chore(sync): mirror docs from openclaw/openclaw@1ee885123f

.openclaw-sync/source.json

@@ -1,5 +1,5 @@
 {
   "repository": "openclaw/openclaw",
-  "sha": "3af34316f212707b18a938de272f3d16cce4a6af",
-  "syncedAt": "2026-04-27T09:26:23.884Z"
+  "sha": "1ee885123ffbcc2e439a3eab1f1469a231dc70ad",
+  "syncedAt": "2026-04-27T09:33:23.290Z"
 }

docs/gateway/local-models.md

@@ -174,6 +174,31 @@ Compatibility notes for stricter OpenAI-compatible backends:
   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.
+- For OpenAI-compatible Chat Completions backends whose tool parser works only
+  when tool use is forced, set a per-model request override instead of relying
+  on text parsing:
+
+  ```json5
+  {
+    agents: {
+      defaults: {
+        models: {
+          "local/my-local-model": {
+            params: {
+              extra_body: {
+                tool_choice: "required",
+              },
+            },
+          },
+        },
+      },
+    },
+  }
+  ```
+
+  Use this only for models/sessions where every normal turn should call a tool.
+  It overrides OpenClaw's default proxy value of `tool_choice: "auto"`.
+
 - 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

docs/providers/vllm.md

@@ -168,6 +168,41 @@ Use explicit config when:
 
   </Accordion>
 
+  <Accordion title="Qwen tool-call parser needs required">
+    First make sure vLLM was started with the right tool-call parser and chat
+    template for the model. For example, vLLM documents `hermes` for Qwen2.5
+    models and `qwen3_xml` for Qwen3-Coder models.
+
+    Some Qwen/vLLM combinations still return raw tool-call text or an empty
+    `tool_calls` array when the request uses `tool_choice: "auto"`, but return
+    structured tool calls when the request uses `tool_choice: "required"`. For
+    those model entries, force the OpenAI-compatible request field with
+    `params.extra_body`:
+
+    ```json5
+    {
+      agents: {
+        defaults: {
+          models: {
+            "vllm/Qwen-Qwen2.5-Coder-32B-Instruct": {
+              params: {
+                extra_body: {
+                  tool_choice: "required",
+                },
+              },
+            },
+          },
+        },
+      },
+    }
+    ```
+
+    This is an opt-in compatibility workaround. It makes every model turn with
+    tools require a tool call, so use it only for a dedicated local model entry
+    where that behavior is acceptable.
+
+  </Accordion>
+
   <Accordion title="Custom base URL">
     If your vLLM server runs on a non-default host or port, set `baseUrl` in the explicit provider config: