---
title: "Resume an AI Assistant turn waiting on your approval"
method: POST
path: "/assistant/chat/conversations/{conversation_id}/messages/{sequence}/resume/"
tags: ["assistant"]
---

# Resume an AI Assistant turn waiting on your approval

`POST /assistant/chat/conversations/{conversation_id}/messages/{sequence}/resume/`

## Request

- Base URL: `https://api.getoneprofile.ai` (the document declares no server; this is the origin it was published from)
- URL: `https://api.getoneprofile.ai/assistant/chat/conversations/{conversation_id}/messages/{sequence}/resume/`
- Auth: HTTP bearer

Continue the turn whose reply sits at `sequence` and is `waiting`, once every card it raised has been approved or declined. Streams the same frames as sending a message: `delta` frames carrying the whole reply so far, a `said` frame when a later round starts writing, then one `result`, or another `approval` if the turn goes on to ask for something else.

Ends in an `error` frame with reason `not_found` when there is no waiting turn at that position, and an `error` frame with no reason while any of its cards is still undecided. Costs nothing against the workspace's allowance: the turn was claimed when it started.

## Path parameters

- `conversation_id` string, uuid, required
- `sequence` integer, required

## Response `200`

A stream of Server-Sent Events, ending in one `result`, `approval` or `error` frame.

## Other responses

- `401`: Unauthorized
- `403`: Forbidden
- `422`: Invalid request made to the API.
- `500`: Internal server error.
- `502`: Bad gateway error.
- `503`: Service unavailable.

---

[API](https://skmtc.dev/getoneprofile/apis/api-reference-oneprofile.md) · [All operations](https://skmtc.dev/getoneprofile/apis/api-reference-oneprofile/llms.txt) · [OpenAPI document](https://skmtc.dev/getoneprofile/apis/api-reference-oneprofile/revisions/dc5ac3c84444?raw)