Add Discord-hosted preview caching (C11)

media-scrape/test/run.ts

@@ -8,7 +8,7 @@ import { createHash } from "node:crypto";
 import { existsSync, mkdirSync, mkdtempSync, rmSync } from "node:fs";
 import { tmpdir } from "node:os";
 import { join } from "node:path";
-import { downloadOne } from "../src/download.js";
+import { downloadOne, downloadPreview, previewUrlFor } from "../src/download.js";
 import { ScrapeEngine, type FetchPage, type ScrapeBackend } from "../src/engine.js";
 import { extractMedia } from "../src/extract.js";
 import { PuppetBackend } from "../src/puppet-backend.js";
@@ -85,6 +85,7 @@ function engineFor(root: string, backend: ScrapeBackend, extra: Record<string, u
         sleep: async () => {},
         random: () => 0,
         log: () => {},
+        previews: false,
         ...extra
     });
 }
@@ -366,6 +367,7 @@ void (async () => {
             sleep: async () => {},
             random: () => 0,
             log: () => {},
+            previews: false,
             download: {
                 fetchImpl: async () =>
                     new Response("png-bytes", { status: 200, headers: { "content-type": "image/png" } }),
@@ -394,6 +396,77 @@ void (async () => {
         assert.equal(existsSync(join(root, started.id, row.file_path)), true);
     });
 
+    await test("preview urls are Discord-only resizes", () => {
+        assert.equal(
+            previewUrlFor({ url: "https://cdn.discordapp.com/attachments/1/2/pic.png", kind: "image" }),
+            "https://media.discordapp.net/attachments/1/2/pic.png?width=320&height=320&format=webp"
+        );
+        assert.equal(previewUrlFor({ url: "https://www.youtube.com/watch?v=x", kind: "video" }), null);
+        assert.equal(previewUrlFor({ url: "https://i.ytimg.com/vi/x/hq.jpg", kind: "image" }), null);
+    });
+
+    await test("preview downloads are written by hash", async () => {
+        const dir = join(root, "preview-test");
+        mkdirSync(dir, { recursive: true });
+
+        const outcome = await downloadPreview(
+            { id: 9, url: "https://cdn.discordapp.com/attachments/1/2/pic.png", kind: "image" },
+            dir,
+            {
+                fetchImpl: async () =>
+                    new Response("webp-bytes", { status: 200, headers: { "content-type": "image/webp" } })
+            }
+        );
+
+        assert.equal(outcome.state, "downloaded");
+        assert.equal(outcome.path, `${outcome.hash}.webp`);
+        assert.equal(existsSync(join(dir, `${outcome.hash}.webp`)), true);
+    });
+
+    await test("engine caches previews in links mode", async () => {
+        const backend = new FakeBackend([
+            {
+                messages: [
+                    message("600", {
+                        attachments: [attachment({ filename: "prev.png", contentType: "image/png" })]
+                    })
+                ]
+            }
+        ]);
+
+        const engine = new ScrapeEngine({
+            rootDir: root,
+            pageSize: 2,
+            pageMinMs: 0,
+            pageMaxMs: 0,
+            sleep: async () => {},
+            random: () => 0,
+            log: () => {},
+            previews: true,
+            download: {
+                fetchImpl: async () =>
+                    new Response("webp-bytes", { status: 200, headers: { "content-type": "image/webp" } }),
+                minGapMs: 0,
+                maxGapMs: 0,
+                sleep: async () => {}
+            }
+        });
+
+        const started = await engine.start({ channelId: "128", guildId: null, mode: "links", backend });
+        await engine.processQueue();
+
+        const meta = engine.get(started.id);
+        assert.equal(meta?.state, "done");
+        assert.equal(meta?.previewed, 1);
+
+        const store = new ScrapeStore(join(root, started.id));
+        const row = store.queryMedia({ kind: "image" })[0];
+        assert.ok(row.preview_hash);
+        assert.ok((row.preview_bytes ?? 0) > 0);
+        store.close();
+        assert.equal(existsSync(join(root, started.id, "thumbs", `${row.preview_hash}.webp`)), true);
+    });
+
     await test("retention marks the oldest completed scrapes up to the limit", () => {
         const scrapes = [
             { id: "old", state: "done", createdAt: "2026-09-01T00:00:00.000Z", bytes: 600 },