fix(rectification): prevent collect focus dead-end after choice answers

docs/BUG_HISTORY.md

@@ -6895,18 +6895,18 @@
 - 复发自：BUG-441
 - 修复版本：待发布
 
-## BUG-450 | 非收敛区间提议无数值、无时间卡、无下一问
+## BUG-450 | 点选题答完后的非收敛区间提议卡死
 
 - 状态：resolved
 - 首次发现：2026-08-30
 - 最近更新：2026-08-30
-- 影响面：`offerRangeWithoutAdopt`、`persistNextInterviewIfIdle`、`projectRectificationChoiceCard`、`buildCandidateContrastPacket`、出题层 `rankRenderableDiscriminators`、POST `/api/rectification/agent` 消息快路径
-- 用户现象：答完最后一问后助手说「可以先按当前区间看盘，也可以再补一件记得时间的经历」，界面既没有可采用的时间卡，也没有下一个问题，正文里连区间数值都没有，对话到此为止。
-- 触发条件：训练门已开、occupation 等阻塞覆盖未齐、`datedMethodCollectOpen` 为假、引擎已放行 accept/propose、`probe === null`、`canOfferRange=true` 且 `canAdopt` / `selectionAllowed` / `proposeAllowed` 全假。本例活跃候选 04:47/04:51/04:53/04:59，family 已 declined，账本已有 2020 career 与 2024 relationship。
-- 根因：三段叠加。(1) P0 消费端死胡同：`offerRangeWithoutAdopt` 把 `canOfferRange` 设真却把 `canAdopt`/`selectionAllowed` 保持假；`isNonConvergingRangeOffer` 让 `persistNextInterviewIfIdle` 早退不落下一问；`projectRectificationChoiceCard` 对 `provisional_range` 一律 null；前端时间卡要 `selectionAllowed`。同一句双出口常量又重复写在 `rectification-decision.ts`、`route.ts`、`answer-choice.ts`，正文许诺看盘或再补经历，两个出口都没有承载。(2) P1 `probe=null` 的真实输入：年份探针活在 `inference_state.probes`（对比包）而不是 `discriminating_event_probes`。`buildCandidateContrastPacket` 对非结构化探针在 `provided.has(domain)` 时整域丢弃，2020 career 证据因此杀掉全部 career 存在/大运题，包括 `career.2024.04.dasha_boundary`。这与出题层「Dasha existence 跳过账本已有的那年，不是整个领域」不一致。`remainingConflictProbes` 走年份邻近规则，所以把同一探针放进 `discriminating_event_probes` 的重建会问出来。出题层在 discriminate 模式下于是落到 occupation `method_coverage` 口述题，`followupAsksRenderableDiscriminator` 为假，决策把 `probe` 打成 null。occupation 阻塞 adopt 但不在 `datedMethodCollectOpen` 里，于是进入 `offerRangeWithoutAdopt`。该跳过没有写入 `dropped_probes`。已排除：`askedKeys` 把 `candidate_split_hash` 误判为已答（2023.05 与 2024.04 哈希不同）；`activeFocus` 未关（`discriminatorProbeIfFollowupCanAsk` 不传入旧焦点）。(3) P2：即使按年保留，`career.2024.04` 切的是 05:00 之后 vs 之前，`career.2023.dasha_activation` 只拎 05:15；淘汰后活跃四分钟上信息量为 0。出题层原先沿用建题时对全窗口的 IG，零区分力探针既不问也不 drop。
-- 修复：P0 选口述采集出口，不放开确认门与 `canAdopt`（occupation 仍挡住 adopt，也不新造无选项容器）。`offerRangeWithoutAdopt` 正文改为 `nonConvergingRangeNarration`（区间数值 + 代表分钟 + 既有免责口径）；同一轮 `exhaustionSpokenCollectFollowup` 按 family → education → finance 落一条未用过的 `oos_blind` 口述题并持久化，使 `current_question` 非 null。三处相同字符串合并为该导出函数。P1：对比包与 `rankRenderableDiscriminators` 对带年份非结构化探针改为按年跳过，不再整域丢弃。P2：按当前活跃候选重算信息量；零区分力写入 `dropped_probes.reason=no_split_among_active`。未放宽 `MIN_BOUNDARY_DAYS`、distinguish 契约、confirmation gate，未回退 b43808b0 无年份收窄。
