diff --git a/.openclaw-sync/source.json b/.openclaw-sync/source.json
index 136c537c6..156b1bb32 100644
--- a/.openclaw-sync/source.json
+++ b/.openclaw-sync/source.json
@@ -1,5 +1,5 @@
 {
   "repository": "openclaw/openclaw",
-  "sha": "cf834e2a21eac7fd218989fb5b85e7e8dd4c3246",
-  "syncedAt": "2026-04-26T03:10:53.654Z"
+  "sha": "a91baa16de69ac3d7f3eea76ed950f3110f4bbe4",
+  "syncedAt": "2026-04-26T03:15:43.703Z"
 }
diff --git a/docs/tools/tts.md b/docs/tools/tts.md
index 600ed89da..e9e7c3858 100644
--- a/docs/tools/tts.md
+++ b/docs/tools/tts.md
@@ -685,6 +685,10 @@ channel sees them, even when a directive is split across adjacent blocks. Final
 mode still parses the accumulated raw reply for TTS synthesis.
 
 `provider=...` directives are ignored unless `modelOverrides.allowProvider: true`.
+When a reply declares `provider=...`, the other keys in that directive are
+parsed only by that provider. Unsupported keys are stripped from visible text
+and reported as TTS directive warnings instead of being routed to another
+provider.
 
 Example reply payload: