diff --git a/.openclaw-sync/source.json b/.openclaw-sync/source.json
index a38952371..571864e77 100644
--- a/.openclaw-sync/source.json
+++ b/.openclaw-sync/source.json
@@ -1,5 +1,5 @@
 {
   "repository": "openclaw/openclaw",
-  "sha": "7688b696de2b99e10b4313b4771854164b55bbb0",
-  "syncedAt": "2026-04-27T10:37:11.432Z"
+  "sha": "9ef0131e1c8df696010b0f2a77038cf121705986",
+  "syncedAt": "2026-04-27T10:40:49.067Z"
 }
diff --git a/docs/gateway/local-models.md b/docs/gateway/local-models.md
index 149f87f7e..c72cbd729 100644
--- a/docs/gateway/local-models.md
+++ b/docs/gateway/local-models.md
@@ -148,6 +148,10 @@ servers before raising `agents.defaults.timeoutSeconds`. The provider timeout
 applies only to model HTTP requests, including connect, headers, body streaming,
 and the total guarded-fetch abort.
 
+<Note>
+For custom OpenAI-compatible providers, persisting a non-secret local marker such as `apiKey: "ollama-local"` is accepted when `baseUrl` resolves to loopback, a private LAN, `.local`, or a bare hostname. OpenClaw treats it as a valid local credential instead of reporting a missing key. Use a real value for any provider that accepts a public hostname.
+</Note>
+
 Behavior note for local/proxied `/v1` backends:
 
 - OpenClaw treats these as proxy-style OpenAI-compatible routes, not native