Struct DeduplicationConfig 

pub struct DeduplicationConfig {
    pub enabled: bool,
    pub similarity_thresholds: HashMap<Namespace, f32>,
    pub default_threshold: f32,
    pub recent_window: Duration,
    pub cache_capacity: usize,
    pub min_semantic_length: usize,
}

Configuration for the deduplication service.

Environment Variables

Variable	Type	Default	Description
SUBCOG_DEDUP_ENABLED	bool	true	Enable deduplication
SUBCOG_DEDUP_THRESHOLD_DECISIONS	f32	0.92	Threshold for decisions namespace
SUBCOG_DEDUP_THRESHOLD_PATTERNS	f32	0.90	Threshold for patterns namespace
SUBCOG_DEDUP_THRESHOLD_LEARNINGS	f32	0.88	Threshold for learnings namespace
SUBCOG_DEDUP_THRESHOLD_DEFAULT	f32	0.90	Default threshold
SUBCOG_DEDUP_TIME_WINDOW_SECS	u64	300	Recent capture window
SUBCOG_DEDUP_CACHE_CAPACITY	usize	1000	LRU cache size
SUBCOG_DEDUP_MIN_SEMANTIC_LENGTH	usize	50	Min content length for semantic check

Example

use subcog::services::deduplication::DeduplicationConfig;
use subcog::models::Namespace;

let config = DeduplicationConfig::default();
assert!(config.enabled);
assert_eq!(config.default_threshold, 0.90);
assert_eq!(config.get_threshold(Namespace::Decisions), 0.92);

Fields

enabled: bool

Enable/disable entire deduplication.

similarity_thresholds: HashMap<Namespace, f32>

Per-namespace similarity thresholds.

default_threshold: f32

Default threshold when namespace not configured.

recent_window: Duration

Recent capture time window.

cache_capacity: usize

Recent capture cache capacity.

min_semantic_length: usize

Minimum content length for semantic check.

Content shorter than this will skip semantic similarity checking and rely only on exact match and recent capture detection.

Implementations

impl DeduplicationConfig

pub fn from_env() -> Self

Creates a new configuration from environment variables.

Falls back to defaults for any unset variables.

Example

use subcog::services::deduplication::DeduplicationConfig;

let config = DeduplicationConfig::from_env();
// Config is populated from environment with defaults

pub fn get_threshold(&self, namespace: Namespace) -> f32

Gets the similarity threshold for a namespace.

Returns the namespace-specific threshold if configured, otherwise returns the default threshold.

Arguments

• namespace - The namespace to get the threshold for

Example

use subcog::services::deduplication::DeduplicationConfig;
use subcog::models::Namespace;

let config = DeduplicationConfig::default();
assert_eq!(config.get_threshold(Namespace::Decisions), 0.92);
assert_eq!(config.get_threshold(Namespace::Patterns), 0.90);

pub const fn with_enabled(self, enabled: bool) -> Self

Builder method to set enabled state.

pub fn with_threshold(self, namespace: Namespace, threshold: f32) -> Self

Builder method to set a namespace threshold.

pub const fn with_default_threshold(self, threshold: f32) -> Self

Builder method to set the default threshold.

pub const fn with_recent_window(self, duration: Duration) -> Self

Builder method to set the recent window duration.

pub const fn with_cache_capacity(self, capacity: usize) -> Self

Builder method to set the cache capacity.

pub const fn with_min_semantic_length(self, length: usize) -> Self

Builder method to set the minimum semantic length.

Trait Implementations

impl Clone for DeduplicationConfig

fn clone(&self) -> DeduplicationConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for DeduplicationConfig

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

Formats the value using the given formatter.

impl Default for DeduplicationConfig

fn default() -> Self

Returns the “default value” for a type.