Skip to main content
python_exec lets chat models calculate over queried health records, including comparisons across indicators, medications, genetics and pharmacogenomics. It receives the original data automatically, so the model does not need to copy values from a displayed table. A cloud model can write the code, but the code runs in a local Docker container.

​
Inputs and outputs

The code can use:
  • data: original rows from the latest successful, nonempty record query.
  • results: successful query results from the current turn, including metadata, assumptions, source information and tool-call IDs.
  • /workspace/data.json: the same data and results inside the calculation container. This is not a path for uploading or reading documents.
The current turn starts with the latest user question; automatic requests to repair an answer remain part of that turn. If the latest query fails or returns no rows, calculation is refused rather than using older data or substituting zero. Use query stats and time-bucket views for the aggregates they already provide. Code should print its result and source rids. The tool reports exit status, source-call IDs and incomplete inputs or output. Output is limited to 40,000 bytes; longer output is explicitly marked incomplete.

​
Local setup

For a source installation, install the application dependencies and download the calculation image:
Supported runtimes are Docker Desktop or Colima on macOS, and Docker Engine on Linux. The executor checks PYTHON_SANDBOX_DOCKER_HOST, DOCKER_HOST, /var/run/docker.sock, then the active Docker CLI context. Only local Unix sockets are accepted; TCP and SSH endpoints are rejected. The default image provides Python’s standard library. To add analysis packages, prepare a local image and set PYTHON_SANDBOX_IMAGE. Install its dependencies in advance: calculation containers have no network access.

​
When the app also runs in Docker

The app needs access to the host’s Docker daemon to start calculation containers. The optional compose-python.yaml mounts the management socket into the app, granting it permission to manage containers. This is opt-in; the main Compose file does not mount the socket. Calculation containers never receive it. Set PYTHON_DOCKER_SOCKET to the socket path on the Docker host and PYTHON_DOCKER_GID to its owning group ID, then run:
If the executor is unavailable, the tool reports a setup problem; existing query results remain valid. To hide the calculator, set DISALLOWED_TOOLS: [python_exec].

​
Execution limits

Calculation containers have no application mounts, database credentials or network. They run as UID/GID 65534 with a read-only image and temporary writable storage, limited to one CPU, 512 MB of memory and 64 processes. Commands have a 1–30 second deadline, with up to ten additional seconds for the host to wait. Timeout or cancellation closes the stream and removes the container; a finite lease and automatic removal also clean up abandoned runs. Only Python execution is exposed to the model, not a general shell tool. For implementation and validation details, see the calculation benchmarks and Deep Agents sandbox interface.