Skip to main content
Get the session state and counts for bugs and agent verdicts. Add --full for the findings and latest message.

Arguments

string
required
The session to inspect.

Output

By default, the command prints:
--full replaces counts with findings.bugs and findings.verdicts arrays. It also adds latestMessage (null when unavailable). Bugs are limited to the main agent. Verdicts are the signed-off outcomes from sub-agents. displayState is the session’s state as the UI shows it: needs_you, running, waiting_on_agents, failed_start, cancelled, ready, or sleeping. It is the field to prefer. state is a legacy alias of sessionState, and both carry the lifecycle state (starting, working, waitingOnUser, waitingOnAgents, idle, or stopped). Servers running an earlier API report the display word in state instead. qa read and qa report report the identical displayState, so scripts can compare the commands directly. completed is the root agent’s explicit completion flag. It is not inferred from verdicts or a turn ending. Mo clears it when resuming work. Older servers omit it; an absent flag does not establish completion. Check displayState as well for active work, blockers, or input Mo needs.

Examples

List bug names:
Poll a session until it stops running, then list the bugs it found:

Notes