vellum-ai 0.14.89__py3-none-any.whl → 1.0.1__py3-none-any.whl

vellum/__init__.py

@@ -3,7 +3,7 @@ from .plugins.utils import load_runtime_plugins
 
 load_runtime_plugins()
 
-from .types import (
+from .client.types import (
     AdHocExecutePromptEvent,
     AdHocExpandMeta,
     AdHocFulfilledPromptExecutionMeta,
@@ -287,6 +287,7 @@ from .types import (
     OpenAiVectorizerTextEmbedding3SmallRequest,
     OpenAiVectorizerTextEmbeddingAda002,
     OpenAiVectorizerTextEmbeddingAda002Request,
+    OrganizationLimitConfig,
     OrganizationRead,
     PaginatedContainerImageReadList,
     PaginatedDeploymentReleaseTagReadList,
@@ -327,6 +328,7 @@ from .types import (
     PromptRequestStringInput,
     PromptSettings,
     PromptVersionBuildConfigSandbox,
+    Quota,
     RawPromptExecutionOverridesRequest,
     ReductoChunkerConfig,
     ReductoChunkerConfigRequest,
@@ -524,6 +526,7 @@ from .types import (
     VellumVariableExtensions,
     VellumVariableType,
     VellumWorkflowExecutionEvent,
+    VembdaServiceTierEnum,
     WorkflowDeploymentEventExecutionsResponse,
     WorkflowDeploymentHistoryItem,
     WorkflowDeploymentParentContext,
@@ -932,6 +935,7 @@ __all__ = [
     "OpenAiVectorizerTextEmbedding3SmallRequest",
     "OpenAiVectorizerTextEmbeddingAda002",
     "OpenAiVectorizerTextEmbeddingAda002Request",
+    "OrganizationLimitConfig",
     "OrganizationRead",
     "PaginatedContainerImageReadList",
     "PaginatedDeploymentReleaseTagReadList",
@@ -972,6 +976,7 @@ __all__ = [
     "PromptRequestStringInput",
     "PromptSettings",
     "PromptVersionBuildConfigSandbox",
+    "Quota",
     "RawPromptExecutionOverridesRequest",
     "ReductoChunkerConfig",
     "ReductoChunkerConfigRequest",
@@ -1171,6 +1176,7 @@ __all__ = [
     "VellumVariableExtensions",
     "VellumVariableType",
     "VellumWorkflowExecutionEvent",
+    "VembdaServiceTierEnum",
     "WorkflowDeploymentEventExecutionsResponse",
     "WorkflowDeploymentHistoryItem",
     "WorkflowDeploymentParentContext",

vellum/client/__init__.py

@@ -128,7 +128,7 @@ class Vellum:
         self,
         *,
         environment: VellumEnvironment = VellumEnvironment.PRODUCTION,
-        api_version: typing.Optional[ApiVersionEnum] = os.getenv("VELLUM_API_VERSION", "2024-10-25"),
+        api_version: typing.Optional[ApiVersionEnum] = os.getenv("VELLUM_API_VERSION", "2025-07-30"),
         api_key: str,
         timeout: typing.Optional[float] = None,
         follow_redirects: typing.Optional[bool] = True,
@@ -1562,7 +1562,7 @@ class AsyncVellum:
         self,
         *,
         environment: VellumEnvironment = VellumEnvironment.PRODUCTION,
-        api_version: typing.Optional[ApiVersionEnum] = os.getenv("VELLUM_API_VERSION", "2024-10-25"),
+        api_version: typing.Optional[ApiVersionEnum] = os.getenv("VELLUM_API_VERSION", "2025-07-30"),
         api_key: str,
         timeout: typing.Optional[float] = None,
         follow_redirects: typing.Optional[bool] = True,

vellum/client/core/client_wrapper.py

@@ -25,10 +25,10 @@ class BaseClientWrapper:
 
