Workflows and apps
Execution trace
Everything needed to debug one run offline: the trigger input, the run record, the logs, and the step-by-step thread.
GET
https://cloud.generalinput.com/v1/workflows/:id/executions/:executionId/traceAuthenticationRequires
workflows:manage on a personal API key. A CLI session always passes.The bundle the CLI writes to disk with geni workflow execution --download. For an agent workflow, thread is the agent's conversation, every tool call and result.
Response
{
"id": "exec_01HX…",
"workflowId": "wf_01HX…",
"status": "failed",
"error": "Slack 429: rate limited",
"startedAt": "2026-09-03T10:00:02.000Z",
"completedAt": "2026-09-03T10:03:11.000Z",
"input": { "days": 7 },
"run": null,
"logs": "…",
"thread": [
{
"role": "assistant",
"type": "tool-call",
"content": { "name": "bash", "args": {} },
"createdAt": "…"
},
{ "role": "tool", "type": "tool-result", "content": "…", "createdAt": "…" }
]
}| Field | Notes |
|---|---|
input | The trigger payload that started the run. |
thread | Steps for a code run, the agent conversation for an agent run. type is text, tool-call, or tool-result. |