⚡ Bolt: Optimize DocxXMLEditor tracked change ID generation

.jules/bolt.md

@@ -5,3 +5,7 @@
 ## 2024-05-24 - openpyxl read_only optimization
 **Learning:** `openpyxl.load_workbook(..., read_only=True)` is significantly faster (1.75x) for parsing large files but requires explicit `wb.close()` (preferably in `try...finally`) as it keeps file handles open and `Workbook` objects may not support context managers in all versions.
 **Action:** Use `read_only=True` for read-heavy Excel tasks and always ensure `close()` is called.
+
+## 2024-05-25 - DocxXMLEditor ID Generation Optimization
+**Learning:** Generating sequential IDs by scanning the full DOM on every insertion is O(N^2) for batch operations. Caching the next ID reduces this to O(N).
+**Action:** When generating unique IDs in a document, initialize a counter by scanning once, then increment locally, while watching for manual insertions to keep the counter valid.

skills/docx/scripts/document.py

@@ -71,20 +71,26 @@ def __init__(
         self.rsid = rsid
         self.author = author
         self.initials = initials
+        self._next_change_id = None
 
     def _get_next_change_id(self):
-        """Get the next available change ID by checking all tracked change elements."""
-        max_id = -1
-        for tag in ("w:ins", "w:del"):
-            elements = self.dom.getElementsByTagName(tag)
-            for elem in elements:
-                change_id = elem.getAttribute("w:id")
-                if change_id:
-                    try:
-                        max_id = max(max_id, int(change_id))
-                    except ValueError:
-                        pass
-        return max_id + 1
+        """Get the next available change ID."""
+        if self._next_change_id is None:
+            max_id = -1
+            for tag in ("w:ins", "w:del"):
+                elements = self.dom.getElementsByTagName(tag)
+                for elem in elements:
+                    change_id = elem.getAttribute("w:id")
+                    if change_id:
+                        try:
+                            max_id = max(max_id, int(change_id))
+                        except ValueError:
+                            pass
+            self._next_change_id = max_id + 1
+
+        next_id = self._next_change_id
+        self._next_change_id += 1
+        return next_id
 
     def _ensure_w16du_namespace(self):
         """Ensure w16du namespace is declared on the root element."""
@@ -168,6 +174,15 @@ def add_tracked_change_attrs(elem):
             # Auto-assign w:id if not present
             if not elem.hasAttribute("w:id"):
                 elem.setAttribute("w:id", str(self._get_next_change_id()))
+            elif self._next_change_id is not None:
+                # Update cache if we see a higher ID manually inserted
+                try:
+                    current_id = int(elem.getAttribute("w:id"))
+                    if current_id >= self._next_change_id:
+                        self._next_change_id = current_id + 1
+                except ValueError:
+                    pass
+
             if not elem.hasAttribute("w:author"):
                 elem.setAttribute("w:author", self.author)
             if not elem.hasAttribute("w:date"):