Clean and regen docs (#401)

diff --git a/docs/dyn/ml_v1beta1.projects.models.html b/docs/dyn/ml_v1beta1.projects.models.html
index 0a36f05..ed302d3 100644
--- a/docs/dyn/ml_v1beta1.projects.models.html
+++ b/docs/dyn/ml_v1beta1.projects.models.html
@@ -136,40 +136,65 @@
         # prediction requests. A model can have multiple versions. You can get
         # information about all of the versions of a given model by calling
         # [projects.models.versions.list](/ml-engine/reference/rest/v1beta1/projects.models.versions/list).
-      "name": "A String", # Required.The name specified for the version when it was created.
-          #
-          # The version name must be unique within the model it is created in.
+      "description": "A String", # Optional. The description specified for the version when it was created.
       "runtimeVersion": "A String", # Optional. The Google Cloud ML runtime version to use for this deployment.
           # If not set, Google Cloud ML will choose a version.
-      "manualScaling": { # Options for manually scaling a model. # Optional. Manually select the number of nodes to use for serving the
-          # model. If unset (i.e., by default), the number of nodes used to serve
-          # the model automatically scales with traffic. However, care should be
-          # taken to ramp up traffic according to the model's ability to scale. If
-          # your model needs to handle bursts of traffic beyond it's ability to
-          # scale, it is recommended you set this field appropriately.
+      "manualScaling": { # Options for manually scaling a model. # Manually select the number of nodes to use for serving the
+          # model. You should generally use `automatic_scaling` with an appropriate
+          # `min_nodes` instead, but this option is available if you want predictable
+          # billing. Beware that latency and error rates will increase if the
+          # traffic exceeds that capability of the system to serve it based on
+          # the selected number of nodes.
         "nodes": 42, # The number of nodes to allocate for this model. These nodes are always up,
             # starting from the time the model is deployed, so the cost of operating
-            # this model will be proportional to nodes * number of hours since
-            # deployment.
+            # this model will be proportional to `nodes` * number of hours since
+            # last billing cycle.
       },
-      "lastUseTime": "A String", # Output only. The time the version was last used for prediction.
       "deploymentUri": "A String", # Required. The Google Cloud Storage location of the trained model used to
           # create the version. See the
-          # [overview of model deployment](/ml-engine/docs/concepts/deployment-overview) for
-          # more informaiton.
+          # [overview of model
+          # deployment](/ml-engine/docs/concepts/deployment-overview) for more
+          # informaiton.
           #
           # When passing Version to
           # [projects.models.versions.create](/ml-engine/reference/rest/v1beta1/projects.models.versions/create)
           # the model service uses the specified location as the source of the model.
           # Once deployed, the model version is hosted by the prediction service, so
           # this location is useful only as a historical record.
+          # The total number of model files can't exceed 1000.
+      "lastUseTime": "A String", # Output only. The time the version was last used for prediction.
+      "automaticScaling": { # Options for automatically scaling a model. # Automatically scale the number of nodes used to serve the model in
+          # response to increases and decreases in traffic. Care should be
+          # taken to ramp up traffic according to the model's ability to scale
+          # or you will start seeing increases in latency and 429 response codes.
+        "minNodes": 42, # Optional. The minimum number of nodes to allocate for this model. These
+            # nodes are always up, starting from the time the model is deployed, so the
+            # cost of operating this model will be at least
+            # `rate` * `min_nodes` * number of hours since last billing cycle,
+            # where `rate` is the cost per node-hour as documented in
+            # [pricing](https://cloud.google.com/ml-engine/pricing#prediction_pricing),
+            # even if no predictions are performed. There is additional cost for each
+            # prediction performed.
+            #
+            # Unlike manual scaling, if the load gets too heavy for the nodes
+            # that are up, the service will automatically add nodes to handle the
+            # increased load as well as scale back as traffic drops, always maintaining
+            # at least `min_nodes`. You will be charged for the time in which additional
+            # nodes are used.
+            #
+            # If not specified, `min_nodes` defaults to 0, in which case, when traffic
+            # to a model stops (and after a cool-down period), nodes will be shut down
+            # and no charges will be incurred until traffic to the model resumes.
+      },
       "createTime": "A String", # Output only. The time the version was created.
