Skip to content

strands.decisions.decision_model

Base interface for making structured “decisions” from inside the SDK.

DecisionModel

Section titled “DecisionModel”
class DecisionModel(abc.ABC)

Defined in: src/strands/decisions/decision_model.py:15

Abstract base for anything that can answer closed questions.

The public ask opens a decision span, validates the question map, delegates to the subclass _ask, records usage and the answer set as span attributes/events, and closes the span. Every implementation is traced identically. Given an invocation_context, ask also adds the reported usage to that request once _ask returns.

ask

Section titled “ask”
async def ask(state: DecisionInput,
              questions: dict[str, Question],
              *,
              invocation_context: InvocationContext | None = None,
              **kwargs: Any) -> DecisionResult

Defined in: src/strands/decisions/decision_model.py:24

Ask one or more closed questions over the given state.

Arguments:

  • state - A plain string, a one-shot content list, or a message history.
  • questions - Map of identifier to question. The returned answers dict is keyed off this same map.
  • invocation_context - Request to add this decision’s token usage to. The request’s limits do not apply to the decision.
  • **kwargs - Additional keyword arguments forwarded to the implementation for future extensibility.

Returns:

A DecisionResult whose answers are keyed by the question identifiers.

Raises:

  • ValueError - If questions is empty or a question violates its semantic constraints.
  • TypeError - If invocation_context was not created by the SDK.
  • StructuredOutputException - If the model declines to produce a valid answer set, omits an answer, or returns a value outside a question’s allowed choices.