Skip to content

Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.

fix(reindex): reuse semantic overview parser (#5251)

zhanggaoyuanff44a172f2db
diff --git a/openviking/service/reindex_executor.py b/openviking/service/reindex_executor.py
index 7b6c0334e..67087c419 100644
--- a/openviking/service/reindex_executor.py
+++ b/openviking/service/reindex_executor.py
@@ -1820,7 +1820,7 @@ class ReindexExecutor:
file_name = uri.rsplit("/", 1)[-1]
overviews = await self._safe_read_text(f"{parent_uri}/.overview.md", ctx=ctx)
if overviews:
- parsed = self._parse_overview_md(body_for_preview(overviews))
+ parsed = SemanticProcessor._parse_overview_md(overviews)
if file_name in parsed:
return parsed[file_name]
existing = await self._fetch_existing_record(
@@ -2036,21 +2036,3 @@ class ReindexExecutor:
if value:
return value
return ""
-
- @staticmethod
- def _parse_overview_md(content: str) -> dict[str, str]:
- parsed: dict[str, str] = {}
- current_name: Optional[str] = None
- current_lines: list[str] = []
- for line in (content or "").splitlines():
- if line.startswith("## "):
- if current_name is not None:
- parsed[current_name] = "\n".join(current_lines).strip()
- current_name = line[3:].strip()
- current_lines = []
- continue
- if current_name is not None:
- current_lines.append(line)
- if current_name is not None:
- parsed[current_name] = "\n".join(current_lines).strip()
- return parsed
diff --git a/openviking/storage/queuefs/semantic_processor.py b/openviking/storage/queuefs/semantic_processor.py
index 1fd57bc66..27b967f58 100644
--- a/openviking/storage/queuefs/semantic_processor.py
+++ b/openviking/storage/queuefs/semantic_processor.py
@@ -1422,7 +1422,8 @@ class SemanticProcessor(DequeueHandlerBase):
abstract = self._truncate_generated_text(abstract, semantic.abstract_max_chars)
return overview, abstract
- def _parse_overview_md(self, overview_content: str) -> Dict[str, str]:
+ @classmethod
+ def _parse_overview_md(cls, overview_content: str) -> Dict[str, str]:
"""Parse overview.md and extract file summaries.
Args:
@@ -1449,7 +1450,7 @@ class SemanticProcessor(DequeueHandlerBase):
if current_file and current_summary_lines:
summaries[current_file] = " ".join(current_summary_lines).strip()
- file_name = self._overview_heading_cache_key(header_match.group(1).strip())
+ file_name = cls._overview_heading_cache_key(header_match.group(1).strip())
parts = file_name.split()
if len(parts) >= 2 and parts[0] == parts[1]:
file_name = parts[0]
diff --git a/tests/server/test_admin_rebuild_api.py b/tests/server/test_admin_rebuild_api.py
index c94dd9db8..2468bce06 100644
--- a/tests/server/test_admin_rebuild_api.py
+++ b/tests/server/test_admin_rebuild_api.py
@@ -2493,7 +2493,12 @@ async def test_reindex_file_summary_reads_existing_record_as_uri_owner(monkeypat
raw = render_abstract_overview(
ContextLevel.OVERVIEW,
"viking://resources/demo",
- "# Demo\n\n## image.png\nVisible file summary.",
+ (
+ "# Demo\n\n"
+ "## Detailed Description\n\n"
+ "### [Image](viking://resources/demo/image.png)\n"
+ "Visible file summary."
+ ),
{
"source": {
"kind": "http",