feat(invoices): add hybrid OCR + vision invoice/document parsing with PaddleOCR, consensus voting, and prompt/test refactors

test/test.invoices.ts

@@ -45,7 +45,8 @@ async function extractOcrText(imageBase64: string): Promise<string> {
  * Build prompt with optional OCR text
  */
 function buildPrompt(ocrText: string): string {
-  const base = `You are an invoice parser. Extract the following fields from this invoice:
+  const base = `/nothink
+You are an invoice parser. Extract the following fields from this invoice:
 
 1. invoice_number: The invoice/receipt number
 2. invoice_date: Date in YYYY-MM-DD format
@@ -62,11 +63,17 @@ If a field is not visible, use null for strings or 0 for numbers.
 No explanation, just the JSON object.`;
 
   if (ocrText) {
+    // Limit OCR text to prevent context overflow
+    const maxOcrLength = 4000;
+    const truncatedOcr = ocrText.length > maxOcrLength
+      ? ocrText.substring(0, maxOcrLength) + '\n... (truncated)'
+      : ocrText;
+
     return `${base}
 
-OCR text extracted from the invoice:
+OCR text extracted from the invoice (use for reference):
 ---
-${ocrText}
+${truncatedOcr}
 ---
 
 Cross-reference the image with the OCR text above for accuracy.`;