> ## Documentation Index
> Fetch the complete documentation index at: https://docs.mossx.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Chat area
> Read streaming replies, thinking, tool calls, context usage, and the status panel.
The chat area is the main CC GUI surface. You watch how the assistant thinks, which tools it calls, which files it changes, and how much context this turn uses.
## Empty session and welcome screen
A new session with no messages shows a welcome screen: the current provider logo, a version number, and “Send a message to …”. Click the version number to open the changelog.
After the SDK is installed and a provider is enabled, the input box is ready. If it says the SDK is not installed, **Go to install** jumps to [SDK dependencies](/en/jetbrains/start/setup).
## What a message can contain
Assistant messages are usually several blocks:
| Block | Meaning |
| ---------- | -------------------------------------------------------------------------------------------------------- |
| Thinking | The model’s internal reasoning. You can collapse it |
| Body | Markdown reply. Code blocks can be copied |
| Tool calls | Read files, edit files, run commands, search, open web pages |
| Diff | File-change comparison. Click to open the file |
| Usage | Input / output tokens for this turn. With detailed output on, you also see cache hits and estimated cost |
A tool call spins while it runs. After a multi-step task finishes, the spinner should stop. If it keeps spinning, see [FAQ](/en/jetbrains/community/faq).
Click a message to rewind to before that turn. See [Sessions, tabs, and history](/en/jetbrains/chat/sessions#rewind-to-a-message).
## Streaming and stop
Streaming is on by default: text and tool blocks appear as they are generated. Turn it off in **Settings → General → Behavior** to receive the full reply at once.
While generating, the input box becomes **Stop**. Click it to interrupt the current turn:
* Claude / Codex: end the current request
* Grok / Kimi / OpenCode / Pi: also end the matching child process
If you stop it yourself, completion toasts and sounds do not play.
## Search in the conversation
Press `Cmd+F` (Windows / Linux: `Ctrl+F`) to search inside the chat.
* `Enter` / `Shift+Enter`: next / previous
* `Esc`: close
If early messages are collapsed, search expands them first, then jumps.
## Context usage
The context indicator near the input box shows how much of the current window is used. Click it for a finer breakdown.
When you are close to the limit:
* Send `/compact` so the model summarizes earlier turns
* Start a new session and keep only the files you need
* Avoid pasting large logs. Use `@` to cite files instead
## Status panel
On longer tasks, a status panel appears on the right or bottom:
| Tab | Contents |
| ------------- | ------------------------------------------------------------- |
| Todo | Todos the model split out |
| Subagents | Parallel subtasks |
| Files / edits | Files changed this turn. You can view the diff, undo, or keep |
Undoing file changes cannot be undone again. Review the list before you confirm.
## Permissions, questions, and Plan
When the model wants to edit files, run a command, or ask you a multiple-choice question, a dialog appears. The timeout is in **Settings → General → Behavior**. After timeout the dialog closes and the model continues with the current policy.
In plan mode, the model first gives a read-only plan and waits for your approval before changing code. See [Run modes and permissions](/en/jetbrains/chat/modes).
## Related pages
`@`, `/`, `#`, `!`, attachments, and the send shortcut.
Tabs, favorites, export, and rewind.