Use new evals cmd

Makefile

@@ -8,7 +8,8 @@ cover:
 
 .PHONY: evaluate
 evaluate:
-	@go test -json -run TestEval ./... | evals
+	go test -run TestEval ./...
+	evals | glow
 
 .PHONY: lint
 lint:

eval/run.go

@@ -75,6 +75,7 @@ func (e *E) Score(s Sample, scorer Scorer) Result {
 }
 
 type logLine struct {
+	Name     string
 	Sample   Sample
 	Result   Result
 	Duration time.Duration
@@ -90,6 +91,7 @@ func (e *E) Log(s Sample, r Result) {
 	e.T.Helper()
 
 	l := logLine{
+		Name:     e.T.Name(),
 		Sample:   s,
 		Result:   r,
 		Duration: time.Since(e.start),

go.mod

@@ -9,7 +9,7 @@ require (
 	github.com/openai/openai-go v0.1.0-alpha.45
 	google.golang.org/api v0.216.0
 	maragu.dev/env v0.2.0
-	maragu.dev/evals v0.0.0-20250110140605-d045751e4b4d
+	maragu.dev/evals v0.0.0-20250114114008-6c73fea1551c
 	maragu.dev/is v0.2.0
 )
 

go.sum

@@ -128,8 +128,8 @@ maragu.dev/env v0.2.0 h1:nQKitDEB65ArZsh6E7vxzodOqY9bxEVFdBg+tskS1ys=
 maragu.dev/env v0.2.0/go.mod h1:t5CCbaEnjCM5mewiAVVzTS4N+oXTus2+SRnzKQbQVME=
 maragu.dev/errors v0.3.0 h1:huI+n+ddMfVgQFD+cEqIPaozUlfz3TkfgpkssNip5G0=
 maragu.dev/errors v0.3.0/go.mod h1:cygLiyNnq4ofF3whYscilo2ecUADCaUQXwvwFrMOhmM=
-maragu.dev/evals v0.0.0-20250110140605-d045751e4b4d h1:q8VMFOPZIJNnbFYRK7OWRWVvDrl3RtyCUYOg5/Fhlmg=
-maragu.dev/evals v0.0.0-20250110140605-d045751e4b4d/go.mod h1:zEwfRDpHBpRcgkG9pBzoZlnETLYRt9Shj+cIAFNizW8=
+maragu.dev/evals v0.0.0-20250114114008-6c73fea1551c h1:huPj1S5RhqgpbBAd3aCLfdVie3ZsU8Du7kepL2ZtDUQ=
+maragu.dev/evals v0.0.0-20250114114008-6c73fea1551c/go.mod h1:+2Y3dYZ6oANM+cL88kFxaPD1H7rq3FXOrI3NOeNKaZ8=
 maragu.dev/is v0.2.0 h1:poeuVEA5GG3vrDpGmzo2KjWtIMZmqUyvGnOB0/pemig=
 maragu.dev/is v0.2.0/go.mod h1:bviaM5S0fBshCw7wuumFGTju/izopZ/Yvq4g7Klc7y8=
 maragu.dev/migrate v0.6.0 h1:gJLAIVaRh9z9sN55Q2sWwScpEH+JsT6N0L1DnzedXFE=