diff --git a/.openclaw-sync/source.json b/.openclaw-sync/source.json
index 71fb4ddc8..f71317fc4 100644
--- a/.openclaw-sync/source.json
+++ b/.openclaw-sync/source.json
@@ -1,5 +1,5 @@
 {
   "repository": "openclaw/openclaw",
-  "sha": "d8da04e58eeddc19c53a0df3ecee7b21dce6f263",
-  "syncedAt": "2026-05-04T06:30:16.601Z"
+  "sha": "deffd11a430838cf64b39342823032343b3ed12d",
+  "syncedAt": "2026-05-04T06:37:35.485Z"
 }
diff --git a/docs/plugins/google-meet.md b/docs/plugins/google-meet.md
index 9e5cd6d13..162e26e14 100644
--- a/docs/plugins/google-meet.md
+++ b/docs/plugins/google-meet.md
@@ -1707,6 +1707,11 @@ Chrome talk-back modes need `BlackHole 2ch` plus either:
   audio path and must exit after starting or validating its daemon. This is only
   valid for `bidi` because `agent` mode needs direct command-pair access for TTS.
 
+When an agent calls the `google_meet` tool in agent mode, the meeting consultant
+session forks the caller's current transcript before answering participant
+speech. The Meet session still stays separate (`agent:<agentId>:subagent:google-meet:<sessionId>`)
+so meeting follow-ups do not mutate the caller transcript directly.
+
 For clean duplex audio, route Meet output and Meet microphone through separate
 virtual devices or a Loopback-style virtual device graph. A single shared
 BlackHole device can echo other participants back into the call.