chore(sync): mirror docs from openclaw/openclaw@c3833f7729

.openclaw-sync/source.json

@@ -1,5 +1,5 @@
 {
   "repository": "openclaw/openclaw",
-  "sha": "7a85c1a8226eb7d3a96906d2721a189768d3034a",
-  "syncedAt": "2026-04-26T02:53:58.043Z"
+  "sha": "c3833f7729163a8f6cdc47d3b0be86fd5fcab160",
+  "syncedAt": "2026-04-26T02:56:41.507Z"
 }

docs/concepts/model-providers.md

@@ -631,6 +631,11 @@ Notes:
 - For OpenAI-compatible Completions proxies that need vendor-specific fields,
   set `agents.defaults.models["provider/model"].params.extra_body` (or
   `extraBody`) to merge extra JSON into the outbound request body.
+- For vLLM chat-template controls, set
+  `agents.defaults.models["provider/model"].params.chat_template_kwargs`.
+  OpenClaw automatically sends `enable_thinking: false` and
+  `force_nonempty_content: true` for `vllm/nemotron-3-*` when the session
+  thinking level is off.
 - If `baseUrl` is empty/omitted, OpenClaw keeps the default OpenAI behavior (which resolves to `api.openai.com`).
 - For safety, an explicit `compat.supportsDeveloperRole: true` is still overridden on non-native `openai-completions` endpoints.
 

docs/gateway/config-agents.md

@@ -364,13 +364,14 @@ Time format in system prompt. Default: `auto` (OS preference).
 - `verboseDefault`: default verbose level for agents. Values: `"off"`, `"on"`, `"full"`. Default: `"off"`.
 - `elevatedDefault`: default elevated-output level for agents. Values: `"off"`, `"on"`, `"ask"`, `"full"`. Default: `"on"`.
 - `model.primary`: format `provider/model` (e.g. `openai/gpt-5.5` for API-key access or `openai-codex/gpt-5.5` for Codex OAuth). If you omit the provider, OpenClaw tries an alias first, then a unique configured-provider match for that exact model id, and only then falls back to the configured default provider (deprecated compatibility behavior, so prefer explicit `provider/model`). If that provider no longer exposes the configured default model, OpenClaw falls back to the first configured provider/model instead of surfacing a stale removed-provider default.
-- `models`: the configured model catalog and allowlist for `/model`. Each entry can include `alias` (shortcut) and `params` (provider-specific, for example `temperature`, `maxTokens`, `cacheRetention`, `context1m`, `responsesServerCompaction`, `responsesCompactThreshold`, `extra_body`/`extraBody`).
+- `models`: the configured model catalog and allowlist for `/model`. Each entry can include `alias` (shortcut) and `params` (provider-specific, for example `temperature`, `maxTokens`, `cacheRetention`, `context1m`, `responsesServerCompaction`, `responsesCompactThreshold`, `chat_template_kwargs`, `extra_body`/`extraBody`).
   - Safe edits: use `openclaw config set agents.defaults.models '<json>' --strict-json --merge` to add entries. `config set` refuses replacements that would remove existing allowlist entries unless you pass `--replace`.
   - Provider-scoped configure/onboarding flows merge selected provider models into this map and preserve unrelated providers already configured.
   - For direct OpenAI Responses models, server-side compaction is enabled automatically. Use `params.responsesServerCompaction: false` to stop injecting `context_management`, or `params.responsesCompactThreshold` to override the threshold. See [OpenAI server-side compaction](/providers/openai#server-side-compaction-responses-api).
 - `params`: global default provider parameters applied to all models. Set at `agents.defaults.params` (e.g. `{ cacheRetention: "long" }`).
 - `params` merge precedence (config): `agents.defaults.params` (global base) is overridden by `agents.defaults.models["provider/model"].params` (per-model), then `agents.list[].params` (matching agent id) overrides by key. See [Prompt Caching](/reference/prompt-caching) for details.
 - `params.extra_body`/`params.extraBody`: advanced pass-through JSON merged into `api: "openai-completions"` request bodies for OpenAI-compatible proxies. If it collides with generated request keys, the extra body wins; non-native completions routes still strip OpenAI-only `store` afterward.
+- `params.chat_template_kwargs`: vLLM/OpenAI-compatible chat-template arguments merged into top-level `api: "openai-completions"` request bodies. For `vllm/nemotron-3-*` with thinking off, OpenClaw automatically sends `enable_thinking: false` and `force_nonempty_content: true`; explicit `chat_template_kwargs` override those defaults, and `extra_body.chat_template_kwargs` still has final precedence.
 - `embeddedHarness`: default low-level embedded agent runtime policy. Omitted runtime defaults to OpenClaw Pi. Use `runtime: "pi"` to force the built-in PI harness, `runtime: "auto"` to let registered plugin harnesses claim supported models, or a registered harness id such as `runtime: "codex"`. Set `fallback: "none"` to disable automatic PI fallback. Explicit plugin runtimes such as `codex` fail closed by default unless you set `fallback: "pi"` in the same override scope. Keep model refs canonical as `provider/model`; select Codex, Claude CLI, Gemini CLI, and other execution backends through runtime config instead of legacy runtime provider prefixes. See [Agent runtimes](/concepts/agent-runtimes) for how this differs from provider/model selection.
 - Config writers that mutate these fields (for example `/models set`, `/models set-image`, and fallback add/remove commands) save canonical object form and preserve existing fallback lists when possible.
 - `maxConcurrent`: max parallel agent runs across sessions (each session still serialized). Default: 4.

