diff --git a/cmd/membench/eval_llm.go b/cmd/membench/eval_llm.go
index 430548003..7318b76bb 100644
--- a/cmd/membench/eval_llm.go
+++ b/cmd/membench/eval_llm.go
@@ -38,7 +38,11 @@ func generateAnswer(ctx context.Context, client *LLMClient, contextText, questio
 
 // judgeAnswer asks the LLM to score the candidate answer vs the gold answer.
 // Returns a score from 0.0 to 1.0.
-func judgeAnswer(ctx context.Context, client *LLMClient, question, goldAnswer, candidateAnswer string) (float64, error) {
+func judgeAnswer(
+	ctx context.Context,
+	client *LLMClient,
+	question, goldAnswer, candidateAnswer string,
+) (float64, error) {
 	userPrompt := fmt.Sprintf(
 		"Question: %s\n\nReference Answer: %s\n\nCandidate Answer: %s\n\nScore:",
 		question, goldAnswer, candidateAnswer,
diff --git a/cmd/membench/llm_client.go b/cmd/membench/llm_client.go
index 57734ae5b..cb7b1ee2a 100644
--- a/cmd/membench/llm_client.go
+++ b/cmd/membench/llm_client.go
@@ -46,11 +46,11 @@ func NewLLMClient(opts LLMClientOptions) *LLMClient {
 }
 
 type chatRequest struct {
-	Model              string                 `json:"model"`
-	Messages           []chatMessage          `json:"messages"`
-	Temperature        float64                `json:"temperature"`
-	MaxTokens          int                    `json:"max_tokens"`
-	ChatTemplateKwargs map[string]interface{} `json:"chat_template_kwargs,omitempty"`
+	Model              string         `json:"model"`
+	Messages           []chatMessage  `json:"messages"`
+	Temperature        float64        `json:"temperature"`
+	MaxTokens          int            `json:"max_tokens"`
+	ChatTemplateKwargs map[string]any `json:"chat_template_kwargs,omitempty"`
 }
 
 type chatMessage struct {
@@ -81,7 +81,7 @@ func (c *LLMClient) Complete(ctx context.Context, systemPrompt, userPrompt strin
 		MaxTokens:   512,
 	}
 	if c.NoThinking {
-		body.ChatTemplateKwargs = map[string]interface{}{
+		body.ChatTemplateKwargs = map[string]any{
 			"enable_thinking": false,
 		}
 	}
diff --git a/cmd/membench/main.go b/cmd/membench/main.go
index ff1970d52..c85105fb2 100644
--- a/cmd/membench/main.go
+++ b/cmd/membench/main.go
@@ -54,11 +54,13 @@ func main() {
 	evalCmd.Flags().StringVar(&flagOut, "out", "./bench-out", "output working directory")
 	evalCmd.Flags().StringVar(&flagMode, "mode", "all", "modes to evaluate: legacy, seahorse, or all")
 	evalCmd.Flags().IntVar(&flagBudget, "budget", 4000, "token budget for retrieval")
-	evalCmd.Flags().StringVar(&flagEvalMode, "eval-mode", "token", "evaluation mode: token (direct match) or llm (LLM-as-Judge)")
+	evalCmd.Flags().
+		StringVar(&flagEvalMode, "eval-mode", "token", "evaluation mode: token (direct match) or llm (LLM-as-Judge)")
 	evalCmd.Flags().StringVar(&flagAPIBase, "api-base", "", "OpenAI-compatible API base URL (env: MEMBENCH_API_BASE)")
 	evalCmd.Flags().StringVar(&flagAPIKey, "api-key", "", "API key for the LLM endpoint (env: MEMBENCH_API_KEY)")
 	evalCmd.Flags().StringVar(&flagModel, "model", "", "model name for LLM eval (env: MEMBENCH_MODEL)")
-	evalCmd.Flags().BoolVar(&flagNoThinking, "no-thinking", false, "disable thinking mode via chat_template_kwargs (llama.cpp + Qwen)")
+	evalCmd.Flags().
+		BoolVar(&flagNoThinking, "no-thinking", false, "disable thinking mode via chat_template_kwargs (llama.cpp + Qwen)")
 	evalCmd.Flags().IntVar(&flagLimit, "limit", 0, "max QA questions per sample (0 = all)")
 
 	reportCmd := &cobra.Command{
@@ -77,11 +79,13 @@ func main() {
 	runCmd.Flags().StringVar(&flagOut, "out", "./bench-out", "output working directory")
 	runCmd.Flags().StringVar(&flagMode, "mode", "all", "modes to run: legacy, seahorse, or all")
 	runCmd.Flags().IntVar(&flagBudget, "budget", 4000, "token budget for retrieval")
-	runCmd.Flags().StringVar(&flagEvalMode, "eval-mode", "token", "evaluation mode: token (direct match) or llm (LLM-as-Judge)")
+	runCmd.Flags().
+		StringVar(&flagEvalMode, "eval-mode", "token", "evaluation mode: token (direct match) or llm (LLM-as-Judge)")
 	runCmd.Flags().StringVar(&flagAPIBase, "api-base", "", "OpenAI-compatible API base URL (env: MEMBENCH_API_BASE)")
 	runCmd.Flags().StringVar(&flagAPIKey, "api-key", "", "API key for the LLM endpoint (env: MEMBENCH_API_KEY)")
 	runCmd.Flags().StringVar(&flagModel, "model", "", "model name for LLM eval (env: MEMBENCH_MODEL)")
-	runCmd.Flags().BoolVar(&flagNoThinking, "no-thinking", false, "disable thinking mode via chat_template_kwargs (llama.cpp + Qwen)")
+	runCmd.Flags().
+		BoolVar(&flagNoThinking, "no-thinking", false, "disable thinking mode via chat_template_kwargs (llama.cpp + Qwen)")
 	runCmd.Flags().IntVar(&flagLimit, "limit", 0, "max QA questions per sample (0 = all)")
 
 	rootCmd.AddCommand(ingestCmd, evalCmd, reportCmd, runCmd)