Teach local AI from user category corrections

- Add MerchantCorrection model: upsert by merchantName, Category enum
- Check corrections DB first in suggestCategoryForMerchant (source: "learned",
  no confirmation required); falls through to rules then Ollama if no match
- Inject recent corrections as few-shot examples in the Ollama prompt so the
  model improves even for merchants not yet explicitly corrected
- Add POST /categories/correct route to persist corrections
- Detect category override on form save (suggestedCategory !== chosen category)
  and silently fire a correction — no extra UX required
- Fix test isolation: beforeEach re-applies vi.fn() defaults after restoreAllMocks

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

prisma/migrations/20260323212510_add_merchant_corrections/migration.sql

@@ -0,0 +1,11 @@
+-- CreateTable
+CREATE TABLE "MerchantCorrection" (
+    "id" TEXT NOT NULL PRIMARY KEY,
+    "merchantName" TEXT NOT NULL,
+    "category" TEXT NOT NULL,
+    "createdAt" DATETIME NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    "updatedAt" DATETIME NOT NULL
+);
+
+-- CreateIndex
+CREATE UNIQUE INDEX "MerchantCorrection_merchantName_key" ON "MerchantCorrection"("merchantName");