diff --git a/.openclaw-sync/source.json b/.openclaw-sync/source.json
index 7482b1acc..16999a343 100644
--- a/.openclaw-sync/source.json
+++ b/.openclaw-sync/source.json
@@ -1,5 +1,5 @@
 {
   "repository": "openclaw/openclaw",
-  "sha": "0055e404cf21b5b4d6ba9ea081e61e62e004eddc",
-  "syncedAt": "2026-04-27T08:04:59.781Z"
+  "sha": "f9181835e8700f3e2c56ebe7cdec050276f75458",
+  "syncedAt": "2026-04-27T08:15:57.939Z"
 }
diff --git a/docs/gateway/local-models.md b/docs/gateway/local-models.md
index 2967a39ed..65c52e399 100644
--- a/docs/gateway/local-models.md
+++ b/docs/gateway/local-models.md
@@ -169,6 +169,11 @@ Compatibility notes for stricter OpenAI-compatible backends:
   those into real tool calls only when the name exactly matches a registered
   tool for the turn; otherwise the block is treated as unsupported text and is
   hidden from user-visible replies.
+- If a model emits JSON, XML, or ReAct-style text that looks like a tool call
+  but the provider did not emit a structured invocation, OpenClaw leaves it as
+  text and logs a warning with the run id, provider/model, detected pattern, and
+  tool name when available. Treat that as provider/model tool-call
+  incompatibility, not a completed tool run.
 - Some smaller or stricter local backends are unstable with OpenClaw's full
   agent-runtime prompt shape, especially when tool schemas are included. If the
   backend works for tiny direct `/v1/chat/completions` calls but fails on normal