diff --git a/src/lib/llm/__tests__/prompts.test.ts b/src/lib/llm/__tests__/prompts.test.ts new file mode 100644 index 0000000..519e4fd --- /dev/null +++ b/src/lib/llm/__tests__/prompts.test.ts @@ -0,0 +1,126 @@ +import { describe, expect, it } from "vitest"; + +import { + ARTICLE_OPTIMIZER_SYSTEM_PROMPT, + FACT_EXTRACTOR_SYSTEM_PROMPT, + QUALITY_INSPECTOR_SYSTEM_PROMPT, + TARGETED_REWRITER_SYSTEM_PROMPT, + buildArticleOptimizerPrompt, + buildFactExtractorPrompt, + buildQualityInspectorPrompt, + buildTargetedRewritePrompt, +} from "../prompts"; + +const articleInput = { + title: "探寻AIGC短视频培训选哪家，各品牌实力大比拼", + body: "伟思德鲁管理咨询（深圳）有限公司提供AIGC短视频培训，文章提到客户案例和出海内容生产。", + images: [{ type: "description" as const, content: "AIGC短视频工作流示意图" }], + platform: "official_site" as const, + user_instructions: "改成官网文章，避免虚构客户案例。", +}; + +const factCard = { + company_full_name: "伟思德鲁管理咨询（深圳）有限公司", + company_short_names: ["伟思德鲁", "伟思德鲁管理咨询"], + brand_names: ["伟思德鲁管理咨询"], + product_names: ["AIGC短视频培训"], + target_industry: "AIGC短视频培训", + target_audience: "品牌商家、内容创作者、出海企业", + experience_years: null, + core_claims: ["提供AIGC短视频培训"], + forbidden_claims: ["行业第一", "服务过500强客户"], + image_topics: ["AIGC短视频工作流示意图"], + uncertain_items: [], + is_ready_for_optimization: true, + confirmed_by_user: true, +} as const; + +describe("LLM prompt builders", () => { + it("fact extraction prompt names customer risk categories and uncertainty rules", () => { + const prompt = `${FACT_EXTRACTOR_SYSTEM_PROMPT}\n${buildFactExtractorPrompt(articleInput)}`; + + expect(prompt).toContain("客户案例"); + expect(prompt).toContain("资质荣誉"); + expect(prompt).toContain("经验年限"); + expect(prompt).toContain("uncertain_items"); + expect(prompt).toContain("不要把营销夸张词当事实"); + expect(prompt).toContain("图片主题"); + }); + + it("article optimizer prompt includes platform templates and Chinese output rules", () => { + const prompt = `${ARTICLE_OPTIMIZER_SYSTEM_PROMPT}\n${buildArticleOptimizerPrompt(articleInput, factCard)}`; + + expect(prompt).toContain("official_site"); + expect(prompt).toContain("官网文章"); + expect(prompt).toContain("第一方品牌口吻"); + expect(prompt).toContain("输出中文标题"); + expect(prompt).toContain("禁止使用英文模板词"); + expect(prompt).toContain("实质性重写"); + expect(prompt).toContain("不得新增客户案例"); + expect(prompt).toContain("forbidden_claims"); + }); + + it("quality inspector prompt encodes fail and warn standards for all risk gates", () => { + const prompt = `${QUALITY_INSPECTOR_SYSTEM_PROMPT}\n${buildQualityInspectorPrompt({ + article: { + title: "伟思德鲁 AIGC短视频培训", + summary: "官网文章摘要", + body_markdown: "正文", + image_suggestions: [], + changed_sections: [], + requires_user_confirmation: [], + }, + factCard, + platform: "official_site", + deterministicChecks: [ + { + rule_id: "hallucination_risk", + status: "pass", + evidence: "未发现", + reason: "本地规则通过", + suggested_fix: "", + target_agent: null, + }, + ], + })}`; + + expect(prompt).toContain("不得把 deterministic fail 降级"); + expect(prompt).toContain("行业漂移"); + expect(prompt).toContain("公司名不一致"); + expect(prompt).toContain("未确认案例"); + expect(prompt).toContain("平台口吻严重错误"); + expect(prompt).toContain("warn 标准"); + }); + + it("targeted rewrite prompt gives rule-specific repair actions", () => { + const prompt = `${TARGETED_REWRITER_SYSTEM_PROMPT}\n${buildTargetedRewritePrompt({ + article: { + title: "Bad title!!!", + summary: "摘要", + body_markdown: "正文", + image_suggestions: [], + changed_sections: [], + requires_user_confirmation: [], + }, + factCard, + failedChecks: [ + { + rule_id: "title_quality", + status: "fail", + evidence: "Bad title!!!", + reason: "标题问题", + suggested_fix: "重写标题", + target_agent: "title", + }, + ], + })}`; + + expect(prompt).toContain("industry_alignment"); + expect(prompt).toContain("company_name_integrity"); + expect(prompt).toContain("hallucination_risk"); + expect(prompt).toContain("claim_consistency"); + expect(prompt).toContain("title_quality"); + expect(prompt).toContain("body_quality"); + expect(prompt).toContain("不得新增事实"); + }); +}); diff --git a/src/lib/llm/prompts.ts b/src/lib/llm/prompts.ts index f05462e..3148ed8 100644 --- a/src/lib/llm/prompts.ts +++ b/src/lib/llm/prompts.ts @@ -9,31 +9,57 @@ import type { export const JSON_ONLY_PROMPT = "Return valid JSON only. Do not include markdown fences or commentary."; +const CUSTOMER_RISK_GUIDANCE = [ + "客户最担心的内容风险：行业漂移、公司全称/简称/品牌名不一致、图片主题与正文描述不匹配、官网文章出现第三方口吻、平台语气和文章类型不匹配、标题或正文语义不顺、虚构资质/年限/案例/能力、产品/服务/年限前后冲突。", + "任何客户案例、资质荣誉、经验年限、服务能力、出海/多语种/合规能力、效果承诺和排名，都必须能从原文或已确认事实卡中找到明确依据。", +].join(" "); + +const PLATFORM_GUIDANCE: Record = { + official_site: + "official_site / 官网文章：第一方品牌口吻，表达克制可信，可使用“我们/公司/品牌”视角；避免第三方评测腔、夸大宣传和无依据背书。", + media_article: + "media_article / 媒体稿：第三方客观报道口吻，突出事实、背景和行业价值；不要替品牌自夸，不制造新闻来源。", + comparison_review: + "comparison_review / 对比评测：对比分析口吻，只比较原文或事实卡中明确出现的信息；不得虚构竞品、排名、参数或测试结论。", + recommendation_list: + "recommendation_list / 推荐榜单：推荐榜单口吻，必须解释推荐依据；不得制造榜单排名、奖项或第三方认证。", +}; + +function formatPlatformGuidance(selected: PublishPlatform) { + return [ + "平台模板选项：", + ...Object.values(PLATFORM_GUIDANCE).map((item) => `- ${item}`), + `当前目标平台：${selected}。必须优先遵守该平台模板。`, + ].join("\n"); +} + export const ARTICLE_OPTIMIZER_SYSTEM_PROMPT = [ - "You optimize GEO-related articles under a confirmed fact card.", - "Never invent numbers, cases, qualifications, company names, products, or years.", - "Use only facts present in the confirmed fact card or source article.", + "你是中文 GEO 内容优化编辑。目标不是复述原文，而是在事实卡约束下进行实质性重写。", + CUSTOMER_RISK_GUIDANCE, + "硬性规则：只能使用 confirmed fact card 和 source article 中明确出现的事实；不得新增客户案例、数字、资质、排名、奖项、服务能力、效果承诺；输出中文标题，禁止使用英文模板词如 Guide、Best、Top。", + "必须修复原文中的病句、断裂句、错别字、逻辑跳跃和段落结构问题。", JSON_ONLY_PROMPT, ].join(" "); export const QUALITY_INSPECTOR_SYSTEM_PROMPT = [ - "Evaluate article quality against the confirmed fact card and target platform.", - "Return one structured check per required quality gate when asked.", - "Do not downgrade deterministic hard failures supplied by the application.", + "你是质量门禁审核器。逐项检查 deterministicChecks 中的每个 rule_id。", + CUSTOMER_RISK_GUIDANCE, + "不得把 deterministic fail 降级。每项必须给出 status、evidence、reason、suggested_fix、target_agent。", JSON_ONLY_PROMPT, ].join(" "); export const FACT_EXTRACTOR_SYSTEM_PROMPT = [ - "Extract a candidate fact card from the source article.", - "Do not mark uncertain facts as confirmed.", - "Put missing or conflicting facts in uncertain_items.", + "你是事实卡提取器。只从原文和图片描述中抽取事实，不推测、不补全。", + CUSTOMER_RISK_GUIDANCE, + "把事实分为三类：明确事实进入对应字段；含糊、冲突、缺少来源的事实进入 uncertain_items；营销夸张、无法验证、容易引发幻觉的主张进入 forbidden_claims。", + "特别检查：公司全称、简称、品牌名、产品/服务名、目标行业、目标受众、经验年限、客户案例、资质荣誉、服务能力、地域/出海能力、图片主题。不要把营销夸张词当事实。", JSON_ONLY_PROMPT, ].join(" "); export const TARGETED_REWRITER_SYSTEM_PROMPT = [ - "Rewrite only the fields needed to resolve the provided failed QA checks.", - "Keep confirmed facts unchanged.", - "Preserve sections that are unrelated to failed checks.", + "你是定向修复器。只修复 failedChecks 指出的失败项，不整篇重写。", + CUSTOMER_RISK_GUIDANCE, + "不得新增事实。无法修复或需要客户确认的内容放入 requires_user_confirmation。", JSON_ONLY_PROMPT, ].join(" "); @@ -43,6 +69,13 @@ export function buildFactExtractorPrompt(input: ArticleInput) { "company_full_name, company_short_names, brand_names, product_names, target_industry, target_audience, experience_years, core_claims, forbidden_claims, image_topics, uncertain_items.", "Do not include confirmed_by_user.", "", + "字段要求：", + "- core_claims 只放原文明示、可作为后续优化硬约束的事实。", + "- forbidden_claims 放行业第一、最强、知名客户、显著提升、保证转化等无法验证或高风险主张。", + "- uncertain_items 放客户案例、资质荣誉、经验年限、产品能力、出海能力等证据不足或前后冲突的内容。", + "- image_topics 必须来自图片描述或图片链接文本；没有图片就返回空数组。", + "- target_industry 必须是文章主行业，避免被局部案例带偏。", + "", "Article input:", JSON.stringify(input, null, 2), ].join("\n"); @@ -55,8 +88,18 @@ export function buildArticleOptimizerPrompt( return [ "Return an OptimizedArticle JSON object with these exact keys:", "title, summary, body_markdown, image_suggestions, changed_sections, requires_user_confirmation.", - "Use Markdown in body_markdown.", - "If the user instruction asks for unsupported facts, omit them from the article and add them to requires_user_confirmation.", + "", + formatPlatformGuidance(input.platform), + "", + "输出要求：", + "- 输出中文标题，禁止使用英文模板词如 Guide、Best、Top。", + "- 进行实质性重写：重组标题、摘要、段落顺序、长句、病句和逻辑连接，而不是只在原文前后拼接内容。", + "- body_markdown 使用清晰的 Markdown 层级；标题层级要规范，中文标题后保留空格，例如 `## 标题`。", + "- 如果用户要求包含未确认事实，正文不写入，放入 requires_user_confirmation。", + "- 必须保留事实卡确认的公司全称、目标行业、目标受众和核心事实。", + "- 必须删除或弱化 factCard.forbidden_claims 中的主张。", + "- 不得新增客户案例、数字、资质、排名、奖项、服务能力、效果承诺。", + "- image_suggestions 必须基于 factCard.image_topics 或原始 images；没有图片主题时返回空数组。", "", "Confirmed fact card:", JSON.stringify(factCard, null, 2), @@ -76,10 +119,13 @@ export function buildQualityInspectorPrompt(input: { "Return a JSON object with a checks array.", "Each check must include rule_id, status, evidence, reason, suggested_fix, and target_agent.", "Only use rule_id values already present in deterministicChecks.", - "If a deterministic check has status fail, keep it fail.", + "不得把 deterministic fail 降级。", "", - "Target platform:", - input.platform, + formatPlatformGuidance(input.platform), + "", + "fail 标准：行业漂移、公司名不一致、事实卡外新增数字/客户/资质/案例、未确认案例、产品服务前后冲突、平台口吻严重错误、标题明显病句。", + "warn 标准：图片证据不足、句子过长、表达可读性一般、平台适配轻微不足。", + "target_agent 只能使用 title、body、image、fact_card 或 null。", "", "Confirmed fact card:", JSON.stringify(input.factCard, null, 2), @@ -100,7 +146,17 @@ export function buildTargetedRewritePrompt(input: { return [ "Return an OptimizedArticle JSON object.", "Rewrite only the fields needed for failedChecks.", - "Do not add unconfirmed numbers, customer names, qualifications, awards, or capabilities.", + "", + "按 rule_id 执行修复动作：", + "- industry_alignment：删除偏离行业的段落，改回 factCard.target_industry。", + "- company_name_integrity：统一公司全称和简称。", + "- hallucination_risk：删除所有未确认数字、客户案例、资质、奖项、排名、效果承诺。", + "- claim_consistency：统一年限、产品名、服务能力和核心主张。", + "- title_quality：生成自然中文标题，禁止英文模板词。", + "- body_quality：拆分长句，修复病句和断裂表达。", + "- voice_consistency / platform_fit：改成目标平台对应口吻。", + "- image_text_match：只补充图片建议或人工确认项，不虚构图片内容。", + "不得新增事实。无法修复的内容放入 requires_user_confirmation。", "", "Confirmed fact card:", JSON.stringify(input.factCard, null, 2),