Add page-marker grouping and party-aware naming

Consecutive captures whose printed PAGE X OF Y markers advance under the same total are grouped into one multi-page PDF, with duplicate pages keeping the better read. Naming gains doc-title/party components and a scan-date fallback so nothing lands in UNSORTED. Vision LLM default switches to minicpm-v (faster, fewer false blanks on dense mono pages).

config.yaml

@@ -66,9 +66,11 @@ llm:
   # Reads whole documents at once — far more robust than Tesseract for
   # curled receipts and stylized logos — and flags quality issues
   # (fingers_visible, blurry, glare) in export_summary.csv.
-  # Slower: ~20-40s per document. Falls back to Tesseract when Ollama is down.
+  # minicpm-v: ~8-12s/doc; avoids qwen2.5vl's false "blank" on dense
+  # bank statements. OCR still fills date/total when the model hallucinates.
+  # Falls back to Tesseract when Ollama is down.
   enabled: true
-  model: qwen2.5vl
+  model: minicpm-v
   base_url: http://localhost:11434
   timeout_s: 180