anthropic 1.80.0 → 2.3.0

data/rbi/anthropic/resources/beta/vaults.rbi

@@ -7,7 +7,7 @@ module Anthropic
         sig { returns(Anthropic::Resources::Beta::Vaults::Credentials) }
         attr_reader :credentials
 
-        # Create Vault
+        # Create a Vault
         sig do
           params(
             display_name: String,
@@ -37,7 +37,7 @@ module Anthropic
         )
         end
 
-        # Get Vault
+        # Retrieve a Vault
         sig do
           params(
             vault_id: String,
@@ -63,7 +63,7 @@ module Anthropic
         )
         end
 
-        # Update Vault
+        # Update a Vault
         sig do
           params(
             vault_id: String,
@@ -112,12 +112,15 @@ module Anthropic
           )
         end
         def list(
-          # Query param: Whether to include archived vaults in the results.
+          # Query param: Whether to include archived vaults in the results. Defaults to
+          # `false`.
           include_archived: nil,
           # Query param: Maximum number of vaults to return per page. Defaults to 20,
           # maximum 100.
           limit: nil,
-          # Query param: Opaque pagination token from a previous `list_vaults` response.
+          # Query param: The `next_page` value from a previous
+          # [List Vaults](https://platform.claude.com/docs/en/api/beta/vaults/list)
+          # response, to get the next page. Leave it out to get the first page.
           page: nil,
           # Header param: This endpoint is in beta: requests must send
           # `managed-agents-2026-04-01` in this header.
@@ -133,7 +136,7 @@ module Anthropic
         )
         end
 
-        # Delete Vault
+        # Delete a Vault
         sig do
           params(
             vault_id: String,
@@ -159,7 +162,7 @@ module Anthropic
         )
         end
 
-        # Archive Vault
+        # Archive a Vault
         sig do
           params(
             vault_id: String,

data/rbi/anthropic/resources/messages/batches.rbi

@@ -26,10 +26,9 @@ module Anthropic
           # request to create a Message.
           requests:,
           # Header param: The user profile ID to attribute the requests in this batch to.
-          # Use when acting on behalf of a party other than your organization. Requires the
-          # `user-profiles` beta header. Applies to every request in the batch; an
-          # individual request whose `user_profile_id` body field conflicts with this header
-          # is errored.
+          # Use when acting on behalf of a party other than your organization. Applies to
+          # every request in the batch; an individual request whose `user_profile_id` body
+          # field conflicts with this header is errored.
           user_profile_id: nil,
           # Header param: Optional header to select the Workspace for this request. The
           # value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).

