Struct OrchestratorConfig 

pub struct OrchestratorConfig {
    pub enabled: bool,
    pub max_context_tokens: usize,
    pub auto_optimize: bool,
    pub enable_metrics: bool,
    pub session_timeout_seconds: u64,
    pub enable_smart_retrieval: bool,
    pub smart_retrieval_config: SmartRetrievalConfig,
    pub ctx_size: u32,
}

Configuration for the orchestrator

Fields

enabled: bool

max_context_tokens: usize

auto_optimize: bool

enable_metrics: bool

session_timeout_seconds: u64

enable_smart_retrieval: bool

Enable smart retrieval optimization (default: true)

smart_retrieval_config: SmartRetrievalConfig

Smart retrieval configuration

ctx_size: u32

Model context window size in tokens — 0 means not set (use defaults)

Implementations

impl OrchestratorConfig

pub fn from_ctx_size(ctx_size: u32) -> Self

Derive token limits from the model’s context window. 75% of CTX_SIZE is the ceiling for the total context sent to the LLM, leaving 25% headroom for the model’s own generation output.

Trait Implementations

impl Clone for OrchestratorConfig

fn clone(&self) -> OrchestratorConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for OrchestratorConfig

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

Formats the value using the given formatter.

impl Default for OrchestratorConfig

fn default() -> Self

Returns the “default value” for a type.