-- 验证：`frontend/tests/rectification-range-offer-deadend.test.ts`。修复前：`persistNextInterviewIfIdle` 在 `isNonConvergingRangeOffer` 返回 `{persisted:false, hostNarration:null}`；正文是无数值的双出口常量；`projectRectificationChoiceCard` 为 null；`canAdopt=false`。修复后：正文含 `04:47–04:53` 与代表分钟 `04:51`，并落 education `collect_spoken`。P1 最小夹具：探针只在 `inference_state.probes`、career 领域已有 2020 证据、occupation 未覆盖；对活跃四分钟仍有切分的 `career.2022.dasha_boundary` 走 `ask_candidate_discriminator`，不得进区间提议。P2：`career.2024.04.dasha_boundary` 与 `career.2023.dasha_activation` 进入 `dropped_probes` 且 reason 为 `no_split_among_active`。`userStopped` 仍走 `provisional_range_user_stopped` 且 `canAdopt=true`。`rectification-collect-stall` / `rectification-spoken-collect` / BUG-442 occupation / b43808b0 无年份收窄保持绿。`assert.doesNotMatch(/answerText\.(?:includes|match|search)\(/)` 仍绿。
-- 防复发：助手正文承诺的每个出口，同一轮必须有对应的可点承载；区间提议必须带区间数值与代表分钟口径；探针信息量必须对当前活跃候选计算，失去区分力的探针要显式 drop 而不是静默留着。不得为了出看盘按钮而放宽 `canAdopt` / confirmation gate。
-- 相关记录：BUG-432、BUG-440、BUG-441、BUG-442、BUG-449
-- 复发自：无
-- 修复版本：待发布
+- 影响面：`offerRangeWithoutAdopt`、`persistNextInterviewIfIdle`、`projectRectificationChoiceCard`、`buildCandidateContrastPacket`、出题层 `rankRenderableDiscriminators`、`record-evidence-batch`、POST `/api/rectification/agent` 消息快路径
+- 用户现象：点选题答完后，助手说「可以先按当前区间看盘，也可以再补一件记得时间的经历」；界面既没有可采用的时间卡，也没有下一道口述题。用户随后用真实带时间经历回答时，旧焦点仍指向已经回答的采集题，对话到此停止。
+- 触发条件：训练门已开、occupation 等方法覆盖未齐、`datedMethodCollectOpen` 为假、引擎已放行 accept/propose、`probe === null`、`canOfferRange=true` 但 `canAdopt` / `selectionAllowed` / `proposeAllowed` 全为假；随后 `collect_spoken` 焦点收到已成功入账的真实事件，且本轮工具调用可能先执行 `record-evidence-batch`。
+- 根因：五段同时成立。(A) 探针耗尽是假耗尽：带年份探针的分支只把已淘汰候选切出，当前活跃候选在所有 `answer_class` 分支中待遇相同，按活跃集合重算信息量为零；旧出题层沿用全窗口信息量，不重算，也不把该探针写入 `dropped_probes`，于是以 `probe=null` 静默失效。(B) `probe=null` 且方法覆盖未齐时，`rectification-decision.ts` 的 `offerRangeWithoutAdopt` 仍把 `canOfferRange` 设为真，但保持 `canAdopt` / `selectionAllowed` / `proposeAllowed` 为假并关闭 focus；这把本应继续补覆盖的状态送进没有承载的区间出口。(C) `provisional_range` 的 `deferAdoption` 原本连 `intent=collect_method_evidence` 的覆盖追问一起吞掉，把它从 `next_followup` 挪到 `deferred_followup`；消费端不读后者，因覆盖不足进入的状态反而结构性阻止补覆盖，形成自锁。(D) 用户用真实事件回答口述采集焦点并成功落库后，服务端没有按 active focus 确定性执行 `resolved`；焦点继续存在，`persistNextInterviewIfIdle` 因 active focus 提前返回，旧题仍出现在 `current_question`。这与「确实没有」必须走 `declined` 的语义不同。(E) 本轮工具顺序可能是 `record-evidence-batch` 先于 `rectification-read-case`，模型未拿到服务端 focusId 时仍能记证据；旧实现把工具顺序当成硬前置，既没有先补读 dossier，也没有保证后续焦点关闭和下一问落库。
+- 修复：P0：`provisional_range` 只对 `intent=distinguish_candidates` 延后 followup；`collect_method_evidence` 覆盖题继续从 `next_followup` 返回并正常落焦点。`adopt_representative` / `validated_range` / `exact_minute_confirmed` / `provisional_range_user_stopped` / `completed_with_range` 的既有收口行为不变。P1：对比包和 `rankRenderableDiscriminators` 均按当前活跃候选重算探针信息量；零区分力探针显式写入 `dropped_probes.reason=no_split_among_active`，不放宽 `MIN_BOUNDARY_DAYS`、distinguish 合同或确认门。P2：`record-evidence-batch` 成功且当前 active focus 是 `collect_spoken` 时，服务端按 dossier 中的 focus 自行 `resolve(status=resolved, evidenceId=acceptedEvidenceId)`，不依赖模型传 `focusId`；否定回答仍走 `declined`。关闭后继续走下一问持久化。P3：`offerRangeWithoutAdopt` 使用统一的 `nonConvergingRangeNarration` 输出可信区间、代表分钟及「代表分钟不是已确认的唯一出生分钟」口径，并在同一轮持久化至少一个可执行的 `collect_spoken` focus；不为无选项问题新造视觉容器，也不为看盘按钮放宽 `canAdopt` / `confirmationAllowed`。P4：若本轮尚未成功执行 `rectification-read-case`，`record-evidence-batch` 先自行读取一次 dossier 再落库，不因模型工具顺序错误打断用户。
+- 验证：修复前基线（`79f65ac8`）实际回归输出：record-before-read 时第一条 RPC 为 `insert_agentic_rectification_tool_receipt` 而非 dossier read；`provisional_range.next_followup` 为 `undefined` 而不是 `collect_method_evidence`。修复后 `tests/rectification-eight-method.test.ts` 为 62/62；该套件同时锁定首条 RPC、accepted evidence 使用其 evidence ID 关闭 spoken collect focus、resolve 发生在 record 之后且不再返回旧题；`tests/rectification-range-offer-deadend.test.ts` 覆盖活跃候选零信息量 drop、仍有真实 split 时继续出区分卡、数字区间与代表分钟叙述、口述 focus 落库、userStopped 行为；`tests/rectification-spoken-collect.test.ts` 与 BUG-440 / BUG-442 / b43808b0 无年份收窄回归保持绿。`npx tsc --noEmit` 通过；改动文件 ESLint 0 error（6 条既有 unused-vars warning）；focused rectification/contract suite 727/727；全量 `tests/*.test.ts` 2339/2339；`/opt/anaconda3/bin/python3.12 -m pytest tests/test_rectification_event_probes.py tests/test_candidate_discriminator_contract.py` 35/35。
+- 防复发：任何因缺某项覆盖而进入的状态，不得阻止获取该项覆盖；探针信息量必须针对当前活跃候选计算，失去区分力的探针必须显式 drop；口述采集焦点被真实证据回答后必须由服务端确定性关闭，不依赖模型传 `focusId`；`resolved` 与 `declined` 语义不得互换；助手正文承诺的每个出口，同一轮必须有对应承载，区间提议必须带数值与代表分钟口径；`record-evidence-batch` 不得因未先 read-case 而丢弃用户证据。不得用 `answerText` 文本判断问题是否已经问出，不得引入语义正则、关键词表或 A/B/C/D 位置推断，不得回退无年份 `varga_style` 收窄或放宽 confirmation gate。
+- 相关记录：BUG-405、BUG-407、BUG-432、BUG-440、BUG-441、BUG-442、BUG-449
+- 复发自：BUG-432（出题层/决策层/可见承载再次分裂）、BUG-440（覆盖不足状态再次空转）、BUG-441/BUG-449（口述焦点可见性与服务端兜底边界未覆盖本路径）
+- 修复版本：`fix(rectification): prevent collect focus dead-end after choice answers`（Skill 保持 `10.0.13`）

