scale-gp-beta 0.1.0a32__py3-none-any.whl → 0.1.0a34__py3-none-any.whl

scale_gp_beta/resources/spans.py

@@ -256,10 +256,13 @@ class SpansResource(SyncAPIResource):
         starting_after: str | Omit = omit,
         to_ts: Union[str, datetime] | Omit = omit,
         application_variant_ids: SequenceNotStr[str] | Omit = omit,
+        assessment_types: SequenceNotStr[str] | Omit = omit,
         excluded_span_ids: SequenceNotStr[str] | Omit = omit,
         excluded_trace_ids: SequenceNotStr[str] | Omit = omit,
         extra_metadata: Dict[str, object] | Omit = omit,
         group_id: str | Omit = omit,
+        max_duration_ms: int | Omit = omit,
+        min_duration_ms: int | Omit = omit,
         names: SequenceNotStr[str] | Omit = omit,
         parents_only: bool | Omit = omit,
         search_texts: SequenceNotStr[str] | Omit = omit,
@@ -284,6 +287,8 @@ class SpansResource(SyncAPIResource):
 
           application_variant_ids: Filter by application variant IDs
 
+          assessment_types: Filter spans by traces that have assessments of these types
+
           excluded_span_ids: List of span IDs to exclude from results
 
           excluded_trace_ids: List of trace IDs to exclude from results
@@ -292,6 +297,10 @@ class SpansResource(SyncAPIResource):
 
           group_id: Filter by group ID
 
+          max_duration_ms: Maximum span duration in milliseconds (inclusive)
+
+          min_duration_ms: Minimum span duration in milliseconds (inclusive)
+
           names: Filter by trace/span name
 
           parents_only: Only fetch spans that are the top-level (ie. have no parent_id)
@@ -318,10 +327,13 @@ class SpansResource(SyncAPIResource):
             body=maybe_transform(
                 {
                     "application_variant_ids": application_variant_ids,
+                    "assessment_types": assessment_types,
                     "excluded_span_ids": excluded_span_ids,
                     "excluded_trace_ids": excluded_trace_ids,
                     "extra_metadata": extra_metadata,
                     "group_id": group_id,
+                    "max_duration_ms": max_duration_ms,
+                    "min_duration_ms": min_duration_ms,
                     "names": names,
                     "parents_only": parents_only,
                     "search_texts": search_texts,
@@ -604,10 +616,13 @@ class AsyncSpansResource(AsyncAPIResource):
         starting_after: str | Omit = omit,
         to_ts: Union[str, datetime] | Omit = omit,
         application_variant_ids: SequenceNotStr[str] | Omit = omit,
+        assessment_types: SequenceNotStr[str] | Omit = omit,
         excluded_span_ids: SequenceNotStr[str] | Omit = omit,
         excluded_trace_ids: SequenceNotStr[str] | Omit = omit,
         extra_metadata: Dict[str, object] | Omit = omit,
         group_id: str | Omit = omit,
+        max_duration_ms: int | Omit = omit,
+        min_duration_ms: int | Omit = omit,
         names: SequenceNotStr[str] | Omit = omit,
         parents_only: bool | Omit = omit,
         search_texts: SequenceNotStr[str] | Omit = omit,
@@ -632,6 +647,8 @@ class AsyncSpansResource(AsyncAPIResource):
 
           application_variant_ids: Filter by application variant IDs
 
+          assessment_types: Filter spans by traces that have assessments of these types
+
           excluded_span_ids: List of span IDs to exclude from results
 
           excluded_trace_ids: List of trace IDs to exclude from results
@@ -640,6 +657,10 @@ class AsyncSpansResource(AsyncAPIResource):
 
           group_id: Filter by group ID
 
+          max_duration_ms: Maximum span duration in milliseconds (inclusive)
+
+          min_duration_ms: Minimum span duration in milliseconds (inclusive)
+
           names: Filter by trace/span name
 
           parents_only: Only fetch spans that are the top-level (ie. have no parent_id)
@@ -666,10 +687,13 @@ class AsyncSpansResource(AsyncAPIResource):
             body=maybe_transform(
                 {
                     "application_variant_ids": application_variant_ids,
+                    "assessment_types": assessment_types,
                     "excluded_span_ids": excluded_span_ids,
                     "excluded_trace_ids": excluded_trace_ids,
                     "extra_metadata": extra_metadata,
                     "group_id": group_id,
+                    "max_duration_ms": max_duration_ms,
+                    "min_duration_ms": min_duration_ms,
                     "names": names,
                     "parents_only": parents_only,
                     "search_texts": search_texts,

scale_gp_beta/types/__init__.py

@@ -12,20 +12,23 @@ from .question import Question as Question
 from .response import Response as Response
 from .component import Component as Component
 from .container import Container as Container
-from .file_list import FileList as FileList
 from .span_type import SpanType as SpanType
 from .completion import Completion as Completion
+from .credential import Credential as Credential
 from .evaluation import Evaluation as Evaluation
 from .span_status import SpanStatus as SpanStatus
 from .dataset_item import DatasetItem as DatasetItem
 from .item_locator import ItemLocator as ItemLocator
-from .question_list import QuestionList as QuestionList
+from .approval_status import ApprovalStatus as ApprovalStatus
+from .assessment_type import AssessmentType as AssessmentType
 from .component_param import ComponentParam as ComponentParam
 from .container_param import ContainerParam as ContainerParam
 from .evaluation_item import EvaluationItem as EvaluationItem
 from .evaluation_task import EvaluationTask as EvaluationTask
 from .inference_model import InferenceModel as InferenceModel
+from .span_assessment import SpanAssessment as SpanAssessment
 from .file_list_params import FileListParams as FileListParams
+from .credential_secret import CredentialSecret as CredentialSecret
 from .model_list_params import ModelListParams as ModelListParams
 from .span_batch_params import SpanBatchParams as SpanBatchParams
 from .file_create_params import FileCreateParams as FileCreateParams
@@ -39,13 +42,13 @@ from .model_create_params import ModelCreateParams as ModelCreateParams
 from .model_update_params import ModelUpdateParams as ModelUpdateParams
 from .span_batch_response import SpanBatchResponse as SpanBatchResponse
 from .file_delete_response import FileDeleteResponse as FileDeleteResponse
-from .inference_model_list import InferenceModelList as InferenceModelList
 from .question_list_params import QuestionListParams as QuestionListParams
 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 .item_locator_template import ItemLocatorTemplate as ItemLocatorTemplate
 from .model_delete_response import ModelDeleteResponse as ModelDeleteResponse
+from .credential_list_params import CredentialListParams as CredentialListParams
 from .evaluation_list_params import EvaluationListParams as EvaluationListParams
 from .question_create_params import QuestionCreateParams as QuestionCreateParams
 from .response_create_params import ResponseCreateParams as ResponseCreateParams
@@ -53,6 +56,8 @@ from .dataset_delete_response import DatasetDeleteResponse as DatasetDeleteRespo
 from .dataset_retrieve_params import DatasetRetrieveParams as DatasetRetrieveParams
 from .inference_create_params import InferenceCreateParams as InferenceCreateParams
 from .completion_create_params import CompletionCreateParams as CompletionCreateParams
+from .credential_create_params import CredentialCreateParams as CredentialCreateParams
+from .credential_update_params import CredentialUpdateParams as CredentialUpdateParams
 from .dataset_item_list_params import DatasetItemListParams as DatasetItemListParams
 from .evaluation_create_params import EvaluationCreateParams as EvaluationCreateParams
 from .evaluation_update_params import EvaluationUpdateParams as EvaluationUpdateParams
@@ -60,14 +65,18 @@ from .inference_response_chunk import InferenceResponseChunk as InferenceRespons
 from .response_create_response import ResponseCreateResponse as ResponseCreateResponse
 from .span_upsert_batch_params import SpanUpsertBatchParams as SpanUpsertBatchParams
 from .inference_create_response import InferenceCreateResponse as InferenceCreateResponse
+from .credential_delete_response import CredentialDeleteResponse as CredentialDeleteResponse
 from .dataset_item_update_params import DatasetItemUpdateParams as DatasetItemUpdateParams
-from .evaluation_delete_response import EvaluationDeleteResponse as EvaluationDeleteResponse
 from .evaluation_retrieve_params import EvaluationRetrieveParams as EvaluationRetrieveParams
 from .span_upsert_batch_response import SpanUpsertBatchResponse as SpanUpsertBatchResponse
 from .evaluation_item_list_params import EvaluationItemListParams as EvaluationItemListParams
+from .span_assessment_list_params import SpanAssessmentListParams as SpanAssessmentListParams
 from .dataset_item_delete_response import DatasetItemDeleteResponse as DatasetItemDeleteResponse
 from .dataset_item_retrieve_params import DatasetItemRetrieveParams as DatasetItemRetrieveParams
+from .span_assessment_create_params import SpanAssessmentCreateParams as SpanAssessmentCreateParams
+from .span_assessment_update_params import SpanAssessmentUpdateParams as SpanAssessmentUpdateParams
 from .evaluation_item_retrieve_params import EvaluationItemRetrieveParams as EvaluationItemRetrieveParams
+from .span_assessment_delete_response import SpanAssessmentDeleteResponse as SpanAssessmentDeleteResponse
 from .dataset_item_batch_create_params import DatasetItemBatchCreateParams as DatasetItemBatchCreateParams
 from .dataset_item_batch_create_response import DatasetItemBatchCreateResponse as DatasetItemBatchCreateResponse
 

scale_gp_beta/types/approval_status.py

@@ -0,0 +1,7 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing_extensions import Literal, TypeAlias
+
+__all__ = ["ApprovalStatus"]
+
+ApprovalStatus: TypeAlias = Literal["approved", "rejected"]

scale_gp_beta/types/assessment_type.py

@@ -0,0 +1,7 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing_extensions import Literal, TypeAlias
+
+__all__ = ["AssessmentType"]
+
+AssessmentType: TypeAlias = Literal["comment", "rating", "approval", "rubric", "metadata", "overwrite"]

scale_gp_beta/types/credential.py

@@ -0,0 +1,30 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing import Dict, Optional
+from datetime import datetime
+
+from .._models import BaseModel
+
+__all__ = ["Credential"]
+
+
+class Credential(BaseModel):
+    id: str
+
+    created_at: datetime
+
+    created_by_identity_type: str
+
+    created_by_user_id: str
+
+    credential_metadata: Dict[str, object]
+
+    description: str
+
+    name: str
+
+    type: str
+
+    updated_at: datetime
+
+    object: Optional[str] = None

scale_gp_beta/types/credential_create_params.py

@@ -0,0 +1,25 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Dict
+from typing_extensions import Required, TypedDict
+
+__all__ = ["CredentialCreateParams"]
+
+
+class CredentialCreateParams(TypedDict, total=False):
+    name: Required[str]
+    """User-friendly name for the credential"""
+
+    payload: Required[str]
+    """The credential payload to be encrypted"""
+
+    type: Required[str]
+    """Type of credential: key or json"""
+
+    credential_metadata: Dict[str, object]
+    """Optional unencrypted credential_metadata"""
+
+    description: str
+    """Optional description"""

scale_gp_beta/types/credential_delete_response.py

@@ -0,0 +1,13 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from .._models import BaseModel
+
+__all__ = ["CredentialDeleteResponse"]
+
+
+class CredentialDeleteResponse(BaseModel):
+    id: str
+
+    deleted: bool
+
+    object: str

