Add vision OCR via Ollama vision model with Tesseract fallback

Introduces VISION_OCR_MODEL setting. When set (e.g. llama3.2-vision:11b),
receipt images are transcribed by the Ollama vision model before falling
back to Tesseract. Also improves Tesseract preprocessing with adaptive
binarisation (autocontrast + threshold at 140) for better accuracy on
thermal receipts.

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

agent_service/config.py

@@ -16,6 +16,10 @@ class Settings(BaseSettings):
     ollama_model: str = 'activeblue-chat'
     ollama_timeout: int = 120
     ollama_max_concurrent: int = 2
+    # Set to a vision-capable model (e.g. llama3.2-vision:11b) to use
+    # vision OCR for receipt images instead of Tesseract.  Leave empty
+    # to keep the Tesseract pipeline.
+    vision_ocr_model: str = ''
 
     # Anthropic / Claude
     anthropic_api_key: str = ''