Struct AgentReviewer 

pub struct AgentReviewer { /* private fields */ }

LLM-backed reviewer using a strict structured Runifold Agent.

Implementations

impl AgentReviewer

pub fn new( agent: Agent, rubric: ReviewRubric, ) -> Result<Self, WorkflowReviewError>

Creates an Agent-backed reviewer and installs the trusted rubric as a system instruction.

Errors

Returns WorkflowReviewError::InvalidConfiguration when the derived terminal-review identity cannot be represented safely.

pub const fn rubric(&self) -> &ReviewRubric

Returns the versioned reviewer rubric.

pub const fn agent(&self) -> &StructuredAgent<AgentReviewDecision>

Returns the structured reviewer Agent.

Trait Implementations

impl Clone for AgentReviewer

fn clone(&self) -> AgentReviewer

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for AgentReviewer

fn fmt(&self, formatter: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl TerminalReviewer for AgentReviewer

fn descriptor(&self) -> &TerminalReviewerDescriptor

Returns the stable identity persisted into Agent checkpoints.

fn review_terminal<'a>( &'a self, request: TerminalReviewRequest, run: &'a RunContext, ) -> TerminalReviewFuture<'a>

Reviews a candidate inside an explicitly attenuated child run.

impl WorkflowReviewer for AgentReviewer

fn review<'a>( &'a self, request: WorkflowReviewRequest, run: &'a RunContext, ) -> WorkflowReviewFuture<'a>

Reviews one candidate without owning remediation or retry policy.