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>

docker-compose.yml

@@ -85,6 +85,7 @@ services:
     environment:
       KRAKEN_MODEL_PATH: /app/models/german_kurrent.mlmodel
       OCR_CONFIDENCE_THRESHOLD: "0.3"
+      OCR_CONFIDENCE_THRESHOLD_KURRENT: "0.5"
     networks:
       - archive-net
     healthcheck: