chore(sync): mirror docs from openclaw/openclaw@da55212c6e

.openclaw-sync/source.json

@@ -1,5 +1,5 @@
 {
   "repository": "openclaw/openclaw",
-  "sha": "d5e6abcb3d22c5fb96869e916059163928dba718",
-  "syncedAt": "2026-04-27T07:38:03.611Z"
+  "sha": "da55212c6e2ad3fa730b1708ba8d0f893e23e4de",
+  "syncedAt": "2026-04-27T07:39:50.095Z"
 }

docs/gateway/local-models.md

@@ -164,6 +164,11 @@ Compatibility notes for stricter OpenAI-compatible backends:
   structured content-part arrays. Set
   `models.providers.<provider>.models[].compat.requiresStringContent: true` for
   those endpoints.
+- Some local models emit standalone bracketed tool requests as text, such as
+  `[tool_name]` followed by JSON and `[END_TOOL_REQUEST]`. OpenClaw promotes
+  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.
 - 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