AgentExecutionResult
junjo.agent.result.AgentExecutionResult
Kind: Class
SDK version: 0.69.0
Documentation channel: Stable release
Signature
Section titled “Signature”AgentExecutionResult(*, agent_key: str, name: str, definition_id: str, structural_id: str, run_id: str, output: OutputT, transcript: tuple[AgentMessage, ...], usage: AgentUsage, model_request_count: int, tool_call_requested_count: int, tool_call_admitted_count: int, tool_call_started_count: int, tool_call_completed_count: int, application_state: StateT | None = None, application_store_id: str | None = None)Frozen detached result returned only after validated final output.
Constructor
Section titled “Constructor”Create a detached successful Agent execution result.
The public constructor enforces portable identities, exact Agent
fingerprint form, a complete normalized transcript, usage/request
consistency, and completed <= started <= admitted <= requested.
Parameters
Section titled “Parameters”| Name | Type | Description | Default |
|---|---|---|---|
application_state |
StateT | None |
Detached typed application state at this run boundary. The live Store may continue changing in another execution. |
None |
application_store_id |
str | None |
Identity of that application Store, if configured. | None |
output |
OutputT |
Already validated typed output owned by the caller. | |
transcript |
tuple[AgentMessage, ...] |
One or more complete normalized exchanges. | |
usage |
AgentUsage |
Immutable aggregate usage evidence. |
Raises
Section titled “Raises”| Exception | Description |
|---|---|
TypeError |
If typed members have the wrong public type. |
ValueError |
If identities, transcript, or counters conflict. |
Members
Section titled “Members”agent_key
Section titled “agent_key”agent_key: strApplication-owned stable key of the Agent definition.
name: strHuman-readable Agent name captured for this execution.
definition_id
Section titled “definition_id”definition_id: strIdentity of the Agent definition used for this invocation.
structural_id
Section titled “structural_id”structural_id: strCompiled structural identity used to correlate equivalent executable shapes.
run_id
Section titled “run_id”run_id: strIdentity of this admitted Agent invocation, distinct from an evaluation run ID.
output
Section titled “output”output: OutputTFinal output validated against the Agent output type.
application_state
Section titled “application_state”application_state: StateT | NoneDetached application-state checkpoint at completion; None when no Store was configured.
application_store_id
Section titled “application_store_id”application_store_id: str | NoneIdentity of the application Store observed by this invocation.
transcript
Section titled “transcript”transcript: tuple[AgentMessage, ...]Immutable normalized records of the messages and operations captured for this invocation.
usage: AgentUsageAggregated provider-reported usage; unavailable fields remain absent rather than becoming zero.
model_request_count
Section titled “model_request_count”model_request_count: intNumber of model requests recorded during this invocation.
tool_call_requested_count
Section titled “tool_call_requested_count”tool_call_requested_count: intNumber of tool calls requested by model responses.
tool_call_admitted_count
Section titled “tool_call_admitted_count”tool_call_admitted_count: intRequested tool calls accepted for execution by the Agent runtime.
tool_call_started_count
Section titled “tool_call_started_count”tool_call_started_count: intAdmitted tool calls whose execution started.
tool_call_completed_count
Section titled “tool_call_completed_count”tool_call_completed_count: intStarted tool calls whose execution completed.
termination_reason
Section titled “termination_reason”termination_reason: strSuccessful result termination reason; currently final_output.