Praison AI

Run Outcome • AI Agent SDK

Structured run outcome types for agent execution results.

run_outcome

AI Agent

Structured run outcome types for agent execution results.

Provides a typed, closed discriminant union for agent run completions, task validation outcomes, and handoff results across the SDK.

Replaces freeform string-based validation outcomes with type-safe status values that enable exhaustive error handling and structured metadata.

Import

python
from praisonaiagents import run_outcome

Classes

TerminationReason

Typed terminal reasons for an autonomous run.

 AgentRunOutcome

Structured outcome for agent execution, validation, and handoff operations.

 RunTerminal

One authoritative way a run ended — a closed discriminated union.

Functions

termination_to_run_status()

Map a `TerminationReason (or its string value) to a RunStatus`.

 validate_decision_string()

Convert legacy validation decision strings to typed RunStatus.

 is_sticky()

Whether `outcome` can never be overwritten by a later observation.

 merge_run_terminal()

Fold a newly-observed terminal into the current one (refine-only).

 collapse()

Project a `RunTerminal onto the existing RunStatus` vocabulary.

Constants

NameValue
_STICKY_SOURCESfrozenset({'external', 'run_budget', 'superseded'})