data/rbi/anthropic/resources/messages.rbi

@@ -19,7 +19,14 @@ module Anthropic
       sig do
         params(
           max_tokens: Integer,
-          messages: T::Array[Anthropic::MessageParam::OrHash],
+          messages:
+            T::Array[
+              T.any(
+                Anthropic::UserMessageParam::OrHash,
+                Anthropic::AssistantMessageParam::OrHash,
+                Anthropic::SystemMessageParam::OrHash
+              )
+            ],
           model: T.any(Anthropic::Model::OrSymbol, String),
           cache_control: T.nilable(Anthropic::CacheControlEphemeral::OrHash),
           container:
@@ -32,7 +39,6 @@ module Anthropic
           speed: T.nilable(Anthropic::MessageCreateParams::Speed::OrSymbol),
           stop_sequences: T::Array[String],
           system_: Anthropic::MessageCreateParams::System::Variants,
-          temperature: Float,
           thinking:
             T.any(
               Anthropic::ThinkingConfigEnabled::OrHash,
@@ -73,8 +79,6 @@ module Anthropic
                 Anthropic::ToolSearchToolRegex20251119::OrHash
               )
             ],
-          top_k: Integer,
-          top_p: Float,
           user_profile_id: String,
           workspace_id: String,
           stream: T.noreturn,
@@ -161,8 +165,7 @@ module Anthropic
         #
         # Note that if you want to include a
         # [system prompt](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices#give-claude-a-role),
-        # you can use the top-level `system` parameter — there is no `"system"` role for
-        # input messages in the Messages API.
+        # you can use the top-level `system` parameter.
         #
         # There is a limit of 100,000 messages in a single request.
         messages:,
@@ -219,15 +222,6 @@ module Anthropic
         # as specifying a particular goal or role. See our
         # [guide to system prompts](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices#give-claude-a-role).
         system_: nil,
-        # Body param: Amount of randomness injected into the response.
-        #
-        # Defaults to `1.0`. Ranges from `0.0` to `1.0`. Use `temperature` closer to `0.0`
-        # for analytical / multiple choice, and closer to `1.0` for creative and
-        # generative tasks.
-        #
-        # Note that even with `temperature` of `0.0`, the results will not be fully
-        # deterministic.
-        temperature: nil,
         # Body param: Configuration for Claude's thinking.
         #
         # With `{"type": "adaptive"}`, Claude decides when and how much to think. With
@@ -320,24 +314,8 @@ module Anthropic
         # [guide](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview)
         # for more details.
         tools: nil,
-        # Body param: Only sample from the top K options for each subsequent token.
-        #
-        # Used to remove "long tail" low probability responses.
-        # [Learn more technical details here](https://towardsdatascience.com/how-to-sample-from-language-models-682bceb97277).
-        #
-        # Recommended for advanced use cases only.
-        top_k: nil,
-        # Body param: Use nucleus sampling.
-        #
-        # In nucleus sampling, we compute the cumulative distribution over all the options
-        # for each subsequent token in decreasing probability order and cut it off once it
-        # reaches a particular probability specified by `top_p`.
-        #
-        # Recommended for advanced use cases only.
-        top_p: nil,
         # Header param: The user profile ID to attribute this request to. Use when acting
-        # on behalf of a party other than your organization. Requires the `user-profiles`
-        # beta header.
+        # on behalf of a party other than your organization.
         user_profile_id: nil,
         # Header param: Optional header to select the Workspace for this request. The
         # value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
@@ -353,9 +331,6 @@ module Anthropic
       )
       end
 