       "isDefault": True or False, # Output only. If true, this version will be used to handle prediction
           # requests that do not specify a version.
           #
           # You can change the default version by calling
           # [projects.methods.versions.setDefault](/ml-engine/reference/rest/v1beta1/projects.models.versions/setDefault).
-      "description": "A String", # Optional. The description specified for the version when it was created.
+      "name": "A String", # Required.The name specified for the version when it was created.
+          #
+          # The version name must be unique within the model it is created in.
     },
     "name": "A String", # Required. The name specified for the model when it was created.
         # 
@@ -213,40 +238,65 @@
           # prediction requests. A model can have multiple versions. You can get
           # information about all of the versions of a given model by calling
           # [projects.models.versions.list](/ml-engine/reference/rest/v1beta1/projects.models.versions/list).
-        "name": "A String", # Required.The name specified for the version when it was created.
-            #
-            # The version name must be unique within the model it is created in.
+        "description": "A String", # Optional. The description specified for the version when it was created.
         "runtimeVersion": "A String", # Optional. The Google Cloud ML runtime version to use for this deployment.
             # If not set, Google Cloud ML will choose a version.
-        "manualScaling": { # Options for manually scaling a model. # Optional. Manually select the number of nodes to use for serving the
-            # model. If unset (i.e., by default), the number of nodes used to serve
-            # the model automatically scales with traffic. However, care should be
-            # taken to ramp up traffic according to the model's ability to scale. If
-            # your model needs to handle bursts of traffic beyond it's ability to
-            # scale, it is recommended you set this field appropriately.
+        "manualScaling": { # Options for manually scaling a model. # Manually select the number of nodes to use for serving the
+            # model. You should generally use `automatic_scaling` with an appropriate
+            # `min_nodes` instead, but this option is available if you want predictable
+            # billing. Beware that latency and error rates will increase if the
+            # traffic exceeds that capability of the system to serve it based on
+            # the selected number of nodes.
           "nodes": 42, # The number of nodes to allocate for this model. These nodes are always up,
               # starting from the time the model is deployed, so the cost of operating
-              # this model will be proportional to nodes * number of hours since
-              # deployment.
+              # this model will be proportional to `nodes` * number of hours since
+              # last billing cycle.
         },
-        "lastUseTime": "A String", # Output only. The time the version was last used for prediction.
         "deploymentUri": "A String", # Required. The Google Cloud Storage location of the trained model used to
             # create the version. See the
-            # [overview of model deployment](/ml-engine/docs/concepts/deployment-overview) for
-            # more informaiton.
+            # [overview of model
+            # deployment](/ml-engine/docs/concepts/deployment-overview) for more
+            # informaiton.
             #
             # When passing Version to
             # [projects.models.versions.create](/ml-engine/reference/rest/v1beta1/projects.models.versions/create)
             # the model service uses the specified location as the source of the model.
             # Once deployed, the model version is hosted by the prediction service, so
             # this location is useful only as a historical record.
+            # The total number of model files can't exceed 1000.
+        "lastUseTime": "A String", # Output only. The time the version was last used for prediction.
+        "automaticScaling": { # Options for automatically scaling a model. # Automatically scale the number of nodes used to serve the model in
+            # response to increases and decreases in traffic. Care should be
+            # taken to ramp up traffic according to the model's ability to scale
+            # or you will start seeing increases in latency and 429 response codes.
+          "minNodes": 42, # Optional. The minimum number of nodes to allocate for this model. These
+              # nodes are always up, starting from the time the model is deployed, so the
+              # cost of operating this model will be at least
+              # `rate` * `min_nodes` * number of hours since last billing cycle,
+              # where `rate` is the cost per node-hour as documented in
+              # [pricing](https://cloud.google.com/ml-engine/pricing#prediction_pricing),
+              # even if no predictions are performed. There is additional cost for each
+              # prediction performed.
+              #
+              # Unlike manual scaling, if the load gets too heavy for the nodes
+              # that are up, the service will automatically add nodes to handle the
+              # increased load as well as scale back as traffic drops, always maintaining
+              # at least `min_nodes`. You will be charged for the time in which additional
+              # nodes are used.
