feat: wrap /v1/messages/count_tokens (regenerate core + ergonomic method) (#10)

* chore: regenerate SDK client core from gateway OpenAPI spec

* feat: wrap /v1/messages/count_tokens (regenerate core + ergonomic method)

The gateway spec gained POST /v1/messages/count_tokens, which the
endpoint-coverage drift gate flagged as unaccounted-for (CI red on main).

This regenerates the client core to include the count_tokens operation
(absorbs the open codegen PR) and adds a hand-written count_tokens()
ergonomic method to the sync and async shells, mirroring message(). It
returns a typed CountTokensResponse and omits max_tokens, since the
endpoint only counts input tokens. The endpoint is listed under
[covered] in sdk-endpoints.txt and covered by sync + async unit tests.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: khaledosman <2937633+khaledosman@users.noreply.github.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

Author: 3 people

sdk-endpoints.txt

@@ -16,6 +16,7 @@
 POST /v1/chat/completions
 POST /v1/responses
 POST /v1/messages
+POST /v1/messages/count_tokens
 POST /v1/embeddings
 POST /v1/moderations
 POST /v1/rerank

src/otari/_client/__init__.py

@@ -91,6 +91,8 @@
     "Content8",
     "Content9Inner",
     "ContentAnyOfInner",
+    "CountTokensRequest",
+    "CountTokensResponse",
     "CreateBatchRequest",
     "CreateBudgetRequest",
     "CreateEmbeddingResponse",
@@ -195,6 +197,7 @@
     "SetPricingRequest",
     "Source",
     "System",
+    "System1",
     "ToolCallsInner",
     "ToolChoice",
     "UpdateBudgetRequest",
@@ -284,6 +287,8 @@
 from otari._client.models.content8 import Content8 as Content8
 from otari._client.models.content9_inner import Content9Inner as Content9Inner
 from otari._client.models.content_any_of_inner import ContentAnyOfInner as ContentAnyOfInner
+from otari._client.models.count_tokens_request import CountTokensRequest as CountTokensRequest
+from otari._client.models.count_tokens_response import CountTokensResponse as CountTokensResponse
 from otari._client.models.create_batch_request import CreateBatchRequest as CreateBatchRequest
 from otari._client.models.create_budget_request import CreateBudgetRequest as CreateBudgetRequest
 from otari._client.models.create_embedding_response import CreateEmbeddingResponse as CreateEmbeddingResponse
@@ -388,6 +393,7 @@
 from otari._client.models.set_pricing_request import SetPricingRequest as SetPricingRequest
 from otari._client.models.source import Source as Source
 from otari._client.models.system import System as System
+from otari._client.models.system1 import System1 as System1
 from otari._client.models.tool_calls_inner import ToolCallsInner as ToolCallsInner
 from otari._client.models.tool_choice import ToolChoice as ToolChoice
 from otari._client.models.update_budget_request import UpdateBudgetRequest as UpdateBudgetRequest

src/otari/_client/api/messages_api.py

@@ -15,6 +15,8 @@
 from typing import Any, Dict, List, Optional, Tuple, Union
 from typing_extensions import Annotated
 
+from otari._client.models.count_tokens_request import CountTokensRequest
+from otari._client.models.count_tokens_response import CountTokensResponse
 from otari._client.models.message_response import MessageResponse
 from otari._client.models.messages_request import MessagesRequest
 
@@ -36,6 +38,282 @@ def __init__(self, api_client=None) -> None:
         self.api_client = api_client
 
