diff --git a/.openclaw-sync/source.json b/.openclaw-sync/source.json
index 9cb3bbed7..9a6db03cf 100644
--- a/.openclaw-sync/source.json
+++ b/.openclaw-sync/source.json
@@ -1,5 +1,5 @@
 {
   "repository": "openclaw/openclaw",
-  "sha": "ea2d95e23e87636ff8b8f8493c4cd5b53db68cbb",
-  "syncedAt": "2026-04-27T22:54:58.350Z"
+  "sha": "78d3fce5f9b98196b671892cbfb010adc42df457",
+  "syncedAt": "2026-04-27T22:55:23.187Z"
 }
diff --git a/docs/reference/transcript-hygiene.md b/docs/reference/transcript-hygiene.md
index 198167d3d..922c75eae 100644
--- a/docs/reference/transcript-hygiene.md
+++ b/docs/reference/transcript-hygiene.md
@@ -112,6 +112,7 @@ external end-user instructions.
 
 - Image sanitization only.
 - Drop orphaned reasoning signatures (standalone reasoning items without a following content block) for OpenAI Responses/Codex transcripts, and drop replayable OpenAI reasoning after a model route switch.
+- Preserve replayable OpenAI Responses reasoning item payloads, including encrypted empty-summary items, so manual/WebSocket replay keeps required `rs_*` state paired with assistant output items.
 - No tool call id sanitization.
 - Tool result pairing repair may move real matched outputs and synthesize Codex-style `aborted` outputs for missing tool calls.
 - No turn validation or reordering.