feat(report): give the writer a static interpretation guide

The report writer had no interpretation methodology at all: a local agent calling the jyotish skill can read the reference library, the report model could read nothing. It could only restate the bundle. - frontend/src/lib/report-interpretation-packs/ holds one general pack and one pack per report theme, distilled from the in-repo reference guides. They constrain wording and reasoning discipline (term modernisation, how to talk about relative strength and SAV scores, the reasoning errors to avoid, the banned phrasings) and never assert a chart fact. - The general pack rides INSIDE the cached system message so the cached prefix stays byte-identical across sections; the chapter pack follows it and summary calls get the general pack only. - Skill jyotish-personal-report goes to 1.1.0 (1.0.0 deprecated): the contract now names interpretiveFacts and themeNarrativeSeeds as a bounded fact layer and states that the knowledge pack is not a fact source and cannot raise certainty. - Telemetry records interpretiveFactCount and knowledgePackCharacters as numbers only; the counter never throws so telemetry cannot break a run. Tests lock every theme resolving a pack, the 3,000 character budget, a forbidden-substring scan (paths, module names, vendor names, artefact names), the byte-stable cache prefix, and that no evidence id or date appears in the static content. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_016P5RoqzmUQEbeC2qjAkeGr
2026-09-01 18:54:52 +00:00
parent 90bad10d6f
commit ef1bd6dfa9
14 changed files with 567 additions and 29 deletions
@@ -0,0 +1,29 @@
+/**
+ * Cross-theme interpretation pack. Distilled product copy: it constrains HOW a
+ * fact is explained and worded, never WHICH facts exist. It contains no paths,
+ * no module names, no vendor names and no user data.
+ */
+export const GENERAL_INTERPRETATION_PACK = `【解读方法与措辞规范·通用】
+
+一、表达顺序
+每段先说结构，再说这个结构在现实里怎么表现，最后才说可以怎么做。不要先下结论再补理由，也不要只罗列术语。一个结构最多展开三层：它是什么、它在生活里长什么样、当事人可以据此调整什么。
+
+二、术语现代化（必须转译，不要原样堆砌）
+· 太阳＝自我定位与公开身份；月亮＝情绪与内在需求；火星＝执行力与冲突处理；水星＝分析、沟通与商务；木星＝扩张、学习与判断力；金星＝审美、关系与资源交换；土星＝责任、结构与长期积累；Rahu＝突破、非常规与放大；Ketu＝收束、专注与抽离。
+· 入庙＝天赋领域；落陷＝需要方法弥补的领域，不是"注定不行"；逆行＝能量内向化与反复打磨；合相＝能力叠加；相位＝影响外溢到另一个领域。
+· 大运＝人生主阶段；小运＝阶段内的子周期。用"阶段特征"表达，不要用"运势好坏"。
+
+三、强弱与分值怎么说
+六分力排名只说明发力顺序与相对可依赖度，不等于好坏，也不能推出成败。八分力分值只说明该宫位的支持厚度：偏高＝阻力小、可持续推进；偏低＝需要更多准备与外部条件。任何分值都不要换算成百分比、概率或成功率。
+
+四、多层验证
+一条结论至少要有两层证据同时支持（本命结构、分盘、强度层、时间层任取其二）。只有一层时必须写成倾向或需要观察的方向，并说明还缺什么。不同层给出的方向不一致时，如实写出张力，不要挑一层当定论。
+
+五、必须避免的推理错误
+· 不要按宫位字面名外推：第8宫是转化与共有资源，不是死亡；第12宫是消耗、独处与远方，不是牢狱；第6宫是日常劳务、竞争与健康管理，不是疾病判定。
+· 不要把一个配置的含义扩张到它不负责的领域（例如用第12宫谈婚姻质量、用第2宫谈职场竞争）。
+· 不要因为出现某个吉利组合就宣称结果必然发生；组合只说明可能性的通道，还要看时间层是否激活。
+· 不要用星座（太阳/月亮所在星座）替代上升与宫位结构来下判断。
+
+六、语气与禁语
+直接、克制、可执行。不用"业力""前世""诅咒""厄运""劫难""注定"。不写"必定/一定/肯定/保证/必然/百分之百"。不做医疗诊断、用药、投资标的、法律裁断、生死与生育结果的断言。不提具体日期与月份，除非已明确允许精确时间表达；否则只写阶段与顺序。不要提及任何计算过程、内部流程或资料来源的名称。`;
@@ -0,0 +1,41 @@
+import { GENERAL_INTERPRETATION_PACK } from "./general.ts";
+import { THEME_INTERPRETATION_PACKS } from "./themes.ts";
+
+/**
+ * Static, product-owned interpretation packs for the report writer.
+ *
+ * These are the only prose the writer agent receives besides the evidence
+ * bundle. They constrain wording and reasoning discipline; they never assert a
+ * fact about a chart, never name a technique's implementation, and never carry
+ * user data. The writer's fact source stays the bundle (claimCards +
+ * interpretiveFacts + themeNarrativeSeeds).
+ *
+ * Hard bounds enforced by tests:
+ * - each pack is at most PACK_CHARACTER_LIMIT characters;
+ * - no pack may contain a file path, an internal module name, a vendor/engine
+ *   name, or the word for a prompt/skill artefact.
+ */
+export const PACK_CHARACTER_LIMIT = 3_000;
+
+export { GENERAL_INTERPRETATION_PACK, THEME_INTERPRETATION_PACKS };
+
+export function interpretationPackForTheme(theme: string | null | undefined): string | null {
+  if (!theme) return null;
+  return THEME_INTERPRETATION_PACKS[theme] ?? null;
+}
+
+/**
+ * The system content that rides in front of the prompt-cache boundary. Stable
+ * across every section call so the cached prefix is reused; the per-theme pack
+ * is sent separately, after the boundary.
+ */
+export function cachedInterpretationPreamble(): string {
+  return GENERAL_INTERPRETATION_PACK;
+}
+
+export function allInterpretationPacks(): readonly Readonly<{ id: string; text: string }>[] {
+  return [
+    { id: "general_method", text: GENERAL_INTERPRETATION_PACK },
+    ...Object.entries(THEME_INTERPRETATION_PACKS).map(([id, text]) => ({ id, text })),
+  ];
+}
@@ -0,0 +1,72 @@
+/**
+ * Per-theme interpretation packs. Same contract as the general pack: wording
+ * and reasoning discipline only, never new astrological claims and never a
+ * statement about a particular person.
+ */
+export const THEME_INTERPRETATION_PACKS: Readonly<Record<string, string>> = {
+  career: `【事业主题·解读要点】
+主指标：第10宫（社会角色与可见产出）、第6宫（日常劳务与竞争）、第1宫（自我定位）、事业分盘、以及承接职责的相关星曜。
+· 把第10宫说成"别人看得见的你在做什么"，把第6宫说成"每天真正在处理的事"。两者强度不一致时，写成"对外形象与日常内容错位"，而不是"事业好/不好"。
+· yogakaraka 或同时管辖角宫与三方宫的星曜，写成"最值得押注的行动主轴"，并说明它对应的现实动作（承担责任、做系统、做交付）。
+· 六分力靠前的星曜说明"最容易发力的方式"，不是"最赚钱的方向"。
+· 事业分盘与本命盘方向不一致时，写成"心里想做的和实际被认可的不是同一件事"，两边都要写。
+禁止：不承诺升职、录用、薪资数字、创业成败或具体公司；不给出跳槽的确定时点；不把行业名当成命定答案，只给能力形态与适配场景。`,
+
+  marriage: `【婚恋与长期合作主题·解读要点】
+主指标：第7宫（长期对等关系）、九分盘（关系底层质地）、第2宫与第11宫（关系带来的资源与圈层）、以及关系相关的特殊上升点与配偶星。
+· 第7宫既是婚姻也是一切长期对等合作，写作时说明这一点，避免读者以为只在谈结婚。
+· 九分盘描述的是关系里长期稳定下来的相处方式，本命盘描述的是相遇与初期吸引；两者不同时，写成"吸引点和长期相处的重点不是同一件事"。
+· 土星相关配置写成"关系建立慢、但一旦稳定就耐久"，不要写成"婚姻延迟"或"晚婚"。
+· 谈伴侣画像时只谈可观察的相处风格、节奏与需求，不谈外貌、身份、国籍、财产。
+禁止：不预测结婚年份或分手时点；不判断第三方是否忠诚；不评价现有关系该不该继续；不做生育相关结果的断言。`,
+
+  wealth: `【财富主题·解读要点】
+主指标：第2宫（可留存的资产与收入结构）、第11宫（收入增量与圈层带来的机会）、第5宫（判断力与投入决策）、财富相关分盘与八分力支持度。
+· 必须把"赚到"和"留住"分开写：第11宫偏进项与增量，第2宫偏留存与结构。两者强度差异大时，写成"进得来但留不住"或"进项慢但沉淀好"。
+· 八分力分值偏低的宫位写成"这条通路需要更多前置条件"，不要写成"破财"。
+· 财富组合只说明积累通道的形态（靠专业、靠合作、靠资产、靠周期），不说明金额与时点。
+禁止：不推荐任何具体投资标的、资产类别、币种或平台；不预测收益率、涨跌与回本时间；不判断借贷是否应该做；不给出税务或法律意见。`,
+
+  education: `【教育与学习主题·解读要点】
+主指标：第4宫（基础学习与积累）、第5宫（吸收与创造）、第9宫（高阶与体系化学习）、教育相关分盘。
+· 区分"学得快"与"学得深"：第5宫偏理解与灵感，第9宫偏体系与长期钻研，第4宫偏基础扎实度。
+· 学习困难写成"当前方法与自身吸收方式不匹配"，给出可换的方法（结构化、实践导向、讨论导向），不要写成"资质不足"。
+· 分盘与本命盘不一致时，写成"考试表现与真实掌握程度不一致"。
+禁止：不预测考试通过与否、录取结果、学校名次或具体分数；不判断学历路径必须怎么走。`,
+
+  migration_home: `【迁移与居所主题·解读要点】
+主指标：第4宫（居所与安定感）、第12宫（远方、独处与消耗）、第3宫（短程移动）、第9宫（长程与跨文化）、相关分盘。
+· 第12宫写成"离开熟悉环境后的消耗与独处"，不要写成"损失"或"隔离"。
+· 第4宫与第12宫同时活跃时，写成"想安定与想离开同时存在"，两种需求都要给出安放方式。
+· 居所议题谈的是环境适配（节奏、密度、通勤、独处空间），不是房产买卖建议。
+禁止：不指定国家、城市、方位或搬迁日期；不给购房、租售或移民法律建议；不预测签证与手续结果。`,
+
+  family: `【家庭与子女主题·解读要点】
+主指标：第4宫（原生环境与母系）、第9宫（父系与价值观来源）、第2宫（家族共同资源）、第5宫（子女与创造）、相关分盘。
+· 家庭议题写成"关系模式与角色分工"，不评价家庭成员的人品，也不替当事人判断对错。
+· 第5宫谈的是创造力与养育关系的相处方式，不是生育能力。
+· 代际张力写成"两代人对安全感的定义不同"，并给出可操作的边界设定方式。
+禁止：不预测生育时间、性别或数量；不判断亲属健康与寿数；不建议断绝或维持任何具体亲属关系。`,
+
+  health_pressure: `【健康压力主题·解读要点（非医疗）】
+主指标：第6宫（日常负荷与恢复）、第1宫（体感与精力基线）、第8宫（长期消耗与转化）、压力相关分盘。
+· 全篇只谈"压力来源、负荷节奏与恢复方式"，不谈器官、疾病、症状或诊断。
+· 第6宫写成"每天消耗你的事情的形状"，第1宫写成"精力的基线与恢复速度"。
+· 给出的建议限于作息节奏、工作负荷分配、压力释放方式与就医提醒（"持续不适请交给专业医疗人员判断"）。
+禁止：不做任何诊断、不点名疾病、不建议用药或停药、不预测健康事件的时间、不评估寿数。`,
+
+  timing: `【阶段与时机主题·解读要点】
+主指标：主运与副运的层级关系、多套时间系统是否指向同一领域、以及本命结构是否本来就允许该事发生。
+· 时间层只能"激活"本命已经存在的结构。本命没有的承诺，时间层再强也不写成会发生。
+· 主运定基调，副运定当下重点；两者不一致时写成"大方向与眼前重点不同步"。
+· 多套时间系统同时指向同一领域时，写成"该领域是本阶段的主线"，仍然不给具体日期。
+· 未获准精确时间表达时，只写阶段顺序（现在处于哪一段、下一段的重点会转向哪里），不写年份、月份与日期。
+禁止：不给择日建议；不预测具体事件发生的日期；不把阶段特征写成不可改变的命运。`,
+
+  general: `【综合基础章·解读要点】
+主指标：上升与第1宫（自我定位与出场方式）、功能吉凶星（哪些星曜在本盘天然站在你这边）、六分力顺序（发力方式）、当前阶段。
+· 本章负责建立"这个人怎么运作"的整体框架，供后面各主题引用，不抢主题章的具体结论。
+· 功能吉凶是按上升推出的角色分工，不是性格好坏；写成"哪几股力量在本盘是助力，哪几股需要方法去驾驭"。
+· 先写稳定的结构（上升、角色分工），再写当前阶段，让读者知道哪些是长期的、哪些是这一段时间的。
+禁止：不在本章下任何主题性的确定结论；不做性格标签化的定性（如"你是内向的人"），只描述倾向与适配场景。`,
+};
@@ -1,13 +1,16 @@
-export type ReportTheme =
-  | "career"
-  | "marriage"
-  | "wealth"
-  | "education"
-  | "migration_home"
-  | "family"
-  | "health_pressure"
-  | "timing"
-  | "general";
+export const REPORT_THEME_IDS = [
+  "career",
+  "marriage",
+  "wealth",
+  "education",
+  "migration_home",
+  "family",
+  "health_pressure",
+  "timing",
+  "general",
+] as const;
+
+export type ReportTheme = (typeof REPORT_THEME_IDS)[number];

 export type ReportThemeEvidencePlan = Readonly<{
  theme: ReportTheme;
@@ -3,6 +3,7 @@ import { z } from "zod";
 import type { ResolvedLanguageModel } from "./model";
 import type { PersonalReportSectionPlan, ReportSectionPlanEntry } from "@/lib/personal-report-plan";
 import { cachedSystemMessage, mergePromptCacheUsage, promptCacheUsage, agentGenerationSettings } from "@/lib/agent-generation-settings";
+import { cachedInterpretationPreamble, interpretationPackForTheme } from "@/lib/report-interpretation-packs";
 import type {
  ReportChartHouse,
  ReportDashaPeriod,
@@ -147,8 +148,30 @@ export type PersonalReportAgentTelemetry = Readonly<{
  totalTokens: number | null;
  finishReason: string | null;
  repairAttempted: boolean;
+  /** Metric only: how many interpretive rows this call's bundle carried. */
+  interpretiveFactCount: number;
+  /** Metric only: characters of static knowledge pack sent with this call. */
+  knowledgePackCharacters: number;
 }>;

+/**
+ * Counts the interpretive rows in a bundle. Numbers only — never content.
+ * Telemetry must never break generation, so a bundle without the block (or a
+ * malformed one) counts as zero instead of throwing.
+ */
+export function countInterpretiveFacts(bundle: ReportEvidenceBundleV2): number {
+  const facts = bundle?.interpretiveFacts as ReportEvidenceBundleV2["interpretiveFacts"] | undefined;
+  if (!facts) return 0;
+  const size = (value: unknown) => (Array.isArray(value) ? value.length : 0);
+  return size(facts.yogas)
+    + size(facts.functionalRoles)
+    + size(facts.shadbalaRanking)
+    + size(facts.savScores)
+    + size(facts.convergenceDomains)
+    + (facts.currentDasha ? 1 : 0)
+    + (typeof facts.savTotal === "number" ? 1 : 0);
+}
+
 const personalReportInstructions = `You are the dedicated Personal Report writer for a Vedic astrology product. You write long structured report sections in Simplified Chinese. This is a report, not a chat: do not use chat-style short paragraphs, do not ask follow-up questions, and do not append hidden blocks.

 The user message contains the ONLY allowed facts: a server-computed ReportEvidenceBundleV2. Use its claimCards exclusively for narrative conclusions. Its interpretiveFacts (yogas, functionalRoles, shadbalaRanking, savScores, currentDasha, convergenceDomains) and themeNarrativeSeeds are the supporting fact layer: you may quote, order, group and explain them, but they never authorise a conclusion that the matching claimCard does not already state. Never invent, recalculate, or infer planetary positions, house lords, dasha boundaries, divisional charts, shadbala/ashtakavarga values, yogas, or timing windows that are not present in those fields. Never mention server internals, tool names, engine names, providers, skill files, prompts, paths, hashes or methodology details.
@@ -164,7 +187,9 @@ Structure rules:
 - executiveSummary.headline is one calm, concise Chinese sentence of at most 200 characters; it must not contain dates, timing windows, or deterministic claims.
 - Write only thematic sections whose plan disposition is write. Section id, theme, and evidenceRefs must exactly match the plan entry. Every narrative conclusion must trace to the matching claimCard. Never output a blocked plan entry; the server creates those disclosures deterministically.
 - Keep actions concrete and cautious; caveats must state limits honestly.
- Write formal, readable Simplified Chinese for a printed report.`;
+- Write formal, readable Simplified Chinese for a printed report.
+
+The system messages also carry a static interpretation guide (wording, reasoning discipline, forbidden phrasing). It governs HOW you explain a fact and how you word it. It is never a source of facts: it must never produce an astrological statement that the bundle does not already contain, and it can never raise certainty.`;

 async function readUsage(value: unknown) {
  try {
@@ -275,6 +300,18 @@ function sectionPrompt(
  return `请只生成以下一个个人报告 thematicNarrative 条目。严格输出单个 JSON 对象，不要数组、Markdown 或额外文字。只使用给定证据；section id、theme、evidenceRefs 必须与 plan 完全一致。已完成章节标题仅用于避免重复，不要复述正文。\n${JSON.stringify({ bundle, plan: section, completedSectionTitles: completedTitles })}`;
 }

+/**
+ * System content sent ahead of the report input. Index 0 is the prompt-cache
+ * prefix and stays byte-identical for every call so the cache is actually
+ * reused; the per-theme pack follows it and is intentionally not cached.
+ * Summary calls get the general pack only.
+ */
+export function buildWriterSystemContents(theme: string | null | undefined): readonly string[] {
+  const cached = `${cachedInterpretationPreamble()}\n\n【上下文缓存边界】后续内容为本次报告输入。`;
+  const themePack = theme ? interpretationPackForTheme(theme) : null;
+  return themePack ? [cached, themePack] : [cached];
+}
+
 function summaryPrompt(
  sections: readonly Readonly<{ title: string; claimStatus: string }>[],
 ): string {
@@ -305,6 +342,10 @@ export function createPersonalReportAgent(model: ResolvedLanguageModel): ReportA
    schema: z.ZodType<T>;
    signal?: AbortSignal;
    maxOutputTokens?: number;
+    /** Theme whose interpretation pack rides after the cache boundary. */
+    themePack?: string | null;
+    /** Metric only: interpretive rows in the bundle this call received. */
+    interpretiveFactCount?: number;
    accept: (value: T) => void;
  }>): Promise<T> => {
    const startedAt = Date.now();
@@ -312,10 +353,21 @@ export function createPersonalReportAgent(model: ResolvedLanguageModel): ReportA
    const prompt = input.prompt;
    let repairAttempted = false;
    let attemptReturned = false;
-    const cacheBoundary = cachedSystemMessage("【上下文缓存边界】后续内容为本次报告输入。", model.model);
+    // The general interpretation pack sits INSIDE the cached system message so
+    // the cached prefix stays byte-identical across every section call. The
+    // per-theme pack changes each section, so it goes after the boundary.
+    const [cachedContent, ...uncachedContents] = buildWriterSystemContents(input.themePack);
+    const cacheBoundary = cachedSystemMessage(cachedContent, model.model)
+      ?? { role: "system" as const, content: cachedContent };
+    const metrics = {
+      interpretiveFactCount: input.interpretiveFactCount ?? 0,
+      knowledgePackCharacters: cachedContent.length
+        + uncachedContents.reduce((total, item) => total + item.length, 0),
+    };
    const runOnce = (content: string) => agent.generate(
      [
-        ...(cacheBoundary ? [cacheBoundary] : []),
+        cacheBoundary,
+        ...uncachedContents.map((item) => ({ role: "system" as const, content: item })),
        { role: "user", content },
      ],
      {
@@ -345,11 +397,11 @@ export function createPersonalReportAgent(model: ResolvedLanguageModel): ReportA
      const accepted = accept(first);
      if (accepted.ok) {
        await recordUsage(first.usage);
-        await logTelemetry(model.id, startedAt, false, "resolved", first.usage, first.finishReason);
+        await logTelemetry(model.id, startedAt, false, "resolved", first.usage, first.finishReason, metrics);
        return accepted.data;
      }
      await recordUsage(first.usage);
-      await logTelemetry(model.id, startedAt, false, "failed", first.usage, first.finishReason);
+      await logTelemetry(model.id, startedAt, false, "failed", first.usage, first.finishReason, metrics);
      repairAttempted = true;
      attemptReturned = false;
      const repaired = await runOnce(`${prompt}${REPAIR_PROMPT_SUFFIX}`);
@@ -357,18 +409,18 @@ export function createPersonalReportAgent(model: ResolvedLanguageModel): ReportA
      const repairedAccepted = accept(repaired);
      if (repairedAccepted.ok) {
        await recordUsage(repaired.usage);
-        await logTelemetry(model.id, startedAt, true, "resolved", repaired.usage, repaired.finishReason);
+        await logTelemetry(model.id, startedAt, true, "resolved", repaired.usage, repaired.finishReason, metrics);
        return repairedAccepted.data;
      }
      await recordUsage(repaired.usage);
-      await logTelemetry(model.id, startedAt, true, "failed", repaired.usage, repaired.finishReason);
+      await logTelemetry(model.id, startedAt, true, "failed", repaired.usage, repaired.finishReason, metrics);
      if (repairedAccepted.error) throw repairedAccepted.error;
      throw new PersonalReportAgentOutputError();
    } catch (error) {
      if (error instanceof PersonalReportAgentOutputError) throw error;
      if (isAbortError(error, input.signal)) throw error;
      if (error instanceof Error && error.message.startsWith("report_writer_")) throw error;
-      if (!attemptReturned) await logTelemetry(model.id, startedAt, repairAttempted, "failed", null, null);
+      if (!attemptReturned) await logTelemetry(model.id, startedAt, repairAttempted, "failed", null, null, metrics);
      throw error;
    }
  };
@@ -382,6 +434,7 @@ export function createPersonalReportAgent(model: ResolvedLanguageModel): ReportA
        prompt: buildReportPrompt(bundle, plan),
        schema: personalReportAgentOutputSchema,
        signal,
+        interpretiveFactCount: countInterpretiveFacts(bundle),
        accept: (output) => options?.assertWriterOutput?.(output),
      });
    },
@@ -390,6 +443,8 @@ export function createPersonalReportAgent(model: ResolvedLanguageModel): ReportA
      schema: personalReportThematicNarrativeSchema,
      signal: options?.signal,
      maxOutputTokens: options?.maxOutputTokens,
+      themePack: section.theme,
+      interpretiveFactCount: countInterpretiveFacts(bundle),
      accept: (output) => options?.assertWriterOutput?.(output),
    }),
    generateSummary: (sections, options) => runStructured({
@@ -409,6 +464,7 @@ async function logTelemetry(
  outcome: "resolved" | "failed",
  usage: unknown,
  finishReason: unknown,
+  metrics: Readonly<{ interpretiveFactCount: number; knowledgePackCharacters: number }>,
 ) {
  const [tokens, finishReasonValue] = await Promise.all([
    readUsage(usage),
@@ -423,8 +479,11 @@ async function logTelemetry(
    totalTokens: tokens.totalTokens,
    finishReason: finishReasonValue,
    repairAttempted,
+    interpretiveFactCount: metrics.interpretiveFactCount,
+    knowledgePackCharacters: metrics.knowledgePackCharacters,
  };
  // Telemetry must never include the prompt, the packet, birth data or the
-  // report body.
+  // report body. interpretiveFactCount and knowledgePackCharacters are counts
+  // and lengths only — never the facts, the seeds or the pack text.
  console.info("[personal-report-agent]", JSON.stringify(telemetry));
 }
@@ -56,3 +56,41 @@ test("personal report telemetry records each truncated attempt without private p
  assert.equal("bundle" in telemetry[0], false);
  assert.equal("report" in telemetry[0], false);
 });
+
+test("telemetry carries interpretive and knowledge-pack sizes as numbers only", async () => {
+  const originalGenerate = Agent.prototype.generate;
+  const originalInfo = console.info;
+  const logs: unknown[][] = [];
+  Agent.prototype.generate = (async function () {
+    return {
+      object: {},
+      usage: Promise.resolve({ inputTokens: 11, outputTokens: 3, totalTokens: 14 }),
+      finishReason: Promise.resolve("length"),
+    };
+  }) as never;
+  console.info = (...args: unknown[]) => logs.push(args);
+
+  try {
+    const agent = createPersonalReportAgent(testModel());
+    await assert.rejects(agent.generateSection!(
+      { interpretiveFacts: { yogas: [{}, {}], functionalRoles: [{}], shadbalaRanking: [], savScores: [{}], convergenceDomains: [], currentDasha: {}, savTotal: 337 } } as never,
+      { id: "theme-wealth", kind: "thematic", theme: "wealth", disposition: "write", evidenceRefs: [], targetCharacters: { min: 1, max: 2 } } as never,
+      [],
+    ));
+  } finally {
+    Agent.prototype.generate = originalGenerate;
+    console.info = originalInfo;
+  }
+
+  const telemetry = logs
+    .filter(([label]) => label === "[personal-report-agent]")
+    .map(([, payload]) => JSON.parse(String(payload)) as Record<string, unknown>);
+  assert.ok(telemetry.length >= 1);
+  assert.equal(telemetry[0].interpretiveFactCount, 6);
+  assert.equal(typeof telemetry[0].knowledgePackCharacters, "number");
+  assert.ok((telemetry[0].knowledgePackCharacters as number) > 500);
+  // The metrics are sizes, not payloads: no seed text or fact text may appear.
+  const serialized = JSON.stringify(telemetry[0]);
+  assert.ok(!serialized.includes("宫"));
+  assert.ok(!serialized.includes("yogakaraka"));
+});
@@ -811,7 +811,9 @@ test("generatePersonalReport fails with report_schema_invalid when the writer em
 test("skill snapshot is the real packaged report manifest sha256, never the literal unknown", async () => {
  const snapshot: SkillSnapshot = resolveSkillSnapshot();
  assert.equal(snapshot.name, "jyotish-personal-report");
-  assert.equal(snapshot.version, "1.0.0");
+  // was "1.0.0"; bumped 2026-09-01 when the skill contract gained the
+  // interpretive fact layer and the static interpretation packs.
+  assert.equal(snapshot.version, "1.1.0");
  assert.match(snapshot.sha256, /^[0-9a-f]{64}$/);
  assert.notEqual(snapshot.sha256, "unknown");
  const again: SkillSnapshot = resolveSkillSnapshot();
@@ -0,0 +1,91 @@
+import assert from "node:assert/strict";
+import test from "node:test";
+import {
+  PACK_CHARACTER_LIMIT,
+  allInterpretationPacks,
+  cachedInterpretationPreamble,
+  interpretationPackForTheme,
+} from "../src/lib/report-interpretation-packs/index.ts";
+import { REPORT_THEME_IDS } from "../src/lib/report-theme-evidence-plan.ts";
+import { buildWriterSystemContents } from "../src/mastra/personal-report.ts";
+
+test("every report theme resolves an interpretation pack", () => {
+  for (const theme of REPORT_THEME_IDS) {
+    const pack = interpretationPackForTheme(theme);
+    assert.ok(pack && pack.length > 200, `theme ${theme} has no usable pack`);
+  }
+  assert.equal(interpretationPackForTheme("not_a_theme"), null);
+  assert.equal(interpretationPackForTheme(null), null);
+  assert.ok(cachedInterpretationPreamble().length > 500);
+});
+
+test("packs stay inside the character budget", () => {
+  for (const pack of allInterpretationPacks()) {
+    assert.ok(
+      pack.text.length <= PACK_CHARACTER_LIMIT,
+      `${pack.id} is ${pack.text.length} characters, over the ${PACK_CHARACTER_LIMIT} budget`,
+    );
+  }
+});
+
+// The packs travel into a model prompt, so they must not leak repository
+// structure, internal module names, vendor names or artefact names.
+const FORBIDDEN_PACK_SUBSTRINGS = [
+  "references/", "scripts/", "frontend/", "src/", "node_modules",
+  "SKILL.md", ".md", ".ts", ".py", ".json",
+  "vedastro", "swisseph", "swiss ephemeris", "jyotish_engine", "mastra",
+  "anthropic", "openai", "claude", "gpt-",
+  "prompt", "system message", "schema", "bundle", "claimcard", "evidenceref",
+  "mevg", "workflow", "endpoint", "http://", "https://", "sha256",
+];
+
+test("packs contain no paths, module names, vendor names or artefact names", () => {
+  for (const pack of allInterpretationPacks()) {
+    const lowered = pack.text.toLowerCase();
+    for (const token of FORBIDDEN_PACK_SUBSTRINGS) {
+      assert.ok(!lowered.includes(token), `${pack.id} leaks "${token}"`);
+    }
+  }
+});
+
+test("packs restate the hard truth boundaries instead of relaxing them", () => {
+  const general = cachedInterpretationPreamble();
+  for (const banned of ["必定", "一定", "保证", "百分之百"]) {
+    assert.ok(general.includes(banned), `general pack must name "${banned}" as forbidden phrasing`);
+  }
+  assert.ok(general.includes("不做医疗诊断"));
+  const health = interpretationPackForTheme("health_pressure")!;
+  assert.ok(health.includes("不做任何诊断"));
+  const wealth = interpretationPackForTheme("wealth")!;
+  assert.ok(wealth.includes("不推荐任何具体投资标的"));
+  const timing = interpretationPackForTheme("timing")!;
+  assert.ok(timing.includes("不写年份、月份与日期"));
+});
+
+test("writer system content caches the general pack and appends only the chapter pack", () => {
+  const summaryContents = buildWriterSystemContents(null);
+  assert.equal(summaryContents.length, 1, "summary calls carry the general pack only");
+  assert.ok(summaryContents[0].includes(cachedInterpretationPreamble()));
+  assert.ok(summaryContents[0].includes("【上下文缓存边界】"));
+
+  const previousCached = summaryContents[0];
+  for (const theme of REPORT_THEME_IDS) {
+    const contents = buildWriterSystemContents(theme);
+    assert.equal(contents.length, 2, `${theme} must add its own pack`);
+    assert.equal(
+      contents[0],
+      previousCached,
+      "the cached prefix must stay byte-identical across sections or the cache never hits",
+    );
+    assert.equal(contents[1], interpretationPackForTheme(theme));
+  }
+});
+
+test("writer system content never carries chart, subject or evidence data", () => {
+  for (const theme of [null, ...REPORT_THEME_IDS]) {
+    for (const content of buildWriterSystemContents(theme)) {
+      assert.ok(!/ev-[a-z0-9_-]+/.test(content), "no evidence ids in the static packs");
+      assert.ok(!/\d{4}-\d{2}-\d{2}/.test(content), "no dates in the static packs");
+    }
+  }
+});
@@ -90,8 +90,10 @@ test("checked-in registry verifies hashed product packages and leaves consult on
      },
      {
        name: "jyotish-personal-report",
-        version: "1.0.0",
-        sha256: "23149b9e1146b5a66b0762520b58eb750b67d95007144b959f0ff3d9ee2bf982",
+        // was 1.0.0 / 23149b9e...982; bumped 2026-09-01 with the interpretive
+        // fact layer and the static interpretation packs.
+        version: "1.1.0",
+        sha256: "6be2279b69b7da9446adeb508e27746c5aeb8b00dc9f5921f48f82bd8a8010e9",
      },
    ],
  );
@@ -1,10 +1,10 @@
 ---
 name: jyotish-personal-report
-version: 1.0.0
-description: "个人 Jyotish 报告编排与写作 Skill。仅以服务器验证的 ReportEvidenceBundleV2、其中的 Claim Cards/Blocked Sections，以及由该 Bundle 派生的结构计划组织报告；适用于 personal full/thematic report、个人报告、专题报告、报告重写与 research-depth 报告。不得计算星盘、读取聊天历史或使用工具轨迹补证。"
+version: 1.1.0
+description: "个人 Jyotish 报告编排与写作 Skill。仅以服务器验证的 ReportEvidenceBundleV2、其中的 Claim Cards/Interpretive Facts/Theme Narrative Seeds/Blocked Sections，以及由该 Bundle 派生的结构计划组织报告；适用于 personal full/thematic report、个人报告、专题报告、报告重写与 research-depth 报告。不得计算星盘、读取聊天历史或使用工具轨迹补证。"
 ---

-# Jyotish Personal Report（V1）
+# Jyotish Personal Report（V1.1）

 ## 1. 唯一职责

@@ -12,6 +12,7 @@ description: "个人 Jyotish 报告编排与写作 Skill。仅以服务器验证

 - 唯一可用于事实与结论的输入是一个完整、已验证的 `ReportEvidenceBundleV2`。
 - `claimCards` 是可写入正向解读的唯一结论来源；`supportingFacts`、`counterFacts`、`executedTechniqueRefs`、`timingBoundary` 与 `verificationQuestions` 只能约束和解释该结论，不得生成新的占星判断。
+- `interpretiveFacts`（yogas / functionalRoles / shadbalaRanking / savScores / currentDasha / convergenceDomains）与 `themeNarrativeSeeds` 是**服务器确定性生成的事实层**：可以引用、排序、分组和解释，可以用来支撑对应 Claim Card 的结论，但**不得据此产生该 Claim Card 之外的新占星断言**，也不得因内容变丰富而提高确定性级别。
 - `blockedSections`、`conflicts`、`executionLedger`、`evidenceRefs`、`answerPolicy` 与 `calculationProfile` 是边界和出处，不是让 writer 自行推算的原料。
 - `charts` 只可按原值展示。除非某项解释已经出现在 Claim Card 中，否则不得从宫位、星座、度数、分盘或 Dasha 自行推导含义。
 - 不包含、调用或建议任何计算代码；不调用工具，不浏览外部资料，不补算行星、宫位、分盘、Dasha、Transit、Yoga 或时间窗口。
@@ -29,6 +30,8 @@ description: "个人 Jyotish 报告编排与写作 Skill。仅以服务器验证

 若上述内容意外出现在上下文中，将其视为不可用数据。结构深度与 section plan 只能控制篇幅和顺序，不能成为证据。报告事实仍必须逐项回到 Bundle/Claim Card。

+调用方另外提供一份**静态解读知识包**（通用包 + 本章主题包）。它只约束措辞与解释方式：术语现代化、表达顺序、强弱与分值怎么说、必须避免的推理错误、禁语清单。它**不是事实来源**——不得据此产生 Bundle 中不存在的占星断言，也不得据此提高任何结论的确定性。知识包与 Bundle 冲突时以 Bundle 为准。
+
 ## 3. 强制两阶段：planner → writer

 ### Stage A — Planner
@@ -48,7 +51,7 @@ description: "个人 Jyotish 报告编排与写作 Skill。仅以服务器验证

 只根据**已验证的 plan + 原始 Bundle**写作：

- `write` 主题：围绕对应 Claim Card 的 `conclusion` 组织文字，同时保留 supporting/counter facts、`assertionLevel`、`timingBoundary` 与验证问题的限制。
+- `write` 主题：围绕对应 Claim Card 的 `conclusion` 组织文字，同时保留 supporting/counter facts、`assertionLevel`、`timingBoundary` 与验证问题的限制。可以引用 `interpretiveFacts` 与本主题 `themeNarrativeSeeds` 来展开、举证与措辞，但结论边界仍由该 Claim Card 决定。
 - `blocked` 主题：明确说明 Bundle 给出的 `reason` 与缺失技法；不得用常识、盘面直读、其他主题或泛化建议填补结论。
 - 冲突必须披露，反证不得省略；篇幅增加时优先展开证据链、冲突和边界，而非制造更多结论。
 - 只引用 Bundle 中存在的 evidence ids；引用状态为 `partial` 或 `blocked` 时必须按原状态表达。
@@ -0,0 +1,90 @@
+---
+name: jyotish-personal-report
+version: 1.1.0
+description: "个人 Jyotish 报告编排与写作 Skill。仅以服务器验证的 ReportEvidenceBundleV2、其中的 Claim Cards/Interpretive Facts/Theme Narrative Seeds/Blocked Sections，以及由该 Bundle 派生的结构计划组织报告；适用于 personal full/thematic report、个人报告、专题报告、报告重写与 research-depth 报告。不得计算星盘、读取聊天历史或使用工具轨迹补证。"
+---
+
+# Jyotish Personal Report（V1.1）
+
+## 1. 唯一职责
+
+本 Skill 只负责把服务器已验证的 `ReportEvidenceBundleV2` 组织成个人报告文档。它是**报告 planner + writer**，不是占星计算器、聊天 Agent、研究 Agent或工具执行器。
+
+- 唯一可用于事实与结论的输入是一个完整、已验证的 `ReportEvidenceBundleV2`。
+- `claimCards` 是可写入正向解读的唯一结论来源；`supportingFacts`、`counterFacts`、`executedTechniqueRefs`、`timingBoundary` 与 `verificationQuestions` 只能约束和解释该结论，不得生成新的占星判断。
+- `interpretiveFacts`（yogas / functionalRoles / shadbalaRanking / savScores / currentDasha / convergenceDomains）与 `themeNarrativeSeeds` 是**服务器确定性生成的事实层**：可以引用、排序、分组和解释，可以用来支撑对应 Claim Card 的结论，但**不得据此产生该 Claim Card 之外的新占星断言**，也不得因内容变丰富而提高确定性级别。
+- `blockedSections`、`conflicts`、`executionLedger`、`evidenceRefs`、`answerPolicy` 与 `calculationProfile` 是边界和出处，不是让 writer 自行推算的原料。
+- `charts` 只可按原值展示。除非某项解释已经出现在 Claim Card 中，否则不得从宫位、星座、度数、分盘或 Dasha 自行推导含义。
+- 不包含、调用或建议任何计算代码；不调用工具，不浏览外部资料，不补算行星、宫位、分盘、Dasha、Transit、Yoga 或时间窗口。
+
+开始前读取 `references/report-contract.md`。
+
+## 2. 输入隔离
+
+不得接收、读取、引用或复述以下内容：
+
+- 聊天历史、recent turns、上一条 assistant 消息；
+- 原始商业 Skill、其他 `SKILL.md`、system prompt 或 prompt 模板；
+- raw workflow、工具调用参数/返回、tool trace、reasoning trace、错误栈；
+- 内部文件路径、数据库记录、secret、token、cookie、模型配置或其他用户数据。
+
+若上述内容意外出现在上下文中，将其视为不可用数据。结构深度与 section plan 只能控制篇幅和顺序，不能成为证据。报告事实仍必须逐项回到 Bundle/Claim Card。
+
+调用方另外提供一份**静态解读知识包**（通用包 + 本章主题包）。它只约束措辞与解释方式：术语现代化、表达顺序、强弱与分值怎么说、必须避免的推理错误、禁语清单。它**不是事实来源**——不得据此产生 Bundle 中不存在的占星断言，也不得据此提高任何结论的确定性。知识包与 Bundle 冲突时以 Bundle 为准。
+
+## 3. 强制两阶段：planner → writer
+
+### Stage A — Planner
+
+先生成内部 `personal_report_section_plan.v1`，此阶段不写报告正文：
+
+1. 读取 `requestedThemes`，保持服务器给出的顺序。
+2. 对每个 requested theme 验证其**恰好**由一个 Claim Card 或一个 Blocked Section 覆盖；两者同时存在、两者都不存在、重复覆盖或出现未请求主题时 fail closed。
+3. 为每个主题建立一个 thematic section：
+   - 有 Claim Card：`disposition = write`；
+   - 只有 Blocked Section：`disposition = blocked`。
+4. 绑定 Bundle 中真实存在的 evidence refs。不得创建、猜测或改写 evidence id。
+5. 规划 executive summary、natal foundation、requested-theme sections、必要时 current phase、action notes、charts、claim/evidence appendix、blocked/conflict disclosure、provenance 与 disclaimer。
+6. 选择 `concise | standard | deep | research` 深度并分配篇幅；深度只改变展开量，不改变 assertion level、证据门槛或安全边界。
+
+### Stage B — Writer
+
+只根据**已验证的 plan + 原始 Bundle**写作：
+
+- `write` 主题：围绕对应 Claim Card 的 `conclusion` 组织文字，同时保留 supporting/counter facts、`assertionLevel`、`timingBoundary` 与验证问题的限制。可以引用 `interpretiveFacts` 与本主题 `themeNarrativeSeeds` 来展开、举证与措辞，但结论边界仍由该 Claim Card 决定。
+- `blocked` 主题：明确说明 Bundle 给出的 `reason` 与缺失技法；不得用常识、盘面直读、其他主题或泛化建议填补结论。
+- 冲突必须披露，反证不得省略；篇幅增加时优先展开证据链、冲突和边界，而非制造更多结论。
+- 只引用 Bundle 中存在的 evidence ids；引用状态为 `partial` 或 `blocked` 时必须按原状态表达。
+- 最终只返回调用方 schema 要求的结构化报告内容。禁止 HTML、CSS、JavaScript、内联样式、外链资源或可执行 URL。
+
+## 4. 四档深度
+
+遵循 section plan 的 `targetCharacters`；默认 thematic section 目标范围如下：
+
+| depth | 每个可写主题目标字符 | 写作要求 |
+|---|---:|---|
+| `concise` | 120–500 | 一段核心结论，最少证据与必要 caveat；不省略任何 requested theme。 |
+| `standard` | 260–1200 | 结论、主要支持/反证、行动提示与边界。 |
+| `deep` | 480–2000 | 展开证据链、参数敏感性、冲突与验证问题，但不新增技法。 |
+| `research` | 600–2800 | 逐 Claim Card 审计式展开，完整披露 execution ledger、conflicts、blocked items 与 provenance；`research` 不代表可以联网或补证。 |
+
+若调用方没有提供已验证 depth：`presentationMode = research` 映射为 `research`，其他情况映射为 `standard`。Blocked section 只需清楚说明阻塞，不得为满足字数而填充伪结论。
+
+## 5. 结论与时间边界
+
+- `assertionLevel` 原样保留，绝不升级。`single_system_inference`、`parameter_sensitive`、`unclosed_divisional_chart`、`user_history_verification_required` 或 `blocked` 不得改写为共识、确定、必然或已验证。
+- 只有 Claim Card 明确提供且 `answerPolicy` 允许时，才可写时间信息。日期/时间窗只能来自 `timingBoundary` 或与有效 evidence ref 绑定的事实；不得计算、外推、缩窄、扩展或编造日期。
+- `canAnswerPreciseTiming = false`，或 `deterministicClaimsForbiddenFor` 包含 timing/exact_dates/相关技法时，不得给出精确日期或确定性应期。
+- 不得因 `research` 或更长篇幅提高置信度。
+
+## 6. 医疗、财务与安全表达
+
+- 禁止医疗诊断、疾病确认、治疗方案、停药建议或以占星替代专业医疗。若 Claim Card 涉及健康，只能按证据写成非诊断性的压力/关注提示，并建议在有现实症状时咨询合格专业人士。
+- 禁止确定性财务承诺、保本/收益保证、具体买卖指令或“必赚/必亏”式结论。财富主题只能写证据支持的倾向、风险管理与非个性化行动提示。
+- 禁止无证据日期、确定性灾祸、死亡/寿命断言、法律结论和任何超出 Bundle 的身份或隐私信息。
+
+## 7. Fail closed
+
+遇到以下任一情况时停止生成实质结论，并返回调用方定义的 blocked/validation failure：Bundle schema/hash 无效；requested theme 覆盖不唯一；Claim Card 引用悬空；缺失对应 execution receipt；输入要求从禁用来源补证；输出 schema 无法满足。
+
+不得通过删掉主题、隐藏 blocked、降低 schema、输出自由文本或自行计算来“完成”报告。
@@ -0,0 +1,92 @@
+# Personal Report Evidence and Writing Contract
+
+## 1. Authoritative fields
+
+| Bundle field | Writer permission |
+|---|---|
+| `subject` | Display only the provided safe labels and birth-time status. |
