aether-evals 0.2.10

Dockerized eval harness for Aether AI agents
Documentation
1
2
3
4
5
6
7
8
9
10
11
mod agent;
mod docker_agent;
mod env;
mod fake_agent;
mod transcript;

pub use agent::{Agent, AgentRunResult, RunError};
pub use docker_agent::{AETHER_EVAL_CWD_ENV, AETHER_EVAL_TASK_PROMPT_ENV, AETHER_EVAL_WORKSPACE_ROOT_ENV, DockerAgent};
pub use env::{CONTAINER_AETHER_HOME, default_eval_env_vars};
pub use fake_agent::FakeAgent;
pub use transcript::{ToolCall, Transcript, TranscriptError};