feat(ssa): Complete QPER architecture - Query, Planner, Execute, Reflection layers

Implement the full QPER intelligent analysis pipeline:

- Phase E+: Block-based standardization for all 7 R tools, DynamicReport renderer, Word export enhancement

- Phase Q: LLM intent parsing with dynamic Zod validation against real column names, ClarificationCard component, DataProfile is_id_like tagging

- Phase P: ConfigLoader with Zod schema validation and hot-reload API, DecisionTableService (4-dimension matching), FlowTemplateService with EPV protection, PlannedTrace audit output

- Phase R: ReflectionService with statistical slot injection, sensitivity analysis conflict rules, ConclusionReport with section reveal animation, conclusion caching API, graceful R error classification

End-to-end test: 40/40 passed across two complete analysis scenarios.

Co-authored-by: Cursor <cursoragent@cursor.com>

frontend-v2/src/modules/ssa/components/SSAChatPane.tsx

@@ -29,6 +29,8 @@ import { useWorkflow } from '../hooks/useWorkflow';
 import type { SSAMessage } from '../types';
 import { TypeWriter } from './TypeWriter';
 import { DataProfileCard } from './DataProfileCard';
+import { ClarificationCard } from './ClarificationCard';
+import type { ClarificationCardData, IntentResult } from '../types';
 
 export const SSAChatPane: React.FC = () => {
   const navigate = useNavigate();
@@ -46,15 +48,21 @@ export const SSAChatPane: React.FC = () => {
     error,
     setError,
     addToast,
+    addMessage,
     selectAnalysisRecord,
     dataProfile,
     dataProfileLoading,
   } = useSSAStore();
 
   const { uploadData, generatePlan, isUploading, uploadProgress } = useAnalysis();
-  const { generateDataProfile, generateWorkflowPlan, isProfileLoading, isPlanLoading } = useWorkflow();
+  const { generateDataProfile, generateWorkflowPlan, parseIntent, handleClarify, isProfileLoading, isPlanLoading } = useWorkflow();
   const [inputValue, setInputValue] = useState('');
   const [uploadStatus, setUploadStatus] = useState<'idle' | 'uploading' | 'parsing' | 'success' | 'error'>('idle');
+  const [pendingClarification, setPendingClarification] = useState<{
+    cards: ClarificationCardData[];
+    originalQuery: string;
+    intent: IntentResult;
+  } | null>(null);
   const fileInputRef = useRef<HTMLInputElement>(null);
   const chatEndRef = useRef<HTMLDivElement>(null);
   const messagesContainerRef = useRef<HTMLDivElement>(null);
@@ -143,20 +151,83 @@ export const SSAChatPane: React.FC = () => {
   const handleSend = async () => {
     if (!inputValue.trim()) return;
 
+    const query = inputValue;
+    setInputValue('');
+
     try {
-      // Phase 2A: 如果已有 session，使用多步骤工作流规划
       if (currentSession?.id) {
-        await generateWorkflowPlan(currentSession.id, inputValue);
+        // Phase Q: 先做意图解析，低置信度时追问
+        const intentResp = await parseIntent(currentSession.id, query);
+
+        if (intentResp.needsClarification && intentResp.clarificationCards?.length > 0) {
+          addMessage({
+            id: crypto.randomUUID(),
+            role: 'user',
+            content: query,
+            createdAt: new Date().toISOString(),
+          });
+          addMessage({
+            id: crypto.randomUUID(),
+            role: 'assistant',
+            content: `我大致理解了你的意图（${intentResp.intent.reasoning}），但为了生成更精确的分析方案，想确认几个细节：`,
+            createdAt: new Date().toISOString(),
+          });
+          setPendingClarification({
+            cards: intentResp.clarificationCards,
+            originalQuery: query,
+            intent: intentResp.intent,
+          });
+          return;
+        }
+
+        // 置信度足够 → 直接生成工作流计划
+        await generateWorkflowPlan(currentSession.id, query);
       } else {
-        // 没有数据时，使用旧流程
-        await generatePlan(inputValue);
+        await generatePlan(query);
       }
-      setInputValue('');
     } catch (err: any) {
       addToast(err?.message || '生成计划失败', 'error');
     }
   };
 
+  const handleClarificationSelect = async (selections: Record<string, string>) => {
+    if (!currentSession?.id || !pendingClarification) return;
+
+    setPendingClarification(null);
+
+    const selectedLabel = Object.values(selections).join(', ');
+    addMessage({
+      id: crypto.randomUUID(),
+      role: 'user',
+      content: selectedLabel,
+      createdAt: new Date().toISOString(),
+    });
+
+    try {
+      const resp = await handleClarify(
+        currentSession.id,
+        pendingClarification.originalQuery,
+        selections
+      );
+
+      if (resp.needsClarification && resp.clarificationCards?.length > 0) {
+        addMessage({
+          id: crypto.randomUUID(),
+          role: 'assistant',
+          content: '还需要确认一下：',
+          createdAt: new Date().toISOString(),
+        });
+        setPendingClarification({
+          cards: resp.clarificationCards,
+          originalQuery: pendingClarification.originalQuery,
+          intent: resp.intent,
+        });
+      }
+    } catch (err: any) {
+      addToast(err?.message || '处理追问失败', 'error');
+    }
+  };
+
   const handleKeyDown = (e: React.KeyboardEvent) => {
     if (e.key === 'Enter' && !e.shiftKey) {
       e.preventDefault();
@@ -308,6 +379,20 @@ export const SSAChatPane: React.FC = () => {
             旧的"数据挂载成功消息"已移除，避免在没有用户输入时就显示 SAP 卡片
           */}
 
+          {/* Phase Q: 追问卡片 */}
+          {pendingClarification && (
+            <div className="message-row assistant">
+              <div className="avatar-col"><Bot size={18} /></div>
+              <div className="msg-content">
+                <ClarificationCard
+                  cards={pendingClarification.cards}
+                  onSelect={handleClarificationSelect}
+                  disabled={isLoading}
+                />
+              </div>
+            </div>
+          )}
+
           {/* 自动滚动锚点与占位垫片 - 解决底部输入框遮挡的终极方案 */}
           <div ref={chatEndRef} className="scroll-spacer" />
         </div>