Struct ContextManager 

pub struct ContextManager {
    pub max_tokens: usize,
    pub reserve_ratio: f32,
    pub max_output_lines: usize,
    pub max_output_bytes: usize,
    pub compression_token_threshold: usize,
    pub compression_enabled: bool,
}

Manages the context window, truncating history when approaching token limits.

Fields

max_tokens: usize

Model’s context window size in tokens.

reserve_ratio: f32

Ratio of context window to reserve for LLM response (default 0.2 = 20%).

max_output_lines: usize

Max output lines for tool results.

max_output_bytes: usize

Max output bytes for tool results.

compression_token_threshold: usize

Token threshold for triggering compression.

compression_enabled: bool

Whether compression is enabled.

Implementations

impl ContextManager

pub fn new(context_window: Option<u64>, config: Option<&ContextConfig>) -> Self

pub fn available_tokens(&self) -> usize

Maximum tokens available for input (total - reserved for response).

pub fn truncate_tool_output(&self, content: &str) -> String

Truncate tool output using the configured limits.

pub fn maybe_truncate( &self, messages: &mut Vec<ChatCompletionRequestMessage>, ) -> TruncationResult

Check if history needs truncation and perform it if necessary. Returns TruncationResult with removed messages for async compression.

Strategy: remove oldest non-system messages by “rounds” (user + assistant + tool_calls + tool_results grouped together).