Merge the eval label and kill script fixes

internal/phraser/eval/llmphraser_test.go

@@ -7,6 +7,7 @@ import (
 	"testing"
 	"time"
 
+	"github.com/kami/maven/internal/llm"
 	"github.com/kami/maven/internal/phraser"
 )
 
@@ -32,6 +33,7 @@ func TestLLMPhrasingBaseline(t *testing.T) {
 	// case as a phrasing error and read as "the model cannot phrase".
 	noProxyLoopback(t)
 
+	ctx := context.Background()
 	f, err := Load()
 	if err != nil {
 		t.Fatalf("Load: %v", err)
@@ -44,7 +46,19 @@ func TestLLMPhrasingBaseline(t *testing.T) {
 	p := phraser.NewLLMPhraserAt(base, cfg)
 	defer p.Close()
 
-	rep, err := Score(context.Background(), "llm (0.8B, built-in persona)", p, f)
+	// Label the run with whatever gguf the server actually has loaded. It used
+	// to say "0.8B" no matter what, so two runs of two different models came
+	// out named the same and were easy to mix up when comparing.
+	model, err := llm.ModelID(ctx, base)
+	if err != nil {
+		// An unlabelled score is still a score, but say so loudly — a made-up
+		// name in a bake-off table is worse than no name.
+		t.Logf("could not read model id from %s: %v — report will say %q", base, err, llm.UnknownModel)
+		model = llm.UnknownModel
+	}
+	t.Logf("scoring model %s at %s", model, base)
+
+	rep, err := Score(ctx, "llm ("+model+", built-in persona)", p, f)
 	if err != nil {
 		t.Fatalf("Score: %v", err)
 	}