     def get_headers(self) -> typing.Dict[str, str]:
         headers: typing.Dict[str, str] = {
-            "User-Agent": "vellum-ai/0.14.89",
+            "User-Agent": "vellum-ai/1.0.1",
             "X-Fern-Language": "Python",
             "X-Fern-SDK-Name": "vellum-ai",
-            "X-Fern-SDK-Version": "0.14.89",
+            "X-Fern-SDK-Version": "1.0.1",
         }
         if self._api_version is not None:
             headers["X-API-Version"] = self._api_version

vellum/client/types/__init__.py

@@ -295,6 +295,7 @@ from .open_ai_vectorizer_text_embedding_3_small import OpenAiVectorizerTextEmbed
 from .open_ai_vectorizer_text_embedding_3_small_request import OpenAiVectorizerTextEmbedding3SmallRequest
 from .open_ai_vectorizer_text_embedding_ada_002 import OpenAiVectorizerTextEmbeddingAda002
 from .open_ai_vectorizer_text_embedding_ada_002_request import OpenAiVectorizerTextEmbeddingAda002Request
+from .organization_limit_config import OrganizationLimitConfig
 from .organization_read import OrganizationRead
 from .paginated_container_image_read_list import PaginatedContainerImageReadList
 from .paginated_deployment_release_tag_read_list import PaginatedDeploymentReleaseTagReadList
@@ -335,6 +336,7 @@ from .prompt_request_json_input import PromptRequestJsonInput
 from .prompt_request_string_input import PromptRequestStringInput
 from .prompt_settings import PromptSettings
 from .prompt_version_build_config_sandbox import PromptVersionBuildConfigSandbox
+from .quota import Quota
 from .raw_prompt_execution_overrides_request import RawPromptExecutionOverridesRequest
 from .reducto_chunker_config import ReductoChunkerConfig
 from .reducto_chunker_config_request import ReductoChunkerConfigRequest
@@ -548,6 +550,7 @@ from .vellum_variable import VellumVariable
 from .vellum_variable_extensions import VellumVariableExtensions
 from .vellum_variable_type import VellumVariableType
 from .vellum_workflow_execution_event import VellumWorkflowExecutionEvent
+from .vembda_service_tier_enum import VembdaServiceTierEnum
 from .workflow_deployment_event_executions_response import WorkflowDeploymentEventExecutionsResponse
 from .workflow_deployment_history_item import WorkflowDeploymentHistoryItem
 from .workflow_deployment_parent_context import WorkflowDeploymentParentContext
@@ -912,6 +915,7 @@ __all__ = [
     "OpenAiVectorizerTextEmbedding3SmallRequest",
     "OpenAiVectorizerTextEmbeddingAda002",
     "OpenAiVectorizerTextEmbeddingAda002Request",
+    "OrganizationLimitConfig",
     "OrganizationRead",
     "PaginatedContainerImageReadList",
     "PaginatedDeploymentReleaseTagReadList",
@@ -952,6 +956,7 @@ __all__ = [
     "PromptRequestStringInput",
     "PromptSettings",
     "PromptVersionBuildConfigSandbox",
+    "Quota",
     "RawPromptExecutionOverridesRequest",
     "ReductoChunkerConfig",
     "ReductoChunkerConfigRequest",
@@ -1149,6 +1154,7 @@ __all__ = [
     "VellumVariableExtensions",
     "VellumVariableType",
     "VellumWorkflowExecutionEvent",
+    "VembdaServiceTierEnum",
     "WorkflowDeploymentEventExecutionsResponse",
     "WorkflowDeploymentHistoryItem",
     "WorkflowDeploymentParentContext",

vellum/client/types/organization_limit_config.py

@@ -0,0 +1,24 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from ..core.pydantic_utilities import UniversalBaseModel
+import typing
+from .vembda_service_tier_enum import VembdaServiceTierEnum
+from .quota import Quota
+from ..core.pydantic_utilities import IS_PYDANTIC_V2
+import pydantic
+
+
+class OrganizationLimitConfig(UniversalBaseModel):
+    vembda_service_tier: typing.Optional[VembdaServiceTierEnum] = None
+    prompt_executions_quota: typing.Optional[Quota] = None
+    workflow_executions_quota: typing.Optional[Quota] = None
+    workflow_runtime_seconds_quota: typing.Optional[Quota] = None
+
+    if IS_PYDANTIC_V2:
+        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
+    else:
+
+        class Config:
+            frozen = True
+            smart_union = True
+            extra = pydantic.Extra.allow

vellum/client/types/organization_read.py

@@ -3,6 +3,7 @@
 from ..core.pydantic_utilities import UniversalBaseModel
 import typing
 from .new_member_join_behavior_enum import NewMemberJoinBehaviorEnum
+from .organization_limit_config import OrganizationLimitConfig
 from ..core.pydantic_utilities import IS_PYDANTIC_V2
 import pydantic
 
@@ -12,6 +13,7 @@ class OrganizationRead(UniversalBaseModel):
     name: str
     allow_staff_access: typing.Optional[bool] = None
     new_member_join_behavior: NewMemberJoinBehaviorEnum
+    limit_config: OrganizationLimitConfig
 
     if IS_PYDANTIC_V2:
         model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2

vellum/client/types/quota.py

@@ -0,0 +1,21 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from ..core.pydantic_utilities import UniversalBaseModel
+import typing
+from ..core.pydantic_utilities import IS_PYDANTIC_V2
+import pydantic
+
+
+class Quota(UniversalBaseModel):
+    name: str
+    value: typing.Optional[int] = None
+    period_seconds: typing.Optional[int] = None
+
+    if IS_PYDANTIC_V2:
+        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
+    else:
+
+        class Config:
+            frozen = True
+            smart_union = True
+            extra = pydantic.Extra.allow

vellum/client/types/vembda_service_tier_enum.py

@@ -0,0 +1,5 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+VembdaServiceTierEnum = typing.Union[typing.Literal["FREE", "PAID"], typing.Any]

vellum/client/types/workflow_execution_actual.py

@@ -12,7 +12,7 @@ import pydantic
 class WorkflowExecutionActual(UniversalBaseModel):
     output: ExecutionVellumValue
     timestamp: dt.datetime
-    quality: float
+    quality: typing.Optional[float] = None
     metadata: typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]] = None
 
     if IS_PYDANTIC_V2:

vellum/evaluations/resources.py

@@ -8,11 +8,7 @@ from typing import Callable, Generator, Iterable, List, cast
 
 from vellum import TestSuiteRunMetricNumberOutput, TestSuiteRunRead
 from vellum.client import OMIT, Vellum
-from vellum.evaluations.constants import DEFAULT_MAX_POLLING_DURATION_MS, DEFAULT_POLLING_INTERVAL_MS
-from vellum.evaluations.exceptions import TestSuiteRunResultsException
-from vellum.evaluations.utils.env import get_api_key
-from vellum.evaluations.utils.paginator import PaginatedResults, get_all_results
-from vellum.types import (
+from vellum.client.types import (
     ExternalTestCaseExecutionRequest,
     NamedTestCaseVariableValueRequest,
     TestCaseVariableValue,
@@ -22,6 +18,10 @@ from vellum.types import (
     TestSuiteRunMetricOutput,
     TestSuiteRunState,
 )
+from vellum.evaluations.constants import DEFAULT_MAX_POLLING_DURATION_MS, DEFAULT_POLLING_INTERVAL_MS
+from vellum.evaluations.exceptions import TestSuiteRunResultsException
+from vellum.evaluations.utils.env import get_api_key
+from vellum.evaluations.utils.paginator import PaginatedResults, get_all_results
 from vellum.utils.typing import cast_not_optional
 from vellum.utils.uuid import is_valid_uuid
 

vellum/types/organization_limit_config.py

@@ -0,0 +1,3 @@
+# WARNING: This file will be removed in a future release. Please import from "vellum.client" instead.
+
+from vellum.client.types.organization_limit_config import *