 
+    @validate_call
+    def count_message_tokens_v1_messages_count_tokens_post(
+        self,
+        count_tokens_request: CountTokensRequest,
+        _request_timeout: Union[
+            None,
+            Annotated[StrictFloat, Field(gt=0)],
+            Tuple[
+                Annotated[StrictFloat, Field(gt=0)],
+                Annotated[StrictFloat, Field(gt=0)]
+            ]
+        ] = None,
+        _request_auth: Optional[Dict[StrictStr, Any]] = None,
+        _content_type: Optional[StrictStr] = None,
+        _headers: Optional[Dict[StrictStr, Any]] = None,
+        _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0,
+    ) -> CountTokensResponse:
+        """Count Message Tokens
+
+        Anthropic ``/v1/messages/count_tokens``-compatible endpoint.  Returns ``{\"input_tokens\": N}`` without contacting an upstream provider: counting is local, so there is no budget reservation, pricing, or usage logging. Authentication mirrors :func:`create_message` — platform mode resolves the caller's token against the platform, standalone mode validates the API key — so the endpoint is not an open token-counting oracle.
+
+        :param count_tokens_request: (required)
+        :type count_tokens_request: CountTokensRequest
+        :param _request_timeout: timeout setting for this request. If one
+                                 number provided, it will be total request
+                                 timeout. It can also be a pair (tuple) of
+                                 (connection, read) timeouts.
+        :type _request_timeout: int, tuple(int, int), optional
+        :param _request_auth: set to override the auth_settings for an a single
+                              request; this effectively ignores the
+                              authentication in the spec for a single request.
+        :type _request_auth: dict, optional
+        :param _content_type: force content-type for the request.
+        :type _content_type: str, Optional
+        :param _headers: set to override the headers for a single
+                         request; this effectively ignores the headers
+                         in the spec for a single request.
+        :type _headers: dict, optional
+        :param _host_index: set to override the host_index for a single
+                            request; this effectively ignores the host_index
+                            in the spec for a single request.
+        :type _host_index: int, optional
+        :return: Returns the result object.
+        """ # noqa: E501
+
+        _param = self._count_message_tokens_v1_messages_count_tokens_post_serialize(
+            count_tokens_request=count_tokens_request,
+            _request_auth=_request_auth,
+            _content_type=_content_type,
+            _headers=_headers,
+            _host_index=_host_index
+        )
+
+        _response_types_map: Dict[str, Optional[str]] = {
+            '200': "CountTokensResponse",
+            '422': "HTTPValidationError",
+        }
+        response_data = self.api_client.call_api(
+            *_param,
+            _request_timeout=_request_timeout
+        )
+        response_data.read()
+        return self.api_client.response_deserialize(
+            response_data=response_data,
+            response_types_map=_response_types_map,
+        ).data
+
+
+    @validate_call
+    def count_message_tokens_v1_messages_count_tokens_post_with_http_info(
+        self,
+        count_tokens_request: CountTokensRequest,
+        _request_timeout: Union[
+            None,
+            Annotated[StrictFloat, Field(gt=0)],
+            Tuple[
+                Annotated[StrictFloat, Field(gt=0)],
+                Annotated[StrictFloat, Field(gt=0)]
+            ]
+        ] = None,
+        _request_auth: Optional[Dict[StrictStr, Any]] = None,
+        _content_type: Optional[StrictStr] = None,
+        _headers: Optional[Dict[StrictStr, Any]] = None,
+        _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0,
+    ) -> ApiResponse[CountTokensResponse]:
+        """Count Message Tokens
+
+        Anthropic ``/v1/messages/count_tokens``-compatible endpoint.  Returns ``{\"input_tokens\": N}`` without contacting an upstream provider: counting is local, so there is no budget reservation, pricing, or usage logging. Authentication mirrors :func:`create_message` — platform mode resolves the caller's token against the platform, standalone mode validates the API key — so the endpoint is not an open token-counting oracle.
+
+        :param count_tokens_request: (required)
+        :type count_tokens_request: CountTokensRequest
+        :param _request_timeout: timeout setting for this request. If one
+                                 number provided, it will be total request
+                                 timeout. It can also be a pair (tuple) of
+                                 (connection, read) timeouts.
+        :type _request_timeout: int, tuple(int, int), optional
+        :param _request_auth: set to override the auth_settings for an a single
+                              request; this effectively ignores the
+                              authentication in the spec for a single request.
+        :type _request_auth: dict, optional
+        :param _content_type: force content-type for the request.
+        :type _content_type: str, Optional
+        :param _headers: set to override the headers for a single
+                         request; this effectively ignores the headers
+                         in the spec for a single request.
+        :type _headers: dict, optional
+        :param _host_index: set to override the host_index for a single
+                            request; this effectively ignores the host_index
+                            in the spec for a single request.
+        :type _host_index: int, optional
+        :return: Returns the result object.
+        """ # noqa: E501
+
+        _param = self._count_message_tokens_v1_messages_count_tokens_post_serialize(
+            count_tokens_request=count_tokens_request,
+            _request_auth=_request_auth,
+            _content_type=_content_type,
+            _headers=_headers,
+            _host_index=_host_index
+        )
+
+        _response_types_map: Dict[str, Optional[str]] = {
+            '200': "CountTokensResponse",
+            '422': "HTTPValidationError",
+        }
+        response_data = self.api_client.call_api(
+            *_param,
+            _request_timeout=_request_timeout
+        )
+        response_data.read()
+        return self.api_client.response_deserialize(
+            response_data=response_data,
+            response_types_map=_response_types_map,
+        )
+
+
