Messages, Up next and steering.

The session view

The conversation is on the left. The panel on the right has these tabs.

Any member of the workspace can send messages in any session. Each message also tells the agent which page the Preview is showing, so "this page" means what you are looking at. When the sandbox is paused, sending a message starts it again.

Send a message

1. Type in the composer. Press Shift+Enter for a new line.
2. To add files, press Attach files or drag them onto the composer. You can also paste an image.
3. Press Enter or the send button.

Type / to open the menu of skills and commands. In a Codex session, type $ instead. See Skills.

Attachments

Some models read fewer kinds of file:

The composer refuses a file the model cannot read and says why. If you switch to such a model, those files stay in your draft and the send is held until you remove them or pick a model that can read them.

Up next

A message you send while the agent is working joins Up next, the list above the composer. When the running turn ends, the message at the top starts the next turn. Messages go one turn at a time, in list order. A message sent while a Runtime Command runs also waits Up next and starts its turn after the command finishes.

Every member sees the same Up next, and it keeps sending after you close the tab.

Only a message's author can edit, move or steer it. The author or a workspace owner or admin can delete it. Up next holds up to 20 messages.

Sync starts an ordinary turn, so it also waits in Up next while the agent is working.

When Up next pauses

In these cases Up next pauses instead of sending.

To restart it, send a new message. It goes out at once, and Up next carries on after its turn. Any member can restart it this way.

Moving a task to Completed, Archived or Backlog empties its Up next.

Steer the running turn

Steering adds your message to the turn that is already running. The agent changes course without starting over.

1. Send your message while the agent works. It joins Up next.
2. Press Steer now, the arrow on your message's row.

To steer as you send, press ⌘Enter (Ctrl+Enter on Windows and Linux) or ⌘-click the send button. The message passes through Up next and goes straight on into the running turn. When the turn cannot take a steer, the message stays in Up next like any other.

Steer now and the shortcut work only when all of these are true:

• The running turn is your own, started by a message you sent.
• The message is yours.

If the turn ends before it takes your message, the message goes back to the top of Up next.

Stop a turn

Press Stop, the square button in the composer, or press Esc. The agent stops where it is, and Up next pauses. Send a message, or press Send now on one of your own messages in Up next, to carry on.

Answer a Clarification

Sometimes the agent asks a Clarification before it goes on. It appears in the transcript, one tab per question, and the turn ends. The task's card on the Tasks page shows "Your turn" to the session's Assignee.

1. On each question tab, pick an option. To write your own answer, pick Other and type it.
2. Open the Summary tab to check your answers. Add anything else under Extra information (optional).
3. Press Submit answers. It appears once every question has an answer.

Your answers go to the agent as your next message, and it carries on. You can also type a reply in the composer instead.

Clear or compact the conversation

Two commands in the skills menu act on the agent's memory of the session. They are marked Runtime. Neither starts a turn. Commands sent during a turn wait in Up next and run automatically in list order. In a Codex session, $clear and $compact work as well as /clear and /compact.

Codex compacts without a prompt, so in a Codex session the text after $compact stays in the conversation's history as a note, which Codex may not follow.

While a Runtime Command runs, the composer stays open and names what is happening, such as "Compacting the conversation". Press Enter to put a message Up next. It goes out after the command finishes. The composer offers no Stop or steering during the command, including ⌘Enter (Ctrl+Enter on Windows and Linux). If the command fails, Up next pauses.

You can edit, move or delete a queued command. Commands cannot be steered into a running turn. A command also waits while another command runs, and follows the same pause rules as other messages.

The messages stay on screen either way. After /clear, the agent remembers nothing said before it. The branch and the files in the sandbox are unchanged.

Watch the context

The ring beside Attach files shows how full the model's context window is. Hover over it to see the tokens used. It turns red at 90%. When it gets close to full, run /compact or /clear.

See what subagents are doing

When the agent starts helper agents, a row of their icons appears in the chat. Press it to open Agent activity. It lists the helpers as Active, Failed, Stopped or Done. Pick one to read its own conversation, and press Back to the main chat to return.

In a chat session, every helper is a Delegated Run. On Subscriptions or workspace Credentials, a helper that names neither a provider nor a provider to avoid runs on the turn's own model and effort, at every level. If that provider reached its limit or cannot take the helper, the helper does not start and the agent reads why. A helper that names a provider, or one to avoid, such as a review or a QA test, gets its model from its level. On Subscriptions or workspace Credentials, the row names the helper and its model, such as "reviewer (Opus 5.5, xHigh)" for a Hard helper, and the chat header names the model while you read it. On Free, helpers always use their parent Turn’s model and Source, even when the agent names another provider or level. Their model, Source and provider stay hidden in the chat, run lists and results. If the Source reaches its limit, is paused or is removed, Sensei moves the work to another Source running the same model, or stops it when none is available. The agent cannot start subagents of its own here. Crons and the deploy agent still can.

The agent can steer a helper that is still running: its message reaches the helper at its next step, or joins its prompt when the helper is still queued, and it shows in the helper's conversation as a new message. When a helper has finished, the agent can continue it. That starts a new run that resumes the helper's session on the same model, so it keeps what it read and did, and it shows in the same row with its prompt as a new message. A helper can be continued while its session is still on the sandbox, also in a later turn, and one run at a time. When it cannot, for example after the sandbox was replaced, the agent starts a new helper and gives it the earlier output.

A helper has no time limit while it works. When a helper shows no activity for 25 minutes, its row says how long it has been quiet and what it did last, and the agent decides to steer it, stop it or wait. A long build or test can be quiet that long. Sensei stops a helper by itself only after 3 hours. A helper stopped that way keeps its session, so the agent can continue it.

When a turn fails

A banner above the composer says the turn failed and why. Press Try Again to send your last message again. When the banner offers Reconnect or Fix it instead, the provider needs attention first. For workspace work, ask an admin to fix workspace Credentials. For personal work, fix your Subscription, or use Sensei free if you hold none. Reassigning never supplies personal Subscriptions to workspace work. See AI providers.

Under Review, Completed and Archived sessions

An Under Review session takes your messages and stays Under Review: the message goes out as it would in an Active session, and the pull request stays ready. When the agent changes the pull request, it turns it back into a draft first, and the session follows GitHub to Active. A sync alone keeps it ready. Above the composer, a banner reads "Ready for review. Send a message or Resume to keep working." It links to the pull request by its number. Press Resume to turn the pull request back into a draft without sending anything.

Completed and Archived sessions take no messages. To work on an archived session, restore it. See Chat sessions and tasks.

Next steps

• Preview and sandboxes
• Review the changes
• Models