fix(voice): speak first, then keep Level 2 skeleton and boundary semantics

Natal answers were opening on parameter tables, and rectification turns were one-sentence legal copy. Centralize user-facing strings, keep representative-minute and question-slot red lines, and stop duplicating the opening collect prompt as a second assistant message.

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

frontend/src/app/api/consult/route.ts

@@ -1195,7 +1195,7 @@ export async function POST(request: Request) {
         content: [
           currentTimeContext(requestTime),
           name ? `用户称呼：${name}` : "",
-          "请按 skill Level 2 模板回答下面的问题：原始结构、六步宫位、Yoga 表、时机、综合、文末技法审计表，然后才是现代生活措辞。星盘事实只使用系统里已经注入的计算结果，不要复述内部字段、JSON 或再跑一遍咨询流程。",
+          "先用 3–6 句口语直接回答下面的问题，不要加标题；然后再按 skill Level 2 骨架写：原始结构、六步宫位、Yoga 表、时机、综合、文末技法审计表，最后才是现代生活。骨架不可省略。星盘事实只使用系统里已经注入的计算结果，不要复述内部字段、JSON 或再跑一遍咨询流程。",
           resolvedQuestion.modelQuestion,
         ].filter(Boolean).join("\n"),
       },

frontend/src/app/api/rectification/agent/route.ts

@@ -40,6 +40,7 @@ import {
 import { persistServerOwnedFocus, openQuestionFromPersistedFocus, isCollectFocusSchema, isRenderableChoiceOpenQuestion } from "@/lib/rectification-agentic/v9/server-focus";
 import { buildMethodFollowupPlan } from "@/lib/rectification-agentic/v9/method-followup";
 import { isNonConvergingRangeOffer, nonConvergingRangeNarration } from "@/lib/rectification-agentic/core/rectification-decision";
+import { RECTIFICATION_USER_COPY } from "@/lib/rectification-agentic/user-copy";
 import {
   awaitTurnExitBeforeResponse,
   finalizeSuccessfulTurnExit,
@@ -351,7 +352,7 @@ export async function POST(request: Request) {
           classified = null;
         }
         if (!classified || classified.intent === "unclear") {
-          const narration = "我没能确定这句话是否在回答当前问题。请点选下面的选项，或换一种说法。";
+          const narration = RECTIFICATION_USER_COPY.unclearFocusReply;
           await persistV9DeterministicTurn(accounting, userId, caseId, {
             requestId,
             userMessage: parsed.data.message ?? null,
@@ -361,11 +362,11 @@ export async function POST(request: Request) {
         }
         if (classified.intent === "answer_current_focus") {
           if (!classified.answer_class) {
-            return completedMessageResponse("当前问题已更新，请刷新后重新作答。", requestId, caseId);
+            return completedMessageResponse(RECTIFICATION_USER_COPY.questionUpdated, requestId, caseId);
           }
           const optionId = optionIdForAnswerClass(focus, classified.answer_class);
           if (!optionId) {
-            return completedMessageResponse("当前问题已更新，请刷新后重新作答。", requestId, caseId);
+            return completedMessageResponse(RECTIFICATION_USER_COPY.questionUpdated, requestId, caseId);
           }
           const continueToAgent = shouldContinueAgentForDatedEvent(classified);
           const previous = previousInferenceFromReceipt(dossier.latestResult?.decisionReceipt ?? null);
@@ -514,7 +515,7 @@ export async function POST(request: Request) {
                 return completedMessageResponse(applied.narration, requestId, caseId);
               }
             }
-            const narration = "请点选下面的选项作答。点选和一句话回答会按同一规则计入当前区分题。";
+            const narration = RECTIFICATION_USER_COPY.choicePrompt;
             await persistV9DeterministicTurn(accounting, userId, caseId, {
               requestId,
               userMessage: parsed.data.message ?? null,
@@ -722,6 +723,7 @@ export async function POST(request: Request) {
               userId,
               caseId,
               action,
+              assistantBodyPresent: Boolean(result.answerText?.trim()),
             });
           } catch (error) {
             const code = error instanceof RectificationToolServiceError ? error.code : "run_failed";