List Sessions
const url = 'https://agents.lumalabs.ai/v1/sessions?limit=25';const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};
try { const response = await fetch(url, options); const data = await response.json(); console.log(data);} catch (error) { console.error(error);}curl --request GET \ --url 'https://agents.lumalabs.ai/v1/sessions?limit=25' \ --header 'Authorization: Bearer <token>'Keyset-paginated list of the caller's sessions, newest first.
Scoped to the token's (client_id, client_user_id) pair — the same
boundary get_session_or_404 enforces, so the list returns exactly the
sessions this token could already read one by one. Widening it to the
whole client would hand one end-user's JWT the session ids and tags of
every sibling end-user, which is the cross-user leak the pair-check
exists to close.
?metadata.<key>=<value> may repeat; the filters AND together and are
matched by JSONB containment, so a session carrying extra tags still
matches.
Authorizations
Section titled “Authorizations”Parameters
Section titled “ Parameters ”Query Parameters
Section titled “Query Parameters”Responses
Section titled “ Responses ”Successful Response
Keyset-paginated session list (GET /v1/sessions). See ListScopesResponse.
object
One row of GET /v1/sessions — the cheap fields only.
Deliberately not a SessionSnapshotResponse: a list must not pay for
the per-row message peek turn_running needs, and a partner scanning
pages does not want every plan artifact inlined. Fetch
GET /v1/sessions/{id} for the live view of one session.
object
object
Example
{ "data": [ { "state": "active" } ]}Validation Error
object
object
object
Examplegenerated
{ "detail": [ { "ctx": {}, "input": "example", "loc": [ "example" ], "msg": "example", "type": "example" } ]}