feat(cli): kebab eval variants <run_id> — 변형 일관성 진단 리포트

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
2026-05-29 17:45:10 +00:00
parent 82e02aa4fe
commit 0988f66331

View File

@@ -422,6 +422,14 @@ enum EvalWhat {
/// into `eval_runs.aggregate_json` (P5-2).
Aggregate { run_id: String },
/// Compute variant-consistency metrics for a stored run and print
/// a Markdown report (or JSON with `--json`).
Variants {
run_id: String,
#[arg(long)]
json: bool,
},
/// Diff two stored runs (P5-2). Default output is a Markdown
/// summary; use `--json` (top-level flag) for the raw report.
Compare {
@@ -1392,6 +1400,16 @@ fn run(cli: &Cli) -> anyhow::Result<()> {
Ok(())
}
EvalWhat::Variants { run_id, json } => {
let rep = kebab_eval::compute_variant_consistency_with_config(&cfg, run_id)?;
if *json {
println!("{}", serde_json::to_string_pretty(&rep)?);
} else {
print!("{}", kebab_eval::render_variants_md(&rep));
}
Ok(())
}
EvalWhat::Compare {
run_a,
run_b,