diff --git a/.openclaw-sync/source.json b/.openclaw-sync/source.json
index 5be2d1ac9..257b4eba2 100644
--- a/.openclaw-sync/source.json
+++ b/.openclaw-sync/source.json
@@ -1,5 +1,5 @@
 {
   "repository": "openclaw/openclaw",
-  "sha": "343f2d7245933a249716f550ecdd1c25ce56a13b",
-  "syncedAt": "2026-04-28T03:14:07.669Z"
+  "sha": "4b4cde71874f1140346456640b8913042e560661",
+  "syncedAt": "2026-04-28T03:17:32.906Z"
 }
diff --git a/docs/concepts/memory-qmd.md b/docs/concepts/memory-qmd.md
index daa425c92..502a672e1 100644
--- a/docs/concepts/memory-qmd.md
+++ b/docs/concepts/memory-qmd.md
@@ -64,6 +64,9 @@ present.
   same-source collections into one QMD search invocation. Older QMD releases
   keep the compatible per-collection fallback.
 - If QMD fails entirely, OpenClaw falls back to the builtin SQLite engine.
+  Repeated chat-turn attempts back off briefly after an open failure so a
+  missing binary or broken sidecar dependency does not create a retry storm;
+  `openclaw memory status` and one-shot CLI probes still recheck QMD directly.
 
 <Info>
 The first search may be slow -- QMD auto-downloads GGUF models (~2 GB) for