Enable bounded output repair in the engine

engine_test.go

@@ -3486,9 +3486,10 @@ extra_params:
 }
 
 type fakeLLMClient struct {
-	response *promptkit.GenerateResponse
-	err      error
-	requests []promptkit.GenerateRequest
+	response  *promptkit.GenerateResponse
+	responses []*promptkit.GenerateResponse
+	err       error
+	requests  []promptkit.GenerateRequest
 }
 
 type recordingArtifactReader struct {
@@ -3664,5 +3665,12 @@ func (f *fakeLLMClient) Generate(_ context.Context, req promptkit.GenerateReques
 	if f.err != nil {
 		return nil, f.err
 	}
+	if len(f.responses) > 0 {
+		index := len(f.requests) - 1
+		if index >= len(f.responses) {
+			return nil, fmt.Errorf("no response configured for generation %d", index+1)
+		}
+		return f.responses[index], nil
+	}
 	return f.response, nil
 }