feat: C-vs-A eval comparison; go/no-go metric
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
@@ -0,0 +1,12 @@
|
||||
use std::process::Command;
|
||||
|
||||
#[test]
|
||||
fn eval_mode_c_runs_and_reports_billable_recall() {
|
||||
let out = Command::new(env!("CARGO_BIN_EXE_alpha-id"))
|
||||
.args(["eval", "--mode", "c", "--cases", "30"])
|
||||
.arg("--config").arg("config/default.toml")
|
||||
.output().unwrap();
|
||||
assert!(out.status.success(), "stderr: {}", String::from_utf8_lossy(&out.stderr));
|
||||
let s = String::from_utf8_lossy(&out.stdout);
|
||||
assert!(s.contains("BillableRecall@10="));
|
||||
}
|
||||
Reference in New Issue
Block a user