gate_action
Gate an action before execution by signing the decision and returning APPROVED, DENIED, or PENDING_APPROVAL. Supports AI agent governance and multi-party authorization.
Instructions
Pre-execution gate; signs the decision and returns APPROVED, DENIED, or PENDING_APPROVAL. After an APPROVED gate, call complete_action(gate_id, result) to close the bilateral receipt.
Args:
action_type: The action to gate (e.g. "data:delete:users", "tool:execute:sql")
agent_id: The agent requesting the action
tool_name: Optional name of the tool being invoked
arguments: Optional JSON string of the tool arguments
risk_context: Optional description of why this action is risky
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| action_type | Yes | ||
| agent_id | Yes | ||
| tool_name | No | ||
| arguments | No | ||
| risk_context | No |
Output Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |