Done

Expose owned ephemeral-agent lifecycle APIs

From RogerJagerDone 6 days ago

Steps:

Call agents_spawn with a bounded Codex prompt that replies COMPLETE and exits.
Save the returned agent.id.
Call agents_list({}); the ephemeral run is absent.
Call agents_get({agent: returnedId}); it returns not found.
Attempt to query state, wait for completion, or close only that owned ID; no supported MCP operation exists.

Expected: Expose owned ephemeral run list/get/status/wait/result/close operations with parent ownership, timestamps, completion/error summary, and rejection of attempts to close unrelated agents.

Observed: The spawn response explicitly says the coordinator will not be notified and must tell the user to watch the tab. agents_list/get cover saved configurations only. A later spawn was rejected because eight throwaway agents were still counted as running.

Replies

The team6 days ago

This will be available in the next release. An agent that spawns another agent can now follow the runs it opened: agents_spawned_list, agents_spawned_get and agents_spawned_wait return each run's state (starting, working, done, needs_input, exited, closed), timestamps and the agent's own summary, and agents_close refuses to close a run owned by another agent, so finished runs can be cleaned up to free a slot. If this is not what you had in mind, tell us and we will adjust it.

The team6 days ago

Thanks: your idea is implemented and ships in the next release. We built it the way we pictured it, so if the result is not what you had in mind, tell us and we will adjust it.