> ## Documentation Index
> Fetch the complete documentation index at: https://platform.stepfun.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Interaction and input

Step Code centers interaction on one input box: type messages, paste images, reference files, and run shell commands. You can also switch approvals, Plan mode, and goals, or send messages while output streams.

## Input basics

| Action                           | Shortcut                                                   |
| -------------------------------- | ---------------------------------------------------------- |
| Send a message                   | Enter                                                      |
| Insert a newline                 | Shift+Enter, Ctrl+J, or Alt+Enter                          |
| Browse input history             | ↑ / ↓ with an empty input box                              |
| Jump forward to a character      | Ctrl+]                                                     |
| Delete a word backward / forward | Ctrl+W / Alt+D                                             |
| Delete to start / end of line    | Ctrl+U / Ctrl+K                                            |
| Restore deleted text             | Ctrl+Y; Alt+Y cycles the kill ring                         |
| Undo                             | Ctrl+-; Ctrl+Z on Windows, Alt+Z on WSL                    |
| Exit                             | Ctrl+C to clear, then press again; Ctrl+D with empty input |
| Suspend to background            | Ctrl+Z, except native Windows                              |

Windows Terminal also supports Ctrl+Enter for newlines. Customize `~/.stepcode/agent/keybindings.json`, then run `/reload`. See [Keyboard shortcuts](/docs/en/step-code/reference/keyboard-shortcuts).

## Pasting images

Use Ctrl+V to paste an image, or Alt+V on Windows / WSL. Supported terminals also let you drag in an image path.

```bash theme={"theme":{"light":"light-plus","dark":"dark-plus"}}
step -p @screenshot.png "How do I fix the error in this screenshot?"
```

Select a model that accepts images. By default, large images are resized to within 2,000 px to reduce input size; adjust this in `[images]`. Inline terminal display and sending images to a model are separate capabilities. Disabling display does not prevent image transmission.

## Slash commands

Type `/` to open completion; Esc closes it.

| Command                | Action                                               |
| ---------------------- | ---------------------------------------------------- |
| `/model`               | Select a model                                       |
| `/permissions`         | Choose approval mode                                 |
| `/thinking`, `/effort` | Change thinking level                                |
| `/plan`                | Toggle Plan mode, or start planning an included task |
| `/new`, `/resume`      | Create or restore a session                          |
| `/compact`             | Compact context                                      |
| `/goal`, `/cron`       | Manage goals or scheduled tasks                      |
| `/tree`, `/fork`       | Browse the session tree or fork a session            |

Invoke Skills with `/skill:<name>`. See [Slash commands](/docs/en/step-code/reference/slash-commands) for the full list.

## File references

Type `@` to search project files and Tab to complete paths. This works in Git and non-Git directories and on the command line:

```bash theme={"theme":{"light":"light-plus","dark":"dark-plus"}}
step @README.md "Summarize this project's purpose and how to run it"
step @src/app.ts @src/app.test.ts "Review whether the implementation and tests agree"
```

Referenced files and files read by tools may enter model context. Check for keys, personal information, and sensitive business data before referencing them.

## Approval flow

In Ask mode, or when Autopilot encounters an item requiring confirmation, Step Code opens a dialog titled `Approve <tool>` or `Dangerous <tool>`. It shows the reason and a summary of the arguments. Approval starts execution; rejection cancels that call and returns the reason to the model. A batch may prompt for each call.

### Permission modes

| Mode             | Ordinary tool calls                                                                    |
| ---------------- | -------------------------------------------------------------------------------------- |
| Ask              | Safe read-only tools run directly; writes and commands ask first                       |
| Read Only        | Only read-only and discovery tools are allowed                                         |
| Bypass (default) | No per-call approval for ordinary tools                                                |
| Autopilot        | Skips ordinary approvals and automatically recovers from some transient model failures |

Use `/permissions` to choose, or `/permissions cycle` and Shift+Tab to cycle. Environment variables can override the initial mode; see [Environment variables](/docs/en/step-code/configuration/environment).

Operations identified by dangerous-command rules still require confirmation and are rejected in Read Only. These rules cannot cover every script or dangerous action and are not a sandbox.

Non-interactive mode (`step -p`) rejects calls requiring approval by default. Use `--approval-mode` to adjust ordinary-call policy; dangerous commands are not exempted. See [The step command](/docs/en/step-code/reference/cli).

## Switching modes

### Plan mode

```text theme={"theme":{"light":"light-plus","dark":"dark-plus"}}
/plan Map the authentication module's dependencies and propose a migration plan. Do not change application code yet.
```

`/plan` toggles the mode, `/plan <task>` starts planning a task, and `step --plan` starts in Plan mode. The model investigates and writes a plan before implementation.

File editing is restricted to read-only investigation, with the plan file as the only writable file. Shell commands still follow normal permissions. Approving the plan exits Plan mode and begins implementation.

### Direct shell commands

```text theme={"theme":{"light":"light-plus","dark":"dark-plus"}}
!npm run lint
!!git status --short
```

`!` runs a local command and sends its output to the model; `!!` runs it without sending the output. Each prefix applies to one command: there is no separate shell mode or user-side background execution. Output appears as a card; long output collapses automatically and can be expanded with Ctrl+O.

### Goal mode

```text theme={"theme":{"light":"light-plus","dark":"dark-plus"}}
/goal Migrate the tests to Vitest, keep existing cases passing, and summarize the changes.
```

Goal mode drives multiple turns until the goal is achieved or stopped manually. It suits hours-long tasks. Keep the Step Code process running during the task.

| Command        | Action                                                                       |
| -------------- | ---------------------------------------------------------------------------- |
| `/goal status` | View the goal, status, and usage                                             |
| `/goal pause`  | Pause automatic continuation and interrupt the active goal continuation turn |
| `/goal resume` | Resume the goal                                                              |
| `/goal edit`   | Edit the goal                                                                |
| `/goal clear`  | Clear the goal                                                               |

The status line shows active time, such as `Goal: active · 12m 3s`, counting only time when the goal is active.

Scheduled tasks use five-field cron expressions. Durable tasks are saved to `.stepcode/cron/tasks.json` in the project and require project trust. Persisting a task does not let it run without a running scheduler process.

## During streaming output

* Enter queues a message for delivery after the current assistant turn's tools finish.
* Esc interrupts the turn and restores queued messages to the input box.
* Alt+↑ retrieves queued messages; use Alt+Q on Windows / WSL.
* Ctrl+O collapses or expands tool output.

Configure `steeringMode` and `followUpMode` in settings. Follow-up delivery has no dedicated shortcut by default.

## External editor

Ctrl+G edits the current input in an external editor; the action is `app.editor.external`. Selection order is `externalEditor`, `VISUAL`, `EDITOR`, then Notepad on Windows or nano elsewhere.

## Next steps

* [Sessions and context](/docs/en/step-code/guides/sessions)
* [Common use cases](/docs/en/step-code/guides/use-cases)
* [Agents and subagents](/docs/en/step-code/customization/agents)