fix: stabilize rectification staging release

2026-07-29 18:17:46 +08:00
parent ee9d432762
commit 163d3fd1be
12 changed files with 317 additions and 11 deletions
@@ -191,6 +191,31 @@ test("Builder 的领域排序不受事件输入数组顺序影响", () => {
  assert.deepEqual(domains([education, career]), domains([career, education]));
 });

+test("Builder 和 Reasoner 按事件创建时间承接最近经历而不是 UUID 顺序", () => {
+  const older = event({
+    eventId: "ffffffff-ffff-4fff-8fff-ffffffffffff",
+    summary: "较早的研究院实习",
+    createdAt: "2026-07-29T01:00:00.000Z",
+  });
+  const newer = event({
+    eventId: "00000000-0000-4000-8000-000000000000",
+    domain: "relocation",
+    eventKind: "relocation",
+    summary: "刚提到的搬到北京",
+    rawText: "2018年8月搬到北京",
+    dateRange: { start: "2018-08-01", end: "2018-08-31", precision: "month", label: "2018年8月" },
+    createdAt: "2026-07-29T02:00:00.000Z",
+  });
+  const opportunities = buildQuestionOpportunities({ caseId, events: [newer, older], turns: [], snapshot: null, diagnostics: null });
+  const askNewEvent = opportunities.find((item) => item.kind === "ask_new_event");
+  assert.ok(askNewEvent);
+  assert.match(askNewEvent.fallbackPrompt, /刚提到的搬到北京/);
+  assert.doesNotMatch(askNewEvent.fallbackPrompt, /较早的研究院实习/);
+
+  const state = buildReasonerState({ snapshot: null, diagnostics: diagnostics(), opportunities, recentEvents: [newer, older] });
+  assert.equal(state.recentEvents.at(-1)?.summary, "刚提到的搬到北京");
+});
+
 test("Reasoner 状态包含最近语义上下文但不包含贡献矩阵", () => {
  const latestEvent = event();
  const opportunity = targetOpportunity(latestEvent);
@@ -0,0 +1,66 @@
+import assert from "node:assert/strict";
+import { randomUUID } from "node:crypto";
+import test from "node:test";
+import { validatedModelAssistedEvidence } from "../src/lib/conversational-rectification/evidence-extractor.ts";
+
+test("模型辅助提取拒绝 self 与家庭 relatedPerson 的矛盾组合", () => {
+  const rawText = "2020年4月老爸进了ICU。";
+  const result = validatedModelAssistedEvidence({
+    rawText,
+    sourceTurnId: randomUUID(),
+    asOfDate: "2026-07-29",
+    extraction: {
+      sourceSpan: "2020年4月老爸进了ICU",
+      summary: "老爸进了ICU",
+      domain: "health_pressure",
+      eventKind: "self_health_event",
+      subject: "self",
+      relatedPerson: "father",
+      dateText: "2020年4月",
+    },
+  });
+
+  assert.equal(result, null);
+});
+
+test("明确家庭主体不能被模型伪装为 self scoreable", () => {
+  const rawText = "2021年6月家里老人病危。";
+  const result = validatedModelAssistedEvidence({
+    rawText,
+    sourceTurnId: randomUUID(),
+    asOfDate: "2026-07-29",
+    extraction: {
+      sourceSpan: "2021年6月家里老人病危",
+      summary: "家里老人病危",
+      domain: "health_pressure",
+      eventKind: "self_health_event",
+      subject: "self",
+      relatedPerson: null,
+      dateText: "2021年6月",
+    },
+  });
+
+  assert.equal(result, null);
+});
+
+test("合法家庭健康事件只作为 context_only", () => {
+  const rawText = "2020年4月老爸进了ICU。";
+  const result = validatedModelAssistedEvidence({
+    rawText,
+    sourceTurnId: randomUUID(),
+    asOfDate: "2026-07-29",
+    extraction: {
+      sourceSpan: "2020年4月老爸进了ICU",
+      summary: "老爸进了ICU",
+      domain: "family",
+      eventKind: "family_health_event",
+      subject: "family",
+      relatedPerson: "father",
+      dateText: "2020年4月",
+    },
+  });
+
+  assert.ok(result);
+  assert.equal(result.scoreability, "context_only");
+  assert.equal(result.scoreable, false);
+});
@@ -0,0 +1,136 @@
+import assert from "node:assert/strict";
+import { randomUUID } from "node:crypto";
+import test from "node:test";
+import type { QuestionOpportunity, ValidatedDecision } from "../src/lib/rectification-agent/contracts.ts";
+import { realizePublicMessage, validateQuestionRealization } from "../src/lib/rectification-agent/renderer-agent.ts";
+import type { CandidateSnapshot, LifeEventRevision, PendingEvidence } from "../src/lib/rectification-v4/contracts.ts";
+
+const caseId = "00000000-0000-4000-8000-000000000701";
+const now = "2026-07-29T00:00:00.000Z";
+
+function event(): LifeEventRevision {
+  return {
+    id: randomUUID(),
+    eventId: randomUUID(),
+    revision: 1,
+    domain: "career",
+    eventKind: "career_change",
+    subject: "self",
+    relatedPerson: null,
+    summary: "2020年4月研究院实习",
+    rawText: "2020年4月去石油化工研究院实习做研究员。",
+    dateRange: { start: "2020-04-01", end: "2020-04-30", precision: "month", label: "2020年4月" },
+    scoreability: "scoreable",
+    supersedesRevisionId: null,
+    createdAt: now,
+  };
+}
+
+function opportunity(target: LifeEventRevision): QuestionOpportunity {
+  return {
+    contractVersion: "semantic-question-v2",
+    opportunityId: randomUUID(),
+    kind: "refine_event_date",
+    domain: "career",
+    targetEventId: target.eventId,
+    goal: "确认研究院实习发生的大概阶段。",
+    requestedFields: ["event_stage"],
+    anchors: [target.summary],
+    contextFacts: [],
+    forbiddenMoves: ["switch_target_event", "ask_multiple_questions", "claim_exact_birth_minute", "invent_event", "invent_date", "expose_private_score", "expose_internal_id", "expose_technique_trace"],
+    fallbackPrompt: `关于“${target.summary}”，你更记得是开始、高峰还是结束阶段吗？`,
+    reason: "当前事件仍需区分发生阶段。",
+    expectedInformationGain: 0.7,
+    dateSensitivity: 0.7,
+    candidateSplitRelevance: 0.4,
+    domainCoverageGain: 0,
+    recallEase: 0.6,
+    novelty: 0.8,
+    repetitionPenalty: 0,
+    privacyCost: 0.05,
+    utility: 0.65,
+    active: true,
+  };
+}
+
+function validated(selectedOpportunity: QuestionOpportunity): ValidatedDecision {
+  return {
+    decision: { action: "ask_question", opportunityId: selectedOpportunity.opportunityId, narrativeFocus: ["latest_event"] },
+    mode: "agent",
+    validationIssues: [],
+    selectedOpportunity,
+  };
+}
+
+function snapshot(range: readonly [string, string]): CandidateSnapshot {
+  const [startTime, endTime] = range;
+  return {
+    id: randomUUID(),
+    caseId,
+    caseVersion: 3,
+    evidenceSetHash: "e".repeat(64),
+    calculationSpecHash: "c".repeat(64),
+    algorithmVersion: "rectification-v5-matrix-scoring-1",
+    candidates: [{ time: startTime, score: 10, supportingEventIds: [], conflictingEventIds: [] }],
+    clusters: [{ rank: 1, startTime, endTime, representativeTime: startTime, widthMinutes: 7, peakScore: 10, scoreMass: 1 }],
+    robustness: { neighborSupportMinutes: 8, leaveOneOutRetentionRate: 0.8, dateSensitivityRetentionRate: 0.8, calculationSpecHashMatched: true },
+    canConfirmExactMinute: false,
+    canAcceptRange: true,
+    gateReasons: [],
+    createdAt: now,
+  };
+}
+
+test("Renderer 对全部模型可见文本执行 exact-minute 和内部信息安全回落", () => {
+  const target = event();
+  const selectedOpportunity = opportunity(target);
+  const input = {
+    latestAnswer: target.rawText,
+    acceptedEvents: [target],
+    pendingEvidence: [] as PendingEvidence[],
+    snapshot: null,
+    previousSnapshot: null,
+    validated: validated(selectedOpportunity),
+  };
+
+  const message = realizePublicMessage({
+    acknowledgement: `你提到的是“${target.summary}”，所以准确出生分钟是05:13。`,
+    candidateUpdate: null,
+    limitation: "准确出生分钟是五点十三分，snapshotId 已确认。",
+    question: `关于${target.summary}，唯一出生分钟是什么？`,
+  }, input);
+
+  assert.equal(message.acknowledgement, `你提到的是 ${target.dateRange.label} 的“${target.summary}”。`);
+  assert.equal(message.limitation, null);
+  assert.equal(message.question, selectedOpportunity.fallbackPrompt);
+  assert.doesNotMatch(JSON.stringify(message), /05:13|五点十三分|准确出生分钟|唯一出生分钟|snapshotId/);
+
+  for (const question of [
+    `关于${target.summary}，你是不是五点十三分出生？`,
+    `关于${target.summary}，eventId 是什么？`,
+  ]) {
+    assert.equal(validateQuestionRealization(question, selectedOpportunity).valid, false, question);
+  }
+});
+
+test("Renderer 保留服务器生成的合法候选范围表达", () => {
+  const target = event();
+  const selectedOpportunity = opportunity(target);
+  const message = realizePublicMessage({
+    acknowledgement: `你提到的是“${target.summary}”。`,
+    candidateUpdate: "模型声称出生时间就是05:13。",
+    limitation: null,
+    question: `关于${target.summary}，你更记得是开始、高峰还是结束阶段吗？`,
+  }, {
+    latestAnswer: target.rawText,
+    acceptedEvents: [target],
+    pendingEvidence: [],
+    snapshot: snapshot(["05:12", "05:18"]),
+    previousSnapshot: null,
+    validated: validated(selectedOpportunity),
+  });
+
+  assert.match(message.candidateUpdate ?? "", /候选范围.*05:12.*05:18/);
+  assert.match(message.candidateUpdate ?? "", /不代表其中某一分钟已被确认/);
+  assert.doesNotMatch(message.candidateUpdate ?? "", /就是05:13/);
+});