chore(sync): mirror docs from openclaw/openclaw@4015138df9

.openclaw-sync/source.json

@@ -1,5 +1,5 @@
 {
   "repository": "openclaw/openclaw",
-  "sha": "dae060390b1d17aa949c4a1a0c12fbc3b1eedb79",
-  "syncedAt": "2026-04-14T13:42:46.346Z"
+  "sha": "4015138df93eb3f3fa30a195fb2f5c4f6cb97967",
+  "syncedAt": "2026-04-14T13:46:28.648Z"
 }

docs/gateway/local-models.md

@@ -164,8 +164,10 @@ Compatibility notes for stricter OpenAI-compatible backends:
 - 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
-  OpenClaw agent turns, try
-  `models.providers.<provider>.models[].compat.supportsTools: false` first.
+  OpenClaw agent turns, first try
+  `agents.defaults.localModelMode: "lean"` to drop heavyweight default tools
+  like `browser`, `cron`, and `message`; if that still fails, try
+  `models.providers.<provider>.models[].compat.supportsTools: false`.
 - If the backend still fails only on larger OpenClaw runs, the remaining issue
   is usually upstream model/server capacity or a backend bug, not OpenClaw's
   transport layer.