run
Unified execution tool for both project-level and model-level runs in sync or async mode. Discriminators: scope=‘project’|‘model’ and mode=‘sync’|‘async’. When scope=‘project’, omit model_name; when scope=‘model’, model_name is required. When mode=‘async’, a run_id is returned in pending state and you should poll get_run. When mode=‘sync’, terminal stdout/stderr/outputs are returned inline. Optional parameters are delivered as read-only /inputs/parameters.json, including an explicit empty object {}. Worked examples: 1) Project + sync: run(scope=‘project’, mode=‘sync’, project_name=‘acme’). 2) Model + sync with parameters: run(scope=‘model’, mode=‘sync’, project_name=‘acme’, model_name=‘revenue’, parameters={‘discount_rate’: 0.08}). 3) Project + async: run(scope=‘project’, mode=‘async’, project_name=‘acme’). 4) Model + async: run(scope=‘model’, mode=‘async’, project_name=‘acme’, model_name=‘revenue’). Returns: Sync mode returns terminal fields (status, exit_code, stdout, stderr, outputs, duration_seconds, run_id). Async mode returns queued-run fields (run_id, run_number, status=‘pending’, project_name, model_name, commit_sha, message, warning).
Parameters
Section titled “Parameters”| Name | Type | Required | Default | Description |
|---|---|---|---|---|
scope | Literal['project', 'model'] | Yes | — | |
mode | Literal['sync', 'async'] | Yes | — | |
project_name | str | Yes | — | |
model_name | `str | None` | No | None |
branch | `str | None` | No | None |
commit_sha | `str | None` | No | None |
parameters | `dict[str, Any] | None` | No | None |
Returns
Section titled “Returns”Returns a structured object. Top-level fields:
run_id(string)project(string)branch(null)commit_sha(string)status(string)exit_code(integer)stdout(string)stderr(string)stdout_truncated(boolean)stderr_truncated(boolean)outputs(object)duration_seconds(number)data_snapshot_ref(null)error(null)
See the response example below for the full payload shape.
Example
Section titled “Example”Tool Call
Section titled “Tool Call”{ "name": "run", "arguments": { "scope": "project", "mode": "sync", "project_name": "forecasts", "parameters": { "discount_rate": 0.08 } }}Response
Section titled “Response”{ "run_id": "66666666-6666-6666-6666-666666666666", "project": "forecasts", "branch": null, "commit_sha": "abc1234def5678901234567890abcdef12345678", "status": "success", "exit_code": 0, "stdout": "Run completed in 1.42s\n", "stderr": "", "stdout_truncated": false, "stderr_truncated": false, "outputs": { "revenue": [ 100, 110, 121 ] }, "duration_seconds": 1.42, "data_snapshot_ref": null, "error": null}- Module:
Execution - Requires authentication via API token or Auth0 JWT.