Skip to main content
Some work Patchwork cannot do. A step that must happen in your UI, on a device, or by a human is declared as a proposed_action patch. The agent proposes it, the run pauses in awaiting_outcome, and waits for you to say what happened. This is the mirror image of a confirmation: there we ask permission before acting, here you act and then report.

Finding a pending action

GET /v1/loom/threads returns pending_action on the thread:
args is what the agent proposed. Carry it out however your product does.

Reporting

detail is optional, recorded on the outcome, and passed to the model. A short structured reason produces a better next turn than a bare failed. The response is 202 and the run resumes.

Idempotent

Posting an outcome for a tool call that already has one returns success without doing anything. Safe to retry.

Errors