chore(sync): mirror docs from openclaw/openclaw@ddae71537d

.openclaw-sync/source.json

@@ -1,5 +1,5 @@
 {
   "repository": "openclaw/openclaw",
-  "sha": "07a11c48069aad29badc8f8f4c8558de0631671b",
-  "syncedAt": "2026-05-03T16:29:47.671Z"
+  "sha": "ddae71537d8ba38bf8fb720ca0d718281924382e",
+  "syncedAt": "2026-05-03T16:39:58.308Z"
 }

docs/cli/memory.md

@@ -51,7 +51,7 @@ openclaw memory index --agent main --verbose
 
 `memory status`:
 
-- `--deep`: probe vector + embedding availability. Plain `memory status` stays fast and does not run a live embedding ping. QMD lexical `searchMode: "search"` skips semantic vector probes and embedding maintenance even with `--deep`.
+- `--deep`: probe local vector-store readiness, embedding-provider readiness, and semantic vector-search readiness. Plain `memory status` stays fast and does not run live embedding or provider discovery work; unknown vector-store or semantic-vector state means it was not probed in that command. QMD lexical `searchMode: "search"` skips semantic vector probes and embedding maintenance even with `--deep`.
 - `--index`: run a reindex if the store is dirty (implies `--deep`).
 - `--fix`: repair stale recall locks and normalize promotion metadata.
 - `--json`: print JSON output.

docs/concepts/memory-builtin.md

@@ -127,7 +127,10 @@ when `memorySearch.local.modelPath` points to an existing local file.
 may miss changes in rare edge cases.
 
 **sqlite-vec not loading?** OpenClaw falls back to in-process cosine similarity
-automatically. Check logs for the specific load error.
+automatically. `openclaw memory status --deep` reports the local vector store
+separately from the embedding provider, so `Vector store: unavailable` points
+at sqlite-vec loading while `Embeddings: unavailable` points at provider/auth
+or model readiness. Check logs for the specific load error.
 
 ## Configuration