Enum ReduceStrategy 

pub enum ReduceStrategy {
    Structural,
    Llm,
}

Strategy used to reduce several partial DistilledMemory results — one per transcript chunk — into a single result.

Structural is the default: deterministic, no extra model call, and therefore no extra risk of re-introducing the prompt-size problem chunking exists to fix. Llm is strictly opt-in — it can produce better prose and more semantic deduplication, but it is a second, non- deterministic pass that re-reads already-distilled output and could silently drop a detail the first pass captured. Prefer Structural unless you have a specific reason to accept that tradeoff.

Variants

Structural

Merge partial results with merge_distilled. Deterministic, no model call.

Llm

Render partial results back into text and call the distiller on them once more for a consolidated pass.

Trait Implementations

impl Clone for ReduceStrategy

fn clone(&self) -> ReduceStrategy

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Copy for ReduceStrategy

impl Debug for ReduceStrategy

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

Formats the value using the given formatter.

impl Default for ReduceStrategy

fn default() -> ReduceStrategy

Returns the “default value” for a type.

impl Eq for ReduceStrategy

impl PartialEq for ReduceStrategy

fn eq(&self, other: &ReduceStrategy) -> 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 StructuralPartialEq for ReduceStrategy