+              #
+              # If not specified, `min_nodes` defaults to 0, in which case, when traffic
+              # to a model stops (and after a cool-down period), nodes will be shut down
+              # and no charges will be incurred until traffic to the model resumes.
+        },
         "createTime": "A String", # Output only. The time the version was created.
         "isDefault": True or False, # Output only. If true, this version will be used to handle prediction
             # requests that do not specify a version.
             #
             # You can change the default version by calling
             # [projects.methods.versions.setDefault](/ml-engine/reference/rest/v1beta1/projects.models.versions/setDefault).
-        "description": "A String", # Optional. The description specified for the version when it was created.
+        "name": "A String", # Required.The name specified for the version when it was created.
+            #
+            # The version name must be unique within the model it is created in.
       },
       "name": "A String", # Required. The name specified for the model when it was created.
           #
@@ -285,22 +335,6 @@
         # long-running operation should document the metadata type, if any.
       "a_key": "", # Properties of the object. Contains field @type with type URL.
     },
-    "done": True or False, # If the value is `false`, it means the operation is still in progress.
-        # If true, the operation is completed, and either `error` or `response` is
-        # available.
-    "response": { # The normal response of the operation in case of success.  If the original
-        # method returns no data on success, such as `Delete`, the response is
-        # `google.protobuf.Empty`.  If the original method is standard
-        # `Get`/`Create`/`Update`, the response should be the resource.  For other
-        # methods, the response should have the type `XxxResponse`, where `Xxx`
-        # is the original method name.  For example, if the original method name
-        # is `TakeSnapshot()`, the inferred response type is
-        # `TakeSnapshotResponse`.
-      "a_key": "", # Properties of the object. Contains field @type with type URL.
-    },
-    "name": "A String", # The server-assigned name, which is only unique within the same service that
-        # originally returns it. If you use the default HTTP mapping, the
-        # `name` should have the format of `operations/some/unique/name`.
     "error": { # The `Status` type defines a logical error model that is suitable for different # The error result of the operation in case of failure or cancellation.
         # programming environments, including REST APIs and RPC APIs. It is used by
         # [gRPC](https://github.com/grpc). The error model is designed to be:
@@ -318,7 +352,7 @@
         # error message is needed, put the localized message in the error details or
         # localize it in the client. The optional error details may contain arbitrary
         # information about the error. There is a predefined set of error detail types
-        # in the package `google.rpc` which can be used for common error conditions.
+        # in the package `google.rpc` that can be used for common error conditions.
         #
         # # Language mapping
         #
@@ -341,7 +375,7 @@
         #     errors.
         #
         # - Workflow errors. A typical workflow has multiple steps. Each step may
-        #     have a `Status` message for error reporting purpose.
+        #     have a `Status` message for error reporting.
         #
         # - Batch operations. If a client uses batch request and batch response, the
         #     `Status` message should be used directly inside batch response, one for
@@ -364,6 +398,22 @@
         },
       ],
     },
+    "done": True or False, # If the value is `false`, it means the operation is still in progress.
+        # If true, the operation is completed, and either `error` or `response` is
+        # available.
+    "response": { # The normal response of the operation in case of success.  If the original
+        # method returns no data on success, such as `Delete`, the response is
+        # `google.protobuf.Empty`.  If the original method is standard
+        # `Get`/`Create`/`Update`, the response should be the resource.  For other
+        # methods, the response should have the type `XxxResponse`, where `Xxx`
+        # is the original method name.  For example, if the original method name
+        # is `TakeSnapshot()`, the inferred response type is
+        # `TakeSnapshotResponse`.
+      "a_key": "", # Properties of the object. Contains field @type with type URL.
+    },
+    "name": "A String", # The server-assigned name, which is only unique within the same service that
+        # originally returns it. If you use the default HTTP mapping, the
+        # `name` should have the format of `operations/some/unique/name`.
   }</pre>
 </div>
 
@@ -411,40 +461,65 @@
           # prediction requests. A model can have multiple versions. You can get
           # information about all of the versions of a given model by calling
           # [projects.models.versions.list](/ml-engine/reference/rest/v1beta1/projects.models.versions/list).
-        "name": "A String", # Required.The name specified for the version when it was created.
-            #
-            # The version name must be unique within the model it is created in.
+        "description": "A String", # Optional. The description specified for the version when it was created.
