Struct MemoryConfig 

pub struct MemoryConfig {
    pub enabled: bool,
    pub recorder_cost: ModelCost,
    pub context_message_count: usize,
    pub summarizer_cost: ModelCost,
    pub recent_memories_count: usize,
    pub auto_compaction_threshold: Option<usize>,
}

Tycode allows models to store memories which persist between conversations. When enabled, Tycode will also send background requests to models specifically to extract memories from user input, otherwise models may choose to store memories, but generally do not. Memories are appended to a file (in ~/.tycode/memories/memories_log.json) and occasionally compacted in to a memory summary. Memories are injected to prompts so future conversations may benefit from the learnings.

Fields

enabled: bool

Enable or Disable background calls to extract memories from conversation context.

recorder_cost: ModelCost

Cost control for the background model that is used to record memories.

context_message_count: usize

Number of recent messages send to the background model; more messages will improve context for the background model, however will increase costs.

summarizer_cost: ModelCost

Cost control for the model that is used to compact memories.

recent_memories_count: usize

Number of recent memories to include in the agent’s context

auto_compaction_threshold: Option<usize>

When set, automatically trigger background compaction after this many new memories since the last compaction.

Implementations

impl MemoryConfig

pub const NAMESPACE: &str = "memory"

Trait Implementations

impl Clone for MemoryConfig

fn clone(&self) -> MemoryConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for MemoryConfig

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

Formats the value using the given formatter.

impl Default for MemoryConfig

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for MemoryConfig

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl JsonSchema for MemoryConfig

fn schema_name() -> String

The name of the generated JSON Schema.

fn schema_id() -> Cow<'static, str>

Returns a string that uniquely identifies the schema produced by this type.

fn json_schema(generator: &mut SchemaGenerator) -> Schema

Generates a JSON Schema for this type.

fn is_referenceable() -> bool

Whether JSON Schemas generated for this type should be re-used where possible using the $ref keyword.

impl Serialize for MemoryConfig

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.