scale_gp_beta/types/credential_list_params.py

@@ -0,0 +1,20 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing_extensions import Literal, TypedDict
+
+__all__ = ["CredentialListParams"]
+
+
+class CredentialListParams(TypedDict, total=False):
+    ending_before: str
+
+    limit: int
+
+    name: str
+    """Filter credentials by name"""
+
+    sort_order: Literal["asc", "desc"]
+
+    starting_after: str

scale_gp_beta/types/credential_secret.py

@@ -0,0 +1,13 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing import Optional
+
+from .._models import BaseModel
+
+__all__ = ["CredentialSecret"]
+
+
+class CredentialSecret(BaseModel):
+    result: str
+
+    object: Optional[str] = None

scale_gp_beta/types/credential_update_params.py

@@ -0,0 +1,25 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Dict
+from typing_extensions import TypedDict
+
+__all__ = ["CredentialUpdateParams"]
+
+
+class CredentialUpdateParams(TypedDict, total=False):
+    credential_metadata: Dict[str, object]
+    """Optional unencrypted credential_metadata"""
+
+    description: str
+    """Optional description"""
+
+    name: str
+    """User-friendly name for the credential"""
+
+    payload: str
+    """The credential payload to be encrypted"""
+
+    type: str
+    """Type of credential: key or json"""

scale_gp_beta/types/dataset_delete_response.py

@@ -1,8 +1,5 @@
 # File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
 
-from typing import Optional
-from typing_extensions import Literal
-
 from .._models import BaseModel
 
 __all__ = ["DatasetDeleteResponse"]
@@ -13,4 +10,4 @@ class DatasetDeleteResponse(BaseModel):
 
     deleted: bool
 
-    object: Optional[Literal["dataset"]] = None
+    object: str

scale_gp_beta/types/dataset_item_delete_response.py

@@ -1,8 +1,5 @@
 # File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
 
-from typing import Optional
-from typing_extensions import Literal
-
 from .._models import BaseModel
 
 __all__ = ["DatasetItemDeleteResponse"]
@@ -13,4 +10,4 @@ class DatasetItemDeleteResponse(BaseModel):
 
     deleted: bool
 
-    object: Optional[Literal["dataset.item"]] = None
+    object: str

scale_gp_beta/types/evaluation_create_params.py

@@ -42,7 +42,7 @@ class EvaluationFromDatasetCreateRequest(TypedDict, total=False):
     name: Required[str]
 
     data: Iterable[EvaluationFromDatasetCreateRequestData]
-    """Items to be evaluated, including references to the input dataset items"""
+    """Items to be evaluated, including references to the input dataset"""
 
     description: str
 

scale_gp_beta/types/evaluation_task.py

@@ -41,6 +41,27 @@ __all__ = [
     "AutoEvaluationGuidedDecodingEvaluationTaskConfiguration",
     "AutoEvaluationGuidedDecodingEvaluationTaskConfigurationAutoEvaluationStructuredOutputTaskRequestWithItemLocator",
     "AutoEvaluationGuidedDecodingEvaluationTaskConfigurationAutoEvaluationGuidedDecodingTaskRequestWithItemLocator",
+    "AutoEvaluationGuidedDecodingEvaluationTaskConfigurationAutoEvaluationAgentTaskRequestWithItemLocator",
+    "AutoEvaluationGuidedDecodingEvaluationTaskConfigurationAutoEvaluationAgentTaskRequestWithItemLocatorDesignatedTo",
+    "AutoEvaluationGuidedDecodingEvaluationTaskConfigurationAutoEvaluationAgentTaskRequestWithItemLocatorDesignatedToApeAgent",
+    "AutoEvaluationGuidedDecodingEvaluationTaskConfigurationAutoEvaluationAgentTaskRequestWithItemLocatorDesignatedToApeAgentConfig",
+    "AutoEvaluationGuidedDecodingEvaluationTaskConfigurationAutoEvaluationAgentTaskRequestWithItemLocatorDesignatedToIfAgent",
+    "AutoEvaluationGuidedDecodingEvaluationTaskConfigurationAutoEvaluationAgentTaskRequestWithItemLocatorDesignatedToIfAgentConfig",
+    "AutoEvaluationGuidedDecodingEvaluationTaskConfigurationAutoEvaluationAgentTaskRequestWithItemLocatorDesignatedToTruthfulnessAgent",
+    "AutoEvaluationGuidedDecodingEvaluationTaskConfigurationAutoEvaluationAgentTaskRequestWithItemLocatorDesignatedToTruthfulnessAgentConfig",
+    "AutoEvaluationGuidedDecodingEvaluationTaskConfigurationAutoEvaluationAgentTaskRequestWithItemLocatorDesignatedToBaseAgent",
+    "AutoEvaluationGuidedDecodingEvaluationTaskConfigurationAutoEvaluationAgentTaskRequestWithItemLocatorDesignatedToBaseAgentConfig",
+    "AutoEvaluationAgentEvaluationTask",
+    "AutoEvaluationAgentEvaluationTaskConfiguration",
+    "AutoEvaluationAgentEvaluationTaskConfigurationDesignatedTo",
+    "AutoEvaluationAgentEvaluationTaskConfigurationDesignatedToApeAgent",
+    "AutoEvaluationAgentEvaluationTaskConfigurationDesignatedToApeAgentConfig",
+    "AutoEvaluationAgentEvaluationTaskConfigurationDesignatedToIfAgent",
+    "AutoEvaluationAgentEvaluationTaskConfigurationDesignatedToIfAgentConfig",
+    "AutoEvaluationAgentEvaluationTaskConfigurationDesignatedToTruthfulnessAgent",
+    "AutoEvaluationAgentEvaluationTaskConfigurationDesignatedToTruthfulnessAgentConfig",
+    "AutoEvaluationAgentEvaluationTaskConfigurationDesignatedToBaseAgent",
+    "AutoEvaluationAgentEvaluationTaskConfigurationDesignatedToBaseAgentConfig",
     "ContributorEvaluationQuestionTask",
     "ContributorEvaluationQuestionTaskConfiguration",
 ]
@@ -368,9 +389,94 @@ class AutoEvaluationGuidedDecodingEvaluationTaskConfigurationAutoEvaluationGuide
     system_prompt: Optional[str] = None
 
 
+class AutoEvaluationGuidedDecodingEvaluationTaskConfigurationAutoEvaluationAgentTaskRequestWithItemLocatorDesignatedToApeAgentConfig(
+    BaseModel
+):
+    model: Optional[str] = None
+
+    temperature: Optional[float] = None
+
+
+class AutoEvaluationGuidedDecodingEvaluationTaskConfigurationAutoEvaluationAgentTaskRequestWithItemLocatorDesignatedToApeAgent(
+    BaseModel
+):
+    config: AutoEvaluationGuidedDecodingEvaluationTaskConfigurationAutoEvaluationAgentTaskRequestWithItemLocatorDesignatedToApeAgentConfig
+
+    agent_name: Optional[Literal["APEAgent"]] = None
+
+
+class AutoEvaluationGuidedDecodingEvaluationTaskConfigurationAutoEvaluationAgentTaskRequestWithItemLocatorDesignatedToIfAgentConfig(
+    BaseModel
+):
+    model: Optional[str] = None
+
+
+class AutoEvaluationGuidedDecodingEvaluationTaskConfigurationAutoEvaluationAgentTaskRequestWithItemLocatorDesignatedToIfAgent(
+    BaseModel
+):
+    config: AutoEvaluationGuidedDecodingEvaluationTaskConfigurationAutoEvaluationAgentTaskRequestWithItemLocatorDesignatedToIfAgentConfig
+
+    agent_name: Optional[Literal["IFAgent"]] = None
+
+
+class AutoEvaluationGuidedDecodingEvaluationTaskConfigurationAutoEvaluationAgentTaskRequestWithItemLocatorDesignatedToTruthfulnessAgentConfig(
+    BaseModel
+):
+    model: Optional[str] = None
+
+
+class AutoEvaluationGuidedDecodingEvaluationTaskConfigurationAutoEvaluationAgentTaskRequestWithItemLocatorDesignatedToTruthfulnessAgent(
+    BaseModel
+):
+    config: AutoEvaluationGuidedDecodingEvaluationTaskConfigurationAutoEvaluationAgentTaskRequestWithItemLocatorDesignatedToTruthfulnessAgentConfig
+
+    agent_name: Optional[Literal["TruthfulnessAgent"]] = None
+
+
+class AutoEvaluationGuidedDecodingEvaluationTaskConfigurationAutoEvaluationAgentTaskRequestWithItemLocatorDesignatedToBaseAgentConfig(
+    BaseModel
+):
+    model: Optional[str] = None
+
+
+class AutoEvaluationGuidedDecodingEvaluationTaskConfigurationAutoEvaluationAgentTaskRequestWithItemLocatorDesignatedToBaseAgent(
+    BaseModel
+):
+    config: AutoEvaluationGuidedDecodingEvaluationTaskConfigurationAutoEvaluationAgentTaskRequestWithItemLocatorDesignatedToBaseAgentConfig
+
+    agent_name: Optional[Literal["BaseAgent"]] = None
+
+
+AutoEvaluationGuidedDecodingEvaluationTaskConfigurationAutoEvaluationAgentTaskRequestWithItemLocatorDesignatedTo: TypeAlias = Union[
+    AutoEvaluationGuidedDecodingEvaluationTaskConfigurationAutoEvaluationAgentTaskRequestWithItemLocatorDesignatedToApeAgent,
+    AutoEvaluationGuidedDecodingEvaluationTaskConfigurationAutoEvaluationAgentTaskRequestWithItemLocatorDesignatedToIfAgent,
+    AutoEvaluationGuidedDecodingEvaluationTaskConfigurationAutoEvaluationAgentTaskRequestWithItemLocatorDesignatedToTruthfulnessAgent,
+    AutoEvaluationGuidedDecodingEvaluationTaskConfigurationAutoEvaluationAgentTaskRequestWithItemLocatorDesignatedToBaseAgent,
+]
+
+
+class AutoEvaluationGuidedDecodingEvaluationTaskConfigurationAutoEvaluationAgentTaskRequestWithItemLocator(BaseModel):
+    definition: str
+
+    name: str
+
+    output_rules: List[str]
+
+    data_fields: Optional[List[str]] = None
+
+    designated_to: Optional[
+        AutoEvaluationGuidedDecodingEvaluationTaskConfigurationAutoEvaluationAgentTaskRequestWithItemLocatorDesignatedTo
+    ] = None
+
+    output_type: Optional[Literal["text", "integer", "float", "boolean"]] = None
+
+    output_values: Optional[List[Union[str, float, bool]]] = None
+
+
 AutoEvaluationGuidedDecodingEvaluationTaskConfiguration: TypeAlias = Union[
     AutoEvaluationGuidedDecodingEvaluationTaskConfigurationAutoEvaluationStructuredOutputTaskRequestWithItemLocator,
     AutoEvaluationGuidedDecodingEvaluationTaskConfigurationAutoEvaluationGuidedDecodingTaskRequestWithItemLocator,
+    AutoEvaluationGuidedDecodingEvaluationTaskConfigurationAutoEvaluationAgentTaskRequestWithItemLocator,
 ]
 
 
@@ -386,6 +492,81 @@ class AutoEvaluationGuidedDecodingEvaluationTask(BaseModel):
     task_type: Optional[Literal["auto_evaluation.guided_decoding"]] = None
 
 
+class AutoEvaluationAgentEvaluationTaskConfigurationDesignatedToApeAgentConfig(BaseModel):
+    model: Optional[str] = None
+
+    temperature: Optional[float] = None
+
+
+class AutoEvaluationAgentEvaluationTaskConfigurationDesignatedToApeAgent(BaseModel):
+    config: AutoEvaluationAgentEvaluationTaskConfigurationDesignatedToApeAgentConfig
+
+    agent_name: Optional[Literal["APEAgent"]] = None
+
+
+class AutoEvaluationAgentEvaluationTaskConfigurationDesignatedToIfAgentConfig(BaseModel):
+    model: Optional[str] = None
+
+
+class AutoEvaluationAgentEvaluationTaskConfigurationDesignatedToIfAgent(BaseModel):
+    config: AutoEvaluationAgentEvaluationTaskConfigurationDesignatedToIfAgentConfig
+
+    agent_name: Optional[Literal["IFAgent"]] = None
+
+
+class AutoEvaluationAgentEvaluationTaskConfigurationDesignatedToTruthfulnessAgentConfig(BaseModel):
+    model: Optional[str] = None
+
+
+class AutoEvaluationAgentEvaluationTaskConfigurationDesignatedToTruthfulnessAgent(BaseModel):
+    config: AutoEvaluationAgentEvaluationTaskConfigurationDesignatedToTruthfulnessAgentConfig
+
+    agent_name: Optional[Literal["TruthfulnessAgent"]] = None
+
+
+class AutoEvaluationAgentEvaluationTaskConfigurationDesignatedToBaseAgentConfig(BaseModel):
+    model: Optional[str] = None
+
+
+class AutoEvaluationAgentEvaluationTaskConfigurationDesignatedToBaseAgent(BaseModel):
+    config: AutoEvaluationAgentEvaluationTaskConfigurationDesignatedToBaseAgentConfig
+
+    agent_name: Optional[Literal["BaseAgent"]] = None
+
+
+AutoEvaluationAgentEvaluationTaskConfigurationDesignatedTo: TypeAlias = Union[
+    AutoEvaluationAgentEvaluationTaskConfigurationDesignatedToApeAgent,
+    AutoEvaluationAgentEvaluationTaskConfigurationDesignatedToIfAgent,
+    AutoEvaluationAgentEvaluationTaskConfigurationDesignatedToTruthfulnessAgent,
+    AutoEvaluationAgentEvaluationTaskConfigurationDesignatedToBaseAgent,
+]
+
+
+class AutoEvaluationAgentEvaluationTaskConfiguration(BaseModel):
+    definition: str
+
+    name: str
+
+    output_rules: List[str]
+
+    data_fields: Optional[List[str]] = None
+
+    designated_to: Optional[AutoEvaluationAgentEvaluationTaskConfigurationDesignatedTo] = None
+
+    output_type: Optional[Literal["text", "integer", "float", "boolean"]] = None
+
+    output_values: Optional[List[Union[str, float, bool]]] = None
+
+
+class AutoEvaluationAgentEvaluationTask(BaseModel):
+    configuration: AutoEvaluationAgentEvaluationTaskConfiguration
+
+    alias: Optional[str] = None
+    """Alias to title the results column. Defaults to the `auto_evaluation_agent`"""
+
+    task_type: Optional[Literal["auto_evaluation.agent"]] = None
+
+
 class ContributorEvaluationQuestionTaskConfiguration(BaseModel):
     layout: "Container"
 
@@ -415,6 +596,7 @@ EvaluationTask: TypeAlias = Annotated[
         MetricEvaluationTask,
         AutoEvaluationQuestionTask,
         AutoEvaluationGuidedDecodingEvaluationTask,
+        AutoEvaluationAgentEvaluationTask,
         ContributorEvaluationQuestionTask,
     ],
     PropertyInfo(discriminator="task_type"),