frontend/src/lib/rectification-agentic/v9/method-followup.ts

@@ -1944,13 +1944,15 @@ export function buildMethodFollowupPlan(input: {
   const deferAdoption = sessionOutcome === "adopt_representative"
     || sessionOutcome === "validated_range"
     || sessionOutcome === "exact_minute_confirmed"
-    || sessionOutcome === "provisional_range"
     || sessionOutcome === "provisional_range_user_stopped"
     || sessionOutcome === "completed_with_range";
+  const deferProvisionalDiscriminator = sessionOutcome === "provisional_range"
+    && next?.intent === "distinguish_candidates";
+  const deferFollowup = deferAdoption || deferProvisionalDiscriminator;
   return {
     methods,
-    next_followup: deferAdoption ? null : next,
-    deferred_followup: deferAdoption ? next : null,
+    next_followup: deferFollowup ? null : next,
+    deferred_followup: deferFollowup ? next : null,
     session_outcome: sessionOutcome ?? "collect_evidence",
     stop_domain_rotation: true,
     do_not_poll: DO_NOT_POLL,

frontend/src/mastra/rectification-v9-tools.ts

@@ -76,6 +76,7 @@ import {
   stampChoiceSchemaWithProbe,
 } from "@/lib/rectification-agentic/v9/inference-adapter";
 import {
+  isCollectFocusSchema,
   openQuestionFromPersistedFocus,
   persistServerOwnedFocus,
 } from "@/lib/rectification-agentic/v9/server-focus";
@@ -738,6 +739,7 @@ export function createRectificationV9ReadOnlyTools(ctx: RectificationV9Context)
 export function createRectificationV9Tools(ctx: RectificationV9Context) {
   const { accounting, userId, caseId, turnId, attemptId, userMessage } = ctx;
   const engineVersion = v9EngineVersion();
+  let hasReadCase = false;
 
   const receipt = async (
     toolName: string,
@@ -1109,6 +1111,7 @@ export function createRectificationV9Tools(ctx: RectificationV9Context) {
               )
               : projectTurnDecision(refreshed);
             await receipt("rectification-read-case", "case.loaded", "completed", { inputFingerprint, resultFingerprint: hashResult(projection) });
+            hasReadCase = true;
             return projection;
           }
         }
@@ -1120,6 +1123,7 @@ export function createRectificationV9Tools(ctx: RectificationV9Context) {
           )
           : projectTurnDecision(dossier);
         await receipt("rectification-read-case", "case.loaded", "completed", { inputFingerprint, resultFingerprint: hashResult(projection) });
+        hasReadCase = true;
         return projection;
       } catch (error) {
         await receipt("rectification-read-case", "case.loaded", "failed", { inputFingerprint, safeErrorCode: safeToolErrorCode(error) });
@@ -1360,6 +1364,10 @@ export function createRectificationV9Tools(ctx: RectificationV9Context) {
     }).strict(),
     execute: async (input) => {
       assertCaseRef(input);
+      if (!hasReadCase) {
+        await loadV9CaseDossier(accounting, userId, input.caseId);
+        hasReadCase = true;
+      }
       for (const item of input.items) {
         if (!isEvidenceKind(item.proposedKind)) throw new RectificationToolServiceError("invalid_event_kind");
         if (!isEvidenceDomain(item.domain)) throw new RectificationToolServiceError("invalid_domain");
@@ -1459,6 +1467,22 @@ export function createRectificationV9Tools(ctx: RectificationV9Context) {
           }));
         if (result.acceptedCount > 0) {
           const dossier = await loadV9CaseDossier(accounting, userId, input.caseId);
+          const acceptedEvidenceId = result.items.find(
+            (item) => item.outcome === "accepted" && item.evidenceId,
+          )?.evidenceId ?? null;
+          const activeFocus = dossier.conversationSummary.activeFocus;
+          if (
+            acceptedEvidenceId
+            && activeFocus
+            && activeFocus.intent === "collect_method_evidence"
+            && isCollectFocusSchema(activeFocus.expectedAnswerSchema)
+          ) {
+            await resolveV10ConversationFocus(accounting, userId, input.caseId, {
+              focusId: activeFocus.id,
+              status: "resolved",
+              evidenceId: acceptedEvidenceId,
+            });
+          }
           if (isResumableStatus(dossier.case.status as RectificationCaseStatus)) {
             await transitionV9CaseStatus(accounting, userId, input.caseId, "collecting_evidence");
           }

frontend/tests/rectification-eight-method.test.ts

@@ -39,7 +39,9 @@ import {
   USER_ID,
   candidateSnapshotFixture,
   computeFixture,
+  conversationSummaryFixture,
   dossierFixture,
+  activeFocusFixture,
   fakeAccounting,
   receiptHandlers,
 } from "./rectification-v9-test-support.ts";
@@ -918,14 +920,24 @@ test("read-case follows method plan and keeps D9/D10 type tables when SQL missin
   assert.match(JSON.stringify(projection.method_followup_plan.next_followup), /自然语言/);
 });
 
