Prompting and Input

Writing a prompt

The prompt is a multi-line text area. Type into the prompt and press Enter to send. Shift+Enter and Alt+Enter insert a line break without sending.

When the cursor is on the last line of a multi-line text area, pressing Down moves the cursor to the end of that line. This applies to every multi-line text area: the prompt, free-text answers to questions, and the feedback editor. In the prompt window, this behavior applies while you are typing a new prompt. When you have recalled a previous prompt with Up, pressing Down moves to the next newer entry in your prompt history instead.

The prompt accepts mouse input. Single-click inside the prompt to place the cursor where you clicked. A click beyond a row’s visible text moves the cursor to the end of that row. A click below the prompt text moves the cursor to the end of the final line.

Click and drag inside the prompt to select text, then release the mouse to copy the selection. Polytoken copies authored line breaks and ignores soft-wrapped display rows. Double-click the same prompt position to copy the complete prompt. Ctrl+Y copies the complete prompt when the prompt has focus.

Polytoken keeps a separate copy of the prompt text inside the TUI, so you can move text out of the prompt and bring it back even when your terminal does not expose a system clipboard. Ctrl+Shift+Y copies the prompt text and clears the prompt buffer, leaving the text ready to restore with Ctrl+V or your terminal’s paste shortcut. Ctrl+V pastes from the TUI-local copy, so it works over SSH where clipboard passthrough may be unavailable. All three shortcuts are configurable through tui.keyboard.commands under the copy-prompt, cut-prompt, and local-paste command IDs. See the configuration reference.

The prompt copy shortcut and the navigation card copy shortcut both default to Ctrl+Y, but they are independent commands. One acts in the prompt, the other acts in navigation mode, and you can set them to different chords.

Prompts you send while Polytoken is working go into a queue. Polytoken delivers queued prompts on the next turn.

While the queue holds messages, Polytoken shows the next one (the first message you queued, which Polytoken delivers next) as a single dimmed line just above the prompt, separated from the conversation by one blank line. A long message is cut short with an ellipsis, and when more messages wait behind it, Polytoken appends (+N) to the text to show the count. Press Up to pull the most recently queued message back into the prompt, where you can edit it or send it again.

Referencing things with `@`

Type @ anywhere in the prompt to open the reference picker. As you type after the @, Polytoken fuzzy-matches candidates and shows them in a bar above the prompt. Matching is case-insensitive: a query with uppercase letters matches the same candidates as its lowercase form.

The picker offers four categories:

You want to reference	Type	Short form
A file in your project	`@path/to/file`
The current directory	`@./path`
A file outside your project	`@../path`, `@~/path`, `@/path`
A skill	`@skill:name`	`@s:name`
A subagent	`@subagent:name`	`@a:name`
A model	`@model:name`	`@m:name`

Project file references use the project-relative path and show every file in the project tree, filtered as you type. By default, Polytoken leaves out hidden files, the project’s Polytoken directory, and anything covered by .gitignore, .claudeignore, or .polytokenignore.

You can browse the current directory with @. (or @./). This shows the immediate children of the directory you are working in: the project root by default, or the subdirectory you navigated to with pushd. Unlike the external browse prefixes below, files you reference this way stay inside the project, so they resolve through the project file catalog just like regular project-relative references.

You can also reference files outside the project tree. Three prefixes take you out of the project:

@.. browses the project’s parent directory. Keep typing path components to drill in: @../sibling/notes.md references a file in a sibling directory.
@~ browses your home directory. @~/Documents/report.md references a file there.
@/ browses the filesystem root (Unix only). @/etc/hosts references the system hosts file.

Outside the project, the picker shows only the immediate children of the directory you are browsing. Type a subdirectory name and press / to enter it. The same ignore rules apply in browsed directories: hidden files and .gitignore matches are hidden by default, and Shift+Tab reveals them.

When you select a file from outside the project, Polytoken reads its content at submit time and injects it as a system reminder, exactly as it does for project-relative references.

Two extra controls appear while the picker is open, and the bar shows them when they apply:

Shift+Tab turns off those ignore rules. When it is on, hidden files and the project’s Polytoken directory appear in the picker alongside everything .gitignore would normally hide. Version-control metadata directories such as .git stay hidden, since referencing their internals is never useful.
[ and ] adjust the reasoning level when you have a model reference selected.

Running commands with `/`

Type / as the first character of an empty prompt to open the command palette. A / later in your text is just text, unlike @, which works anywhere.

Some commands run immediately, some open a second menu to pick a value such as a model or a facet, and some take text you type after them:

/model switches the active model; /facet switches the active facet. /theme previews and switches the active theme for the current session. See Themes.
/compact and /clear manage your context. /reset-shell restores the shell environment without clearing context. See Sessions.
/rewind returns the conversation to an earlier point. See Sessions.
/feedback opens a feedback form where you can send a message and optional diagnostic artifacts to the Polytoken team. See Crash Reporting and Feedback.
/permissions changes how tool approvals are handled. See Permissions. Ctrl+Shift+P opens the permissions typeahead from the prompt without typing the command, even while the model is working on a turn.
/todo and /jobs show your todos and running jobs. See Managing Work.
/mcp enables or disables an MCP server. Type a server name, then choose enable or disable from the typeahead.
/version shows the TUI and daemon build versions.

The full list is in the Command Reference.

The typeahead bar

The reference picker and the command palette share the same bar above the prompt and the same keys:

Up / Down move through the candidates.
Tab accepts the highlighted one. For slash commands and slash arguments (facets, models, permissions), Enter accepts the selection and submits the prompt in a single press. For the file reference (@) picker and for commands that need further input (like /model), Enter accepts the selection without submitting.
Esc dismisses the bar.

The bar labels the keys that apply at each moment, including the file-ignore and reasoning controls when they are relevant.

A facet controls how Polytoken frames your prompt. The same prompt (“fix the login bug”) leads to different behavior depending on which facet is active. A facet sets the model’s prompt framing, the tools the model can use, and the accent color of the session.

Polytoken ships two facets. Plan is for planning out your work. Polytoken withholds tools that change files or run commands, so the model investigates and asks questions using read-only tools. If the model writes a plan, you can review it before it takes effect.

Execute is for getting things done, including following plans made by the plan facet. The model has access to every tool and carries out the plan you approved or follows new instructions.

Switch facets with /facet plan or /facet execute, or press Shift+Tab (or click the facet in the status bar) to open the facet picker. The picker opens whether or not the prompt has text, and Polytoken preserves any draft you have typed: the text returns to the prompt when the switch completes, and Esc cancels the switch and restores the draft without changing facets. The sidebar updates to show the new facet and its color, and the change takes effect on your next prompt.

Facets and models are independent: switching one does not switch the other. You can plan and execute on different models, or hold one model across both. You can also write your own facets; see Facets in Harness Engineering.

Plan mode

Plan mode uses the plan facet when a request needs a handoff to implementation. The model writes a structured handoff plan for the execute facet, then waits for your decision. You can customize the handoff-plan format; see Facets.

At the handoff you get three choices plus a refuse field:

Implement in a new context. Switch to execute and start fresh. Polytoken clears the planning conversation and carries the plan forward.
Implement in the current context. Switch to execute and keep the whole conversation, plan and all.
Cancel. Stay in plan. The model can revise the plan and hand off again.
Refuse (Tab to add feedback). Stay in plan. The model can revise the plan and hand off again. Press Tab to enter a feedback text field where you can type refusal feedback that gets sent back to the planner.

To refuse, press Tab to enter the feedback text field. Type your feedback, then press Enter to send it to the planner. The planner receives your feedback and can revise the plan for another handoff.

If you have text in the feedback field and press Esc or Ctrl+C, the text clears instead of cancelling. Press Esc or Ctrl+C again to cancel the handoff normally. This is the same clear-first rule the custom answer field in ask-user-question uses.

Press Ctrl+Y at the plan review to copy the full plan text to your clipboard.

The first choice clears the conversation with the same operation as /clear; see Sessions. The plan survives the clear.

Moving through the conversation

The conversation above the prompt is a stack of cards. A card is one selectable piece of the conversation: your prompt, a reply, a tool call, a notice. Most cards start collapsed. A tool card expands to show its result; a compaction marker expands to show what it summarized. Your prompts and Polytoken’s replies always show in full.

With the mouse

Scroll to move through the conversation. Scrolling does not interrupt what you are typing.
Single-click a card to expand or collapse it without leaving the prompt.
Double-click a card to enter navigation mode with that card selected.
Click and drag to select text within a card. Release to copy the selection to your clipboard.
Click and drag inside a plan handoff preview or an ask_user_question explanation area to select and copy that text the same way.
Double-click a link to copy it.
Double-click a flagged file in the sidebar to copy its absolute path.

Collapsing the ask_user_question context

When Polytoken asks you a question with a long explanation, you can hide the context to focus on the question and its options. Press the sidebar-toggle binding (default Ctrl+Shift+B) to collapse the context area. The conversation behind the question becomes visible and you can scroll it with the mouse wheel to read earlier messages while deciding. Press the binding again or click the key hint in the top-right corner of the question panel to bring the context back. The same key that toggles the sidebar outside a question is reused here; the sidebar itself is not affected.

Scrolling the conversation with the keyboard

The conversation window follows the latest messages by default. To scroll back and read earlier history without leaving the prompt, hold Shift with the paging keys:

Shift+PageUp scrolls up one screen.
Shift+PageDown scrolls down one screen.
Shift+Home jumps to the very first messages in the session.
Shift+End jumps back to the latest messages.

These keys work from the prompt, from navigation mode, and while a dismissible overlay like the Jobs or Todos viewer is open. They do not work inside a modal that captures all input, such as the help overlay, an error dialog, or the feedback form.

Without Shift, PageUp, PageDown, Home, and End behave as ordinary text-editing keys in the prompt composer and in multi-line text fields like the feedback form or a custom answer to an ask_user_question question.

With the keyboard

Press Ctrl+Up to enter navigation mode. From there:

Up / Down move between cards; Shift+Up / Shift+Down page through them.
Left / Right collapse and expand the selected card.
Ctrl+Y copies the selected card’s content.
Ctrl+R opens the rewind view for the selected card. For a prompt card, confirming removes the prompt and every card after it, including the assistant response and any tool calls, and the prompt text returns to the input area so you can edit and resubmit. For a compaction or context-clear card, confirming removes that boundary card and every card after it. See Sessions for what rewind can move past.
Esc returns to the prompt. Pressing a printable character returns to the prompt and inserts that character.

To rewind without entering navigation mode, press Esc twice at the prompt. You can also type /rewind to open the same picker. The picker shows every rewind point in conversation order: prompts, compaction summaries, and context-clear boundaries. Use Up and Down to move through them, then press Enter to select a point. In the confirmation dialog, Enter rewinds and Esc returns to the picker. Press Esc again to close the picker without rewinding. The most recent rewind point is selected by default.

These keys are the defaults. Action shortcuts like Ctrl+Y (copy card), Ctrl+R (rewind), and Ctrl+Up (enter navigation) can be remapped through tui.keyboard.commands; arrow keys and other structural navigation remain fixed. See the configuration reference.