Crate harness_core 

Core traits and types for the harness agent framework.

This crate is intentionally dependency-light and runtime-agnostic so every upper-layer crate can share a single source of truth for the framework’s vocabulary.

See DESIGN.md at the workspace root for architectural intent.

Re-exports

pub use compactor::*;

pub use context::*;

pub use embed::*;

pub use error::*;

pub use event::*;

pub use guide::*;

pub use hook::*;

pub use memory::*;

pub use model::*;

pub use profile::*;

pub use recall::*;

pub use recall_testkit::*;

pub use sensor::*;

pub use signal::*;

pub use skill::*;

pub use tool::*;

pub use world::*;

Modules

compactor

context

embed

Optional embeddings trait. Strictly opt-in — nothing in Model, AgentLoop, Hook, Guide, Sensor, or Memory references this. Code that wants semantic search / vector recall holds an Arc<dyn Embedder> explicitly; everything else compiles without ever touching this module.

error

event

guide

hook

memory

Long-term, cross-session memory.

model

profile

User profile — ambient context every agent inherits.

recall

Cross-session conversation recall.

recall_testkit

Reusable conformance suite for crate::RecallStore backends. Each backend crate calls recall_contract(store) from a #[tokio::test] so all impls are held to identical behaviour — including the privacy-critical owner isolation.

sensor

signal

skill

Skill trait — strictly aligned with the agentskills.io specification.

tool

world

Enums

Execution

How a control-plane component executes: