From 6c6e5c140cc0471abe3ef2c57a051c4837fd8a84 Mon Sep 17 00:00:00 2001
From: "copilot-swe-agent[bot]" <198982749+Copilot@users.noreply.github.com>
Date: Wed, 1 Jul 2026 23:48:28 +0000
Subject: [PATCH] feat(staging): render list bullets and title heading depth in
 markdown

---
 test_unstructured/staging/test_base.py | 13 +++++++++++++
 unstructured/staging/base.py           | 13 +++++++++++--
 2 files changed, 24 insertions(+), 2 deletions(-)

diff --git a/test_unstructured/staging/test_base.py b/test_unstructured/staging/test_base.py
index 8f2b0c35f6..8b2f3c516b 100644
--- a/test_unstructured/staging/test_base.py
+++ b/test_unstructured/staging/test_base.py
@@ -592,6 +592,19 @@ def test_elements_to_md_conversion(json_filename: str, expected_md_filename: str
     ("element", "expected_markdown", "exclude_binary"),
     [
         (Title("Test Title"), "# Test Title", False),
+        (
+            Title("Second Level", metadata=ElementMetadata(category_depth=2)),
+            "## Second Level",
+            False,
+        ),
+        (
+            Title("Third Level", metadata=ElementMetadata(category_depth=3)),
+            "### Third Level",
+            False,
+        ),
+        (Title("No Depth"), "# No Depth", False),
+        (ListItem("Buy milk"), "- Buy milk", False),
+        (ListItem("Another item"), "- Another item", False),
         (NarrativeText("This is some narrative text."), "This is some narrative text.", False),
         (Formula(r"\int_a^b x^2 dx"), "$$\n\\int_a^b x^2 dx\n$$", False),
         (
diff --git a/unstructured/staging/base.py b/unstructured/staging/base.py
index 47d8c99f83..dce3fa5514 100644
--- a/unstructured/staging/base.py
+++ b/unstructured/staging/base.py
@@ -18,6 +18,7 @@
     ElementMetadata,
     Formula,
     Image,
+    ListItem,
     Table,
     Title,
 )
@@ -278,8 +279,16 @@ def element_to_md(
     formula_markdown_style: str = FORMULA_MARKDOWN_AUTO,
 ) -> str:
     match element:
-        case Title(text=text):
-            return f"# {text}"
+        case Title(text=text, metadata=metadata):
+            depth = metadata.category_depth if metadata.category_depth else 1
+            if not isinstance(depth, int):
+                try:
+                    depth = int(depth) if isinstance(depth, (str, float)) else 1
+                except (TypeError, ValueError):
+                    depth = 1
+            return f"{'#' * depth} {text}"
+        case ListItem(text=text):
+            return f"- {text}"
         case Formula(text=text):
             return _emit_formula_markdown(
                 text,