get_run_output

Retrieve a single named output from a completed model run. Use this instead of get_run when you only need one output and want to avoid the 1 MiB truncation cliff for large multi-tab runs. Resolves run_id using full UUID or UUID prefix. Requires a successful run status. Returns: run_id (str); project_name (str); output_name (str) — the name you requested; resolved_output_name (str) — the key that was found; content (any) — the output value (JSON, text, or base64 depending on encoding); encoding (str) — ‘json’, ‘text’, or ‘base64’; size_bytes (int) — byte size of the underlying data; truncated (bool) — always false (over-cap outputs raise an error); resolution_path (str) — ‘literal’, ‘scaffold’, or ‘ambiguous_literal’.

read-only · idempotent

Parameters

Name	Type	Required	Default	Description
run_id	str	Yes	—
output_name	str	Yes	—
encoding	str	No	'auto'

Returns

Returns a structured object. Top-level fields:

• run_id (string)
• project_name (string)
• output_name (string)
• resolved_output_name (string)
• content (array<object>)
• encoding (string)
• size_bytes (integer)
• truncated (boolean)
• resolution_path (string)

See the response example below for the full payload shape.

Example

Tool Call

{
  "name": "get_run_output",
  "arguments": {
    "run_id": "66666666-6666-6666-6666-666666666666",
    "output_name": "revenue",
    "encoding": "auto"
  }
}

Response

{
  "run_id": "66666666-6666-6666-6666-666666666666",
  "project_name": "forecasts",
  "output_name": "revenue",
  "resolved_output_name": "revenue",
  "content": [
    {
      "month": "2026-01",
      "revenue": 100
    },
    {
      "month": "2026-02",
      "revenue": 110
    }
  ],
  "encoding": "json",
  "size_bytes": 78,
  "truncated": false,
  "resolution_path": "literal"
}

Notes

• Module: Execution
• Requires authentication via API token or Auth0 JWT.