fix(agents): only run InputGate on first message to prevent mid-conversation misclassification

Short follow-up answers like "计算机，信息技术" were being classified as
OFF_TOPIC (0.85) because the InputGate has no conversation context. Now the
gate only runs when there are no previous messages (first message in conversation).
Mid-conversation topic management is handled by the Coordinator prompt.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

packages/services/conversation-service/src/infrastructure/agents/coordinator/coordinator-agent.service.ts

@@ -196,13 +196,17 @@ export class CoordinatorAgentService implements OnModuleInit {
     const startTime = Date.now();
 
     try {
-      // 0. Input Gate — 轻量级预检
+      // 0. Input Gate — 仅对首条消息运行（无历史对话时）
+      //    已在对话中的用户由 Coordinator prompt 管理话题，避免短回复被误判偏题
+      const hasPreviousMessages = context.previousMessages && context.previousMessages.length > 0;
+      if (!hasPreviousMessages) {
         const gateResult = await this.inputGate.classify(userContent);
         if (gateResult.classification !== 'ON_TOPIC' && gateResult.fixedResponse) {
           yield { type: 'text', content: gateResult.fixedResponse };
           yield { type: 'end', inputTokens: 0, outputTokens: 0 };
           return;
         }
+      }
 
       // 1. Build messages from conversation history (async: 文本附件需下载内容)
       const messages = await this.buildMessages(context, userContent, attachments);