feat(ocr): replace Google Vision with Mistral OCR as PDF fallback

Switches the scanned-PDF fallback from Google Cloud Vision to
Mistral OCR (mistral-ocr-latest) for better Hebrew accuracy and
robustness against broken embedded OCR layers (e.g. case 1044-03-26
which returned English garbage through Vision).

Routing strategy (document-level, not per-page):
- PyMuPDF extracts all pages; pages that pass _text_quality_ok()
  use PyMuPDF output directly (free, ~50ms).
- If ANY page fails quality → Mistral OCR called once for the whole
  PDF, returning per-page Markdown for all pages (consistent format,
  no plain-text/Markdown mix within a document).

Markdown output preserved: Mistral returns ## headers and |tables|;
chunker updated to recognise ATX Markdown headers (##/###) as section
boundaries in _split_into_sections().

Config: GOOGLE_CLOUD_VISION_API_KEY → MISTRAL_API_KEY; allowlist
updated vision.googleapis.com → api.mistral.ai.
MISTRAL_API_KEY added to Coolify container env.

Invariants: G1 (single OCR fallback path, not parallel), G2 (no
duplicate extractor route), INV-AH (Mistral handles gershayim
natively; quote-fix only on PyMuPDF path).

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

mcp-server/src/legal_mcp/services/chunker.py

@@ -144,9 +144,12 @@ def _split_into_sections(text: str) -> list[tuple[str, str]]:
     markers: list[tuple[int, str]] = []
 
     for pattern, section_type in SECTION_PATTERNS:
-        # ^ + MULTILINE: line start only. Optional leading spaces/tabs and an
+        # ^ + MULTILINE: line start only. Optional leading spaces/tabs, an
+        # optional Markdown ATX header prefix (``## ``/``### ``), and an
         # optional ordinal prefix ("5.", "5)", "ג.") before the keyword.
-        anchored = rf"^[ \t]*(?:\d+[.)]\s*|[א-ת][.)]\s*)?(?:{pattern})"
+        # The Markdown prefix handles Mistral OCR output where section
+        # titles are rendered as ``## נימוקי הערר`` etc.
+        anchored = rf"^[ \t]*(?:#{1,3}\s+)?(?:\d+[.)]\s*|[א-ת][.)]\s*)?(?:{pattern})"
         for match in re.finditer(anchored, text, re.MULTILINE):
             markers.append((match.start(), section_type))