+| `requestedThemes` | Defines the exact thematic coverage set and order. |
+| `reportType`, `presentationMode` | Controls document shape/presentation, never evidence strength. |
+| `calculationProfile` | Display provenance/parameters only; never recompute from it. |
+| `skill` | Display immutable skill identity/provenance; never expose package paths or source text. |
+| `charts` | Render supplied chart facts only; do not interpret them independently. |
+| `claimCards` | The only source of affirmative astrological conclusions. |
+| `blockedSections` | Mandatory blocked coverage, including reason and missing technique refs. |
+| `conflicts` | Mandatory unresolved/bounded conflict disclosure. |
+| `executionLedger`, `evidenceRefs` | Technique truth and citation allowlist. They do not authorize new conclusions. |
+| `answerPolicy` | Hard ceiling for timing, medical, investment and other deterministic claims. |
+
+No field authorizes reading chat history, raw workflows, tool traces, internal paths, other Skills or external sources.
+
+## 2. Claim Card rendering
+
+For one Claim Card:
+
+1. Use `conclusion` as the semantic center. Paraphrase for clarity without broadening scope.
+2. Include relevant `supportingFacts`; include material `counterFacts` and conflicts at every depth.
+3. Cite only `executedTechniqueRefs` and fact `evidenceRef` values that exist in Bundle `evidenceRefs`.
+4. Preserve `assertionLevel` exactly:
+   - `multi_system_consensus`: multiple executed, usable systems agree; still avoid absolute certainty.
+   - `single_system_inference`: one-system interpretation; label as limited inference.
+   - `parameter_sensitive`: state which conclusion is sensitive without inventing the parameter effect.
+   - `unclosed_divisional_chart`: state that the divisional-chart evidence is incomplete.
+   - `user_history_verification_required`: present as a hypothesis requiring the provided verification questions.
+   - `blocked`: no affirmative prediction.
+5. `timingBoundary` is a ceiling. Do not derive a smaller interval or a calendar date from it.
+
+A Claim Card never grants permission to infer a second claim from raw chart facts.
+
+## 3. Requested-theme invariant
+
+For every entry in `requestedThemes`, the plan and final document must contain exactly one thematic section:
+
+```text
+Claim Card exists, Blocked Section absent  -> write section
+Claim Card absent, Blocked Section exists  -> blocked section
+otherwise                                  -> validation failure
+```
+
+Do not merge away a requested theme, replace it with another theme, or add an unrequested theme. A blocked theme remains visible even when other themes are writable.
+
+## 4. Planner checklist
+
+The planner emits structure, not prose or facts:
+
+- validate Bundle identity/hash before use;
+- select or validate one of `concise`, `standard`, `deep`, `research`;
+- preserve requested-theme order and one-to-one coverage;
+- assign `write`/`blocked` disposition;
+- attach only existing evidence ids;
+- include fixed report sections required by the runtime schema;
+- mark current phase blocked when timing is blocked;
+- keep provenance and disclaimer sections;
+- reject dangling refs or contradictory coverage.
+
+## 5. Writer checklist
+
+Before finalizing each section, verify:
+
+- every sentence is traceable to the corresponding Claim Card, fact, blocked reason, conflict, receipt, policy or safe subject/provenance field;
+- no assertion level was upgraded;
+- no chart interpretation was invented;
+- no date was calculated or supplied without evidence and policy permission;
+- medical wording is non-diagnostic;
+- financial wording contains no deterministic promise or personalized trade instruction;
+- blocked sections contain no deterministic prediction;
+- HTML/CSS/scripts/internal paths/tool traces/chat content are absent;
+- evidence references exist and match the cited technique status.
+
+## 6. Depth behavior
+
+Depth changes explanation density only:
+
+- `concise`: conclusion + strongest support/counterpoint + caveat.
+- `standard`: add evidence context, actions and verification notes.
+- `deep`: add full supporting/counter evidence, parameter sensitivity and conflict discussion.
+- `research`: add claim-by-claim audit, ledger/provenance detail and explicit blocked inventory.
+
+At all depths, requested-theme coverage, conflicts, blocked sections, answer policy and disclaimer remain mandatory. Never pad a blocked section or repeat the same claim to hit a target length.
+
+## 7. Output boundary
+
+Produce only the structured data required by the caller's report-document schema. The rendering layer owns typography, layout, charts, print and export. Therefore the Skill must not emit HTML, CSS, JavaScript, SVG markup, inline styles, remote resources, executable links, file paths, or implementation instructions.
@@ -135,6 +135,14 @@
      "sha256": "23149b9e1146b5a66b0762520b58eb750b67d95007144b959f0ff3d9ee2bf982",
      "sourceCommit": null,
      "packagePath": "skills/jyotish-personal-report/versions/1.0.0",
+      "status": "deprecated"
+    },
+    {
+      "name": "jyotish-personal-report",
+      "version": "1.1.0",
+      "sha256": "6be2279b69b7da9446adeb508e27746c5aeb8b00dc9f5921f48f82bd8a8010e9",
+      "sourceCommit": null,
+      "packagePath": "skills/jyotish-personal-report/versions/1.1.0",
      "status": "active"
    }
  ]
@@ -7,7 +7,10 @@ from pathlib import Path

