Jesse_ChenandClaude Opus 5.5
4e6e8d87ef
- D1 引导窗口题每个校正最多 2 道（前端 GUIDED_WINDOW_CASE_LIMIT；引擎 GUIDED_COLLECT_LIMIT 未动：event_probes.py 属冻结评分身份，改它需重新冻结） - D2 七条定向线与跳过线重问问完即出卡，没问到的引导窗口不再挡卡，出卡后也不再挂窗口题 - D3 卡头加副标题「最可能 HH:MM」 - D4 前两列相差 ≥5 个百分点才显示相对可能性，否则一句「这几个时刻目前区分不开……」 - 离线回放 scripts/research/fewer_probes_card_replay.py：真值不降、宽度中位 ±1 分钟、提问 11.4→7.8 - Skill 10.0.29 → 10.0.30；DESIGN / VOICE / CHANGELOG / PROGRESS / 真机清单 Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_017eEAG8HD3mm8gsKXgk8uU8
261 lines
12 KiB
TypeScript
261 lines
12 KiB
TypeScript
import assert from "node:assert/strict";
|
||
import { readFileSync } from "node:fs";
|
||
import { fileURLToPath } from "node:url";
|
||
import test from "node:test";
|
||
|
||
import {
|
||
MAX_RESUMABLE_CASES_PER_USER,
|
||
RECTIFICATION_CASE_STATUSES,
|
||
RECTIFICATION_SKILL_NAME,
|
||
RECTIFICATION_SKILL_VERSION,
|
||
RESUMABLE_CASE_STATUSES,
|
||
TERMINAL_CASE_STATUSES,
|
||
canTransitToTerminal,
|
||
evidenceWritesAllowed,
|
||
isRectificationCaseStatus,
|
||
isResumableStatus,
|
||
isTerminalStatus,
|
||
} from "../src/lib/rectification-agentic/v9/case-status.ts";
|
||
import {
|
||
evidenceKindSchema,
|
||
evidenceDomainSchema,
|
||
BACKGROUND_ONLY_KINDS,
|
||
DISTINCT_KIND_GROUPS,
|
||
EVIDENCE_KINDS,
|
||
canTransitEvidenceStatus,
|
||
evidenceSubjectForDomain,
|
||
isBackgroundEvidenceKind,
|
||
isDatePrecision,
|
||
isEvidenceDomain,
|
||
isEvidenceKind,
|
||
isEvidenceStatus,
|
||
datedPrecision,
|
||
normalizeQuote,
|
||
quoteIsGroundedInMessage,
|
||
} from "../src/lib/rectification-agentic/v9/evidence-model.ts";
|
||
import {
|
||
PUBLIC_ACTIVITY_EVENTS,
|
||
PUBLIC_RECTIFICATION_PHASES,
|
||
PUBLIC_RECTIFICATION_TOOLS,
|
||
safeActivityEvent,
|
||
} from "../src/lib/rectification-agentic/v9/public-receipt.ts";
|
||
import {
|
||
openRectificationCaseRequestSchema,
|
||
shouldStartOpening,
|
||
} from "../src/lib/rectification-agentic/v9/open-request.ts";
|
||
|
||
const skillDirectory = fileURLToPath(
|
||
new URL("../../skills/jyotish-birth-time-rectification", import.meta.url),
|
||
);
|
||
const skill = readFileSync(`${skillDirectory}/SKILL.md`, "utf8");
|
||
const references = [
|
||
"evidence-model.md",
|
||
"conversation-strategy.md",
|
||
"candidate-comparison.md",
|
||
"technique-routing.md",
|
||
"truth-consent-boundaries.md",
|
||
];
|
||
|
||
test("v9 case status machine separates resumable from terminal statuses", () => {
|
||
assert.deepEqual([...RESUMABLE_CASE_STATUSES], [
|
||
"draft",
|
||
"collecting_evidence",
|
||
"candidate_ready",
|
||
"candidate_accepted",
|
||
"needs_rebaseline",
|
||
"paused",
|
||
]);
|
||
assert.deepEqual([...TERMINAL_CASE_STATUSES], [
|
||
"confirmed",
|
||
"closed",
|
||
"abandoned",
|
||
"superseded",
|
||
]);
|
||
for (const status of RECTIFICATION_CASE_STATUSES) {
|
||
assert.equal(isRectificationCaseStatus(status), true);
|
||
assert.equal(isResumableStatus(status), RESUMABLE_CASE_STATUSES.includes(status));
|
||
assert.equal(isTerminalStatus(status), TERMINAL_CASE_STATUSES.includes(status));
|
||
}
|
||
assert.equal(isRectificationCaseStatus("mystery"), false);
|
||
});
|
||
|
||
test("terminal transitions are one-way and evidence writes stop at terminal", () => {
|
||
assert.equal(canTransitToTerminal("candidate_accepted", "confirmed"), true);
|
||
assert.equal(canTransitToTerminal("collecting_evidence", "closed"), true);
|
||
assert.equal(canTransitToTerminal("confirmed", "closed"), false);
|
||
assert.equal(canTransitToTerminal("closed", "candidate_ready"), false);
|
||
assert.equal(evidenceWritesAllowed("collecting_evidence"), true);
|
||
assert.equal(evidenceWritesAllowed("candidate_accepted"), true);
|
||
assert.equal(evidenceWritesAllowed("needs_rebaseline"), true);
|
||
assert.equal(evidenceWritesAllowed("confirmed"), false);
|
||
assert.equal(evidenceWritesAllowed("closed"), false);
|
||
assert.equal(evidenceWritesAllowed("superseded"), false);
|
||
assert.equal(MAX_RESUMABLE_CASES_PER_USER, 1);
|
||
});
|
||
|
||
test("the active rectification skill pins the v10 identity and lives in the right directory", () => {
|
||
assert.equal(RECTIFICATION_SKILL_NAME, "jyotish-birth-time-rectification");
|
||
// 原值: "10.0.25"
|
||
// 原值: "10.0.26"
|
||
// 新值: "10.0.27"
|
||
// 原因: 出卡精度门槛 + 引导式补经历
|
||
// 原因: BUG-668 定向补事第四选项写进 Skill
|
||
// 原值: "10.0.28" / 新值: "10.0.29" / 原因: 年月阶段改口述并禁止追问本人
|
||
// 原值: "10.0.29" / 新值: "10.0.30" / 原因: D2 出卡句与 D4 卡上百分比规则写进 Skill（2026-09-26）
|
||
assert.equal(RECTIFICATION_SKILL_VERSION, "10.0.30");
|
||
assert.match(skill, /^---\nname: jyotish-birth-time-rectification/m);
|
||
// 原值: "10.0.25"
|
||
// 原值: "10.0.26"
|
||
// 新值: "10.0.27"
|
||
// 原因: 出卡精度门槛 + 引导式补经历
|
||
// 原因: BUG-668 定向补事第四选项写进 Skill
|
||
// 原值: /^version: 10\.0\.28$/ / 新值: /^version: 10\.0\.29$/ / 原因: 年月阶段改口述并禁止追问本人
|
||
// 原值: /^version: 10\.0\.29$/ / 新值: /^version: 10\.0\.30$/ / 原因: D2 出卡句与 D4 卡上百分比规则写进 Skill（2026-09-26）
|
||
assert.match(skill, /^version: 10\.0\.30$/m);
|
||
assert.match(skill, /至多一个主问题且唯一来源：[\s\S]*不得自行提出、复述、改写或预告问题/);
|
||
for (const reference of references) {
|
||
const content = readFileSync(`${skillDirectory}/references/${reference}`, "utf8");
|
||
assert.ok(content.length > 0, `${reference} must be non-empty`);
|
||
}
|
||
assert.ok(skill.split("\n").length <= 200, "SKILL.md must stay within 200 lines");
|
||
});
|
||
|
||
test("skill keeps Path C A/B/C/D questions and forbids unique-minute claims", () => {
|
||
assert.match(skill, /不再有固定 10[–-]15 个事件/);
|
||
assert.match(skill, /A\/B\/C\/D 主题问卷/);
|
||
assert.match(skill, /80%\/60%/);
|
||
assert.match(skill, /事件吻合率/);
|
||
assert.match(skill, /D9\/D10 类型表/);
|
||
assert.match(skill, /不得伪造出生分钟/);
|
||
assert.match(skill, /日期精度真实保留/);
|
||
assert.match(skill, /candidate[\s\S]*accepted[\s\S]*confirmed/);
|
||
assert.match(skill, /candidate_range_not_birth_time_truth/);
|
||
assert.doesNotMatch(skill, /固定 A\/B\/C\/D 问卷、D9\/D10 类型表贴标签/);
|
||
});
|
||
|
||
test("evidence model exposes the full kind/domain/precision/status sets", () => {
|
||
for (const kind of EVIDENCE_KINDS) assert.equal(isEvidenceKind(kind), true);
|
||
assert.equal(isEvidenceKind("education"), false);
|
||
assert.equal(evidenceKindSchema.safeParse("education").success, false);
|
||
assert.equal(evidenceKindSchema.safeParse("education_start").success, true);
|
||
