Solo tracks agent state so you can tell which agents are working, idle, waiting for permission, or blocked by an error.
How it works
Solo uses a mix of signals:
- Built-in agents each get a strategy suited to how they behave. Claude, OpenCode, Copilot, Kimi, and Antigravity are tracked by their visible output. Codex and Amp are considered busy while their terminal title keeps changing, and Gemini reports its status through its terminal title.
- Auto-summarization can also classify the agent — idle, waiting for permission, thinking, working, or stopped on an error — and Solo keeps that classification when it's available.
Summary timing
For summaries, Solo waits until a process has had human input and then watches output activity. A brief quiet window can trigger a summary after output stops. Continuously busy processes can also trigger summaries after a longer busy window.
The summary cadence setting is still enforced per process, so repeated activity does not produce unlimited summary attempts.
Timers
Agents can also set timers for themselves through Solo's MCP timer tools. An active pending timer adds a small timer icon to the sidebar process row; paused timers do not. Select the process to see its nearest timer in the terminal control bar, where active timers take precedence over paused timers. Click that terminal-control indicator to view the timer message, cancel it, fire it now, pause an active timer, or resume a paused timer.
When a timer fires, Solo delivers the timer message back to the owning process.
Limits
Idle detection is a heuristic. Some agents pause between steps before continuing on their own, and a quiet terminal is not always the same thing as completed work.