-test("accepted batch evidence triggers server rescore without offering adoption", async () => {
+test("accepted batch evidence resolves a spoken collect focus before the next question", async () => {
   const restore = stubEngine(ENGINE_SCORE);
+  let collectFocusResolved = false;
   try {
     const accounting = fakeAccounting({
       ...receiptHandlers,
       get_agentic_rectification_case_dossier: () => dossierFixture({
         evidence: [educationEvidence],
         latestResult: null,
+        conversationSummary: conversationSummaryFixture({
+          activeFocus: collectFocusResolved
+            ? null
+            : activeFocusFixture({
+              intent: "collect_method_evidence",
+              targetDomain: "education",
+              expectedAnswerSchema: { collect: true, prompt: "有没有记得住时间的升学经历？" },
+            }),
+        }),
       }),
       get_agentic_rectification_case_compute: () => computeFixture(),
       record_agentic_rectification_evidence_batch: () => ({
@@ -943,6 +955,15 @@ test("accepted batch evidence triggers server rescore without offering adoption"
         rejected_count: 0,
         focus_id: null,
       }),
+      resolve_agentic_rectification_conversation_focus: (_fn, args) => {
+        collectFocusResolved = true;
+        return {
+          focus_id: args.p_focus_id,
+          status: args.p_status,
+          evidence_id: args.p_evidence_id,
+          idempotent: false,
+        };
+      },
       persist_agentic_rectification_candidate_v2: () => ({
         ...candidateSnapshotFixture(),
         cached: false,
@@ -959,6 +980,7 @@ test("accepted batch evidence triggers server rescore without offering adoption"
       execute(input: unknown): Promise<{
         accepted_count: number;
         rescore: { status: string; executed_methods: string[]; error_code: string | null };
+        open_question: { prompt?: string } | null;
       }>;
     }).execute({
       caseId: CASE_ID,
@@ -975,6 +997,15 @@ test("accepted batch evidence triggers server rescore without offering adoption"
     assert.equal(result.accepted_count, 1);
     assert.equal(result.rescore.status, "completed");
     assert.ok(result.rescore.executed_methods.includes("d1-rashi"));
+    assert.equal(accounting.calls[0]?.fn, "get_agentic_rectification_case_dossier");
+    const resolvedFocus = accounting.calls.find((call) => call.fn === "resolve_agentic_rectification_conversation_focus");
+    assert.equal(resolvedFocus?.args.p_focus_id, FOCUS_ID);
+    assert.equal(resolvedFocus?.args.p_status, "resolved");
+    assert.equal(resolvedFocus?.args.p_evidence_id, EDUCATION_ID);
+    const recordIndex = accounting.calls.findIndex((call) => call.fn === "record_agentic_rectification_evidence_batch");
+    const resolveIndex = accounting.calls.findIndex((call) => call.fn === "resolve_agentic_rectification_conversation_focus");
+    assert.ok(recordIndex >= 0 && resolveIndex > recordIndex);
+    assert.doesNotMatch(result.open_question?.prompt ?? "", /升学经历/);
     const persistCall = accounting.calls.find((call) => call.fn === "persist_agentic_rectification_candidate_v2");
     assert.ok(persistCall);
     const receipt = persistCall.args.p_decision_receipt as { window_scan?: { d9_candidates_differ?: boolean; d9_sign_names?: unknown } };
@@ -2306,7 +2337,7 @@ test("coverage-complete tie with encoded D24/D10 collects a dated move instead o
   }), "discriminate_candidates");
 });
 
-test("coverage-complete tie with no remaining split offers a provisional range", () => {
+test("provisional range still exposes method coverage followup", () => {
   const packet = buildCandidateContrastPacket({
     candidateSetVersion: "05:00-05:04",
     candidateTimes: DUMP_SCORES.map((item) => item.time),
@@ -2329,7 +2360,9 @@ test("coverage-complete tie with no remaining split offers a provisional range",
     contrastPacket: packet,
     sessionOutcome: "provisional_range",
   });
-  assert.equal(plan.next_followup, null);
+  assert.equal(plan.next_followup?.intent, "collect_method_evidence");
+  assert.equal(plan.next_followup?.domain, "horary");
+  assert.equal(plan.deferred_followup, null);
   assert.equal(conversationalSessionOutcome({
     selectionAllowed: true,
     proposeAllowed: true,