Struct LearningConfig 

pub struct LearningConfig {
    pub review_model: Arc<dyn Model>,
    pub tools: Vec<Arc<dyn Tool>>,
    pub review_prompt: String,
    pub nudge_interval: u32,
    pub max_iters: u32,
}

Configuration for the learning loop. The app injects the review model + the white-listed tools the review subagent may call (typically a SkillManageTool

• a RememberThisTool); harness-loop never depends on those crates.

Fields

review_model: Arc<dyn Model>

tools: Vec<Arc<dyn Tool>>

review_prompt: String

nudge_interval: u32

max_iters: u32

Implementations

impl LearningConfig

pub fn new(review_model: Arc<dyn Model>) -> Self

pub fn with_tool(self, t: Arc<dyn Tool>) -> Self

pub fn with_nudge_interval(self, n: u32) -> Self

pub fn with_review_prompt(self, p: impl Into<String>) -> Self

pub fn with_max_iters(self, n: u32) -> Self