feat: OCR via tesseract, dedup, category selection for expense receipts

- Dockerfile: install tesseract-ocr so Pillow+pytesseract can OCR receipt images
- operational_store: JSON-serialize raw_data before passing to asyncpg JSONB
- receipt_parser: add SHA256 hash + date extracted from filename timestamps
- expenses_agent: deduplicate receipts by hash before creating expense records
- expenses_agent: fetch all expensable Odoo products, pass list to LLM for
  category selection (Meals, Flights, etc.) per receipt
- expenses_agent: pass date_hint from filename (e.g. 20260509_180857.jpg -> 2026-05-09)
  as fallback when OCR text is unavailable
- expenses_tools: add get_expense_products() to fetch all expensable products

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

agent_service/tools/receipt_parser.py

@@ -1,12 +1,17 @@
 from __future__ import annotations
 import base64
+import hashlib
 import io
 import logging
+import re
 import zipfile
 from pathlib import Path
 
 logger = logging.getLogger(__name__)
 
+# Extract YYYYMMDD from filenames like 20260509_180857.jpg
+_DATE_PATTERN = re.compile(r'(\d{4})(\d{2})(\d{2})_\d{6}')
+
 _MIME = {
     '.jpg': 'image/jpeg', '.jpeg': 'image/jpeg',
     '.png': 'image/png', '.gif': 'image/gif',
@@ -31,6 +36,13 @@ def parse_upload(filename: str, data: bytes) -> list[dict]:
 
     b64 = base64.b64encode(data).decode()
     mimetype = _MIME.get(ext, 'application/octet-stream')
+    sha256 = hashlib.sha256(data).hexdigest()
+
+    # Extract date from timestamp-style filenames (e.g. 20260509_180857.jpg)
+    date_from_name = None
+    m = _DATE_PATTERN.search(filename)
+    if m:
+        date_from_name = f'{m.group(1)}-{m.group(2)}-{m.group(3)}'
 
     if ext in _IMAGE_EXTS:
         text = _ocr_image(data, filename)
@@ -46,7 +58,8 @@ def parse_upload(filename: str, data: bytes) -> list[dict]:
         except Exception:
             text = f'[Binary file: {filename}]'
 
-    return [{'filename': filename, 'text': text, 'b64': b64, 'mimetype': mimetype}]
+    return [{'filename': filename, 'text': text, 'b64': b64, 'mimetype': mimetype,
+             'sha256': sha256, 'date_from_name': date_from_name}]
 
 
 def _extract_zip(zip_filename: str, data: bytes) -> list[dict]: