Add database auto-migration, storage cleanup, and startup fixes

- Add start.sh that runs prisma db push before starting the server,
  creating tables automatically on first deploy
- Copy prisma CLI + engines into production image for runtime migrations
- Add configurable storage cleanup: source PDF retention (default 30d)
  and image retention (default 180d) with manual trigger in Settings
- Add /api/cleanup endpoint (GET for status, POST to run)
- Add retention settings to AppSettings schema
- Add ListObjectsV2 helper to minio.ts for bulk cleanup

Tested: local Docker build passes
Made-with: Cursor

Dockerfile

@@ -32,6 +32,10 @@ COPY --from=builder --chown=nextjs:nodejs /app/.next/standalone ./
 COPY --from=builder --chown=nextjs:nodejs /app/.next/static ./.next/static
 COPY --from=builder /app/prisma ./prisma
 COPY --from=builder /app/prisma.config.ts ./prisma.config.ts
+COPY --from=builder /app/node_modules/prisma ./node_modules/prisma
+COPY --from=builder /app/node_modules/@prisma ./node_modules/@prisma
+COPY --from=builder /app/node_modules/dotenv ./node_modules/dotenv
+COPY --from=builder /app/start.sh ./start.sh
 
 RUN mkdir -p /data/watch && chown -R nextjs:nodejs /data
 
@@ -41,4 +45,4 @@ EXPOSE 3000
 ENV PORT=3000
 ENV HOSTNAME="0.0.0.0"
 
-CMD ["node", "server.js"]
+CMD ["sh", "start.sh"]

package-lock.json

@@ -7,6 +7,7 @@
     "": {
       "name": "echos-ocr",
       "version": "0.1.0",
+      "hasInstallScript": true,
       "dependencies": {
         "@aws-sdk/client-s3": "^3.1005.0",
         "@aws-sdk/s3-request-presigner": "^3.1005.0",
@@ -19,6 +20,7 @@
         "clsx": "^2.1.1",
         "cmdk": "^1.1.1",
         "date-fns": "^4.1.0",
+        "dotenv": "^17.3.1",
         "lucide-react": "^0.577.0",
         "minio": "^8.0.7",
         "next": "16.1.6",

package.json

@@ -24,6 +24,7 @@
     "clsx": "^2.1.1",
     "cmdk": "^1.1.1",
     "date-fns": "^4.1.0",
+    "dotenv": "^17.3.1",
     "lucide-react": "^0.577.0",
     "minio": "^8.0.7",
     "next": "16.1.6",

prisma/schema.prisma

@@ -79,4 +79,7 @@ model AppSettings {
   model     String @default("llava:7b")
   watchDir  String @default("")
   watching  Boolean @default(false)
+
+  sourceRetentionDays Int @default(30)
+  imageRetentionDays  Int @default(180)
 }

src/app/api/cleanup/route.ts

@@ -0,0 +1,134 @@
+import { NextRequest, NextResponse } from "next/server";
+import { prisma } from "@/lib/db";
+import { deleteObject, listObjects } from "@/lib/minio";
+
+export async function POST(request: NextRequest) {
+  try {
+    const body = await request.json().catch(() => ({}));
+    const dryRun = body.dryRun === true;
+
+    let settings = await prisma.appSettings.findUnique({
+      where: { id: "singleton" },
+    });
+    if (!settings) {
+      settings = await prisma.appSettings.create({
+        data: { id: "singleton" },
+      });
+    }
+
+    const now = new Date();
+    const sourcesCutoff = new Date(now.getTime() - settings.sourceRetentionDays * 86400000);
+    const imagesCutoff = new Date(now.getTime() - settings.imageRetentionDays * 86400000);
+
+    const results = {
+      sourcesDeleted: 0,
+      imagesDeleted: 0,
+      cardsUpdated: 0,
+      jobsPurged: 0,
+      dryRun,
+    };
+
+    // 1. Purge source PDFs older than sourceRetentionDays
+    const sourceKeys = await listObjects("sources/");
+    const jobsWithSources = await prisma.processingJob.findMany({
+      where: { createdAt: { lt: sourcesCutoff }, status: "complete" },
+      select: { id: true },
+    });
+    const oldJobIds = new Set(jobsWithSources.map((j) => j.id));
+
+    for (const key of sourceKeys) {
+      const jobId = key.split("/")[1];
+      if (jobId && oldJobIds.has(jobId)) {
+        if (!dryRun) await deleteObject(key);
+        results.sourcesDeleted++;
+      }
+    }
+
+    // 2. Purge card images older than imageRetentionDays
+    const oldCards = await prisma.responseCard.findMany({
+      where: { createdAt: { lt: imagesCutoff } },
+      select: { id: true, frontImagePath: true, backImagePath: true },
+    });
+
+    for (const card of oldCards) {
+      if (card.frontImagePath) {
+        if (!dryRun) await deleteObject(card.frontImagePath);
+        results.imagesDeleted++;
+      }
+      if (card.backImagePath) {
+        if (!dryRun) await deleteObject(card.backImagePath);
+        results.imagesDeleted++;
+      }
+      if (!dryRun) {
+        await prisma.responseCard.update({
+          where: { id: card.id },
+          data: { frontImagePath: null, backImagePath: null },
+        });
+      }
+      results.cardsUpdated++;
+    }
+
+    // 3. Purge completed processing jobs older than sourceRetentionDays
+    if (!dryRun) {
+      const deleted = await prisma.processingJob.deleteMany({
+        where: { createdAt: { lt: sourcesCutoff }, status: { in: ["complete", "error"] } },
+      });
+      results.jobsPurged = deleted.count;
+    } else {
+      results.jobsPurged = await prisma.processingJob.count({
+        where: { createdAt: { lt: sourcesCutoff }, status: { in: ["complete", "error"] } },
+      });
+    }
+
+    return NextResponse.json(results);
+  } catch (error) {
+    console.error("[cleanup POST]", error);
+    return NextResponse.json(
+      { error: "Cleanup failed" },
+      { status: 500 }
+    );
+  }
+}
+
+export async function GET() {
+  try {
+    let settings = await prisma.appSettings.findUnique({
+      where: { id: "singleton" },
+    });
+    if (!settings) {
+      settings = await prisma.appSettings.create({
+        data: { id: "singleton" },
+      });
+    }
+
+    const now = new Date();
+    const sourcesCutoff = new Date(now.getTime() - settings.sourceRetentionDays * 86400000);
+    const imagesCutoff = new Date(now.getTime() - settings.imageRetentionDays * 86400000);
+
+    const sourcesEligible = await prisma.processingJob.count({
+      where: { createdAt: { lt: sourcesCutoff }, status: "complete" },
+    });
+    const imagesEligible = await prisma.responseCard.count({
+      where: {
+        createdAt: { lt: imagesCutoff },
+        OR: [
+          { frontImagePath: { not: null } },
+          { backImagePath: { not: null } },
+        ],
+      },
+    });
+
+    return NextResponse.json({
+      sourceRetentionDays: settings.sourceRetentionDays,
+      imageRetentionDays: settings.imageRetentionDays,
+      sourcesEligible,
+      imagesEligible,
+    });
+  } catch (error) {
+    console.error("[cleanup GET]", error);
+    return NextResponse.json(
+      { error: "Failed to check cleanup status" },
+      { status: 500 }
+    );
+  }
+}

src/app/api/settings/route.ts

@@ -33,6 +33,8 @@ export async function PUT(request: NextRequest) {
     if (body.model != null) data.model = String(body.model);
     if (body.watchDir != null) data.watchDir = String(body.watchDir);
     if (body.watching != null) data.watching = Boolean(body.watching);
+    if (body.sourceRetentionDays != null) data.sourceRetentionDays = Math.max(1, parseInt(String(body.sourceRetentionDays)) || 30);
+    if (body.imageRetentionDays != null) data.imageRetentionDays = Math.max(1, parseInt(String(body.imageRetentionDays)) || 180);
 
     const settings = await prisma.appSettings.upsert({
       where: { id: "singleton" },

src/app/settings/page.tsx

@@ -2,7 +2,7 @@
 
 import * as React from "react";
 import { toast } from "sonner";
-import { Loader2, Save, Wifi, WifiOff } from "lucide-react";
+import { Loader2, Save, Wifi, WifiOff, Trash2 } from "lucide-react";
 
 import { Header } from "@/components/layout/header";
 import { Button } from "@/components/ui/button";
@@ -16,6 +16,8 @@ type Settings = {
   model: string;
   watchDir: string;
   watching: boolean;
+  sourceRetentionDays: number;
+  imageRetentionDays: number;
 };
 
 export default function SettingsPage() {
@@ -24,10 +26,23 @@ export default function SettingsPage() {
     model: "",
     watchDir: "",
     watching: false,
+    sourceRetentionDays: 30,
+    imageRetentionDays: 180,
   });
   const [loading, setLoading] = React.useState(true);
   const [saving, setSaving] = React.useState(false);
   const [ollamaStatus, setOllamaStatus] = React.useState<"unknown" | "connected" | "error">("unknown");
+  const [cleanupStatus, setCleanupStatus] = React.useState<{ sourcesEligible: number; imagesEligible: number } | null>(null);
+  const [cleaning, setCleaning] = React.useState(false);
+
+  const fetchCleanupStatus = React.useCallback(() => {
+    fetch("/api/cleanup")
+      .then((r) => r.json())
+      .then((data) => {
+        if (data.sourcesEligible !== undefined) setCleanupStatus(data);
+      })
+      .catch(() => {});
+  }, []);
 
   React.useEffect(() => {
     fetch("/api/settings")
@@ -39,7 +54,8 @@ export default function SettingsPage() {
       .catch(() => {
         setLoading(false);
       });
-  }, []);
+    fetchCleanupStatus();
+  }, [fetchCleanupStatus]);
 
   const handleSave = async () => {
     setSaving(true);
@@ -94,6 +110,27 @@ export default function SettingsPage() {
     }
   };
 