assert.equal(evidenceDomainSchema.safeParse("education").success, true);
|
||
assert.equal(isEvidenceKind("career"), false);
|
||
assert.equal(isEvidenceDomain("career"), true);
|
||
assert.equal(isEvidenceDomain("nope"), false);
|
||
for (const precision of ["year", "month", "quarter", "day", "range", "unknown"]) {
|
||
assert.equal(isDatePrecision(precision), true);
|
||
}
|
||
assert.equal(isDatePrecision("exact_minute"), false);
|
||
assert.equal(datedPrecision("quarter"), "year");
|
||
assert.equal(datedPrecision("range"), "year");
|
||
assert.equal(datedPrecision("day"), "day");
|
||
assert.equal(datedPrecision("unknown"), "unknown");
|
||
for (const status of ["draft", "pending_confirmation", "confirmed", "superseded", "rejected"]) {
|
||
assert.equal(isEvidenceStatus(status), true);
|
||
}
|
||
assert.equal(isEvidenceStatus("collected"), false);
|
||
});
|
||
|
||
test("semantically distinct kinds are never folded together", () => {
|
||
const flat = DISTINCT_KIND_GROUPS.flat();
|
||
assert.ok(flat.includes("career_entry") && flat.includes("career_pressure") && flat.includes("career_exit"));
|
||
assert.ok(flat.includes("relationship_start") && flat.includes("relationship_commitment") && flat.includes("relationship_separation"));
|
||
assert.equal(new Set(flat).size, flat.length);
|
||
});
|
||
|
||
test("only the server confirmation path may produce confirmed evidence", () => {
|
||
assert.equal(canTransitEvidenceStatus("draft", "pending_confirmation"), true);
|
||
assert.equal(canTransitEvidenceStatus("pending_confirmation", "confirmed"), true);
|
||
assert.equal(canTransitEvidenceStatus("confirmed", "superseded"), true);
|
||
assert.equal(canTransitEvidenceStatus("superseded", "confirmed"), false);
|
||
assert.equal(canTransitEvidenceStatus("rejected", "confirmed"), false);
|
||
assert.equal(canTransitEvidenceStatus("draft", "confirmed"), true);
|
||
});
|
||
|
||
test("quote grounding normalizes whitespace and punctuation", () => {
|
||
assert.equal(
|
||
normalizeQuote("2016 年 9 月，我离开家去北京开始工作。"),
|
||
"2016年9月，我离开家去北京开始工作。".replace(/[\s\u3000，。！？、；：“”‘’（）《》·—…,!.;:?]/g, ""),
|
||
);
|
||
assert.equal(quoteIsGroundedInMessage("2016年6月高考结束", "2016年6月高考结束,"), true);
|
||
assert.equal(quoteIsGroundedInMessage("2016年9月离开家去北京工作", "离开家去北京"), true);
|
||
assert.equal(quoteIsGroundedInMessage("我去了上海", "去了北京"), false);
|
||
assert.equal(quoteIsGroundedInMessage("", "任意"), false);
|
||
});
|
||
|
||
test("family/other background kinds: only other and horary stay off the scoring path", () => {
|
||
assert.equal(isBackgroundEvidenceKind("family_event"), false);
|
||
assert.equal(isBackgroundEvidenceKind("other"), true);
|
||
assert.equal(isBackgroundEvidenceKind("horary_query"), true);
|
||
assert.equal(isBackgroundEvidenceKind("occupation_note"), false);
|
||
assert.equal(isBackgroundEvidenceKind("career_entry"), false);
|
||
assert.equal(isBackgroundEvidenceKind("appearance_note"), false);
|
||
assert.equal(BACKGROUND_ONLY_KINDS.size, 2);
|
||
assert.equal(evidenceSubjectForDomain("family", "self"), "family");
|
||
assert.equal(evidenceSubjectForDomain("career", undefined), "self");
|
||
assert.equal(evidenceSubjectForDomain("appearance"), "self");
