openai 0.10.0 → 0.12.0

data/rbi/openai/helpers/streaming/response_stream.rbi

@@ -0,0 +1,104 @@
+# typed: strong
+
+module OpenAI
+  module Helpers
+    module Streaming
+      class ResponseStream
+        include OpenAI::Internal::Type::BaseStream
+
+        # Define the type union for streaming events that can be yielded
+        ResponseStreamEvent =
+          T.type_alias do
+            T.any(
+              OpenAI::Streaming::ResponseTextDeltaEvent,
+              OpenAI::Streaming::ResponseTextDoneEvent,
+              OpenAI::Streaming::ResponseCompletedEvent,
+              OpenAI::Streaming::ResponseFunctionCallArgumentsDeltaEvent,
+              # Pass through other raw events
+              OpenAI::Models::Responses::ResponseStreamEvent::Variants
+            )
+          end
+
+        Message = type_member { { fixed: ResponseStreamEvent } }
+        Elem = type_member { { fixed: ResponseStreamEvent } }
+
+        sig do
+          params(
+            raw_stream: T.untyped,
+            text_format: T.untyped,
+            starting_after: T.nilable(Integer)
+          ).void
+        end
+        def initialize(raw_stream:, text_format:, starting_after:)
+        end
+
+        sig { void }
+        def close
+        end
+
+        sig { returns(T.self_type) }
+        def until_done
+        end
+
+        sig { returns(OpenAI::Models::Responses::Response) }
+        def get_final_response
+        end
+
+        sig { returns(String) }
+        def get_output_text
+        end
+
+        sig { returns(T::Enumerator::Lazy[String]) }
+        def text
+        end
+
+        # Override the each method to properly type the yielded events
+        sig do
+          params(
+            block: T.nilable(T.proc.params(event: ResponseStreamEvent).void)
+          ).returns(T.any(T.self_type, T::Enumerator[ResponseStreamEvent]))
+        end
+        def each(&block)
+        end
+
+        private
+
+        sig { returns(T.untyped) }
+        def iterator
+        end
+      end
+
+      class ResponseStreamState
+        sig { returns(T.nilable(OpenAI::Models::Responses::Response)) }
+        attr_reader :completed_response
+
+        sig { params(text_format: T.untyped).void }
+        def initialize(text_format:)
+        end
+
+        sig { params(event: T.untyped).returns(T::Array[T.untyped]) }
+        def handle_event(event)
+        end
+
+        sig do
+          params(
+            event: T.untyped,
+            current_snapshot: T.nilable(OpenAI::Models::Responses::Response)
+          ).returns(OpenAI::Models::Responses::Response)
+        end
+        def accumulate_event(event:, current_snapshot:)
+        end
+
+        private
+
+        sig { params(text: T.nilable(String)).returns(T.untyped) }
+        def parse_structured_text(text)
+        end
+
+        sig { params(object: T.untyped, expected_type: Symbol).void }
+        def assert_type(object, expected_type)
+        end
+      end
+    end
+  end
+end

data/rbi/openai/internal/type/base_stream.rbi

@@ -52,10 +52,17 @@ module OpenAI
             url: URI::Generic,
             status: Integer,
             response: Net::HTTPResponse,
+            unwrap:
+              T.any(
+                Symbol,
+                Integer,
+                T::Array[T.any(Symbol, Integer)],
+                T.proc.params(arg0: T.anything).returns(T.anything)
+              ),
             stream: T::Enumerable[Message]
           ).void
         end
-        def initialize(model:, url:, status:, response:, stream:)
+        def initialize(model:, url:, status:, response:, unwrap:, stream:)
         end
 
         # @api private

data/rbi/openai/models/all_models.rbi

@@ -35,6 +35,26 @@ module OpenAI
             :"o3-pro-2025-06-10",
             OpenAI::AllModels::ResponsesOnlyModel::TaggedSymbol
           )
+        O3_DEEP_RESEARCH =
+          T.let(
+            :"o3-deep-research",
+            OpenAI::AllModels::ResponsesOnlyModel::TaggedSymbol
+          )
+        O3_DEEP_RESEARCH_2025_06_26 =
+          T.let(
+            :"o3-deep-research-2025-06-26",
+            OpenAI::AllModels::ResponsesOnlyModel::TaggedSymbol
+          )
+        O4_MINI_DEEP_RESEARCH =
+          T.let(
+            :"o4-mini-deep-research",
+            OpenAI::AllModels::ResponsesOnlyModel::TaggedSymbol
+          )
+        O4_MINI_DEEP_RESEARCH_2025_06_26 =
+          T.let(
+            :"o4-mini-deep-research-2025-06-26",
+            OpenAI::AllModels::ResponsesOnlyModel::TaggedSymbol
+          )
         COMPUTER_USE_PREVIEW =
           T.let(
             :"computer-use-preview",

data/rbi/openai/models/chat/chat_completion.rbi

@@ -32,23 +32,23 @@ module OpenAI
         sig { returns(Symbol) }
         attr_accessor :object
 
-        # Specifies the latency tier to use for processing the request. This parameter is
-        # relevant for customers subscribed to the scale tier service:
+        # Specifies the processing type used for serving the request.
         #
-        # - If set to 'auto', and the Project is Scale tier enabled, the system will
-        #   utilize scale tier credits until they are exhausted.
-        # - If set to 'auto', and the Project is not Scale tier enabled, the request will
-        #   be processed using the default service tier with a lower uptime SLA and no
-        #   latency guarantee.
-        # - If set to 'default', the request will be processed using the default service
-        #   tier with a lower uptime SLA and no latency guarantee.
-        # - If set to 'flex', the request will be processed with the Flex Processing
-        #   service tier.
-        #   [Learn more](https://platform.openai.com/docs/guides/flex-processing).
+        # - If set to 'auto', then the request will be processed with the service tier
+        #   configured in the Project settings. Unless otherwise configured, the Project
+        #   will use 'default'.
+        # - If set to 'default', then the requset will be processed with the standard
+        #   pricing and performance for the selected model.
+        # - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or
+        #   'priority', then the request will be processed with the corresponding service
+        #   tier. [Contact sales](https://openai.com/contact-sales) to learn more about
+        #   Priority processing.
         # - When not set, the default behavior is 'auto'.
         #
-        # When this parameter is set, the response body will include the `service_tier`
-        # utilized.
+        # When the `service_tier` parameter is set, the response body will include the
+        # `service_tier` value based on the processing mode actually used to serve the
+        # request. This response value may be different from the value set in the
+        # parameter.
         sig do
           returns(
             T.nilable(OpenAI::Chat::ChatCompletion::ServiceTier::TaggedSymbol)
@@ -98,23 +98,23 @@ module OpenAI
           created:,
           # The model used for the chat completion.
           model:,
-          # Specifies the latency tier to use for processing the request. This parameter is
-          # relevant for customers subscribed to the scale tier service:
+          # Specifies the processing type used for serving the request.
           #
-          # - If set to 'auto', and the Project is Scale tier enabled, the system will
-          #   utilize scale tier credits until they are exhausted.
-          # - If set to 'auto', and the Project is not Scale tier enabled, the request will
-          #   be processed using the default service tier with a lower uptime SLA and no
-          #   latency guarantee.
-          # - If set to 'default', the request will be processed using the default service
-          #   tier with a lower uptime SLA and no latency guarantee.
-          # - If set to 'flex', the request will be processed with the Flex Processing
-          #   service tier.
-          #   [Learn more](https://platform.openai.com/docs/guides/flex-processing).
+          # - If set to 'auto', then the request will be processed with the service tier
+          #   configured in the Project settings. Unless otherwise configured, the Project
+          #   will use 'default'.
+          # - If set to 'default', then the requset will be processed with the standard
+          #   pricing and performance for the selected model.
+          # - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or
+          #   'priority', then the request will be processed with the corresponding service
+          #   tier. [Contact sales](https://openai.com/contact-sales) to learn more about
+          #   Priority processing.
           # - When not set, the default behavior is 'auto'.
           #
-          # When this parameter is set, the response body will include the `service_tier`
-          # utilized.
+          # When the `service_tier` parameter is set, the response body will include the
+          # `service_tier` value based on the processing mode actually used to serve the
+          # request. This response value may be different from the value set in the
+          # parameter.
           service_tier: nil,
           # This fingerprint represents the backend configuration that the model runs with.
           #
@@ -363,23 +363,23 @@ module OpenAI
           end
         end
 
-        # Specifies the latency tier to use for processing the request. This parameter is
-        # relevant for customers subscribed to the scale tier service:
+        # Specifies the processing type used for serving the request.
         #
-        # - If set to 'auto', and the Project is Scale tier enabled, the system will
-        #   utilize scale tier credits until they are exhausted.
-        # - If set to 'auto', and the Project is not Scale tier enabled, the request will
-        #   be processed using the default service tier with a lower uptime SLA and no
-        #   latency guarantee.
-        # - If set to 'default', the request will be processed using the default service
-        #   tier with a lower uptime SLA and no latency guarantee.
-        # - If set to 'flex', the request will be processed with the Flex Processing
-        #   service tier.
-        #   [Learn more](https://platform.openai.com/docs/guides/flex-processing).
+        # - If set to 'auto', then the request will be processed with the service tier
+        #   configured in the Project settings. Unless otherwise configured, the Project
+        #   will use 'default'.
+        # - If set to 'default', then the requset will be processed with the standard
+        #   pricing and performance for the selected model.
+        # - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or
+        #   'priority', then the request will be processed with the corresponding service
+        #   tier. [Contact sales](https://openai.com/contact-sales) to learn more about
+        #   Priority processing.
         # - When not set, the default behavior is 'auto'.
         #
-        # When this parameter is set, the response body will include the `service_tier`
-        # utilized.
+        # When the `service_tier` parameter is set, the response body will include the
+        # `service_tier` value based on the processing mode actually used to serve the
+        # request. This response value may be different from the value set in the
+        # parameter.
         module ServiceTier
           extend OpenAI::Internal::Type::Enum
 
@@ -409,6 +409,11 @@ module OpenAI
               :scale,
               OpenAI::Chat::ChatCompletion::ServiceTier::TaggedSymbol
             )
+          PRIORITY =
+            T.let(
+              :priority,
+              OpenAI::Chat::ChatCompletion::ServiceTier::TaggedSymbol
+            )
 
           sig do
             override.returns(

data/rbi/openai/models/chat/chat_completion_chunk.rbi

@@ -34,23 +34,23 @@ module OpenAI
         sig { returns(Symbol) }
         attr_accessor :object
 
-        # Specifies the latency tier to use for processing the request. This parameter is
-        # relevant for customers subscribed to the scale tier service:
+        # Specifies the processing type used for serving the request.
         #
-        # - If set to 'auto', and the Project is Scale tier enabled, the system will
-        #   utilize scale tier credits until they are exhausted.
-        # - If set to 'auto', and the Project is not Scale tier enabled, the request will
-        #   be processed using the default service tier with a lower uptime SLA and no
-        #   latency guarantee.
-        # - If set to 'default', the request will be processed using the default service
-        #   tier with a lower uptime SLA and no latency guarantee.
-        # - If set to 'flex', the request will be processed with the Flex Processing
-        #   service tier.
-        #   [Learn more](https://platform.openai.com/docs/guides/flex-processing).
+        # - If set to 'auto', then the request will be processed with the service tier
+        #   configured in the Project settings. Unless otherwise configured, the Project
+        #   will use 'default'.
+        # - If set to 'default', then the requset will be processed with the standard
+        #   pricing and performance for the selected model.
+        # - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or
+        #   'priority', then the request will be processed with the corresponding service
+        #   tier. [Contact sales](https://openai.com/contact-sales) to learn more about
+        #   Priority processing.
         # - When not set, the default behavior is 'auto'.
         #
-        # When this parameter is set, the response body will include the `service_tier`
-        # utilized.
+        # When the `service_tier` parameter is set, the response body will include the
+        # `service_tier` value based on the processing mode actually used to serve the
+        # request. This response value may be different from the value set in the
+        # parameter.
         sig do
           returns(
             T.nilable(
@@ -113,23 +113,23 @@ module OpenAI
           created:,
           # The model to generate the completion.
           model:,
-          # Specifies the latency tier to use for processing the request. This parameter is
-          # relevant for customers subscribed to the scale tier service:
+          # Specifies the processing type used for serving the request.
           #
-          # - If set to 'auto', and the Project is Scale tier enabled, the system will
-          #   utilize scale tier credits until they are exhausted.
-          # - If set to 'auto', and the Project is not Scale tier enabled, the request will
-          #   be processed using the default service tier with a lower uptime SLA and no
-          #   latency guarantee.
-          # - If set to 'default', the request will be processed using the default service
-          #   tier with a lower uptime SLA and no latency guarantee.
-          # - If set to 'flex', the request will be processed with the Flex Processing
-          #   service tier.
-          #   [Learn more](https://platform.openai.com/docs/guides/flex-processing).
+          # - If set to 'auto', then the request will be processed with the service tier
+          #   configured in the Project settings. Unless otherwise configured, the Project
+          #   will use 'default'.
+          # - If set to 'default', then the requset will be processed with the standard
+          #   pricing and performance for the selected model.
+          # - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or
+          #   'priority', then the request will be processed with the corresponding service
+          #   tier. [Contact sales](https://openai.com/contact-sales) to learn more about
+          #   Priority processing.
           # - When not set, the default behavior is 'auto'.
           #
-          # When this parameter is set, the response body will include the `service_tier`
-          # utilized.
+          # When the `service_tier` parameter is set, the response body will include the
+          # `service_tier` value based on the processing mode actually used to serve the
+          # request. This response value may be different from the value set in the
+          # parameter.
           service_tier: nil,
           # This fingerprint represents the backend configuration that the model runs with.
           # Can be used in conjunction with the `seed` request parameter to understand when
@@ -783,23 +783,23 @@ module OpenAI
           end
         end
 
-        # Specifies the latency tier to use for processing the request. This parameter is
-        # relevant for customers subscribed to the scale tier service:
+        # Specifies the processing type used for serving the request.
         #
-        # - If set to 'auto', and the Project is Scale tier enabled, the system will
-        #   utilize scale tier credits until they are exhausted.
-        # - If set to 'auto', and the Project is not Scale tier enabled, the request will
-        #   be processed using the default service tier with a lower uptime SLA and no
-        #   latency guarantee.
-        # - If set to 'default', the request will be processed using the default service
-        #   tier with a lower uptime SLA and no latency guarantee.
-        # - If set to 'flex', the request will be processed with the Flex Processing
-        #   service tier.
-        #   [Learn more](https://platform.openai.com/docs/guides/flex-processing).
+        # - If set to 'auto', then the request will be processed with the service tier
+        #   configured in the Project settings. Unless otherwise configured, the Project
+        #   will use 'default'.
+        # - If set to 'default', then the requset will be processed with the standard
+        #   pricing and performance for the selected model.
+        # - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or
+        #   'priority', then the request will be processed with the corresponding service
+        #   tier. [Contact sales](https://openai.com/contact-sales) to learn more about
+        #   Priority processing.
         # - When not set, the default behavior is 'auto'.
         #
-        # When this parameter is set, the response body will include the `service_tier`
-        # utilized.
+        # When the `service_tier` parameter is set, the response body will include the
+        # `service_tier` value based on the processing mode actually used to serve the
+        # request. This response value may be different from the value set in the
+        # parameter.
         module ServiceTier
           extend OpenAI::Internal::Type::Enum
 
@@ -829,6 +829,11 @@ module OpenAI
               :scale,
               OpenAI::Chat::ChatCompletionChunk::ServiceTier::TaggedSymbol
             )
+          PRIORITY =
+            T.let(
+              :priority,
+              OpenAI::Chat::ChatCompletionChunk::ServiceTier::TaggedSymbol
+            )
 
           sig do
             override.returns(

data/rbi/openai/models/chat/completion_create_params.rbi

@@ -270,23 +270,23 @@ module OpenAI
         sig { returns(T.nilable(Integer)) }
         attr_accessor :seed
 
-        # Specifies the latency tier to use for processing the request. This parameter is
-        # relevant for customers subscribed to the scale tier service:
+        # Specifies the processing type used for serving the request.
         #
-        # - If set to 'auto', and the Project is Scale tier enabled, the system will
-        #   utilize scale tier credits until they are exhausted.
-        # - If set to 'auto', and the Project is not Scale tier enabled, the request will
-        #   be processed using the default service tier with a lower uptime SLA and no
-        #   latency guarantee.
-        # - If set to 'default', the request will be processed using the default service
-        #   tier with a lower uptime SLA and no latency guarantee.
-        # - If set to 'flex', the request will be processed with the Flex Processing
-        #   service tier.
-        #   [Learn more](https://platform.openai.com/docs/guides/flex-processing).
+        # - If set to 'auto', then the request will be processed with the service tier
+        #   configured in the Project settings. Unless otherwise configured, the Project
+        #   will use 'default'.
+        # - If set to 'default', then the requset will be processed with the standard
+        #   pricing and performance for the selected model.
+        # - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or
+        #   'priority', then the request will be processed with the corresponding service
+        #   tier. [Contact sales](https://openai.com/contact-sales) to learn more about
+        #   Priority processing.
         # - When not set, the default behavior is 'auto'.
         #
-        # When this parameter is set, the response body will include the `service_tier`
-        # utilized.
+        # When the `service_tier` parameter is set, the response body will include the
+        # `service_tier` value based on the processing mode actually used to serve the
+        # request. This response value may be different from the value set in the
+        # parameter.
         sig do
           returns(
             T.nilable(
@@ -310,6 +310,8 @@ module OpenAI
         # Whether or not to store the output of this chat completion request for use in
         # our [model distillation](https://platform.openai.com/docs/guides/distillation)
         # or [evals](https://platform.openai.com/docs/guides/evals) products.
+        #
+        # Supports text and image inputs. Note: image inputs over 10MB will be dropped.
         sig { returns(T.nilable(T::Boolean)) }
         attr_accessor :store
 
@@ -625,23 +627,23 @@ module OpenAI
           # should refer to the `system_fingerprint` response parameter to monitor changes
           # in the backend.
           seed: nil,
-          # Specifies the latency tier to use for processing the request. This parameter is
-          # relevant for customers subscribed to the scale tier service:
+          # Specifies the processing type used for serving the request.
           #
-          # - If set to 'auto', and the Project is Scale tier enabled, the system will
-          #   utilize scale tier credits until they are exhausted.
-          # - If set to 'auto', and the Project is not Scale tier enabled, the request will
-          #   be processed using the default service tier with a lower uptime SLA and no
-          #   latency guarantee.
-          # - If set to 'default', the request will be processed using the default service
-          #   tier with a lower uptime SLA and no latency guarantee.
-          # - If set to 'flex', the request will be processed with the Flex Processing
-          #   service tier.
-          #   [Learn more](https://platform.openai.com/docs/guides/flex-processing).
+          # - If set to 'auto', then the request will be processed with the service tier
+          #   configured in the Project settings. Unless otherwise configured, the Project
+          #   will use 'default'.
+          # - If set to 'default', then the requset will be processed with the standard
+          #   pricing and performance for the selected model.
+          # - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or
+          #   'priority', then the request will be processed with the corresponding service
+          #   tier. [Contact sales](https://openai.com/contact-sales) to learn more about
+          #   Priority processing.
           # - When not set, the default behavior is 'auto'.
           #
-          # When this parameter is set, the response body will include the `service_tier`
-          # utilized.
+          # When the `service_tier` parameter is set, the response body will include the
+          # `service_tier` value based on the processing mode actually used to serve the
+          # request. This response value may be different from the value set in the
+          # parameter.
           service_tier: nil,
           # Not supported with latest reasoning models `o3` and `o4-mini`.
           #
@@ -651,6 +653,8 @@ module OpenAI
           # Whether or not to store the output of this chat completion request for use in
           # our [model distillation](https://platform.openai.com/docs/guides/distillation)
           # or [evals](https://platform.openai.com/docs/guides/evals) products.
+          #
+          # Supports text and image inputs. Note: image inputs over 10MB will be dropped.
           store: nil,
           # Options for streaming response. Only set this when you set `stream: true`.
           stream_options: nil,
@@ -1008,23 +1012,23 @@ module OpenAI
           end
         end
 
-        # Specifies the latency tier to use for processing the request. This parameter is
-        # relevant for customers subscribed to the scale tier service:
+        # Specifies the processing type used for serving the request.
         #
-        # - If set to 'auto', and the Project is Scale tier enabled, the system will
-        #   utilize scale tier credits until they are exhausted.
-        # - If set to 'auto', and the Project is not Scale tier enabled, the request will
-        #   be processed using the default service tier with a lower uptime SLA and no
-        #   latency guarantee.
-        # - If set to 'default', the request will be processed using the default service
-        #   tier with a lower uptime SLA and no latency guarantee.
-        # - If set to 'flex', the request will be processed with the Flex Processing
-        #   service tier.
-        #   [Learn more](https://platform.openai.com/docs/guides/flex-processing).
+        # - If set to 'auto', then the request will be processed with the service tier
+        #   configured in the Project settings. Unless otherwise configured, the Project
+        #   will use 'default'.
+        # - If set to 'default', then the requset will be processed with the standard
+        #   pricing and performance for the selected model.
+        # - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or
+        #   'priority', then the request will be processed with the corresponding service
+        #   tier. [Contact sales](https://openai.com/contact-sales) to learn more about
+        #   Priority processing.
         # - When not set, the default behavior is 'auto'.
         #
-        # When this parameter is set, the response body will include the `service_tier`
-        # utilized.
+        # When the `service_tier` parameter is set, the response body will include the
+        # `service_tier` value based on the processing mode actually used to serve the
+        # request. This response value may be different from the value set in the
+        # parameter.
         module ServiceTier
           extend OpenAI::Internal::Type::Enum
 
@@ -1054,6 +1058,11 @@ module OpenAI
               :scale,
               OpenAI::Chat::CompletionCreateParams::ServiceTier::TaggedSymbol
             )
+          PRIORITY =
+            T.let(
+              :priority,
+              OpenAI::Chat::CompletionCreateParams::ServiceTier::TaggedSymbol
+            )
 
           sig do
             override.returns(