Struct ToolResultClearingStrategy 

pub struct ToolResultClearingStrategy { /* private fields */ }

Replaces old tool result content with a placeholder to reduce token usage.

Keeps the most recent keep_recent_n tool results intact and replaces older ones with [tool result cleared] while preserving the tool_use_id so the conversation still makes semantic sense.

Example

use neuron_context::ToolResultClearingStrategy;

let strategy = ToolResultClearingStrategy::new(2, 100_000);

Implementations

impl ToolResultClearingStrategy

pub fn new(keep_recent_n: usize, max_tokens: usize) -> Self

Creates a new ToolResultClearingStrategy.

Arguments

• keep_recent_n — number of most-recent tool results to leave untouched
• max_tokens — token threshold above which compaction is triggered

pub fn with_counter( keep_recent_n: usize, max_tokens: usize, counter: TokenCounter, ) -> Self

Creates a new ToolResultClearingStrategy with a custom TokenCounter.

Trait Implementations

impl ContextStrategy for ToolResultClearingStrategy

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.