docs/providers/openai.md

@@ -829,6 +829,7 @@ the Server-side compaction accordion below.
     - Use looser compat behavior
     - Strip Completions `store` from non-native `openai-completions` payloads
     - Accept advanced `params.extra_body`/`params.extraBody` pass-through JSON for OpenAI-compatible Completions proxies
+    - Accept `params.chat_template_kwargs` for OpenAI-compatible Completions proxies such as vLLM
     - Do not force strict tool schemas or native-only headers
 
     Azure OpenAI uses native transport and compat behavior but does not receive the hidden attribution headers.

docs/providers/vllm.md

@@ -82,6 +82,7 @@ Use explicit config when:
 - vLLM runs on a different host or port
 - You want to pin `contextWindow` or `maxTokens` values
 - Your server requires a real API key (or you want to control headers)
+- You connect to a trusted loopback, LAN, or Tailscale vLLM endpoint
 
 ```json5
 {
@@ -91,6 +92,7 @@ Use explicit config when:
         baseUrl: "http://127.0.0.1:8000/v1",
         apiKey: "${VLLM_API_KEY}",
         api: "openai-completions",
+        request: { allowPrivateNetwork: true },
         models: [
           {
             id: "your-model-id",
@@ -126,6 +128,45 @@ Use explicit config when:
 
   </Accordion>
 
+  <Accordion title="Nemotron 3 thinking controls">
+    vLLM/Nemotron 3 can use chat-template kwargs to control whether reasoning is
+    returned as hidden reasoning or visible answer text. When an OpenClaw session
+    uses `vllm/nemotron-3-*` with thinking off, OpenClaw sends:
+
+    ```json
+    {
+      "chat_template_kwargs": {
+        "enable_thinking": false,
+        "force_nonempty_content": true
+      }
+    }
+    ```
+
+    To customize these values, set `chat_template_kwargs` under the model params.
+    If you also set `params.extra_body.chat_template_kwargs`, that value has
+    final precedence because `extra_body` is the last request-body override.
+
+    ```json5
+    {
+      agents: {
+        defaults: {
+          models: {
+            "vllm/nemotron-3-super": {
+              params: {
+                chat_template_kwargs: {
+                  enable_thinking: false,
+                  force_nonempty_content: true,
+                },
+              },
+            },
+          },
+        },
+      },
+    }
+    ```
+
+  </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:
 
@@ -137,6 +178,7 @@ Use explicit config when:
             baseUrl: "http://192.168.1.50:9000/v1",
             apiKey: "${VLLM_API_KEY}",
             api: "openai-completions",
+            request: { allowPrivateNetwork: true },
             models: [
               {
                 id: "my-custom-model",
@@ -167,6 +209,10 @@ Use explicit config when:
     ```
 
     If you see a connection error, verify the host, port, and that vLLM started with the OpenAI-compatible server mode.
+    For explicit loopback, LAN, or Tailscale endpoints, also set
+    `models.providers.vllm.request.allowPrivateNetwork: true`; provider
+    requests block private-network URLs by default unless the provider is
+    explicitly trusted.
 
   </Accordion>