-      # Hand-written: Anthropic::Resources::Messages#stream (custom code, not generated).
-      # Its sig and parameters copy #stream_raw's below; update them by hand when those change.
-
       # See {Anthropic::Resources::Messages#create} for non-streaming counterpart.
       #
       # Send a structured list of input messages with text and/or image content, and the
@@ -369,7 +344,14 @@ module Anthropic
       sig do
         params(
           max_tokens: Integer,
-          messages: T::Array[Anthropic::MessageParam::OrHash],
+          messages:
+            T::Array[
+              T.any(
+                Anthropic::UserMessageParam::OrHash,
+                Anthropic::AssistantMessageParam::OrHash,
+                Anthropic::SystemMessageParam::OrHash
+              )
+            ],
           model: T.any(Anthropic::Model::OrSymbol, String),
           cache_control: T.nilable(Anthropic::CacheControlEphemeral::OrHash),
           container:
@@ -382,7 +364,6 @@ module Anthropic
           speed: T.nilable(Anthropic::MessageCreateParams::Speed::OrSymbol),
           stop_sequences: T::Array[String],
           system_: Anthropic::MessageCreateParams::System::Variants,
-          temperature: Float,
           thinking:
             T.any(
               Anthropic::ThinkingConfigEnabled::OrHash,
@@ -423,15 +404,18 @@ module Anthropic
                 Anthropic::ToolSearchToolRegex20251119::OrHash
               )
             ],
-          top_k: Integer,
-          top_p: Float,
           user_profile_id: String,
           workspace_id: String,
           stream: T.noreturn,
           request_options: Anthropic::RequestOptions::OrHash
-        ).returns(Anthropic::Helpers::Streaming::MessageStream)
+        ).returns(
+          Anthropic::Internal::Type::BaseStream[
+            T.noreturn,
+            Anthropic::RawMessageStreamEvent::Variants
+          ]
+        )
       end
-      def stream(
+      def stream_raw(
         # Body param: The maximum number of tokens to generate before stopping.
         #
         # Note that our models may stop _before_ reaching this maximum. This parameter
@@ -459,7 +443,10 @@ module Anthropic
         #
         # If the final message uses the `assistant` role, the response content will
         # continue immediately from the content in that message. This can be used to
-        # constrain part of the model's response.
+        # constrain part of the model's response. This is called prefill. On models that
+        # don't support prefill, creating a message that ends with a partial `assistant`
+        # response returns a 400 error. See
+        # [Prefill not supported](https://platform.claude.com/docs/en/api/errors#prefill-not-supported).
         #
         # Example with a single `user` message:
         #
@@ -477,7 +464,8 @@ module Anthropic
         # ]
         # ```
         #
-        # Example with a partially-filled response from Claude:
+        # Example with a partially-filled response from Claude, for models that support
+        # prefill:
         #
         # ```json
         # [
@@ -507,8 +495,7 @@ module Anthropic
         #
         # Note that if you want to include a
         # [system prompt](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices#give-claude-a-role),
-        # you can use the top-level `system` parameter — there is no `"system"` role for
-        # input messages in the Messages API.
+        # you can use the top-level `system` parameter.
         #
         # There is a limit of 100,000 messages in a single request.
         messages:,
@@ -543,6 +530,11 @@ module Anthropic
         service_tier: nil,
         # Body param: The inference speed mode for this request. `"fast"` enables high
         # output-tokens-per-second inference.
+        #
+        # Some models require the `fast-mode-2026-02-01` beta header for any `speed`
+        # value. See
+        # [fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) for
+        # which models.
         speed: nil,
         # Body param: Custom text sequences that will cause the model to stop generating.
         #
@@ -560,24 +552,16 @@ module Anthropic
         # as specifying a particular goal or role. See our
         # [guide to system prompts](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices#give-claude-a-role).
         system_: nil,
-        # Body param: Amount of randomness injected into the response.
-        #
-        # Defaults to `1.0`. Ranges from `0.0` to `1.0`. Use `temperature` closer to `0.0`
-        # for analytical / multiple choice, and closer to `1.0` for creative and
-        # generative tasks.
-        #
-        # Note that even with `temperature` of `0.0`, the results will not be fully
-        # deterministic.
-        temperature: nil,
-        # Body param: Configuration for enabling Claude's extended thinking.
+        # Body param: Configuration for Claude's thinking.
         #
-        # When enabled, responses include `thinking` content blocks showing Claude's
-        # thinking process before the final answer. Requires a minimum budget of 1,024
-        # tokens and counts towards your `max_tokens` limit.
+        # With `{"type": "adaptive"}`, Claude decides when and how much to think. With
+        # `{"type": "enabled"}` (manual extended thinking), you set a `budget_tokens` of
+        # at least 1,024. Thinking tokens count toward your `max_tokens` limit.
         #
-        # See
-        # [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking)
-        # for details.
+        # Which `type` values are accepted, and what happens when you omit `thinking`,
+        # depend on the model. See
+        # [thinking](https://platform.claude.com/docs/en/build-with-claude/thinking#configuring-thinking)
+        # for each model's behavior.
         thinking: nil,
         # Body param: How the model should use the provided tools. The model can use a
         # specific tool, any available tool, decide by itself, or not use tools at all.
@@ -660,24 +644,8 @@ module Anthropic
         # [guide](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview)
         # for more details.
         tools: nil,
-        # Body param: Only sample from the top K options for each subsequent token.
-        #
-        # Used to remove "long tail" low probability responses.
-        # [Learn more technical details here](https://towardsdatascience.com/how-to-sample-from-language-models-682bceb97277).
-        #
-        # Recommended for advanced use cases only.
-        top_k: nil,
-        # Body param: Use nucleus sampling.
-        #
-        # In nucleus sampling, we compute the cumulative distribution over all the options
-        # for each subsequent token in decreasing probability order and cut it off once it
-        # reaches a particular probability specified by `top_p`.
-        #
-        # Recommended for advanced use cases only.
-        top_p: nil,
         # Header param: The user profile ID to attribute this request to. Use when acting
-        # on behalf of a party other than your organization. Requires the `user-profiles`
-        # beta header.
+        # on behalf of a party other than your organization.
         user_profile_id: nil,
         # Header param: Optional header to select the Workspace for this request. The
         # value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
@@ -692,35 +660,30 @@ module Anthropic
         request_options: {}
       )
       end
-      # End of hand-written Anthropic::Resources::Messages#stream.
 
