feat(openai): add websocket warm-up with configurable toggle

docs/concepts/model-providers.md

@@ -45,6 +45,7 @@ OpenClaw ships with the pi‑ai catalog. These providers require **no**
 - CLI: `openclaw onboard --auth-choice openai-api-key`
 - Default transport is `auto` (WebSocket-first, SSE fallback)
 - Override per model via `agents.defaults.models["openai/<model>"].params.transport` (`"sse"`, `"websocket"`, or `"auto"`)
+- OpenAI Responses WebSocket warm-up defaults to enabled via `params.openaiWsWarmup` (`true`/`false`)
 
 ```json5
 {

docs/providers/openai.md

@@ -68,6 +68,9 @@ You can set `agents.defaults.models.<provider/model>.params.transport`:
 - `"websocket"`: force WebSocket
 - `"auto"`: try WebSocket, then fall back to SSE
 
+For `openai/*` (Responses API), OpenClaw also enables WebSocket warm-up by
+default (`openaiWsWarmup: true`) when WebSocket transport is used.
+
 ```json5
 {
   agents: {
@@ -85,6 +88,47 @@ You can set `agents.defaults.models.<provider/model>.params.transport`:
 }
 ```
 
+### OpenAI WebSocket warm-up
+
+OpenAI docs describe warm-up as optional. OpenClaw enables it by default for
+`openai/*` to reduce first-turn latency when using WebSocket transport.
+
+### Disable warm-up
+
+```json5
+{
+  agents: {
+    defaults: {
+      models: {
+        "openai/gpt-5": {
+          params: {
+            openaiWsWarmup: false,
+          },
+        },
+      },
+    },
+  },
+}
+```
+
+### Enable warm-up explicitly
+
+```json5
+{
+  agents: {
+    defaults: {
+      models: {
+        "openai/gpt-5": {
+          params: {
+            openaiWsWarmup: true,
+          },
+        },
+      },
+    },
+  },
+}
+```
+
 ### OpenAI Responses server-side compaction
 
 For direct OpenAI Responses models (`openai/*` using `api: "openai-responses"` with