From 24e1e93b5b2f610ce7b76bd62c80d8047ec39602 Mon Sep 17 00:00:00 2001
From: Benjamin Admin <benjaminadmin@MacBookPro.fritz.box>
Date: Fri, 13 Mar 2026 09:03:01 +0100
Subject: [PATCH] fix: save raw paddle/tesseract words in kombi session for
 debugging

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---
 klausur-service/backend/ocr_pipeline_api.py | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/klausur-service/backend/ocr_pipeline_api.py b/klausur-service/backend/ocr_pipeline_api.py
index 8856cc8..ca6384f 100644
--- a/klausur-service/backend/ocr_pipeline_api.py
+++ b/klausur-service/backend/ocr_pipeline_api.py
@@ -2869,6 +2869,8 @@ async def paddle_kombi(session_id: str):
         "duration_seconds": round(duration, 2),
         "ocr_engine": "kombi",
         "grid_method": "kombi",
+        "raw_paddle_words": paddle_words,
+        "raw_tesseract_words": tess_words,
         "summary": {
             "total_cells": len(cells),
             "non_empty_cells": sum(1 for c in cells if c.get("text")),