vtcode-eval 0.141.2

Agent evaluation framework for VT Code: pass@k / pass^k metrics, capability and regression evals, and environment-based outcome verification.
Documentation 
1
2
3
4
5
6
7
8
9
10
11
12
13

pub mod environment;
pub mod executor;
pub mod metric;
pub mod report;
pub mod suite;
pub mod task;

pub use environment::{CommandProbe, EnvironmentProbe, FileExistsProbe, GitCleanProbe};
pub use executor::{EvalExecutor, run_suite};
pub use metric::{EvalMetric, aggregate_metrics, compute_metric, pass_all_k, pass_at_k};
pub use report::{EvalReport, SuiteReport, TaskReport, build_task_report};
pub use suite::EvalSuite;
pub use task::{EvalCategory, EvalRunResult, EvalTask, RunOutcome};