API
List runs
Runs across the workspace, newest first, without their transcripts.
GET/task-runs
Runs the real call on your workspace.
GET /task-runs
Runs across the workspace, newest first, without their transcripts.
Example
Needs tasks:read, threads:read and emails:read. taskId narrows the list to one task and status to one state. limit goes up to 100 and defaults to 25.
curl "$OE/task-runs?taskId=tsk_4b9e2c7a1f3d86e05a9c2b7d&status=waiting" -H "$AUTH"{ "object": "list", "data": [{ "object": "task_run", "id": "run_9d3a7e1c5b2f48a60c7e1d3b", "taskId": "tsk_4b9e2c7a1f3d86e05a9c2b7d", "taskName": "Morning summary", "trigger": "schedule", "threadId": null, "status": "waiting", "instruction": "Go through the mail that arrived since yesterday. Tell me which conversations need a reply from me, most urgent first, and draft a short reply for each.", "autonomy": "organize", "model": "standard", "steps": 4, "toolCalls": 6, "actions": 1, "result": null, "error": null, "errorDetail": null, "pendingApprovals": 1, "createdAt": "2026-10-13T07:00:04.112Z", "startedAt": "2026-10-13T07:00:05.870Z", "finishedAt": null }], "hasMore": false, "nextCursor": null}taskId and taskName are null for a run started with POST /task-runs.
trigger says what started it: schedule, mail or manual. For mail, threadId is the conversation that arrived.
steps counts how often the model was asked what to do next, toolCalls the tools that ran, and actions the AI actions the run cost.