-      # See {Anthropic::Resources::Messages#create} for non-streaming counterpart.
-      #
-      # Send a structured list of input messages with text and/or image content, and the
-      # model will generate the next message in the conversation.
+      # Count the number of tokens in a Message.
       #
-      # The Messages API can be used for either single queries or stateless multi-turn
-      # conversations.
+      # The Token Count API can be used to count the number of tokens in a Message,
+      # including tools, images, and documents, without creating it.
       #
-      # Learn more about the Messages API in our
-      # [user guide](https://platform.claude.com/docs/en/get-started)
+      # Learn more about token counting in our
+      # [user guide](https://platform.claude.com/docs/en/build-with-claude/token-counting)
       sig do
         params(
-          max_tokens: Integer,
-          messages: T::Array[Anthropic::MessageParam::OrHash],
+          messages:
+            T::Array[
+              T.any(
+                Anthropic::UserMessageParam::OrHash,
+                Anthropic::AssistantMessageParam::OrHash,
+                Anthropic::SystemMessageParam::OrHash
+              )
+            ],
           model: T.any(Anthropic::Model::OrSymbol, String),
           cache_control: T.nilable(Anthropic::CacheControlEphemeral::OrHash),
-          container:
-            T.nilable(T.any(Anthropic::ContainerParams::OrHash, String)),
-          diagnostics: T.nilable(Anthropic::DiagnosticsParam::OrHash),
-          inference_geo: T.nilable(String),
-          metadata: Anthropic::Metadata::OrHash,
           output_config: Anthropic::OutputConfig::OrHash,
-          service_tier: Anthropic::MessageCreateParams::ServiceTier::OrSymbol,
-          speed: T.nilable(Anthropic::MessageCreateParams::Speed::OrSymbol),
-          stop_sequences: T::Array[String],
-          system_: Anthropic::MessageCreateParams::System::Variants,
-          temperature: Float,
+          speed:
+            T.nilable(Anthropic::MessageCountTokensParams::Speed::OrSymbol),
+          system_: Anthropic::MessageCountTokensParams::System::Variants,
           thinking:
             T.any(
               Anthropic::ThinkingConfigEnabled::OrHash,
@@ -761,33 +724,12 @@ module Anthropic
                 Anthropic::ToolSearchToolRegex20251119::OrHash
               )
             ],
-          top_k: Integer,
-          top_p: Float,
           user_profile_id: String,
           workspace_id: String,
-          stream: T.noreturn,
           request_options: Anthropic::RequestOptions::OrHash
-        ).returns(
-          Anthropic::Internal::Type::BaseStream[
-            T.noreturn,
-            Anthropic::RawMessageStreamEvent::Variants
-          ]
-        )
+        ).returns(Anthropic::MessageTokensCount)
       end
-      def stream_raw(
-        # Body param: The maximum number of tokens to generate before stopping.
-        #
-        # Note that our models may stop _before_ reaching this maximum. This parameter
-        # only specifies the absolute maximum number of tokens to generate.
-        #
-        # Set to `0` to populate the
-        # [prompt cache](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#pre-warming-the-cache)
-        # without generating a response.
-        #
-        # Different models have different maximum values for this parameter. See
-        # [models](https://platform.claude.com/docs/en/about-claude/models/overview) for
-        # details.
-        max_tokens:,
+      def count_tokens(
         # Body param: Input messages.
         #
         # Our models are trained to operate on alternating `user` and `assistant`
@@ -854,8 +796,7 @@ module Anthropic
         #
         # Note that if you want to include a
         # [system prompt](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices#give-claude-a-role),
-        # you can use the top-level `system` parameter — there is no `"system"` role for
-        # input messages in the Messages API.
+        # you can use the top-level `system` parameter.
         #
         # There is a limit of 100,000 messages in a single request.
         messages:,
@@ -867,27 +808,9 @@ module Anthropic
         # Body param: Top-level cache control automatically applies a cache_control marker
         # to the last cacheable block in the request.
         cache_control: nil,
-        # Body param: Container identifier for reuse across requests.
-        container: nil,
-        # Body param: Request-level diagnostics. Supply `previous_message_id` to have the
-        # response include `diagnostics.cache_miss_reason` explaining any prompt-cache
-        # divergence from that prior request.
-        diagnostics: nil,
-        # Body param: Specifies the geographic region for inference processing. If not
-        # specified, the workspace's `default_inference_geo` is used.
-        inference_geo: nil,
-        # Body param: An object describing metadata about the request.
-        metadata: nil,
         # Body param: Configuration options for the model's output, such as the output
         # format.
         output_config: nil,
-        # Body param: Determines whether to use priority capacity (if available) or
-        # standard capacity for this request.
-        #
-        # Anthropic offers different levels of service for your API requests. See
-        # [service-tiers](https://platform.claude.com/docs/en/api/service-tiers) for
-        # details.
-        service_tier: nil,
         # Body param: The inference speed mode for this request. `"fast"` enables high
         # output-tokens-per-second inference.
         #
@@ -896,31 +819,12 @@ module Anthropic
         # [fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) for
         # which models.
         speed: nil,
-        # Body param: Custom text sequences that will cause the model to stop generating.
-        #
-        # Our models will normally stop when they have naturally completed their turn,
-        # which will result in a response `stop_reason` of `"end_turn"`.
-        #
-        # If you want the model to stop generating when it encounters custom strings of
-        # text, you can use the `stop_sequences` parameter. If the model encounters one of
-        # the custom sequences, the response `stop_reason` value will be `"stop_sequence"`
-        # and the response `stop_sequence` value will contain the matched stop sequence.
-        stop_sequences: nil,
         # Body param: System prompt.
         #
         # A system prompt is a way of providing context and instructions to Claude, such
         # as specifying a particular goal or role. See our
         # [guide to system prompts](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices#give-claude-a-role).
         system_: nil,
-        # Body param: Amount of randomness injected into the response.
-        #
-        # Defaults to `1.0`. Ranges from `0.0` to `1.0`. Use `temperature` closer to `0.0`
-        # for analytical / multiple choice, and closer to `1.0` for creative and
-        # generative tasks.
-        #
-        # Note that even with `temperature` of `0.0`, the results will not be fully
-        # deterministic.
-        temperature: nil,
         # Body param: Configuration for Claude's thinking.
         #
         # With `{"type": "adaptive"}`, Claude decides when and how much to think. With
@@ -1013,24 +917,8 @@ module Anthropic
         # [guide](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview)
         # for more details.
         tools: nil,
-        # Body param: Only sample from the top K options for each subsequent token.
-        #
-        # Used to remove "long tail" low probability responses.
-        # [Learn more technical details here](https://towardsdatascience.com/how-to-sample-from-language-models-682bceb97277).
-        #
-        # Recommended for advanced use cases only.
-        top_k: nil,
-        # Body param: Use nucleus sampling.
-        #
-        # In nucleus sampling, we compute the cumulative distribution over all the options
-        # for each subsequent token in decreasing probability order and cut it off once it
-        # reaches a particular probability specified by `top_p`.
-        #
-        # Recommended for advanced use cases only.
-        top_p: nil,
         # Header param: The user profile ID to attribute this request to. Use when acting
-        # on behalf of a party other than your organization. Requires the `user-profiles`
-        # beta header.
+        # on behalf of a party other than your organization.
         user_profile_id: nil,
         # Header param: Optional header to select the Workspace for this request. The
         # value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
@@ -1039,29 +927,35 @@ module Anthropic
         # credential that belongs to a specific Workspace may omit it; if sent, it must
         # match that Workspace.
         workspace_id: nil,
-        # There is no need to provide `stream:`. Instead, use `#stream_raw` or `#create`
-        # for streaming and non-streaming use cases, respectively.
-        stream: true,
         request_options: {}
       )
       end
 
