Hands Delegated Run
alterlab_hands_runHands supplies structure, verification and execution; your own model supplies drafts and decisions, and no platform model is called. action=create starts a run from a goal (mode preview runs the loop in a throwaway context and never commits; mode run commits after verification and policy). action=advance sends facts you found (each with its sources), a batch of actions to execute, or finish. A contradicted fact blocks the run until it is found again. When the approval policy asks, the run is awaiting_user with a pending_request to relay to the user; reply with action=answer. action=status returns the run and action=events returns events after a seq cursor (the same stream the CLI and the Playground Studio read).
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "alterlab_hands_run"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| act | No | Advance: the batch to execute, as for alterlab_task_act | |
| goal | No | Create: the goal in the user's words | |
| mode | No | Create: default run | |
| after | No | Events: return events with seq greater than this | |
| facts | No | Advance: facts you found, each with evidence | |
| graph | No | Create: optional task graph you propose; validated, never executed as given | |
| action | No | Default create | |
| answer | No | Answer: the user's words for a question | |
| finish | No | Advance: you are done; ends the run with a receipt | |
| inputs | No | Create: values the goal needs | |
| run_id | No | Required for advance, answer, status and events | |
| target | No | Create: what the run acts on | |
| decision | No | Answer: for an approval | |
| policy_ref | No | Create: approval-policy label the run's actions match | |
| request_id | No | Answer: the pending request id |