> ## Documentation Index
> Fetch the complete documentation index at: https://composio-preview.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Remote Workbench

> Use this persistent Jupyter sandbox only for remote files or scripted bulk tool executions

**Slug:** `COMPOSIO_REMOTE_WORKBENCH`

**Tags:** destructiveHint, openWorldHint

Runs Python in a persistent remote sandbox to process large remote files and script bulk or repeated tool executions.

## When to use it

Reach for `COMPOSIO_REMOTE_WORKBENCH` when data lives in a remote file rather than inline in the chat, when you need to run a known tool in bulk (for example, label 100 emails), or when you want to call an API via `proxy_execute` because no Composio tool exists for it.

> [!NOTE]
>
> State persists across calls like a Jupyter notebook, and helper functions such as `run_composio_tool` and `invoke_llm` are preloaded. There is a hard 3-minute execution limit per cell, so split work into steps and checkpoint intermediate results to `/mnt/files/`. Do not use it for data you can already see inline.

## Input parameters

**code\_to\_execute** `string` *required*

Python to run inside the persistent remote Jupyter sandbox. State (imports, variables, files) is preserved across executions. Keep code concise. Avoid unnecessary comments. Hard 3-minute (180s) execution limit — break large tasks into smaller cells.

**thought** `string`

Brief objective for this step.

**current\_step** `string`

Short enum for current step of the workflow execution. Eg FETCHING\_EMAILS, GENERATING\_REPLIES. Always include to keep execution aligned with the workflow.

**current\_step\_metric** `string`

Progress metrics for the current step - use to track how far execution has advanced. Format as a string "done/total units" - example "10/100 emails", "0/n messages", "3/10 pages".

**session\_id** `string`

Pass the session\_id if you received one from a prior COMPOSIO\_SEARCH\_TOOLS call.

## Response

**data** `object`

Data from the action execution

**properties**

**error** `string`

Error message if any

**results** `string`

The results of the code execution

**results\_file\_path** `string`

Path to file containing full results if output was truncated

**session** `object`

Session info echoed back to reinforce reuse: \{ id: string, instructions: string }

**properties**

**id** `string`

**instructions** `string`

**stderr** `string`

The standard error output from the command

**stderr\_file\_path** `string`

Path to file containing full stderr if output was truncated

**stdout** `string`

The standard output from the command

**stdout\_file\_path** `string`

Path to file containing full stdout if output was truncated

**sandbox\_id\_suffix** `string`

Last 4 digits of the sandbox ID for easier reference

**error** `string`

Error if any occurred during the execution of the action

**successful** `boolean`

Whether or not the action execution was successful or not
