Implementation:Openai Openai python Response Function Shell Tool Call Output

Knowledge Sources	Openai_Openai_python OpenAI API Reference
Domains	API_Types, Responses_API
Last Updated	2026-02-15 00:00 GMT

Overview

Concrete response type representing the output of a shell tool call, provided by the openai-python SDK.

Description

ResponseFunctionShellToolCallOutput is a Pydantic model representing the output produced by a shell tool call. It contains an id for the output item, a call_id linking back to the originating shell tool call, an optional max_output_length (generated by the model and passed back with raw output), a list of Output items each containing stdout, stderr, an outcome (either OutputOutcomeTimeout or OutputOutcomeExit with an exit_code), and an optional created_by field. The top-level model also has a status field and a fixed type of "shell_call_output". This type is auto-generated from the OpenAI OpenAPI specification by Stainless.

Usage

Import ResponseFunctionShellToolCallOutput when constructing input items for a follow-up Responses API request that provides the results of previously executed shell commands back to the model.

Code Reference

Source Location

• Repository: openai-python
• File: src/openai/types/responses/response_function_shell_tool_call_output.py

Signature

class ResponseFunctionShellToolCallOutput(BaseModel):
    """The output of a shell tool call that was emitted."""

    id: str
    call_id: str
    max_output_length: Optional[int] = None
    output: List[Output]
    status: Literal["in_progress", "completed", "incomplete"]
    type: Literal["shell_call_output"]
    created_by: Optional[str] = None

Import

from openai.types.responses import ResponseFunctionShellToolCallOutput

I/O Contract

Fields

Name	Type	Required	Description
id	str	Yes	The unique ID of the shell call output.
call_id	str	Yes	The unique ID of the shell tool call generated by the model.
max_output_length	Optional[int]	No	The maximum length of the shell command output, generated by the model.
output	List[Output]	Yes	An array of shell call output contents.
status	Literal["in_progress", "completed", "incomplete"]	Yes	The status of the shell call output.
type	Literal["shell_call_output"]	Yes	The type of the output. Always "shell_call_output".
created_by	Optional[str]	No	The identifier of the actor that created the item.

Output Sub-Type

Name	Type	Required	Description
outcome	OutputOutcome	Yes	Either an exit outcome (with exit_code) or a timeout outcome.
stderr	str	Yes	The standard error output that was captured.
stdout	str	Yes	The standard output that was captured.
created_by	Optional[str]	No	The identifier of the actor that created the item.

Outcome Sub-Types

Type	Fields	Description
OutputOutcomeTimeout	type: Literal["timeout"]	Indicates the shell call exceeded its configured time limit.
OutputOutcomeExit	exit_code: int, type: Literal["exit"]	Indicates the shell commands finished and returned an exit code.

Usage Examples

from openai.types.responses import ResponseFunctionShellToolCallOutput

# Inspect shell call output from a response
for item in response.output:
    if isinstance(item, ResponseFunctionShellToolCallOutput):
        print(f"Shell output for call {item.call_id}")
        for output in item.output:
            print(f"  stdout: {output.stdout}")
            print(f"  stderr: {output.stderr}")
            if output.outcome.type == "exit":
                print(f"  exit code: {output.outcome.exit_code}")
            elif output.outcome.type == "timeout":
                print("  Command timed out")

Related Pages

• Environment:Openai_Openai_python_Python_3_9_Plus