
+        ],
+        &quot;tempStoragePrefix&quot;: &quot;A String&quot;, # The prefix of the resources the system should use for temporary
+            # storage.  The system will append the suffix &quot;/temp-{JOBNAME} to
+            # this resource prefix, where {JOBNAME} is the value of the
+            # job_name field.  The resulting bucket and object prefix is used
+            # as the prefix of the resources used to store temporary data
+            # needed during the job execution.  NOTE: This will override the
+            # value in taskrunner_settings.
+            # The supported resource type is:
+            #
+            # Google Cloud Storage:
+            #
+            #   storage.googleapis.com/{bucket}/{object}
+            #   bucket.storage.googleapis.com/{object}
+        &quot;internalExperiments&quot;: { # Experimental settings.
+          &quot;a_key&quot;: &quot;&quot;, # Properties of the object. Contains field @type with type URL.
         },
-      ],
-      &quot;dataset&quot;: &quot;A String&quot;, # The dataset for the current project where various workflow
-          # related tables are stored.
-          #
-          # The supported resource type is:
-          #
-          # Google BigQuery:
-          #   bigquery.googleapis.com/{dataset}
-    },
-    &quot;stageStates&quot;: [ # This field may be mutated by the Cloud Dataflow service;
-        # callers cannot mutate it.
-      { # A message describing the state of a particular execution stage.
-        &quot;currentStateTime&quot;: &quot;A String&quot;, # The time at which the stage transitioned to this state.
-        &quot;executionStageState&quot;: &quot;A String&quot;, # Executions stage states allow the same set of values as JobState.
-        &quot;executionStageName&quot;: &quot;A String&quot;, # The name of the execution stage.
-      },
-    ],
-    &quot;jobMetadata&quot;: { # Metadata available primarily for filtering jobs. Will be included in the # This field is populated by the Dataflow service to support filtering jobs
-        # by the metadata values provided here. Populated for ListJobs and all GetJob
-        # views SUMMARY and higher.
-        # ListJob response and Job SUMMARY view.
-      &quot;datastoreDetails&quot;: [ # Identification of a Datastore source used in the Dataflow job.
-        { # Metadata for a Datastore connector used by the job.
-          &quot;namespace&quot;: &quot;A String&quot;, # Namespace used in the connection.
-          &quot;projectId&quot;: &quot;A String&quot;, # ProjectId accessed in the connection.
-        },
-      ],
-      &quot;sdkVersion&quot;: { # The version of the SDK used to run the job. # The SDK version used to run the job.
-        &quot;version&quot;: &quot;A String&quot;, # The version of the SDK used to run the job.
-        &quot;sdkSupportStatus&quot;: &quot;A String&quot;, # The support status for this SDK version.
-        &quot;versionDisplayName&quot;: &quot;A String&quot;, # A readable string describing the version of the SDK.
-      },
-      &quot;bigqueryDetails&quot;: [ # Identification of a BigQuery source used in the Dataflow job.
-        { # Metadata for a BigQuery connector used by the job.
-          &quot;table&quot;: &quot;A String&quot;, # Table accessed in the connection.
-          &quot;dataset&quot;: &quot;A String&quot;, # Dataset accessed in the connection.
-          &quot;query&quot;: &quot;A String&quot;, # Query used to access data in the connection.
-          &quot;projectId&quot;: &quot;A String&quot;, # Project accessed in the connection.
-        },
-      ],
-      &quot;fileDetails&quot;: [ # Identification of a File source used in the Dataflow job.
-        { # Metadata for a File connector used by the job.
-          &quot;filePattern&quot;: &quot;A String&quot;, # File Pattern used to access files by the connector.
-        },
-      ],
-      &quot;pubsubDetails&quot;: [ # Identification of a PubSub source used in the Dataflow job.
-        { # Metadata for a PubSub connector used by the job.
-          &quot;topic&quot;: &quot;A String&quot;, # Topic accessed in the connection.
-          &quot;subscription&quot;: &quot;A String&quot;, # Subscription used in the connection.
-        },
-      ],
-      &quot;bigTableDetails&quot;: [ # Identification of a BigTable source used in the Dataflow job.
-        { # Metadata for a BigTable connector used by the job.
-          &quot;projectId&quot;: &quot;A String&quot;, # ProjectId accessed in the connection.
-          &quot;instanceId&quot;: &quot;A String&quot;, # InstanceId accessed in the connection.
-          &quot;tableId&quot;: &quot;A String&quot;, # TableId accessed in the connection.
-        },
-      ],
-      &quot;spannerDetails&quot;: [ # Identification of a Spanner source used in the Dataflow job.
-        { # Metadata for a Spanner connector used by the job.
-          &quot;instanceId&quot;: &quot;A String&quot;, # InstanceId accessed in the connection.
-          &quot;projectId&quot;: &quot;A String&quot;, # ProjectId accessed in the connection.
-          &quot;databaseId&quot;: &quot;A String&quot;, # DatabaseId accessed in the connection.
-        },
-      ],
-    },
-    &quot;type&quot;: &quot;A String&quot;, # The type of Cloud Dataflow job.
-    &quot;projectId&quot;: &quot;A String&quot;, # The ID of the Cloud Platform project that the job belongs to.
-    &quot;createdFromSnapshotId&quot;: &quot;A String&quot;, # If this is specified, the job&#x27;s initial state is populated from the given
-        # snapshot.
-    &quot;pipelineDescription&quot;: { # A descriptive representation of submitted pipeline as well as the executed # Preliminary field: The format of this data may change at any time.
-        # A description of the user pipeline and stages through which it is executed.
-        # Created by Cloud Dataflow service.  Only retrieved with
-        # JOB_VIEW_DESCRIPTION or JOB_VIEW_ALL.
-        # form.  This data is provided by the Dataflow service for ease of visualizing
-        # the pipeline and interpreting Dataflow provided metrics.
-      &quot;executionPipelineStage&quot;: [ # Description of each stage of execution of the pipeline.
-        { # Description of the composing transforms, names/ids, and input/outputs of a
-            # stage of execution.  Some composing transforms and sources may have been
-            # generated by the Dataflow service during execution planning.
-          &quot;outputSource&quot;: [ # Output sources for this stage.
-            { # Description of an input or output of an execution stage.
-              &quot;sizeBytes&quot;: &quot;A String&quot;, # Size of the source, if measurable.
-              &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
-              &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this source; may be user or system generated.
-              &quot;originalTransformOrCollection&quot;: &quot;A String&quot;, # User name for the original user transform or collection with which this
-                  # source is most closely associated.
-            },
-          ],
-          &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this stage.
-          &quot;inputSource&quot;: [ # Input sources for this stage.
-            { # Description of an input or output of an execution stage.
-              &quot;sizeBytes&quot;: &quot;A String&quot;, # Size of the source, if measurable.
-              &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
-              &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this source; may be user or system generated.
-              &quot;originalTransformOrCollection&quot;: &quot;A String&quot;, # User name for the original user transform or collection with which this
-                  # source is most closely associated.
-            },
-          ],
-          &quot;id&quot;: &quot;A String&quot;, # Dataflow service generated id for this stage.
-          &quot;componentTransform&quot;: [ # Transforms that comprise this execution stage.
-            { # Description of a transform executed as part of an execution stage.
-              &quot;originalTransform&quot;: &quot;A String&quot;, # User name for the original user transform with which this transform is
-                  # most closely associated.
-              &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
-              &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this transform; may be user or system generated.
-            },
-          ],
-          &quot;componentSource&quot;: [ # Collections produced and consumed by component transforms of this stage.
-            { # Description of an interstitial value between transforms in an execution
-                # stage.
-              &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
-              &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this transform; may be user or system generated.
-              &quot;originalTransformOrCollection&quot;: &quot;A String&quot;, # User name for the original user transform or collection with which this
-                  # source is most closely associated.
-            },
-          ],
-          &quot;kind&quot;: &quot;A String&quot;, # Type of tranform this stage is executing.
-        },
-      ],
-      &quot;originalPipelineTransform&quot;: [ # Description of each transform in the pipeline and collections between them.
-        { # Description of the type, names/ids, and input/outputs for a transform.
-          &quot;kind&quot;: &quot;A String&quot;, # Type of transform.
-          &quot;inputCollectionName&quot;: [ # User names for all collection inputs to this transform.
-            &quot;A String&quot;,
-          ],
-          &quot;name&quot;: &quot;A String&quot;, # User provided name for this transform instance.
-          &quot;id&quot;: &quot;A String&quot;, # SDK generated id of this transform instance.
-          &quot;displayData&quot;: [ # Transform-specific display data.
-            { # Data provided with a pipeline or transform to provide descriptive info.
-              &quot;durationValue&quot;: &quot;A String&quot;, # Contains value if the data is of duration type.
-              &quot;int64Value&quot;: &quot;A String&quot;, # Contains value if the data is of int64 type.
-              &quot;namespace&quot;: &quot;A String&quot;, # The namespace for the key. This is usually a class name or programming
-                  # language namespace (i.e. python module) which defines the display data.
-                  # This allows a dax monitoring system to specially handle the data
-                  # and perform custom rendering.
-              &quot;floatValue&quot;: 3.14, # Contains value if the data is of float type.
-              &quot;key&quot;: &quot;A String&quot;, # The key identifying the display data.
-                  # This is intended to be used as a label for the display data
-                  # when viewed in a dax monitoring system.
-              &quot;shortStrValue&quot;: &quot;A String&quot;, # A possible additional shorter value to display.
-                  # For example a java_class_name_value of com.mypackage.MyDoFn
-                  # will be stored with MyDoFn as the short_str_value and
-                  # com.mypackage.MyDoFn as the java_class_name value.
-                  # short_str_value can be displayed and java_class_name_value
-                  # will be displayed as a tooltip.
-              &quot;url&quot;: &quot;A String&quot;, # An optional full URL.
-              &quot;label&quot;: &quot;A String&quot;, # An optional label to display in a dax UI for the element.
-              &quot;timestampValue&quot;: &quot;A String&quot;, # Contains value if the data is of timestamp type.
-              &quot;boolValue&quot;: True or False, # Contains value if the data is of a boolean type.
-              &quot;javaClassValue&quot;: &quot;A String&quot;, # Contains value if the data is of java class type.
-              &quot;strValue&quot;: &quot;A String&quot;, # Contains value if the data is of string type.
-            },
-          ],
-          &quot;outputCollectionName&quot;: [ # User  names for all collection outputs to this transform.
-            &quot;A String&quot;,
-          ],
-        },
-      ],
-      &quot;displayData&quot;: [ # Pipeline level display data.
-        { # Data provided with a pipeline or transform to provide descriptive info.
-          &quot;durationValue&quot;: &quot;A String&quot;, # Contains value if the data is of duration type.
-          &quot;int64Value&quot;: &quot;A String&quot;, # Contains value if the data is of int64 type.
-          &quot;namespace&quot;: &quot;A String&quot;, # The namespace for the key. This is usually a class name or programming
-              # language namespace (i.e. python module) which defines the display data.
-              # This allows a dax monitoring system to specially handle the data
-              # and perform custom rendering.
-          &quot;floatValue&quot;: 3.14, # Contains value if the data is of float type.
-          &quot;key&quot;: &quot;A String&quot;, # The key identifying the display data.
-              # This is intended to be used as a label for the display data
-              # when viewed in a dax monitoring system.
-          &quot;shortStrValue&quot;: &quot;A String&quot;, # A possible additional shorter value to display.
-              # For example a java_class_name_value of com.mypackage.MyDoFn
-              # will be stored with MyDoFn as the short_str_value and
-              # com.mypackage.MyDoFn as the java_class_name value.
-              # short_str_value can be displayed and java_class_name_value
-              # will be displayed as a tooltip.
-          &quot;url&quot;: &quot;A String&quot;, # An optional full URL.
-          &quot;label&quot;: &quot;A String&quot;, # An optional label to display in a dax UI for the element.
-          &quot;timestampValue&quot;: &quot;A String&quot;, # Contains value if the data is of timestamp type.
-          &quot;boolValue&quot;: True or False, # Contains value if the data is of a boolean type.
-          &quot;javaClassValue&quot;: &quot;A String&quot;, # Contains value if the data is of java class type.
-          &quot;strValue&quot;: &quot;A String&quot;, # Contains value if the data is of string type.
-        },
-      ],
-    },
-    &quot;replaceJobId&quot;: &quot;A String&quot;, # If this job is an update of an existing job, this field is the job ID
-        # of the job it replaced.
-        #
-        # When sending a `CreateJobRequest`, you can update a job by specifying it
-        # here. The job named here is stopped, and its intermediate state is
-        # transferred to this job.
-    &quot;tempFiles&quot;: [ # A set of files the system should be aware of that are used
-        # for temporary storage. These temporary files will be
-        # removed on job completion.
-        # No duplicates are allowed.
-        # No file patterns are supported.
-        #
-        # The supported files are:
-        #
-        # Google Cloud Storage:
-        #
-        #    storage.googleapis.com/{bucket}/{object}
-        #    bucket.storage.googleapis.com/{object}
-      &quot;A String&quot;,
-    ],
-    &quot;name&quot;: &quot;A String&quot;, # The user-specified Cloud Dataflow job name.
-        #
-        # Only one Job with a given name may exist in a project at any
-        # given time. If a caller attempts to create a Job with the same
-        # name as an already-existing Job, the attempt returns the
-        # existing Job.
-        #
-        # The name must match the regular expression
-        # `[a-z]([-a-z0-9]{0,38}[a-z0-9])?`
-    &quot;steps&quot;: [ # Exactly one of step or steps_location should be specified.
-        #
-        # The top-level steps that constitute the entire job.
-      { # Defines a particular step within a Cloud Dataflow job.
-          #
-          # A job consists of multiple steps, each of which performs some
-          # specific operation as part of the overall job.  Data is typically
-          # passed from one step to another as part of the job.
-          #
-          # Here&#x27;s an example of a sequence of steps which together implement a
-          # Map-Reduce job:
-          #
-          #   * Read a collection of data from some source, parsing the
-          #     collection&#x27;s elements.
-          #
-          #   * Validate the elements.
-          #
-          #   * Apply a user-defined function to map each element to some value
-          #     and extract an element-specific key value.
-          #
-          #   * Group elements with the same key into a single element with
-          #     that key, transforming a multiply-keyed collection into a
-          #     uniquely-keyed collection.
-          #
-          #   * Write the elements out to some data sink.
-          #
-          # Note that the Cloud Dataflow service may be used to run many different
-          # types of jobs, not just Map-Reduce.
-        &quot;name&quot;: &quot;A String&quot;, # The name that identifies the step. This must be unique for each
-            # step with respect to all other steps in the Cloud Dataflow job.
-        &quot;kind&quot;: &quot;A String&quot;, # The kind of step in the Cloud Dataflow job.
-        &quot;properties&quot;: { # Named properties associated with the step. Each kind of
-            # predefined step has its own required set of properties.
-            # Must be provided on Create.  Only retrieved with JOB_VIEW_ALL.
+        &quot;sdkPipelineOptions&quot;: { # The Cloud Dataflow SDK pipeline options specified by the user. These
+            # options are passed through the service and are used to recreate the
+            # SDK pipeline options on the worker in a language agnostic and platform
+            # independent way.
           &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
         },
+        &quot;dataset&quot;: &quot;A String&quot;, # The dataset for the current project where various workflow
+            # related tables are stored.
+            #
+            # The supported resource type is:
+            #
+            # Google BigQuery:
+            #   bigquery.googleapis.com/{dataset}
+        &quot;clusterManagerApiService&quot;: &quot;A String&quot;, # The type of cluster manager API to use.  If unknown or
+            # unspecified, the service will attempt to choose a reasonable
+            # default.  This should be in the form of the API service name,
+            # e.g. &quot;compute.googleapis.com&quot;.
       },
-    ],
-    &quot;replacedByJobId&quot;: &quot;A String&quot;, # If another job is an update of this job (and thus, this job is in
-        # `JOB_STATE_UPDATED`), this field contains the ID of that job.
-    &quot;executionInfo&quot;: { # Additional information about how a Cloud Dataflow job will be executed that # Deprecated.
-        # isn&#x27;t contained in the submitted job.
-      &quot;stages&quot;: { # A mapping from each stage to the information about that stage.
-        &quot;a_key&quot;: { # Contains information about how a particular
-            # google.dataflow.v1beta3.Step will be executed.
-          &quot;stepName&quot;: [ # The steps associated with the execution stage.
-              # Note that stages may have several steps, and that a given step
-              # might be run by more than one stage.
-            &quot;A String&quot;,
-          ],
+      &quot;stepsLocation&quot;: &quot;A String&quot;, # The GCS location where the steps are stored.
+      &quot;steps&quot;: [ # Exactly one of step or steps_location should be specified.
+          #
+          # The top-level steps that constitute the entire job.
+        { # Defines a particular step within a Cloud Dataflow job.
+            #
+            # A job consists of multiple steps, each of which performs some
+            # specific operation as part of the overall job.  Data is typically
+            # passed from one step to another as part of the job.
+            #
+            # Here&#x27;s an example of a sequence of steps which together implement a
+            # Map-Reduce job:
+            #
+            #   * Read a collection of data from some source, parsing the
+            #     collection&#x27;s elements.
+            #
+            #   * Validate the elements.
+            #
+            #   * Apply a user-defined function to map each element to some value
+            #     and extract an element-specific key value.
+            #
+            #   * Group elements with the same key into a single element with
+            #     that key, transforming a multiply-keyed collection into a
+            #     uniquely-keyed collection.
+            #
+            #   * Write the elements out to some data sink.
+            #
+            # Note that the Cloud Dataflow service may be used to run many different
+            # types of jobs, not just Map-Reduce.
+          &quot;kind&quot;: &quot;A String&quot;, # The kind of step in the Cloud Dataflow job.
+          &quot;properties&quot;: { # Named properties associated with the step. Each kind of
+              # predefined step has its own required set of properties.
+              # Must be provided on Create.  Only retrieved with JOB_VIEW_ALL.
+            &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
+          },
+          &quot;name&quot;: &quot;A String&quot;, # The name that identifies the step. This must be unique for each
+              # step with respect to all other steps in the Cloud Dataflow job.
+        },
+      ],
+      &quot;stageStates&quot;: [ # This field may be mutated by the Cloud Dataflow service;
+          # callers cannot mutate it.
+        { # A message describing the state of a particular execution stage.
+          &quot;executionStageState&quot;: &quot;A String&quot;, # Executions stage states allow the same set of values as JobState.
+          &quot;executionStageName&quot;: &quot;A String&quot;, # The name of the execution stage.
+          &quot;currentStateTime&quot;: &quot;A String&quot;, # The time at which the stage transitioned to this state.
+        },
+      ],
+      &quot;replacedByJobId&quot;: &quot;A String&quot;, # If another job is an update of this job (and thus, this job is in
+          # `JOB_STATE_UPDATED`), this field contains the ID of that job.
+      &quot;jobMetadata&quot;: { # Metadata available primarily for filtering jobs. Will be included in the # This field is populated by the Dataflow service to support filtering jobs
+          # by the metadata values provided here. Populated for ListJobs and all GetJob
+          # views SUMMARY and higher.
+          # ListJob response and Job SUMMARY view.
+        &quot;sdkVersion&quot;: { # The version of the SDK used to run the job. # The SDK version used to run the job.
+          &quot;sdkSupportStatus&quot;: &quot;A String&quot;, # The support status for this SDK version.
+          &quot;versionDisplayName&quot;: &quot;A String&quot;, # A readable string describing the version of the SDK.
+          &quot;version&quot;: &quot;A String&quot;, # The version of the SDK used to run the job.
+        },
+        &quot;bigTableDetails&quot;: [ # Identification of a BigTable source used in the Dataflow job.
+          { # Metadata for a BigTable connector used by the job.
+            &quot;instanceId&quot;: &quot;A String&quot;, # InstanceId accessed in the connection.
+            &quot;tableId&quot;: &quot;A String&quot;, # TableId accessed in the connection.
+            &quot;projectId&quot;: &quot;A String&quot;, # ProjectId accessed in the connection.
+          },
+        ],
+        &quot;pubsubDetails&quot;: [ # Identification of a PubSub source used in the Dataflow job.
+          { # Metadata for a PubSub connector used by the job.
+            &quot;subscription&quot;: &quot;A String&quot;, # Subscription used in the connection.
+            &quot;topic&quot;: &quot;A String&quot;, # Topic accessed in the connection.
+          },
+        ],
+        &quot;bigqueryDetails&quot;: [ # Identification of a BigQuery source used in the Dataflow job.
+          { # Metadata for a BigQuery connector used by the job.
+            &quot;dataset&quot;: &quot;A String&quot;, # Dataset accessed in the connection.
+            &quot;projectId&quot;: &quot;A String&quot;, # Project accessed in the connection.
+            &quot;query&quot;: &quot;A String&quot;, # Query used to access data in the connection.
+            &quot;table&quot;: &quot;A String&quot;, # Table accessed in the connection.
+          },
+        ],
+        &quot;fileDetails&quot;: [ # Identification of a File source used in the Dataflow job.
+          { # Metadata for a File connector used by the job.
+            &quot;filePattern&quot;: &quot;A String&quot;, # File Pattern used to access files by the connector.
+          },
+        ],
+        &quot;datastoreDetails&quot;: [ # Identification of a Datastore source used in the Dataflow job.
+          { # Metadata for a Datastore connector used by the job.
+            &quot;namespace&quot;: &quot;A String&quot;, # Namespace used in the connection.
+            &quot;projectId&quot;: &quot;A String&quot;, # ProjectId accessed in the connection.
+          },
+        ],
+        &quot;spannerDetails&quot;: [ # Identification of a Spanner source used in the Dataflow job.
+          { # Metadata for a Spanner connector used by the job.
+            &quot;instanceId&quot;: &quot;A String&quot;, # InstanceId accessed in the connection.
+            &quot;databaseId&quot;: &quot;A String&quot;, # DatabaseId accessed in the connection.
+            &quot;projectId&quot;: &quot;A String&quot;, # ProjectId accessed in the connection.
+          },
+        ],
+      },
+      &quot;location&quot;: &quot;A String&quot;, # The [regional endpoint]
+          # (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that
+          # contains this job.
+      &quot;transformNameMapping&quot;: { # The map of transform name prefixes of the job to be replaced to the
+          # corresponding name prefixes of the new job.
+        &quot;a_key&quot;: &quot;A String&quot;,
+      },
+      &quot;startTime&quot;: &quot;A String&quot;, # The timestamp when the job was started (transitioned to JOB_STATE_PENDING).
+          # Flexible resource scheduling jobs are started with some delay after job
+          # creation, so start_time is unset before start and is updated when the
+          # job is started by the Cloud Dataflow service. For other jobs, start_time
+          # always equals to create_time and is immutable and set by the Cloud Dataflow
+          # service.
+      &quot;clientRequestId&quot;: &quot;A String&quot;, # The client&#x27;s unique identifier of the job, re-used across retried attempts.
+          # If this field is set, the service will ensure its uniqueness.
+          # The request to create a job will fail if the service has knowledge of a
+          # previously submitted job with the same client&#x27;s ID and job name.
+          # The caller may use this field to ensure idempotence of job
+          # creation across retried attempts to create a job.
+          # By default, the field is empty and, in that case, the service ignores it.
+      &quot;executionInfo&quot;: { # Additional information about how a Cloud Dataflow job will be executed that # Deprecated.
+          # isn&#x27;t contained in the submitted job.
+        &quot;stages&quot;: { # A mapping from each stage to the information about that stage.
+          &quot;a_key&quot;: { # Contains information about how a particular
+              # google.dataflow.v1beta3.Step will be executed.
+            &quot;stepName&quot;: [ # The steps associated with the execution stage.
+                # Note that stages may have several steps, and that a given step
+                # might be run by more than one stage.
+              &quot;A String&quot;,
+            ],
+          },
         },
       },
-    },
-    &quot;currentState&quot;: &quot;A String&quot;, # The current state of the job.
-        #
-        # Jobs are created in the `JOB_STATE_STOPPED` state unless otherwise
-        # specified.
-        #
-        # A job in the `JOB_STATE_RUNNING` state may asynchronously enter a
-        # terminal state. After a job has reached a terminal state, no
-        # further state updates may be made.
-        #
-        # This field may be mutated by the Cloud Dataflow service;
-        # callers cannot mutate it.
-    &quot;location&quot;: &quot;A String&quot;, # The [regional endpoint]
-        # (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that
-        # contains this job.
-    &quot;startTime&quot;: &quot;A String&quot;, # The timestamp when the job was started (transitioned to JOB_STATE_PENDING).
-        # Flexible resource scheduling jobs are started with some delay after job
-        # creation, so start_time is unset before start and is updated when the
-        # job is started by the Cloud Dataflow service. For other jobs, start_time
-        # always equals to create_time and is immutable and set by the Cloud Dataflow
-        # service.
-    &quot;stepsLocation&quot;: &quot;A String&quot;, # The GCS location where the steps are stored.
-    &quot;labels&quot;: { # User-defined labels for this job.
-        #
-        # The labels map can contain no more than 64 entries.  Entries of the labels
-        # map are UTF8 strings that comply with the following restrictions:
-        #
-        # * Keys must conform to regexp:  \p{Ll}\p{Lo}{0,62}
-        # * Values must conform to regexp:  [\p{Ll}\p{Lo}\p{N}_-]{0,63}
-        # * Both keys and values are additionally constrained to be &lt;= 128 bytes in
-        # size.
-      &quot;a_key&quot;: &quot;A String&quot;,
-    },
-    &quot;createTime&quot;: &quot;A String&quot;, # The timestamp when the job was initially created. Immutable and set by the
-        # Cloud Dataflow service.
-    &quot;requestedState&quot;: &quot;A String&quot;, # The job&#x27;s requested state.
-        #
-        # `UpdateJob` may be used to switch between the `JOB_STATE_STOPPED` and
-        # `JOB_STATE_RUNNING` states, by setting requested_state.  `UpdateJob` may
-        # also be used to directly set a job&#x27;s requested state to
-        # `JOB_STATE_CANCELLED` or `JOB_STATE_DONE`, irrevocably terminating the
-        # job if it has not already reached a terminal state.
-  }</pre>
+      &quot;type&quot;: &quot;A String&quot;, # The type of Cloud Dataflow job.
+      &quot;createTime&quot;: &quot;A String&quot;, # The timestamp when the job was initially created. Immutable and set by the
+          # Cloud Dataflow service.
+      &quot;tempFiles&quot;: [ # A set of files the system should be aware of that are used
+          # for temporary storage. These temporary files will be
+          # removed on job completion.
+          # No duplicates are allowed.
+          # No file patterns are supported.
+          #
+          # The supported files are:
+          #
+          # Google Cloud Storage:
+          #
+          #    storage.googleapis.com/{bucket}/{object}
+          #    bucket.storage.googleapis.com/{object}
+        &quot;A String&quot;,
+      ],
+      &quot;id&quot;: &quot;A String&quot;, # The unique ID of this job.
+          #
+          # This field is set by the Cloud Dataflow service when the Job is
+          # created, and is immutable for the life of the job.
+      &quot;requestedState&quot;: &quot;A String&quot;, # The job&#x27;s requested state.
+          #
+          # `UpdateJob` may be used to switch between the `JOB_STATE_STOPPED` and
+          # `JOB_STATE_RUNNING` states, by setting requested_state.  `UpdateJob` may
+          # also be used to directly set a job&#x27;s requested state to
+          # `JOB_STATE_CANCELLED` or `JOB_STATE_DONE`, irrevocably terminating the
+          # job if it has not already reached a terminal state.
+      &quot;replaceJobId&quot;: &quot;A String&quot;, # If this job is an update of an existing job, this field is the job ID
+          # of the job it replaced.
+          #
+          # When sending a `CreateJobRequest`, you can update a job by specifying it
+          # here. The job named here is stopped, and its intermediate state is
+          # transferred to this job.
+      &quot;createdFromSnapshotId&quot;: &quot;A String&quot;, # If this is specified, the job&#x27;s initial state is populated from the given
+          # snapshot.
+      &quot;currentState&quot;: &quot;A String&quot;, # The current state of the job.
+          #
+          # Jobs are created in the `JOB_STATE_STOPPED` state unless otherwise
+          # specified.
+          #
+          # A job in the `JOB_STATE_RUNNING` state may asynchronously enter a
+          # terminal state. After a job has reached a terminal state, no
+          # further state updates may be made.
+          #
+          # This field may be mutated by the Cloud Dataflow service;
+          # callers cannot mutate it.
+      &quot;name&quot;: &quot;A String&quot;, # The user-specified Cloud Dataflow job name.
+          #
+          # Only one Job with a given name may exist in a project at any
+          # given time. If a caller attempts to create a Job with the same
+          # name as an already-existing Job, the attempt returns the
+          # existing Job.
+          #
+          # The name must match the regular expression
+          # `[a-z]([-a-z0-9]{0,38}[a-z0-9])?`
+      &quot;currentStateTime&quot;: &quot;A String&quot;, # The timestamp associated with the current state.
+    }</pre>
 </div>
 
 <div class="method">
@@ -2584,45 +2584,30 @@
       # This resource captures only the most recent values of each metric;
       # time-series data can be queried for them (under the same metric names)
       # from Cloud Monitoring.
+    &quot;metricTime&quot;: &quot;A String&quot;, # Timestamp as of which metric values are current.
     &quot;metrics&quot;: [ # All metrics for this job.
       { # Describes the state of a metric.
-        &quot;set&quot;: &quot;&quot;, # Worker-computed aggregate value for the &quot;Set&quot; aggregation kind.  The only
-            # possible value type is a list of Values whose type can be Long, Double,
-            # or String, according to the metric&#x27;s type.  All Values in the list must
-            # be of the same type.
-        &quot;gauge&quot;: &quot;&quot;, # A struct value describing properties of a Gauge.
-            # Metrics of gauge type show the value of a metric across time, and is
-            # aggregated based on the newest value.
-        &quot;cumulative&quot;: True or False, # True if this metric is reported as the total cumulative aggregate
-            # value accumulated since the worker started working on this WorkItem.
-            # By default this is false, indicating that this metric is reported
-            # as a delta that is not associated with any WorkItem.
-        &quot;internal&quot;: &quot;&quot;, # Worker-computed aggregate value for internal use by the Dataflow
-            # service.
+        &quot;distribution&quot;: &quot;&quot;, # A struct value describing properties of a distribution of numeric values.
         &quot;kind&quot;: &quot;A String&quot;, # Metric aggregation kind.  The possible metric aggregation kinds are
             # &quot;Sum&quot;, &quot;Max&quot;, &quot;Min&quot;, &quot;Mean&quot;, &quot;Set&quot;, &quot;And&quot;, &quot;Or&quot;, and &quot;Distribution&quot;.
             # The specified aggregation kind is case-insensitive.
             #
             # If omitted, this is not an aggregated value but instead
             # a single metric sample value.
-        &quot;scalar&quot;: &quot;&quot;, # Worker-computed aggregate value for aggregation kinds &quot;Sum&quot;, &quot;Max&quot;, &quot;Min&quot;,
-            # &quot;And&quot;, and &quot;Or&quot;.  The possible value types are Long, Double, and Boolean.
-        &quot;meanCount&quot;: &quot;&quot;, # Worker-computed aggregate value for the &quot;Mean&quot; aggregation kind.
-            # This holds the count of the aggregated values and is used in combination
-            # with mean_sum above to obtain the actual mean aggregate value.
-            # The only possible value type is Long.
-        &quot;meanSum&quot;: &quot;&quot;, # Worker-computed aggregate value for the &quot;Mean&quot; aggregation kind.
-            # This holds the sum of the aggregated values and is used in combination
-            # with mean_count below to obtain the actual mean aggregate value.
-            # The only possible value types are Long and Double.
+        &quot;gauge&quot;: &quot;&quot;, # A struct value describing properties of a Gauge.
+            # Metrics of gauge type show the value of a metric across time, and is
+            # aggregated based on the newest value.
         &quot;updateTime&quot;: &quot;A String&quot;, # Timestamp associated with the metric value. Optional when workers are
             # reporting work progress; it will be filled in responses from the
             # metrics API.
+        &quot;scalar&quot;: &quot;&quot;, # Worker-computed aggregate value for aggregation kinds &quot;Sum&quot;, &quot;Max&quot;, &quot;Min&quot;,
+            # &quot;And&quot;, and &quot;Or&quot;.  The possible value types are Long, Double, and Boolean.
+        &quot;cumulative&quot;: True or False, # True if this metric is reported as the total cumulative aggregate
+            # value accumulated since the worker started working on this WorkItem.
+            # By default this is false, indicating that this metric is reported
+            # as a delta that is not associated with any WorkItem.
         &quot;name&quot;: { # Identifies a metric, by describing the source which generated the # Name of the metric.
             # metric.
-          &quot;name&quot;: &quot;A String&quot;, # Worker-defined metric name.
-          &quot;origin&quot;: &quot;A String&quot;, # Origin (namespace) of metric name. May be blank for user-define metrics;
-              # will be &quot;dataflow&quot; for metrics defined by the Dataflow service or SDK.
           &quot;context&quot;: { # Zero or more labeled fields which identify the part of the job this
               # metric is associated with, such as the name of a step or collection.
               #
@@ -2631,20 +2616,35 @@
               # in the SDK will have context[&#x27;pcollection&#x27;] = &lt;pcollection-name&gt;.
             &quot;a_key&quot;: &quot;A String&quot;,
           },
+          &quot;name&quot;: &quot;A String&quot;, # Worker-defined metric name.
+          &quot;origin&quot;: &quot;A String&quot;, # Origin (namespace) of metric name. May be blank for user-define metrics;
+              # will be &quot;dataflow&quot; for metrics defined by the Dataflow service or SDK.
         },
-        &quot;distribution&quot;: &quot;&quot;, # A struct value describing properties of a distribution of numeric values.
+        &quot;meanCount&quot;: &quot;&quot;, # Worker-computed aggregate value for the &quot;Mean&quot; aggregation kind.
+            # This holds the count of the aggregated values and is used in combination
+            # with mean_sum above to obtain the actual mean aggregate value.
+            # The only possible value type is Long.
+        &quot;meanSum&quot;: &quot;&quot;, # Worker-computed aggregate value for the &quot;Mean&quot; aggregation kind.
+            # This holds the sum of the aggregated values and is used in combination
+            # with mean_count below to obtain the actual mean aggregate value.
+            # The only possible value types are Long and Double.
+        &quot;set&quot;: &quot;&quot;, # Worker-computed aggregate value for the &quot;Set&quot; aggregation kind.  The only
+            # possible value type is a list of Values whose type can be Long, Double,
+            # or String, according to the metric&#x27;s type.  All Values in the list must
+            # be of the same type.
+        &quot;internal&quot;: &quot;&quot;, # Worker-computed aggregate value for internal use by the Dataflow
+            # service.
       },
     ],
-    &quot;metricTime&quot;: &quot;A String&quot;, # Timestamp as of which metric values are current.
   }</pre>
 </div>
 
 <div class="method">
-    <code class="details" id="list">list(projectId, filter=None, location=None, pageToken=None, pageSize=None, view=None, x__xgafv=None)</code>
+    <code class="details" id="list">list(projectId, filter=None, pageSize=None, location=None, view=None, pageToken=None, x__xgafv=None)</code>
   <pre>List the jobs of a project.
 
 To list the jobs of a project in a region, we recommend using
-`projects.locations.jobs.get` with a [regional endpoint]
+`projects.locations.jobs.list` with a [regional endpoint]
 (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints). To
 list the all jobs across all regions, use `projects.jobs.aggregated`. Using
 `projects.jobs.list` is not recommended, as you can only get the list of
@@ -2653,15 +2653,15 @@
 Args:
   projectId: string, The project which owns the jobs. (required)
   filter: string, The kind of filter to use.
-  location: string, The [regional endpoint]
-(https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that
-contains this job.
-  pageToken: string, Set this to the &#x27;next_page_token&#x27; field of a previous response
-to request additional results in a long list.
   pageSize: integer, If there are many jobs, limit response to at most this many.
 The actual number of jobs returned will be the lesser of max_responses
 and an unspecified server-defined limit.
+  location: string, The [regional endpoint]
+(https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that
+contains this job.
   view: string, Level of information requested in response. Default is `JOB_VIEW_SUMMARY`.
+  pageToken: string, Set this to the &#x27;next_page_token&#x27; field of a previous response
+to request additional results in a long list.
   x__xgafv: string, V1 error format.
     Allowed values
       1 - v1 error format
@@ -2677,243 +2677,285 @@
       # body is empty {}.
     &quot;jobs&quot;: [ # A subset of the requested job information.
       { # Defines a job to be run by the Cloud Dataflow service.
-        &quot;clientRequestId&quot;: &quot;A String&quot;, # The client&#x27;s unique identifier of the job, re-used across retried attempts.
-            # If this field is set, the service will ensure its uniqueness.
-            # The request to create a job will fail if the service has knowledge of a
-            # previously submitted job with the same client&#x27;s ID and job name.
-            # The caller may use this field to ensure idempotence of job
-            # creation across retried attempts to create a job.
-            # By default, the field is empty and, in that case, the service ignores it.
-        &quot;id&quot;: &quot;A String&quot;, # The unique ID of this job.
-            #
-            # This field is set by the Cloud Dataflow service when the Job is
-            # created, and is immutable for the life of the job.
-        &quot;currentStateTime&quot;: &quot;A String&quot;, # The timestamp associated with the current state.
-        &quot;transformNameMapping&quot;: { # The map of transform name prefixes of the job to be replaced to the
-            # corresponding name prefixes of the new job.
-          &quot;a_key&quot;: &quot;A String&quot;,
-        },
-        &quot;environment&quot;: { # Describes the environment in which a Dataflow Job runs. # The environment for the job.
-          &quot;internalExperiments&quot;: { # Experimental settings.
-            &quot;a_key&quot;: &quot;&quot;, # Properties of the object. Contains field @type with type URL.
-          },
-          &quot;workerRegion&quot;: &quot;A String&quot;, # The Compute Engine region
-              # (https://cloud.google.com/compute/docs/regions-zones/regions-zones) in
-              # which worker processing should occur, e.g. &quot;us-west1&quot;. Mutually exclusive
-              # with worker_zone. If neither worker_region nor worker_zone is specified,
-              # default to the control plane&#x27;s region.
-          &quot;serviceKmsKeyName&quot;: &quot;A String&quot;, # If set, contains the Cloud KMS key identifier used to encrypt data
-              # at rest, AKA a Customer Managed Encryption Key (CMEK).
-              #
-              # Format:
-              #   projects/PROJECT_ID/locations/LOCATION/keyRings/KEY_RING/cryptoKeys/KEY
-          &quot;userAgent&quot;: { # A description of the process that generated the request.
-            &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
-          },
-          &quot;workerZone&quot;: &quot;A String&quot;, # The Compute Engine zone
-              # (https://cloud.google.com/compute/docs/regions-zones/regions-zones) in
-              # which worker processing should occur, e.g. &quot;us-west1-a&quot;. Mutually exclusive
-              # with worker_region. If neither worker_region nor worker_zone is specified,
-              # a zone in the control plane&#x27;s region is chosen based on available capacity.
-          &quot;clusterManagerApiService&quot;: &quot;A String&quot;, # The type of cluster manager API to use.  If unknown or
-              # unspecified, the service will attempt to choose a reasonable
-              # default.  This should be in the form of the API service name,
-              # e.g. &quot;compute.googleapis.com&quot;.
-          &quot;tempStoragePrefix&quot;: &quot;A String&quot;, # The prefix of the resources the system should use for temporary
-              # storage.  The system will append the suffix &quot;/temp-{JOBNAME} to
-              # this resource prefix, where {JOBNAME} is the value of the
-              # job_name field.  The resulting bucket and object prefix is used
-              # as the prefix of the resources used to store temporary data
-              # needed during the job execution.  NOTE: This will override the
-              # value in taskrunner_settings.
-              # The supported resource type is:
-              #
-              # Google Cloud Storage:
-              #
-              #   storage.googleapis.com/{bucket}/{object}
-              #   bucket.storage.googleapis.com/{object}
-          &quot;experiments&quot;: [ # The list of experiments to enable.
-            &quot;A String&quot;,
-          ],
-          &quot;version&quot;: { # A structure describing which components and their versions of the service
-              # are required in order to run the job.
-            &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
-          },
-          &quot;serviceAccountEmail&quot;: &quot;A String&quot;, # Identity to run virtual machines as. Defaults to the default account.
-          &quot;sdkPipelineOptions&quot;: { # The Cloud Dataflow SDK pipeline options specified by the user. These
-              # options are passed through the service and are used to recreate the
-              # SDK pipeline options on the worker in a language agnostic and platform
-              # independent way.
-            &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
-          },
-          &quot;flexResourceSchedulingGoal&quot;: &quot;A String&quot;, # Which Flexible Resource Scheduling mode to run in.
-          &quot;workerPools&quot;: [ # The worker pools. At least one &quot;harness&quot; worker pool must be
-              # specified in order for the job to have workers.
-            { # Describes one particular pool of Cloud Dataflow workers to be
-                # instantiated by the Cloud Dataflow service in order to perform the
-                # computations required by a job.  Note that a workflow job may use
-                # multiple pools, in order to match the various computational
-                # requirements of the various stages of the job.
-              &quot;numThreadsPerWorker&quot;: 42, # The number of threads per worker harness. If empty or unspecified, the
-                  # service will choose a number of threads (according to the number of cores
-                  # on the selected machine type for batch, or 1 by convention for streaming).
-              &quot;numWorkers&quot;: 42, # Number of Google Compute Engine workers in this pool needed to
-                  # execute the job.  If zero or unspecified, the service will
-                  # attempt to choose a reasonable default.
-              &quot;zone&quot;: &quot;A String&quot;, # Zone to run the worker pools in.  If empty or unspecified, the service
-                  # will attempt to choose a reasonable default.
-              &quot;diskSourceImage&quot;: &quot;A String&quot;, # Fully qualified source image for disks.
-              &quot;packages&quot;: [ # Packages to be installed on workers.
-                { # The packages that must be installed in order for a worker to run the
-                    # steps of the Cloud Dataflow job that will be assigned to its worker
-                    # pool.
-                    #
-                    # This is the mechanism by which the Cloud Dataflow SDK causes code to
-                    # be loaded onto the workers. For example, the Cloud Dataflow Java SDK
-                    # might use this to install jars containing the user&#x27;s code and all of the
-                    # various dependencies (libraries, data files, etc.) required in order
-                    # for that code to run.
-                  &quot;name&quot;: &quot;A String&quot;, # The name of the package.
-                  &quot;location&quot;: &quot;A String&quot;, # The resource to read the package from. The supported resource type is:
-                      #
-                      # Google Cloud Storage:
-                      #
-                      #   storage.googleapis.com/{bucket}
-                      #   bucket.storage.googleapis.com/
-                },
-              ],
-              &quot;teardownPolicy&quot;: &quot;A String&quot;, # Sets the policy for determining when to turndown worker pool.
-                  # Allowed values are: `TEARDOWN_ALWAYS`, `TEARDOWN_ON_SUCCESS`, and
-                  # `TEARDOWN_NEVER`.
-                  # `TEARDOWN_ALWAYS` means workers are always torn down regardless of whether
-                  # the job succeeds. `TEARDOWN_ON_SUCCESS` means workers are torn down
-                  # if the job succeeds. `TEARDOWN_NEVER` means the workers are never torn
-                  # down.
-                  #
-                  # If the workers are not torn down by the service, they will
-                  # continue to run and use Google Compute Engine VM resources in the
-                  # user&#x27;s project until they are explicitly terminated by the user.
-                  # Because of this, Google recommends using the `TEARDOWN_ALWAYS`
-                  # policy except for small, manually supervised test jobs.
-                  #
-                  # If unknown or unspecified, the service will attempt to choose a reasonable
-                  # default.
-              &quot;onHostMaintenance&quot;: &quot;A String&quot;, # The action to take on host maintenance, as defined by the Google
-                  # Compute Engine API.
-              &quot;poolArgs&quot;: { # Extra arguments for this worker pool.
-                &quot;a_key&quot;: &quot;&quot;, # Properties of the object. Contains field @type with type URL.
+          &quot;pipelineDescription&quot;: { # A descriptive representation of submitted pipeline as well as the executed # Preliminary field: The format of this data may change at any time.
+              # A description of the user pipeline and stages through which it is executed.
+              # Created by Cloud Dataflow service.  Only retrieved with
+              # JOB_VIEW_DESCRIPTION or JOB_VIEW_ALL.
+              # form.  This data is provided by the Dataflow service for ease of visualizing
+              # the pipeline and interpreting Dataflow provided metrics.
+            &quot;displayData&quot;: [ # Pipeline level display data.
+              { # Data provided with a pipeline or transform to provide descriptive info.
+                &quot;url&quot;: &quot;A String&quot;, # An optional full URL.
+                &quot;javaClassValue&quot;: &quot;A String&quot;, # Contains value if the data is of java class type.
+                &quot;timestampValue&quot;: &quot;A String&quot;, # Contains value if the data is of timestamp type.
+                &quot;durationValue&quot;: &quot;A String&quot;, # Contains value if the data is of duration type.
+                &quot;label&quot;: &quot;A String&quot;, # An optional label to display in a dax UI for the element.
+                &quot;key&quot;: &quot;A String&quot;, # The key identifying the display data.
+                    # This is intended to be used as a label for the display data
+                    # when viewed in a dax monitoring system.
+                &quot;namespace&quot;: &quot;A String&quot;, # The namespace for the key. This is usually a class name or programming
+                    # language namespace (i.e. python module) which defines the display data.
+                    # This allows a dax monitoring system to specially handle the data
+                    # and perform custom rendering.
+                &quot;floatValue&quot;: 3.14, # Contains value if the data is of float type.
+                &quot;strValue&quot;: &quot;A String&quot;, # Contains value if the data is of string type.
+                &quot;int64Value&quot;: &quot;A String&quot;, # Contains value if the data is of int64 type.
+                &quot;boolValue&quot;: True or False, # Contains value if the data is of a boolean type.
+                &quot;shortStrValue&quot;: &quot;A String&quot;, # A possible additional shorter value to display.
+                    # For example a java_class_name_value of com.mypackage.MyDoFn
+                    # will be stored with MyDoFn as the short_str_value and
+                    # com.mypackage.MyDoFn as the java_class_name value.
+                    # short_str_value can be displayed and java_class_name_value
+                    # will be displayed as a tooltip.
               },
-              &quot;diskSizeGb&quot;: 42, # Size of root disk for VMs, in GB.  If zero or unspecified, the service will
-                  # attempt to choose a reasonable default.
-              &quot;workerHarnessContainerImage&quot;: &quot;A String&quot;, # Required. Docker container image that executes the Cloud Dataflow worker
-                  # harness, residing in Google Container Registry.
-                  #
-                  # Deprecated for the Fn API path. Use sdk_harness_container_images instead.
-              &quot;diskType&quot;: &quot;A String&quot;, # Type of root disk for VMs.  If empty or unspecified, the service will
-                  # attempt to choose a reasonable default.
-              &quot;machineType&quot;: &quot;A String&quot;, # Machine type (e.g. &quot;n1-standard-1&quot;).  If empty or unspecified, the
-                  # service will attempt to choose a reasonable default.
-              &quot;kind&quot;: &quot;A String&quot;, # The kind of the worker pool; currently only `harness` and `shuffle`
-                  # are supported.
-              &quot;sdkHarnessContainerImages&quot;: [ # Set of SDK harness containers needed to execute this pipeline. This will
-                  # only be set in the Fn API path. For non-cross-language pipelines this
-                  # should have only one entry. Cross-language pipelines will have two or more
-                  # entries.
-                { # Defines a SDK harness container for executing Dataflow pipelines.
-                  &quot;containerImage&quot;: &quot;A String&quot;, # A docker container image that resides in Google Container Registry.
-                  &quot;useSingleCorePerContainer&quot;: True or False, # If true, recommends the Dataflow service to use only one core per SDK
-                      # container instance with this image. If false (or unset) recommends using
-                      # more than one core per SDK container instance with this image for
-                      # efficiency. Note that Dataflow service may choose to override this property
-                      # if needed.
-                },
-              ],
-              &quot;dataDisks&quot;: [ # Data disks that are used by a VM in this workflow.
-                { # Describes the data disk used by a workflow job.
-                  &quot;diskType&quot;: &quot;A String&quot;, # Disk storage type, as defined by Google Compute Engine.  This
-                      # must be a disk type appropriate to the project and zone in which
-                      # the workers will run.  If unknown or unspecified, the service
-                      # will attempt to choose a reasonable default.
-                      #
-                      # For example, the standard persistent disk type is a resource name
-                      # typically ending in &quot;pd-standard&quot;.  If SSD persistent disks are
-                      # available, the resource name typically ends with &quot;pd-ssd&quot;.  The
-                      # actual valid values are defined the Google Compute Engine API,
-                      # not by the Cloud Dataflow API; consult the Google Compute Engine
-                      # documentation for more information about determining the set of
-                      # available disk types for a particular project and zone.
-                      #
-                      # Google Compute Engine Disk types are local to a particular
-                      # project in a particular zone, and so the resource name will
-                      # typically look something like this:
-                      #
-                      # compute.googleapis.com/projects/project-id/zones/zone/diskTypes/pd-standard
-                  &quot;sizeGb&quot;: 42, # Size of disk in GB.  If zero or unspecified, the service will
-                      # attempt to choose a reasonable default.
-                  &quot;mountPoint&quot;: &quot;A String&quot;, # Directory in a VM where disk is mounted.
-                },
-              ],
-              &quot;subnetwork&quot;: &quot;A String&quot;, # Subnetwork to which VMs will be assigned, if desired.  Expected to be of
-                  # the form &quot;regions/REGION/subnetworks/SUBNETWORK&quot;.
-              &quot;ipConfiguration&quot;: &quot;A String&quot;, # Configuration for VM IPs.
-              &quot;taskrunnerSettings&quot;: { # Taskrunner configuration settings. # Settings passed through to Google Compute Engine workers when
-                  # using the standard Dataflow task runner.  Users should ignore
-                  # this field.
-                &quot;alsologtostderr&quot;: True or False, # Whether to also send taskrunner log info to stderr.
-                &quot;taskGroup&quot;: &quot;A String&quot;, # The UNIX group ID on the worker VM to use for tasks launched by
-                    # taskrunner; e.g. &quot;wheel&quot;.
-                &quot;harnessCommand&quot;: &quot;A String&quot;, # The command to launch the worker harness.
-                &quot;logDir&quot;: &quot;A String&quot;, # The directory on the VM to store logs.
-                &quot;oauthScopes&quot;: [ # The OAuth2 scopes to be requested by the taskrunner in order to
-                    # access the Cloud Dataflow API.
+            ],
+            &quot;originalPipelineTransform&quot;: [ # Description of each transform in the pipeline and collections between them.
+              { # Description of the type, names/ids, and input/outputs for a transform.
+                &quot;outputCollectionName&quot;: [ # User  names for all collection outputs to this transform.
                   &quot;A String&quot;,
                 ],
-                &quot;dataflowApiVersion&quot;: &quot;A String&quot;, # The API version of endpoint, e.g. &quot;v1b3&quot;
-                &quot;logUploadLocation&quot;: &quot;A String&quot;, # Indicates where to put logs.  If this is not specified, the logs
-                    # will not be uploaded.
-                    #
-                    # The supported resource type is:
-                    #
-                    # Google Cloud Storage:
-                    #   storage.googleapis.com/{bucket}/{object}
-                    #   bucket.storage.googleapis.com/{object}
-                &quot;streamingWorkerMainClass&quot;: &quot;A String&quot;, # The streaming worker main class name.
-                &quot;workflowFileName&quot;: &quot;A String&quot;, # The file to store the workflow in.
-                &quot;languageHint&quot;: &quot;A String&quot;, # The suggested backend language.
-                &quot;commandlinesFileName&quot;: &quot;A String&quot;, # The file to store preprocessing commands in.
-                &quot;baseTaskDir&quot;: &quot;A String&quot;, # The location on the worker for task-specific subdirectories.
-                &quot;tempStoragePrefix&quot;: &quot;A String&quot;, # The prefix of the resources the taskrunner should use for
-                    # temporary storage.
-                    #
-                    # The supported resource type is:
-                    #
-                    # Google Cloud Storage:
-                    #   storage.googleapis.com/{bucket}/{object}
-                    #   bucket.storage.googleapis.com/{object}
-                &quot;baseUrl&quot;: &quot;A String&quot;, # The base URL for the taskrunner to use when accessing Google Cloud APIs.
-                    #
-                    # When workers access Google Cloud APIs, they logically do so via
-                    # relative URLs.  If this field is specified, it supplies the base
-                    # URL to use for resolving these relative URLs.  The normative
-                    # algorithm used is defined by RFC 1808, &quot;Relative Uniform Resource
-                    # Locators&quot;.
-                    #
-                    # If not specified, the default value is &quot;http://www.googleapis.com/&quot;
-                &quot;logToSerialconsole&quot;: True or False, # Whether to send taskrunner log info to Google Compute Engine VM serial
-                    # console.
-                &quot;continueOnException&quot;: True or False, # Whether to continue taskrunner if an exception is hit.
-                &quot;parallelWorkerSettings&quot;: { # Provides data to pass through to the worker harness. # The settings to pass to the parallel worker harness.
-                  &quot;tempStoragePrefix&quot;: &quot;A String&quot;, # The prefix of the resources the system should use for temporary
-                      # storage.
+                &quot;displayData&quot;: [ # Transform-specific display data.
+                  { # Data provided with a pipeline or transform to provide descriptive info.
+                    &quot;url&quot;: &quot;A String&quot;, # An optional full URL.
+                    &quot;javaClassValue&quot;: &quot;A String&quot;, # Contains value if the data is of java class type.
+                    &quot;timestampValue&quot;: &quot;A String&quot;, # Contains value if the data is of timestamp type.
+                    &quot;durationValue&quot;: &quot;A String&quot;, # Contains value if the data is of duration type.
+                    &quot;label&quot;: &quot;A String&quot;, # An optional label to display in a dax UI for the element.
+                    &quot;key&quot;: &quot;A String&quot;, # The key identifying the display data.
+                        # This is intended to be used as a label for the display data
+                        # when viewed in a dax monitoring system.
+                    &quot;namespace&quot;: &quot;A String&quot;, # The namespace for the key. This is usually a class name or programming
+                        # language namespace (i.e. python module) which defines the display data.
+                        # This allows a dax monitoring system to specially handle the data
+                        # and perform custom rendering.
+                    &quot;floatValue&quot;: 3.14, # Contains value if the data is of float type.
+                    &quot;strValue&quot;: &quot;A String&quot;, # Contains value if the data is of string type.
+                    &quot;int64Value&quot;: &quot;A String&quot;, # Contains value if the data is of int64 type.
+                    &quot;boolValue&quot;: True or False, # Contains value if the data is of a boolean type.
+                    &quot;shortStrValue&quot;: &quot;A String&quot;, # A possible additional shorter value to display.
+                        # For example a java_class_name_value of com.mypackage.MyDoFn
+                        # will be stored with MyDoFn as the short_str_value and
+                        # com.mypackage.MyDoFn as the java_class_name value.
+                        # short_str_value can be displayed and java_class_name_value
+                        # will be displayed as a tooltip.
+                  },
+                ],
+                &quot;id&quot;: &quot;A String&quot;, # SDK generated id of this transform instance.
+                &quot;inputCollectionName&quot;: [ # User names for all collection inputs to this transform.
+                  &quot;A String&quot;,
+                ],
+                &quot;name&quot;: &quot;A String&quot;, # User provided name for this transform instance.
+                &quot;kind&quot;: &quot;A String&quot;, # Type of transform.
+              },
+            ],
+            &quot;executionPipelineStage&quot;: [ # Description of each stage of execution of the pipeline.
+              { # Description of the composing transforms, names/ids, and input/outputs of a
+                  # stage of execution.  Some composing transforms and sources may have been
+                  # generated by the Dataflow service during execution planning.
+                &quot;componentSource&quot;: [ # Collections produced and consumed by component transforms of this stage.
+                  { # Description of an interstitial value between transforms in an execution
+                      # stage.
+                    &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this transform; may be user or system generated.
+                    &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
+                    &quot;originalTransformOrCollection&quot;: &quot;A String&quot;, # User name for the original user transform or collection with which this
+                        # source is most closely associated.
+                  },
+                ],
+                &quot;inputSource&quot;: [ # Input sources for this stage.
+                  { # Description of an input or output of an execution stage.
+                    &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this source; may be user or system generated.
+                    &quot;originalTransformOrCollection&quot;: &quot;A String&quot;, # User name for the original user transform or collection with which this
+                        # source is most closely associated.
+                    &quot;sizeBytes&quot;: &quot;A String&quot;, # Size of the source, if measurable.
+                    &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
+                  },
+                ],
+                &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this stage.
+                &quot;componentTransform&quot;: [ # Transforms that comprise this execution stage.
+                  { # Description of a transform executed as part of an execution stage.
+                    &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
+                    &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this transform; may be user or system generated.
+                    &quot;originalTransform&quot;: &quot;A String&quot;, # User name for the original user transform with which this transform is
+                        # most closely associated.
+                  },
+                ],
+                &quot;id&quot;: &quot;A String&quot;, # Dataflow service generated id for this stage.
+                &quot;outputSource&quot;: [ # Output sources for this stage.
+                  { # Description of an input or output of an execution stage.
+                    &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this source; may be user or system generated.
+                    &quot;originalTransformOrCollection&quot;: &quot;A String&quot;, # User name for the original user transform or collection with which this
+                        # source is most closely associated.
+                    &quot;sizeBytes&quot;: &quot;A String&quot;, # Size of the source, if measurable.
+                    &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
+                  },
+                ],
+                &quot;kind&quot;: &quot;A String&quot;, # Type of tranform this stage is executing.
+              },
+            ],
+          },
+          &quot;labels&quot;: { # User-defined labels for this job.
+              #
+              # The labels map can contain no more than 64 entries.  Entries of the labels
+              # map are UTF8 strings that comply with the following restrictions:
+              #
+              # * Keys must conform to regexp:  \p{Ll}\p{Lo}{0,62}
+              # * Values must conform to regexp:  [\p{Ll}\p{Lo}\p{N}_-]{0,63}
+              # * Both keys and values are additionally constrained to be &lt;= 128 bytes in
+              # size.
+            &quot;a_key&quot;: &quot;A String&quot;,
+          },
+          &quot;projectId&quot;: &quot;A String&quot;, # The ID of the Cloud Platform project that the job belongs to.
+          &quot;environment&quot;: { # Describes the environment in which a Dataflow Job runs. # The environment for the job.
+            &quot;flexResourceSchedulingGoal&quot;: &quot;A String&quot;, # Which Flexible Resource Scheduling mode to run in.
+            &quot;workerRegion&quot;: &quot;A String&quot;, # The Compute Engine region
+                # (https://cloud.google.com/compute/docs/regions-zones/regions-zones) in
+                # which worker processing should occur, e.g. &quot;us-west1&quot;. Mutually exclusive
+                # with worker_zone. If neither worker_region nor worker_zone is specified,
+                # default to the control plane&#x27;s region.
+            &quot;userAgent&quot;: { # A description of the process that generated the request.
+              &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
+            },
+            &quot;serviceAccountEmail&quot;: &quot;A String&quot;, # Identity to run virtual machines as. Defaults to the default account.
+            &quot;version&quot;: { # A structure describing which components and their versions of the service
+                # are required in order to run the job.
+              &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
+            },
+            &quot;serviceKmsKeyName&quot;: &quot;A String&quot;, # If set, contains the Cloud KMS key identifier used to encrypt data
+                # at rest, AKA a Customer Managed Encryption Key (CMEK).
+                #
+                # Format:
+                #   projects/PROJECT_ID/locations/LOCATION/keyRings/KEY_RING/cryptoKeys/KEY
+            &quot;experiments&quot;: [ # The list of experiments to enable.
+              &quot;A String&quot;,
+            ],
+            &quot;workerZone&quot;: &quot;A String&quot;, # The Compute Engine zone
+                # (https://cloud.google.com/compute/docs/regions-zones/regions-zones) in
+                # which worker processing should occur, e.g. &quot;us-west1-a&quot;. Mutually exclusive
+                # with worker_region. If neither worker_region nor worker_zone is specified,
+                # a zone in the control plane&#x27;s region is chosen based on available capacity.
+            &quot;workerPools&quot;: [ # The worker pools. At least one &quot;harness&quot; worker pool must be
+                # specified in order for the job to have workers.
+              { # Describes one particular pool of Cloud Dataflow workers to be
+                  # instantiated by the Cloud Dataflow service in order to perform the
+                  # computations required by a job.  Note that a workflow job may use
+                  # multiple pools, in order to match the various computational
+                  # requirements of the various stages of the job.
+                &quot;onHostMaintenance&quot;: &quot;A String&quot;, # The action to take on host maintenance, as defined by the Google
+                    # Compute Engine API.
+                &quot;sdkHarnessContainerImages&quot;: [ # Set of SDK harness containers needed to execute this pipeline. This will
+                    # only be set in the Fn API path. For non-cross-language pipelines this
+                    # should have only one entry. Cross-language pipelines will have two or more
+                    # entries.
+                  { # Defines a SDK harness container for executing Dataflow pipelines.
+                    &quot;containerImage&quot;: &quot;A String&quot;, # A docker container image that resides in Google Container Registry.
+                    &quot;useSingleCorePerContainer&quot;: True or False, # If true, recommends the Dataflow service to use only one core per SDK
+                        # container instance with this image. If false (or unset) recommends using
+                        # more than one core per SDK container instance with this image for
+                        # efficiency. Note that Dataflow service may choose to override this property
+                        # if needed.
+                  },
+                ],
+                &quot;zone&quot;: &quot;A String&quot;, # Zone to run the worker pools in.  If empty or unspecified, the service
+                    # will attempt to choose a reasonable default.
+                &quot;kind&quot;: &quot;A String&quot;, # The kind of the worker pool; currently only `harness` and `shuffle`
+                    # are supported.
+                &quot;metadata&quot;: { # Metadata to set on the Google Compute Engine VMs.
+                  &quot;a_key&quot;: &quot;A String&quot;,
+                },
+                &quot;diskSourceImage&quot;: &quot;A String&quot;, # Fully qualified source image for disks.
+                &quot;dataDisks&quot;: [ # Data disks that are used by a VM in this workflow.
+                  { # Describes the data disk used by a workflow job.
+                    &quot;sizeGb&quot;: 42, # Size of disk in GB.  If zero or unspecified, the service will
+                        # attempt to choose a reasonable default.
+                    &quot;diskType&quot;: &quot;A String&quot;, # Disk storage type, as defined by Google Compute Engine.  This
+                        # must be a disk type appropriate to the project and zone in which
+                        # the workers will run.  If unknown or unspecified, the service
+                        # will attempt to choose a reasonable default.
+                        #
+                        # For example, the standard persistent disk type is a resource name
+                        # typically ending in &quot;pd-standard&quot;.  If SSD persistent disks are
+                        # available, the resource name typically ends with &quot;pd-ssd&quot;.  The
+                        # actual valid values are defined the Google Compute Engine API,
+                        # not by the Cloud Dataflow API; consult the Google Compute Engine
+                        # documentation for more information about determining the set of
+                        # available disk types for a particular project and zone.
+                        #
+                        # Google Compute Engine Disk types are local to a particular
+                        # project in a particular zone, and so the resource name will
+                        # typically look something like this:
+                        #
+                        # compute.googleapis.com/projects/project-id/zones/zone/diskTypes/pd-standard
+                    &quot;mountPoint&quot;: &quot;A String&quot;, # Directory in a VM where disk is mounted.
+                  },
+                ],
+                &quot;packages&quot;: [ # Packages to be installed on workers.
+                  { # The packages that must be installed in order for a worker to run the
+                      # steps of the Cloud Dataflow job that will be assigned to its worker
+                      # pool.
                       #
-                      # The supported resource type is:
-                      #
-                      # Google Cloud Storage:
-                      #
-                      #   storage.googleapis.com/{bucket}/{object}
-                      #   bucket.storage.googleapis.com/{object}
-                  &quot;reportingEnabled&quot;: True or False, # Whether to send work progress updates to the service.
-                  &quot;baseUrl&quot;: &quot;A String&quot;, # The base URL for accessing Google Cloud APIs.
+                      # This is the mechanism by which the Cloud Dataflow SDK causes code to
+                      # be loaded onto the workers. For example, the Cloud Dataflow Java SDK
+                      # might use this to install jars containing the user&#x27;s code and all of the
+                      # various dependencies (libraries, data files, etc.) required in order
+                      # for that code to run.
+                    &quot;name&quot;: &quot;A String&quot;, # The name of the package.
+                    &quot;location&quot;: &quot;A String&quot;, # The resource to read the package from. The supported resource type is:
+                        #
+                        # Google Cloud Storage:
+                        #
+                        #   storage.googleapis.com/{bucket}
+                        #   bucket.storage.googleapis.com/
+                  },
+                ],
+                &quot;teardownPolicy&quot;: &quot;A String&quot;, # Sets the policy for determining when to turndown worker pool.
+                    # Allowed values are: `TEARDOWN_ALWAYS`, `TEARDOWN_ON_SUCCESS`, and
+                    # `TEARDOWN_NEVER`.
+                    # `TEARDOWN_ALWAYS` means workers are always torn down regardless of whether
+                    # the job succeeds. `TEARDOWN_ON_SUCCESS` means workers are torn down
+                    # if the job succeeds. `TEARDOWN_NEVER` means the workers are never torn
+                    # down.
+                    #
+                    # If the workers are not torn down by the service, they will
+                    # continue to run and use Google Compute Engine VM resources in the
+                    # user&#x27;s project until they are explicitly terminated by the user.
+                    # Because of this, Google recommends using the `TEARDOWN_ALWAYS`
+                    # policy except for small, manually supervised test jobs.
+                    #
+                    # If unknown or unspecified, the service will attempt to choose a reasonable
+                    # default.
+                &quot;network&quot;: &quot;A String&quot;, # Network to which VMs will be assigned.  If empty or unspecified,
+                    # the service will use the network &quot;default&quot;.
+                &quot;ipConfiguration&quot;: &quot;A String&quot;, # Configuration for VM IPs.
+                &quot;diskSizeGb&quot;: 42, # Size of root disk for VMs, in GB.  If zero or unspecified, the service will
+                    # attempt to choose a reasonable default.
+                &quot;autoscalingSettings&quot;: { # Settings for WorkerPool autoscaling. # Settings for autoscaling of this WorkerPool.
+                  &quot;maxNumWorkers&quot;: 42, # The maximum number of workers to cap scaling at.
+                  &quot;algorithm&quot;: &quot;A String&quot;, # The algorithm to use for autoscaling.
+                },
+                &quot;poolArgs&quot;: { # Extra arguments for this worker pool.
+                  &quot;a_key&quot;: &quot;&quot;, # Properties of the object. Contains field @type with type URL.
+                },
+                &quot;subnetwork&quot;: &quot;A String&quot;, # Subnetwork to which VMs will be assigned, if desired.  Expected to be of
+                    # the form &quot;regions/REGION/subnetworks/SUBNETWORK&quot;.
+                &quot;numWorkers&quot;: 42, # Number of Google Compute Engine workers in this pool needed to
+                    # execute the job.  If zero or unspecified, the service will
+                    # attempt to choose a reasonable default.
+                &quot;numThreadsPerWorker&quot;: 42, # The number of threads per worker harness. If empty or unspecified, the
+                    # service will choose a number of threads (according to the number of cores
+                    # on the selected machine type for batch, or 1 by convention for streaming).
+                &quot;workerHarnessContainerImage&quot;: &quot;A String&quot;, # Required. Docker container image that executes the Cloud Dataflow worker
+                    # harness, residing in Google Container Registry.
+                    #
+                    # Deprecated for the Fn API path. Use sdk_harness_container_images instead.
+                &quot;taskrunnerSettings&quot;: { # Taskrunner configuration settings. # Settings passed through to Google Compute Engine workers when
+                    # using the standard Dataflow task runner.  Users should ignore
+                    # this field.
+                  &quot;dataflowApiVersion&quot;: &quot;A String&quot;, # The API version of endpoint, e.g. &quot;v1b3&quot;
+                  &quot;oauthScopes&quot;: [ # The OAuth2 scopes to be requested by the taskrunner in order to
+                      # access the Cloud Dataflow API.
+                    &quot;A String&quot;,
+                  ],
+                  &quot;baseUrl&quot;: &quot;A String&quot;, # The base URL for the taskrunner to use when accessing Google Cloud APIs.
                       #
                       # When workers access Google Cloud APIs, they logically do so via
                       # relative URLs.  If this field is specified, it supplies the base
@@ -2922,340 +2964,299 @@
                       # Locators&quot;.
                       #
                       # If not specified, the default value is &quot;http://www.googleapis.com/&quot;
-                  &quot;servicePath&quot;: &quot;A String&quot;, # The Cloud Dataflow service path relative to the root URL, for example,
-                      # &quot;dataflow/v1b3/projects&quot;.
-                  &quot;shuffleServicePath&quot;: &quot;A String&quot;, # The Shuffle service path relative to the root URL, for example,
-                      # &quot;shuffle/v1beta1&quot;.
-                  &quot;workerId&quot;: &quot;A String&quot;, # The ID of the worker running this pipeline.
+                  &quot;workflowFileName&quot;: &quot;A String&quot;, # The file to store the workflow in.
+                  &quot;logToSerialconsole&quot;: True or False, # Whether to send taskrunner log info to Google Compute Engine VM serial
+                      # console.
+                  &quot;baseTaskDir&quot;: &quot;A String&quot;, # The location on the worker for task-specific subdirectories.
+                  &quot;taskUser&quot;: &quot;A String&quot;, # The UNIX user ID on the worker VM to use for tasks launched by
+                      # taskrunner; e.g. &quot;root&quot;.
+                  &quot;vmId&quot;: &quot;A String&quot;, # The ID string of the VM.
+                  &quot;alsologtostderr&quot;: True or False, # Whether to also send taskrunner log info to stderr.
+                  &quot;parallelWorkerSettings&quot;: { # Provides data to pass through to the worker harness. # The settings to pass to the parallel worker harness.
+                    &quot;shuffleServicePath&quot;: &quot;A String&quot;, # The Shuffle service path relative to the root URL, for example,
+                        # &quot;shuffle/v1beta1&quot;.
+                    &quot;tempStoragePrefix&quot;: &quot;A String&quot;, # The prefix of the resources the system should use for temporary
+                        # storage.
+                        #
+                        # The supported resource type is:
+                        #
+                        # Google Cloud Storage:
+                        #
+                        #   storage.googleapis.com/{bucket}/{object}
+                        #   bucket.storage.googleapis.com/{object}
+                    &quot;reportingEnabled&quot;: True or False, # Whether to send work progress updates to the service.
+                    &quot;servicePath&quot;: &quot;A String&quot;, # The Cloud Dataflow service path relative to the root URL, for example,
+                        # &quot;dataflow/v1b3/projects&quot;.
+                    &quot;baseUrl&quot;: &quot;A String&quot;, # The base URL for accessing Google Cloud APIs.
+                        #
+                        # When workers access Google Cloud APIs, they logically do so via
+                        # relative URLs.  If this field is specified, it supplies the base
+                        # URL to use for resolving these relative URLs.  The normative
+                        # algorithm used is defined by RFC 1808, &quot;Relative Uniform Resource
+                        # Locators&quot;.
+                        #
+                        # If not specified, the default value is &quot;http://www.googleapis.com/&quot;
+                    &quot;workerId&quot;: &quot;A String&quot;, # The ID of the worker running this pipeline.
+                  },
+                  &quot;harnessCommand&quot;: &quot;A String&quot;, # The command to launch the worker harness.
+                  &quot;logDir&quot;: &quot;A String&quot;, # The directory on the VM to store logs.
+                  &quot;streamingWorkerMainClass&quot;: &quot;A String&quot;, # The streaming worker main class name.
+                  &quot;languageHint&quot;: &quot;A String&quot;, # The suggested backend language.
+                  &quot;taskGroup&quot;: &quot;A String&quot;, # The UNIX group ID on the worker VM to use for tasks launched by
+                      # taskrunner; e.g. &quot;wheel&quot;.
+                  &quot;logUploadLocation&quot;: &quot;A String&quot;, # Indicates where to put logs.  If this is not specified, the logs
+                      # will not be uploaded.
+                      #
+                      # The supported resource type is:
+                      #
+                      # Google Cloud Storage:
+                      #   storage.googleapis.com/{bucket}/{object}
+                      #   bucket.storage.googleapis.com/{object}
+                  &quot;commandlinesFileName&quot;: &quot;A String&quot;, # The file to store preprocessing commands in.
+                  &quot;continueOnException&quot;: True or False, # Whether to continue taskrunner if an exception is hit.
+                  &quot;tempStoragePrefix&quot;: &quot;A String&quot;, # The prefix of the resources the taskrunner should use for
+                      # temporary storage.
+                      #
+                      # The supported resource type is:
+                      #
+                      # Google Cloud Storage:
+                      #   storage.googleapis.com/{bucket}/{object}
+                      #   bucket.storage.googleapis.com/{object}
                 },
-                &quot;taskUser&quot;: &quot;A String&quot;, # The UNIX user ID on the worker VM to use for tasks launched by
-                    # taskrunner; e.g. &quot;root&quot;.
-                &quot;vmId&quot;: &quot;A String&quot;, # The ID string of the VM.
+                &quot;diskType&quot;: &quot;A String&quot;, # Type of root disk for VMs.  If empty or unspecified, the service will
+                    # attempt to choose a reasonable default.
+                &quot;defaultPackageSet&quot;: &quot;A String&quot;, # The default package set to install.  This allows the service to
+                    # select a default set of packages which are useful to worker
+                    # harnesses written in a particular language.
+                &quot;machineType&quot;: &quot;A String&quot;, # Machine type (e.g. &quot;n1-standard-1&quot;).  If empty or unspecified, the
+                    # service will attempt to choose a reasonable default.
               },
-              &quot;autoscalingSettings&quot;: { # Settings for WorkerPool autoscaling. # Settings for autoscaling of this WorkerPool.
-                &quot;algorithm&quot;: &quot;A String&quot;, # The algorithm to use for autoscaling.
-                &quot;maxNumWorkers&quot;: 42, # The maximum number of workers to cap scaling at.
-              },
-              &quot;metadata&quot;: { # Metadata to set on the Google Compute Engine VMs.
-                &quot;a_key&quot;: &quot;A String&quot;,
-              },
-              &quot;defaultPackageSet&quot;: &quot;A String&quot;, # The default package set to install.  This allows the service to
-                  # select a default set of packages which are useful to worker
-                  # harnesses written in a particular language.
-              &quot;network&quot;: &quot;A String&quot;, # Network to which VMs will be assigned.  If empty or unspecified,
-                  # the service will use the network &quot;default&quot;.
+            ],
+            &quot;tempStoragePrefix&quot;: &quot;A String&quot;, # The prefix of the resources the system should use for temporary
+                # storage.  The system will append the suffix &quot;/temp-{JOBNAME} to
+                # this resource prefix, where {JOBNAME} is the value of the
+                # job_name field.  The resulting bucket and object prefix is used
+                # as the prefix of the resources used to store temporary data
+                # needed during the job execution.  NOTE: This will override the
+                # value in taskrunner_settings.
+                # The supported resource type is:
+                #
+                # Google Cloud Storage:
+                #
+                #   storage.googleapis.com/{bucket}/{object}
+                #   bucket.storage.googleapis.com/{object}
+            &quot;internalExperiments&quot;: { # Experimental settings.
+              &quot;a_key&quot;: &quot;&quot;, # Properties of the object. Contains field @type with type URL.
             },
-          ],
-          &quot;dataset&quot;: &quot;A String&quot;, # The dataset for the current project where various workflow
-              # related tables are stored.
-              #
-              # The supported resource type is:
-              #
-              # Google BigQuery:
-              #   bigquery.googleapis.com/{dataset}
-        },
-        &quot;stageStates&quot;: [ # This field may be mutated by the Cloud Dataflow service;
-            # callers cannot mutate it.
-          { # A message describing the state of a particular execution stage.
-            &quot;currentStateTime&quot;: &quot;A String&quot;, # The time at which the stage transitioned to this state.
-            &quot;executionStageState&quot;: &quot;A String&quot;, # Executions stage states allow the same set of values as JobState.
-            &quot;executionStageName&quot;: &quot;A String&quot;, # The name of the execution stage.
-          },
-        ],
-        &quot;jobMetadata&quot;: { # Metadata available primarily for filtering jobs. Will be included in the # This field is populated by the Dataflow service to support filtering jobs
-            # by the metadata values provided here. Populated for ListJobs and all GetJob
-            # views SUMMARY and higher.
-            # ListJob response and Job SUMMARY view.
-          &quot;datastoreDetails&quot;: [ # Identification of a Datastore source used in the Dataflow job.
-            { # Metadata for a Datastore connector used by the job.
-              &quot;namespace&quot;: &quot;A String&quot;, # Namespace used in the connection.
-              &quot;projectId&quot;: &quot;A String&quot;, # ProjectId accessed in the connection.
-            },
-          ],
-          &quot;sdkVersion&quot;: { # The version of the SDK used to run the job. # The SDK version used to run the job.
-            &quot;version&quot;: &quot;A String&quot;, # The version of the SDK used to run the job.
-            &quot;sdkSupportStatus&quot;: &quot;A String&quot;, # The support status for this SDK version.
-            &quot;versionDisplayName&quot;: &quot;A String&quot;, # A readable string describing the version of the SDK.
-          },
-          &quot;bigqueryDetails&quot;: [ # Identification of a BigQuery source used in the Dataflow job.
-            { # Metadata for a BigQuery connector used by the job.
-              &quot;table&quot;: &quot;A String&quot;, # Table accessed in the connection.
-              &quot;dataset&quot;: &quot;A String&quot;, # Dataset accessed in the connection.
-              &quot;query&quot;: &quot;A String&quot;, # Query used to access data in the connection.
-              &quot;projectId&quot;: &quot;A String&quot;, # Project accessed in the connection.
-            },
-          ],
-          &quot;fileDetails&quot;: [ # Identification of a File source used in the Dataflow job.
-            { # Metadata for a File connector used by the job.
-              &quot;filePattern&quot;: &quot;A String&quot;, # File Pattern used to access files by the connector.
-            },
-          ],
-          &quot;pubsubDetails&quot;: [ # Identification of a PubSub source used in the Dataflow job.
-            { # Metadata for a PubSub connector used by the job.
-              &quot;topic&quot;: &quot;A String&quot;, # Topic accessed in the connection.
-              &quot;subscription&quot;: &quot;A String&quot;, # Subscription used in the connection.
-            },
-          ],
-          &quot;bigTableDetails&quot;: [ # Identification of a BigTable source used in the Dataflow job.
-            { # Metadata for a BigTable connector used by the job.
-              &quot;projectId&quot;: &quot;A String&quot;, # ProjectId accessed in the connection.
-              &quot;instanceId&quot;: &quot;A String&quot;, # InstanceId accessed in the connection.
-              &quot;tableId&quot;: &quot;A String&quot;, # TableId accessed in the connection.
-            },
-          ],
-          &quot;spannerDetails&quot;: [ # Identification of a Spanner source used in the Dataflow job.
-            { # Metadata for a Spanner connector used by the job.
-              &quot;instanceId&quot;: &quot;A String&quot;, # InstanceId accessed in the connection.
-              &quot;projectId&quot;: &quot;A String&quot;, # ProjectId accessed in the connection.
-              &quot;databaseId&quot;: &quot;A String&quot;, # DatabaseId accessed in the connection.
-            },
-          ],
-        },
-        &quot;type&quot;: &quot;A String&quot;, # The type of Cloud Dataflow job.
-        &quot;projectId&quot;: &quot;A String&quot;, # The ID of the Cloud Platform project that the job belongs to.
-        &quot;createdFromSnapshotId&quot;: &quot;A String&quot;, # If this is specified, the job&#x27;s initial state is populated from the given
-            # snapshot.
-        &quot;pipelineDescription&quot;: { # A descriptive representation of submitted pipeline as well as the executed # Preliminary field: The format of this data may change at any time.
-            # A description of the user pipeline and stages through which it is executed.
-            # Created by Cloud Dataflow service.  Only retrieved with
-            # JOB_VIEW_DESCRIPTION or JOB_VIEW_ALL.
-            # form.  This data is provided by the Dataflow service for ease of visualizing
-            # the pipeline and interpreting Dataflow provided metrics.
-          &quot;executionPipelineStage&quot;: [ # Description of each stage of execution of the pipeline.
-            { # Description of the composing transforms, names/ids, and input/outputs of a
-                # stage of execution.  Some composing transforms and sources may have been
-                # generated by the Dataflow service during execution planning.
-              &quot;outputSource&quot;: [ # Output sources for this stage.
-                { # Description of an input or output of an execution stage.
-                  &quot;sizeBytes&quot;: &quot;A String&quot;, # Size of the source, if measurable.
-                  &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
-                  &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this source; may be user or system generated.
-                  &quot;originalTransformOrCollection&quot;: &quot;A String&quot;, # User name for the original user transform or collection with which this
-                      # source is most closely associated.
-                },
-              ],
-              &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this stage.
-              &quot;inputSource&quot;: [ # Input sources for this stage.
-                { # Description of an input or output of an execution stage.
-                  &quot;sizeBytes&quot;: &quot;A String&quot;, # Size of the source, if measurable.
-                  &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
-                  &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this source; may be user or system generated.
-                  &quot;originalTransformOrCollection&quot;: &quot;A String&quot;, # User name for the original user transform or collection with which this
-                      # source is most closely associated.
-                },
-              ],
-              &quot;id&quot;: &quot;A String&quot;, # Dataflow service generated id for this stage.
-              &quot;componentTransform&quot;: [ # Transforms that comprise this execution stage.
-                { # Description of a transform executed as part of an execution stage.
-                  &quot;originalTransform&quot;: &quot;A String&quot;, # User name for the original user transform with which this transform is
-                      # most closely associated.
-                  &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
-                  &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this transform; may be user or system generated.
-                },
-              ],
-              &quot;componentSource&quot;: [ # Collections produced and consumed by component transforms of this stage.
-                { # Description of an interstitial value between transforms in an execution
-                    # stage.
-                  &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
-                  &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this transform; may be user or system generated.
-                  &quot;originalTransformOrCollection&quot;: &quot;A String&quot;, # User name for the original user transform or collection with which this
-                      # source is most closely associated.
-                },
-              ],
-              &quot;kind&quot;: &quot;A String&quot;, # Type of tranform this stage is executing.
-            },
-          ],
-          &quot;originalPipelineTransform&quot;: [ # Description of each transform in the pipeline and collections between them.
-            { # Description of the type, names/ids, and input/outputs for a transform.
-              &quot;kind&quot;: &quot;A String&quot;, # Type of transform.
-              &quot;inputCollectionName&quot;: [ # User names for all collection inputs to this transform.
-                &quot;A String&quot;,
-              ],
-              &quot;name&quot;: &quot;A String&quot;, # User provided name for this transform instance.
-              &quot;id&quot;: &quot;A String&quot;, # SDK generated id of this transform instance.
-              &quot;displayData&quot;: [ # Transform-specific display data.
-                { # Data provided with a pipeline or transform to provide descriptive info.
-                  &quot;durationValue&quot;: &quot;A String&quot;, # Contains value if the data is of duration type.
-                  &quot;int64Value&quot;: &quot;A String&quot;, # Contains value if the data is of int64 type.
-                  &quot;namespace&quot;: &quot;A String&quot;, # The namespace for the key. This is usually a class name or programming
-                      # language namespace (i.e. python module) which defines the display data.
-                      # This allows a dax monitoring system to specially handle the data
-                      # and perform custom rendering.
-                  &quot;floatValue&quot;: 3.14, # Contains value if the data is of float type.
-                  &quot;key&quot;: &quot;A String&quot;, # The key identifying the display data.
-                      # This is intended to be used as a label for the display data
-                      # when viewed in a dax monitoring system.
-                  &quot;shortStrValue&quot;: &quot;A String&quot;, # A possible additional shorter value to display.
-                      # For example a java_class_name_value of com.mypackage.MyDoFn
-                      # will be stored with MyDoFn as the short_str_value and
-                      # com.mypackage.MyDoFn as the java_class_name value.
-                      # short_str_value can be displayed and java_class_name_value
-                      # will be displayed as a tooltip.
-                  &quot;url&quot;: &quot;A String&quot;, # An optional full URL.
-                  &quot;label&quot;: &quot;A String&quot;, # An optional label to display in a dax UI for the element.
-                  &quot;timestampValue&quot;: &quot;A String&quot;, # Contains value if the data is of timestamp type.
-                  &quot;boolValue&quot;: True or False, # Contains value if the data is of a boolean type.
-                  &quot;javaClassValue&quot;: &quot;A String&quot;, # Contains value if the data is of java class type.
-                  &quot;strValue&quot;: &quot;A String&quot;, # Contains value if the data is of string type.
-                },
-              ],
-              &quot;outputCollectionName&quot;: [ # User  names for all collection outputs to this transform.
-                &quot;A String&quot;,
-              ],
-            },
-          ],
-          &quot;displayData&quot;: [ # Pipeline level display data.
-            { # Data provided with a pipeline or transform to provide descriptive info.
-              &quot;durationValue&quot;: &quot;A String&quot;, # Contains value if the data is of duration type.
-              &quot;int64Value&quot;: &quot;A String&quot;, # Contains value if the data is of int64 type.
-              &quot;namespace&quot;: &quot;A String&quot;, # The namespace for the key. This is usually a class name or programming
-                  # language namespace (i.e. python module) which defines the display data.
-                  # This allows a dax monitoring system to specially handle the data
-                  # and perform custom rendering.
-              &quot;floatValue&quot;: 3.14, # Contains value if the data is of float type.
-              &quot;key&quot;: &quot;A String&quot;, # The key identifying the display data.
-                  # This is intended to be used as a label for the display data
-                  # when viewed in a dax monitoring system.
-              &quot;shortStrValue&quot;: &quot;A String&quot;, # A possible additional shorter value to display.
-                  # For example a java_class_name_value of com.mypackage.MyDoFn
-                  # will be stored with MyDoFn as the short_str_value and
-                  # com.mypackage.MyDoFn as the java_class_name value.
-                  # short_str_value can be displayed and java_class_name_value
-                  # will be displayed as a tooltip.
-              &quot;url&quot;: &quot;A String&quot;, # An optional full URL.
-              &quot;label&quot;: &quot;A String&quot;, # An optional label to display in a dax UI for the element.
-              &quot;timestampValue&quot;: &quot;A String&quot;, # Contains value if the data is of timestamp type.
-              &quot;boolValue&quot;: True or False, # Contains value if the data is of a boolean type.
-              &quot;javaClassValue&quot;: &quot;A String&quot;, # Contains value if the data is of java class type.
-              &quot;strValue&quot;: &quot;A String&quot;, # Contains value if the data is of string type.
-            },
-          ],
-        },
-        &quot;replaceJobId&quot;: &quot;A String&quot;, # If this job is an update of an existing job, this field is the job ID
-            # of the job it replaced.
-            #
-            # When sending a `CreateJobRequest`, you can update a job by specifying it
-            # here. The job named here is stopped, and its intermediate state is
-            # transferred to this job.
-        &quot;tempFiles&quot;: [ # A set of files the system should be aware of that are used
-            # for temporary storage. These temporary files will be
-            # removed on job completion.
-            # No duplicates are allowed.
-            # No file patterns are supported.
-            #
-            # The supported files are:
-            #
-            # Google Cloud Storage:
-            #
-            #    storage.googleapis.com/{bucket}/{object}
-            #    bucket.storage.googleapis.com/{object}
-          &quot;A String&quot;,
-        ],
-        &quot;name&quot;: &quot;A String&quot;, # The user-specified Cloud Dataflow job name.
-            #
-            # Only one Job with a given name may exist in a project at any
-            # given time. If a caller attempts to create a Job with the same
-            # name as an already-existing Job, the attempt returns the
-            # existing Job.
-            #
-            # The name must match the regular expression
-            # `[a-z]([-a-z0-9]{0,38}[a-z0-9])?`
-        &quot;steps&quot;: [ # Exactly one of step or steps_location should be specified.
-            #
-            # The top-level steps that constitute the entire job.
-          { # Defines a particular step within a Cloud Dataflow job.
-              #
-              # A job consists of multiple steps, each of which performs some
-              # specific operation as part of the overall job.  Data is typically
-              # passed from one step to another as part of the job.
-              #
-              # Here&#x27;s an example of a sequence of steps which together implement a
-              # Map-Reduce job:
-              #
-              #   * Read a collection of data from some source, parsing the
-              #     collection&#x27;s elements.
-              #
-              #   * Validate the elements.
-              #
-              #   * Apply a user-defined function to map each element to some value
-              #     and extract an element-specific key value.
-              #
-              #   * Group elements with the same key into a single element with
-              #     that key, transforming a multiply-keyed collection into a
-              #     uniquely-keyed collection.
-              #
-              #   * Write the elements out to some data sink.
-              #
-              # Note that the Cloud Dataflow service may be used to run many different
-              # types of jobs, not just Map-Reduce.
-            &quot;name&quot;: &quot;A String&quot;, # The name that identifies the step. This must be unique for each
-                # step with respect to all other steps in the Cloud Dataflow job.
-            &quot;kind&quot;: &quot;A String&quot;, # The kind of step in the Cloud Dataflow job.
-            &quot;properties&quot;: { # Named properties associated with the step. Each kind of
-                # predefined step has its own required set of properties.
-                # Must be provided on Create.  Only retrieved with JOB_VIEW_ALL.
+            &quot;sdkPipelineOptions&quot;: { # The Cloud Dataflow SDK pipeline options specified by the user. These
+                # options are passed through the service and are used to recreate the
+                # SDK pipeline options on the worker in a language agnostic and platform
+                # independent way.
               &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
             },
+            &quot;dataset&quot;: &quot;A String&quot;, # The dataset for the current project where various workflow
+                # related tables are stored.
+                #
+                # The supported resource type is:
+                #
+                # Google BigQuery:
+                #   bigquery.googleapis.com/{dataset}
+            &quot;clusterManagerApiService&quot;: &quot;A String&quot;, # The type of cluster manager API to use.  If unknown or
+                # unspecified, the service will attempt to choose a reasonable
+                # default.  This should be in the form of the API service name,
+                # e.g. &quot;compute.googleapis.com&quot;.
           },
-        ],
-        &quot;replacedByJobId&quot;: &quot;A String&quot;, # If another job is an update of this job (and thus, this job is in
-            # `JOB_STATE_UPDATED`), this field contains the ID of that job.
-        &quot;executionInfo&quot;: { # Additional information about how a Cloud Dataflow job will be executed that # Deprecated.
-            # isn&#x27;t contained in the submitted job.
-          &quot;stages&quot;: { # A mapping from each stage to the information about that stage.
-            &quot;a_key&quot;: { # Contains information about how a particular
-                # google.dataflow.v1beta3.Step will be executed.
-              &quot;stepName&quot;: [ # The steps associated with the execution stage.
-                  # Note that stages may have several steps, and that a given step
-                  # might be run by more than one stage.
-                &quot;A String&quot;,
-              ],
+          &quot;stepsLocation&quot;: &quot;A String&quot;, # The GCS location where the steps are stored.
+          &quot;steps&quot;: [ # Exactly one of step or steps_location should be specified.
+              #
+              # The top-level steps that constitute the entire job.
+            { # Defines a particular step within a Cloud Dataflow job.
+                #
+                # A job consists of multiple steps, each of which performs some
+                # specific operation as part of the overall job.  Data is typically
+                # passed from one step to another as part of the job.
+                #
+                # Here&#x27;s an example of a sequence of steps which together implement a
+                # Map-Reduce job:
+                #
+                #   * Read a collection of data from some source, parsing the
+                #     collection&#x27;s elements.
+                #
+                #   * Validate the elements.
+                #
+                #   * Apply a user-defined function to map each element to some value
+                #     and extract an element-specific key value.
+                #
+                #   * Group elements with the same key into a single element with
+                #     that key, transforming a multiply-keyed collection into a
+                #     uniquely-keyed collection.
+                #
+                #   * Write the elements out to some data sink.
+                #
+                # Note that the Cloud Dataflow service may be used to run many different
+                # types of jobs, not just Map-Reduce.
+              &quot;kind&quot;: &quot;A String&quot;, # The kind of step in the Cloud Dataflow job.
+              &quot;properties&quot;: { # Named properties associated with the step. Each kind of
+                  # predefined step has its own required set of properties.
+                  # Must be provided on Create.  Only retrieved with JOB_VIEW_ALL.
+                &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
+              },
+              &quot;name&quot;: &quot;A String&quot;, # The name that identifies the step. This must be unique for each
+                  # step with respect to all other steps in the Cloud Dataflow job.
+            },
+          ],
+          &quot;stageStates&quot;: [ # This field may be mutated by the Cloud Dataflow service;
+              # callers cannot mutate it.
+            { # A message describing the state of a particular execution stage.
+              &quot;executionStageState&quot;: &quot;A String&quot;, # Executions stage states allow the same set of values as JobState.
+              &quot;executionStageName&quot;: &quot;A String&quot;, # The name of the execution stage.
+              &quot;currentStateTime&quot;: &quot;A String&quot;, # The time at which the stage transitioned to this state.
+            },
+          ],
+          &quot;replacedByJobId&quot;: &quot;A String&quot;, # If another job is an update of this job (and thus, this job is in
+              # `JOB_STATE_UPDATED`), this field contains the ID of that job.
+          &quot;jobMetadata&quot;: { # Metadata available primarily for filtering jobs. Will be included in the # This field is populated by the Dataflow service to support filtering jobs
+              # by the metadata values provided here. Populated for ListJobs and all GetJob
+              # views SUMMARY and higher.
+              # ListJob response and Job SUMMARY view.
+            &quot;sdkVersion&quot;: { # The version of the SDK used to run the job. # The SDK version used to run the job.
+              &quot;sdkSupportStatus&quot;: &quot;A String&quot;, # The support status for this SDK version.
+              &quot;versionDisplayName&quot;: &quot;A String&quot;, # A readable string describing the version of the SDK.
+              &quot;version&quot;: &quot;A String&quot;, # The version of the SDK used to run the job.
+            },
+            &quot;bigTableDetails&quot;: [ # Identification of a BigTable source used in the Dataflow job.
+              { # Metadata for a BigTable connector used by the job.
+                &quot;instanceId&quot;: &quot;A String&quot;, # InstanceId accessed in the connection.
+                &quot;tableId&quot;: &quot;A String&quot;, # TableId accessed in the connection.
+                &quot;projectId&quot;: &quot;A String&quot;, # ProjectId accessed in the connection.
+              },
+            ],
+            &quot;pubsubDetails&quot;: [ # Identification of a PubSub source used in the Dataflow job.
+              { # Metadata for a PubSub connector used by the job.
+                &quot;subscription&quot;: &quot;A String&quot;, # Subscription used in the connection.
+                &quot;topic&quot;: &quot;A String&quot;, # Topic accessed in the connection.
+              },
+            ],
+            &quot;bigqueryDetails&quot;: [ # Identification of a BigQuery source used in the Dataflow job.
+              { # Metadata for a BigQuery connector used by the job.
+                &quot;dataset&quot;: &quot;A String&quot;, # Dataset accessed in the connection.
+                &quot;projectId&quot;: &quot;A String&quot;, # Project accessed in the connection.
+                &quot;query&quot;: &quot;A String&quot;, # Query used to access data in the connection.
+                &quot;table&quot;: &quot;A String&quot;, # Table accessed in the connection.
+              },
+            ],
+            &quot;fileDetails&quot;: [ # Identification of a File source used in the Dataflow job.
+              { # Metadata for a File connector used by the job.
+                &quot;filePattern&quot;: &quot;A String&quot;, # File Pattern used to access files by the connector.
+              },
+            ],
+            &quot;datastoreDetails&quot;: [ # Identification of a Datastore source used in the Dataflow job.
+              { # Metadata for a Datastore connector used by the job.
+                &quot;namespace&quot;: &quot;A String&quot;, # Namespace used in the connection.
+                &quot;projectId&quot;: &quot;A String&quot;, # ProjectId accessed in the connection.
+              },
+            ],
+            &quot;spannerDetails&quot;: [ # Identification of a Spanner source used in the Dataflow job.
+              { # Metadata for a Spanner connector used by the job.
+                &quot;instanceId&quot;: &quot;A String&quot;, # InstanceId accessed in the connection.
+                &quot;databaseId&quot;: &quot;A String&quot;, # DatabaseId accessed in the connection.
+                &quot;projectId&quot;: &quot;A String&quot;, # ProjectId accessed in the connection.
+              },
+            ],
+          },
+          &quot;location&quot;: &quot;A String&quot;, # The [regional endpoint]
+              # (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that
+              # contains this job.
+          &quot;transformNameMapping&quot;: { # The map of transform name prefixes of the job to be replaced to the
+              # corresponding name prefixes of the new job.
+            &quot;a_key&quot;: &quot;A String&quot;,
+          },
+          &quot;startTime&quot;: &quot;A String&quot;, # The timestamp when the job was started (transitioned to JOB_STATE_PENDING).
+              # Flexible resource scheduling jobs are started with some delay after job
+              # creation, so start_time is unset before start and is updated when the
+              # job is started by the Cloud Dataflow service. For other jobs, start_time
+              # always equals to create_time and is immutable and set by the Cloud Dataflow
+              # service.
+          &quot;clientRequestId&quot;: &quot;A String&quot;, # The client&#x27;s unique identifier of the job, re-used across retried attempts.
+              # If this field is set, the service will ensure its uniqueness.
+              # The request to create a job will fail if the service has knowledge of a
+              # previously submitted job with the same client&#x27;s ID and job name.
+              # The caller may use this field to ensure idempotence of job
+              # creation across retried attempts to create a job.
+              # By default, the field is empty and, in that case, the service ignores it.
+          &quot;executionInfo&quot;: { # Additional information about how a Cloud Dataflow job will be executed that # Deprecated.
+              # isn&#x27;t contained in the submitted job.
+            &quot;stages&quot;: { # A mapping from each stage to the information about that stage.
+              &quot;a_key&quot;: { # Contains information about how a particular
+                  # google.dataflow.v1beta3.Step will be executed.
+                &quot;stepName&quot;: [ # The steps associated with the execution stage.
+                    # Note that stages may have several steps, and that a given step
+                    # might be run by more than one stage.
+                  &quot;A String&quot;,
+                ],
+              },
             },
           },
+          &quot;type&quot;: &quot;A String&quot;, # The type of Cloud Dataflow job.
+          &quot;createTime&quot;: &quot;A String&quot;, # The timestamp when the job was initially created. Immutable and set by the
+              # Cloud Dataflow service.
+          &quot;tempFiles&quot;: [ # A set of files the system should be aware of that are used
+              # for temporary storage. These temporary files will be
+              # removed on job completion.
+              # No duplicates are allowed.
+              # No file patterns are supported.
+              #
+              # The supported files are:
+              #
+              # Google Cloud Storage:
+              #
+              #    storage.googleapis.com/{bucket}/{object}
+              #    bucket.storage.googleapis.com/{object}
+            &quot;A String&quot;,
+          ],
+          &quot;id&quot;: &quot;A String&quot;, # The unique ID of this job.
+              #
+              # This field is set by the Cloud Dataflow service when the Job is
+              # created, and is immutable for the life of the job.
+          &quot;requestedState&quot;: &quot;A String&quot;, # The job&#x27;s requested state.
+              #
+              # `UpdateJob` may be used to switch between the `JOB_STATE_STOPPED` and
+              # `JOB_STATE_RUNNING` states, by setting requested_state.  `UpdateJob` may
+              # also be used to directly set a job&#x27;s requested state to
+              # `JOB_STATE_CANCELLED` or `JOB_STATE_DONE`, irrevocably terminating the
+              # job if it has not already reached a terminal state.
+          &quot;replaceJobId&quot;: &quot;A String&quot;, # If this job is an update of an existing job, this field is the job ID
+              # of the job it replaced.
+              #
+              # When sending a `CreateJobRequest`, you can update a job by specifying it
+              # here. The job named here is stopped, and its intermediate state is
+              # transferred to this job.
+          &quot;createdFromSnapshotId&quot;: &quot;A String&quot;, # If this is specified, the job&#x27;s initial state is populated from the given
+              # snapshot.
+          &quot;currentState&quot;: &quot;A String&quot;, # The current state of the job.
+              #
+              # Jobs are created in the `JOB_STATE_STOPPED` state unless otherwise
+              # specified.
+              #
+              # A job in the `JOB_STATE_RUNNING` state may asynchronously enter a
+              # terminal state. After a job has reached a terminal state, no
+              # further state updates may be made.
+              #
+              # This field may be mutated by the Cloud Dataflow service;
+              # callers cannot mutate it.
+          &quot;name&quot;: &quot;A String&quot;, # The user-specified Cloud Dataflow job name.
+              #
+              # Only one Job with a given name may exist in a project at any
+              # given time. If a caller attempts to create a Job with the same
+              # name as an already-existing Job, the attempt returns the
+              # existing Job.
+              #
+              # The name must match the regular expression
+              # `[a-z]([-a-z0-9]{0,38}[a-z0-9])?`
+          &quot;currentStateTime&quot;: &quot;A String&quot;, # The timestamp associated with the current state.
         },
-        &quot;currentState&quot;: &quot;A String&quot;, # The current state of the job.
-            #
-            # Jobs are created in the `JOB_STATE_STOPPED` state unless otherwise
-            # specified.
-            #
-            # A job in the `JOB_STATE_RUNNING` state may asynchronously enter a
-            # terminal state. After a job has reached a terminal state, no
-            # further state updates may be made.
-            #
-            # This field may be mutated by the Cloud Dataflow service;
-            # callers cannot mutate it.
-        &quot;location&quot;: &quot;A String&quot;, # The [regional endpoint]
-            # (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that
-            # contains this job.
-        &quot;startTime&quot;: &quot;A String&quot;, # The timestamp when the job was started (transitioned to JOB_STATE_PENDING).
-            # Flexible resource scheduling jobs are started with some delay after job
-            # creation, so start_time is unset before start and is updated when the
-            # job is started by the Cloud Dataflow service. For other jobs, start_time
-            # always equals to create_time and is immutable and set by the Cloud Dataflow
-            # service.
-        &quot;stepsLocation&quot;: &quot;A String&quot;, # The GCS location where the steps are stored.
-        &quot;labels&quot;: { # User-defined labels for this job.
-            #
-            # The labels map can contain no more than 64 entries.  Entries of the labels
-            # map are UTF8 strings that comply with the following restrictions:
-            #
-            # * Keys must conform to regexp:  \p{Ll}\p{Lo}{0,62}
-            # * Values must conform to regexp:  [\p{Ll}\p{Lo}\p{N}_-]{0,63}
-            # * Both keys and values are additionally constrained to be &lt;= 128 bytes in
-            # size.
-          &quot;a_key&quot;: &quot;A String&quot;,
-        },
-        &quot;createTime&quot;: &quot;A String&quot;, # The timestamp when the job was initially created. Immutable and set by the
-            # Cloud Dataflow service.
-        &quot;requestedState&quot;: &quot;A String&quot;, # The job&#x27;s requested state.
-            #
-            # `UpdateJob` may be used to switch between the `JOB_STATE_STOPPED` and
-            # `JOB_STATE_RUNNING` states, by setting requested_state.  `UpdateJob` may
-            # also be used to directly set a job&#x27;s requested state to
-            # `JOB_STATE_CANCELLED` or `JOB_STATE_DONE`, irrevocably terminating the
-            # job if it has not already reached a terminal state.
-      },
     ],
+    &quot;nextPageToken&quot;: &quot;A String&quot;, # Set if there may be more results than fit in this response.
     &quot;failedLocation&quot;: [ # Zero or more messages describing the [regional endpoints]
         # (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that
         # failed to respond.
@@ -3267,7 +3268,6 @@
             # failed to respond.
       },
     ],
-    &quot;nextPageToken&quot;: &quot;A String&quot;, # Set if there may be more results than fit in this response.
   }</pre>
 </div>
 
@@ -3296,10 +3296,10 @@
     The object takes the form of:
 
 { # Request to create a snapshot of a job.
-    &quot;description&quot;: &quot;A String&quot;, # User specified description of the snapshot. Maybe empty.
     &quot;snapshotSources&quot;: True or False, # If true, perform snapshots for sources which support this.
-    &quot;ttl&quot;: &quot;A String&quot;, # TTL for the snapshot.
     &quot;location&quot;: &quot;A String&quot;, # The location that contains this job.
+    &quot;description&quot;: &quot;A String&quot;, # User specified description of the snapshot. Maybe empty.
+    &quot;ttl&quot;: &quot;A String&quot;, # TTL for the snapshot.
   }
 
   x__xgafv: string, V1 error format.
@@ -3311,20 +3311,20 @@
   An object of the form:
 
     { # Represents a snapshot of a job.
+    &quot;ttl&quot;: &quot;A String&quot;, # The time after which this snapshot will be automatically deleted.
+    &quot;state&quot;: &quot;A String&quot;, # State of the snapshot.
+    &quot;id&quot;: &quot;A String&quot;, # The unique ID of this snapshot.
+    &quot;sourceJobId&quot;: &quot;A String&quot;, # The job this snapshot was created from.
+    &quot;creationTime&quot;: &quot;A String&quot;, # The time this snapshot was created.
+    &quot;description&quot;: &quot;A String&quot;, # User specified description of the snapshot. Maybe empty.
     &quot;pubsubMetadata&quot;: [ # PubSub snapshot metadata.
       { # Represents a Pubsub snapshot.
         &quot;snapshotName&quot;: &quot;A String&quot;, # The name of the Pubsub snapshot.
-        &quot;topicName&quot;: &quot;A String&quot;, # The name of the Pubsub topic.
         &quot;expireTime&quot;: &quot;A String&quot;, # The expire time of the Pubsub snapshot.
+        &quot;topicName&quot;: &quot;A String&quot;, # The name of the Pubsub topic.
       },
     ],
-    &quot;creationTime&quot;: &quot;A String&quot;, # The time this snapshot was created.
-    &quot;sourceJobId&quot;: &quot;A String&quot;, # The job this snapshot was created from.
-    &quot;state&quot;: &quot;A String&quot;, # State of the snapshot.
     &quot;projectId&quot;: &quot;A String&quot;, # The project this snapshot belongs to.
-    &quot;ttl&quot;: &quot;A String&quot;, # The time after which this snapshot will be automatically deleted.
-    &quot;id&quot;: &quot;A String&quot;, # The unique ID of this snapshot.
-    &quot;description&quot;: &quot;A String&quot;, # User specified description of the snapshot. Maybe empty.
     &quot;diskSizeBytes&quot;: &quot;A String&quot;, # The disk byte size of the snapshot. Only available for snapshots in READY
         # state.
   }</pre>
@@ -3347,667 +3347,162 @@
     The object takes the form of:
 
 { # Defines a job to be run by the Cloud Dataflow service.
-  &quot;clientRequestId&quot;: &quot;A String&quot;, # The client&#x27;s unique identifier of the job, re-used across retried attempts.
-      # If this field is set, the service will ensure its uniqueness.
-      # The request to create a job will fail if the service has knowledge of a
-      # previously submitted job with the same client&#x27;s ID and job name.
-      # The caller may use this field to ensure idempotence of job
-      # creation across retried attempts to create a job.
-      # By default, the field is empty and, in that case, the service ignores it.
-  &quot;id&quot;: &quot;A String&quot;, # The unique ID of this job.
-      # 
-      # This field is set by the Cloud Dataflow service when the Job is
-      # created, and is immutable for the life of the job.
-  &quot;currentStateTime&quot;: &quot;A String&quot;, # The timestamp associated with the current state.
-  &quot;transformNameMapping&quot;: { # The map of transform name prefixes of the job to be replaced to the
-      # corresponding name prefixes of the new job.
-    &quot;a_key&quot;: &quot;A String&quot;,
-  },
-  &quot;environment&quot;: { # Describes the environment in which a Dataflow Job runs. # The environment for the job.
-    &quot;internalExperiments&quot;: { # Experimental settings.
-      &quot;a_key&quot;: &quot;&quot;, # Properties of the object. Contains field @type with type URL.
-    },
-    &quot;workerRegion&quot;: &quot;A String&quot;, # The Compute Engine region
-        # (https://cloud.google.com/compute/docs/regions-zones/regions-zones) in
-        # which worker processing should occur, e.g. &quot;us-west1&quot;. Mutually exclusive
-        # with worker_zone. If neither worker_region nor worker_zone is specified,
-        # default to the control plane&#x27;s region.
-    &quot;serviceKmsKeyName&quot;: &quot;A String&quot;, # If set, contains the Cloud KMS key identifier used to encrypt data
-        # at rest, AKA a Customer Managed Encryption Key (CMEK).
-        #
-        # Format:
-        #   projects/PROJECT_ID/locations/LOCATION/keyRings/KEY_RING/cryptoKeys/KEY
-    &quot;userAgent&quot;: { # A description of the process that generated the request.
-      &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
-    },
-    &quot;workerZone&quot;: &quot;A String&quot;, # The Compute Engine zone
-        # (https://cloud.google.com/compute/docs/regions-zones/regions-zones) in
-        # which worker processing should occur, e.g. &quot;us-west1-a&quot;. Mutually exclusive
-        # with worker_region. If neither worker_region nor worker_zone is specified,
-        # a zone in the control plane&#x27;s region is chosen based on available capacity.
-    &quot;clusterManagerApiService&quot;: &quot;A String&quot;, # The type of cluster manager API to use.  If unknown or
-        # unspecified, the service will attempt to choose a reasonable
-        # default.  This should be in the form of the API service name,
-        # e.g. &quot;compute.googleapis.com&quot;.
-    &quot;tempStoragePrefix&quot;: &quot;A String&quot;, # The prefix of the resources the system should use for temporary
-        # storage.  The system will append the suffix &quot;/temp-{JOBNAME} to
-        # this resource prefix, where {JOBNAME} is the value of the
-        # job_name field.  The resulting bucket and object prefix is used
-        # as the prefix of the resources used to store temporary data
-        # needed during the job execution.  NOTE: This will override the
-        # value in taskrunner_settings.
-        # The supported resource type is:
-        #
-        # Google Cloud Storage:
-        #
-        #   storage.googleapis.com/{bucket}/{object}
-        #   bucket.storage.googleapis.com/{object}
-    &quot;experiments&quot;: [ # The list of experiments to enable.
-      &quot;A String&quot;,
-    ],
-    &quot;version&quot;: { # A structure describing which components and their versions of the service
-        # are required in order to run the job.
-      &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
-    },
-    &quot;serviceAccountEmail&quot;: &quot;A String&quot;, # Identity to run virtual machines as. Defaults to the default account.
-    &quot;sdkPipelineOptions&quot;: { # The Cloud Dataflow SDK pipeline options specified by the user. These
-        # options are passed through the service and are used to recreate the
-        # SDK pipeline options on the worker in a language agnostic and platform
-        # independent way.
-      &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
-    },
-    &quot;flexResourceSchedulingGoal&quot;: &quot;A String&quot;, # Which Flexible Resource Scheduling mode to run in.
-    &quot;workerPools&quot;: [ # The worker pools. At least one &quot;harness&quot; worker pool must be
-        # specified in order for the job to have workers.
-      { # Describes one particular pool of Cloud Dataflow workers to be
-          # instantiated by the Cloud Dataflow service in order to perform the
-          # computations required by a job.  Note that a workflow job may use
-          # multiple pools, in order to match the various computational
-          # requirements of the various stages of the job.
-        &quot;numThreadsPerWorker&quot;: 42, # The number of threads per worker harness. If empty or unspecified, the
-            # service will choose a number of threads (according to the number of cores
-            # on the selected machine type for batch, or 1 by convention for streaming).
-        &quot;numWorkers&quot;: 42, # Number of Google Compute Engine workers in this pool needed to
-            # execute the job.  If zero or unspecified, the service will
-            # attempt to choose a reasonable default.
-        &quot;zone&quot;: &quot;A String&quot;, # Zone to run the worker pools in.  If empty or unspecified, the service
-            # will attempt to choose a reasonable default.
-        &quot;diskSourceImage&quot;: &quot;A String&quot;, # Fully qualified source image for disks.
-        &quot;packages&quot;: [ # Packages to be installed on workers.
-          { # The packages that must be installed in order for a worker to run the
-              # steps of the Cloud Dataflow job that will be assigned to its worker
-              # pool.
-              #
-              # This is the mechanism by which the Cloud Dataflow SDK causes code to
-              # be loaded onto the workers. For example, the Cloud Dataflow Java SDK
-              # might use this to install jars containing the user&#x27;s code and all of the
-              # various dependencies (libraries, data files, etc.) required in order
-              # for that code to run.
-            &quot;name&quot;: &quot;A String&quot;, # The name of the package.
-            &quot;location&quot;: &quot;A String&quot;, # The resource to read the package from. The supported resource type is:
-                #
-                # Google Cloud Storage:
-                #
-                #   storage.googleapis.com/{bucket}
-                #   bucket.storage.googleapis.com/
-          },
-        ],
-        &quot;teardownPolicy&quot;: &quot;A String&quot;, # Sets the policy for determining when to turndown worker pool.
-            # Allowed values are: `TEARDOWN_ALWAYS`, `TEARDOWN_ON_SUCCESS`, and
-            # `TEARDOWN_NEVER`.
-            # `TEARDOWN_ALWAYS` means workers are always torn down regardless of whether
-            # the job succeeds. `TEARDOWN_ON_SUCCESS` means workers are torn down
-            # if the job succeeds. `TEARDOWN_NEVER` means the workers are never torn
-            # down.
-            #
-            # If the workers are not torn down by the service, they will
-            # continue to run and use Google Compute Engine VM resources in the
-            # user&#x27;s project until they are explicitly terminated by the user.
-            # Because of this, Google recommends using the `TEARDOWN_ALWAYS`
-            # policy except for small, manually supervised test jobs.
-            #
-            # If unknown or unspecified, the service will attempt to choose a reasonable
-            # default.
-        &quot;onHostMaintenance&quot;: &quot;A String&quot;, # The action to take on host maintenance, as defined by the Google
-            # Compute Engine API.
-        &quot;poolArgs&quot;: { # Extra arguments for this worker pool.
-          &quot;a_key&quot;: &quot;&quot;, # Properties of the object. Contains field @type with type URL.
+    &quot;pipelineDescription&quot;: { # A descriptive representation of submitted pipeline as well as the executed # Preliminary field: The format of this data may change at any time.
+        # A description of the user pipeline and stages through which it is executed.
+        # Created by Cloud Dataflow service.  Only retrieved with
+        # JOB_VIEW_DESCRIPTION or JOB_VIEW_ALL.
+        # form.  This data is provided by the Dataflow service for ease of visualizing
+        # the pipeline and interpreting Dataflow provided metrics.
+      &quot;displayData&quot;: [ # Pipeline level display data.
+        { # Data provided with a pipeline or transform to provide descriptive info.
+          &quot;url&quot;: &quot;A String&quot;, # An optional full URL.
+          &quot;javaClassValue&quot;: &quot;A String&quot;, # Contains value if the data is of java class type.
+          &quot;timestampValue&quot;: &quot;A String&quot;, # Contains value if the data is of timestamp type.
+          &quot;durationValue&quot;: &quot;A String&quot;, # Contains value if the data is of duration type.
+          &quot;label&quot;: &quot;A String&quot;, # An optional label to display in a dax UI for the element.
+          &quot;key&quot;: &quot;A String&quot;, # The key identifying the display data.
+              # This is intended to be used as a label for the display data
+              # when viewed in a dax monitoring system.
+          &quot;namespace&quot;: &quot;A String&quot;, # The namespace for the key. This is usually a class name or programming
+              # language namespace (i.e. python module) which defines the display data.
+              # This allows a dax monitoring system to specially handle the data
+              # and perform custom rendering.
+          &quot;floatValue&quot;: 3.14, # Contains value if the data is of float type.
+          &quot;strValue&quot;: &quot;A String&quot;, # Contains value if the data is of string type.
+          &quot;int64Value&quot;: &quot;A String&quot;, # Contains value if the data is of int64 type.
+          &quot;boolValue&quot;: True or False, # Contains value if the data is of a boolean type.
+          &quot;shortStrValue&quot;: &quot;A String&quot;, # A possible additional shorter value to display.
+              # For example a java_class_name_value of com.mypackage.MyDoFn
+              # will be stored with MyDoFn as the short_str_value and
+              # com.mypackage.MyDoFn as the java_class_name value.
+              # short_str_value can be displayed and java_class_name_value
+              # will be displayed as a tooltip.
         },
-        &quot;diskSizeGb&quot;: 42, # Size of root disk for VMs, in GB.  If zero or unspecified, the service will
-            # attempt to choose a reasonable default.
-        &quot;workerHarnessContainerImage&quot;: &quot;A String&quot;, # Required. Docker container image that executes the Cloud Dataflow worker
-            # harness, residing in Google Container Registry.
-            #
-            # Deprecated for the Fn API path. Use sdk_harness_container_images instead.
-        &quot;diskType&quot;: &quot;A String&quot;, # Type of root disk for VMs.  If empty or unspecified, the service will
-            # attempt to choose a reasonable default.
-        &quot;machineType&quot;: &quot;A String&quot;, # Machine type (e.g. &quot;n1-standard-1&quot;).  If empty or unspecified, the
-            # service will attempt to choose a reasonable default.
-        &quot;kind&quot;: &quot;A String&quot;, # The kind of the worker pool; currently only `harness` and `shuffle`
-            # are supported.
-        &quot;sdkHarnessContainerImages&quot;: [ # Set of SDK harness containers needed to execute this pipeline. This will
-            # only be set in the Fn API path. For non-cross-language pipelines this
-            # should have only one entry. Cross-language pipelines will have two or more
-            # entries.
-          { # Defines a SDK harness container for executing Dataflow pipelines.
-            &quot;containerImage&quot;: &quot;A String&quot;, # A docker container image that resides in Google Container Registry.
-            &quot;useSingleCorePerContainer&quot;: True or False, # If true, recommends the Dataflow service to use only one core per SDK
-                # container instance with this image. If false (or unset) recommends using
-                # more than one core per SDK container instance with this image for
-                # efficiency. Note that Dataflow service may choose to override this property
-                # if needed.
-          },
-        ],
-        &quot;dataDisks&quot;: [ # Data disks that are used by a VM in this workflow.
-          { # Describes the data disk used by a workflow job.
-            &quot;diskType&quot;: &quot;A String&quot;, # Disk storage type, as defined by Google Compute Engine.  This
-                # must be a disk type appropriate to the project and zone in which
-                # the workers will run.  If unknown or unspecified, the service
-                # will attempt to choose a reasonable default.
-                #
-                # For example, the standard persistent disk type is a resource name
-                # typically ending in &quot;pd-standard&quot;.  If SSD persistent disks are
-                # available, the resource name typically ends with &quot;pd-ssd&quot;.  The
-                # actual valid values are defined the Google Compute Engine API,
-                # not by the Cloud Dataflow API; consult the Google Compute Engine
-                # documentation for more information about determining the set of
-                # available disk types for a particular project and zone.
-                #
-                # Google Compute Engine Disk types are local to a particular
-                # project in a particular zone, and so the resource name will
-                # typically look something like this:
-                #
-                # compute.googleapis.com/projects/project-id/zones/zone/diskTypes/pd-standard
-            &quot;sizeGb&quot;: 42, # Size of disk in GB.  If zero or unspecified, the service will
-                # attempt to choose a reasonable default.
-            &quot;mountPoint&quot;: &quot;A String&quot;, # Directory in a VM where disk is mounted.
-          },
-        ],
-        &quot;subnetwork&quot;: &quot;A String&quot;, # Subnetwork to which VMs will be assigned, if desired.  Expected to be of
-            # the form &quot;regions/REGION/subnetworks/SUBNETWORK&quot;.
-        &quot;ipConfiguration&quot;: &quot;A String&quot;, # Configuration for VM IPs.
-        &quot;taskrunnerSettings&quot;: { # Taskrunner configuration settings. # Settings passed through to Google Compute Engine workers when
-            # using the standard Dataflow task runner.  Users should ignore
-            # this field.
-          &quot;alsologtostderr&quot;: True or False, # Whether to also send taskrunner log info to stderr.
-          &quot;taskGroup&quot;: &quot;A String&quot;, # The UNIX group ID on the worker VM to use for tasks launched by
-              # taskrunner; e.g. &quot;wheel&quot;.
-          &quot;harnessCommand&quot;: &quot;A String&quot;, # The command to launch the worker harness.
-          &quot;logDir&quot;: &quot;A String&quot;, # The directory on the VM to store logs.
-          &quot;oauthScopes&quot;: [ # The OAuth2 scopes to be requested by the taskrunner in order to
-              # access the Cloud Dataflow API.
+      ],
+      &quot;originalPipelineTransform&quot;: [ # Description of each transform in the pipeline and collections between them.
+        { # Description of the type, names/ids, and input/outputs for a transform.
+          &quot;outputCollectionName&quot;: [ # User  names for all collection outputs to this transform.
             &quot;A String&quot;,
           ],
-          &quot;dataflowApiVersion&quot;: &quot;A String&quot;, # The API version of endpoint, e.g. &quot;v1b3&quot;
-          &quot;logUploadLocation&quot;: &quot;A String&quot;, # Indicates where to put logs.  If this is not specified, the logs
-              # will not be uploaded.
-              #
-              # The supported resource type is:
-              #
-              # Google Cloud Storage:
-              #   storage.googleapis.com/{bucket}/{object}
-              #   bucket.storage.googleapis.com/{object}
-          &quot;streamingWorkerMainClass&quot;: &quot;A String&quot;, # The streaming worker main class name.
-          &quot;workflowFileName&quot;: &quot;A String&quot;, # The file to store the workflow in.
-          &quot;languageHint&quot;: &quot;A String&quot;, # The suggested backend language.
-          &quot;commandlinesFileName&quot;: &quot;A String&quot;, # The file to store preprocessing commands in.
-          &quot;baseTaskDir&quot;: &quot;A String&quot;, # The location on the worker for task-specific subdirectories.
-          &quot;tempStoragePrefix&quot;: &quot;A String&quot;, # The prefix of the resources the taskrunner should use for
-              # temporary storage.
-              #
-              # The supported resource type is:
-              #
-              # Google Cloud Storage:
-              #   storage.googleapis.com/{bucket}/{object}
-              #   bucket.storage.googleapis.com/{object}
-          &quot;baseUrl&quot;: &quot;A String&quot;, # The base URL for the taskrunner to use when accessing Google Cloud APIs.
-              #
-              # When workers access Google Cloud APIs, they logically do so via
-              # relative URLs.  If this field is specified, it supplies the base
-              # URL to use for resolving these relative URLs.  The normative
-              # algorithm used is defined by RFC 1808, &quot;Relative Uniform Resource
-              # Locators&quot;.
-              #
-              # If not specified, the default value is &quot;http://www.googleapis.com/&quot;
-          &quot;logToSerialconsole&quot;: True or False, # Whether to send taskrunner log info to Google Compute Engine VM serial
-              # console.
-          &quot;continueOnException&quot;: True or False, # Whether to continue taskrunner if an exception is hit.
-          &quot;parallelWorkerSettings&quot;: { # Provides data to pass through to the worker harness. # The settings to pass to the parallel worker harness.
-            &quot;tempStoragePrefix&quot;: &quot;A String&quot;, # The prefix of the resources the system should use for temporary
-                # storage.
-                #
-                # The supported resource type is:
-                #
-                # Google Cloud Storage:
-                #
-                #   storage.googleapis.com/{bucket}/{object}
-                #   bucket.storage.googleapis.com/{object}
-            &quot;reportingEnabled&quot;: True or False, # Whether to send work progress updates to the service.
-            &quot;baseUrl&quot;: &quot;A String&quot;, # The base URL for accessing Google Cloud APIs.
-                #
-                # When workers access Google Cloud APIs, they logically do so via
-                # relative URLs.  If this field is specified, it supplies the base
-                # URL to use for resolving these relative URLs.  The normative
-                # algorithm used is defined by RFC 1808, &quot;Relative Uniform Resource
-                # Locators&quot;.
-                #
-                # If not specified, the default value is &quot;http://www.googleapis.com/&quot;
-            &quot;servicePath&quot;: &quot;A String&quot;, # The Cloud Dataflow service path relative to the root URL, for example,
-                # &quot;dataflow/v1b3/projects&quot;.
-            &quot;shuffleServicePath&quot;: &quot;A String&quot;, # The Shuffle service path relative to the root URL, for example,
-                # &quot;shuffle/v1beta1&quot;.
-            &quot;workerId&quot;: &quot;A String&quot;, # The ID of the worker running this pipeline.
-          },
-          &quot;taskUser&quot;: &quot;A String&quot;, # The UNIX user ID on the worker VM to use for tasks launched by
-              # taskrunner; e.g. &quot;root&quot;.
-          &quot;vmId&quot;: &quot;A String&quot;, # The ID string of the VM.
+          &quot;displayData&quot;: [ # Transform-specific display data.
+            { # Data provided with a pipeline or transform to provide descriptive info.
+              &quot;url&quot;: &quot;A String&quot;, # An optional full URL.
+              &quot;javaClassValue&quot;: &quot;A String&quot;, # Contains value if the data is of java class type.
+              &quot;timestampValue&quot;: &quot;A String&quot;, # Contains value if the data is of timestamp type.
+              &quot;durationValue&quot;: &quot;A String&quot;, # Contains value if the data is of duration type.
+              &quot;label&quot;: &quot;A String&quot;, # An optional label to display in a dax UI for the element.
+              &quot;key&quot;: &quot;A String&quot;, # The key identifying the display data.
+                  # This is intended to be used as a label for the display data
+                  # when viewed in a dax monitoring system.
+              &quot;namespace&quot;: &quot;A String&quot;, # The namespace for the key. This is usually a class name or programming
+                  # language namespace (i.e. python module) which defines the display data.
+                  # This allows a dax monitoring system to specially handle the data
+                  # and perform custom rendering.
+              &quot;floatValue&quot;: 3.14, # Contains value if the data is of float type.
+              &quot;strValue&quot;: &quot;A String&quot;, # Contains value if the data is of string type.
+              &quot;int64Value&quot;: &quot;A String&quot;, # Contains value if the data is of int64 type.
+              &quot;boolValue&quot;: True or False, # Contains value if the data is of a boolean type.
+              &quot;shortStrValue&quot;: &quot;A String&quot;, # A possible additional shorter value to display.
+                  # For example a java_class_name_value of com.mypackage.MyDoFn
+                  # will be stored with MyDoFn as the short_str_value and
+                  # com.mypackage.MyDoFn as the java_class_name value.
+                  # short_str_value can be displayed and java_class_name_value
+                  # will be displayed as a tooltip.
+            },
+          ],
+          &quot;id&quot;: &quot;A String&quot;, # SDK generated id of this transform instance.
+          &quot;inputCollectionName&quot;: [ # User names for all collection inputs to this transform.
+            &quot;A String&quot;,
+          ],
+          &quot;name&quot;: &quot;A String&quot;, # User provided name for this transform instance.
+          &quot;kind&quot;: &quot;A String&quot;, # Type of transform.
         },
-        &quot;autoscalingSettings&quot;: { # Settings for WorkerPool autoscaling. # Settings for autoscaling of this WorkerPool.
-          &quot;algorithm&quot;: &quot;A String&quot;, # The algorithm to use for autoscaling.
-          &quot;maxNumWorkers&quot;: 42, # The maximum number of workers to cap scaling at.
+      ],
+      &quot;executionPipelineStage&quot;: [ # Description of each stage of execution of the pipeline.
+        { # Description of the composing transforms, names/ids, and input/outputs of a
+            # stage of execution.  Some composing transforms and sources may have been
+            # generated by the Dataflow service during execution planning.
+          &quot;componentSource&quot;: [ # Collections produced and consumed by component transforms of this stage.
+            { # Description of an interstitial value between transforms in an execution
+                # stage.
+              &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this transform; may be user or system generated.
+              &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
+              &quot;originalTransformOrCollection&quot;: &quot;A String&quot;, # User name for the original user transform or collection with which this
+                  # source is most closely associated.
+            },
+          ],
+          &quot;inputSource&quot;: [ # Input sources for this stage.
+            { # Description of an input or output of an execution stage.
+              &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this source; may be user or system generated.
+              &quot;originalTransformOrCollection&quot;: &quot;A String&quot;, # User name for the original user transform or collection with which this
+                  # source is most closely associated.
+              &quot;sizeBytes&quot;: &quot;A String&quot;, # Size of the source, if measurable.
+              &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
+            },
+          ],
+          &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this stage.
+          &quot;componentTransform&quot;: [ # Transforms that comprise this execution stage.
+            { # Description of a transform executed as part of an execution stage.
+              &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
+              &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this transform; may be user or system generated.
+              &quot;originalTransform&quot;: &quot;A String&quot;, # User name for the original user transform with which this transform is
+                  # most closely associated.
+            },
+          ],
+          &quot;id&quot;: &quot;A String&quot;, # Dataflow service generated id for this stage.
+          &quot;outputSource&quot;: [ # Output sources for this stage.
+            { # Description of an input or output of an execution stage.
+              &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this source; may be user or system generated.
+              &quot;originalTransformOrCollection&quot;: &quot;A String&quot;, # User name for the original user transform or collection with which this
+                  # source is most closely associated.
+              &quot;sizeBytes&quot;: &quot;A String&quot;, # Size of the source, if measurable.
+              &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
+            },
+          ],
+          &quot;kind&quot;: &quot;A String&quot;, # Type of tranform this stage is executing.
         },
-        &quot;metadata&quot;: { # Metadata to set on the Google Compute Engine VMs.
-          &quot;a_key&quot;: &quot;A String&quot;,
-        },
-        &quot;defaultPackageSet&quot;: &quot;A String&quot;, # The default package set to install.  This allows the service to
-            # select a default set of packages which are useful to worker
-            # harnesses written in a particular language.
-        &quot;network&quot;: &quot;A String&quot;, # Network to which VMs will be assigned.  If empty or unspecified,
-            # the service will use the network &quot;default&quot;.
-      },
-    ],
-    &quot;dataset&quot;: &quot;A String&quot;, # The dataset for the current project where various workflow
-        # related tables are stored.
-        #
-        # The supported resource type is:
-        #
-        # Google BigQuery:
-        #   bigquery.googleapis.com/{dataset}
-  },
-  &quot;stageStates&quot;: [ # This field may be mutated by the Cloud Dataflow service;
-      # callers cannot mutate it.
-    { # A message describing the state of a particular execution stage.
-      &quot;currentStateTime&quot;: &quot;A String&quot;, # The time at which the stage transitioned to this state.
-      &quot;executionStageState&quot;: &quot;A String&quot;, # Executions stage states allow the same set of values as JobState.
-      &quot;executionStageName&quot;: &quot;A String&quot;, # The name of the execution stage.
+      ],
     },
-  ],
-  &quot;jobMetadata&quot;: { # Metadata available primarily for filtering jobs. Will be included in the # This field is populated by the Dataflow service to support filtering jobs
-      # by the metadata values provided here. Populated for ListJobs and all GetJob
-      # views SUMMARY and higher.
-      # ListJob response and Job SUMMARY view.
-    &quot;datastoreDetails&quot;: [ # Identification of a Datastore source used in the Dataflow job.
-      { # Metadata for a Datastore connector used by the job.
-        &quot;namespace&quot;: &quot;A String&quot;, # Namespace used in the connection.
-        &quot;projectId&quot;: &quot;A String&quot;, # ProjectId accessed in the connection.
-      },
-    ],
-    &quot;sdkVersion&quot;: { # The version of the SDK used to run the job. # The SDK version used to run the job.
-      &quot;version&quot;: &quot;A String&quot;, # The version of the SDK used to run the job.
-      &quot;sdkSupportStatus&quot;: &quot;A String&quot;, # The support status for this SDK version.
-      &quot;versionDisplayName&quot;: &quot;A String&quot;, # A readable string describing the version of the SDK.
-    },
-    &quot;bigqueryDetails&quot;: [ # Identification of a BigQuery source used in the Dataflow job.
-      { # Metadata for a BigQuery connector used by the job.
-        &quot;table&quot;: &quot;A String&quot;, # Table accessed in the connection.
-        &quot;dataset&quot;: &quot;A String&quot;, # Dataset accessed in the connection.
-        &quot;query&quot;: &quot;A String&quot;, # Query used to access data in the connection.
-        &quot;projectId&quot;: &quot;A String&quot;, # Project accessed in the connection.
-      },
-    ],
-    &quot;fileDetails&quot;: [ # Identification of a File source used in the Dataflow job.
-      { # Metadata for a File connector used by the job.
-        &quot;filePattern&quot;: &quot;A String&quot;, # File Pattern used to access files by the connector.
-      },
-    ],
-    &quot;pubsubDetails&quot;: [ # Identification of a PubSub source used in the Dataflow job.
-      { # Metadata for a PubSub connector used by the job.
-        &quot;topic&quot;: &quot;A String&quot;, # Topic accessed in the connection.
-        &quot;subscription&quot;: &quot;A String&quot;, # Subscription used in the connection.
-      },
-    ],
-    &quot;bigTableDetails&quot;: [ # Identification of a BigTable source used in the Dataflow job.
-      { # Metadata for a BigTable connector used by the job.
-        &quot;projectId&quot;: &quot;A String&quot;, # ProjectId accessed in the connection.
-        &quot;instanceId&quot;: &quot;A String&quot;, # InstanceId accessed in the connection.
-        &quot;tableId&quot;: &quot;A String&quot;, # TableId accessed in the connection.
-      },
-    ],
-    &quot;spannerDetails&quot;: [ # Identification of a Spanner source used in the Dataflow job.
-      { # Metadata for a Spanner connector used by the job.
-        &quot;instanceId&quot;: &quot;A String&quot;, # InstanceId accessed in the connection.
-        &quot;projectId&quot;: &quot;A String&quot;, # ProjectId accessed in the connection.
-        &quot;databaseId&quot;: &quot;A String&quot;, # DatabaseId accessed in the connection.
-      },
-    ],
-  },
-  &quot;type&quot;: &quot;A String&quot;, # The type of Cloud Dataflow job.
-  &quot;projectId&quot;: &quot;A String&quot;, # The ID of the Cloud Platform project that the job belongs to.
-  &quot;createdFromSnapshotId&quot;: &quot;A String&quot;, # If this is specified, the job&#x27;s initial state is populated from the given
-      # snapshot.
-  &quot;pipelineDescription&quot;: { # A descriptive representation of submitted pipeline as well as the executed # Preliminary field: The format of this data may change at any time.
-      # A description of the user pipeline and stages through which it is executed.
-      # Created by Cloud Dataflow service.  Only retrieved with
-      # JOB_VIEW_DESCRIPTION or JOB_VIEW_ALL.
-      # form.  This data is provided by the Dataflow service for ease of visualizing
-      # the pipeline and interpreting Dataflow provided metrics.
-    &quot;executionPipelineStage&quot;: [ # Description of each stage of execution of the pipeline.
-      { # Description of the composing transforms, names/ids, and input/outputs of a
-          # stage of execution.  Some composing transforms and sources may have been
-          # generated by the Dataflow service during execution planning.
-        &quot;outputSource&quot;: [ # Output sources for this stage.
-          { # Description of an input or output of an execution stage.
-            &quot;sizeBytes&quot;: &quot;A String&quot;, # Size of the source, if measurable.
-            &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
-            &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this source; may be user or system generated.
-            &quot;originalTransformOrCollection&quot;: &quot;A String&quot;, # User name for the original user transform or collection with which this
-                # source is most closely associated.
-          },
-        ],
-        &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this stage.
-        &quot;inputSource&quot;: [ # Input sources for this stage.
-          { # Description of an input or output of an execution stage.
-            &quot;sizeBytes&quot;: &quot;A String&quot;, # Size of the source, if measurable.
-            &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
-            &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this source; may be user or system generated.
-            &quot;originalTransformOrCollection&quot;: &quot;A String&quot;, # User name for the original user transform or collection with which this
-                # source is most closely associated.
-          },
-        ],
-        &quot;id&quot;: &quot;A String&quot;, # Dataflow service generated id for this stage.
-        &quot;componentTransform&quot;: [ # Transforms that comprise this execution stage.
-          { # Description of a transform executed as part of an execution stage.
-            &quot;originalTransform&quot;: &quot;A String&quot;, # User name for the original user transform with which this transform is
-                # most closely associated.
-            &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
-            &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this transform; may be user or system generated.
-          },
-        ],
-        &quot;componentSource&quot;: [ # Collections produced and consumed by component transforms of this stage.
-          { # Description of an interstitial value between transforms in an execution
-              # stage.
-            &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
-            &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this transform; may be user or system generated.
-            &quot;originalTransformOrCollection&quot;: &quot;A String&quot;, # User name for the original user transform or collection with which this
-                # source is most closely associated.
-          },
-        ],
-        &quot;kind&quot;: &quot;A String&quot;, # Type of tranform this stage is executing.
-      },
-    ],
-    &quot;originalPipelineTransform&quot;: [ # Description of each transform in the pipeline and collections between them.
-      { # Description of the type, names/ids, and input/outputs for a transform.
-        &quot;kind&quot;: &quot;A String&quot;, # Type of transform.
-        &quot;inputCollectionName&quot;: [ # User names for all collection inputs to this transform.
-          &quot;A String&quot;,
-        ],
-        &quot;name&quot;: &quot;A String&quot;, # User provided name for this transform instance.
-        &quot;id&quot;: &quot;A String&quot;, # SDK generated id of this transform instance.
-        &quot;displayData&quot;: [ # Transform-specific display data.
-          { # Data provided with a pipeline or transform to provide descriptive info.
-            &quot;durationValue&quot;: &quot;A String&quot;, # Contains value if the data is of duration type.
-            &quot;int64Value&quot;: &quot;A String&quot;, # Contains value if the data is of int64 type.
-            &quot;namespace&quot;: &quot;A String&quot;, # The namespace for the key. This is usually a class name or programming
-                # language namespace (i.e. python module) which defines the display data.
-                # This allows a dax monitoring system to specially handle the data
-                # and perform custom rendering.
-            &quot;floatValue&quot;: 3.14, # Contains value if the data is of float type.
-            &quot;key&quot;: &quot;A String&quot;, # The key identifying the display data.
-                # This is intended to be used as a label for the display data
-                # when viewed in a dax monitoring system.
-            &quot;shortStrValue&quot;: &quot;A String&quot;, # A possible additional shorter value to display.
-                # For example a java_class_name_value of com.mypackage.MyDoFn
-                # will be stored with MyDoFn as the short_str_value and
-                # com.mypackage.MyDoFn as the java_class_name value.
-                # short_str_value can be displayed and java_class_name_value
-                # will be displayed as a tooltip.
-            &quot;url&quot;: &quot;A String&quot;, # An optional full URL.
-            &quot;label&quot;: &quot;A String&quot;, # An optional label to display in a dax UI for the element.
-            &quot;timestampValue&quot;: &quot;A String&quot;, # Contains value if the data is of timestamp type.
-            &quot;boolValue&quot;: True or False, # Contains value if the data is of a boolean type.
-            &quot;javaClassValue&quot;: &quot;A String&quot;, # Contains value if the data is of java class type.
-            &quot;strValue&quot;: &quot;A String&quot;, # Contains value if the data is of string type.
-          },
-        ],
-        &quot;outputCollectionName&quot;: [ # User  names for all collection outputs to this transform.
-          &quot;A String&quot;,
-        ],
-      },
-    ],
-    &quot;displayData&quot;: [ # Pipeline level display data.
-      { # Data provided with a pipeline or transform to provide descriptive info.
-        &quot;durationValue&quot;: &quot;A String&quot;, # Contains value if the data is of duration type.
-        &quot;int64Value&quot;: &quot;A String&quot;, # Contains value if the data is of int64 type.
-        &quot;namespace&quot;: &quot;A String&quot;, # The namespace for the key. This is usually a class name or programming
-            # language namespace (i.e. python module) which defines the display data.
-            # This allows a dax monitoring system to specially handle the data
-            # and perform custom rendering.
-        &quot;floatValue&quot;: 3.14, # Contains value if the data is of float type.
-        &quot;key&quot;: &quot;A String&quot;, # The key identifying the display data.
-            # This is intended to be used as a label for the display data
-            # when viewed in a dax monitoring system.
-        &quot;shortStrValue&quot;: &quot;A String&quot;, # A possible additional shorter value to display.
-            # For example a java_class_name_value of com.mypackage.MyDoFn
-            # will be stored with MyDoFn as the short_str_value and
-            # com.mypackage.MyDoFn as the java_class_name value.
-            # short_str_value can be displayed and java_class_name_value
-            # will be displayed as a tooltip.
-        &quot;url&quot;: &quot;A String&quot;, # An optional full URL.
-        &quot;label&quot;: &quot;A String&quot;, # An optional label to display in a dax UI for the element.
-        &quot;timestampValue&quot;: &quot;A String&quot;, # Contains value if the data is of timestamp type.
-        &quot;boolValue&quot;: True or False, # Contains value if the data is of a boolean type.
-        &quot;javaClassValue&quot;: &quot;A String&quot;, # Contains value if the data is of java class type.
-        &quot;strValue&quot;: &quot;A String&quot;, # Contains value if the data is of string type.
-      },
-    ],
-  },
-  &quot;replaceJobId&quot;: &quot;A String&quot;, # If this job is an update of an existing job, this field is the job ID
-      # of the job it replaced.
-      # 
-      # When sending a `CreateJobRequest`, you can update a job by specifying it
-      # here. The job named here is stopped, and its intermediate state is
-      # transferred to this job.
-  &quot;tempFiles&quot;: [ # A set of files the system should be aware of that are used
-      # for temporary storage. These temporary files will be
-      # removed on job completion.
-      # No duplicates are allowed.
-      # No file patterns are supported.
-      # 
-      # The supported files are:
-      # 
-      # Google Cloud Storage:
-      # 
-      #    storage.googleapis.com/{bucket}/{object}
-      #    bucket.storage.googleapis.com/{object}
-    &quot;A String&quot;,
-  ],
-  &quot;name&quot;: &quot;A String&quot;, # The user-specified Cloud Dataflow job name.
-      # 
-      # Only one Job with a given name may exist in a project at any
-      # given time. If a caller attempts to create a Job with the same
-      # name as an already-existing Job, the attempt returns the
-      # existing Job.
-      # 
-      # The name must match the regular expression
-      # `[a-z]([-a-z0-9]{0,38}[a-z0-9])?`
-  &quot;steps&quot;: [ # Exactly one of step or steps_location should be specified.
-      # 
-      # The top-level steps that constitute the entire job.
-    { # Defines a particular step within a Cloud Dataflow job.
-        #
-        # A job consists of multiple steps, each of which performs some
-        # specific operation as part of the overall job.  Data is typically
-        # passed from one step to another as part of the job.
-        #
-        # Here&#x27;s an example of a sequence of steps which together implement a
-        # Map-Reduce job:
-        #
-        #   * Read a collection of data from some source, parsing the
-        #     collection&#x27;s elements.
-        #
-        #   * Validate the elements.
-        #
-        #   * Apply a user-defined function to map each element to some value
-        #     and extract an element-specific key value.
-        #
-        #   * Group elements with the same key into a single element with
-        #     that key, transforming a multiply-keyed collection into a
-        #     uniquely-keyed collection.
-        #
-        #   * Write the elements out to some data sink.
-        #
-        # Note that the Cloud Dataflow service may be used to run many different
-        # types of jobs, not just Map-Reduce.
-      &quot;name&quot;: &quot;A String&quot;, # The name that identifies the step. This must be unique for each
-          # step with respect to all other steps in the Cloud Dataflow job.
-      &quot;kind&quot;: &quot;A String&quot;, # The kind of step in the Cloud Dataflow job.
-      &quot;properties&quot;: { # Named properties associated with the step. Each kind of
-          # predefined step has its own required set of properties.
-          # Must be provided on Create.  Only retrieved with JOB_VIEW_ALL.
-        &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
-      },
-    },
-  ],
-  &quot;replacedByJobId&quot;: &quot;A String&quot;, # If another job is an update of this job (and thus, this job is in
-      # `JOB_STATE_UPDATED`), this field contains the ID of that job.
-  &quot;executionInfo&quot;: { # Additional information about how a Cloud Dataflow job will be executed that # Deprecated.
-      # isn&#x27;t contained in the submitted job.
-    &quot;stages&quot;: { # A mapping from each stage to the information about that stage.
-      &quot;a_key&quot;: { # Contains information about how a particular
-          # google.dataflow.v1beta3.Step will be executed.
-        &quot;stepName&quot;: [ # The steps associated with the execution stage.
-            # Note that stages may have several steps, and that a given step
-            # might be run by more than one stage.
-          &quot;A String&quot;,
-        ],
-      },
-    },
-  },
-  &quot;currentState&quot;: &quot;A String&quot;, # The current state of the job.
-      # 
-      # Jobs are created in the `JOB_STATE_STOPPED` state unless otherwise
-      # specified.
-      # 
-      # A job in the `JOB_STATE_RUNNING` state may asynchronously enter a
-      # terminal state. After a job has reached a terminal state, no
-      # further state updates may be made.
-      # 
-      # This field may be mutated by the Cloud Dataflow service;
-      # callers cannot mutate it.
-  &quot;location&quot;: &quot;A String&quot;, # The [regional endpoint]
-      # (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that
-      # contains this job.
-  &quot;startTime&quot;: &quot;A String&quot;, # The timestamp when the job was started (transitioned to JOB_STATE_PENDING).
-      # Flexible resource scheduling jobs are started with some delay after job
-      # creation, so start_time is unset before start and is updated when the
-      # job is started by the Cloud Dataflow service. For other jobs, start_time
-      # always equals to create_time and is immutable and set by the Cloud Dataflow
-      # service.
-  &quot;stepsLocation&quot;: &quot;A String&quot;, # The GCS location where the steps are stored.
-  &quot;labels&quot;: { # User-defined labels for this job.
-      # 
-      # The labels map can contain no more than 64 entries.  Entries of the labels
-      # map are UTF8 strings that comply with the following restrictions:
-      # 
-      # * Keys must conform to regexp:  \p{Ll}\p{Lo}{0,62}
-      # * Values must conform to regexp:  [\p{Ll}\p{Lo}\p{N}_-]{0,63}
-      # * Both keys and values are additionally constrained to be &lt;= 128 bytes in
-      # size.
-    &quot;a_key&quot;: &quot;A String&quot;,
-  },
-  &quot;createTime&quot;: &quot;A String&quot;, # The timestamp when the job was initially created. Immutable and set by the
-      # Cloud Dataflow service.
-  &quot;requestedState&quot;: &quot;A String&quot;, # The job&#x27;s requested state.
-      # 
-      # `UpdateJob` may be used to switch between the `JOB_STATE_STOPPED` and
-      # `JOB_STATE_RUNNING` states, by setting requested_state.  `UpdateJob` may
-      # also be used to directly set a job&#x27;s requested state to
-      # `JOB_STATE_CANCELLED` or `JOB_STATE_DONE`, irrevocably terminating the
-      # job if it has not already reached a terminal state.
-}
-
-  location: string, The [regional endpoint]
-(https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that
-contains this job.
-  x__xgafv: string, V1 error format.
-    Allowed values
-      1 - v1 error format
-      2 - v2 error format
-
-Returns:
-  An object of the form:
-
-    { # Defines a job to be run by the Cloud Dataflow service.
-    &quot;clientRequestId&quot;: &quot;A String&quot;, # The client&#x27;s unique identifier of the job, re-used across retried attempts.
-        # If this field is set, the service will ensure its uniqueness.
-        # The request to create a job will fail if the service has knowledge of a
-        # previously submitted job with the same client&#x27;s ID and job name.
-        # The caller may use this field to ensure idempotence of job
-        # creation across retried attempts to create a job.
-        # By default, the field is empty and, in that case, the service ignores it.
-    &quot;id&quot;: &quot;A String&quot;, # The unique ID of this job.
-        #
-        # This field is set by the Cloud Dataflow service when the Job is
-        # created, and is immutable for the life of the job.
-    &quot;currentStateTime&quot;: &quot;A String&quot;, # The timestamp associated with the current state.
-    &quot;transformNameMapping&quot;: { # The map of transform name prefixes of the job to be replaced to the
-        # corresponding name prefixes of the new job.
+    &quot;labels&quot;: { # User-defined labels for this job.
+        # 
+        # The labels map can contain no more than 64 entries.  Entries of the labels
+        # map are UTF8 strings that comply with the following restrictions:
+        # 
+        # * Keys must conform to regexp:  \p{Ll}\p{Lo}{0,62}
+        # * Values must conform to regexp:  [\p{Ll}\p{Lo}\p{N}_-]{0,63}
+        # * Both keys and values are additionally constrained to be &lt;= 128 bytes in
+        # size.
       &quot;a_key&quot;: &quot;A String&quot;,
     },
+    &quot;projectId&quot;: &quot;A String&quot;, # The ID of the Cloud Platform project that the job belongs to.
     &quot;environment&quot;: { # Describes the environment in which a Dataflow Job runs. # The environment for the job.
-      &quot;internalExperiments&quot;: { # Experimental settings.
-        &quot;a_key&quot;: &quot;&quot;, # Properties of the object. Contains field @type with type URL.
-      },
+      &quot;flexResourceSchedulingGoal&quot;: &quot;A String&quot;, # Which Flexible Resource Scheduling mode to run in.
       &quot;workerRegion&quot;: &quot;A String&quot;, # The Compute Engine region
           # (https://cloud.google.com/compute/docs/regions-zones/regions-zones) in
           # which worker processing should occur, e.g. &quot;us-west1&quot;. Mutually exclusive
           # with worker_zone. If neither worker_region nor worker_zone is specified,
           # default to the control plane&#x27;s region.
+      &quot;userAgent&quot;: { # A description of the process that generated the request.
+        &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
+      },
+      &quot;serviceAccountEmail&quot;: &quot;A String&quot;, # Identity to run virtual machines as. Defaults to the default account.
+      &quot;version&quot;: { # A structure describing which components and their versions of the service
+          # are required in order to run the job.
+        &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
+      },
       &quot;serviceKmsKeyName&quot;: &quot;A String&quot;, # If set, contains the Cloud KMS key identifier used to encrypt data
           # at rest, AKA a Customer Managed Encryption Key (CMEK).
           #
           # Format:
           #   projects/PROJECT_ID/locations/LOCATION/keyRings/KEY_RING/cryptoKeys/KEY
-      &quot;userAgent&quot;: { # A description of the process that generated the request.
-        &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
-      },
+      &quot;experiments&quot;: [ # The list of experiments to enable.
+        &quot;A String&quot;,
+      ],
       &quot;workerZone&quot;: &quot;A String&quot;, # The Compute Engine zone
           # (https://cloud.google.com/compute/docs/regions-zones/regions-zones) in
           # which worker processing should occur, e.g. &quot;us-west1-a&quot;. Mutually exclusive
           # with worker_region. If neither worker_region nor worker_zone is specified,
           # a zone in the control plane&#x27;s region is chosen based on available capacity.
-      &quot;clusterManagerApiService&quot;: &quot;A String&quot;, # The type of cluster manager API to use.  If unknown or
-          # unspecified, the service will attempt to choose a reasonable
-          # default.  This should be in the form of the API service name,
-          # e.g. &quot;compute.googleapis.com&quot;.
-      &quot;tempStoragePrefix&quot;: &quot;A String&quot;, # The prefix of the resources the system should use for temporary
-          # storage.  The system will append the suffix &quot;/temp-{JOBNAME} to
-          # this resource prefix, where {JOBNAME} is the value of the
-          # job_name field.  The resulting bucket and object prefix is used
-          # as the prefix of the resources used to store temporary data
-          # needed during the job execution.  NOTE: This will override the
-          # value in taskrunner_settings.
-          # The supported resource type is:
-          #
-          # Google Cloud Storage:
-          #
-          #   storage.googleapis.com/{bucket}/{object}
-          #   bucket.storage.googleapis.com/{object}
-      &quot;experiments&quot;: [ # The list of experiments to enable.
-        &quot;A String&quot;,
-      ],
-      &quot;version&quot;: { # A structure describing which components and their versions of the service
-          # are required in order to run the job.
-        &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
-      },
-      &quot;serviceAccountEmail&quot;: &quot;A String&quot;, # Identity to run virtual machines as. Defaults to the default account.
-      &quot;sdkPipelineOptions&quot;: { # The Cloud Dataflow SDK pipeline options specified by the user. These
-          # options are passed through the service and are used to recreate the
-          # SDK pipeline options on the worker in a language agnostic and platform
-          # independent way.
-        &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
-      },
-      &quot;flexResourceSchedulingGoal&quot;: &quot;A String&quot;, # Which Flexible Resource Scheduling mode to run in.
       &quot;workerPools&quot;: [ # The worker pools. At least one &quot;harness&quot; worker pool must be
           # specified in order for the job to have workers.
         { # Describes one particular pool of Cloud Dataflow workers to be
@@ -4015,15 +3510,54 @@
             # computations required by a job.  Note that a workflow job may use
             # multiple pools, in order to match the various computational
             # requirements of the various stages of the job.
-          &quot;numThreadsPerWorker&quot;: 42, # The number of threads per worker harness. If empty or unspecified, the
-              # service will choose a number of threads (according to the number of cores
-              # on the selected machine type for batch, or 1 by convention for streaming).
-          &quot;numWorkers&quot;: 42, # Number of Google Compute Engine workers in this pool needed to
-              # execute the job.  If zero or unspecified, the service will
-              # attempt to choose a reasonable default.
+          &quot;onHostMaintenance&quot;: &quot;A String&quot;, # The action to take on host maintenance, as defined by the Google
+              # Compute Engine API.
+          &quot;sdkHarnessContainerImages&quot;: [ # Set of SDK harness containers needed to execute this pipeline. This will
+              # only be set in the Fn API path. For non-cross-language pipelines this
+              # should have only one entry. Cross-language pipelines will have two or more
+              # entries.
+            { # Defines a SDK harness container for executing Dataflow pipelines.
+              &quot;containerImage&quot;: &quot;A String&quot;, # A docker container image that resides in Google Container Registry.
+              &quot;useSingleCorePerContainer&quot;: True or False, # If true, recommends the Dataflow service to use only one core per SDK
+                  # container instance with this image. If false (or unset) recommends using
+                  # more than one core per SDK container instance with this image for
+                  # efficiency. Note that Dataflow service may choose to override this property
+                  # if needed.
+            },
+          ],
           &quot;zone&quot;: &quot;A String&quot;, # Zone to run the worker pools in.  If empty or unspecified, the service
               # will attempt to choose a reasonable default.
+          &quot;kind&quot;: &quot;A String&quot;, # The kind of the worker pool; currently only `harness` and `shuffle`
+              # are supported.
+          &quot;metadata&quot;: { # Metadata to set on the Google Compute Engine VMs.
+            &quot;a_key&quot;: &quot;A String&quot;,
+          },
           &quot;diskSourceImage&quot;: &quot;A String&quot;, # Fully qualified source image for disks.
+          &quot;dataDisks&quot;: [ # Data disks that are used by a VM in this workflow.
+            { # Describes the data disk used by a workflow job.
+              &quot;sizeGb&quot;: 42, # Size of disk in GB.  If zero or unspecified, the service will
+                  # attempt to choose a reasonable default.
+              &quot;diskType&quot;: &quot;A String&quot;, # Disk storage type, as defined by Google Compute Engine.  This
+                  # must be a disk type appropriate to the project and zone in which
+                  # the workers will run.  If unknown or unspecified, the service
+                  # will attempt to choose a reasonable default.
+                  #
+                  # For example, the standard persistent disk type is a resource name
+                  # typically ending in &quot;pd-standard&quot;.  If SSD persistent disks are
+                  # available, the resource name typically ends with &quot;pd-ssd&quot;.  The
+                  # actual valid values are defined the Google Compute Engine API,
+                  # not by the Cloud Dataflow API; consult the Google Compute Engine
+                  # documentation for more information about determining the set of
+                  # available disk types for a particular project and zone.
+                  #
+                  # Google Compute Engine Disk types are local to a particular
+                  # project in a particular zone, and so the resource name will
+                  # typically look something like this:
+                  #
+                  # compute.googleapis.com/projects/project-id/zones/zone/diskTypes/pd-standard
+              &quot;mountPoint&quot;: &quot;A String&quot;, # Directory in a VM where disk is mounted.
+            },
+          ],
           &quot;packages&quot;: [ # Packages to be installed on workers.
             { # The packages that must be installed in order for a worker to run the
                 # steps of the Cloud Dataflow job that will be assigned to its worker
@@ -4059,98 +3593,38 @@
               #
               # If unknown or unspecified, the service will attempt to choose a reasonable
               # default.
-          &quot;onHostMaintenance&quot;: &quot;A String&quot;, # The action to take on host maintenance, as defined by the Google
-              # Compute Engine API.
+          &quot;network&quot;: &quot;A String&quot;, # Network to which VMs will be assigned.  If empty or unspecified,
+              # the service will use the network &quot;default&quot;.
+          &quot;ipConfiguration&quot;: &quot;A String&quot;, # Configuration for VM IPs.
+          &quot;diskSizeGb&quot;: 42, # Size of root disk for VMs, in GB.  If zero or unspecified, the service will
+              # attempt to choose a reasonable default.
+          &quot;autoscalingSettings&quot;: { # Settings for WorkerPool autoscaling. # Settings for autoscaling of this WorkerPool.
+            &quot;maxNumWorkers&quot;: 42, # The maximum number of workers to cap scaling at.
+            &quot;algorithm&quot;: &quot;A String&quot;, # The algorithm to use for autoscaling.
+          },
           &quot;poolArgs&quot;: { # Extra arguments for this worker pool.
             &quot;a_key&quot;: &quot;&quot;, # Properties of the object. Contains field @type with type URL.
           },
-          &quot;diskSizeGb&quot;: 42, # Size of root disk for VMs, in GB.  If zero or unspecified, the service will
+          &quot;subnetwork&quot;: &quot;A String&quot;, # Subnetwork to which VMs will be assigned, if desired.  Expected to be of
+              # the form &quot;regions/REGION/subnetworks/SUBNETWORK&quot;.
+          &quot;numWorkers&quot;: 42, # Number of Google Compute Engine workers in this pool needed to
+              # execute the job.  If zero or unspecified, the service will
               # attempt to choose a reasonable default.
+          &quot;numThreadsPerWorker&quot;: 42, # The number of threads per worker harness. If empty or unspecified, the
+              # service will choose a number of threads (according to the number of cores
+              # on the selected machine type for batch, or 1 by convention for streaming).
           &quot;workerHarnessContainerImage&quot;: &quot;A String&quot;, # Required. Docker container image that executes the Cloud Dataflow worker
               # harness, residing in Google Container Registry.
               #
               # Deprecated for the Fn API path. Use sdk_harness_container_images instead.
-          &quot;diskType&quot;: &quot;A String&quot;, # Type of root disk for VMs.  If empty or unspecified, the service will
-              # attempt to choose a reasonable default.
-          &quot;machineType&quot;: &quot;A String&quot;, # Machine type (e.g. &quot;n1-standard-1&quot;).  If empty or unspecified, the
-              # service will attempt to choose a reasonable default.
-          &quot;kind&quot;: &quot;A String&quot;, # The kind of the worker pool; currently only `harness` and `shuffle`
-              # are supported.
-          &quot;sdkHarnessContainerImages&quot;: [ # Set of SDK harness containers needed to execute this pipeline. This will
-              # only be set in the Fn API path. For non-cross-language pipelines this
-              # should have only one entry. Cross-language pipelines will have two or more
-              # entries.
-            { # Defines a SDK harness container for executing Dataflow pipelines.
-              &quot;containerImage&quot;: &quot;A String&quot;, # A docker container image that resides in Google Container Registry.
-              &quot;useSingleCorePerContainer&quot;: True or False, # If true, recommends the Dataflow service to use only one core per SDK
-                  # container instance with this image. If false (or unset) recommends using
-                  # more than one core per SDK container instance with this image for
-                  # efficiency. Note that Dataflow service may choose to override this property
-                  # if needed.
-            },
-          ],
-          &quot;dataDisks&quot;: [ # Data disks that are used by a VM in this workflow.
-            { # Describes the data disk used by a workflow job.
-              &quot;diskType&quot;: &quot;A String&quot;, # Disk storage type, as defined by Google Compute Engine.  This
-                  # must be a disk type appropriate to the project and zone in which
-                  # the workers will run.  If unknown or unspecified, the service
-                  # will attempt to choose a reasonable default.
-                  #
-                  # For example, the standard persistent disk type is a resource name
-                  # typically ending in &quot;pd-standard&quot;.  If SSD persistent disks are
-                  # available, the resource name typically ends with &quot;pd-ssd&quot;.  The
-                  # actual valid values are defined the Google Compute Engine API,
-                  # not by the Cloud Dataflow API; consult the Google Compute Engine
-                  # documentation for more information about determining the set of
-                  # available disk types for a particular project and zone.
-                  #
-                  # Google Compute Engine Disk types are local to a particular
-                  # project in a particular zone, and so the resource name will
-                  # typically look something like this:
-                  #
-                  # compute.googleapis.com/projects/project-id/zones/zone/diskTypes/pd-standard
-              &quot;sizeGb&quot;: 42, # Size of disk in GB.  If zero or unspecified, the service will
-                  # attempt to choose a reasonable default.
-              &quot;mountPoint&quot;: &quot;A String&quot;, # Directory in a VM where disk is mounted.
-            },
-          ],
-          &quot;subnetwork&quot;: &quot;A String&quot;, # Subnetwork to which VMs will be assigned, if desired.  Expected to be of
-              # the form &quot;regions/REGION/subnetworks/SUBNETWORK&quot;.
-          &quot;ipConfiguration&quot;: &quot;A String&quot;, # Configuration for VM IPs.
           &quot;taskrunnerSettings&quot;: { # Taskrunner configuration settings. # Settings passed through to Google Compute Engine workers when
               # using the standard Dataflow task runner.  Users should ignore
               # this field.
-            &quot;alsologtostderr&quot;: True or False, # Whether to also send taskrunner log info to stderr.
-            &quot;taskGroup&quot;: &quot;A String&quot;, # The UNIX group ID on the worker VM to use for tasks launched by
-                # taskrunner; e.g. &quot;wheel&quot;.
-            &quot;harnessCommand&quot;: &quot;A String&quot;, # The command to launch the worker harness.
-            &quot;logDir&quot;: &quot;A String&quot;, # The directory on the VM to store logs.
+            &quot;dataflowApiVersion&quot;: &quot;A String&quot;, # The API version of endpoint, e.g. &quot;v1b3&quot;
             &quot;oauthScopes&quot;: [ # The OAuth2 scopes to be requested by the taskrunner in order to
                 # access the Cloud Dataflow API.
               &quot;A String&quot;,
             ],
-            &quot;dataflowApiVersion&quot;: &quot;A String&quot;, # The API version of endpoint, e.g. &quot;v1b3&quot;
-            &quot;logUploadLocation&quot;: &quot;A String&quot;, # Indicates where to put logs.  If this is not specified, the logs
-                # will not be uploaded.
-                #
-                # The supported resource type is:
-                #
-                # Google Cloud Storage:
-                #   storage.googleapis.com/{bucket}/{object}
-                #   bucket.storage.googleapis.com/{object}
-            &quot;streamingWorkerMainClass&quot;: &quot;A String&quot;, # The streaming worker main class name.
-            &quot;workflowFileName&quot;: &quot;A String&quot;, # The file to store the workflow in.
-            &quot;languageHint&quot;: &quot;A String&quot;, # The suggested backend language.
-            &quot;commandlinesFileName&quot;: &quot;A String&quot;, # The file to store preprocessing commands in.
-            &quot;baseTaskDir&quot;: &quot;A String&quot;, # The location on the worker for task-specific subdirectories.
-            &quot;tempStoragePrefix&quot;: &quot;A String&quot;, # The prefix of the resources the taskrunner should use for
-                # temporary storage.
-                #
-                # The supported resource type is:
-                #
-                # Google Cloud Storage:
-                #   storage.googleapis.com/{bucket}/{object}
-                #   bucket.storage.googleapis.com/{object}
             &quot;baseUrl&quot;: &quot;A String&quot;, # The base URL for the taskrunner to use when accessing Google Cloud APIs.
                 #
                 # When workers access Google Cloud APIs, they logically do so via
@@ -4160,10 +3634,17 @@
                 # Locators&quot;.
                 #
                 # If not specified, the default value is &quot;http://www.googleapis.com/&quot;
+            &quot;workflowFileName&quot;: &quot;A String&quot;, # The file to store the workflow in.
             &quot;logToSerialconsole&quot;: True or False, # Whether to send taskrunner log info to Google Compute Engine VM serial
                 # console.
-            &quot;continueOnException&quot;: True or False, # Whether to continue taskrunner if an exception is hit.
+            &quot;baseTaskDir&quot;: &quot;A String&quot;, # The location on the worker for task-specific subdirectories.
+            &quot;taskUser&quot;: &quot;A String&quot;, # The UNIX user ID on the worker VM to use for tasks launched by
+                # taskrunner; e.g. &quot;root&quot;.
+            &quot;vmId&quot;: &quot;A String&quot;, # The ID string of the VM.
+            &quot;alsologtostderr&quot;: True or False, # Whether to also send taskrunner log info to stderr.
             &quot;parallelWorkerSettings&quot;: { # Provides data to pass through to the worker harness. # The settings to pass to the parallel worker harness.
+              &quot;shuffleServicePath&quot;: &quot;A String&quot;, # The Shuffle service path relative to the root URL, for example,
+                  # &quot;shuffle/v1beta1&quot;.
               &quot;tempStoragePrefix&quot;: &quot;A String&quot;, # The prefix of the resources the system should use for temporary
                   # storage.
                   #
@@ -4174,6 +3655,8 @@
                   #   storage.googleapis.com/{bucket}/{object}
                   #   bucket.storage.googleapis.com/{object}
               &quot;reportingEnabled&quot;: True or False, # Whether to send work progress updates to the service.
+              &quot;servicePath&quot;: &quot;A String&quot;, # The Cloud Dataflow service path relative to the root URL, for example,
+                  # &quot;dataflow/v1b3/projects&quot;.
               &quot;baseUrl&quot;: &quot;A String&quot;, # The base URL for accessing Google Cloud APIs.
                   #
                   # When workers access Google Cloud APIs, they logically do so via
@@ -4183,30 +3666,64 @@
                   # Locators&quot;.
                   #
                   # If not specified, the default value is &quot;http://www.googleapis.com/&quot;
-              &quot;servicePath&quot;: &quot;A String&quot;, # The Cloud Dataflow service path relative to the root URL, for example,
-                  # &quot;dataflow/v1b3/projects&quot;.
-              &quot;shuffleServicePath&quot;: &quot;A String&quot;, # The Shuffle service path relative to the root URL, for example,
-                  # &quot;shuffle/v1beta1&quot;.
               &quot;workerId&quot;: &quot;A String&quot;, # The ID of the worker running this pipeline.
             },
-            &quot;taskUser&quot;: &quot;A String&quot;, # The UNIX user ID on the worker VM to use for tasks launched by
-                # taskrunner; e.g. &quot;root&quot;.
-            &quot;vmId&quot;: &quot;A String&quot;, # The ID string of the VM.
+            &quot;harnessCommand&quot;: &quot;A String&quot;, # The command to launch the worker harness.
+            &quot;logDir&quot;: &quot;A String&quot;, # The directory on the VM to store logs.
+            &quot;streamingWorkerMainClass&quot;: &quot;A String&quot;, # The streaming worker main class name.
+            &quot;languageHint&quot;: &quot;A String&quot;, # The suggested backend language.
+            &quot;taskGroup&quot;: &quot;A String&quot;, # The UNIX group ID on the worker VM to use for tasks launched by
+                # taskrunner; e.g. &quot;wheel&quot;.
+            &quot;logUploadLocation&quot;: &quot;A String&quot;, # Indicates where to put logs.  If this is not specified, the logs
+                # will not be uploaded.
+                #
+                # The supported resource type is:
+                #
+                # Google Cloud Storage:
+                #   storage.googleapis.com/{bucket}/{object}
+                #   bucket.storage.googleapis.com/{object}
+            &quot;commandlinesFileName&quot;: &quot;A String&quot;, # The file to store preprocessing commands in.
+            &quot;continueOnException&quot;: True or False, # Whether to continue taskrunner if an exception is hit.
+            &quot;tempStoragePrefix&quot;: &quot;A String&quot;, # The prefix of the resources the taskrunner should use for
+                # temporary storage.
+                #
+                # The supported resource type is:
+                #
+                # Google Cloud Storage:
+                #   storage.googleapis.com/{bucket}/{object}
+                #   bucket.storage.googleapis.com/{object}
           },
-          &quot;autoscalingSettings&quot;: { # Settings for WorkerPool autoscaling. # Settings for autoscaling of this WorkerPool.
-            &quot;algorithm&quot;: &quot;A String&quot;, # The algorithm to use for autoscaling.
-            &quot;maxNumWorkers&quot;: 42, # The maximum number of workers to cap scaling at.
-          },
-          &quot;metadata&quot;: { # Metadata to set on the Google Compute Engine VMs.
-            &quot;a_key&quot;: &quot;A String&quot;,
-          },
+          &quot;diskType&quot;: &quot;A String&quot;, # Type of root disk for VMs.  If empty or unspecified, the service will
+              # attempt to choose a reasonable default.
           &quot;defaultPackageSet&quot;: &quot;A String&quot;, # The default package set to install.  This allows the service to
               # select a default set of packages which are useful to worker
               # harnesses written in a particular language.
-          &quot;network&quot;: &quot;A String&quot;, # Network to which VMs will be assigned.  If empty or unspecified,
-              # the service will use the network &quot;default&quot;.
+          &quot;machineType&quot;: &quot;A String&quot;, # Machine type (e.g. &quot;n1-standard-1&quot;).  If empty or unspecified, the
+              # service will attempt to choose a reasonable default.
         },
       ],
+      &quot;tempStoragePrefix&quot;: &quot;A String&quot;, # The prefix of the resources the system should use for temporary
+          # storage.  The system will append the suffix &quot;/temp-{JOBNAME} to
+          # this resource prefix, where {JOBNAME} is the value of the
+          # job_name field.  The resulting bucket and object prefix is used
+          # as the prefix of the resources used to store temporary data
+          # needed during the job execution.  NOTE: This will override the
+          # value in taskrunner_settings.
+          # The supported resource type is:
+          #
+          # Google Cloud Storage:
+          #
+          #   storage.googleapis.com/{bucket}/{object}
+          #   bucket.storage.googleapis.com/{object}
+      &quot;internalExperiments&quot;: { # Experimental settings.
+        &quot;a_key&quot;: &quot;&quot;, # Properties of the object. Contains field @type with type URL.
+      },
+      &quot;sdkPipelineOptions&quot;: { # The Cloud Dataflow SDK pipeline options specified by the user. These
+          # options are passed through the service and are used to recreate the
+          # SDK pipeline options on the worker in a language agnostic and platform
+          # independent way.
+        &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
+      },
       &quot;dataset&quot;: &quot;A String&quot;, # The dataset for the current project where various workflow
           # related tables are stored.
           #
@@ -4214,215 +3731,14 @@
           #
           # Google BigQuery:
           #   bigquery.googleapis.com/{dataset}
+      &quot;clusterManagerApiService&quot;: &quot;A String&quot;, # The type of cluster manager API to use.  If unknown or
+          # unspecified, the service will attempt to choose a reasonable
+          # default.  This should be in the form of the API service name,
+          # e.g. &quot;compute.googleapis.com&quot;.
