test: add smoke test based on examples/samples-readme.md

Signed-off-by: Nick Hale <[email protected]>

Author: njhale

pkg/tests/judge/judge.go

@@ -84,10 +84,10 @@ func New[T any](client *openai.Client) (*Judge[T], error) {
 }
 
 func (j *Judge[T]) Equal(ctx context.Context, expected, actual T, criteria string) (equal bool, reasoning string, err error) {
-	comparisonJSON, err := json.MarshalIndent(&comparison[T]{
+	comparisonJSON, err := json.Marshal(&comparison[T]{
 		Expected: expected,
 		Actual:   actual,
-	}, "", "    ")
+	})
 	if err != nil {
 		return false, "", fmt.Errorf("failed to marshal judge testcase JSON: %w", err)
 	}

pkg/tests/smoke/smoke_test.go

@@ -83,7 +83,6 @@ func TestSmoke(t *testing.T) {
 				actualEvents,
 				`
 - disregard differences in timestamps, generated IDs, natural language verbiage, and event order
-- omit callProgress events from the comparision
 - the overall stream of events and set of tools called should roughly match
 - arguments passed in tool calls should be roughly the same
 - the final callFinish event should be semantically similar
@@ -175,6 +174,11 @@ func getActualEvents(t *testing.T, eventsFile string) []event {
 
 		var e event
 		require.NoError(t, json.Unmarshal([]byte(line), &e))
+
+		if e.Type == runner.EventTypeCallProgress {
+			continue
+		}
+
 		events = append(events, e)
 	}