Clean and regen docs (#401)

diff --git a/docs/dyn/ml_v1.projects.models.versions.html b/docs/dyn/ml_v1.projects.models.versions.html
index aad4165..1df296a 100644
--- a/docs/dyn/ml_v1.projects.models.versions.html
+++ b/docs/dyn/ml_v1.projects.models.versions.html
@@ -84,7 +84,7 @@
   <code><a href="#get">get(name, x__xgafv=None)</a></code></p>
 <p class="firstline">Gets information about a model version.</p>
 <p class="toc_element">
-  <code><a href="#list">list(parent, pageSize=None, pageToken=None, x__xgafv=None)</a></code></p>
+  <code><a href="#list">list(parent, pageToken=None, x__xgafv=None, pageSize=None)</a></code></p>
 <p class="firstline">Gets basic information about all the versions of a model.</p>
 <p class="toc_element">
   <code><a href="#list_next">list_next(previous_request, previous_response)</a></code></p>
@@ -120,28 +120,53 @@
   "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 more
+      # 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 plus the cost for each prediction performed.
   },
-  "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/v1/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.
@@ -163,28 +188,12 @@
 
     { # This resource represents a long-running operation that is the result of a
       # network API call.
-    "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.
-    },
     "metadata": { # Service-specific metadata associated with the operation.  It typically
         # contains progress information and common metadata such as create time.
         # Some services might not provide such metadata.  Any method that returns a
         # 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.
-    "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:
@@ -202,7 +211,7 @@
         # 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
         #
@@ -225,7 +234,7 @@
         #     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
@@ -248,6 +257,22 @@
         },
       ],
     },
+    "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>
 
@@ -277,28 +302,12 @@
 
     { # This resource represents a long-running operation that is the result of a
       # network API call.
-    "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.
-    },
     "metadata": { # Service-specific metadata associated with the operation.  It typically
         # contains progress information and common metadata such as create time.
         # Some services might not provide such metadata.  Any method that returns a
         # 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.
-    "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:
@@ -316,7 +325,7 @@
         # 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
         #
@@ -339,7 +348,7 @@
         #     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
@@ -362,6 +371,22 @@
         },
       ],
     },
+    "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>
 
@@ -395,28 +420,53 @@
     "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 more
+        # 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 plus the cost for each prediction performed.
     },
-    "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/v1/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.
@@ -430,7 +480,7 @@
 </div>
 
 <div class="method">
-    <code class="details" id="list">list(parent, pageSize=None, pageToken=None, x__xgafv=None)</code>
+    <code class="details" id="list">list(parent, pageToken=None, x__xgafv=None, pageSize=None)</code>
   <pre>Gets basic information about all the versions of a model.
 
 If you expect that a model has a lot of versions, or if you need to handle
@@ -441,11 +491,6 @@
   parent: string, Required. The name of the model for which to list the version.
 
 Authorization: requires `Viewer` role on the parent project. (required)
-  pageSize: integer, Optional. The number of versions to retrieve per "page" of results. If
-there are more remaining results than this number, the response message
-will contain a valid value in the `next_page_token` field.
-
-The default value is 20, and the maximum page size is 100.
   pageToken: string, Optional. A page token to request the next page of results.
 
 You get the token from the `next_page_token` field of the response from
@@ -454,6 +499,11 @@
     Allowed values
       1 - v1 error format
       2 - v2 error format
+  pageSize: integer, Optional. The number of versions to retrieve per "page" of results. If
+there are more remaining results than this number, the response message
+will contain a valid value in the `next_page_token` field.
+
+The default value is 20, and the maximum page size is 100.
 
 Returns:
   An object of the form:
@@ -471,28 +521,53 @@
         "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 more
+            # 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 plus the cost for each prediction performed.
         },
-        "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/v1/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.
@@ -561,28 +636,53 @@
     "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 more
+        # 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 plus the cost for each prediction performed.
     },
-    "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/v1/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.