         "runtimeVersion": "A String", # Optional. The Google Cloud ML runtime version to use for this deployment.
             # If not set, Google Cloud ML will choose a version.
-        "manualScaling": { # Options for manually scaling a model. # Optional. Manually select the number of nodes to use for serving the
-            # model. If unset (i.e., by default), the number of nodes used to serve
-            # the model automatically scales with traffic. However, care should be
-            # taken to ramp up traffic according to the model's ability to scale. If
-            # your model needs to handle bursts of traffic beyond it's ability to
-            # scale, it is recommended you set this field appropriately.
+        "manualScaling": { # Options for manually scaling a model. # Manually select the number of nodes to use for serving the
+            # model. You should generally use `automatic_scaling` with an appropriate
+            # `min_nodes` instead, but this option is available if you want predictable
+            # billing. Beware that latency and error rates will increase if the
+            # traffic exceeds that capability of the system to serve it based on
+            # the selected number of nodes.
           "nodes": 42, # The number of nodes to allocate for this model. These nodes are always up,
               # starting from the time the model is deployed, so the cost of operating
-              # this model will be proportional to nodes * number of hours since
-              # deployment.
+              # this model will be proportional to `nodes` * number of hours since
+              # last billing cycle.
         },
-        "lastUseTime": "A String", # Output only. The time the version was last used for prediction.
         "deploymentUri": "A String", # Required. The Google Cloud Storage location of the trained model used to
             # create the version. See the
-            # [overview of model deployment](/ml-engine/docs/concepts/deployment-overview) for
-            # more informaiton.
+            # [overview of model
+            # deployment](/ml-engine/docs/concepts/deployment-overview) for more
+            # informaiton.
             #
             # When passing Version to
             # [projects.models.versions.create](/ml-engine/reference/rest/v1beta1/projects.models.versions/create)
             # the model service uses the specified location as the source of the model.
             # Once deployed, the model version is hosted by the prediction service, so
             # this location is useful only as a historical record.
+            # The total number of model files can't exceed 1000.
+        "lastUseTime": "A String", # Output only. The time the version was last used for prediction.
+        "automaticScaling": { # Options for automatically scaling a model. # Automatically scale the number of nodes used to serve the model in
+            # response to increases and decreases in traffic. Care should be
+            # taken to ramp up traffic according to the model's ability to scale
+            # or you will start seeing increases in latency and 429 response codes.
+          "minNodes": 42, # Optional. The minimum number of nodes to allocate for this model. These
+              # nodes are always up, starting from the time the model is deployed, so the
+              # cost of operating this model will be at least
+              # `rate` * `min_nodes` * number of hours since last billing cycle,
+              # where `rate` is the cost per node-hour as documented in
+              # [pricing](https://cloud.google.com/ml-engine/pricing#prediction_pricing),
+              # even if no predictions are performed. There is additional cost for each
+              # prediction performed.
+              #
+              # Unlike manual scaling, if the load gets too heavy for the nodes
+              # that are up, the service will automatically add nodes to handle the
+              # increased load as well as scale back as traffic drops, always maintaining
+              # at least `min_nodes`. You will be charged for the time in which additional
+              # nodes are used.
+              #
+              # If not specified, `min_nodes` defaults to 0, in which case, when traffic
+              # to a model stops (and after a cool-down period), nodes will be shut down
+              # and no charges will be incurred until traffic to the model resumes.
+        },
         "createTime": "A String", # Output only. The time the version was created.
         "isDefault": True or False, # Output only. If true, this version will be used to handle prediction
             # requests that do not specify a version.
             #
             # You can change the default version by calling
             # [projects.methods.versions.setDefault](/ml-engine/reference/rest/v1beta1/projects.models.versions/setDefault).
-        "description": "A String", # Optional. The description specified for the version when it was created.
+        "name": "A String", # Required.The name specified for the version when it was created.
+            #
+            # The version name must be unique within the model it is created in.
       },
       "name": "A String", # Required. The name specified for the model when it was created.
           #
@@ -513,40 +588,65 @@
               # prediction requests. A model can have multiple versions. You can get
               # information about all of the versions of a given model by calling
               # [projects.models.versions.list](/ml-engine/reference/rest/v1beta1/projects.models.versions/list).
-            "name": "A String", # Required.The name specified for the version when it was created.
-                #
-                # The version name must be unique within the model it is created in.
+            "description": "A String", # Optional. The description specified for the version when it was created.
             "runtimeVersion": "A String", # Optional. The Google Cloud ML runtime version to use for this deployment.
                 # If not set, Google Cloud ML will choose a version.
-            "manualScaling": { # Options for manually scaling a model. # Optional. Manually select the number of nodes to use for serving the
-                # model. If unset (i.e., by default), the number of nodes used to serve
-                # the model automatically scales with traffic. However, care should be
-                # taken to ramp up traffic according to the model's ability to scale. If
-                # your model needs to handle bursts of traffic beyond it's ability to
-                # scale, it is recommended you set this field appropriately.
+            "manualScaling": { # Options for manually scaling a model. # Manually select the number of nodes to use for serving the
+                # model. You should generally use `automatic_scaling` with an appropriate
+                # `min_nodes` instead, but this option is available if you want predictable
+                # billing. Beware that latency and error rates will increase if the
+                # traffic exceeds that capability of the system to serve it based on
+                # the selected number of nodes.
               "nodes": 42, # The number of nodes to allocate for this model. These nodes are always up,
                   # starting from the time the model is deployed, so the cost of operating
-                  # this model will be proportional to nodes * number of hours since
-                  # deployment.
+                  # this model will be proportional to `nodes` * number of hours since
+                  # last billing cycle.
             },
-            "lastUseTime": "A String", # Output only. The time the version was last used for prediction.
             "deploymentUri": "A String", # Required. The Google Cloud Storage location of the trained model used to
                 # create the version. See the
-                # [overview of model deployment](/ml-engine/docs/concepts/deployment-overview) for
-                # more informaiton.
+                # [overview of model
+                # deployment](/ml-engine/docs/concepts/deployment-overview) for more
+                # informaiton.
                 #
                 # When passing Version to
                 # [projects.models.versions.create](/ml-engine/reference/rest/v1beta1/projects.models.versions/create)
                 # the model service uses the specified location as the source of the model.
                 # Once deployed, the model version is hosted by the prediction service, so
                 # this location is useful only as a historical record.
+                # The total number of model files can't exceed 1000.
+            "lastUseTime": "A String", # Output only. The time the version was last used for prediction.
+            "automaticScaling": { # Options for automatically scaling a model. # Automatically scale the number of nodes used to serve the model in
+                # response to increases and decreases in traffic. Care should be
+                # taken to ramp up traffic according to the model's ability to scale
+                # or you will start seeing increases in latency and 429 response codes.
+              "minNodes": 42, # Optional. The minimum number of nodes to allocate for this model. These
+                  # nodes are always up, starting from the time the model is deployed, so the
+                  # cost of operating this model will be at least
+                  # `rate` * `min_nodes` * number of hours since last billing cycle,
+                  # where `rate` is the cost per node-hour as documented in
+                  # [pricing](https://cloud.google.com/ml-engine/pricing#prediction_pricing),
+                  # even if no predictions are performed. There is additional cost for each
+                  # prediction performed.
+                  #
+                  # Unlike manual scaling, if the load gets too heavy for the nodes
+                  # that are up, the service will automatically add nodes to handle the
+                  # increased load as well as scale back as traffic drops, always maintaining
+                  # at least `min_nodes`. You will be charged for the time in which additional
+                  # nodes are used.
+                  #
+                  # If not specified, `min_nodes` defaults to 0, in which case, when traffic
+                  # to a model stops (and after a cool-down period), nodes will be shut down
+                  # and no charges will be incurred until traffic to the model resumes.
+            },
             "createTime": "A String", # Output only. The time the version was created.
             "isDefault": True or False, # Output only. If true, this version will be used to handle prediction
                 # requests that do not specify a version.
                 #
                 # You can change the default version by calling
                 # [projects.methods.versions.setDefault](/ml-engine/reference/rest/v1beta1/projects.models.versions/setDefault).
-            "description": "A String", # Optional. The description specified for the version when it was created.
+            "name": "A String", # Required.The name specified for the version when it was created.
+                #
+                # The version name must be unique within the model it is created in.
           },
           "name": "A String", # Required. The name specified for the model when it was created.
               #