Crate kvlar_core 

kvlar-core

Core policy engine for Kvlar. Evaluates agent actions against YAML-based security policies. Pure logic — no I/O, no async, fully deterministic.

Architecture

• Policy: A set of rules defining what agents can and cannot do
• Action: A description of something an agent wants to do (tool call, data access, etc.)
• Decision: The engine’s verdict — Allow, Deny, or RequireApproval
• Engine: Evaluates actions against loaded policies

Re-exports

pub use action::Action;

pub use approval::ApprovalRequest;

pub use approval::ApprovalResponse;

pub use decision::Decision;

pub use decision::ErrorDetail;

pub use engine::Engine;

pub use error::KvlarError;

pub use policy::Policy;

Modules

action

Action types representing what an agent wants to do.

approval

Approval types for human-in-the-loop decisions.

decision

Decision types — the output of policy evaluation.

engine

Policy evaluation engine — the heart of Kvlar.

error

Error types for kvlar-core.

policy

Policy definitions — rules that govern agent behavior.

testing

Policy testing framework — types and runner.