Struct CompactionConfig 

pub struct CompactionConfig {
    pub preserve_recent_messages: usize,
    pub max_estimated_tokens: usize,
}

Professional Compaction Configuration.

Fields

preserve_recent_messages: usize

max_estimated_tokens: usize

Token threshold before compaction fires. Set dynamically via adaptive().

Implementations

impl CompactionConfig

pub fn adaptive(context_length: usize, vram_ratio: f64) -> Self

Build a hardware-aware config that scales with the model’s context window and current VRAM pressure.

• context_length: tokens the loaded model can handle (from /api/v0/models)
• vram_ratio: current VRAM usage 0.0–1.0 (from GpuState::ratio)

Formula: threshold = ctx * 0.40 * (1 - vram * 0.5), clamped [4k, 60k]. preserve_recent_messages scales with context: roughly 1 message per 3k tokens.

Trait Implementations

impl Clone for CompactionConfig

fn clone(&self) -> CompactionConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for CompactionConfig

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

Formats the value using the given formatter.

impl Default for CompactionConfig

fn default() -> Self

Returns the “default value” for a type.

impl PartialEq for CompactionConfig

fn eq(&self, other: &CompactionConfig) -> 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 CompactionConfig

impl Eq for CompactionConfig

impl StructuralPartialEq for CompactionConfig