You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
@@ -333,7 +333,7 @@ See [/providers/kilocode](/providers/kilocode) for setup details.
333
333
Model ids use a `nvidia/<vendor>/<model>` namespace (for example `nvidia/nvidia/nemotron-...` alongside `nvidia/moonshotai/kimi-k2.5`); pickers preserve the literal `<provider>/<model-id>` composition while the canonical key sent to the API stays single-prefixed.
334
334
</Accordion>
335
335
<Accordiontitle="xAI">
336
-
Uses the xAI Responses path. `grok-4.3` is the bundled default chat model. `/fast` or `params.fastMode: true` rewrites `grok-3`, `grok-3-mini`, `grok-4`, and `grok-4-0709` to their `*-fast` variants. `tool_stream` defaults on; disable via `agents.defaults.models["xai/<model>"].params.tool_stream=false`.
336
+
Uses the xAI Responses path. The recommended path is SuperGrok/X Premium OAuth; API keys still work via `XAI_API_KEY` or plugin config. `grok-4.3` is the bundled default chat model. `/fast` or `params.fastMode: true` rewrites `grok-3`, `grok-3-mini`, `grok-4`, and `grok-4-0709` to their `*-fast` variants. `tool_stream` defaults on; disable via `agents.defaults.models["xai/<model>"].params.tool_stream=false`.
337
337
</Accordion>
338
338
<Accordiontitle="Cerebras">
339
339
Ships as the bundled `cerebras` provider plugin. GLM uses `zai-glm-4.7`; OpenAI-compatible base URL is `https://api.cerebras.ai/v1`.
Copy file name to clipboardExpand all lines: docs/tools/code-execution.md
+33-14Lines changed: 33 additions & 14 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -9,14 +9,14 @@ title: "Code execution"
9
9
10
10
`code_execution` runs sandboxed remote Python analysis on xAI's Responses API. It is registered by the bundled `xai` plugin (under the `tools` contract) and dispatches to the same `https://api.x.ai/v1/responses` endpoint used by `x_search`.
@@ -66,7 +83,9 @@ Do **not** use it when you need local files, your shell, your repo, or paired de
66
83
</Step>
67
84
68
85
<Steptitle="Enable and tune code_execution">
69
-
The tool is gated on `plugins.entries.xai.config.codeExecution.enabled`. Default is off.
86
+
`code_execution` is available when xAI credentials are available. Set
87
+
`plugins.entries.xai.config.codeExecution.enabled` to `false` to disable it,
88
+
or use the same block to tune the model and timeout.
70
89
71
90
```json5
72
91
{
@@ -124,7 +143,7 @@ When the tool runs without auth, it returns a structured `missing_xai_api_key` e
124
143
```json
125
144
{
126
145
"error": "missing_xai_api_key",
127
-
"message": "code_execution needs an xAI API key. Run openclaw onboard --auth-choice xai-api-key, set XAI_API_KEY in the Gateway environment, or configure plugins.entries.xai.config.webSearch.apiKey.",
146
+
"message": "code_execution needs xAI credentials. Run `openclaw models auth login --provider xai --method oauth` to sign in with Grok, run `openclaw models auth login --provider xai --method api-key`, set `XAI_API_KEY` in the Gateway environment, or configure `plugins.entries.xai.config.webSearch.apiKey`.",
0 commit comments