From bd4b0ca76640bc629402a941cacff6348d2d2e44 Mon Sep 17 00:00:00 2001
From: Chaim <chaim@marcus-law.co.il>
Date: Tue, 5 May 2026 19:18:57 +0000
Subject: [PATCH] =?UTF-8?q?feat(mcp):=20case=5Fget=5Ffinal=5Ftext=20?=
 =?UTF-8?q?=E2=80=94=20fall=20back=20to=20PDF/DOC/RTF/TXT/MD?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The Hermes Knowledge Curator's hermes-curator.md says it must be able to
read both DOCX and PDF final decisions. The original implementation
hardcoded the .docx extension only. Extend to try .docx → .pdf → .doc →
.rtf → .txt → .md, returning the first match. extractor.extract_text
already supports all six formats, so no extractor changes needed.

If none found, the not_found response now includes the tried_extensions
list so the caller knows what was attempted.

Verified on case 1130-25 (.docx still picked first) and tested via
`curator-cmp mcp test legal-ai`.
---
 mcp-server/src/legal_mcp/tools/cases.py | 17 ++++++++++++++---
 1 file changed, 14 insertions(+), 3 deletions(-)

diff --git a/mcp-server/src/legal_mcp/tools/cases.py b/mcp-server/src/legal_mcp/tools/cases.py
index 0219de5..1ebd8de 100644
--- a/mcp-server/src/legal_mcp/tools/cases.py
+++ b/mcp-server/src/legal_mcp/tools/cases.py
@@ -377,19 +377,30 @@ async def case_get_final_text(case_number: str, max_chars: int = 0) -> str:
 
     בניגוד ל-`document_get_text` שעובד על שורות בטבלת `documents`,
     הקובץ הסופי הוא רק קובץ בתיקייה (נוצר על ידי `api_mark_final`).
+    תומך בכל הפורמטים ש-extractor.extract_text מטפל בהם — מנסה
+    `.docx` תחילה, ואז `.pdf`, `.doc`, `.rtf`, `.txt`, `.md`.
 
     Args:
         case_number: מספר תיק הערר
         max_chars: אם >0, חתוך את הטקסט המוחזר לאורך הזה. 0 = הכל.
     """
     case_dir = config.find_case_dir(case_number)
-    final_path = case_dir / "exports" / f"סופי-{case_number}.docx"
+    exports_dir = case_dir / "exports"
+    final_stem = f"סופי-{case_number}"
 
-    if not final_path.exists():
+    final_path = None
+    for ext in (".docx", ".pdf", ".doc", ".rtf", ".txt", ".md"):
+        candidate = exports_dir / f"{final_stem}{ext}"
+        if candidate.exists():
+            final_path = candidate
+            break
+
+    if final_path is None:
         return json.dumps({
             "status": "not_found",
             "case_number": case_number,
-            "expected_path": str(final_path),
+            "expected_path": str(exports_dir / f"{final_stem}.docx"),
+            "tried_extensions": [".docx", ".pdf", ".doc", ".rtf", ".txt", ".md"],
             "hint": (
                 "ההחלטה הסופית עדיין לא סומנה כ'סופית' ב-UI. "
                 "דפנה צריכה ללחוץ 'סמן כסופי' על קובץ הטיוטה הנכון."