Rumatadocs
Browse documentation

Chat, sessions, models, and file controls

Choose a conversation and model, give the assistant context, queue instructions, and navigate its replies.

Step-by-step guidance.

Before you start

  • Open the named screen in Rumata. Available controls may depend on your account, permissions, and resource state.

Sessions and conversation navigation

A session is a conversation with its own history. The assistant still works in the same factory.

ControlWhat it does
Main agent / session rowOpen that conversation. The selected row is highlighted.
Sub-agent rowInspect a child conversation created by the assistant. Its indentation identifies its parent.
New Session / Create session / plusOpen a dialog for a new conversation.
Session name / Create SessionEnter a name of up to 120 characters, then create the session. The name cannot be empty.
Rename session / Save NameRename a main session. Child sessions do not show the same rename action.
Cancel / dialog XClose the create or rename dialog without applying the pending name.
LatestJump to the newest messages.
Previous user messages markersJump back to one of your earlier prompts.
ForkCreate a new session branching from that point in the conversation.
Name a new conversation before creating it. This blank form was cancelled without creating a session.

Prompt, mode, model, and queue

Describe the outcome you want in everyday language. Technical users can add exact files, interfaces, and acceptance criteria.

ControlWhat it does
Take screenshotWhen supported by the browser, choose a display source and capture a PNG as a pending attachment. The capture stream stops afterward. Review the image for private data and send the prompt separately; capture alone does not submit it.
Message field / Enter / Shift+EnterWrite your request. Enter sends it; Shift+Enter inserts a new line.
Plan / Build / agent selectorChoose an available assistant mode. Plan develops an approach for review; Build carries out changes. Available choices depend on the factory’s agent runtime.
Model selectorChoose a model from the available provider groups. Connected providers appear first; the image icon identifies models with image input support.
Default / Current / Use runtime default labelCheck which model is in use when you haven’t selected one explicitly. The label can reflect factory settings or the session’s current model.
SendSubmit the prompt, selected references, attachments, and command. While a response is running, a new message can enter the Up next queue.
StopAsk the assistant to stop its current response. It appears while work is running and the composer is empty. Changes already made are not rolled back.
Up next → Move back to composerRemove that instruction from the pending queue and return it to the input for editing.
Up next → SteerSend a queued instruction into the current response when the runtime supports steering.

Files, skills, and commands

A reference points the assistant to existing project context. A local attachment supplies a file from your computer.

ControlWhat it does
@ / Search skills or files…Open and search the reference picker from the message field.
File or skill resultAdd the selected reference to the pending prompt. Choosing a reference alone does not send the prompt.
Reference chip → XRemove that reference from the pending prompt.
/ / Search commands…Find commands available in the current agent runtime. Read the description before selecting one.
Command result / Arguments fieldSelect a command, then provide the arguments it expects. Send executes the selected command.
Command chip → XRemove the selected command. If the command was typed directly in the message rather than picked, this action clears that typed prompt.
Add to chat → Upload from computerChoose up to six local files for the prompt. Each prepared attachment must fit within 1 MiB; non-image files above that limit are rejected.
Attachment chip → XRemove a file from the unsent prompt. Selecting files does not upload them into the factory’s storage bucket.

Read replies and tool activity

Expandable activity cards explain what the assistant attempted and what the tool returned.

ControlWhat it does
Copy below a messageCopy the message text.
Tool activity / reasoning / task-list disclosureExpand or collapse details such as input, output, errors, reasoning text, or the assistant’s task list. Expanding does not rerun the tool.
Preview telemetry disclosureInspect preview network and console context attached to the conversation.
Image attachmentOpen a larger image view. Close the dialog to return to the chat.
Other file attachmentOpen its file link in a new tab.
Recognized workspace file linkOpen that file in Code, at the supplied position when available. Code access depends on the plan and project setup state.
MCPs ConnectedInspect the services available to the assistant and whether each is connected, disabled, failed, or needs authentication or registration.