scale-gp-beta 0.1.0a6__tar.gz → 0.1.0a8__tar.gz

scale_gp_beta-0.1.0a8/.release-please-manifest.json

@@ -0,0 +1,3 @@
+{
+  ".": "0.1.0-alpha.8"
+}

{scale_gp_beta-0.1.0a6 → scale_gp_beta-0.1.0a8}/CHANGELOG.md

@@ -1,5 +1,28 @@
 # Changelog
 
+## 0.1.0-alpha.8 (2025-03-26)
+
+Full Changelog: [v0.1.0-alpha.7...v0.1.0-alpha.8](https://github.com/scaleapi/sgp-python-beta/compare/v0.1.0-alpha.7...v0.1.0-alpha.8)
+
+### Features
+
+* **api:** manual updates ([#83](https://github.com/scaleapi/sgp-python-beta/issues/83)) ([a742789](https://github.com/scaleapi/sgp-python-beta/commit/a74278982def1c9ce87d1568cc3e6f65c992ec8b))
+* **api:** manual updates ([#85](https://github.com/scaleapi/sgp-python-beta/issues/85)) ([de471f9](https://github.com/scaleapi/sgp-python-beta/commit/de471f973d6dfd512841ec7af8b762da4c1c9ade))
+
+## 0.1.0-alpha.7 (2025-03-26)
+
+Full Changelog: [v0.1.0-alpha.6...v0.1.0-alpha.7](https://github.com/scaleapi/sgp-python-beta/compare/v0.1.0-alpha.6...v0.1.0-alpha.7)
+
+### Features
+
+* **api:** api update ([#78](https://github.com/scaleapi/sgp-python-beta/issues/78)) ([29cfd2f](https://github.com/scaleapi/sgp-python-beta/commit/29cfd2f2eb0cdc8526ea45c382433f52734c393c))
+* **api:** api update ([#81](https://github.com/scaleapi/sgp-python-beta/issues/81)) ([10144d1](https://github.com/scaleapi/sgp-python-beta/commit/10144d14f6fcbafef4725bbcce06b90fc9c74152))
+
+
+### Chores
+
+* fix typos ([#80](https://github.com/scaleapi/sgp-python-beta/issues/80)) ([89f1f30](https://github.com/scaleapi/sgp-python-beta/commit/89f1f30ab410cc5af7f55dfb7e5bfc4a050324a7))
+
 ## 0.1.0-alpha.6 (2025-03-25)
 
 Full Changelog: [v0.1.0-alpha.5...v0.1.0-alpha.6](https://github.com/scaleapi/sgp-python-beta/compare/v0.1.0-alpha.5...v0.1.0-alpha.6)

{scale_gp_beta-0.1.0a6 → scale_gp_beta-0.1.0a8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: scale-gp-beta
-Version: 0.1.0a6
+Version: 0.1.0a8
 Summary: The official Python library for the Scale GP API
 Project-URL: Homepage, https://github.com/scaleapi/sgp-python-beta
 Project-URL: Repository, https://github.com/scaleapi/sgp-python-beta

{scale_gp_beta-0.1.0a6 → scale_gp_beta-0.1.0a8}/api.md

@@ -101,7 +101,7 @@ Methods:
 Types:
 
 ```python
-from scale_gp_beta.types import Evaluation, EvaluationArchiveResponse
+from scale_gp_beta.types import Evaluation, EvaluationTask, EvaluationArchiveResponse
 ```
 
 Methods:

{scale_gp_beta-0.1.0a6 → scale_gp_beta-0.1.0a8}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "scale-gp-beta"
-version = "0.1.0-alpha.6"
+version = "0.1.0-alpha.8"
 description = "The official Python library for the Scale GP API"
 dynamic = ["readme"]
 license = "Apache-2.0"

{scale_gp_beta-0.1.0a6 → scale_gp_beta-0.1.0a8}/src/scale_gp_beta/_models.py

@@ -681,7 +681,7 @@ def set_pydantic_config(typ: Any, config: pydantic.ConfigDict) -> None:
     setattr(typ, "__pydantic_config__", config)  # noqa: B010
 
 
-# our use of subclasssing here causes weirdness for type checkers,
+# our use of subclassing here causes weirdness for type checkers,
 # so we just pretend that we don't subclass
 if TYPE_CHECKING:
     GenericModel = BaseModel

{scale_gp_beta-0.1.0a6 → scale_gp_beta-0.1.0a8}/src/scale_gp_beta/_utils/_transform.py

@@ -126,7 +126,7 @@ def _get_annotated_type(type_: type) -> type | None:
 def _maybe_transform_key(key: str, type_: type) -> str:
     """Transform the given `data` based on the annotations provided in `type_`.
 
-    Note: this function only looks at `Annotated` types that contain `PropertInfo` metadata.
+    Note: this function only looks at `Annotated` types that contain `PropertyInfo` metadata.
     """
     annotated_type = _get_annotated_type(type_)
     if annotated_type is None:

{scale_gp_beta-0.1.0a6 → scale_gp_beta-0.1.0a8}/src/scale_gp_beta/_version.py

@@ -1,4 +1,4 @@
 # File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
 
 __title__ = "scale_gp_beta"
-__version__ = "0.1.0-alpha.6"  # x-release-please-version
+__version__ = "0.1.0-alpha.8"  # x-release-please-version

{scale_gp_beta-0.1.0a6 → scale_gp_beta-0.1.0a8}/src/scale_gp_beta/resources/evaluations.py

@@ -25,6 +25,7 @@ from .._response import (
 from ..pagination import SyncCursorPage, AsyncCursorPage
 from .._base_client import AsyncPaginator, make_request_options
 from ..types.evaluation import Evaluation
+from ..types.evaluation_task_param import EvaluationTaskParam
 from ..types.evaluation_archive_response import EvaluationArchiveResponse
 
 __all__ = ["EvaluationsResource", "AsyncEvaluationsResource"]
@@ -57,7 +58,7 @@ class EvaluationsResource(SyncAPIResource):
         data: Iterable[Dict[str, object]],
         name: str,
         description: str | NotGiven = NOT_GIVEN,
-        tasks: Iterable[evaluation_create_params.EvaluationStandaloneCreateRequestTask] | NotGiven = NOT_GIVEN,
+        tasks: Iterable[EvaluationTaskParam] | NotGiven = NOT_GIVEN,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
         # The extra values given here take precedence over values defined on the client or passed to this method.
         extra_headers: Headers | None = None,
@@ -87,11 +88,11 @@ class EvaluationsResource(SyncAPIResource):
     def create(
         self,
         *,
-        data: Iterable[evaluation_create_params.EvaluationFromDatasetCreateRequestData],
         dataset_id: str,
         name: str,
+        data: Iterable[evaluation_create_params.EvaluationFromDatasetCreateRequestData] | NotGiven = NOT_GIVEN,
         description: str | NotGiven = NOT_GIVEN,
-        tasks: Iterable[evaluation_create_params.EvaluationFromDatasetCreateRequestTask] | NotGiven = NOT_GIVEN,
+        tasks: Iterable[EvaluationTaskParam] | NotGiven = NOT_GIVEN,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
         # The extra values given here take precedence over values defined on the client or passed to this method.
         extra_headers: Headers | None = None,
@@ -103,10 +104,10 @@ class EvaluationsResource(SyncAPIResource):
         Create Evaluation
 
         Args:
-          data: Items to be evaluated, including references to the input dataset items
-
           dataset_id: The ID of the dataset containing the items referenced by the `data` field
 
+          data: Items to be evaluated, including references to the input dataset items
+
           tasks: Tasks allow you to augment and evaluate your data
 
           extra_headers: Send extra headers
@@ -127,7 +128,7 @@ class EvaluationsResource(SyncAPIResource):
         dataset: evaluation_create_params.EvaluationWithDatasetCreateRequestDataset,
         name: str,
         description: str | NotGiven = NOT_GIVEN,
-        tasks: Iterable[evaluation_create_params.EvaluationWithDatasetCreateRequestTask] | NotGiven = NOT_GIVEN,
+        tasks: Iterable[EvaluationTaskParam] | NotGiven = NOT_GIVEN,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
         # The extra values given here take precedence over values defined on the client or passed to this method.
         extra_headers: Headers | None = None,
@@ -155,14 +156,16 @@ class EvaluationsResource(SyncAPIResource):
         """
         ...
 
