agentcarousel 0.2.2

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
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42

use assert_cmd::Command;
use std::fs;
use std::path::PathBuf;

fn temp_fixture_dir() -> PathBuf {
    tempfile::tempdir().expect("temp dir").keep()
}

#[test]
fn test_command_returns_failure_on_bad_output() {
    let dir = temp_fixture_dir();
    let fixture_path = dir.join("example-fail.yaml");
    fs::write(
        &fixture_path,
        r#"schema_version: 1
skill_or_agent: example-skill
cases:
  - id: example-skill/positive
    input:
      messages:
        - role: user
          content: "hello"
    expected:
      output:
        - kind: contains
          value: "does-not-exist"
"#,
    )
    .expect("write fixture");

    Command::cargo_bin("agentcarousel")
        .unwrap()
        .args([
            "test",
            fixture_path.to_str().expect("fixture path"),
            "--mock-dir",
            "mocks",
        ])
        .assert()
        .failure()
        .code(1);
}