feat(scan): whiten receipt backgrounds and embed OCR in PDFs

backend/src/routes/instanceAgents.ts

@@ -152,6 +152,7 @@ export default async function instanceAgentRoutes(server: FastifyInstance) {
                 active: instanceAgents.active,
                 preferredScannerName: instanceAgents.preferredScannerName,
                 scanDefaults: instanceAgents.scanDefaults,
+                capabilities: instanceAgents.capabilities,
             })
             .from(instanceAgents)
             .where(eq(instanceAgents.id, body.agentId))
@@ -161,6 +162,14 @@ export default async function instanceAgentRoutes(server: FastifyInstance) {
             return reply.code(404).send({ error: "Active agent not found" })
         }
 
+        const settings = { ...((agent.scanDefaults || {}) as Record<string, any>), ...(body.settings || {}) }
+        const enabled = (value: unknown) => value === true || (typeof value === "string" && ["1", "true", "yes", "ja", "on"].includes(value.toLowerCase().trim()))
+        const capabilities = agent.capabilities as Record<string, any>
+        if (((settings.format || "pdf") === "pdf" && enabled(settings.ocr) && !capabilities?.ocr) ||
+            (enabled(settings.backgroundCleanup) && !capabilities?.backgroundCleanup)) {
+            return reply.code(409).send({ error: "Bitte den Scanner-Agenten mit Tesseract und OpenCV aktualisieren. Die angeforderte Scan-Verarbeitung ist dort noch nicht verfügbar." })
+        }
+
         const [job] = await server.db
             .insert(instanceAgentScanJobs)
             .values({
@@ -169,10 +178,7 @@ export default async function instanceAgentRoutes(server: FastifyInstance) {
                 requestedBy: req.user?.user_id,
                 scannerName: body.scannerName || agent.preferredScannerName,
                 requestedFilename: body.requestedFilename,
-                settings: {
-                    ...((agent.scanDefaults || {}) as Record<string, any>),
-                    ...(body.settings || {}),
-                },
+                settings,
                 target: body.target || {},
             })
             .returning()

backend/tests/instanceAgentSetup.test.ts

@@ -55,3 +55,30 @@ test("unknown agents cannot receive setup credentials", async (t) => {
     assert.equal(response.statusCode, 404)
     assert.equal(f.updates.length, 0)
 })
+
+test("OCR and background cleanup require an agent that supports the requested processing", async t => {
+    const app = Fastify()
+    t.after(() => app.close())
+    const jobs: any[] = []
+    let capabilities: Record<string, boolean> = { scan: true }
+    app.addHook("onRequest", async request => { request.user = { is_admin: true, tenant_id: 1 } as any })
+    app.decorate("db", {
+        select: () => ({ from: () => ({ where: () => ({ limit: async () => [{ id, active: true, scanDefaults: {}, capabilities }] }) }) }),
+        insert: () => ({ values: (data: any) => ({ returning: async () => { jobs.push(data); return [{ id: "job", ...data }] } }) }),
+    })
+    await app.register(routes)
+    for (const settings of [{ ocr: true }, { ocr: "true" }, { backgroundCleanup: true }]) {
+        const response = await app.inject({ method: "POST", url: "/scan-jobs", payload: { agentId: id, settings } })
+        assert.equal(response.statusCode, 409)
+        assert.equal(jobs.length, 0)
+    }
+    capabilities = { scan: true, ocr: true, backgroundCleanup: true }
+    const response = await app.inject({
+        method: "POST", url: "/scan-jobs",
+        payload: { agentId: id, settings: { ocr: true, ocrLanguage: "deu+eng", backgroundCleanup: true }, target: { folder: null, type: null } },
+    })
+    assert.equal(response.statusCode, 200)
+    assert.equal(jobs.length, 1)
+    assert.equal(jobs[0].settings.ocr, true)
+    assert.equal(jobs[0].target.type, null)
+})