 ROOT = Path(__file__).resolve().parents[1]
 PACKAGE_ROOT = ROOT / "skills/jyotish-personal-report"
-VERSION_ROOT = PACKAGE_ROOT / "versions/1.0.0"
+# was versions/1.0.0; bumped 2026-09-01 when the skill contract gained the
+# interpretive fact layer and the static interpretation packs.
+ACTIVE_VERSION = "1.1.0"
+VERSION_ROOT = PACKAGE_ROOT / f"versions/{ACTIVE_VERSION}"
 REGISTRY = ROOT / "skills/skill-package-registry.json"
 HASH_DOMAIN = b"jyotisha-skill-package-v1\0"

@@ -45,10 +48,10 @@ def test_personal_report_skill_is_versioned_and_registry_hash_matches_package_by
    ]
    assert matches == [{
        "name": "jyotish-personal-report",
-        "version": "1.0.0",
+        "version": ACTIVE_VERSION,
        "sha256": _package_sha256(VERSION_ROOT),
        "sourceCommit": None,
-        "packagePath": "skills/jyotish-personal-report/versions/1.0.0",
+        "packagePath": f"skills/jyotish-personal-report/versions/{ACTIVE_VERSION}",
        "status": "active",
    }]
    assert (PACKAGE_ROOT / "SKILL.md").read_bytes() == (VERSION_ROOT / "SKILL.md").read_bytes()
@@ -87,3 +90,8 @@ def test_personal_report_skill_encodes_evidence_only_two_stage_and_safety_bounda
    assert "恰好" in skill
    assert "不得从宫位、星座、度数、分盘或 Dasha 自行推导含义" in skill
    assert "research` 不代表可以联网或补证" in skill
+    # v1.1.0: the interpretive layer and the static packs are fact-bounded.
+    assert "interpretiveFacts" in skill
+    assert "themeNarrativeSeeds" in skill
+    assert "不得据此产生该 Claim Card 之外的新占星断言" in skill
+    assert "它**不是事实来源**" in skill