feat(tree_renderer): add type+description to PageIndex summary frontmatter

Author: KylinMountain

openkb/indexer.py

@@ -174,7 +174,7 @@ def index_long_document(
     # Write wiki/summaries/ (no images, just summaries)
     summaries_dir = kb_dir / "wiki" / "summaries"
     summaries_dir.mkdir(parents=True, exist_ok=True)
-    summary_md = render_summary_md(tree, source_name, doc_id)
+    summary_md = render_summary_md(tree, source_name, doc_id, description=description)
     (summaries_dir / f"{source_name}.md").write_text(summary_md, encoding="utf-8")
 
     return IndexResult(doc_id=doc_id, description=description, tree=tree)

openkb/tree_renderer.py

@@ -1,17 +1,23 @@
 """Markdown renderers for PageIndex tree structures."""
 from __future__ import annotations
 
+import json
 
-def _yaml_frontmatter(source_name: str, doc_id: str) -> str:
-    """Return a YAML frontmatter block for a PageIndex wiki page."""
-    return (
-        "---\n"
-        "doc_type: pageindex\n"
-        f"full_text: sources/{source_name}.json\n"
-        "---\n"
-    )
+
+def _yaml_kv_line(key: str, value: str) -> str:
+    """Return a single YAML key-value line with the value JSON-quoted."""
+    return f"{key}: {json.dumps(value, ensure_ascii=False)}"
 
 
+def _yaml_frontmatter(source_name: str, doc_id: str, description: str = "") -> str:
+    """Return a YAML frontmatter block for a PageIndex wiki page."""
+    lines = [_yaml_kv_line("type", "Summary")]
+    if description:
+        lines.append(_yaml_kv_line("description", description))
+    lines.append("doc_type: pageindex")
+    lines.append(f"full_text: sources/{source_name}.json")
+    return "---\n" + "\n".join(lines) + "\n---\n"
+
 
 def _render_nodes_summary(nodes: list[dict], depth: int) -> str:
     """Recursively render nodes for the *summary* view (summaries only)."""
@@ -24,7 +30,7 @@ def _render_nodes_summary(nodes: list[dict], depth: int) -> str:
         summary = node.get("summary", "")
         children = node.get("nodes", [])
 
-        lines.append(f"{heading_prefix} {title} (pages {start}\u2013{end})\n")
+        lines.append(f"{heading_prefix} {title} (pages {start}–{end})\n")
         if summary:
             lines.append(f"Summary: {summary}\n")
         if children:
@@ -33,13 +39,15 @@ def _render_nodes_summary(nodes: list[dict], depth: int) -> str:
     return "\n".join(lines)
 
 
-
-def render_summary_md(tree: dict, source_name: str, doc_id: str) -> str:
+def render_summary_md(tree: dict, source_name: str, doc_id: str,
+                      description: str = "") -> str:
     """Render the summary Markdown page for a PageIndex tree.
 
     Renders each node as a heading with page range and its summary text.
+    Includes a YAML frontmatter block with ``type: "Summary"`` and an
+    optional ``description`` field.
     """
-    frontmatter = _yaml_frontmatter(source_name, doc_id)
+    frontmatter = _yaml_frontmatter(source_name, doc_id, description)
     structure = tree.get("structure", [])
     body = _render_nodes_summary(structure, depth=1)
     return frontmatter + "\n" + body

tests/test_tree_renderer.py

@@ -38,3 +38,13 @@ def test_summary_included_not_text(self, sample_tree):
         assert "Summary: Historical context." in output
         # Raw text should NOT appear in summary view
         assert "This document introduces the core concepts of the system." not in output
+
+
+def test_summary_md_has_type_and_description():
+    tree = {"structure": [{"title": "Intro", "start_index": 1,
+                           "end_index": 2, "summary": "x", "nodes": []}]}
+    md = render_summary_md(tree, "my-doc", "doc-123", description="Quarterly report.")
+    assert 'type: "Summary"' in md
+    assert 'description: "Quarterly report."' in md
+    assert "doc_type: pageindex" in md
+    assert "full_text: sources/my-doc.json" in md