Ellipsis APIReferenceSessions

Get Agent Session Records

Return the session's stored transcript records. Pagination is opt-in (after_seq/limit — the same feed_seq cursor as the stream); a bare call returns the full retained transcript. Available to sandbox tokens too: an agent answering "did X look into Y?" needs to read the session it found via /sessions/search, and any org member sees the same transcript in the dashboard (laptop transcripts are redacted client-side before they are ever uploaded).

GET
/v1/sessions/{session_id}/records

Return the session's stored transcript records.

Pagination is opt-in (after_seq/limit — the same feed_seq cursor as the stream); a bare call returns the full retained transcript. Available to sandbox tokens too: an agent answering "did X look into Y?" needs to read the session it found via /sessions/search, and any org member sees the same transcript in the dashboard (laptop transcripts are redacted client-side before they are ever uploaded).

Authorization

HTTPBearer
AuthorizationBearer <token>

In: header

Path Parameters

session_id*Session Id

Query Parameters

after_seq?After Seq
Default0
limit?|null

Header Parameters

user-agent?string|null

Response Body

application/json

application/json

curl -X GET "https://example.com/v1/sessions/string/records"
{  "earliest_feed_seq": 0,  "has_more": false,  "messages": [],  "records": [    {      "agent_session_id": "string",      "agent_turn_id": "string",      "cost": 0,      "created_at": "2019-08-24T14:15:22Z",      "duration": 0,      "feed_seq": 0,      "id": "string",      "model": "string",      "payload": {},      "record_format": "string",      "record_type": "string",      "session_message_id": "string",      "source": "lifecycle",      "stream_seq": 0,      "tokens_info": {        "cache_creation_input_tokens": 0,        "cache_read_input_tokens": 0,        "cost_usd": 0,        "input_tokens": 0,        "num_turns": 0,        "output_tokens": 0      },      "tools": [        "string"      ]    }  ]}