Messages and context

Give the agent a task in the composer. Add files, quote a previous response, or include a skill when the task needs more context.

Messages can contain up to 120,000 characters. Longer drafts stay in the composer so you can shorten them or split them into several messages.

Pasting 32 KiB or more of text adds that fragment as a text-file attachment so the agent can inspect it without filling the model context. A smaller paste also becomes an attachment when inserting it would exceed the message limit. On a hardware keyboard, use Cmd+Shift+V on Apple devices or Ctrl+Shift+V elsewhere to keep a large paste editable in the composer instead.

Formatting

The composer writes Markdown and shows it styled as you type. Markers such as ** stay in the text and show beside the styled words when your cursor is on them. Lines starting with - , 1. , - [ ] , > , # or --- become lists, task lists, quotes, headings and rules; ``` followed by Enter opens a code block. What you typed is what the agent receives, markers and numbering included, and #1234 without a space still looks up a pull request.

Enter sends. In a list or quote, Shift+Enter continues it, and Shift+Enter on an empty line moves out one level, then leaves it; Tab nests a list item under the one above and Shift+Tab moves it back out. In a code block, Enter starts a new line at the current indentation, Tab and Shift+Tab indent the selected lines, and a closing ``` followed by Enter, or two blank lines at the end, leave the block. Backspace at the start of a code block turns it back into plain lines. Choose the language in a code block’s corner to change it. Very large code blocks are shown without syntax highlighting.

Attach files

Attach up to 100 files per message. Each image can be up to 10 MiB, with at most 80 MiB of images in one message. Other files, including videos, can be up to 50 MiB each, subject to the environment’s upload support and limit. The agent receives them on the environment’s machine. Provider and model limits still apply, including images already in the conversation. A video attachment gives the agent a file path; it does not enable native video input.

Uploads begin when you add an attachment. All uploads must finish before the message can send. Retry or remove a failed upload. On web and desktop, reloading before an upload finishes requires you to attach that file again.

You can drag or paste images into the web or desktop composer. HEIC and HEIF photos are converted to JPEG there and when selected from the mobile photo library; photos over the image limit are also resized to fit. On mobile, you can also send files to GOAT through another app’s system share sheet.

See images and videos for previewing and saving media.

Send while the agent is working

On web and desktop, choose Settings → General → Follow-up behavior to queue new messages for a later turn or steer the running turn immediately. The setting applies to this client; already queued messages keep their place. Queued messages are saved on the server and can be edited, reordered, or removed above the composer. When Enter sends, Cmd+Enter on macOS or Ctrl+Enter on Windows and Linux uses the opposite action: it steers when your default is Queue and queues when your default is Steer. If your Send shortcut requires Cmd+Enter or Ctrl+Enter, that shortcut uses your default follow-up behavior; add Shift to use the opposite action. This applies only to multiline messages when you choose the multiline send option.

Use Cmd+Shift+Enter on macOS or Ctrl+Shift+Enter on Windows and Linux to send the oldest queued message as a steer. This leaves the current draft intact and requires an active turn that supports steering. If that shortcut sends the opposite action for your draft, click elsewhere in the thread, outside the composer and any terminal, to steer the queued message. Change thread.steerQueuedMessage in Settings → Keybindings to use another shortcut.

Press Option+Up on macOS or Alt+Up on Windows and Linux with the cursor at the start of the composer to edit the most recently queued message. Change thread.editQueuedMessage to use another shortcut.

Mobile has the same choice under Settings → Follow-ups. While a turn is running the send button shows which action it will take. Long-press it to use the other action for a single message, or hold Cmd while sending from a hardware keyboard. The button only offers Steer when the running agent supports it.

Cloud tasks

Most cloud providers use the published remote branch and exclude local edits and unpushed commits; push first if you want those tasks to use them. Some also require a clean checkout of that pushed revision. Claude Cloud starts from the project folder and its current branch instead, and local changes may be included without publishing the branch. Check the provider’s source notice before sending.

Open the task or its returned pull request from the conversation. Cloud changes stay in the remote repository, so this thread has no local checkpoint or worktree to diff or rewind. Project files, editor and terminal still show your local source; they do not show cloud changes. Your task history keeps its summary and links.

Follow-ups use the same cloud conversation when supported. Otherwise the composer explains why another message cannot be sent. A task marked “Running in the cloud” with link-only tracking has been submitted; its link is the place to check progress. Restarting GOAT does not stop remote cloud work.

Queue messages offline on mobile

Mobile keeps local copies of draft attachments, so you can preview them and queue messages while disconnected. Uploads resume when you reconnect. Drafts and queued messages survive app restarts. Reconnect to the environment to send queued work.

Custom models

On web and desktop, use Settings → Providers → Models to add an unlisted model with a custom name and options. Only options supported by the provider integration affect turns. Antigravity uses its account catalog and does not support custom models.

To rename a built-in model on every client, edit the server’s settings.json in its userdata directory. Add a custom model entry with the built-in model ID and a new name under that provider instance:

{
  "providerInstances": {
    "codex": {
      "driver": "codex",
      "config": { "customModels": [{ "slug": "gpt-5.5", "name": "Team GPT" }] }
    }
  }
}

Model defaults

GOAT remembers your provider, model, and model options for new threads. A project’s configured model takes precedence; resetting that project setting returns to the remembered selection.

Leaving reasoning level or service tier unset uses the provider’s own configuration.

Model and reasoning on mobile

Tap the model button in the composer to open the reasoning popover. It shows the current reasoning level, the model it applies to, and a slider over the levels that model offers; a model without reasoning levels says so instead. Runtime and the model’s other options sit below the slider. Tap the model name to open the model picker, with favorites, search, provider filters, hidden models, and pull to refresh. Picking a model applies it right away.

Quote an assistant response

On web and desktop, select text within one assistant response and choose Cite in composer. You can add a comment about the quote and write instructions around it.

Select the quote in a draft or sent message to return to its source. If the source is unavailable or has changed, the saved quote remains readable.

The chip shows your comment when it has one, or a short quote preview otherwise. Use the pencil button to add or change the comment. To remove the citation, place the caret beside its chip and delete it like other inline context. Copying, reloading, and restoring a stashed prompt keep each comment with its quote, and sending tells the agent which words were quoted and which comment you wrote. The quoted text and comment count toward the message limit.

Mobile displays saved quotes and comments, but does not create citations or navigate to their sources.

Recall a sent prompt

Press ArrowUp in an empty composer to bring back the last prompt you sent in this thread. Press ArrowUp again to go further back, and ArrowDown to come forward. Moving forward past the newest prompt clears the composer. Recall walks the prompts loaded in the thread. Attachments, terminal context, and other extras from the original message are not restored, only the text you typed. A composer that holds an attachment or a picked element does not count as empty.

When the composer has text, the arrow keys move the caret as usual. Recall takes over only while the text is an unedited recalled prompt, with the caret on the first visual line for ArrowUp or the last visual line for ArrowDown, counting wrapped lines. Editing a recalled prompt turns it into a normal draft.

Edit an earlier prompt

On web and desktop, choose Edit from here beneath a sent message to rewind the conversation to before that message. Choose Revert and keep changes to leave workspace files as they are, or Revert files too to put the workspace back to its checkpoint from before that message. That also undoes edits you made yourself. File restore is only offered for threads running in a worktree, and it is refused when another thread or agent session also uses that directory, a folder inside it, or a folder that contains it, since restoring would erase their changes. A thread that works in the project directory rewinds the conversation only. The selected prompt and its attachments return to the composer for editing and resending. Any unsent draft stays above the restored prompt.

This removes the selected message and later conversation from the active thread and provider history. It does not undo external actions or separate provider memory. The action is available only when the provider supports rewind.

Prompt stash

On web and desktop, press Cmd+S on macOS or Ctrl+S on Windows and Linux to save the current prompt and its attachments for later. Wait for uploads to finish first. With an empty composer, the same shortcut restores a single stash or opens the stash menu when there are several.

Stashes containing uploaded files must be restored in their original environment. Those files are retained for 24 hours. After an upload expires, restore the prompt and use Attach again or remove the missing file before sending.

Voice input on iPhone

On supported iPhones with iOS 26 or later, use the composer’s microphone to record, then confirm to transcribe. Text is inserted where your selection was when recording started, ready for you to review and edit before sending.

The first use may download Apple’s speech model and needs a network connection. Later transcription works offline for that language. Recordings can be up to five minutes long. Canceling, leaving the screen, or an audio interruption discards the recording and preserves your existing draft. While recording, the screen stays awake; it can sleep normally once recording stops.

Voice input records from the first connected microphone in Settings → Microphone. The list mixes kinds (built-in, other wired, other Bluetooth, CarPlay) with wired and Bluetooth devices you have dictated with, listed by name. Drag to rank them together: for example, put Other Bluetooth above your AirPods so a new headset is preferred while the AirPods microphone stays low. By default, CarPlay comes after the built-in microphone.

Transcription runs on your iPhone when Apple’s speech model supports your language. Otherwise the recording is transcribed by the environment the thread belongs to, and the composer names it while you record. GOAT deletes the temporary audio after transcription or cancellation; only the message text is sent when you submit.

Voice input on desktop and web

Click the composer’s microphone to record, then confirm to insert the text or send it.

The desktop app transcribes on this computer, even when the thread runs on another machine: the recording goes to the transcription service through this computer’s Codex sign-in or OpenCodex, and never to the other machine. If you turned off Local environment in Settings › Connections, desktop voice input is unavailable until you turn it back on. In a browser, the environment you are connected to transcribes. The recorder shows which device transcribes.