|
||
});
|
||
|
||
test("public receipt allowlists are exact and deny unknown values", () => {
|
||
for (const phase of PUBLIC_RECTIFICATION_PHASES) {
|
||
assert.equal(safeActivityEvent(phase), phase);
|
||
}
|
||
assert.equal(safeActivityEvent("provider.reasoning"), null);
|
||
assert.equal(safeActivityEvent("tool.payload"), null);
|
||
assert.ok(!(PUBLIC_RECTIFICATION_PHASES as readonly string[]).includes("thinking.delta"));
|
||
assert.ok((PUBLIC_RECTIFICATION_PHASES as readonly string[]).includes("activity.changed"));
|
||
assert.equal(PUBLIC_ACTIVITY_EVENTS.length, PUBLIC_RECTIFICATION_PHASES.length);
|
||
assert.ok(PUBLIC_RECTIFICATION_TOOLS.includes("rectification-read-case"));
|
||
assert.ok(!(PUBLIC_RECTIFICATION_TOOLS as readonly string[]).includes("rectification-scan"));
|
||
});
|
||
|
||
test("open request schemas reject userId, birth data and range from the browser", () => {
|
||
const homepage = openRectificationCaseRequestSchema.safeParse({
|
||
intent: "homepage",
|
||
requestId: "aaaaaaaa-bbbb-4ccc-8ddd-eeeeeeeeeeee",
|
||
});
|
||
assert.equal(homepage.success, true);
|
||
const withUserId = openRectificationCaseRequestSchema.safeParse({
|
||
intent: "homepage",
|
||
requestId: "aaaaaaaa-bbbb-4ccc-8ddd-eeeeeeeeeeee",
|
||
userId: "ffffffff-0000-4aaa-9bbb-cccccccccccc",
|
||
});
|
||
assert.equal(withUserId.success, false);
|
||
const withBirthData = openRectificationCaseRequestSchema.safeParse({
|
||
intent: "homepage",
|
||
requestId: "aaaaaaaa-bbbb-4ccc-8ddd-eeeeeeeeeeee",
|
||
birth_date: "1997-08-08",
|
||
});
|
||
assert.equal(withBirthData.success, false);
|
||
const withRange = openRectificationCaseRequestSchema.safeParse({
|
||
intent: "homepage",
|
||
requestId: "aaaaaaaa-bbbb-4ccc-8ddd-eeeeeeeeeeee",
|
||
candidate_range: { start_time: "04:00", end_time: "06:00" },
|
||
});
|
||
assert.equal(withRange.success, false);
|
||
const supersedeTrue = openRectificationCaseRequestSchema.safeParse({
|
||
intent: "new",
|
||
requestId: "aaaaaaaa-bbbb-4ccc-8ddd-eeeeeeeeeeee",
|
||
supersedeActive: true,
|
||
});
|
||
assert.equal(supersedeTrue.success, false);
|
||
});
|
||
|
||
test("shouldStartOpening is server-owned: only freshly created never-started cases", () => {
|
||
assert.equal(shouldStartOpening("created", 0), true);
|
||
assert.equal(shouldStartOpening("created", 1), false);
|
||
assert.equal(shouldStartOpening("resumed", 0), false);
|
||
assert.equal(shouldStartOpening("resumed", 5), false);
|
||
assert.equal(shouldStartOpening("readonly", 0), false);
|
||
});
|
||
|
||
test("case snapshot includes step_state without a composer strip", () => {
|
||
// 原值: 断言读 cases/[caseId]/route.ts
|
||
// 新值: 断言读 case-dossier-response.ts
|
||
// 原因: Next App Router 不允许 route.ts 导出非 HTTP handler。
|
||
const route = readFileSync(new URL("../src/lib/rectification-agentic/v9/case-dossier-response.ts", import.meta.url), "utf8");
|
||
const chat = readFileSync(new URL("../src/components/rectification-agentic-chat.tsx", import.meta.url), "utf8");
|
||
assert.match(route, /step_state: stepStateFromCaseDossier\(dossier\)/);
|
||
assert.doesNotMatch(chat, /rectification-step-state/);
|
||
});
|