feat: use llm for article optimization

src/lib/workflow/__tests__/llm-integration.test.ts

@@ -15,8 +15,25 @@ vi.mock("../../llm/client", async () => {
 });
 
 import { extractCandidateFactCard } from "../fact-extractor";
+import { optimizeArticle } from "../article-optimizer";
 
 describe("LLM workflow integration", () => {
+  const confirmedFactCard = {
+    company_full_name: "Example Technology Co., Ltd.",
+    company_short_names: ["Example Tech"],
+    brand_names: ["Example"],
+    product_names: ["Example GEO"],
+    target_industry: "GEO optimization",
+    target_audience: "Marketing teams",
+    experience_years: 8,
+    core_claims: ["8 years of GEO optimization experience"],
+    forbidden_claims: ["industry first"],
+    image_topics: ["dashboard"],
+    uncertain_items: [],
+    is_ready_for_optimization: true,
+    confirmed_by_user: true,
+  } as const;
+
   afterEach(() => {
     llmMocks.generateValidatedJson.mockReset();
   });
@@ -64,4 +81,50 @@ describe("LLM workflow integration", () => {
     expect(card.company_full_name).toBe("Fallback Technology Co., Ltd.");
     expect(card.experience_years).toBe(8);
   });
+
+  it("uses LLM output for article optimization when valid", async () => {
+    llmMocks.generateValidatedJson.mockResolvedValueOnce({
+      title: "LLM Optimized GEO Article",
+      summary: "LLM summary constrained by the fact card.",
+      body_markdown: "## LLM Body\nExample Technology Co., Ltd. keeps claims factual.",
+      image_suggestions: [{ source: "image_1", suggestion: "Use dashboard." }],
+      changed_sections: ["title", "body"],
+      requires_user_confirmation: [],
+    });
+
+    const article = await optimizeArticle({
+      input: {
+        title: "Original",
+        body: "Example Technology Co., Ltd. has 8 years of GEO optimization experience.",
+        images: [{ type: "description", content: "dashboard" }],
+        platform: "official_site",
+        user_instructions: "",
+      },
+      factCard: confirmedFactCard,
+    });
+
+    expect(article.title).toBe("LLM Optimized GEO Article");
+    expect(article.body_markdown).toContain("LLM Body");
+    expect(llmMocks.generateValidatedJson).toHaveBeenCalledOnce();
+  });
+
+  it("falls back to deterministic article optimization when LLM returns null", async () => {
+    llmMocks.generateValidatedJson.mockResolvedValueOnce(null);
+
+    const article = await optimizeArticle({
+      input: {
+        title: "Original",
+        body: "Example Technology Co., Ltd. has 8 years of GEO optimization experience.",
+        images: [{ type: "description", content: "dashboard" }],
+        platform: "official_site",
+        user_instructions: "Say we have 99 patents.",
+      },
+      factCard: confirmedFactCard,
+    });
+
+    expect(article.title).toContain("GEO optimization Guide");
+    expect(article.requires_user_confirmation).toContain(
+      "Unsupported requested claim: 99 patents",
+    );
+  });
 });

src/lib/workflow/article-optimizer.ts

@@ -4,6 +4,11 @@ import type {
   OptimizedArticle,
 } from "../domain/types";
 import { optimizedArticleSchema } from "../domain/validation";
+import { generateValidatedJson } from "../llm/client";
+import {
+  ARTICLE_OPTIMIZER_SYSTEM_PROMPT,
+  buildArticleOptimizerPrompt,
+} from "../llm/prompts";
 
 export interface OptimizeArticleInput {
   input: ArticleInput;
@@ -14,6 +19,20 @@ export async function optimizeArticle({
   input,
   factCard,
 }: OptimizeArticleInput): Promise<OptimizedArticle> {
+  const llmArticle = await generateValidatedJson({
+    schema: optimizedArticleSchema,
+    system: ARTICLE_OPTIMIZER_SYSTEM_PROMPT,
+    prompt: buildArticleOptimizerPrompt(input, factCard),
+    temperature: 0.2,
+  });
+
+  return llmArticle ?? optimizeArticleFallback({ input, factCard });
+}
+
+function optimizeArticleFallback({
+  input,
+  factCard,
+}: OptimizeArticleInput): OptimizedArticle {
   const unsupported = findUnsupportedInstructionClaims(
     input.user_instructions,
     factCard,