-    @required_args(["data", "name"], ["data", "dataset_id", "name"], ["data", "dataset", "name"])
+    @required_args(["data", "name"], ["dataset_id", "name"], ["data", "dataset", "name"])
     def create(
         self,
         *,
-        data: Iterable[Dict[str, object]] | Iterable[evaluation_create_params.EvaluationFromDatasetCreateRequestData],
+        data: Iterable[Dict[str, object]]
+        | Iterable[evaluation_create_params.EvaluationFromDatasetCreateRequestData]
+        | NotGiven = NOT_GIVEN,
         name: str,
         description: str | NotGiven = NOT_GIVEN,
-        tasks: Iterable[evaluation_create_params.EvaluationStandaloneCreateRequestTask] | NotGiven = NOT_GIVEN,
+        tasks: Iterable[EvaluationTaskParam] | NotGiven = NOT_GIVEN,
         dataset_id: str | NotGiven = NOT_GIVEN,
         dataset: evaluation_create_params.EvaluationWithDatasetCreateRequestDataset | NotGiven = NOT_GIVEN,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
@@ -339,7 +342,7 @@ class AsyncEvaluationsResource(AsyncAPIResource):
         data: Iterable[Dict[str, object]],
         name: str,
         description: str | NotGiven = NOT_GIVEN,
-        tasks: Iterable[evaluation_create_params.EvaluationStandaloneCreateRequestTask] | NotGiven = NOT_GIVEN,
+        tasks: Iterable[EvaluationTaskParam] | NotGiven = NOT_GIVEN,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
         # The extra values given here take precedence over values defined on the client or passed to this method.
         extra_headers: Headers | None = None,
@@ -369,11 +372,11 @@ class AsyncEvaluationsResource(AsyncAPIResource):
     async def create(
         self,
         *,
-        data: Iterable[evaluation_create_params.EvaluationFromDatasetCreateRequestData],
         dataset_id: str,
         name: str,
+        data: Iterable[evaluation_create_params.EvaluationFromDatasetCreateRequestData] | NotGiven = NOT_GIVEN,
         description: str | NotGiven = NOT_GIVEN,
-        tasks: Iterable[evaluation_create_params.EvaluationFromDatasetCreateRequestTask] | NotGiven = NOT_GIVEN,
+        tasks: Iterable[EvaluationTaskParam] | NotGiven = NOT_GIVEN,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
         # The extra values given here take precedence over values defined on the client or passed to this method.
         extra_headers: Headers | None = None,
@@ -385,10 +388,10 @@ class AsyncEvaluationsResource(AsyncAPIResource):
         Create Evaluation
 
         Args:
-          data: Items to be evaluated, including references to the input dataset items
-
           dataset_id: The ID of the dataset containing the items referenced by the `data` field
 
+          data: Items to be evaluated, including references to the input dataset items
+
           tasks: Tasks allow you to augment and evaluate your data
 
           extra_headers: Send extra headers
@@ -409,7 +412,7 @@ class AsyncEvaluationsResource(AsyncAPIResource):
         dataset: evaluation_create_params.EvaluationWithDatasetCreateRequestDataset,
         name: str,
         description: str | NotGiven = NOT_GIVEN,
-        tasks: Iterable[evaluation_create_params.EvaluationWithDatasetCreateRequestTask] | NotGiven = NOT_GIVEN,
+        tasks: Iterable[EvaluationTaskParam] | NotGiven = NOT_GIVEN,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
         # The extra values given here take precedence over values defined on the client or passed to this method.
         extra_headers: Headers | None = None,
@@ -437,14 +440,16 @@ class AsyncEvaluationsResource(AsyncAPIResource):
         """
         ...
 
-    @required_args(["data", "name"], ["data", "dataset_id", "name"], ["data", "dataset", "name"])
+    @required_args(["data", "name"], ["dataset_id", "name"], ["data", "dataset", "name"])
     async def create(
         self,
         *,
-        data: Iterable[Dict[str, object]] | Iterable[evaluation_create_params.EvaluationFromDatasetCreateRequestData],
+        data: Iterable[Dict[str, object]]
+        | Iterable[evaluation_create_params.EvaluationFromDatasetCreateRequestData]
+        | NotGiven = NOT_GIVEN,
         name: str,
         description: str | NotGiven = NOT_GIVEN,
-        tasks: Iterable[evaluation_create_params.EvaluationStandaloneCreateRequestTask] | NotGiven = NOT_GIVEN,
+        tasks: Iterable[EvaluationTaskParam] | NotGiven = NOT_GIVEN,
         dataset_id: str | NotGiven = NOT_GIVEN,
         dataset: evaluation_create_params.EvaluationWithDatasetCreateRequestDataset | NotGiven = NOT_GIVEN,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.

{scale_gp_beta-0.1.0a6 → scale_gp_beta-0.1.0a8}/src/scale_gp_beta/types/__init__.py

@@ -22,6 +22,7 @@ from .file_delete_response import FileDeleteResponse as FileDeleteResponse
 from .inference_model_list import InferenceModelList as InferenceModelList
 from .dataset_create_params import DatasetCreateParams as DatasetCreateParams
 from .dataset_update_params import DatasetUpdateParams as DatasetUpdateParams
+from .evaluation_task_param import EvaluationTaskParam as EvaluationTaskParam
 from .model_delete_response import ModelDeleteResponse as ModelDeleteResponse
 from .evaluation_list_params import EvaluationListParams as EvaluationListParams
 from .dataset_delete_response import DatasetDeleteResponse as DatasetDeleteResponse

{scale_gp_beta-0.1.0a6 → scale_gp_beta-0.1.0a8}/src/scale_gp_beta/types/chat/chat_completion.py

@@ -10,6 +10,8 @@ __all__ = [
     "ChatCompletion",
     "Choice",
     "ChoiceMessage",
+    "ChoiceMessageAnnotation",
+    "ChoiceMessageAnnotationURLCitation",
     "ChoiceMessageAudio",
     "ChoiceMessageFunctionCall",
     "ChoiceMessageToolCall",
@@ -25,6 +27,34 @@ __all__ = [
 ]
 
 
+class ChoiceMessageAnnotationURLCitation(BaseModel):
+    end_index: int
+
+    start_index: int
+
+    title: str
+
+    url: str
+
+    if TYPE_CHECKING:
+        # Stub to indicate that arbitrary properties are accepted.
+        # To access properties that are not valid identifiers you can use `getattr`, e.g.
+        # `getattr(obj, '$type')`
+        def __getattr__(self, attr: str) -> object: ...
+
+
+class ChoiceMessageAnnotation(BaseModel):
+    type: Literal["url_citation"]
+
+    url_citation: ChoiceMessageAnnotationURLCitation
+
+    if TYPE_CHECKING:
+        # Stub to indicate that arbitrary properties are accepted.
+        # To access properties that are not valid identifiers you can use `getattr`, e.g.
+        # `getattr(obj, '$type')`
+        def __getattr__(self, attr: str) -> object: ...
+
+
 class ChoiceMessageAudio(BaseModel):
     id: str
 
@@ -82,6 +112,8 @@ class ChoiceMessageToolCall(BaseModel):
 class ChoiceMessage(BaseModel):
     role: Literal["assistant"]
 
+    annotations: Optional[List[ChoiceMessageAnnotation]] = None
+
     audio: Optional[ChoiceMessageAudio] = None
 
     content: Optional[str] = None

{scale_gp_beta-0.1.0a6 → scale_gp_beta-0.1.0a8}/src/scale_gp_beta/types/chat/chat_completion_chunk.py

@@ -71,7 +71,7 @@ class ChoiceDelta(BaseModel):
 
     refusal: Optional[str] = None
 
-    role: Optional[Literal["system", "user", "assistant", "tool"]] = None
+    role: Optional[Literal["developer", "system", "user", "assistant", "tool"]] = None
 
