Push Call Context

curl --request POST \
  --url https://api.agentline.cloud/v1/calls/{call_id}/context \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{}'

import requests

url = "https://api.agentline.cloud/v1/calls/{call_id}/context"

payload = {}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({})
};

fetch('https://api.agentline.cloud/v1/calls/{call_id}/context', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>",
      "input": "<unknown>",
      "ctx": {}
    }
  ]
}

Calls

Push Call Context

Push context into a LIVE relay-mode call (mid-call context injection). This is the required way for backend agents (Hermes, OpenClaw, etc.) to answer a live caller after a ``call.utterance`` event. Do your work, then POST facts here — do NOT only send the answer to WhatsApp/SMS/chat. AUTHENTICATION (one of): 1. **Push token** (preferred — no API key): the ``push_token`` from the ``call.utterance`` payload, via ``X-Push-Token`` header, ``?token=`` query param, or ``push_token`` body field. 2. **Bearer API key**: ``Authorization: Bearer al_live_...`` for the account that owns the call. Body — any of these keys works (``context`` is canonical): {"context": "the facts/answer the voice agent should speak"} Other accepted keys: ``summary``, ``answer``, ``response``, ``message``, ``reply``, ``text``, ``result``. Returns: delivered=true, status="live" — voice agent will speak it now delivered=true, status="buffered" — caller moved on; held for their next question (late pushes are NOT rejected) HTTP 410 — **call has ended.** STOP working on this request and abandon any in-flight lookup. No further context will be spoken.

POST

calls

{call_id}

context

Push Call Context

curl --request POST \
  --url https://api.agentline.cloud/v1/calls/{call_id}/context \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{}'

import requests

url = "https://api.agentline.cloud/v1/calls/{call_id}/context"

payload = {}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({})
};

fetch('https://api.agentline.cloud/v1/calls/{call_id}/context', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>",
      "input": "<unknown>",
      "ctx": {}
    }
  ]
}

Authorizations

Authorization

string

header

required

AgentLine API key. Get one via the email OTP flow (POST /v1/auth/otp then POST /v1/auth/verify). Pass as: Authorization: Bearer sk_live_...

Headers

X-Push-Token

string | null

Path Parameters

call_id

string

required

Query Parameters

token

string | null

Push token (alt to X-Push-Token header / body).

Body

application/json

The body is of type Body · object.

Response

Successful Response

⌘I

Voice

Agents

Billing

Calls

Events

Messages

Numbers

Webhooks

Push Call Context

Authorizations

Headers

Path Parameters

Query Parameters

Body

Response