+  const runCleanup = async () => {
+    setCleaning(true);
+    try {
+      const res = await fetch("/api/cleanup", {
+        method: "POST",
+        headers: { "Content-Type": "application/json" },
+        body: JSON.stringify({ dryRun: false }),
+      });
+      if (!res.ok) throw new Error();
+      const data = await res.json();
+      toast.success(
+        `Cleanup complete: ${data.sourcesDeleted} source files, ${data.imagesDeleted} images, ${data.jobsPurged} jobs removed`
+      );
+      fetchCleanupStatus();
+    } catch {
+      toast.error("Cleanup failed");
+    } finally {
+      setCleaning(false);
+    }
+  };
+
   if (loading) {
     return (
       <div className="flex items-center justify-center py-20">
@@ -198,8 +235,80 @@ export default function SettingsPage() {
           </CardContent>
         </Card>
 
+        {/* Storage & Cleanup */}
+        <Card>
+          <CardHeader>
+            <CardTitle className="text-base">Storage & Cleanup</CardTitle>
+            <CardDescription>Auto-purge uploaded files and images to save storage</CardDescription>
+          </CardHeader>
+          <CardContent className="space-y-4">
+            <div>
+              <Label className="mb-1.5 block text-xs font-medium text-muted-foreground">
+                Source PDF Retention (days)
+              </Label>
+              <Input
+                type="number"
+                min={1}
+                value={settings.sourceRetentionDays}
+                onChange={(e) =>
+                  setSettings((s) => ({
+                    ...s,
+                    sourceRetentionDays: parseInt(e.target.value) || 30,
+                  }))
+                }
+              />
+              <p className="mt-1 text-xs text-muted-foreground">
+                Original uploaded PDFs are deleted after this many days. Card data is kept.
+              </p>
+            </div>
+            <div>
+              <Label className="mb-1.5 block text-xs font-medium text-muted-foreground">
+                Image Retention (days)
+              </Label>
+              <Input
+                type="number"
+                min={1}
+                value={settings.imageRetentionDays}
+                onChange={(e) =>
+                  setSettings((s) => ({
+                    ...s,
+                    imageRetentionDays: parseInt(e.target.value) || 180,
+                  }))
+                }
+              />
+              <p className="mt-1 text-xs text-muted-foreground">
+                Scanned card images are removed after this many days. Card data is kept.
+              </p>
+            </div>
+            <div className="rounded-lg border bg-muted/50 p-3">
+              <div className="flex items-center justify-between">
+                <div className="text-sm">
+                  {cleanupStatus ? (
+                    <>
+                      <span className="font-medium">{cleanupStatus.sourcesEligible}</span> source files
+                      {" and "}
+                      <span className="font-medium">{cleanupStatus.imagesEligible}</span> card images eligible
+                    </>
+                  ) : (
+                    "Checking..."
+                  )}
+                </div>
+                <Button
+                  variant="destructive"
+                  size="sm"
+                  onClick={runCleanup}
+                  disabled={cleaning || !cleanupStatus || (cleanupStatus.sourcesEligible === 0 && cleanupStatus.imagesEligible === 0)}
+                >
+                  {cleaning ? <Loader2 className="mr-2 size-3 animate-spin" /> : <Trash2 className="mr-2 size-3" />}
+                  Run Cleanup Now
+                </Button>
+              </div>
+            </div>
+          </CardContent>
+        </Card>
+
         {/* Monday.com Integration (placeholder) */}
-        <Card className="lg:col-span-2">
+        <Card>
           <CardHeader>
             <CardTitle className="text-base">Monday.com Integration</CardTitle>
             <CardDescription>Push scanned card data to Monday.com boards (coming soon)</CardDescription>

src/lib/minio.ts

@@ -1,4 +1,4 @@
-import { S3Client, PutObjectCommand, GetObjectCommand, DeleteObjectCommand } from "@aws-sdk/client-s3";
+import { S3Client, PutObjectCommand, GetObjectCommand, DeleteObjectCommand, ListObjectsV2Command } from "@aws-sdk/client-s3";
 import { getSignedUrl } from "@aws-sdk/s3-request-presigner";
 
 const MINIO_ENDPOINT = process.env.MINIO_ENDPOINT || "192.168.68.105";
@@ -44,3 +44,24 @@ export async function deleteObject(key: string): Promise<void> {
     new DeleteObjectCommand({ Bucket: BUCKET, Key: key })
   );
 }
+
+export async function listObjects(prefix: string): Promise<string[]> {
+  const keys: string[] = [];
+  let continuationToken: string | undefined;
+
+  do {
+    const res = await s3.send(
+      new ListObjectsV2Command({
+        Bucket: BUCKET,
+        Prefix: prefix,
+        ContinuationToken: continuationToken,
+      })
+    );
+    for (const obj of res.Contents ?? []) {
+      if (obj.Key) keys.push(obj.Key);
+    }
+    continuationToken = res.NextContinuationToken;
+  } while (continuationToken);
+
+  return keys;
+}

start.sh

@@ -0,0 +1,8 @@
+#!/bin/sh
+set -e
+
+echo "Running database migrations..."
+npx prisma db push --skip-generate 2>&1 || echo "Warning: prisma db push failed, tables may already exist"
+
+echo "Starting server..."
+exec node server.js