Struct ConversationSummaryBufferMemory 

pub struct ConversationSummaryBufferMemory { /* private fields */ }

Hybrid memory strategy: keeps recent messages verbatim and summarizes older messages when total estimated tokens exceed max_token_limit.

Combines the benefits of ConversationSummaryMemory (compact history) with ConversationTokenBufferMemory (recent context preserved exactly).

Implementations

impl ConversationSummaryBufferMemory

pub fn new( store: Arc<dyn MemoryStore>, model: Arc<dyn ChatModel>, max_token_limit: usize, ) -> Self

Create a new summary buffer memory.

• store — the underlying message store
• model — the ChatModel used to generate summaries
• max_token_limit — when total estimated tokens exceed this, older messages are summarized

Trait Implementations

impl MemoryStore for ConversationSummaryBufferMemory

fn append<'life0, 'life1, 'async_trait>( &'life0 self, session_id: &'life1 str, message: Message, ) -> Pin<Box<dyn Future<Output = Result<(), SynapseError>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait,

fn load<'life0, 'life1, 'async_trait>( &'life0 self, session_id: &'life1 str, ) -> Pin<Box<dyn Future<Output = Result<Vec<Message>, SynapseError>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait,

fn clear<'life0, 'life1, 'async_trait>( &'life0 self, session_id: &'life1 str, ) -> Pin<Box<dyn Future<Output = Result<(), SynapseError>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait,