Execute Experiment
execute_experimentExecute shell commands inside an isolated sandbox to safely install, build, test, and explore, protecting your host from unwanted side effects.
Instructions
Run a shell command inside a sandbox.
USE THIS for anything you would otherwise run in the developer's terminal: installs, builds, scripts, migrations, one-off exploration. The command runs in the container, never on the host.
RETURNS exit code, stdout, stderr and duration. A non-zero exit is a normal result, not an error -- read it and decide what to try next.
Set background=true for something long-running, then poll get_job_status and fetch get_job_result when it finishes. Otherwise this waits, bounded by the timeout, so it cannot hang your session.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| command | Yes | Shell command. Runs via /bin/sh in the workspace. | |
| timeout | No | Seconds before the command is killed. Defaults to the experiment's. | |
| workdir | No | Working directory. Must be inside the workspace. | |
| background | No | Return a job id immediately instead of waiting. | |
| experiment_id | Yes | The experiment to run in. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| error | No | ||
| job_id | Yes | ||
| status | Yes | ||
| stderr | No | ||
| stdout | No | ||
| command | Yes | ||
| exit_code | No | ||
| duration_ms | No | ||
| experiment_id | Yes | ||
| stderr_truncated | No | ||
| stdout_truncated | No |