Gets the detailed trace of a specific execution.
Returns the full execution trace including all intermediate steps, tool calls, AI model interactions, and timing breakdowns.
Authorization
Bearer JWT Authorization header using the Bearer scheme. Enter 'Bearer' [space] and then your token.
In: header
Path Parameters
The unique identifier of the agent.
The execution record identifier.
The tenant identifier
Response Body
curl -X GET "https://api.fruxon.com/v1/tenants/string/agents/string/executionRecords/string/trace"{
"status": "IN_PROGRESS",
"trace": {
"agentExecutionRecordId": "00000000-0000-0000-0000-000000000000",
"agentId": "string",
"agentRevision": 0,
"startTime": 0,
"endTime": 0,
"traces": [
{
"id": "string",
"displayName": "string",
"type": "UNSPECIFIED",
"llmStepTrace": null,
"toolTrace": null,
"hitlTrace": null,
"steps": [],
"result": null,
"status": "UNSPECIFIED",
"error": "string",
"startTime": 0,
"endTime": 0,
"duration": 0
}
],
"createdAt": 0,
"tenantId": "00000000-0000-0000-0000-000000000000"
},
"parentExecutionRecordId": "00000000-0000-0000-0000-000000000000",
"parentAgentId": "string",
"parentAsyncOperationId": "00000000-0000-0000-0000-000000000000",
"rootExecutionId": "00000000-0000-0000-0000-000000000000",
"runType": "ROOT",
"occurredAt": 0,
"waitingFor": {
"kind": "string",
"participantId": "00000000-0000-0000-0000-000000000000",
"displayName": "string",
"participantKind": "PERSON",
"avatarFileId": "string",
"topicId": "00000000-0000-0000-0000-000000000000",
"approvalRequestId": "00000000-0000-0000-0000-000000000000",
"approvers": [
"string"
],
"childCount": 0,
"resumesAt": 0,
"attempt": 0,
"maxAttempts": 0,
"waitingSince": 0,
"expiresAt": 0
}
}{
"type": "string",
"title": "string",
"status": 0,
"detail": "string",
"instance": "string",
"property1": null,
"property2": null
}Lists execution sessions for an agent — one item per spawn tree, newest activity first.
The grouped counterpart of the flat list: each item is a whole session (a root run plus every sub-task and consult descending from it) collapsed to its root, carrying the same rollups the `/tree` endpoint computes — run count, failures, combined cost, wall-clock span. A session of one is just a run that spawned nothing. Filters apply at the run level and lift to the session: a session is returned when ANY of its runs matches, and `matchedRuns` reports how many did — so filtering by a tool error surfaces the whole session containing the hit, with its root for context. Rollups always cover the whole session regardless of the filter. Pagination counts sessions, not runs.
Gets the whole spawn tree this execution belongs to, in one request.
Returns every run descending from this execution's root — the run itself, whatever spawned it, and every sub-task or consult anywhere beneath — in pre-order with a depth on each node, plus rollups (run count, failures, combined cost, wall-clock span) computed across the tree. This is the whole-session view that `/children` can only serve one level at a time. Because the tree is resolved from the shared root rather than walked link by link, it is neither depth-capped nor truncated, and it does not lose the branches that belong to another agent — a consult child runs under the *consulted* agent, so a level-by-level walk from here cannot see it. Each node carries its own `agentId` for navigation. A run with no lineage returns a single-node tree, not an error.