diff --git a/.openclaw-sync/source.json b/.openclaw-sync/source.json
index d9408926a..6ebfcf328 100644
--- a/.openclaw-sync/source.json
+++ b/.openclaw-sync/source.json
@@ -1,5 +1,5 @@
 {
   "repository": "openclaw/openclaw",
-  "sha": "74a4ff1adcf795b32d00619ccadf1c111bd1701e",
-  "syncedAt": "2026-04-26T10:29:44.569Z"
+  "sha": "cd8187d7cecd88e899e41f332432c587fe424455",
+  "syncedAt": "2026-04-26T10:39:31.290Z"
 }
diff --git a/docs/help/testing.md b/docs/help/testing.md
index c7b012fa7..800255e94 100644
--- a/docs/help/testing.md
+++ b/docs/help/testing.md
@@ -172,6 +172,10 @@ runs the same lanes before release approval.
   - Use `--platform macos`, `--platform windows`, or `--platform linux` while
     iterating on one guest. Use `--json` for the summary artifact path and
     per-lane status.
+  - The OpenAI lane uses `openai/gpt-5.5` for the live agent-turn proof by
+    default. Pass `--model <provider/model>` or set
+    `OPENCLAW_PARALLELS_OPENAI_MODEL` when deliberately validating another
+    OpenAI model.
   - Wrap long local runs in a host timeout so Parallels transport stalls cannot
     consume the rest of the testing window: