Struct MemoryConfig 

pub struct MemoryConfig {

    pub backend: String,
    pub auto_save: bool,
    pub hygiene_enabled: bool,
    pub archive_after_days: u32,
    pub purge_after_days: u32,
    pub conversation_retention_days: u32,
    pub min_relevance_score: f64,
    pub response_cache_enabled: bool,
    pub response_cache_ttl_minutes: u32,
    pub response_cache_max_entries: usize,
    pub response_cache_hot_entries: usize,
    pub snapshot_enabled: bool,
    pub snapshot_on_hygiene: bool,
    pub auto_hydrate: bool,
    pub default_namespace: String,
    pub audit_enabled: bool,
    pub audit_retention_days: u32,
    pub policy: MemoryPolicyConfig,
}

Memory backend configuration ([memory] section).

Persistent memory in Construct is handled exclusively by Kumiho MCP; this section controls in-session auto-save behaviour and response caching.

Fields

backend: String

"kumiho" (persistent via Kumiho MCP) or "none" (no-op, in-session only).

Legacy values (sqlite, lucid, markdown, qdrant) are rejected at startup and should be migrated to kumiho.

auto_save: bool

Auto-save user-stated conversation input to memory (assistant output is excluded)

hygiene_enabled: bool

Run memory/session hygiene (archiving + retention cleanup)

archive_after_days: u32

Archive daily/session files older than this many days

purge_after_days: u32

Purge archived files older than this many days

conversation_retention_days: u32

Prune archived conversation rows older than this many days.

min_relevance_score: f64

Minimum hybrid score (0.0-1.0) for a memory to be included in context. Memories scoring below this threshold are dropped to prevent irrelevant context from bleeding into conversations. Default: 0.4

response_cache_enabled: bool

Enable LLM response caching to avoid paying for duplicate prompts

response_cache_ttl_minutes: u32

TTL in minutes for cached responses (default: 60)

response_cache_max_entries: usize

Max number of cached responses before LRU eviction (default: 5000)

response_cache_hot_entries: usize

Max in-memory hot cache entries for the two-tier response cache (default: 256)

snapshot_enabled: bool

Enable periodic export of core memories to MEMORY_SNAPSHOT.md

snapshot_on_hygiene: bool

Run snapshot during hygiene passes (heartbeat-driven)

auto_hydrate: bool

Auto-hydrate from MEMORY_SNAPSHOT.md when brain.db is missing

default_namespace: String

Default namespace for memory entries.

audit_enabled: bool

Enable audit logging of memory operations.

audit_retention_days: u32

Retention period for audit entries in days (default: 30).

policy: MemoryPolicyConfig

Memory policy configuration.

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() -> Cow<'static, str>

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 inline_schema() -> bool

Whether JSON Schemas generated for this type should be included directly in parent schemas, rather than being 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.