feat(ocr): per-script-type confidence thresholds

Kurrent OCR produces much lower confidence than typewriter/Latin.
Separate thresholds allow aggressive filtering for Kurrent (0.5)
while keeping typewriter lenient (0.3).

- OCR_CONFIDENCE_THRESHOLD: default for Surya paths (0.3)
- OCR_CONFIDENCE_THRESHOLD_KURRENT: Kraken Kurrent path (0.5)
- apply_confidence_markers() now accepts threshold parameter
- get_threshold(script_type) selects the right threshold

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

ocr-service/main.py

@@ -9,7 +9,7 @@ import pypdfium2 as pdfium
 from fastapi import FastAPI, HTTPException
 from PIL import Image
 
-from confidence import apply_confidence_markers
+from confidence import apply_confidence_markers, get_threshold
 from engines import kraken as kraken_engine
 from engines import surya as surya_engine
 from models import OcrBlock, OcrRequest
@@ -72,9 +72,10 @@ async def run_ocr(request: OcrRequest):
         # TYPEWRITER, HANDWRITING_LATIN, UNKNOWN — all use Surya
         blocks = surya_engine.extract_blocks(images, request.language)
 
+    threshold = get_threshold(script_type)
     for block in blocks:
         if block.get("words"):
-            block["text"] = apply_confidence_markers(block["words"])
+            block["text"] = apply_confidence_markers(block["words"], threshold)
         block.pop("words", None)
 
     return [OcrBlock(**b) for b in blocks]