docs/tools/code-execution.md
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.
| Property | Value |
|---|---|
| Tool name | code_execution |
| Provider plugin | xai (bundled, enabledByDefault: true) |
| Auth | xAI auth profile, XAI_API_KEY, or plugins.entries.xai.config.webSearch.apiKey |
| Default model | grok-4-1-fast |
| Default timeout | 30 seconds |
Default maxTurns | unset (xAI applies its own internal limit) |
This is different from local exec:
exec runs shell commands on your machine or paired node.code_execution runs Python in xAI's remote sandbox.Use code_execution for:
x_search or web_search.Do not use it when you need local files, your shell, your repo, or paired devices. Use exec for that.
```bash
export XAI_API_KEY=xai-...
```
Or via config:
```json5
{
plugins: {
entries: {
xai: {
config: {
webSearch: {
apiKey: "xai-...",
},
},
},
},
},
}
```
```json5
{
plugins: {
entries: {
xai: {
config: {
codeExecution: {
enabled: true,
model: "grok-4-1-fast", // override the default xAI code-execution model
maxTurns: 2, // optional cap on internal tool turns
timeoutSeconds: 30, // request timeout (default: 30)
},
},
},
},
},
}
```
`code_execution` shows up in the agent's tool list once the xAI plugin re-registers with `enabled: true`.
Ask naturally and make the analysis intent explicit:
Use code_execution to calculate the 7-day moving average for these numbers: ...
Use x_search to find posts mentioning OpenClaw this week, then use code_execution to count them by day.
Use web_search to gather the latest AI benchmark numbers, then use code_execution to compare percent changes.
The tool takes a single task parameter internally, so the agent should send the full analysis request and any inline data in one prompt.
When the tool runs without auth, it returns a structured missing_xai_api_key error pointing at the auth-profile, env var, and config options. The error is JSON, not a thrown exception, so the agent can self-correct:
{
"error": "missing_xai_api_key",
"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.",
"docs": "https://docs.openclaw.ai/tools/code-execution"
}
x_search first and pipe the result into code_execution.