GET `/api/v1/ai-log`

AI interactions (metadata; inputs and outputs are on the AI log page).

Scope ai_log:read
operationId recordsAiLog

The token needs the scope ai_log:read, and the person or service account behind it needs the matching privileges and account permissions, exactly as on the screens. See Scopes.

Paginated. Cursor pagination: limit (1 to 200, default 50); pass next_cursor as cursor until has_more is false. fields= returns only the named fields.

Request

GET /api/v1/ai-log

Query parameters

Name	Required	Description
`limit`	no	Page size, 1 to 200 (default 50)
`cursor`	no	The next_cursor of the previous page
`sort`	no	"-id" (newest first, default) or "id"
`fields`	no	Sparse fieldset: comma-separated field names
`purpose`	no	Purpose
`client`	no	OAuth client_id

Headers

Header	Required	Value
`Authorization`	yes	`Bearer <token>`: an OAuth access token (`vat_…`) or a personal access token (`vpt_…`). Get a token

Examples

Keep the token in an environment variable (VESTORIS_TOKEN), never in the script.

curl

curl "https://vestoris.com/api/v1/ai-log" \
  -H "Authorization: Bearer $VESTORIS_TOKEN"

Python (requests)

import os, requests

r = requests.get(
    "https://vestoris.com/api/v1/ai-log",
    headers={
        "Authorization": f"Bearer {os.environ['VESTORIS_TOKEN']}",
    },
    timeout=30,
)
r.raise_for_status()  # errors are application/problem+json with a stable "code"
print(r.json())

JavaScript (fetch)

const res = await fetch("https://vestoris.com/api/v1/ai-log", {
  method: "GET",
  headers: {
    Authorization: `Bearer ${process.env.VESTORIS_TOKEN}`,
  },
});
const data = await res.json();
if (!res.ok) throw new Error(`${data.code}: ${data.detail}`); // problem+json
console.log(data);

Response

200 OK, application/json: a page of AiInteraction. Rate-limit headers: RateLimit-Limit, RateLimit-Remaining, RateLimit-Reset.

Response fields

Field	Type	Description
`data`	list of AiInteraction	The records of this page.
`data[].id`	id (string)	The record's id (a string of digits).
`data[].user_id`	id (string) or null	The user.
`data[].client_id`	string or null	The OAuth client id behind the token (null for personal access tokens).
`data[].purpose`	string	What the AI was used for.
`data[].model`	string	The model.
`data[].fallback`	boolean	True when the deterministic fallback answered instead of the AI.
`data[].ok`	boolean	Ok.
`data[].error`	string or null	The error, when it failed.
`data[].latency_ms`	integer	How long the AI call took, in milliseconds.
`data[].input_tokens`	integer	Tokens sent to the model.
`data[].output_tokens`	integer	Tokens the model answered.
`data[].input_sha256`	string	SHA-256 of what was sent to the AI.
`data[].output_sha256`	string or null	SHA-256 of what the AI answered.
`data[].created_at`	date-time or null	When it was created.
`next_cursor`	string or null	Pass as ?cursor= for the next page; null on the last page.
`has_more`	boolean	True when another page follows.

Example response

HTTP/1.1 200 OK
Content-Type: application/json

{
    "data": [
        {
            "id": "1042",
            "user_id": "7",
            "client_id": null,
            "purpose": "copilot",
            "model": "claude-sonnet",
            "fallback": false,
            "ok": true,
            "error": null,
            "latency_ms": 840,
            "input_tokens": 1820,
            "output_tokens": 240,
            "input_sha256": "c9d0…",
            "output_sha256": null,
            "created_at": "2026-10-27T14:30:00Z"
        }
    ],
    "next_cursor": "eyJpZCI6NTI5OX0",
    "has_more": true
}

Example values. Your values depend on your firm's data; prices, orders and fills are simulated.

Status codes and errors

Errors are application/problem+json (RFC 9457) with a stable code to program against; the detail says what to fix. See Errors.

Status	When	Problem codes
200	Success
400	The request is malformed	`invalid_request`
401	No token, or it is invalid or expired	`invalid_token`
403	The token lacks the scope, or the person or service account behind it lacks the privilege or account permission	`insufficient_scope` `forbidden` `ip_not_allowed`
429	Rate limited: wait for Retry-After seconds	`rate_limited`

{
    "type": "https://vestoris.com/developers/errors#validation_failed",
    "title": "Validation failed",
    "status": 422,
    "detail": "Quantity must be greater than zero.",
    "code": "validation_failed",
    "instance": "/api/v1/ai-log"
}

On the screens

The same thing in the app is explained in: