List all tasks

Updated:

GET/genai/{connection_id}/task

Returns a list of GenaiTasks. Narrow the results with the query parameters before paging, then page through them with limit and offset (the default and maximum page size depend on the integration). Use fields to return only the fields you need and reduce the response size. When the integration supports a total count, it is returned in the X-Total-Count response header. Use each item's id to retrieve, update, or delete it where those operations are supported.

Parameters

limitnumber default=100
offsetnumber default=0
updated_gtedate-time
Return only results whose updated date is equal or greater to this value (ISO-8601 / YYYY-MM-DDTHH:MM:SSZ format)
sort enum
order enum
querystring
Query string to search. eg. email address or name
status enum
agent_idstring
The agent ID to filter by
fieldsstring array
Fields to return
rawstring
Raw parameters to include in the 3rd-party request. Encoded as a URL component. eg. raw parameters: foo=bar&zoo=bar -> raw=foo%3Dbar%26zoo%3Dbar
connection_idstring required
ID of the connection

Returns

idstring
created_atdate-time
(ISO-8601 / YYYY-MM-DDTHH:MM:SSZ format)
updated_atdate-time
(ISO-8601 / YYYY-MM-DDTHH:MM:SSZ format)
namestring
A short human-readable title for the coding agent task.
instructionsstring
The natural-language instructions given to the coding agent.
status enum
Valid values:
"PENDING"
"RUNNING"
"BLOCKED"
"COMPLETED"
"FAILED"
model_idstring
user_idstring
(reference to HrisEmployee)
repo_urlstring
The git repository that the coding agent works in.
source_branch_identifierstring
The name of the branch that the coding agent starts its work from.
target_branch_identifierstring
The name of the branch that the coding agent pushed its work to.
pullrequest_urlstring
The pull/merge request that the coding agent opened for its work.
web_urlstring
The provider's own web page for this task.
messages array
The conversation between the user and the coding agent.
summarystring
The coding agent's summary of the work that it performed.
errorstring
The failure description (when the status is FAILED).
files_changednumber
lines_addednumber
lines_deletednumber
tokens_usednumber
started_atdate-time
When the coding agent started working on the task. (ISO-8601 / YYYY-MM-DDTHH:MM:SSZ format)
completed_atdate-time
When the coding agent stopped working on the task. (ISO-8601 / YYYY-MM-DDTHH:MM:SSZ format)
agent_idstring
id of the genai_agent (the reusable agent/preset configuration) that runs this task.
organization_idstring
id of the genai_organization (the organization or execution environment) that this task runs under.

Errors

Errors return the HTTP status code and a JSON body with statusCode, error (the short label) and message (a human-readable detail).

{
  "statusCode": 429,
  "error": "Too Many Requests",
  "message": "Too many requests to unified.to API; max requests per minute: N"
}
StatusErrorMeaning
400Bad RequestThe request was malformed or failed validation.
401UnauthorizedThe connection is likely broken; re-authorize it.
403ForbiddenThe connection is missing permissions or scopes.
404Not FoundThe requested resource does not exist.
429Too Many RequestsRate limit exceeded (see the two sources below).
500Internal Server ErrorAn unexpected error occurred.
501Not ImplementedNot supported by this integration.

Errors from the underlying integration pass through: the integration's status comes back as ours (429, 401, 403, 404 or 5xx), usually with its message. When the integration's error body is unclear, Unified extracts what it can and returns a clearer message.

429 Too Many Requests

A 429 has two possible sources:

  • The integration's own rate limit, passed through.
  • Unified's workspace limit: a rolling 60 seconds, set by plan, with the message Too many requests to unified.to API; max requests per minute: N.
const options = {
  method: 'GET',
  url: 'https://api.unified.to/genai/5de520f96e439b002043d8dc/task',
  headers: {
    authorization: 'bearer .....'
  },
  params: {
    limit: 50,
    offset: 0,
    updated_gte: '2026-01-01T00:00:00.000Z',
    sort: 'updated_at',
    order: 'asc',
    query: '',
    status: '',
    agent_id: '',
    fields: '',
    raw: '',
  }
};

const results = await axios.request(options);
Are we missing anything? Let us know
Was this page helpful?