feat: 记录并展示每次生成消耗的LLM调用次数（llm_calls）

src/lib/ai-analysis-api.ts

@@ -15,6 +15,7 @@ export interface AiReport {
   model: string;
   tokens_used: number;
   generation_count?: number;
+  llm_calls?: number | null;
   issue_number?: number;
   created_at: string;
   updated_at?: string | null;

src/routes/ai-analysis.tsx

@@ -132,6 +132,7 @@ function AiAnalysisPage() {
                     <span className="truncate">{report.updated_at || report.created_at}</span>
                   </span>
                   <span>{report.tokens_used?.toLocaleString()} tokens</span>
+                  {report.llm_calls ? <span>{report.llm_calls} 次 LLM 调用</span> : null}
                   {(report.generation_count ?? 1) > 1 && (
                     <span>第 {report.generation_count} 次生成</span>
                   )}