Enum LoopOutcome 

pub enum LoopOutcome {
    Done,
    WrappedUp,
    HitMaxIterations,
}

Outcome label for a completed run.

Distinguishes natural termination from budget-pressure terminations so callers (notably parent agents reading a subagent’s tool result) can reason about whether the answer is complete or partial. All variants are non-error — a hard error becomes LoopError.

Variants

Done

Model emitted a final assistant turn with no tool calls and no pending steering. The natural happy path.

WrappedUp

The graceful turn-limit plugin injected a wrap-up steering message and the model produced a clean final turn within the grace window. Result text reflects the model’s deliberate close-out, not a truncated transcript.

HitMaxIterations

max_iterations was reached before the model wrapped up. The run stopped at the cap, but earlier turns are still in the transcript. The most recent assistant turn may have had pending tool calls.

Implementations

impl LoopOutcome

pub fn is_complete(self) -> bool

Whether this outcome implies a clean, non-partial final answer.

pub fn label(self) -> &'static str

Short stable label suitable for logs and tool-result prefixes.

Trait Implementations

impl Clone for LoopOutcome

fn clone(&self) -> LoopOutcome

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for LoopOutcome

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

Formats the value using the given formatter.

impl PartialEq for LoopOutcome

fn eq(&self, other: &LoopOutcome) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Copy for LoopOutcome

impl Eq for LoopOutcome

impl StructuralPartialEq for LoopOutcome