     },
-    &quot;stageStates&quot;: [ # This field may be mutated by the Cloud Dataflow service;
-        # callers cannot mutate it.
-      { # A message describing the state of a particular execution stage.
-        &quot;currentStateTime&quot;: &quot;A String&quot;, # The time at which the stage transitioned to this state.
-        &quot;executionStageState&quot;: &quot;A String&quot;, # Executions stage states allow the same set of values as JobState.
-        &quot;executionStageName&quot;: &quot;A String&quot;, # The name of the execution stage.
-      },
-    ],
-    &quot;jobMetadata&quot;: { # Metadata available primarily for filtering jobs. Will be included in the # This field is populated by the Dataflow service to support filtering jobs
-        # by the metadata values provided here. Populated for ListJobs and all GetJob
-        # views SUMMARY and higher.
-        # ListJob response and Job SUMMARY view.
-      &quot;datastoreDetails&quot;: [ # Identification of a Datastore source used in the Dataflow job.
-        { # Metadata for a Datastore connector used by the job.
-          &quot;namespace&quot;: &quot;A String&quot;, # Namespace used in the connection.
-          &quot;projectId&quot;: &quot;A String&quot;, # ProjectId accessed in the connection.
-        },
-      ],
-      &quot;sdkVersion&quot;: { # The version of the SDK used to run the job. # The SDK version used to run the job.
-        &quot;version&quot;: &quot;A String&quot;, # The version of the SDK used to run the job.
-        &quot;sdkSupportStatus&quot;: &quot;A String&quot;, # The support status for this SDK version.
-        &quot;versionDisplayName&quot;: &quot;A String&quot;, # A readable string describing the version of the SDK.
-      },
-      &quot;bigqueryDetails&quot;: [ # Identification of a BigQuery source used in the Dataflow job.
-        { # Metadata for a BigQuery connector used by the job.
-          &quot;table&quot;: &quot;A String&quot;, # Table accessed in the connection.
-          &quot;dataset&quot;: &quot;A String&quot;, # Dataset accessed in the connection.
-          &quot;query&quot;: &quot;A String&quot;, # Query used to access data in the connection.
-          &quot;projectId&quot;: &quot;A String&quot;, # Project accessed in the connection.
-        },
-      ],
-      &quot;fileDetails&quot;: [ # Identification of a File source used in the Dataflow job.
-        { # Metadata for a File connector used by the job.
-          &quot;filePattern&quot;: &quot;A String&quot;, # File Pattern used to access files by the connector.
-        },
-      ],
-      &quot;pubsubDetails&quot;: [ # Identification of a PubSub source used in the Dataflow job.
-        { # Metadata for a PubSub connector used by the job.
-          &quot;topic&quot;: &quot;A String&quot;, # Topic accessed in the connection.
-          &quot;subscription&quot;: &quot;A String&quot;, # Subscription used in the connection.
-        },
-      ],
-      &quot;bigTableDetails&quot;: [ # Identification of a BigTable source used in the Dataflow job.
-        { # Metadata for a BigTable connector used by the job.
-          &quot;projectId&quot;: &quot;A String&quot;, # ProjectId accessed in the connection.
-          &quot;instanceId&quot;: &quot;A String&quot;, # InstanceId accessed in the connection.
-          &quot;tableId&quot;: &quot;A String&quot;, # TableId accessed in the connection.
-        },
-      ],
-      &quot;spannerDetails&quot;: [ # Identification of a Spanner source used in the Dataflow job.
-        { # Metadata for a Spanner connector used by the job.
-          &quot;instanceId&quot;: &quot;A String&quot;, # InstanceId accessed in the connection.
-          &quot;projectId&quot;: &quot;A String&quot;, # ProjectId accessed in the connection.
-          &quot;databaseId&quot;: &quot;A String&quot;, # DatabaseId accessed in the connection.
-        },
-      ],
-    },
-    &quot;type&quot;: &quot;A String&quot;, # The type of Cloud Dataflow job.
-    &quot;projectId&quot;: &quot;A String&quot;, # The ID of the Cloud Platform project that the job belongs to.
-    &quot;createdFromSnapshotId&quot;: &quot;A String&quot;, # If this is specified, the job&#x27;s initial state is populated from the given
-        # snapshot.
-    &quot;pipelineDescription&quot;: { # A descriptive representation of submitted pipeline as well as the executed # Preliminary field: The format of this data may change at any time.
-        # A description of the user pipeline and stages through which it is executed.
-        # Created by Cloud Dataflow service.  Only retrieved with
-        # JOB_VIEW_DESCRIPTION or JOB_VIEW_ALL.
-        # form.  This data is provided by the Dataflow service for ease of visualizing
-        # the pipeline and interpreting Dataflow provided metrics.
-      &quot;executionPipelineStage&quot;: [ # Description of each stage of execution of the pipeline.
-        { # Description of the composing transforms, names/ids, and input/outputs of a
-            # stage of execution.  Some composing transforms and sources may have been
-            # generated by the Dataflow service during execution planning.
-          &quot;outputSource&quot;: [ # Output sources for this stage.
-            { # Description of an input or output of an execution stage.
-              &quot;sizeBytes&quot;: &quot;A String&quot;, # Size of the source, if measurable.
-              &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
-              &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this source; may be user or system generated.
-              &quot;originalTransformOrCollection&quot;: &quot;A String&quot;, # User name for the original user transform or collection with which this
-                  # source is most closely associated.
-            },
-          ],
-          &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this stage.
-          &quot;inputSource&quot;: [ # Input sources for this stage.
-            { # Description of an input or output of an execution stage.
-              &quot;sizeBytes&quot;: &quot;A String&quot;, # Size of the source, if measurable.
-              &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
-              &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this source; may be user or system generated.
-              &quot;originalTransformOrCollection&quot;: &quot;A String&quot;, # User name for the original user transform or collection with which this
-                  # source is most closely associated.
-            },
-          ],
-          &quot;id&quot;: &quot;A String&quot;, # Dataflow service generated id for this stage.
-          &quot;componentTransform&quot;: [ # Transforms that comprise this execution stage.
-            { # Description of a transform executed as part of an execution stage.
-              &quot;originalTransform&quot;: &quot;A String&quot;, # User name for the original user transform with which this transform is
-                  # most closely associated.
-              &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
-              &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this transform; may be user or system generated.
-            },
-          ],
-          &quot;componentSource&quot;: [ # Collections produced and consumed by component transforms of this stage.
-            { # Description of an interstitial value between transforms in an execution
-                # stage.
-              &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
-              &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this transform; may be user or system generated.
-              &quot;originalTransformOrCollection&quot;: &quot;A String&quot;, # User name for the original user transform or collection with which this
-                  # source is most closely associated.
-            },
-          ],
-          &quot;kind&quot;: &quot;A String&quot;, # Type of tranform this stage is executing.
-        },
-      ],
-      &quot;originalPipelineTransform&quot;: [ # Description of each transform in the pipeline and collections between them.
-        { # Description of the type, names/ids, and input/outputs for a transform.
-          &quot;kind&quot;: &quot;A String&quot;, # Type of transform.
-          &quot;inputCollectionName&quot;: [ # User names for all collection inputs to this transform.
-            &quot;A String&quot;,
-          ],
-          &quot;name&quot;: &quot;A String&quot;, # User provided name for this transform instance.
-          &quot;id&quot;: &quot;A String&quot;, # SDK generated id of this transform instance.
-          &quot;displayData&quot;: [ # Transform-specific display data.
-            { # Data provided with a pipeline or transform to provide descriptive info.
-              &quot;durationValue&quot;: &quot;A String&quot;, # Contains value if the data is of duration type.
-              &quot;int64Value&quot;: &quot;A String&quot;, # Contains value if the data is of int64 type.
-              &quot;namespace&quot;: &quot;A String&quot;, # The namespace for the key. This is usually a class name or programming
-                  # language namespace (i.e. python module) which defines the display data.
-                  # This allows a dax monitoring system to specially handle the data
-                  # and perform custom rendering.
-              &quot;floatValue&quot;: 3.14, # Contains value if the data is of float type.
-              &quot;key&quot;: &quot;A String&quot;, # The key identifying the display data.
-                  # This is intended to be used as a label for the display data
-                  # when viewed in a dax monitoring system.
-              &quot;shortStrValue&quot;: &quot;A String&quot;, # A possible additional shorter value to display.
-                  # For example a java_class_name_value of com.mypackage.MyDoFn
-                  # will be stored with MyDoFn as the short_str_value and
-                  # com.mypackage.MyDoFn as the java_class_name value.
-                  # short_str_value can be displayed and java_class_name_value
-                  # will be displayed as a tooltip.
-              &quot;url&quot;: &quot;A String&quot;, # An optional full URL.
-              &quot;label&quot;: &quot;A String&quot;, # An optional label to display in a dax UI for the element.
-              &quot;timestampValue&quot;: &quot;A String&quot;, # Contains value if the data is of timestamp type.
-              &quot;boolValue&quot;: True or False, # Contains value if the data is of a boolean type.
-              &quot;javaClassValue&quot;: &quot;A String&quot;, # Contains value if the data is of java class type.
-              &quot;strValue&quot;: &quot;A String&quot;, # Contains value if the data is of string type.
-            },
-          ],
-          &quot;outputCollectionName&quot;: [ # User  names for all collection outputs to this transform.
-            &quot;A String&quot;,
-          ],
-        },
-      ],
-      &quot;displayData&quot;: [ # Pipeline level display data.
-        { # Data provided with a pipeline or transform to provide descriptive info.
-          &quot;durationValue&quot;: &quot;A String&quot;, # Contains value if the data is of duration type.
-          &quot;int64Value&quot;: &quot;A String&quot;, # Contains value if the data is of int64 type.
-          &quot;namespace&quot;: &quot;A String&quot;, # The namespace for the key. This is usually a class name or programming
-              # language namespace (i.e. python module) which defines the display data.
-              # This allows a dax monitoring system to specially handle the data
-              # and perform custom rendering.
-          &quot;floatValue&quot;: 3.14, # Contains value if the data is of float type.
-          &quot;key&quot;: &quot;A String&quot;, # The key identifying the display data.
-              # This is intended to be used as a label for the display data
-              # when viewed in a dax monitoring system.
-          &quot;shortStrValue&quot;: &quot;A String&quot;, # A possible additional shorter value to display.
-              # For example a java_class_name_value of com.mypackage.MyDoFn
-              # will be stored with MyDoFn as the short_str_value and
-              # com.mypackage.MyDoFn as the java_class_name value.
-              # short_str_value can be displayed and java_class_name_value
-              # will be displayed as a tooltip.
-          &quot;url&quot;: &quot;A String&quot;, # An optional full URL.
-          &quot;label&quot;: &quot;A String&quot;, # An optional label to display in a dax UI for the element.
-          &quot;timestampValue&quot;: &quot;A String&quot;, # Contains value if the data is of timestamp type.
-          &quot;boolValue&quot;: True or False, # Contains value if the data is of a boolean type.
-          &quot;javaClassValue&quot;: &quot;A String&quot;, # Contains value if the data is of java class type.
-          &quot;strValue&quot;: &quot;A String&quot;, # Contains value if the data is of string type.
-        },
-      ],
-    },
-    &quot;replaceJobId&quot;: &quot;A String&quot;, # If this job is an update of an existing job, this field is the job ID
-        # of the job it replaced.
-        #
-        # When sending a `CreateJobRequest`, you can update a job by specifying it
-        # here. The job named here is stopped, and its intermediate state is
-        # transferred to this job.
-    &quot;tempFiles&quot;: [ # A set of files the system should be aware of that are used
-        # for temporary storage. These temporary files will be
-        # removed on job completion.
-        # No duplicates are allowed.
-        # No file patterns are supported.
-        #
-        # The supported files are:
-        #
-        # Google Cloud Storage:
-        #
-        #    storage.googleapis.com/{bucket}/{object}
-        #    bucket.storage.googleapis.com/{object}
-      &quot;A String&quot;,
-    ],
-    &quot;name&quot;: &quot;A String&quot;, # The user-specified Cloud Dataflow job name.
-        #
-        # Only one Job with a given name may exist in a project at any
-        # given time. If a caller attempts to create a Job with the same
-        # name as an already-existing Job, the attempt returns the
-        # existing Job.
-        #
-        # The name must match the regular expression
-        # `[a-z]([-a-z0-9]{0,38}[a-z0-9])?`
+    &quot;stepsLocation&quot;: &quot;A String&quot;, # The GCS location where the steps are stored.
     &quot;steps&quot;: [ # Exactly one of step or steps_location should be specified.
-        #
+        # 
         # The top-level steps that constitute the entire job.
       { # Defines a particular step within a Cloud Dataflow job.
           #
@@ -4449,18 +3765,95 @@
           #
           # Note that the Cloud Dataflow service may be used to run many different
           # types of jobs, not just Map-Reduce.
-        &quot;name&quot;: &quot;A String&quot;, # The name that identifies the step. This must be unique for each
-            # step with respect to all other steps in the Cloud Dataflow job.
         &quot;kind&quot;: &quot;A String&quot;, # The kind of step in the Cloud Dataflow job.
         &quot;properties&quot;: { # Named properties associated with the step. Each kind of
             # predefined step has its own required set of properties.
             # Must be provided on Create.  Only retrieved with JOB_VIEW_ALL.
           &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
         },
+        &quot;name&quot;: &quot;A String&quot;, # The name that identifies the step. This must be unique for each
+            # step with respect to all other steps in the Cloud Dataflow job.
+      },
+    ],
+    &quot;stageStates&quot;: [ # This field may be mutated by the Cloud Dataflow service;
+        # callers cannot mutate it.
+      { # A message describing the state of a particular execution stage.
+        &quot;executionStageState&quot;: &quot;A String&quot;, # Executions stage states allow the same set of values as JobState.
+        &quot;executionStageName&quot;: &quot;A String&quot;, # The name of the execution stage.
+        &quot;currentStateTime&quot;: &quot;A String&quot;, # The time at which the stage transitioned to this state.
       },
     ],
     &quot;replacedByJobId&quot;: &quot;A String&quot;, # If another job is an update of this job (and thus, this job is in
         # `JOB_STATE_UPDATED`), this field contains the ID of that job.
+    &quot;jobMetadata&quot;: { # Metadata available primarily for filtering jobs. Will be included in the # This field is populated by the Dataflow service to support filtering jobs
+        # by the metadata values provided here. Populated for ListJobs and all GetJob
+        # views SUMMARY and higher.
+        # ListJob response and Job SUMMARY view.
+      &quot;sdkVersion&quot;: { # The version of the SDK used to run the job. # The SDK version used to run the job.
+        &quot;sdkSupportStatus&quot;: &quot;A String&quot;, # The support status for this SDK version.
+        &quot;versionDisplayName&quot;: &quot;A String&quot;, # A readable string describing the version of the SDK.
+        &quot;version&quot;: &quot;A String&quot;, # The version of the SDK used to run the job.
+      },
+      &quot;bigTableDetails&quot;: [ # Identification of a BigTable source used in the Dataflow job.
+        { # Metadata for a BigTable connector used by the job.
+          &quot;instanceId&quot;: &quot;A String&quot;, # InstanceId accessed in the connection.
+          &quot;tableId&quot;: &quot;A String&quot;, # TableId accessed in the connection.
+          &quot;projectId&quot;: &quot;A String&quot;, # ProjectId accessed in the connection.
+        },
+      ],
+      &quot;pubsubDetails&quot;: [ # Identification of a PubSub source used in the Dataflow job.
+        { # Metadata for a PubSub connector used by the job.
+          &quot;subscription&quot;: &quot;A String&quot;, # Subscription used in the connection.
+          &quot;topic&quot;: &quot;A String&quot;, # Topic accessed in the connection.
+        },
+      ],
+      &quot;bigqueryDetails&quot;: [ # Identification of a BigQuery source used in the Dataflow job.
+        { # Metadata for a BigQuery connector used by the job.
+          &quot;dataset&quot;: &quot;A String&quot;, # Dataset accessed in the connection.
+          &quot;projectId&quot;: &quot;A String&quot;, # Project accessed in the connection.
+          &quot;query&quot;: &quot;A String&quot;, # Query used to access data in the connection.
+          &quot;table&quot;: &quot;A String&quot;, # Table accessed in the connection.
+        },
+      ],
+      &quot;fileDetails&quot;: [ # Identification of a File source used in the Dataflow job.
+        { # Metadata for a File connector used by the job.
+          &quot;filePattern&quot;: &quot;A String&quot;, # File Pattern used to access files by the connector.
+        },
+      ],
+      &quot;datastoreDetails&quot;: [ # Identification of a Datastore source used in the Dataflow job.
+        { # Metadata for a Datastore connector used by the job.
+          &quot;namespace&quot;: &quot;A String&quot;, # Namespace used in the connection.
+          &quot;projectId&quot;: &quot;A String&quot;, # ProjectId accessed in the connection.
+        },
+      ],
+      &quot;spannerDetails&quot;: [ # Identification of a Spanner source used in the Dataflow job.
+        { # Metadata for a Spanner connector used by the job.
+          &quot;instanceId&quot;: &quot;A String&quot;, # InstanceId accessed in the connection.
+          &quot;databaseId&quot;: &quot;A String&quot;, # DatabaseId accessed in the connection.
+          &quot;projectId&quot;: &quot;A String&quot;, # ProjectId accessed in the connection.
+        },
+      ],
+    },
+    &quot;location&quot;: &quot;A String&quot;, # The [regional endpoint]
+        # (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that
+        # contains this job.
+    &quot;transformNameMapping&quot;: { # The map of transform name prefixes of the job to be replaced to the
+        # corresponding name prefixes of the new job.
+      &quot;a_key&quot;: &quot;A String&quot;,
+    },
+    &quot;startTime&quot;: &quot;A String&quot;, # The timestamp when the job was started (transitioned to JOB_STATE_PENDING).
+        # Flexible resource scheduling jobs are started with some delay after job
+        # creation, so start_time is unset before start and is updated when the
+        # job is started by the Cloud Dataflow service. For other jobs, start_time
+        # always equals to create_time and is immutable and set by the Cloud Dataflow
+        # service.
+    &quot;clientRequestId&quot;: &quot;A String&quot;, # The client&#x27;s unique identifier of the job, re-used across retried attempts.
+        # If this field is set, the service will ensure its uniqueness.
+        # The request to create a job will fail if the service has knowledge of a
+        # previously submitted job with the same client&#x27;s ID and job name.
+        # The caller may use this field to ensure idempotence of job
+        # creation across retried attempts to create a job.
+        # By default, the field is empty and, in that case, the service ignores it.
     &quot;executionInfo&quot;: { # Additional information about how a Cloud Dataflow job will be executed that # Deprecated.
         # isn&#x27;t contained in the submitted job.
       &quot;stages&quot;: { # A mapping from each stage to the information about that stage.
@@ -4474,48 +3867,655 @@
         },
       },
     },
-    &quot;currentState&quot;: &quot;A String&quot;, # The current state of the job.
-        #
-        # Jobs are created in the `JOB_STATE_STOPPED` state unless otherwise
-        # specified.
-        #
-        # A job in the `JOB_STATE_RUNNING` state may asynchronously enter a
-        # terminal state. After a job has reached a terminal state, no
-        # further state updates may be made.
-        #
-        # This field may be mutated by the Cloud Dataflow service;
-        # callers cannot mutate it.
-    &quot;location&quot;: &quot;A String&quot;, # The [regional endpoint]
-        # (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that
-        # contains this job.
-    &quot;startTime&quot;: &quot;A String&quot;, # The timestamp when the job was started (transitioned to JOB_STATE_PENDING).
-        # Flexible resource scheduling jobs are started with some delay after job
-        # creation, so start_time is unset before start and is updated when the
-        # job is started by the Cloud Dataflow service. For other jobs, start_time
-        # always equals to create_time and is immutable and set by the Cloud Dataflow
-        # service.
-    &quot;stepsLocation&quot;: &quot;A String&quot;, # The GCS location where the steps are stored.
-    &quot;labels&quot;: { # User-defined labels for this job.
-        #
-        # The labels map can contain no more than 64 entries.  Entries of the labels
-        # map are UTF8 strings that comply with the following restrictions:
-        #
-        # * Keys must conform to regexp:  \p{Ll}\p{Lo}{0,62}
-        # * Values must conform to regexp:  [\p{Ll}\p{Lo}\p{N}_-]{0,63}
-        # * Both keys and values are additionally constrained to be &lt;= 128 bytes in
-        # size.
-      &quot;a_key&quot;: &quot;A String&quot;,
-    },
+    &quot;type&quot;: &quot;A String&quot;, # The type of Cloud Dataflow job.
     &quot;createTime&quot;: &quot;A String&quot;, # The timestamp when the job was initially created. Immutable and set by the
         # Cloud Dataflow service.
+    &quot;tempFiles&quot;: [ # A set of files the system should be aware of that are used
+        # for temporary storage. These temporary files will be
+        # removed on job completion.
+        # No duplicates are allowed.
+        # No file patterns are supported.
+        # 
+        # The supported files are:
+        # 
+        # Google Cloud Storage:
+        # 
+        #    storage.googleapis.com/{bucket}/{object}
+        #    bucket.storage.googleapis.com/{object}
+      &quot;A String&quot;,
+    ],
+    &quot;id&quot;: &quot;A String&quot;, # The unique ID of this job.
+        # 
+        # This field is set by the Cloud Dataflow service when the Job is
+        # created, and is immutable for the life of the job.
     &quot;requestedState&quot;: &quot;A String&quot;, # The job&#x27;s requested state.
-        #
+        # 
         # `UpdateJob` may be used to switch between the `JOB_STATE_STOPPED` and
         # `JOB_STATE_RUNNING` states, by setting requested_state.  `UpdateJob` may
         # also be used to directly set a job&#x27;s requested state to
         # `JOB_STATE_CANCELLED` or `JOB_STATE_DONE`, irrevocably terminating the
         # job if it has not already reached a terminal state.
-  }</pre>
+    &quot;replaceJobId&quot;: &quot;A String&quot;, # If this job is an update of an existing job, this field is the job ID
+        # of the job it replaced.
+        # 
+        # When sending a `CreateJobRequest`, you can update a job by specifying it
+        # here. The job named here is stopped, and its intermediate state is
+        # transferred to this job.
+    &quot;createdFromSnapshotId&quot;: &quot;A String&quot;, # If this is specified, the job&#x27;s initial state is populated from the given
+        # snapshot.
+    &quot;currentState&quot;: &quot;A String&quot;, # The current state of the job.
+        # 
+        # Jobs are created in the `JOB_STATE_STOPPED` state unless otherwise
+        # specified.
+        # 
+        # A job in the `JOB_STATE_RUNNING` state may asynchronously enter a
+        # terminal state. After a job has reached a terminal state, no
+        # further state updates may be made.
+        # 
+        # This field may be mutated by the Cloud Dataflow service;
+        # callers cannot mutate it.
+    &quot;name&quot;: &quot;A String&quot;, # The user-specified Cloud Dataflow job name.
+        # 
+        # Only one Job with a given name may exist in a project at any
+        # given time. If a caller attempts to create a Job with the same
+        # name as an already-existing Job, the attempt returns the
+        # existing Job.
+        # 
+        # The name must match the regular expression
+        # `[a-z]([-a-z0-9]{0,38}[a-z0-9])?`
+    &quot;currentStateTime&quot;: &quot;A String&quot;, # The timestamp associated with the current state.
+  }
+
+  location: string, The [regional endpoint]
+(https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that
+contains this job.
+  x__xgafv: string, V1 error format.
+    Allowed values
+      1 - v1 error format
+      2 - v2 error format
+
+Returns:
+  An object of the form:
+
+    { # Defines a job to be run by the Cloud Dataflow service.
+      &quot;pipelineDescription&quot;: { # A descriptive representation of submitted pipeline as well as the executed # Preliminary field: The format of this data may change at any time.
+          # A description of the user pipeline and stages through which it is executed.
+          # Created by Cloud Dataflow service.  Only retrieved with
+          # JOB_VIEW_DESCRIPTION or JOB_VIEW_ALL.
+          # form.  This data is provided by the Dataflow service for ease of visualizing
+          # the pipeline and interpreting Dataflow provided metrics.
+        &quot;displayData&quot;: [ # Pipeline level display data.
+          { # Data provided with a pipeline or transform to provide descriptive info.
+            &quot;url&quot;: &quot;A String&quot;, # An optional full URL.
+            &quot;javaClassValue&quot;: &quot;A String&quot;, # Contains value if the data is of java class type.
+            &quot;timestampValue&quot;: &quot;A String&quot;, # Contains value if the data is of timestamp type.
+            &quot;durationValue&quot;: &quot;A String&quot;, # Contains value if the data is of duration type.
+            &quot;label&quot;: &quot;A String&quot;, # An optional label to display in a dax UI for the element.
+            &quot;key&quot;: &quot;A String&quot;, # The key identifying the display data.
+                # This is intended to be used as a label for the display data
+                # when viewed in a dax monitoring system.
+            &quot;namespace&quot;: &quot;A String&quot;, # The namespace for the key. This is usually a class name or programming
+                # language namespace (i.e. python module) which defines the display data.
+                # This allows a dax monitoring system to specially handle the data
+                # and perform custom rendering.
+            &quot;floatValue&quot;: 3.14, # Contains value if the data is of float type.
+            &quot;strValue&quot;: &quot;A String&quot;, # Contains value if the data is of string type.
+            &quot;int64Value&quot;: &quot;A String&quot;, # Contains value if the data is of int64 type.
+            &quot;boolValue&quot;: True or False, # Contains value if the data is of a boolean type.
+            &quot;shortStrValue&quot;: &quot;A String&quot;, # A possible additional shorter value to display.
+                # For example a java_class_name_value of com.mypackage.MyDoFn
+                # will be stored with MyDoFn as the short_str_value and
+                # com.mypackage.MyDoFn as the java_class_name value.
+                # short_str_value can be displayed and java_class_name_value
+                # will be displayed as a tooltip.
+          },
+        ],
+        &quot;originalPipelineTransform&quot;: [ # Description of each transform in the pipeline and collections between them.
+          { # Description of the type, names/ids, and input/outputs for a transform.
+            &quot;outputCollectionName&quot;: [ # User  names for all collection outputs to this transform.
+              &quot;A String&quot;,
+            ],
+            &quot;displayData&quot;: [ # Transform-specific display data.
+              { # Data provided with a pipeline or transform to provide descriptive info.
+                &quot;url&quot;: &quot;A String&quot;, # An optional full URL.
+                &quot;javaClassValue&quot;: &quot;A String&quot;, # Contains value if the data is of java class type.
+                &quot;timestampValue&quot;: &quot;A String&quot;, # Contains value if the data is of timestamp type.
+                &quot;durationValue&quot;: &quot;A String&quot;, # Contains value if the data is of duration type.
+                &quot;label&quot;: &quot;A String&quot;, # An optional label to display in a dax UI for the element.
+                &quot;key&quot;: &quot;A String&quot;, # The key identifying the display data.
+                    # This is intended to be used as a label for the display data
+                    # when viewed in a dax monitoring system.
+                &quot;namespace&quot;: &quot;A String&quot;, # The namespace for the key. This is usually a class name or programming
+                    # language namespace (i.e. python module) which defines the display data.
+                    # This allows a dax monitoring system to specially handle the data
+                    # and perform custom rendering.
+                &quot;floatValue&quot;: 3.14, # Contains value if the data is of float type.
+                &quot;strValue&quot;: &quot;A String&quot;, # Contains value if the data is of string type.
+                &quot;int64Value&quot;: &quot;A String&quot;, # Contains value if the data is of int64 type.
+                &quot;boolValue&quot;: True or False, # Contains value if the data is of a boolean type.
+                &quot;shortStrValue&quot;: &quot;A String&quot;, # A possible additional shorter value to display.
+                    # For example a java_class_name_value of com.mypackage.MyDoFn
+                    # will be stored with MyDoFn as the short_str_value and
+                    # com.mypackage.MyDoFn as the java_class_name value.
+                    # short_str_value can be displayed and java_class_name_value
+                    # will be displayed as a tooltip.
+              },
+            ],
+            &quot;id&quot;: &quot;A String&quot;, # SDK generated id of this transform instance.
+            &quot;inputCollectionName&quot;: [ # User names for all collection inputs to this transform.
+              &quot;A String&quot;,
+            ],
+            &quot;name&quot;: &quot;A String&quot;, # User provided name for this transform instance.
+            &quot;kind&quot;: &quot;A String&quot;, # Type of transform.
+          },
+        ],
+        &quot;executionPipelineStage&quot;: [ # Description of each stage of execution of the pipeline.
+          { # Description of the composing transforms, names/ids, and input/outputs of a
+              # stage of execution.  Some composing transforms and sources may have been
+              # generated by the Dataflow service during execution planning.
+            &quot;componentSource&quot;: [ # Collections produced and consumed by component transforms of this stage.
+              { # Description of an interstitial value between transforms in an execution
+                  # stage.
+                &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this transform; may be user or system generated.
+                &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
+                &quot;originalTransformOrCollection&quot;: &quot;A String&quot;, # User name for the original user transform or collection with which this
+                    # source is most closely associated.
+              },
+            ],
+            &quot;inputSource&quot;: [ # Input sources for this stage.
+              { # Description of an input or output of an execution stage.
+                &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this source; may be user or system generated.
+                &quot;originalTransformOrCollection&quot;: &quot;A String&quot;, # User name for the original user transform or collection with which this
+                    # source is most closely associated.
+                &quot;sizeBytes&quot;: &quot;A String&quot;, # Size of the source, if measurable.
+                &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
+              },
+            ],
+            &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this stage.
+            &quot;componentTransform&quot;: [ # Transforms that comprise this execution stage.
+              { # Description of a transform executed as part of an execution stage.
+                &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
+                &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this transform; may be user or system generated.
+                &quot;originalTransform&quot;: &quot;A String&quot;, # User name for the original user transform with which this transform is
+                    # most closely associated.
+              },
+            ],
+            &quot;id&quot;: &quot;A String&quot;, # Dataflow service generated id for this stage.
+            &quot;outputSource&quot;: [ # Output sources for this stage.
+              { # Description of an input or output of an execution stage.
+                &quot;userName&quot;: &quot;A String&quot;, # Human-readable name for this source; may be user or system generated.
+                &quot;originalTransformOrCollection&quot;: &quot;A String&quot;, # User name for the original user transform or collection with which this
+                    # source is most closely associated.
+                &quot;sizeBytes&quot;: &quot;A String&quot;, # Size of the source, if measurable.
+                &quot;name&quot;: &quot;A String&quot;, # Dataflow service generated name for this source.
+              },
+            ],
+            &quot;kind&quot;: &quot;A String&quot;, # Type of tranform this stage is executing.
+          },
+        ],
+      },
+      &quot;labels&quot;: { # User-defined labels for this job.
+          #
+          # The labels map can contain no more than 64 entries.  Entries of the labels
+          # map are UTF8 strings that comply with the following restrictions:
+          #
+          # * Keys must conform to regexp:  \p{Ll}\p{Lo}{0,62}
+          # * Values must conform to regexp:  [\p{Ll}\p{Lo}\p{N}_-]{0,63}
+          # * Both keys and values are additionally constrained to be &lt;= 128 bytes in
+          # size.
+        &quot;a_key&quot;: &quot;A String&quot;,
+      },
+      &quot;projectId&quot;: &quot;A String&quot;, # The ID of the Cloud Platform project that the job belongs to.
+      &quot;environment&quot;: { # Describes the environment in which a Dataflow Job runs. # The environment for the job.
+        &quot;flexResourceSchedulingGoal&quot;: &quot;A String&quot;, # Which Flexible Resource Scheduling mode to run in.
+        &quot;workerRegion&quot;: &quot;A String&quot;, # The Compute Engine region
+            # (https://cloud.google.com/compute/docs/regions-zones/regions-zones) in
+            # which worker processing should occur, e.g. &quot;us-west1&quot;. Mutually exclusive
+            # with worker_zone. If neither worker_region nor worker_zone is specified,
+            # default to the control plane&#x27;s region.
+        &quot;userAgent&quot;: { # A description of the process that generated the request.
+          &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
+        },
+        &quot;serviceAccountEmail&quot;: &quot;A String&quot;, # Identity to run virtual machines as. Defaults to the default account.
+        &quot;version&quot;: { # A structure describing which components and their versions of the service
+            # are required in order to run the job.
+          &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
+        },
+        &quot;serviceKmsKeyName&quot;: &quot;A String&quot;, # If set, contains the Cloud KMS key identifier used to encrypt data
+            # at rest, AKA a Customer Managed Encryption Key (CMEK).
+            #
+            # Format:
+            #   projects/PROJECT_ID/locations/LOCATION/keyRings/KEY_RING/cryptoKeys/KEY
+        &quot;experiments&quot;: [ # The list of experiments to enable.
+          &quot;A String&quot;,
+        ],
+        &quot;workerZone&quot;: &quot;A String&quot;, # The Compute Engine zone
+            # (https://cloud.google.com/compute/docs/regions-zones/regions-zones) in
+            # which worker processing should occur, e.g. &quot;us-west1-a&quot;. Mutually exclusive
+            # with worker_region. If neither worker_region nor worker_zone is specified,
+            # a zone in the control plane&#x27;s region is chosen based on available capacity.
+        &quot;workerPools&quot;: [ # The worker pools. At least one &quot;harness&quot; worker pool must be
+            # specified in order for the job to have workers.
+          { # Describes one particular pool of Cloud Dataflow workers to be
+              # instantiated by the Cloud Dataflow service in order to perform the
+              # computations required by a job.  Note that a workflow job may use
+              # multiple pools, in order to match the various computational
+              # requirements of the various stages of the job.
+            &quot;onHostMaintenance&quot;: &quot;A String&quot;, # The action to take on host maintenance, as defined by the Google
+                # Compute Engine API.
+            &quot;sdkHarnessContainerImages&quot;: [ # Set of SDK harness containers needed to execute this pipeline. This will
+                # only be set in the Fn API path. For non-cross-language pipelines this
+                # should have only one entry. Cross-language pipelines will have two or more
+                # entries.
+              { # Defines a SDK harness container for executing Dataflow pipelines.
+                &quot;containerImage&quot;: &quot;A String&quot;, # A docker container image that resides in Google Container Registry.
+                &quot;useSingleCorePerContainer&quot;: True or False, # If true, recommends the Dataflow service to use only one core per SDK
+                    # container instance with this image. If false (or unset) recommends using
+                    # more than one core per SDK container instance with this image for
+                    # efficiency. Note that Dataflow service may choose to override this property
+                    # if needed.
+              },
+            ],
+            &quot;zone&quot;: &quot;A String&quot;, # Zone to run the worker pools in.  If empty or unspecified, the service
+                # will attempt to choose a reasonable default.
+            &quot;kind&quot;: &quot;A String&quot;, # The kind of the worker pool; currently only `harness` and `shuffle`
+                # are supported.
+            &quot;metadata&quot;: { # Metadata to set on the Google Compute Engine VMs.
+              &quot;a_key&quot;: &quot;A String&quot;,
+            },
+            &quot;diskSourceImage&quot;: &quot;A String&quot;, # Fully qualified source image for disks.
+            &quot;dataDisks&quot;: [ # Data disks that are used by a VM in this workflow.
+              { # Describes the data disk used by a workflow job.
+                &quot;sizeGb&quot;: 42, # Size of disk in GB.  If zero or unspecified, the service will
+                    # attempt to choose a reasonable default.
+                &quot;diskType&quot;: &quot;A String&quot;, # Disk storage type, as defined by Google Compute Engine.  This
+                    # must be a disk type appropriate to the project and zone in which
+                    # the workers will run.  If unknown or unspecified, the service
+                    # will attempt to choose a reasonable default.
+                    #
+                    # For example, the standard persistent disk type is a resource name
+                    # typically ending in &quot;pd-standard&quot;.  If SSD persistent disks are
+                    # available, the resource name typically ends with &quot;pd-ssd&quot;.  The
+                    # actual valid values are defined the Google Compute Engine API,
+                    # not by the Cloud Dataflow API; consult the Google Compute Engine
+                    # documentation for more information about determining the set of
+                    # available disk types for a particular project and zone.
+                    #
+                    # Google Compute Engine Disk types are local to a particular
+                    # project in a particular zone, and so the resource name will
+                    # typically look something like this:
+                    #
+                    # compute.googleapis.com/projects/project-id/zones/zone/diskTypes/pd-standard
+                &quot;mountPoint&quot;: &quot;A String&quot;, # Directory in a VM where disk is mounted.
+              },
+            ],
+            &quot;packages&quot;: [ # Packages to be installed on workers.
+              { # The packages that must be installed in order for a worker to run the
+                  # steps of the Cloud Dataflow job that will be assigned to its worker
+                  # pool.
+                  #
+                  # This is the mechanism by which the Cloud Dataflow SDK causes code to
+                  # be loaded onto the workers. For example, the Cloud Dataflow Java SDK
+                  # might use this to install jars containing the user&#x27;s code and all of the
+                  # various dependencies (libraries, data files, etc.) required in order
+                  # for that code to run.
+                &quot;name&quot;: &quot;A String&quot;, # The name of the package.
+                &quot;location&quot;: &quot;A String&quot;, # The resource to read the package from. The supported resource type is:
+                    #
+                    # Google Cloud Storage:
+                    #
+                    #   storage.googleapis.com/{bucket}
+                    #   bucket.storage.googleapis.com/
+              },
+            ],
+            &quot;teardownPolicy&quot;: &quot;A String&quot;, # Sets the policy for determining when to turndown worker pool.
+                # Allowed values are: `TEARDOWN_ALWAYS`, `TEARDOWN_ON_SUCCESS`, and
+                # `TEARDOWN_NEVER`.
+                # `TEARDOWN_ALWAYS` means workers are always torn down regardless of whether
+                # the job succeeds. `TEARDOWN_ON_SUCCESS` means workers are torn down
+                # if the job succeeds. `TEARDOWN_NEVER` means the workers are never torn
+                # down.
+                #
+                # If the workers are not torn down by the service, they will
+                # continue to run and use Google Compute Engine VM resources in the
+                # user&#x27;s project until they are explicitly terminated by the user.
+                # Because of this, Google recommends using the `TEARDOWN_ALWAYS`
+                # policy except for small, manually supervised test jobs.
+                #
+                # If unknown or unspecified, the service will attempt to choose a reasonable
+                # default.
+            &quot;network&quot;: &quot;A String&quot;, # Network to which VMs will be assigned.  If empty or unspecified,
+                # the service will use the network &quot;default&quot;.
+            &quot;ipConfiguration&quot;: &quot;A String&quot;, # Configuration for VM IPs.
+            &quot;diskSizeGb&quot;: 42, # Size of root disk for VMs, in GB.  If zero or unspecified, the service will
+                # attempt to choose a reasonable default.
+            &quot;autoscalingSettings&quot;: { # Settings for WorkerPool autoscaling. # Settings for autoscaling of this WorkerPool.
+              &quot;maxNumWorkers&quot;: 42, # The maximum number of workers to cap scaling at.
+              &quot;algorithm&quot;: &quot;A String&quot;, # The algorithm to use for autoscaling.
+            },
+            &quot;poolArgs&quot;: { # Extra arguments for this worker pool.
+              &quot;a_key&quot;: &quot;&quot;, # Properties of the object. Contains field @type with type URL.
+            },
+            &quot;subnetwork&quot;: &quot;A String&quot;, # Subnetwork to which VMs will be assigned, if desired.  Expected to be of
+                # the form &quot;regions/REGION/subnetworks/SUBNETWORK&quot;.
+            &quot;numWorkers&quot;: 42, # Number of Google Compute Engine workers in this pool needed to
+                # execute the job.  If zero or unspecified, the service will
+                # attempt to choose a reasonable default.
+            &quot;numThreadsPerWorker&quot;: 42, # The number of threads per worker harness. If empty or unspecified, the
+                # service will choose a number of threads (according to the number of cores
+                # on the selected machine type for batch, or 1 by convention for streaming).
+            &quot;workerHarnessContainerImage&quot;: &quot;A String&quot;, # Required. Docker container image that executes the Cloud Dataflow worker
+                # harness, residing in Google Container Registry.
+                #
+                # Deprecated for the Fn API path. Use sdk_harness_container_images instead.
+            &quot;taskrunnerSettings&quot;: { # Taskrunner configuration settings. # Settings passed through to Google Compute Engine workers when
+                # using the standard Dataflow task runner.  Users should ignore
+                # this field.
+              &quot;dataflowApiVersion&quot;: &quot;A String&quot;, # The API version of endpoint, e.g. &quot;v1b3&quot;
+              &quot;oauthScopes&quot;: [ # The OAuth2 scopes to be requested by the taskrunner in order to
+                  # access the Cloud Dataflow API.
+                &quot;A String&quot;,
+              ],
+              &quot;baseUrl&quot;: &quot;A String&quot;, # The base URL for the taskrunner to use when accessing Google Cloud APIs.
+                  #
+                  # When workers access Google Cloud APIs, they logically do so via
+                  # relative URLs.  If this field is specified, it supplies the base
+                  # URL to use for resolving these relative URLs.  The normative
+                  # algorithm used is defined by RFC 1808, &quot;Relative Uniform Resource
+                  # Locators&quot;.
+                  #
+                  # If not specified, the default value is &quot;http://www.googleapis.com/&quot;
+              &quot;workflowFileName&quot;: &quot;A String&quot;, # The file to store the workflow in.
+              &quot;logToSerialconsole&quot;: True or False, # Whether to send taskrunner log info to Google Compute Engine VM serial
+                  # console.
+              &quot;baseTaskDir&quot;: &quot;A String&quot;, # The location on the worker for task-specific subdirectories.
+              &quot;taskUser&quot;: &quot;A String&quot;, # The UNIX user ID on the worker VM to use for tasks launched by
+                  # taskrunner; e.g. &quot;root&quot;.
+              &quot;vmId&quot;: &quot;A String&quot;, # The ID string of the VM.
+              &quot;alsologtostderr&quot;: True or False, # Whether to also send taskrunner log info to stderr.
+              &quot;parallelWorkerSettings&quot;: { # Provides data to pass through to the worker harness. # The settings to pass to the parallel worker harness.
+                &quot;shuffleServicePath&quot;: &quot;A String&quot;, # The Shuffle service path relative to the root URL, for example,
+                    # &quot;shuffle/v1beta1&quot;.
+                &quot;tempStoragePrefix&quot;: &quot;A String&quot;, # The prefix of the resources the system should use for temporary
+                    # storage.
+                    #
+                    # The supported resource type is:
+                    #
+                    # Google Cloud Storage:
+                    #
+                    #   storage.googleapis.com/{bucket}/{object}
+                    #   bucket.storage.googleapis.com/{object}
+                &quot;reportingEnabled&quot;: True or False, # Whether to send work progress updates to the service.
+                &quot;servicePath&quot;: &quot;A String&quot;, # The Cloud Dataflow service path relative to the root URL, for example,
+                    # &quot;dataflow/v1b3/projects&quot;.
+                &quot;baseUrl&quot;: &quot;A String&quot;, # The base URL for accessing Google Cloud APIs.
+                    #
+                    # When workers access Google Cloud APIs, they logically do so via
+                    # relative URLs.  If this field is specified, it supplies the base
+                    # URL to use for resolving these relative URLs.  The normative
+                    # algorithm used is defined by RFC 1808, &quot;Relative Uniform Resource
+                    # Locators&quot;.
+                    #
+                    # If not specified, the default value is &quot;http://www.googleapis.com/&quot;
+                &quot;workerId&quot;: &quot;A String&quot;, # The ID of the worker running this pipeline.
+              },
+              &quot;harnessCommand&quot;: &quot;A String&quot;, # The command to launch the worker harness.
+              &quot;logDir&quot;: &quot;A String&quot;, # The directory on the VM to store logs.
+              &quot;streamingWorkerMainClass&quot;: &quot;A String&quot;, # The streaming worker main class name.
+              &quot;languageHint&quot;: &quot;A String&quot;, # The suggested backend language.
+              &quot;taskGroup&quot;: &quot;A String&quot;, # The UNIX group ID on the worker VM to use for tasks launched by
+                  # taskrunner; e.g. &quot;wheel&quot;.
+              &quot;logUploadLocation&quot;: &quot;A String&quot;, # Indicates where to put logs.  If this is not specified, the logs
+                  # will not be uploaded.
+                  #
+                  # The supported resource type is:
+                  #
+                  # Google Cloud Storage:
+                  #   storage.googleapis.com/{bucket}/{object}
+                  #   bucket.storage.googleapis.com/{object}
+              &quot;commandlinesFileName&quot;: &quot;A String&quot;, # The file to store preprocessing commands in.
+              &quot;continueOnException&quot;: True or False, # Whether to continue taskrunner if an exception is hit.
+              &quot;tempStoragePrefix&quot;: &quot;A String&quot;, # The prefix of the resources the taskrunner should use for
+                  # temporary storage.
+                  #
+                  # The supported resource type is:
+                  #
+                  # Google Cloud Storage:
+                  #   storage.googleapis.com/{bucket}/{object}
+                  #   bucket.storage.googleapis.com/{object}
+            },
+            &quot;diskType&quot;: &quot;A String&quot;, # Type of root disk for VMs.  If empty or unspecified, the service will
+                # attempt to choose a reasonable default.
+            &quot;defaultPackageSet&quot;: &quot;A String&quot;, # The default package set to install.  This allows the service to
+                # select a default set of packages which are useful to worker
+                # harnesses written in a particular language.
+            &quot;machineType&quot;: &quot;A String&quot;, # Machine type (e.g. &quot;n1-standard-1&quot;).  If empty or unspecified, the
+                # service will attempt to choose a reasonable default.
+          },
+        ],
+        &quot;tempStoragePrefix&quot;: &quot;A String&quot;, # The prefix of the resources the system should use for temporary
+            # storage.  The system will append the suffix &quot;/temp-{JOBNAME} to
+            # this resource prefix, where {JOBNAME} is the value of the
+            # job_name field.  The resulting bucket and object prefix is used
+            # as the prefix of the resources used to store temporary data
+            # needed during the job execution.  NOTE: This will override the
+            # value in taskrunner_settings.
+            # The supported resource type is:
+            #
+            # Google Cloud Storage:
+            #
+            #   storage.googleapis.com/{bucket}/{object}
+            #   bucket.storage.googleapis.com/{object}
+        &quot;internalExperiments&quot;: { # Experimental settings.
+          &quot;a_key&quot;: &quot;&quot;, # Properties of the object. Contains field @type with type URL.
+        },
+        &quot;sdkPipelineOptions&quot;: { # The Cloud Dataflow SDK pipeline options specified by the user. These
+            # options are passed through the service and are used to recreate the
+            # SDK pipeline options on the worker in a language agnostic and platform
+            # independent way.
+          &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
+        },
+        &quot;dataset&quot;: &quot;A String&quot;, # The dataset for the current project where various workflow
+            # related tables are stored.
+            #
+            # The supported resource type is:
+            #
+            # Google BigQuery:
+            #   bigquery.googleapis.com/{dataset}
+        &quot;clusterManagerApiService&quot;: &quot;A String&quot;, # The type of cluster manager API to use.  If unknown or
+            # unspecified, the service will attempt to choose a reasonable
+            # default.  This should be in the form of the API service name,
+            # e.g. &quot;compute.googleapis.com&quot;.
+      },
+      &quot;stepsLocation&quot;: &quot;A String&quot;, # The GCS location where the steps are stored.
+      &quot;steps&quot;: [ # Exactly one of step or steps_location should be specified.
+          #
+          # The top-level steps that constitute the entire job.
+        { # Defines a particular step within a Cloud Dataflow job.
+            #
+            # A job consists of multiple steps, each of which performs some
+            # specific operation as part of the overall job.  Data is typically
+            # passed from one step to another as part of the job.
+            #
+            # Here&#x27;s an example of a sequence of steps which together implement a
+            # Map-Reduce job:
+            #
+            #   * Read a collection of data from some source, parsing the
+            #     collection&#x27;s elements.
+            #
+            #   * Validate the elements.
+            #
+            #   * Apply a user-defined function to map each element to some value
+            #     and extract an element-specific key value.
+            #
+            #   * Group elements with the same key into a single element with
+            #     that key, transforming a multiply-keyed collection into a
+            #     uniquely-keyed collection.
+            #
+            #   * Write the elements out to some data sink.
+            #
+            # Note that the Cloud Dataflow service may be used to run many different
+            # types of jobs, not just Map-Reduce.
+          &quot;kind&quot;: &quot;A String&quot;, # The kind of step in the Cloud Dataflow job.
+          &quot;properties&quot;: { # Named properties associated with the step. Each kind of
+              # predefined step has its own required set of properties.
+              # Must be provided on Create.  Only retrieved with JOB_VIEW_ALL.
+            &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
+          },
+          &quot;name&quot;: &quot;A String&quot;, # The name that identifies the step. This must be unique for each
+              # step with respect to all other steps in the Cloud Dataflow job.
+        },
+      ],
+      &quot;stageStates&quot;: [ # This field may be mutated by the Cloud Dataflow service;
+          # callers cannot mutate it.
+        { # A message describing the state of a particular execution stage.
+          &quot;executionStageState&quot;: &quot;A String&quot;, # Executions stage states allow the same set of values as JobState.
+          &quot;executionStageName&quot;: &quot;A String&quot;, # The name of the execution stage.
+          &quot;currentStateTime&quot;: &quot;A String&quot;, # The time at which the stage transitioned to this state.
+        },
+      ],
+      &quot;replacedByJobId&quot;: &quot;A String&quot;, # If another job is an update of this job (and thus, this job is in
+          # `JOB_STATE_UPDATED`), this field contains the ID of that job.
+      &quot;jobMetadata&quot;: { # Metadata available primarily for filtering jobs. Will be included in the # This field is populated by the Dataflow service to support filtering jobs
+          # by the metadata values provided here. Populated for ListJobs and all GetJob
+          # views SUMMARY and higher.
+          # ListJob response and Job SUMMARY view.
+        &quot;sdkVersion&quot;: { # The version of the SDK used to run the job. # The SDK version used to run the job.
+          &quot;sdkSupportStatus&quot;: &quot;A String&quot;, # The support status for this SDK version.
+          &quot;versionDisplayName&quot;: &quot;A String&quot;, # A readable string describing the version of the SDK.
+          &quot;version&quot;: &quot;A String&quot;, # The version of the SDK used to run the job.
+        },
+        &quot;bigTableDetails&quot;: [ # Identification of a BigTable source used in the Dataflow job.
+          { # Metadata for a BigTable connector used by the job.
+            &quot;instanceId&quot;: &quot;A String&quot;, # InstanceId accessed in the connection.
+            &quot;tableId&quot;: &quot;A String&quot;, # TableId accessed in the connection.
+            &quot;projectId&quot;: &quot;A String&quot;, # ProjectId accessed in the connection.
+          },
+        ],
+        &quot;pubsubDetails&quot;: [ # Identification of a PubSub source used in the Dataflow job.
+          { # Metadata for a PubSub connector used by the job.
+            &quot;subscription&quot;: &quot;A String&quot;, # Subscription used in the connection.
+            &quot;topic&quot;: &quot;A String&quot;, # Topic accessed in the connection.
+          },
+        ],
+        &quot;bigqueryDetails&quot;: [ # Identification of a BigQuery source used in the Dataflow job.
+          { # Metadata for a BigQuery connector used by the job.
+            &quot;dataset&quot;: &quot;A String&quot;, # Dataset accessed in the connection.
+            &quot;projectId&quot;: &quot;A String&quot;, # Project accessed in the connection.
+            &quot;query&quot;: &quot;A String&quot;, # Query used to access data in the connection.
+            &quot;table&quot;: &quot;A String&quot;, # Table accessed in the connection.
+          },
+        ],
+        &quot;fileDetails&quot;: [ # Identification of a File source used in the Dataflow job.
+          { # Metadata for a File connector used by the job.
+            &quot;filePattern&quot;: &quot;A String&quot;, # File Pattern used to access files by the connector.
+          },
+        ],
+        &quot;datastoreDetails&quot;: [ # Identification of a Datastore source used in the Dataflow job.
+          { # Metadata for a Datastore connector used by the job.
+            &quot;namespace&quot;: &quot;A String&quot;, # Namespace used in the connection.
+            &quot;projectId&quot;: &quot;A String&quot;, # ProjectId accessed in the connection.
+          },
+        ],
+        &quot;spannerDetails&quot;: [ # Identification of a Spanner source used in the Dataflow job.
+          { # Metadata for a Spanner connector used by the job.
+            &quot;instanceId&quot;: &quot;A String&quot;, # InstanceId accessed in the connection.
+            &quot;databaseId&quot;: &quot;A String&quot;, # DatabaseId accessed in the connection.
+            &quot;projectId&quot;: &quot;A String&quot;, # ProjectId accessed in the connection.
+          },
+        ],
+      },
+      &quot;location&quot;: &quot;A String&quot;, # The [regional endpoint]
+          # (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that
+          # contains this job.
+      &quot;transformNameMapping&quot;: { # The map of transform name prefixes of the job to be replaced to the
+          # corresponding name prefixes of the new job.
+        &quot;a_key&quot;: &quot;A String&quot;,
+      },
+      &quot;startTime&quot;: &quot;A String&quot;, # The timestamp when the job was started (transitioned to JOB_STATE_PENDING).
+          # Flexible resource scheduling jobs are started with some delay after job
+          # creation, so start_time is unset before start and is updated when the
+          # job is started by the Cloud Dataflow service. For other jobs, start_time
+          # always equals to create_time and is immutable and set by the Cloud Dataflow
+          # service.
+      &quot;clientRequestId&quot;: &quot;A String&quot;, # The client&#x27;s unique identifier of the job, re-used across retried attempts.
+          # If this field is set, the service will ensure its uniqueness.
+          # The request to create a job will fail if the service has knowledge of a
+          # previously submitted job with the same client&#x27;s ID and job name.
+          # The caller may use this field to ensure idempotence of job
+          # creation across retried attempts to create a job.
+          # By default, the field is empty and, in that case, the service ignores it.
+      &quot;executionInfo&quot;: { # Additional information about how a Cloud Dataflow job will be executed that # Deprecated.
+          # isn&#x27;t contained in the submitted job.
+        &quot;stages&quot;: { # A mapping from each stage to the information about that stage.
+          &quot;a_key&quot;: { # Contains information about how a particular
+              # google.dataflow.v1beta3.Step will be executed.
+            &quot;stepName&quot;: [ # The steps associated with the execution stage.
+                # Note that stages may have several steps, and that a given step
+                # might be run by more than one stage.
+              &quot;A String&quot;,
+            ],
+          },
+        },
+      },
+      &quot;type&quot;: &quot;A String&quot;, # The type of Cloud Dataflow job.
+      &quot;createTime&quot;: &quot;A String&quot;, # The timestamp when the job was initially created. Immutable and set by the
+          # Cloud Dataflow service.
+      &quot;tempFiles&quot;: [ # A set of files the system should be aware of that are used
+          # for temporary storage. These temporary files will be
+          # removed on job completion.
+          # No duplicates are allowed.
+          # No file patterns are supported.
+          #
+          # The supported files are:
+          #
+          # Google Cloud Storage:
+          #
+          #    storage.googleapis.com/{bucket}/{object}
+          #    bucket.storage.googleapis.com/{object}
+        &quot;A String&quot;,
+      ],
+      &quot;id&quot;: &quot;A String&quot;, # The unique ID of this job.
+          #
+          # This field is set by the Cloud Dataflow service when the Job is
+          # created, and is immutable for the life of the job.
+      &quot;requestedState&quot;: &quot;A String&quot;, # The job&#x27;s requested state.
+          #
+          # `UpdateJob` may be used to switch between the `JOB_STATE_STOPPED` and
+          # `JOB_STATE_RUNNING` states, by setting requested_state.  `UpdateJob` may
+          # also be used to directly set a job&#x27;s requested state to
+          # `JOB_STATE_CANCELLED` or `JOB_STATE_DONE`, irrevocably terminating the
+          # job if it has not already reached a terminal state.
+      &quot;replaceJobId&quot;: &quot;A String&quot;, # If this job is an update of an existing job, this field is the job ID
+          # of the job it replaced.
+          #
+          # When sending a `CreateJobRequest`, you can update a job by specifying it
+          # here. The job named here is stopped, and its intermediate state is
+          # transferred to this job.
+      &quot;createdFromSnapshotId&quot;: &quot;A String&quot;, # If this is specified, the job&#x27;s initial state is populated from the given
+          # snapshot.
+      &quot;currentState&quot;: &quot;A String&quot;, # The current state of the job.
+          #
+          # Jobs are created in the `JOB_STATE_STOPPED` state unless otherwise
+          # specified.
+          #
+          # A job in the `JOB_STATE_RUNNING` state may asynchronously enter a
+          # terminal state. After a job has reached a terminal state, no
+          # further state updates may be made.
+          #
+          # This field may be mutated by the Cloud Dataflow service;
+          # callers cannot mutate it.
+      &quot;name&quot;: &quot;A String&quot;, # The user-specified Cloud Dataflow job name.
+          #
+          # Only one Job with a given name may exist in a project at any
+          # given time. If a caller attempts to create a Job with the same
+          # name as an already-existing Job, the attempt returns the
+          # existing Job.
+          #
+          # The name must match the regular expression
+          # `[a-z]([-a-z0-9]{0,38}[a-z0-9])?`
+      &quot;currentStateTime&quot;: &quot;A String&quot;, # The timestamp associated with the current state.
+    }</pre>
 </div>
 
 </body></html>
\ No newline at end of file