     tool_calls: Optional[List[ChoiceDeltaToolCall]] = None
 

scale_gp_beta-0.1.0a8/src/scale_gp_beta/types/evaluation_create_params.py

@@ -0,0 +1,85 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Dict, List, Union, Iterable
+from typing_extensions import Required, TypeAlias, TypedDict
+
+from .evaluation_task_param import EvaluationTaskParam
+
+__all__ = [
+    "EvaluationCreateParams",
+    "EvaluationStandaloneCreateRequest",
+    "EvaluationFromDatasetCreateRequest",
+    "EvaluationFromDatasetCreateRequestData",
+    "EvaluationWithDatasetCreateRequest",
+    "EvaluationWithDatasetCreateRequestDataset",
+]
+
+
+class EvaluationStandaloneCreateRequest(TypedDict, total=False):
+    data: Required[Iterable[Dict[str, object]]]
+    """Items to be evaluated"""
+
+    name: Required[str]
+
+    description: str
+
+    tasks: Iterable[EvaluationTaskParam]
+    """Tasks allow you to augment and evaluate your data"""
+
+
+class EvaluationFromDatasetCreateRequest(TypedDict, total=False):
+    dataset_id: Required[str]
+    """The ID of the dataset containing the items referenced by the `data` field"""
+
+    name: Required[str]
+
+    data: Iterable[EvaluationFromDatasetCreateRequestData]
+    """Items to be evaluated, including references to the input dataset items"""
+
+    description: str
+
+    tasks: Iterable[EvaluationTaskParam]
+    """Tasks allow you to augment and evaluate your data"""
+
+
+class EvaluationFromDatasetCreateRequestDataTyped(TypedDict, total=False):
+    dataset_item_id: Required[str]
+
+
+EvaluationFromDatasetCreateRequestData: TypeAlias = Union[
+    EvaluationFromDatasetCreateRequestDataTyped, Dict[str, object]
+]
+
+
+class EvaluationWithDatasetCreateRequest(TypedDict, total=False):
+    data: Required[Iterable[Dict[str, object]]]
+    """Items to be evaluated"""
+
+    dataset: Required[EvaluationWithDatasetCreateRequestDataset]
+    """Create a reusable dataset from items in the `data` field"""
+
+    name: Required[str]
+
+    description: str
+
+    tasks: Iterable[EvaluationTaskParam]
+    """Tasks allow you to augment and evaluate your data"""
+
+
+class EvaluationWithDatasetCreateRequestDataset(TypedDict, total=False):
+    name: Required[str]
+
+    description: str
+
+    keys: List[str]
+    """Keys from items in the `data` field that should be included in the dataset.
+
+    If not provided, all keys will be included.
+    """
+
+
+EvaluationCreateParams: TypeAlias = Union[
+    EvaluationStandaloneCreateRequest, EvaluationFromDatasetCreateRequest, EvaluationWithDatasetCreateRequest
+]

scale_gp_beta-0.1.0a8/src/scale_gp_beta/types/evaluation_task_param.py

@@ -0,0 +1,212 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Dict, List, Union, Iterable
+from typing_extensions import Literal, Required, TypeAlias, TypedDict
+
+__all__ = [
+    "EvaluationTaskParam",
+    "ChatCompletionEvaluationTaskRequest",
+    "ChatCompletionEvaluationTaskRequestConfiguration",
+    "GenericInferenceEvaluationTaskRequest",
+    "GenericInferenceEvaluationTaskRequestConfiguration",
+    "GenericInferenceEvaluationTaskRequestConfigurationInferenceConfiguration",
+    "GenericInferenceEvaluationTaskRequestConfigurationInferenceConfigurationLaunchInferenceConfiguration",
+    "ApplicationVariantV1EvaluationTaskRequest",
+    "ApplicationVariantV1EvaluationTaskRequestConfiguration",
+    "ApplicationVariantV1EvaluationTaskRequestConfigurationHistoryUnionMember0",
+    "ApplicationVariantV1EvaluationTaskRequestConfigurationOverrides",
+    "ApplicationVariantV1EvaluationTaskRequestConfigurationOverridesAgenticApplicationOverrides",
+    "ApplicationVariantV1EvaluationTaskRequestConfigurationOverridesAgenticApplicationOverridesInitialState",
+    "ApplicationVariantV1EvaluationTaskRequestConfigurationOverridesAgenticApplicationOverridesPartialTrace",
+]
+
+
+class ChatCompletionEvaluationTaskRequestConfigurationTyped(TypedDict, total=False):
+    messages: Required[Union[Iterable[Dict[str, object]], str]]
+
+    model: Required[str]
+
+    audio: Union[Dict[str, object], str]
+
+    frequency_penalty: Union[float, str]
+
+    function_call: Union[Dict[str, object], str]
+
+    functions: Union[Iterable[Dict[str, object]], str]
+
+    logit_bias: Union[Dict[str, int], str]
+
+    logprobs: Union[bool, str]
+
+    max_completion_tokens: Union[int, str]
+
+    max_tokens: Union[int, str]
+
+    metadata: Union[Dict[str, str], str]
+
+    modalities: Union[List[str], str]
+
+    n: Union[int, str]
+
+    parallel_tool_calls: Union[bool, str]
+
+    prediction: Union[Dict[str, object], str]
+
+    presence_penalty: Union[float, str]
+
+    reasoning_effort: str
+
+    response_format: Union[Dict[str, object], str]
+
+    seed: Union[int, str]
+
+    stop: str
+
+    store: Union[bool, str]
+
+    temperature: Union[float, str]
+
+    tool_choice: str
+
+    tools: Union[Iterable[Dict[str, object]], str]
+
+    top_k: Union[int, str]
+
+    top_logprobs: Union[int, str]
+
+    top_p: Union[float, str]
+
+
+ChatCompletionEvaluationTaskRequestConfiguration: TypeAlias = Union[
+    ChatCompletionEvaluationTaskRequestConfigurationTyped, Dict[str, object]
+]
+
+
+class ChatCompletionEvaluationTaskRequest(TypedDict, total=False):
+    configuration: Required[ChatCompletionEvaluationTaskRequestConfiguration]
+
+    alias: str
+    """Alias to title the results column. Defaults to the `task_type`"""
+
+    task_type: Literal["chat_completion"]
+
+
+class GenericInferenceEvaluationTaskRequestConfigurationInferenceConfigurationLaunchInferenceConfiguration(
+    TypedDict, total=False
+):
+    num_retries: int
+
+    timeout_seconds: int
+
+
+GenericInferenceEvaluationTaskRequestConfigurationInferenceConfiguration: TypeAlias = Union[
+    GenericInferenceEvaluationTaskRequestConfigurationInferenceConfigurationLaunchInferenceConfiguration, str
+]
+
+
+class GenericInferenceEvaluationTaskRequestConfiguration(TypedDict, total=False):
+    model: Required[str]
+
+    args: Union[Dict[str, object], str]
+
+    inference_configuration: GenericInferenceEvaluationTaskRequestConfigurationInferenceConfiguration
+
+
+class GenericInferenceEvaluationTaskRequest(TypedDict, total=False):
+    configuration: Required[GenericInferenceEvaluationTaskRequestConfiguration]
+
+    alias: str
+    """Alias to title the results column. Defaults to the `task_type`"""
+
+    task_type: Literal["inference"]
+
+
+class ApplicationVariantV1EvaluationTaskRequestConfigurationHistoryUnionMember0(TypedDict, total=False):
+    request: Required[str]
+    """Request inputs"""
+
+    response: Required[str]
+    """Response outputs"""
+
+    session_data: Dict[str, object]
+    """Session data corresponding to the request response pair"""
+
+
+class ApplicationVariantV1EvaluationTaskRequestConfigurationOverridesAgenticApplicationOverridesInitialState(
+    TypedDict, total=False
+):
+    current_node: Required[str]
+
+    state: Required[Dict[str, object]]
+
+
+class ApplicationVariantV1EvaluationTaskRequestConfigurationOverridesAgenticApplicationOverridesPartialTrace(
+    TypedDict, total=False
+):
+    duration_ms: Required[int]
+
+    node_id: Required[str]
+
+    operation_input: Required[str]
+
+    operation_output: Required[str]
+
+    operation_type: Required[str]
+
+    start_timestamp: Required[str]
+
+    workflow_id: Required[str]
+
+    operation_metadata: Dict[str, object]
+
+
+class ApplicationVariantV1EvaluationTaskRequestConfigurationOverridesAgenticApplicationOverrides(
+    TypedDict, total=False
+):
+    concurrent: bool
+
+    initial_state: (
+        ApplicationVariantV1EvaluationTaskRequestConfigurationOverridesAgenticApplicationOverridesInitialState
+    )
+
+    partial_trace: Iterable[
+        ApplicationVariantV1EvaluationTaskRequestConfigurationOverridesAgenticApplicationOverridesPartialTrace
+    ]
+
+    use_channels: bool
+
+
+ApplicationVariantV1EvaluationTaskRequestConfigurationOverrides: TypeAlias = Union[
+    ApplicationVariantV1EvaluationTaskRequestConfigurationOverridesAgenticApplicationOverrides, str
+]
+
+
+class ApplicationVariantV1EvaluationTaskRequestConfiguration(TypedDict, total=False):
+    application_variant_id: Required[str]
+
+    inputs: Required[Union[Dict[str, object], str]]
+
+    history: Union[Iterable[ApplicationVariantV1EvaluationTaskRequestConfigurationHistoryUnionMember0], str]
+
+    operation_metadata: Union[Dict[str, object], str]
+
+    overrides: ApplicationVariantV1EvaluationTaskRequestConfigurationOverrides
+    """Execution override options for agentic applications"""
+
+
+class ApplicationVariantV1EvaluationTaskRequest(TypedDict, total=False):
+    configuration: Required[ApplicationVariantV1EvaluationTaskRequestConfiguration]
+
+    alias: str
+    """Alias to title the results column. Defaults to the `task_type`"""
+
+    task_type: Literal["application_variant"]
+
+
+EvaluationTaskParam: TypeAlias = Union[
+    ChatCompletionEvaluationTaskRequest,
+    GenericInferenceEvaluationTaskRequest,
+    ApplicationVariantV1EvaluationTaskRequest,
+]

{scale_gp_beta-0.1.0a6 → scale_gp_beta-0.1.0a8}/tests/api_resources/test_evaluations.py

@@ -102,7 +102,6 @@ class TestEvaluations:
     @parametrize
     def test_method_create_overload_2(self, client: SGPClient) -> None:
         evaluation = client.evaluations.create(
-            data=[{"dataset_item_id": "dataset_item_id"}],
             dataset_id="dataset_id",
             name="name",
         )
@@ -111,9 +110,9 @@ class TestEvaluations:
     @parametrize
     def test_method_create_with_all_params_overload_2(self, client: SGPClient) -> None:
         evaluation = client.evaluations.create(
-            data=[{"dataset_item_id": "dataset_item_id"}],
             dataset_id="dataset_id",
             name="name",
+            data=[{"dataset_item_id": "dataset_item_id"}],
             description="description",
             tasks=[
                 {
@@ -156,7 +155,6 @@ class TestEvaluations:
     @parametrize
     def test_raw_response_create_overload_2(self, client: SGPClient) -> None:
         response = client.evaluations.with_raw_response.create(
-            data=[{"dataset_item_id": "dataset_item_id"}],
             dataset_id="dataset_id",
             name="name",
         )
@@ -169,7 +167,6 @@ class TestEvaluations:
     @parametrize
     def test_streaming_response_create_overload_2(self, client: SGPClient) -> None:
         with client.evaluations.with_streaming_response.create(
-            data=[{"dataset_item_id": "dataset_item_id"}],
             dataset_id="dataset_id",
             name="name",
         ) as response:
@@ -471,7 +468,6 @@ class TestAsyncEvaluations:
     @parametrize
     async def test_method_create_overload_2(self, async_client: AsyncSGPClient) -> None:
         evaluation = await async_client.evaluations.create(
-            data=[{"dataset_item_id": "dataset_item_id"}],
             dataset_id="dataset_id",
             name="name",
         )
@@ -480,9 +476,9 @@ class TestAsyncEvaluations:
     @parametrize
     async def test_method_create_with_all_params_overload_2(self, async_client: AsyncSGPClient) -> None:
         evaluation = await async_client.evaluations.create(
-            data=[{"dataset_item_id": "dataset_item_id"}],
             dataset_id="dataset_id",
             name="name",
+            data=[{"dataset_item_id": "dataset_item_id"}],
             description="description",
             tasks=[
                 {
@@ -525,7 +521,6 @@ class TestAsyncEvaluations:
     @parametrize
     async def test_raw_response_create_overload_2(self, async_client: AsyncSGPClient) -> None:
         response = await async_client.evaluations.with_raw_response.create(
-            data=[{"dataset_item_id": "dataset_item_id"}],
             dataset_id="dataset_id",
             name="name",
         )
@@ -538,7 +533,6 @@ class TestAsyncEvaluations:
     @parametrize
     async def test_streaming_response_create_overload_2(self, async_client: AsyncSGPClient) -> None:
         async with async_client.evaluations.with_streaming_response.create(
-            data=[{"dataset_item_id": "dataset_item_id"}],
             dataset_id="dataset_id",
             name="name",
         ) as response:

scale_gp_beta-0.1.0a6/.release-please-manifest.json

@@ -1,3 +0,0 @@
-{
-  ".": "0.1.0-alpha.6"
-}