feat(api): backfill article markdown storage

.prettierignore

@@ -4,4 +4,5 @@
 .codex/
 .omx/
 .turbo/
+pnpm-lock.yaml
 tmp/

README.md

@@ -15,6 +15,8 @@ when needed.
 - The first end-to-end slice is implemented as the current working slice.
 - `apps/api` now ingests feeds into PostgreSQL on boot and serves persisted
   article list and detail endpoints.
+- `apps/api` now also attempts best-effort article body extraction during
+  ingestion and stores markdown internally for later summarization work.
 - `apps/web` renders the reader UI and consumes the API over HTTP.
 - Shared UI primitives live in `packages/ui`.
 
@@ -144,6 +146,17 @@ tests handle the test database internally through `TEST_DATABASE_URL`; those
 test-database operations are intentionally not exposed as developer-facing
 commands.
 
+Article body storage is now part of the normal ingestion lifecycle rather than a
+manual script. If one persisted article needs a repair pass, use the narrow API
+endpoint:
+
+```bash
+curl -X POST http://127.0.0.1:3000/article-content/<article-id>/retry
+```
+
+That endpoint is a secondary repair path only. The public article read APIs
+still do not expose stored markdown in this slice.
+
 `pnpm dev` at the repo root no longer applies Prisma migrations implicitly. Run
 an explicit API migration command before starting the dev servers whenever your
 local schema is behind:

README.zh-Hans.md

@@ -12,6 +12,7 @@ RSSift 是一个基于 Turborepo 的 AI 辅助 RSS 筛选工具单仓库。
 - 项目目前处于敏捷、迭代式开发中。
 - 已完成第一条端到端切片，作为当前可工作的切片。
 - `apps/api` 现在会在启动时把 feed 入库到 PostgreSQL，并提供持久化的文章列表与详情接口。
+- `apps/api` 现在也会在 ingestion 期间以 best-effort 方式尝试抽取并落库文章正文 Markdown，为后续摘要能力准备输入层。
 - `apps/web` 渲染阅读器界面，并通过 HTTP 消费 API。
 - 可复用的 UI 基础组件位于 `packages/ui`。
 
@@ -137,6 +138,16 @@ pnpm --filter api db:seed
 的开发示例数据，请使用 `db:seed`。测试数据库由测试程序通过
 `TEST_DATABASE_URL` 在内部处理，不再作为开发者操作命令暴露。
 
+文章正文落库现在属于正常 ingestion 生命周期，而不是手工脚本。如果某一篇已
+持久化文章需要补救性重跑，可以调用这个狭窄接口：
+
+```bash
+curl -X POST http://127.0.0.1:3000/article-content/<article-id>/retry
+```
+
+这个接口只是 repair path，不是默认工作流。本切片里公开的文章读取 API 仍
+然不会暴露已存储的 Markdown。
+
 仓库根目录的 `pnpm dev` 不会再隐式执行 Prisma 迁移。只要本地 schema
 落后于迁移历史，请先显式运行 API 迁移命令，再启动开发服务：
 

apps/api/README.md

@@ -2,8 +2,8 @@
 
 This app owns the PostgreSQL-backed feed ingestion backbone for the repository.
 It reads `apps/api/feeds.opml`, ingests feeds on boot with best-effort
-isolation, and serves the existing read-only `/articles` contract from
-persisted data.
+isolation, attempts article body extraction during ingestion, and serves the
+existing read-only `/articles` contract from persisted data.
 
 ## Local Run
 
@@ -57,6 +57,8 @@ The API runs on `http://127.0.0.1:3000` by default.
   `FEED_OPML_PATH`, `INGEST_ON_BOOT`, and `PORT`.
 - `apps/api/feeds.opml` is the app-owned local subscription input.
 - Feed parsing uses `feedsmith`.
+- Article body extraction uses `@mozilla/readability`, `jsdom`, and `turndown`
+  inside `apps/api`.
 - Prisma schema, migrations, and generated client stay inside `apps/api`.
 
 ## Endpoints
@@ -76,6 +78,15 @@ The API runs on `http://127.0.0.1:3000` by default.
     - `summary`
     - `originalUrl`
   - Returns `404` for unknown article IDs.
+- `POST /article-content/:id/retry`
+  - Re-runs article body extraction for one persisted article as a repair path.
+  - Returns `{ "status": "succeeded" }`, or a narrow structured
+    `failed`/`skipped` result when extraction cannot complete.
+  - Returns `404` for unknown article IDs.
+
+Article body markdown stays internal in this slice. The public `GET /articles`
+and `GET /articles/:id` payloads remain unchanged even though
+`contentMarkdown` and `contentExtractedAt` are now stored on `Article`.
 
 ## Validation
 

apps/api/e2e/article-content-retry.e2e-spec.ts

@@ -0,0 +1,124 @@
+import type { INestApplication } from "@nestjs/common";
+import { Test } from "@nestjs/testing";
+import {
+  afterAll,
+  beforeAll,
+  beforeEach,
+  describe,
+  expect,
+  it,
+  jest,
+} from "@jest/globals";
+import request from "supertest";
+
+import { AppModule } from "../src/app.module";
+import {
+  createTestPrismaClient,
+  prepareTestDatabase,
+} from "../test-support/database";
+
+describe("Article content retry endpoint (e2e)", () => {
+  let app: INestApplication;
+  let prisma: ReturnType<typeof createTestPrismaClient>;
+
+  beforeAll(async () => {
+    process.env["TEST_DATABASE_URL"] ??=
+      "postgresql://rssift:rssift@127.0.0.1:5432/rssift_test";
+    process.env["DATABASE_URL"] = process.env["TEST_DATABASE_URL"];
+    process.env["INGEST_ON_BOOT"] = "false";
+
+    await prepareTestDatabase();
+    prisma = createTestPrismaClient();
+
+    const moduleFixture = await Test.createTestingModule({
+      imports: [AppModule],
+    }).compile();
+
+    app = moduleFixture.createNestApplication();
+    await app.init();
+  });
+
+  beforeEach(async () => {
+    await prisma.article.deleteMany();
+    await prisma.feed.deleteMany();
+    jest.restoreAllMocks();
+
+    const feed = await prisma.feed.create({
+      data: {
+        feedUrl: "https://example.com/feed.xml",
+        siteTitle: "Example feed",
+      },
+    });
+
+    await prisma.article.create({
+      data: {
+        contentMarkdown: "# Old content",
+        feedId: feed.id,
+        identityHash: "hash-1",
+        identitySourceType: "SOURCE_ID",
+        identitySourceValue: "guid-1",
+        ingestedAt: new Date("2026-04-15T10:00:00.000Z"),
+        originalUrl: "https://example.com/articles/1",
+        publishedAt: new Date("2026-04-15T10:00:00.000Z"),
+        sourceId: "guid-1",
+        summary: "Summary 1",
+        title: "Article 1",
+      },
+    });
+  });
+
+  afterAll(async () => {
+    await app.close();
+    await prisma.$disconnect();
+  });
+
+  it("retries extraction for a single article and persists refreshed markdown", async () => {
+    jest.spyOn(global, "fetch").mockResolvedValue(
+      new Response(
+        `<!doctype html>
+        <html>
+          <body>
+            <article>
+              <h1>Article 1</h1>
+              <p>Freshly retried body content for this article.</p>
+            </article>
+          </body>
+        </html>`,
+        { status: 200 },
+      ),
+    );
+
+    const article = await prisma.article.findFirstOrThrow({
+      orderBy: {
+        id: "asc",
+      },
+    });
+    const server = app.getHttpServer() as Parameters<typeof request>[0];
+    const response = await request(server)
+      .post(`/article-content/${article.id}/retry`)
+      .expect(200);
+
+    expect(response.body).toEqual({
+      status: "succeeded",
+    });
+
+    const updated = await prisma.article.findUniqueOrThrow({
+      where: {
+        id: article.id,
+      },
+    });
+
+    expect(updated.contentMarkdown).toBe(
+      "# Article 1\n\nFreshly retried body content for this article.",
+    );
+    expect(updated.contentExtractedAt).toBeInstanceOf(Date);
+  });
+
+  it("returns 404 for an unknown article id", async () => {
+    const server = app.getHttpServer() as Parameters<typeof request>[0];
+
+    await request(server)
+      .post("/article-content/unknown-article-id/retry")
+      .expect(404);
+  });
+});

apps/api/e2e/articles.e2e-spec.ts

@@ -34,7 +34,7 @@ describe("Articles endpoints (e2e)", () => {
     process.env["TEST_DATABASE_URL"] ??=
       "postgresql://rssift:rssift@127.0.0.1:5432/rssift_test";
     process.env["DATABASE_URL"] = process.env["TEST_DATABASE_URL"];
-    process.env["INGEST_ON_BOOT"] ??= "false";
+    process.env["INGEST_ON_BOOT"] = "false";
 
     await prepareTestDatabase();
     prisma = createTestPrismaClient();
@@ -65,6 +65,8 @@ describe("Articles endpoints (e2e)", () => {
           identityHash: "hash-1",
           identitySourceType: "SOURCE_ID",
           identitySourceValue: "guid-1",
+          contentExtractedAt: new Date("2026-04-15T10:05:00.000Z"),
+          contentMarkdown: "# Article 1\n\nPersisted body",
           ingestedAt: new Date("2026-04-15T10:00:00.000Z"),
           originalUrl: "https://example.com/articles/1",
           publishedAt: new Date("2026-04-15T10:00:00.000Z"),
@@ -106,6 +108,8 @@ describe("Articles endpoints (e2e)", () => {
       "sourceTitle",
       "title",
     ]);
+    expect(list[0]).not.toHaveProperty("contentMarkdown");
+    expect(list[0]).not.toHaveProperty("contentExtractedAt");
   });
 
   it("GET /articles/:id returns detail payload shape", async () => {
@@ -126,6 +130,8 @@ describe("Articles endpoints (e2e)", () => {
       "summary",
       "title",
     ]);
+    expect(detail).not.toHaveProperty("contentMarkdown");
+    expect(detail).not.toHaveProperty("contentExtractedAt");
   });
 
   it("GET /articles/:id returns 404 for unknown article id", async () => {