agentcarousel 0.2.3

Evaluate agents and skills with YAML fixtures, run cases (mock or live), and keep run rows in SQLite for reports and evidence export.
Documentation 
1
2
3
4
5
6
7
8
9
10
11
12

//! Shared domain types for fixtures, runs, traces, and metrics, plus [`CoreError`] and
//! [`judge_provider`] helpers for LLM-backed judges.

pub mod error;
pub mod ids;
pub mod judge_provider;
pub mod models;

pub use error::CoreError;
pub use ids::new_run_id;
pub use judge_provider::{judge_key_candidates, judge_provider_from_model, JudgeProvider};
pub use models::*;