Inputs

What each operation takes: its path and query parameters and its body, as one object.

Properties

Property	Type	Description
`agents.list`	`object`	-
`agents.list.agents?`	`string`[]	The agents to cover, by ID, given once for each. Each covers its conversations too. Every agent you may see unless set.
`agents.forget`	`object`	-
`agents.forget.agents?`	`string`[]	The agents to cover, by ID, given once for each. Each covers its conversations too. Every agent you may see unless set.
`interrupts.list`	`object`	-
`interrupts.list.agents?`	`string`[]	The agents to cover, by ID, given once for each. Each covers its conversations too. Every agent you may see unless set.
`events.list`	`object`	-
`events.list.agents?`	`string`[]	The agents to cover, by ID, given once for each. Each covers its conversations too. Every agent you may see unless set.
`events.list.types?`	`string`[]	The event types to read, as wardrik.run.completed, given once for each. Every type where left out. A wardrik.events.dropped comes whatever the types.
`events.list.after?`	`string`	The cursor to read after: a page's next, the id of an event a stream gave, or a snapshot's cursor.
`events.list.limit?`	`number`	How many to read, 100 unless set.
`events.head`	`object`	-
`events.head.agents?`	`string`[]	The agents to cover, by ID, given once for each. Each covers its conversations too. Every agent you may see unless set.
`agent.read`	`object`	-
`agent.read.agent`	`string`	The agent's ID, as your app chose it, in one URL-encoded path segment.
`agent.read.conversation?`	`string`	The conversation to act on. The agent's own history where left out.
`agent.define`	`object` & `AgentDefinition`	-
`agent.forget`	`object`	-
`agent.forget.agent`	`string`	The agent's ID, as your app chose it, in one URL-encoded path segment.
`agent.ask`	`object` & `Ask1` & `Ask2`	-
`agent.decide`	`object` & `Decisions`	-
`agent.authorization`	`object`	-
`agent.authorization.agent`	`string`	The agent's ID, as your app chose it, in one URL-encoded path segment.
`agent.authorization.interrupt`	`string`	The id of the call the agent waits on.
`agent.authorization.conversation?`	`string`	The conversation to act on. The agent's own history where left out.
`agent.cancel`	`object`	-
`agent.cancel.agent`	`string`	The agent's ID, as your app chose it, in one URL-encoded path segment.
`agent.cancel.conversation?`	`string`	The conversation to act on. The agent's own history where left out.
`agent.events`	`object`	-
`agent.events.agent`	`string`	The agent's ID, as your app chose it, in one URL-encoded path segment.
`agent.events.types?`	`string`[]	The event types to read, as wardrik.run.completed, given once for each. Every type where left out. A wardrik.events.dropped comes whatever the types.
`agent.events.after?`	`string`	The cursor to read after: a page's next, the id of an event a stream gave, or a snapshot's cursor.
`agent.events.limit?`	`number`	How many to read, 100 unless set.
`agent.events.conversation?`	`string`	The conversation to act on. The agent's own history where left out.
`agent.timeline`	`object`	-
`agent.timeline.agent`	`string`	The agent's ID, as your app chose it, in one URL-encoded path segment.
`agent.timeline.conversation?`	`string`	The conversation to act on. The agent's own history where left out.
`agent.runs`	`object`	-
`agent.runs.agent`	`string`	The agent's ID, as your app chose it, in one URL-encoded path segment.
`agent.runs.conversation?`	`string`	The conversation to act on. The agent's own history where left out.
`audit.list`	`object`	-
`audit.list.starting_after?`	`number`	The sequence to read after, a page's next.
`audit.list.limit?`	`number`	How many to read, 100 unless set.
`agent.approve`	`object` & `Approve`	-
`agent.deny`	`object` & `Deny`	-
`agents.cancel`	`object`	-
`agents.cancel.agents?`	`string`[]	The agents to cover, by ID, given once for each. Each covers its conversations too. Every agent you may see unless set.
`agent.definition`	`object`	-
`agent.definition.agent`	`string`	The agent's ID, as your app chose it, in one URL-encoded path segment.
`agent.spawn`	`object`	-
`agent.spawn.agent`	`string`	The agent's ID, as your app chose it, in one URL-encoded path segment.
`agent.stop`	`object`	-
`agent.stop.agent`	`string`	The agent's ID, as your app chose it, in one URL-encoded path segment.
`agent.stop.conversation?`	`string`	The conversation to act on. The agent's own history where left out.
`agent.clear`	`object`	-
`agent.clear.agent`	`string`	The agent's ID, as your app chose it, in one URL-encoded path segment.
`agent.clear.conversation?`	`string`	The conversation to act on. The agent's own history where left out.
`agent.calls`	`object`	-
`agent.calls.agent`	`string`	The agent's ID, as your app chose it, in one URL-encoded path segment.
`agent.calls.conversation?`	`string`	The conversation to act on. The agent's own history where left out.
`agent.kill`	`object`	-
`agent.kill.agent`	`string`	The agent's ID, as your app chose it, in one URL-encoded path segment.
`agent.kill.call`	`string`	The id of the tool call.
`agent.kill.conversation?`	`string`	The conversation to act on. The agent's own history where left out.
`agent.trigger_set`	`object` & `TriggerDefinition`	-
`agent.trigger_remove`	`object`	-
`agent.trigger_remove.agent`	`string`	The agent's ID, as your app chose it, in one URL-encoded path segment.
`agent.trigger_remove.trigger`	`string`	The trigger's name.
`deployment.reload`	`object`	-
`deployment.reload.agents?`	`string`[]	The agents to cover, by ID, given once for each. Each covers its conversations too. Every agent you may see unless set.
`deployment.nodes`	`object`	-
`agent.move`	`object` & `Node`	-