List Agent Run Checkpoints
Checkpoint boundaries
Checkpoints are derived from the stored transcript. checkpoint_id is a 1-based display identifier; message_index is a transcript cut count used by continue_from. For example, checkpoint "1" can refer to message index 4. Use the returned message boundary, rather than the display identifier, for continuation. Listing or reading a checkpoint does not create a separate durable checkpoint record.
GET
/agents/{agent_id}/runs/{run_id}/checkpointsList FE-friendly continuation boundaries derived from the current stored run. No separate checkpoint table is used; entries are inferred from message-level checkpoint markers and the terminal end of the transcript.
Authorization
HTTPBearer AuthorizationBearer <token>
In: header
Path Parameters
agent_id*Agent Id
run_id*Run Id
Query Parameters
session_id*Session Id
Session ID for the run
Response Body
application/json
application/json
application/json
application/json
application/json
application/json
curl --request GET 'https://example.com/agents/string/runs/string/checkpoints?session_id=string'null{ "detail": "string", "error_id": "string", "error_type": "string"}{ "detail": "string", "error_id": "string", "error_type": "string"}{ "detail": "string", "error_id": "string", "error_type": "string"}{ "detail": "string"}{ "detail": "string", "error_id": "string", "error_type": "string"}