-      # Count the number of tokens in a Message.
-      #
-      # The Token Count API can be used to count the number of tokens in a Message,
-      # including tools, images, and documents, without creating it.
-      #
-      # Learn more about token counting in our
-      # [user guide](https://platform.claude.com/docs/en/build-with-claude/token-counting)
+      # Streams a message like `stream_raw` and returns a MessageStream, which
+      # accumulates the streamed events and parses tool inputs and structured output.
       sig do
         params(
-          messages: T::Array[Anthropic::MessageParam::OrHash],
+          max_tokens: Integer,
+          messages:
+            T::Array[
+              T.any(
+                Anthropic::UserMessageParam::OrHash,
+                Anthropic::AssistantMessageParam::OrHash,
+                Anthropic::SystemMessageParam::OrHash
+              )
+            ],
           model: T.any(Anthropic::Model::OrSymbol, String),
           cache_control: T.nilable(Anthropic::CacheControlEphemeral::OrHash),
+          container:
+            T.nilable(T.any(Anthropic::ContainerParams::OrHash, String)),
+          diagnostics: T.nilable(Anthropic::DiagnosticsParam::OrHash),
+          inference_geo: T.nilable(String),
+          metadata: Anthropic::Metadata::OrHash,
           output_config: Anthropic::OutputConfig::OrHash,
-          speed:
-            T.nilable(Anthropic::MessageCountTokensParams::Speed::OrSymbol),
-          system_: Anthropic::MessageCountTokensParams::System::Variants,
+          service_tier: Anthropic::MessageCreateParams::ServiceTier::OrSymbol,
+          speed: T.nilable(Anthropic::MessageCreateParams::Speed::OrSymbol),
+          stop_sequences: T::Array[String],
+          system_: Anthropic::MessageCreateParams::System::Variants,
           thinking:
             T.any(
               Anthropic::ThinkingConfigEnabled::OrHash,
@@ -1105,9 +999,22 @@ module Anthropic
           user_profile_id: String,
           workspace_id: String,
           request_options: Anthropic::RequestOptions::OrHash
-        ).returns(Anthropic::MessageTokensCount)
+        ).returns(Anthropic::Helpers::Streaming::MessageStream)
       end
-      def count_tokens(
+      def stream(
+        # Body param: The maximum number of tokens to generate before stopping.
+        #
+        # Note that our models may stop _before_ reaching this maximum. This parameter
+        # only specifies the absolute maximum number of tokens to generate.
+        #
+        # Set to `0` to populate the
+        # [prompt cache](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#pre-warming-the-cache)
+        # without generating a response.
+        #
+        # Different models have different maximum values for this parameter. See
+        # [models](https://platform.claude.com/docs/en/about-claude/models/overview) for
+        # details.
+        max_tokens:,
         # Body param: Input messages.
         #
         # Our models are trained to operate on alternating `user` and `assistant`
@@ -1174,8 +1081,7 @@ module Anthropic
         #
         # Note that if you want to include a
         # [system prompt](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices#give-claude-a-role),
-        # you can use the top-level `system` parameter — there is no `"system"` role for
-        # input messages in the Messages API.
+        # you can use the top-level `system` parameter.
         #
         # There is a limit of 100,000 messages in a single request.
         messages:,
@@ -1187,9 +1093,27 @@ module Anthropic
         # Body param: Top-level cache control automatically applies a cache_control marker
         # to the last cacheable block in the request.
         cache_control: nil,
+        # Body param: Container identifier for reuse across requests.
+        container: nil,
+        # Body param: Request-level diagnostics. Supply `previous_message_id` to have the
+        # response include `diagnostics.cache_miss_reason` explaining any prompt-cache
+        # divergence from that prior request.
+        diagnostics: nil,
+        # Body param: Specifies the geographic region for inference processing. If not
+        # specified, the workspace's `default_inference_geo` is used.
+        inference_geo: nil,
+        # Body param: An object describing metadata about the request.
+        metadata: nil,
         # Body param: Configuration options for the model's output, such as the output
         # format.
         output_config: nil,
+        # Body param: Determines whether to use priority capacity (if available) or
+        # standard capacity for this request.
+        #
+        # Anthropic offers different levels of service for your API requests. See
+        # [service-tiers](https://platform.claude.com/docs/en/api/service-tiers) for
+        # details.
+        service_tier: nil,
         # Body param: The inference speed mode for this request. `"fast"` enables high
         # output-tokens-per-second inference.
         #
@@ -1198,6 +1122,16 @@ module Anthropic
         # [fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) for
         # which models.
         speed: nil,
+        # Body param: Custom text sequences that will cause the model to stop generating.
+        #
+        # Our models will normally stop when they have naturally completed their turn,
+        # which will result in a response `stop_reason` of `"end_turn"`.
+        #
+        # If you want the model to stop generating when it encounters custom strings of
+        # text, you can use the `stop_sequences` parameter. If the model encounters one of
+        # the custom sequences, the response `stop_reason` value will be `"stop_sequence"`
+        # and the response `stop_sequence` value will contain the matched stop sequence.
+        stop_sequences: nil,
         # Body param: System prompt.
         #
         # A system prompt is a way of providing context and instructions to Claude, such
@@ -1297,8 +1231,7 @@ module Anthropic
         # for more details.
         tools: nil,
         # Header param: The user profile ID to attribute this request to. Use when acting
-        # on behalf of a party other than your organization. Requires the `user-profiles`
-        # beta header.
+        # on behalf of a party other than your organization.
         user_profile_id: nil,
         # Header param: Optional header to select the Workspace for this request. The
         # value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).

