Skip to main content
Melso Agents is available only internally or by private invitation. Agents-specific features require existing access. For the autónomo fiscal service, see Get started.
A Run belongs to a Task. Follow-ups, manual reruns, automatic retries, Cloud lifetime rollovers and pauses create distinct Run IDs, so follow the Task’s Runs rather than one Run. Read one Run you already know with GET /api/runs/{runId}; list the Task’s Runs to find its successors, then fetch a Run’s events/messages. All resource paths below use UUIDs unless noted.

Find successor Runs

Start with GET /api/tasks/{id}/runs. Use the origin and company key from the API quickstart, then set the Task UUID you want to follow:
The response is a JSON array ordered by created_at descending (newest first). Equal creation timestamps have no guaranteed tie-break order. Read status on each attempt and follow any active successor; an older failed Run does not settle the Task’s outcome. Poll this Task-scoped route again or use the Task stream to discover later attempts. To read usage aggregated across the Task’s Runs:

API reference

Request fields, response types and endpoint permissions are defined in the Runs reference. See Pagination for list conventions, or start with the API quickstart.

RunResponse

RunResponse.status uses the complete Run status enum. The Runs endpoint reference defines the response, including the linked RunUsageData, RunAttribution and RunAccessReceipt schemas. Continue observing while any attempt is active. When none is, inspect the newest attempt: read the completed attempt’s stored assistant message, resolve a pause, or inspect the failure/cancellation reason. Do not treat an earlier failed attempt as the final outcome while a successor is active. An execution result, a closed Task and a filed tax return have different evidence requirements.