Agent Status Tracking
- Desktop, mobile and web
- All plans
What it does
Every agent carries a live status you can read from anywhere in the app: Working (the agent is processing or editing, with an elapsed timer counting up), Done (it finished its turn; unread completions are highlighted), Needs input (it is blocked on a question or a permission, the most urgent state) and Idle (ready for a prompt). While an agent works, its card shows a short summary of what it is doing (editing a file, running tests). Projects aggregate their agents: the sidebar shows how many are working, done or waiting, so you can run a dozen agents across projects and always know who needs you first.
Video (1 min 11 s): Agent status tracking, shown in the real app. Three Claude Code agents work on one project: the list on the left files them under Needs you, To review and Working with the counters on top, the waiting agent's multiple-choice question is answered from the message box, and it goes back to work until nobody is waiting any more.
Where to find it
- Agent cards and terminal headers inside a project: colored dot, timer and activity summary.
- Sidebar: per-project badges (2 agents waiting for input, 3 unread agents) and, on hover, the last message of each agent.
- Agents rail: open agents grouped by what they need from you, Needs you, To review, Working, Waiting on an agent, Available, Done, above Inactive; each section shows its count and folds. Since 2026-10-06 every section folds, Needs you and Pinned included (a folded Needs you keeps its red header and its count, and its counter above the list still shows it), on the desktop and the phone alike; the conversation boxes between agents sit under their own foldable Conversations header. Three counters above the list (Needs you, To review, Working) filter it to that state, and Mark all as seen clears the To review pile. One agent at a time: right-click it (long-press on the phone) and pick Mark as seen, or Done to move it to the Done section, ticket or not. Each row reads « title » then « short role · last message »; an open agent with nothing to report says Ready and the title of its previous session.
- Next to an agent's title (card, console header, phone): a small pill with the live status the agent reports itself, such as Monitoring, CR loop or Blocked. It changes as the work moves on, while the title keeps naming the task.
- Title bar: the needs-input pill; Open Space and the Dynamic Island show the same states outside the project.
- End of the title line of an agent card (desktop room, detached window, phone): the time the agent finished, as soon as it has an open session and is not working (done or waiting for you):
14:32, or10 Nov, 14:32when it was not today. Its tooltip reads "Finished:" with the full date. On the phone the time comes before the age it already showed (14:32 · 16m). An agent with no session keeps its age only. - Session info panel on an agent: Status, how long it has been in that state, exchanges, tool uses, tokens.
How to use it
- Glance at the dot: pulsing means working, red pulsing means it waits for you, green means done, none means idle.
- Click a project badge or the needs-input pill to jump to the blocked agent and answer it.
- Use the elapsed timer to spot a step that runs unusually long, and the activity summary to see what it is doing without opening the terminal.
- To answer an agent that asked a multiple-choice question in its terminal, open it (its row under Needs you) and type the number of the option in the message box ("Give your agent a prompt or a task"), then Enter: the agent goes back to Working.
Settings
notificationSoundandneedsInputSound(global, Settings > Notifications): sounds on the transitions to Done and Needs input.agentsBarMinAgents(global, account-synced, default 3, from 1 to 50): Settings > Interface elements > Project card counters > Show Running agents from. The Running agents counters only appear once the project has that many open agents; below that the list is short enough to read at a glance. The phone follows the same value. Hovering the Running agents (or Idea and planning) heading shows a gear that opens this card directly.
Agent tools (MCP)
agents_list_live: list the agents currently running with their status.agents_report_status: an agent publishes its own progress or blocking question so the status is accurate even when its output is hard to parse.agents_get: details of one agent, status included.
Providers
All providers. Status is detected from the terminal stream of each CLI (tool calls, file writes, prompts, completion) with per-provider rules; on a full-screen CLI the summary may be shorter. The "needs input" detection covers permission prompts and questions of every supported CLI.
Mobile
Yes. The phone shows the same statuses and colors on agent rows and terminal screens. Swipe an agent row to the left for Seen (on an unread agent) and Done, next to Close and Delete; long-press it for the same State menu as the desktop right-click. The Companion tab mirrors the global state (Idle, Working, Needs input) with a history of Done and Needs input events.
Limits
- The timer measures the current working step; it resets when the agent finishes or changes state.
- The activity summary depends on what the CLI prints; a silent tool call shows no summary.
- Statuses are per machine; another desktop's agents appear through Remote Fleet.
- The agent you are looking at never drops down the list while it stays open, so its row does not jump out of sight. An agent you opened from To review stays there, and an agent that finishes its turn while you watch it moves up to To review (never kept under Working: that section only lists turns in progress). Open another agent and it moves down to Available.
Common questions
-
Why don't I see the Running agents counters? They only show once the project has 3 open agents (the default). Change the number in Settings > Interface elements > Project card counters, or hover the row heading and click the gear. Set it to 1 to always see them.
-
How is the status detected? Each agent runs in a real terminal and AgentsRoom reads its output continuously for tool calls, questions and completion signals.
-
Several agents need input at once? Each shows its own red dot; the project badge gives the count, and the needs-input pill lists them so you can answer in any order.
-
Why is an agent "Done" but highlighted? You have not looked at it since it finished: the highlight is the unread marker.
-
When did this agent finish? Since 2026-11-11 its card shows the time, at the end of its title line, on the desktop and the phone, in your system's 12 or 24 hour format. Hover it for the full date.
-
Can I see status on my phone? Yes, the mobile app syncs the same statuses over the encrypted relay.
-
How do I see which of my agents needs me? Look at the agent list on the left of the project: agents waiting for an answer are grouped under Needs you (red), finished ones under To review (green), busy ones under Working (orange), and the three counters at the top ("Running agents") give the numbers. A video shows it: https://youtu.be/ucfUVsuAac0
-
Why is an agent under Waiting on an agent instead of To review? Its turn ended with the ball in a colleague's court: it asked another agent for a review or an answer and stops until it replies, or it handed its result back to the agent that asked for it. Nothing is waiting for you, so it gets no notification and no To review badge, and its row says who it waits on (« Waiting on Paul »). The agent says so itself in its session file, or AgentsRoom reads it from Agent Mail (a message to a colleague that has not answered yet); a question for you always wins. When the colleague answers, the agent works again and lands in To review once it has something for you. Same section and badge on the phone and in the Open space (where its column only shows while it holds an agent). Reported by Pirmax, 2026-10-27.
-
Can an agent show where it stands, not only what it works on? Yes. Besides its title (set on the first turn and kept for the whole conversation, so a follow-up question never renames it), an agent can write a short
statusin its session file, such as "Monitoring", "CR loop" or "Blocked". It shows as a small pill next to the title on the agent card, the console header and the phone, and changes whenever the agent rewrites it; an empty value hides it. The card keeps a single status pill: when the agent also waits on a colleague, its pill shows an hourglass and the tooltip says who it waits on. Agents use it for work that goes through stages over several turns; ask yours to keep it up to date ("keep your status at Monitoring / CR loop / Approved"). Requested by Tiago, 2026-11-06. -
Why is the agent I am reading under To review? It is the agent you have open: its turn is over and its row stays in sight while you watch it, even though it is already read. Open another agent and it moves down to Available. Since 2026-11-13 an agent that finishes while you watch it goes to To review instead of staying under Working, which only counts agents actually running a turn.
-
My first agent shows Needs input before I typed anything. What does it want? The CLI is showing a first-run screen in its terminal. For Claude Code and Antigravity, the line under the agent's name says what to do: choose a text style with the arrow keys then Enter, read the Bypass Permissions warning and choose whether to accept, type /login to sign in to Claude, choose a sign-in method, or complete the sign-in opened by the CLI. Open the agent and answer in its terminal; the usual summary comes back once the screen is gone.
-
My agent said Ready but nothing was happening in its terminal. Fixed on 2026-10-20: an agent whose CLI did not start (not installed, an option it refuses, an immediate exit) now shows Needs input with "<CLI> did not start: the terminal shows why.", and so does a Claude Code agent stopped on its question about which MCP servers of the project to enable, or (on Windows) on its Bypass Permissions warning. Open the agent and read or answer the terminal.
-
I selected an agent and the middle of the window only shows a spinner. Its console is still starting; it appears as soon as it is ready. If it takes too long, the message turns to "Still not started" with a Restart the agent button, which relaunches it so you can see what is blocking it.
-
Can my own dashboard or status bar read these statuses? Yes, through the read-only Local status API (Settings > Dev tools), which serves them as versioned JSON on this computer.
-
Is there a video that shows it? Yes, a little over a minute, filmed in the real app: https://youtu.be/ucfUVsuAac0
Related
- Needs Input Inbox: the list of agents waiting for you.
- Agent Notifications: alerts fired on Done and Needs input.
- Dynamic Island: the floating global state.
- Open Space: every agent of every project on one screen, sorted by urgency.
- Local status API: the same statuses read by your own tools (status bars, terminal dashboards).