data/rbi/anthropic/resources/models.rbi

@@ -10,7 +10,6 @@ module Anthropic
       sig do
         params(
           model_id: String,
-          betas: T::Array[T.any(Anthropic::AnthropicBeta::OrSymbol, String)],
           workspace_id: String,
           request_options: Anthropic::RequestOptions::OrHash
         ).returns(Anthropic::ModelInfo)
@@ -18,8 +17,6 @@ module Anthropic
       def retrieve(
         # Model identifier or alias.
         model_id,
-        # Optional header to specify the beta version(s) you want to use.
-        betas: nil,
         # Optional header to select the Workspace for this request. The value is a
         # Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
         #
@@ -41,7 +38,6 @@ module Anthropic
           before_id: String,
           lifecycle: T::Array[Anthropic::ModelListParams::Lifecycle::OrSymbol],
           limit: Integer,
-          betas: T::Array[T.any(Anthropic::AnthropicBeta::OrSymbol, String)],
           workspace_id: String,
           request_options: Anthropic::RequestOptions::OrHash
         ).returns(Anthropic::Internal::Page[Anthropic::ModelInfo])
@@ -62,8 +58,6 @@ module Anthropic
         #
         # Defaults to `20`. Ranges from `1` to `1000`.
         limit: nil,
-        # Header param: Optional header to specify the beta version(s) you want to use.
-        betas: nil,
         # Header param: Optional header to select the Workspace for this request. The
         # value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
         #