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/confidence.py

@@ -2,16 +2,24 @@
 
 import os
 
-CONFIDENCE_THRESHOLD = float(os.environ.get("OCR_CONFIDENCE_THRESHOLD", "0.3"))
+THRESHOLD_DEFAULT = float(os.environ.get("OCR_CONFIDENCE_THRESHOLD", "0.3"))
+THRESHOLD_KURRENT = float(os.environ.get("OCR_CONFIDENCE_THRESHOLD_KURRENT", "0.5"))
 
 ILLEGIBLE_MARKER = "[unleserlich]"
 
 
-def apply_confidence_markers(words: list[dict]) -> str:
+def get_threshold(script_type: str) -> float:
+    if script_type and script_type.upper() == "HANDWRITING_KURRENT":
+        return THRESHOLD_KURRENT
+    return THRESHOLD_DEFAULT
+
+
+def apply_confidence_markers(words: list[dict], threshold: float | None = None) -> str:
     """Replace low-confidence words with [unleserlich], collapsing adjacent markers.
 
     Args:
         words: list of {"text": str, "confidence": float} dicts
+        threshold: confidence threshold (uses THRESHOLD_DEFAULT if None)
 
     Returns:
         Reconstructed text string with [unleserlich] substitutions.
@@ -19,11 +27,14 @@ def apply_confidence_markers(words: list[dict]) -> str:
     if not words:
         return ""
 
+    if threshold is None:
+        threshold = THRESHOLD_DEFAULT
+
     result: list[str] = []
     prev_was_marker = False
 
     for word in words:
-        if word["confidence"] < CONFIDENCE_THRESHOLD:
+        if word["confidence"] < threshold:
             if not prev_was_marker:
                 result.append(ILLEGIBLE_MARKER)
             prev_was_marker = True