Replace Claude Vision OCR with Google Cloud Vision

Benchmark results on Hebrew legal docs (case 1130-25):
- Google Vision: 1s/page, $0.001/page, high accuracy
- Claude Opus Vision: 90s/page, $0.05/page, poor accuracy
- PyMuPDF broken OCR layers now detected via quality check

Changes:
- extractor.py: Google Vision OCR with Hebrew language hint (300 DPI)
- extractor.py: text quality detection (word length, words-per-line, Hebrew ratio)
- extractor.py: Hebrew abbreviation quote fixer (15 known patterns)
- config.py: add GOOGLE_CLOUD_VISION_API_KEY, remove ANTHROPIC_API_KEY
- pyproject.toml: add google-cloud-vision, remove anthropic

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

mcp-server/src/legal_mcp/config.py

@@ -47,8 +47,8 @@ VOYAGE_API_KEY = os.environ.get("VOYAGE_API_KEY", "")
 VOYAGE_MODEL = os.environ.get("VOYAGE_MODEL", "voyage-law-2")
 VOYAGE_DIMENSIONS = 1024
 
-# Anthropic (for Claude Vision OCR)
-ANTHROPIC_API_KEY = os.environ.get("ANTHROPIC_API_KEY", "")
+# Google Cloud Vision (OCR for scanned PDFs)
+GOOGLE_CLOUD_VISION_API_KEY = os.environ.get("GOOGLE_CLOUD_VISION_API_KEY", "")
 
 # Data directory
 DATA_DIR = Path(os.environ.get("DATA_DIR", str(Path.home() / "legal-ai" / "data")))
@@ -82,8 +82,8 @@ CHUNK_OVERLAP_TOKENS = 100
 
 # External service allowlist — case materials may ONLY be sent to these domains
 ALLOWED_EXTERNAL_SERVICES = {
-    "api.anthropic.com",        # Claude API (text generation, OCR)
     "api.voyageai.com",         # Voyage AI (embeddings)
+    "vision.googleapis.com",    # Google Cloud Vision (OCR)
 }
 
 # Audit