diff --git a/backend/packages/harness/deerflow/utils/file_conversion.py b/backend/packages/harness/deerflow/utils/file_conversion.py
index f51b47caa..5c5a28235 100644
--- a/backend/packages/harness/deerflow/utils/file_conversion.py
+++ b/backend/packages/harness/deerflow/utils/file_conversion.py
@@ -279,7 +279,11 @@ def extract_outline(md_path: Path) -> list[dict]:
                     if title:
                         outline.append({"title": title, "line": lineno})
 
-                if len(outline) >= MAX_OUTLINE_ENTRIES:
+                if len(outline) > MAX_OUTLINE_ENTRIES:
+                    # We collected one heading beyond the limit, which proves the
+                    # document genuinely has more than MAX_OUTLINE_ENTRIES headings.
+                    # Drop that extra entry and append the truncation sentinel.
+                    outline.pop()
                     outline.append({"truncated": True})
                     break
     except Exception:
diff --git a/backend/tests/test_file_conversion.py b/backend/tests/test_file_conversion.py
index 4c2189bc2..407b8ae12 100644
--- a/backend/tests/test_file_conversion.py
+++ b/backend/tests/test_file_conversion.py
@@ -422,6 +422,15 @@ class TestExtractOutline:
         assert len(outline) == 5
         assert not any(e.get("truncated") for e in outline)
 
+    def test_no_truncation_sentinel_at_exact_limit(self, tmp_path):
+        """A document with exactly MAX_OUTLINE_ENTRIES headings is not truncated."""
+        lines = [f"# Heading {i}" for i in range(MAX_OUTLINE_ENTRIES)]
+        md = tmp_path / "exact.md"
+        md.write_text("\n".join(lines), encoding="utf-8")
+        outline = extract_outline(md)
+        assert len(outline) == MAX_OUTLINE_ENTRIES
+        assert not any(e.get("truncated") for e in outline)
+
     def test_blank_lines_and_whitespace_ignored(self, tmp_path):
         """Blank lines between headings do not produce empty entries."""
         md = tmp_path / "spaced.md"