nat.data_models.step_adaptor

Attributes

logger

Classes

StepAdaptorMode	Enum where members are also (and must be) strings
StepAdaptorConfig	Configures how intermediate steps are filtered and normalized by the StepAdaptor.

Module Contents

logger

class StepAdaptorMode

Bases: enum.StrEnum

Enum where members are also (and must be) strings

Initialize self. See help(type(self)) for accurate signature.

DEFAULT = 'default'

CUSTOM = 'custom'

OFF = 'off'

class StepAdaptorConfig(/, **data: Any)

Bases: pydantic.BaseModel

Configures how intermediate steps are filtered and normalized by the StepAdaptor.

Args:

mode (StepAdaptorMode): One of:

• ‘current’ => pass only LLM (all LLM_* events) + TOOL_END

• ‘end_events_only’ => pass only LLM_END and TOOL_END

• ‘custom’ => pass only the events in custom_event_types

custom_event_types (list[IntermediateStepType]):

If mode == ‘custom’, we only pass events whose event_type is in this list. Otherwise, this field is ignored.

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

mode: StepAdaptorMode

custom_event_types: list[nat.data_models.intermediate_step.IntermediateStepType] = None

check_custom_event_types() → StepAdaptorConfig

Validates custom configurations