vellum/types/quota.py

@@ -0,0 +1,3 @@
+# WARNING: This file will be removed in a future release. Please import from "vellum.client" instead.
+
+from vellum.client.types.quota import *

vellum/types/vembda_service_tier_enum.py

@@ -0,0 +1,3 @@
+# WARNING: This file will be removed in a future release. Please import from "vellum.client" instead.
+
+from vellum.client.types.vembda_service_tier_enum import *

vellum/workflows/events/node.py

@@ -2,7 +2,7 @@ from typing import TYPE_CHECKING, Any, Dict, Generic, List, Literal, Optional, S
 
 from pydantic import SerializerFunctionWrapHandler, field_serializer, model_serializer
 
-from vellum.core.pydantic_utilities import UniversalBaseModel
+from vellum.client.core.pydantic_utilities import UniversalBaseModel
 from vellum.workflows.errors import WorkflowError
 from vellum.workflows.expressions.accessor import AccessorExpression
 from vellum.workflows.outputs.base import BaseOutput

vellum/workflows/events/types.py

@@ -6,7 +6,7 @@ from typing import Annotated, Any, Literal, Optional, Union, get_args
 from pydantic import Field, GetCoreSchemaHandler, Tag, ValidationInfo
 from pydantic_core import CoreSchema, core_schema
 
-from vellum.core.pydantic_utilities import UniversalBaseModel
+from vellum.client.core.pydantic_utilities import UniversalBaseModel
 from vellum.workflows.state.encoder import DefaultStateEncoder
 from vellum.workflows.types.definition import VellumCodeResourceDefinition
 from vellum.workflows.types.utils import datetime_now

vellum/workflows/events/workflow.py

@@ -4,7 +4,7 @@ from typing_extensions import TypeGuard
 
 from pydantic import field_serializer
 
-from vellum.core.pydantic_utilities import UniversalBaseModel
+from vellum.client.core.pydantic_utilities import UniversalBaseModel
 from vellum.workflows.errors import WorkflowError
 from vellum.workflows.outputs.base import BaseOutput
 from vellum.workflows.references import ExternalInputReference

vellum/workflows/nodes/bases/tests/test_base_node.py

@@ -2,8 +2,8 @@ import pytest
 from uuid import UUID
 from typing import Optional, Set
 
+from vellum.client.core.pydantic_utilities import UniversalBaseModel
 from vellum.client.types.string_vellum_value_request import StringVellumValueRequest
-from vellum.core.pydantic_utilities import UniversalBaseModel
 from vellum.workflows.constants import undefined
 from vellum.workflows.descriptors.tests.test_utils import FixtureState
 from vellum.workflows.inputs.base import BaseInputs

vellum/workflows/nodes/displayable/api_node/node.py

@@ -65,4 +65,5 @@ class APINode(BaseAPINode):
             json=self.json,
             headers=final_headers,
             bearer_token=bearer_token,
+            timeout=self.timeout,
         )

vellum/workflows/nodes/displayable/api_node/tests/test_api_node.py

@@ -233,3 +233,33 @@ def test_api_node_raises_error_for_whitespace_url():
 
     assert excinfo.value.code == WorkflowErrorCode.INVALID_INPUTS
     assert "URL is required and must be a non-empty string" in str(excinfo.value)
+
+
+def test_api_node_passes_timeout_to_vellum_client(vellum_client):
+    """Test that timeout is passed to vellum client as RequestOptions."""
+    vellum_client.execute_api.return_value = ExecuteApiResponse(
+        status_code=200,
+        text='{"result": "success"}',
+        json_={"result": "success"},
+        headers={"content-type": "application/json"},
+    )
+
+    # GIVEN an API node configured with a timeout value of 25 seconds
+    class APINodeWithTimeout(APINode):
+        method = APIRequestMethod.GET
+        authorization_type = AuthorizationType.BEARER_TOKEN
+        url = "https://example.com"
+        timeout = 25
+        bearer_token_value = VellumSecret(name="secret")
+
+    # WHEN the API node is executed
+    node = APINodeWithTimeout()
+    node.run()
+
+    # THEN the vellum client should be called exactly once
+    assert vellum_client.execute_api.call_count == 1
+    call_args = vellum_client.execute_api.call_args
+    request_options = call_args.kwargs["request_options"]
+    # AND the call should include RequestOptions with the correct timeout
+    assert request_options is not None
+    assert request_options["timeout_in_seconds"] == 25

