feat: Box-Zonen durch gesamte Pipeline + Sub-Sessions fuer Box-Inhalt

- Rote semi-transparente Box-Markierung in allen Overlays (Spalten, Zeilen, Woerter)
- Zeilenerkennung: Combined-Image-Ansatz schliesst Box-Bereiche aus
- Woerter-Erkennung: Zeilen innerhalb von Box-Zonen werden gefiltert
- Sub-Sessions: parent_session_id/box_index in DB-Schema
- POST /sessions/{id}/create-box-sessions erstellt Sub-Sessions aus Box-Regionen
- Session-Info zeigt Sub-Sessions bzw. Parent-Verknuepfung
- Sessions-Liste blendet Sub-Sessions per Default aus
- Rekonstruktion: Fabric-JSON merged Sub-Session-Zellen an Box-Positionen
- Save-Reconstruction routet box{N}_* Updates an Sub-Sessions
- GET /sessions/{id}/vocab-entries/merged fuer zusammengefuehrte Eintraege

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

klausur-service/backend/ocr_pipeline_session_store.py

@@ -72,7 +72,9 @@ async def init_ocr_pipeline_tables():
             ADD COLUMN IF NOT EXISTS oriented_png BYTEA,
             ADD COLUMN IF NOT EXISTS cropped_png BYTEA,
             ADD COLUMN IF NOT EXISTS orientation_result JSONB,
-            ADD COLUMN IF NOT EXISTS crop_result JSONB
+            ADD COLUMN IF NOT EXISTS crop_result JSONB,
+            ADD COLUMN IF NOT EXISTS parent_session_id UUID REFERENCES ocr_pipeline_sessions(id) ON DELETE CASCADE,
+            ADD COLUMN IF NOT EXISTS box_index INT
         """)
 
 
@@ -85,22 +87,33 @@ async def create_session_db(
     name: str,
     filename: str,
     original_png: bytes,
+    parent_session_id: Optional[str] = None,
+    box_index: Optional[int] = None,
 ) -> Dict[str, Any]:
-    """Create a new OCR pipeline session."""
+    """Create a new OCR pipeline session.
+
+    Args:
+        parent_session_id: If set, this is a sub-session for a box region.
+        box_index: 0-based index of the box this sub-session represents.
+    """
     pool = await get_pool()
+    parent_uuid = uuid.UUID(parent_session_id) if parent_session_id else None
     async with pool.acquire() as conn:
         row = await conn.fetchrow("""
             INSERT INTO ocr_pipeline_sessions (
-                id, name, filename, original_png, status, current_step
-            ) VALUES ($1, $2, $3, $4, 'active', 1)
+                id, name, filename, original_png, status, current_step,
+                parent_session_id, box_index
+            ) VALUES ($1, $2, $3, $4, 'active', 1, $5, $6)
             RETURNING id, name, filename, status, current_step,
                       orientation_result, crop_result,
                       deskew_result, dewarp_result, column_result, row_result,
                       word_result, ground_truth, auto_shear_degrees,
                       doc_type, doc_type_result,
                       document_category, pipeline_log,
+                      parent_session_id, box_index,
                       created_at, updated_at
-        """, uuid.UUID(session_id), name, filename, original_png)
+        """, uuid.UUID(session_id), name, filename, original_png,
+            parent_uuid, box_index)
 
         return _row_to_dict(row)
 
@@ -116,6 +129,7 @@ async def get_session_db(session_id: str) -> Optional[Dict[str, Any]]:
                    word_result, ground_truth, auto_shear_degrees,
                    doc_type, doc_type_result,
                    document_category, pipeline_log,
+                   parent_session_id, box_index,
                    created_at, updated_at
             FROM ocr_pipeline_sessions WHERE id = $1
         """, uuid.UUID(session_id))
@@ -166,6 +180,7 @@ async def update_session_db(session_id: str, **kwargs) -> Optional[Dict[str, Any
         'word_result', 'ground_truth', 'auto_shear_degrees',
         'doc_type', 'doc_type_result',
         'document_category', 'pipeline_log',
+        'parent_session_id', 'box_index',
     }
 
     jsonb_fields = {'orientation_result', 'crop_result', 'deskew_result', 'dewarp_result', 'column_result', 'row_result', 'word_result', 'ground_truth', 'handwriting_removal_meta', 'doc_type_result', 'pipeline_log'}
@@ -197,6 +212,7 @@ async def update_session_db(session_id: str, **kwargs) -> Optional[Dict[str, Any
                       word_result, ground_truth, auto_shear_degrees,
                       doc_type, doc_type_result,
                       document_category, pipeline_log,
+                      parent_session_id, box_index,
                       created_at, updated_at
         """, *values)
 
@@ -205,18 +221,45 @@ async def update_session_db(session_id: str, **kwargs) -> Optional[Dict[str, Any
         return None
 
 
-async def list_sessions_db(limit: int = 50) -> List[Dict[str, Any]]:
-    """List all sessions (metadata only, no images)."""
+async def list_sessions_db(
+    limit: int = 50,
+    include_sub_sessions: bool = False,
+) -> List[Dict[str, Any]]:
+    """List sessions (metadata only, no images).
+
+    By default, sub-sessions (those with parent_session_id) are excluded.
+    Pass include_sub_sessions=True to include them.
+    """
+    pool = await get_pool()
+    async with pool.acquire() as conn:
+        where = "" if include_sub_sessions else "WHERE parent_session_id IS NULL"
+        rows = await conn.fetch(f"""
+            SELECT id, name, filename, status, current_step,
+                   document_category, doc_type,
+                   parent_session_id, box_index,
+                   created_at, updated_at
+            FROM ocr_pipeline_sessions
+            {where}
+            ORDER BY created_at DESC
+            LIMIT $1
+        """, limit)
+
+        return [_row_to_dict(row) for row in rows]
+
+
+async def get_sub_sessions(parent_session_id: str) -> List[Dict[str, Any]]:
+    """Get all sub-sessions for a parent session, ordered by box_index."""
     pool = await get_pool()
     async with pool.acquire() as conn:
         rows = await conn.fetch("""
             SELECT id, name, filename, status, current_step,
                    document_category, doc_type,
+                   parent_session_id, box_index,
                    created_at, updated_at
             FROM ocr_pipeline_sessions
-            ORDER BY created_at DESC
-            LIMIT $1
-        """, limit)
+            WHERE parent_session_id = $1
+            ORDER BY box_index ASC
+        """, uuid.UUID(parent_session_id))
 
         return [_row_to_dict(row) for row in rows]
 
@@ -255,7 +298,7 @@ def _row_to_dict(row: asyncpg.Record) -> Dict[str, Any]:
     result = dict(row)
 
     # UUID → string
-    for key in ['id', 'session_id']:
+    for key in ['id', 'session_id', 'parent_session_id']:
         if key in result and result[key] is not None:
             result[key] = str(result[key])