Weft
CA
Tasques · MCP

Ask the User a Question

request_input is one of the 32 MCP tools in Weft, the AI task manager you run by talking to Claude, Cursor, Codex or ChatGPT through one MCP endpoint. Ask the person something only they can decide, and wait without losing the claim on the task. If they are at their client, a form appears there and the answer comes back inside the same call — the agent carries on in the same context, with the same claim. If they are away, the call returns parked and the question waits in their queue; the answer reaches the agent at its next start_task or get_my_work. For the irreversible and the genuinely ambiguous, not for "may I continue?" — every question spends the same attention budget that limits new work.

Weft és el gestor de tasques amb IA per a fundadors en solitari i equips petits.

La referència de les eines es manté en anglès: els noms de les eines, els arguments i els exemples són idèntics en tots els idiomes.

Arguments

NomTipusObligatoriDescripció
idstringsíTask ID
runIdstringsíThe runId returned by start_task
leaseTokenstringsíThe leaseToken returned by start_task
questionstringsíOne sentence a person can answer (≤500 chars)
options{ value, label }[]noThe alternatives, when there are any. A question with options gets read; a yes/no gets rubber-stamped.
urgency'blocking' | 'soon'noDefault 'blocking'
holdSecondsnumbernoHow long to wait inside the call before parking (default 120, max 240)

Retorna

Either answered:true with the answer and the same runId/leaseToken to continue with, or parked:true with a questionId — the claim is kept either way, and a parked question is delivered back through start_task and get_my_work.

Anotacions

  • idempotent. Cridar l'eina dues vegades amb els mateixos arguments té el mateix efecte que cridar-la una sola vegada.

Exemple

El que diu l'usuari:

"Ask me before you send anything to a customer."

El que crida la IA internament:

json
{
  "name": "request_input",
  "arguments": {
    "id": "…",
    "runId": "…",
    "leaseToken": "…",
    "question": "Which discount should the email offer?",
    "options": [
      {
        "value": "10",
        "label": "10%"
      },
      {
        "value": "15",
        "label": "15%"
      }
    ]
  }
}

Relacionat