Add media storage limits, retention, and the near-limit flow

media-scrape/test/run.ts

@@ -10,6 +10,7 @@ import { join } from "node:path";
 import { ScrapeEngine, type FetchPage, type ScrapeBackend } from "../src/engine.js";
 import { extractMedia } from "../src/extract.js";
 import { PuppetBackend } from "../src/puppet-backend.js";
+import { isNearLimit, planRetention } from "../src/retention.js";
 import { dirSizeBytes, listScrapes, ScrapeStore } from "../src/store.js";
 import type { CoreAttachment, CoreMessage } from "../src/types.js";
 
@@ -173,7 +174,9 @@ void (async () => {
         const backend = new FakeBackend([
             {
                 messages: [
-                    message("100", { attachments: [attachment({ filename: "one.png", contentType: "image/png" })] }),
+                    message("100", {
+                        attachments: [attachment({ filename: "one.png", contentType: "image/png", size: 10 })]
+                    }),
                     message("101")
                 ]
             },
@@ -202,6 +205,7 @@ void (async () => {
         assert.equal(stored.counts().image, 1);
         assert.equal(stored.queryMedia({ kind: "image" }).length, 1);
         assert.equal(stored.queryMedia({ kind: "video" }).length, 0);
+        assert.equal(stored.sumBytesByKind().image, 10);
         stored.close();
 
         assert.equal(listScrapes(root).length, 1);
@@ -272,6 +276,42 @@ void (async () => {
         assert.deepEqual(calls[0], { channelId: "123", limit: 5, before: "60" });
     });
 
+    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 },
+            { id: "new", state: "done", createdAt: "2026-09-02T00:00:00.000Z", bytes: 600 },
+            { id: "run", state: "running", createdAt: "2026-09-03T00:00:00.000Z", bytes: 600 }
+        ];
+
+        const plan = planRetention(scrapes, 1000, 100);
+        assert.deepEqual(plan.mark, ["old", "new"]);
+        assert.deepEqual(plan.delete, []);
+    });
+
+    await test("retention deletes marked scrapes past the overrun allowance", () => {
+        const scrapes = [
+            { id: "old", state: "pending-delete", createdAt: "2026-09-01T00:00:00.000Z", bytes: 600 },
+            { id: "new", state: "pending-delete", createdAt: "2026-09-02T00:00:00.000Z", bytes: 600 },
+            { id: "run", state: "running", createdAt: "2026-09-03T00:00:00.000Z", bytes: 600 }
+        ];
+
+        const plan = planRetention(scrapes, 1000, 5);
+        assert.deepEqual(plan.delete, ["old", "new"]);
+        assert.deepEqual(plan.mark, []);
+    });
+
+    await test("retention leaves usage under the limit alone", () => {
+        const plan = planRetention(
+            [{ id: "one", state: "done", createdAt: "2026-09-01T00:00:00.000Z", bytes: 500 }],
+            1000,
+            5
+        );
+
+        assert.deepEqual(plan, { mark: [], delete: [], totalBytes: 500 });
+        assert.equal(isNearLimit(900, 1000, 90), true);
+        assert.equal(isNearLimit(899, 1000, 90), false);
+    });
+
     rmSync(root, { recursive: true, force: true });
 
     if (failures > 0) {