harness: delegate.

Words, in a strategy to response cards, as they come, and a task where the work goes on

Request body#

The request body is DelegateInput.

Response#

The route returns a card whose body is Task. Every card ends with a foot that states the basis of each number, the scope of the call, and the time when the facts were true. This route runs as a long step and returns a task with status 202. POST /v1/work/status returns the task’s progress, and POST /v1/work/cancel stops the task.

Headers#

A caller needs the strategy rung and a token with the work grant. The platform serves this route.

Example#

The example sends the smallest body that DelegateInput allows. The build validates it against the schema of DelegateInput.

curl -X POST https://api.scaleintelligence.co/v1/harness/delegate \
  -H "Scale-Key: $SCALE_KEY" -H "Scale-Scope: tenant/<id>" \
  -H "content-type: application/json" \
  -d '{ "words": "…" }'

import { client } from "@scale/sdk";
const answer = await client.harness.delegate({
    "words": "…"
  });
// answer.body is a Task. answer.foot holds the basis, the scope and the time.

import requests
answer = requests.post("https://api.scaleintelligence.co/v1/harness/delegate",
    headers={"Scale-Key": KEY, "Scale-Scope": "tenant/<id>"},
    json={
      "words": "…"
    }).json()

let answer: Card = client.post("https://api.scaleintelligence.co/v1/harness/delegate")
    .header("Scale-Key", key).header("Scale-Scope", "tenant/<id>")
    .json(&DelegateInput { /* the fields of the page */ }).send().await?.json().await?;

MCP tool#

The MCP tool si.harness.delegate takes the same input and returns the same card. The tool changes data and needs a grant. An MCP host that renders cards draws this card from ui://scale-intelligence/cards/Task. The tool’s page describes it.

POST /v1/harness/delegate
Scale-Scope: …
Scale-As-True-On: …
Scale-As-Known-On: …
Scale-Key: …
content-type: application/json

{
  "words": "…"
}