Struct CompositeStrategy 

pub struct CompositeStrategy { /* private fields */ }

Chains multiple strategies, applying each in order until token budget is met.

Each strategy is tried in sequence. After each strategy’s compact runs, the resulting token count is re-estimated. If it falls below max_tokens, iteration stops early.

Use BoxedStrategy::new to wrap concrete strategies before collecting them.

Example

use neuron_context::{CompositeStrategy, SlidingWindowStrategy, ToolResultClearingStrategy};
use neuron_context::strategies::BoxedStrategy;

let strategy = CompositeStrategy::new(vec![
    BoxedStrategy::new(ToolResultClearingStrategy::new(2, 100_000)),
    BoxedStrategy::new(SlidingWindowStrategy::new(10, 100_000)),
], 100_000);

Implementations

impl CompositeStrategy

pub fn new(strategies: Vec<BoxedStrategy>, max_tokens: usize) -> Self

Creates a new CompositeStrategy.

Arguments

• strategies — ordered list of type-erased strategies to apply
• max_tokens — token threshold above which compaction is triggered

Trait Implementations

impl ContextStrategy for CompositeStrategy

fn should_compact(&self, messages: &[Message], token_count: usize) -> bool

Whether compaction should be triggered given the current messages and token count.

fn compact( &self, messages: Vec<Message>, ) -> impl Future<Output = Result<Vec<Message>, ContextError>> + WasmCompatSend

Compact the message list to reduce token usage.

fn token_estimate(&self, messages: &[Message]) -> usize

Estimate the token count for a list of messages.