The first time on a Mac, macOS asks whether GOAT may use the microphone. If you declined, or turned GOAT off later, the composer says so and offers Open System Settings: turn on GOAT in Privacy & Security › Microphone. GOAT may need to restart to notice the change. In a browser, allow the microphone in the site’s settings; recording also needs HTTPS or localhost.

If no sound reaches GOAT within a few seconds, recording stops and the composer asks you to check the selected input. Your draft stays as it was.

On a Mac, the microphone access you give GOAT also covers commands run by terminals and coding agents in GOAT, including work started from your other devices; those commands can record without asking again. GOAT does not ask for the camera, so camera commands such as imagesnap cannot use it when GOAT runs them.

Queued messages

On web and desktop, the composer shows Interrupt while the agent is working and the draft is empty. Adding text or attachments replaces it with a send button that shows your Follow-up behavior: a queue icon for Queue or a steer arrow for Steer. Click it or press your send shortcut to use that action. Hold Cmd on macOS or Ctrl on Windows and Linux to switch the button to the opposite action, then click, or use the opposite-action shortcut described above.

Queued messages appear above the composer. Rows show a thumbnail of any attached image alongside the text. Drag a row by its handle to reorder it, use the handle’s arrow keys, promote the message to a steer, or remove it.

If you stop the agent or the server restarts, queued messages keep their order and are held. Press Resume in an empty composer on web and desktop, or Resume queue on mobile, to continue. Sending a new message also resumes the queue, unless it steers a turn that is already running. You can edit, reorder, or remove held messages without starting them.

The pencil on a queued row opens that message in the composer for editing. The original message stays in the queue until you save, and its row is highlighted while you edit. The message’s attachments appear above the text with a remove control, and new images can be added the usual way. The checkmark saves the queued message in place; Cancel on its row leaves it unchanged. Whatever you had typed in the composer before starting the edit is restored afterwards. If the queued message starts or is removed while you are editing, the edit ends: changed content moves into the composer when it is empty, and is discarded otherwise.

Commands and skills

Type / for commands or $ to add a skill from the selected environment and provider. On mobile, both are also available before starting a thread on New task.

The slash menu also includes skills unless you turn off Settings → General → Show skills in slash menu. Only skills enabled for the provider are listed.

After you add or change skills, plugins, or MCP servers, use Restart agent session in the command palette on web and desktop. The conversation continues, and your next message starts the agent again with the new setup.

Provider commands must start the message to run. GOAT commands such as /model and /plan, and skill mentions, work on any line.

GOAT also ships built-in skills, marked Built in in the $ menu. Development discipline ($goat-discipline) gives the agent GOAT’s longer guidance for code changes: how much process a change needs, what counts as proof, what needs your approval, and how to brief subagents. Every agent already gets a short version; the full guidance goes only to the turn whose message names the skill, on Codex, Claude, Cursor, Grok, Antigravity, ACP registry agents, OpenCode and Pi. It needs no agent restart. A message that starts with a provider command does not load it, and neither does a skill name inside an attachment. Agents can name it in briefs for the tasks they delegate. Turn it off for every project, or for one project, in Settings → Integrations → Agent tools; on mobile, under Agent behavior.

Send /compact in an existing conversation to reduce context usage when the provider supports it. Web and desktop also offer compaction from the context meter.

Claude instances can also compact idle threads for you. See compact long conversations.

Side chat

On web and desktop, send /side <question> to ask about the current thread without adding to it. The question opens in a Side chat tab in the right panel, and its answers never enter the thread’s history. Send /side alone, use the side chat button in the thread header, or press Mod+/ to open or close the tab.

The side chat starts from the conversation up to the last finished turn, and every question you send it also carries the thread’s current state: whether it is working, interrupted, or waiting on you, its goal, its task list, and its latest messages. You can ask what the thread is doing while the agent is still working, and the side chat header shows the thread’s status. It has the full composer, with the thread’s model, workspace, and permission mode. It is meant for questions and leaves files alone unless you ask it to change something. Use Start a new side chat to discard it, or Open as a full thread to continue it on its own.

Goals

With Codex and Claude, send /goal followed by what “done” means, for example /goal all tests in packages/api pass. The agent keeps working across turns until it judges the goal met. The thread shows Goal while it works, and a row above the composer shows the goal and its progress.

/goal alone shows the current goal. /goal clear removes it.
Codex also supports /goal pause and /goal resume. Stopping a Codex goal pauses it, and so does Codex ending its work without meeting the goal.
Stopping Claude ends the current turn, but the goal stays set. Claude checks it again at the end of your next message.
Sending a new goal, or /goal resume, while the agent works stops the current turn and starts the goal, unless you queue it. /goal clear and /goal pause stop the turn only when it is working on the goal. Other goal commands wait for the turn to end.

Context in your message

Context you attach lands where your cursor is, as a chip inside your text: a terminal excerpt, a review comment from a diff or file, a preview annotation, or a file. You can type before and after a chip, move it by cutting and pasting, and delete it like a character. Hover a chip for its brief details. Select a terminal excerpt to open its captured output, or select a review comment, picked element, or preview annotation to open its full details. Chips read as “Terminal excerpt, Terminal 1 lines 3-4” and similar to screen readers.

A pull request appears as its icon and number. Its color reflects whether it was open, draft, merged, or closed when it was attached. Select it to inspect the captured title and branches, then choose Open pull request to visit the pull request. On web and desktop, type # to browse the newest pull requests in the current project’s repository. Pull requests linked to the thread are included from any repository and listed first, after any exact number match. Continue typing digits to filter the recent list by any part of its pull request numbers. A complete number is also resolved directly, even when that pull request is older than the recent list. Type a single word after # to search pull requests in the repository by text. Choose a result to insert it as a chip.

Another thread can be context too. Type @ followed by part of its title to pick one from the same server or a connected, linked environment, on web, desktop, or mobile. On web and desktop, drag a thread from the sidebar or Fleet onto the composer; a sidebar multi-selection drops together. The chip shows the thread’s current title and opens it when selected. Your prompt only carries a reference: the agent reads the thread’s history on demand, so attaching a long thread costs nothing until the agent looks. Attaching a thread does not change it, and the agent cannot send messages to it unless you ask.

Threads from another environment attach as references, not saved transcripts. The agent’s server must have a verified SSH or linked-host route to that environment, and the environment must be connected to the client. If a route cannot be verified, connect the environment or resolve any conflicting host names before attaching the thread. An SSH reference uses its host alias; a linked reference uses the link name. A chip can show “Host not connected” when the client’s connection is interrupted while the agent’s route remains available.

Images keep their thumbnail shelf above the text and also get a chip at your cursor, so you can say exactly which image you mean. Deleting an image chip leaves the image on the shelf; removing the thumbnail asks first when the image is still mentioned in your text, then removes both. Files exist only as chips: deleting a file’s last chip removes the file from the message.

Copy text that holds chips and paste it into another draft, in the same thread or another one, and the chips come along with what they point to. Images and files are fetched again from the environment they came from; while that happens the chip shows a dashed outline, and if it cannot complete GOAT tells you and leaves the chip for you to remove or replace. A chip whose context is no longer available shows the same dashed outline; hover it for what to do.

Copying a message with the copy button, or copying text out of it, gives other apps readable Markdown with a link in place of each chip. Older messages that were sent before chips still show their context. Stashing a prompt keeps its chips and what they point to; restoring brings them back.

On mobile, tap a chip to inspect its content. File references open the current file; attached files show the copy that was attached to the message.

Attached files

Select a file chip in your draft or a sent message to preview it. Code and JSON use syntax highlighting; Markdown, HTML, CSV, and TSV offer rendered and raw views. Audio files have playback controls. Large text files show a limited preview; save the file to read it in full.

On web and desktop, files open beside the conversation with the same controls as a workspace file: a header row with the view toggle, Copy contents and Save file. On mobile, documents open in the same file screen as workspace files; its menu holds Copy contents, Save or share and Open in file viewer. Pictures, videos and PDFs keep their native viewers, and other document formats such as Word or Pages open in the device’s own viewer when it has one. If nothing on the device can show a format, save or share it to open it elsewhere. A ZIP up to 50 MB opens as a folder list on every surface; on mobile, select a file inside it to preview, save, or add it to chat.

Images and videos in messages

Select an image or video attachment or link to preview it. Playback support depends on your browser or device; save an unsupported video to open it in another app.

On web and desktop, right-click media to save it or copy its path or URL. On mobile, touch and hold an image or video thumbnail and choose Save or share. On iOS, return to the thumbnail to open this menu after watching a full-screen video.

File links refer to the environment’s machine, including when you connect remotely. Previews use the original file, even outside the workspace. Moving or deleting it can break the preview, so save a copy if you need to keep it.

Files outside the workspace

Follow an agent’s file link to read a report or other file outside the workspace. These files open read-only. An HTML file outside the workspace cannot load scripts, styles, or images from neighboring files.

HTML and PDF files in the file viewer

On web and desktop, HTML and PDF files open as rendered pages. Switch an HTML file to source view to read its markup; a link to a specific line opens source automatically. HTML previews cannot access your GOAT session.

The file viewer recognizes images, HTML, and PDF files by their filename extension, including filenames or folders containing # or ?.

On mobile, select a PDF attachment or link to open it. iOS uses the native viewer; Android opens a compatible installed file viewer.