vellum/workflows/nodes/displayable/bases/api_node/node.py

@@ -4,6 +4,7 @@ from requests import Request, RequestException, Session
 from requests.exceptions import JSONDecodeError
 
 from vellum.client import ApiError
+from vellum.client.core.request_options import RequestOptions
 from vellum.client.types.vellum_secret import VellumSecret as ClientVellumSecret
 from vellum.workflows.constants import APIRequestMethod
 from vellum.workflows.errors.types import WorkflowErrorCode
@@ -23,6 +24,7 @@ class BaseAPINode(BaseNode, Generic[StateType]):
     data: Optional[str] - The data to send in the request body.
     json: Optional["JsonObject"] - The JSON data to send in the request body.
     headers: Optional[Dict[str, Union[str, VellumSecret]]] - The headers to send in the request.
+    timeout: Optional[int] - The timeout in seconds for the API request.
     """
 
     class Trigger(BaseNode.Trigger):
@@ -33,6 +35,7 @@ class BaseAPINode(BaseNode, Generic[StateType]):
     data: Optional[str] = None
     json: Optional[Json] = None
     headers: Optional[Dict[str, Union[str, VellumSecret]]] = None
+    timeout: Optional[int] = None
 
     class Outputs(BaseOutputs):
         json: Optional[Json]
@@ -45,7 +48,9 @@ class BaseAPINode(BaseNode, Generic[StateType]):
             raise NodeException("URL is required and must be a non-empty string", code=WorkflowErrorCode.INVALID_INPUTS)
 
     def run(self) -> Outputs:
-        return self._run(method=self.method, url=self.url, data=self.data, json=self.json, headers=self.headers)
+        return self._run(
+            method=self.method, url=self.url, data=self.data, json=self.json, headers=self.headers, timeout=self.timeout
+        )
 
     def _run(
         self,
@@ -55,6 +60,7 @@ class BaseAPINode(BaseNode, Generic[StateType]):
         json: Any = None,
         headers: Any = None,
         bearer_token: Optional[VellumSecret] = None,
+        timeout: Optional[int] = None,
     ) -> Outputs:
         self._validate()
 
@@ -63,11 +69,11 @@ class BaseAPINode(BaseNode, Generic[StateType]):
             if isinstance(headers[header], VellumSecret):
                 vellum_instance = True
         if vellum_instance or bearer_token:
-            return self._vellum_execute_api(bearer_token, json, headers, method, url)
+            return self._vellum_execute_api(bearer_token, json, headers, method, url, timeout)
         else:
-            return self._local_execute_api(data, headers, json, method, url)
+            return self._local_execute_api(data, headers, json, method, url, timeout)
 
-    def _local_execute_api(self, data, headers, json, method, url):
+    def _local_execute_api(self, data, headers, json, method, url, timeout):
         try:
             if data is not None:
                 prepped = Request(method=method.value, url=url, data=data, headers=headers).prepare()
@@ -79,25 +85,36 @@ class BaseAPINode(BaseNode, Generic[StateType]):
             raise NodeException(f"Failed to prepare HTTP request: {e}", code=WorkflowErrorCode.PROVIDER_ERROR)
         try:
             with Session() as session:
-                response = session.send(prepped)
+                response = session.send(prepped, timeout=timeout)
         except RequestException as e:
             raise NodeException(f"HTTP request failed: {e}", code=WorkflowErrorCode.PROVIDER_ERROR)
         try:
-            json = response.json()
+            json_response = response.json()
         except JSONDecodeError:
-            json = None
+            json_response = None
         return self.Outputs(
-            json=json,
+            json=json_response,
             headers={header: value for header, value in response.headers.items()},
             status_code=response.status_code,
             text=response.text,
         )
 
-    def _vellum_execute_api(self, bearer_token, data, headers, method, url):
+    def _vellum_execute_api(self, bearer_token, data, headers, method, url, timeout):
         client_vellum_secret = ClientVellumSecret(name=bearer_token.name) if bearer_token else None
+
+        # Create request_options if timeout is specified
+        request_options = None
+        if timeout is not None:
+            request_options = RequestOptions(timeout_in_seconds=timeout)
+
         try:
             vellum_response = self._context.vellum_client.execute_api(
-                url=url, method=method.value, body=data, headers=headers, bearer_token=client_vellum_secret
+                url=url,
+                method=method.value,
+                body=data,
+                headers=headers,
+                bearer_token=client_vellum_secret,
+                request_options=request_options,
             )
         except ApiError as e:
             raise NodeException(f"Failed to prepare HTTP request: {e}", code=WorkflowErrorCode.NODE_EXECUTION)

vellum/workflows/nodes/displayable/bases/base_prompt_node/node.py

@@ -2,8 +2,8 @@ from abc import abstractmethod
 from typing import ClassVar, Generator, Generic, Iterator, List, Optional, Union
 
 from vellum import AdHocExecutePromptEvent, ExecutePromptEvent, PromptOutput
+from vellum.client.core import RequestOptions
 from vellum.client.core.api_error import ApiError
-from vellum.core import RequestOptions
 from vellum.workflows.errors.types import WorkflowErrorCode, vellum_error_to_workflow_error
 from vellum.workflows.events.node import NodeExecutionStreamingEvent
 from vellum.workflows.exceptions import NodeException

vellum/workflows/nodes/displayable/bases/search_node.py

@@ -11,7 +11,7 @@ from vellum import (
     SearchResultMergingRequest,
     SearchWeightsRequest,
 )
-from vellum.core import ApiError, RequestOptions
+from vellum.client.core import ApiError, RequestOptions
 from vellum.workflows.errors import WorkflowErrorCode
 from vellum.workflows.exceptions import NodeException
 from vellum.workflows.nodes.bases import BaseNode

vellum/workflows/nodes/displayable/code_execution_node/node.py

@@ -20,9 +20,9 @@ from vellum import (
     VellumError,
     VellumValue,
 )
+from vellum.client.core import RequestOptions
 from vellum.client.core.api_error import ApiError
 from vellum.client.types.code_executor_secret_input import CodeExecutorSecretInput
-from vellum.core import RequestOptions
 from vellum.workflows.errors.types import WorkflowErrorCode
 from vellum.workflows.exceptions import NodeException
 from vellum.workflows.nodes.bases import BaseNode

vellum/workflows/nodes/displayable/guardrail_node/node.py

@@ -3,7 +3,7 @@ from typing import Any, ClassVar, Dict, Generic, List, Optional, Union, cast
 
 from vellum import ChatHistoryInput, ChatMessage, JsonInput, MetricDefinitionInput, NumberInput, StringInput
 from vellum.client import ApiError
-from vellum.core import RequestOptions
+from vellum.client.core import RequestOptions
 from vellum.workflows.constants import LATEST_RELEASE_TAG
 from vellum.workflows.errors.types import WorkflowErrorCode
 from vellum.workflows.exceptions import NodeException

vellum/workflows/nodes/displayable/subworkflow_deployment_node/node.py

@@ -12,9 +12,9 @@ from vellum import (
     WorkflowRequestNumberInputRequest,
     WorkflowRequestStringInputRequest,
 )
+from vellum.client.core import RequestOptions
 from vellum.client.core.api_error import ApiError
 from vellum.client.types.chat_message_request import ChatMessageRequest
-from vellum.core import RequestOptions
 from vellum.workflows.constants import LATEST_RELEASE_TAG, OMIT
 from vellum.workflows.context import get_execution_context
 from vellum.workflows.errors import WorkflowErrorCode

vellum/workflows/nodes/displayable/tool_calling_node/node.py

@@ -1,6 +1,7 @@
 from typing import ClassVar, Iterator, List, Optional, Set
 
 from vellum import ChatMessage, PromptBlock
+from vellum.client.types.prompt_parameters import PromptParameters
 from vellum.workflows.context import execution_context, get_parent_context
 from vellum.workflows.errors.types import WorkflowErrorCode
 from vellum.workflows.events.workflow import is_workflow_event
@@ -8,6 +9,7 @@ from vellum.workflows.exceptions import NodeException
 from vellum.workflows.graph.graph import Graph
 from vellum.workflows.inputs.base import BaseInputs
 from vellum.workflows.nodes.bases import BaseNode
+from vellum.workflows.nodes.displayable.bases.inline_prompt_node.constants import DEFAULT_PROMPT_PARAMETERS
 from vellum.workflows.nodes.displayable.tool_calling_node.state import ToolCallingState
 from vellum.workflows.nodes.displayable.tool_calling_node.utils import (
     create_function_node,
@@ -29,6 +31,7 @@ class ToolCallingNode(BaseNode):
         blocks: List[PromptBlock] - The prompt blocks to use (same format as InlinePromptNode)
         functions: List[Tool] - The functions that can be called
         prompt_inputs: Optional[EntityInputsInterface] - Mapping of input variable names to values
+        parameters: PromptParameters - The parameters for the Prompt
         max_prompt_iterations: Optional[int] - Maximum number of prompt iterations before stopping
     """
 
@@ -36,6 +39,7 @@ class ToolCallingNode(BaseNode):
     blocks: ClassVar[List[PromptBlock]] = []
     functions: ClassVar[List[Tool]] = []
     prompt_inputs: ClassVar[Optional[EntityInputsInterface]] = None
+    parameters: PromptParameters = DEFAULT_PROMPT_PARAMETERS
     max_prompt_iterations: ClassVar[Optional[int]] = 5
 
     class Outputs(BaseOutputs):
@@ -131,6 +135,7 @@ class ToolCallingNode(BaseNode):
             blocks=self.blocks,
             functions=self.functions,
             prompt_inputs=self.prompt_inputs,
+            parameters=self.parameters,
             max_prompt_iterations=self.max_prompt_iterations,
         )
 

vellum/workflows/nodes/displayable/tool_calling_node/tests/test_node.py

@@ -13,6 +13,7 @@ from vellum.client.types.variable_prompt_block import VariablePromptBlock
 from vellum.workflows import BaseWorkflow
 from vellum.workflows.inputs.base import BaseInputs
 from vellum.workflows.nodes.bases import BaseNode
+from vellum.workflows.nodes.displayable.bases.inline_prompt_node.constants import DEFAULT_PROMPT_PARAMETERS
 from vellum.workflows.nodes.displayable.tool_calling_node.node import ToolCallingNode
 from vellum.workflows.nodes.displayable.tool_calling_node.utils import create_function_node, create_tool_router_node
 from vellum.workflows.outputs.base import BaseOutputs
@@ -39,6 +40,7 @@ def test_port_condition_match_function_name():
         blocks=[],
         functions=[first_function, second_function],
         prompt_inputs=None,
+        parameters=DEFAULT_PROMPT_PARAMETERS,
     )
 
     # AND a state with a function call to the first function
@@ -96,6 +98,7 @@ def test_tool_calling_node_inline_workflow_context():
         blocks=[],
         functions=[MyWorkflow],
         prompt_inputs=None,
+        parameters=DEFAULT_PROMPT_PARAMETERS,
     )
 
     # WHEN we create a function node for the workflow