run_command
Execute a shell command in the workspace root and return its standard output, standard error, and exit code. Use for running tests, linters, formatters, and build steps in automated pipelines.
Instructions
Execute a shell command in the workspace root and return stdout, stderr, exit code.
Use this for running tests (pytest, playwright), linters (black, ruff), formatters, build steps, or any other shell command the pipeline needs to execute hands-free. Intended for use by pipeline agents, not general chat.
Windows note: Do NOT use pytest-xdist parallel flags (-n auto, -n N) in
commands passed to this tool. Worker subprocesses inherit stdout/stderr pipe
handles and can prevent the tool from returning if a worker exits abnormally.
Use plain pytest tests/ -q instead.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| command | Yes | Shell command to run (e.g. ".venv/Scripts/pytest tests/ -q"). Executed in the workspace root directory with shell=True. | |
| timeout | No | Seconds before the process is killed. Default 60s. Maximum 600s. Increase for slow test suites or Playwright runs, but prefer splitting large suites into smaller targeted runs. | |
| max_output_chars | No | Truncate combined output to this many characters to avoid flooding the context window. Default 20000. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||