From 27c649f5c1316062ea369a2d55710cfe2aa80d8d Mon Sep 17 00:00:00 2001
From: 4byounth <1187256439@qq.com>
Date: Sun, 29 Mar 2026 00:16:42 +0800
Subject: [PATCH] fix: correct context_type classification for memories during
 reindex

When reindexing via `/api/v1/content/reindex`, all memories under
`viking://user/*/memories/*` and `viking://agent/*/memories/*` were
incorrectly classified as `context_type="resource"` instead of
`"memory"`. This caused downstream consumers (e.g. OpenClaw auto-recall)
that filter by `context_type=="memory"` to miss all reindexed memories.

Two root causes:

1. `summarizer.py` checked `uri.startswith("viking://memory/")` which
   never matches real memory URIs (actual paths use `/memories/` as a
   path segment, not a top-level scheme). Fixed by using substring match
   `"/memories" in uri`, consistent with `core/directories.get_context_type_for_uri()`.

2. `semantic_dag.py` propagated the root URI's `context_type` to all
   child nodes during recursive traversal. When reindexing from
   `viking://`, the root has no `/memories/` segment, so all children
   inherited `"resource"`. Fixed by calling `get_context_type_for_uri()`
   per node.

Normal memory creation via auto-capture is unaffected (it uses
`memory_updater.py` which hardcodes `"memory"`), so this bug only
manifests during reindex operations.

Closes #1060
---
 openviking/storage/queuefs/semantic_dag.py | 5 +++--
 openviking/utils/summarizer.py             | 5 +++--
 2 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/openviking/storage/queuefs/semantic_dag.py b/openviking/storage/queuefs/semantic_dag.py
index 55cacc691..db8137b8d 100644
--- a/openviking/storage/queuefs/semantic_dag.py
+++ b/openviking/storage/queuefs/semantic_dag.py
@@ -6,6 +6,7 @@
 from dataclasses import dataclass, field
 from typing import Awaitable, Callable, Dict, List, Optional
 
+from openviking.core.directories import get_context_type_for_uri
 from openviking.server.identity import RequestContext
 from openviking.storage.viking_fs import get_viking_fs
 from openviking_cli.utils import VikingURI
@@ -440,7 +441,7 @@ async def _file_summary_task(self, parent_uri: str, file_path: str) -> None:
                 task = VectorizeTask(
                     task_type="file",
                     uri=file_path,
-                    context_type=self._context_type,
+                    context_type=get_context_type_for_uri(file_path),
                     ctx=self._ctx,
                     semantic_msg_id=self._semantic_msg_id,
                     file_path=file_path,
@@ -560,7 +561,7 @@ async def _overview_task(self, dir_uri: str) -> None:
                     task = VectorizeTask(
                         task_type="directory",
                         uri=dir_uri,
-                        context_type=self._context_type,
+                        context_type=get_context_type_for_uri(dir_uri),
                         ctx=self._ctx,
                         semantic_msg_id=self._semantic_msg_id,
                         abstract=abstract,
diff --git a/openviking/utils/summarizer.py b/openviking/utils/summarizer.py
index dff099e62..6f3c2dcd4 100644
--- a/openviking/utils/summarizer.py
+++ b/openviking/utils/summarizer.py
@@ -57,10 +57,11 @@ async def summarize(
         telemetry = get_current_telemetry()
         for uri, temp_uri in zip(resource_uris, temp_uris):
             # Determine context_type based on URI
+            # Use the same logic as core/directories.get_context_type_for_uri()
             context_type = "resource"
-            if uri.startswith("viking://memory/"):
+            if "/memories" in uri:
                 context_type = "memory"
-            elif uri.startswith("viking://agent/skills/"):
+            elif "/skills" in uri:
                 context_type = "skill"
 
             msg = SemanticMsg(