+    @validate_call
+    def count_message_tokens_v1_messages_count_tokens_post_without_preload_content(
+        self,
+        count_tokens_request: CountTokensRequest,
+        _request_timeout: Union[
+            None,
+            Annotated[StrictFloat, Field(gt=0)],
+            Tuple[
+                Annotated[StrictFloat, Field(gt=0)],
+                Annotated[StrictFloat, Field(gt=0)]
+            ]
+        ] = None,
+        _request_auth: Optional[Dict[StrictStr, Any]] = None,
+        _content_type: Optional[StrictStr] = None,
+        _headers: Optional[Dict[StrictStr, Any]] = None,
+        _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0,
+    ) -> RESTResponseType:
+        """Count Message Tokens
+
+        Anthropic ``/v1/messages/count_tokens``-compatible endpoint.  Returns ``{\"input_tokens\": N}`` without contacting an upstream provider: counting is local, so there is no budget reservation, pricing, or usage logging. Authentication mirrors :func:`create_message` — platform mode resolves the caller's token against the platform, standalone mode validates the API key — so the endpoint is not an open token-counting oracle.
+
+        :param count_tokens_request: (required)
+        :type count_tokens_request: CountTokensRequest
+        :param _request_timeout: timeout setting for this request. If one
+                                 number provided, it will be total request
+                                 timeout. It can also be a pair (tuple) of
+                                 (connection, read) timeouts.
+        :type _request_timeout: int, tuple(int, int), optional
+        :param _request_auth: set to override the auth_settings for an a single
+                              request; this effectively ignores the
+                              authentication in the spec for a single request.
+        :type _request_auth: dict, optional
+        :param _content_type: force content-type for the request.
+        :type _content_type: str, Optional
+        :param _headers: set to override the headers for a single
+                         request; this effectively ignores the headers
+                         in the spec for a single request.
+        :type _headers: dict, optional
+        :param _host_index: set to override the host_index for a single
+                            request; this effectively ignores the host_index
+                            in the spec for a single request.
+        :type _host_index: int, optional
+        :return: Returns the result object.
+        """ # noqa: E501
+
+        _param = self._count_message_tokens_v1_messages_count_tokens_post_serialize(
+            count_tokens_request=count_tokens_request,
+            _request_auth=_request_auth,
+            _content_type=_content_type,
+            _headers=_headers,
+            _host_index=_host_index
+        )
+
+        _response_types_map: Dict[str, Optional[str]] = {
+            '200': "CountTokensResponse",
+            '422': "HTTPValidationError",
+        }
+        response_data = self.api_client.call_api(
+            *_param,
+            _request_timeout=_request_timeout
+        )
+        return response_data.response
+
+
+    def _count_message_tokens_v1_messages_count_tokens_post_serialize(
+        self,
+        count_tokens_request,
+        _request_auth,
+        _content_type,
+        _headers,
+        _host_index,
+    ) -> RequestSerialized:
+
+        _host = None
+
+        _collection_formats: Dict[str, str] = {
+        }
+
+        _path_params: Dict[str, str] = {}
+        _query_params: List[Tuple[str, str]] = []
+        _header_params: Dict[str, Optional[str]] = _headers or {}
+        _form_params: List[Tuple[str, str]] = []
+        _files: Dict[
+            str, Union[str, bytes, List[str], List[bytes], List[Tuple[str, bytes]]]
+        ] = {}
+        _body_params: Optional[bytes] = None
+
+        # process the path parameters
+        # process the query parameters
+        # process the header parameters
+        # process the form parameters
+        # process the body parameter
+        if count_tokens_request is not None:
+            _body_params = count_tokens_request
+
+
+        # set the HTTP header `Accept`
+        if 'Accept' not in _header_params:
+            _header_params['Accept'] = self.api_client.select_header_accept(
+                [
+                    'application/json'
+                ]
+            )
+
+        # set the HTTP header `Content-Type`
+        if _content_type:
+            _header_params['Content-Type'] = _content_type
+        else:
+            _default_content_type = (
+                self.api_client.select_header_content_type(
+                    [
+                        'application/json'
+                    ]
+                )
+            )
+            if _default_content_type is not None:
+                _header_params['Content-Type'] = _default_content_type
+
+        # authentication setting
+        _auth_settings: List[str] = [
+        ]
+
+        return self.api_client.param_serialize(
+            method='POST',
+            resource_path='/v1/messages/count_tokens',
+            path_params=_path_params,
+            query_params=_query_params,
+            header_params=_header_params,
+            body=_body_params,
+            post_params=_form_params,
+            files=_files,
+            auth_settings=_auth_settings,
+            collection_formats=_collection_formats,
+            _host=_host,
+            _request_auth=_request_auth
+        )
+
+
+
+
     @validate_call
     def create_message_v1_messages_post(
         self,

src/otari/_client/models/__init__.py

@@ -61,6 +61,8 @@
 from otari._client.models.content8 import Content8
 from otari._client.models.content9_inner import Content9Inner
 from otari._client.models.content_any_of_inner import ContentAnyOfInner
+from otari._client.models.count_tokens_request import CountTokensRequest
+from otari._client.models.count_tokens_response import CountTokensResponse
 from otari._client.models.create_batch_request import CreateBatchRequest
 from otari._client.models.create_budget_request import CreateBudgetRequest
 from otari._client.models.create_embedding_response import CreateEmbeddingResponse
@@ -165,6 +167,7 @@
 from otari._client.models.set_pricing_request import SetPricingRequest
 from otari._client.models.source import Source
 from otari._client.models.system import System
+from otari._client.models.system1 import System1
 from otari._client.models.tool_calls_inner import ToolCallsInner
 from otari._client.models.tool_choice import ToolChoice
 from otari._client.models.update_budget_request import UpdateBudgetRequest