Add "Tour the Menu Bar" page and correct the onboarding wizard steps

docs/user-guide/getting-started/configure-settings.md

@@ -1,6 +1,6 @@
 ---
 title: Configure Settings
-sidebar_position: 2
+sidebar_position: 3
 ---
 
 Use this page to set the storage location, network behavior, and browser-chat defaults. Keep the changes small, apply them, and prove the server still responds before you move on.

docs/user-guide/getting-started/connect-a-client.md

@@ -1,6 +1,6 @@
 ---
 title: Connect a Client
-sidebar_position: 3
+sidebar_position: 4
 ---
 
 Use this page when another app needs to talk to Pico AI Server. The job is to copy the right server address, choose the correct compatibility layer, and prove the client can list models before you try chat.

docs/user-guide/getting-started/install-and-run-pico-ai-server.md

@@ -10,10 +10,13 @@ Pico AI Server is a macOS app for Apple Silicon Macs — it runs models with MLX
 ## Start the server
 
 1. Launch Pico AI Server.
-2. Complete the first-run flow.
-   The onboarding flow can set `Allow local network connections`, `Broadcast Bonjour`, `Open at login`, and `Prevent sleep`.
+2. Complete the first-run setup wizard.
+   The wizard has four steps: `Welcome`, choosing your first model, choosing who can connect, and a `Ready` summary.
+   - **Model:** Pico recommends a starting model based on your Mac's installed memory. Download it, pick a different one, or skip and add a model later. The download keeps running in the background while you finish the wizard.
+   - **Access:** Choose `This Mac only` (private — only apps on this Mac can connect) or `Devices on my local network` (LAN access). When you allow LAN access, an extra toggle lets Pico advertise itself with Bonjour. Pico is private by default; you can change this later in settings.
+   - **Ready:** Shows the live server status, the selected model, the access choice, and the server address with a copy button. `Open Chat` starts the server if needed and opens the WebUI.
 3. Open the WebUI at `http://127.0.0.1:11434/`.
-   The onboarding flow normally opens this address for you after setup.
+   Pressing `Open Chat` at the end of the wizard normally opens this address for you.
 4. If you want LAN access, leave `Allow local network connections` on.
    With that setting on, Pico AI Server binds to `0.0.0.0`.
 5. If you want local-only access, turn `Allow local network connections` off in the native app settings.
@@ -51,5 +54,6 @@ curl http://127.0.0.1:11434/hostname
 
 ## Next steps
 
+- [Tour the Menu Bar](./tour-the-menu-bar.md)
 - [Configure Settings](./configure-settings.md)
 - [Use the WebUI](../webui/use-the-webui.md)

docs/user-guide/getting-started/tour-the-menu-bar.md

@@ -0,0 +1,49 @@
+---
+title: Tour the Menu Bar
+sidebar_position: 2
+---
+
+Pico AI Server lives in the macOS menu bar. Clicking its icon opens a panel that is the fastest way to check the server, watch memory, see which models are loaded, and reach settings. This page walks through each section so you can read the panel at a glance.
+
+Pico AI Server must be installed and its icon visible in the menu bar. If you just finished the setup wizard, the icon is already there.
+
+## Open the menu bar panel
+
+1. Click the Pico icon in the macOS menu bar.
+2. Read the sections from top to bottom:
+   - **Server status** — a colored dot and a label (`Server Running`, `Server Stopped`, `Starting…`, or `Server Error`), with a `Start` or `Stop` button. While the server runs, the panel also shows the LAN server address with a copy button.
+   - **Memory** — a segmented bar that splits memory into `Apps`, `MLX` (memory used by loaded models), and `Free`. Click the `GB` / `%` control in the section header to switch the legend between gigabytes and percentages; Pico remembers your choice. A `Pressure` row reads `Stable`, `Elevated`, or `High`.
+   - **Models in Memory** — each model currently held in memory, with its state (`Loading`, `Active`, or `Idle`). Idle models show a trash button to remove them from memory, and `Clear All` unloads every idle model at once. When nothing is loaded, this reads `No models loaded`.
+   - **Downloads** — appears only while a model is downloading, showing a per-model progress bar.
+3. Use the actions at the bottom of the panel:
+   - `Open Pico Web Chat` opens the browser chat (available only while the server runs).
+   - `Documentation` opens Pico's documentation, and `Settings…` (⌘,) opens the native settings window.
+   - Hold `Option` to reveal `Setup Wizard…` in place of `Settings…`, and `Open Discord` in place of `Documentation`.
+   - `Quit Pico AI Server` (⌘Q) quits the app.
+
+## Verify it worked
+
+The status dot matches the server. With the server running, the dot is green and the API answers:
+
+```bash
+curl http://127.0.0.1:11434/v1/models
+```
+
+Send a chat request to load a model, then reopen the panel: the model appears under `Models in Memory`, and the `MLX` share of the memory bar grows.
+
+## Troubleshooting
+
+- **Symptom:** The `Open Pico Web Chat` action is greyed out.
+  **Cause:** The server is not running.
+  **Fix:** Press `Start` in the `Server status` section, then try again.
+- **Symptom:** `Models in Memory` says `No models loaded` even though a model is installed.
+  **Cause:** Installed models load on first use; nothing is held in memory until a request arrives.
+  **Fix:** Send a chat request, then reopen the panel.
+- **Symptom:** The memory legend shows percentages when you want gigabytes (or the reverse).
+  **Cause:** The `GB` / `%` toggle is set to the other unit.
+  **Fix:** Click `GB` / `%` in the `Memory` header to switch it back.
+
+## Next steps
+
+- [Configure Settings](./configure-settings.md)
+- [Use the WebUI](../webui/use-the-webui.md)

sidebars.ts

@@ -12,6 +12,7 @@ const sidebars: SidebarsConfig = {
       label: 'Getting Started',
       items: [
         'user-guide/getting-started/install-and-run-pico-ai-server',
+        'user-guide/getting-started/tour-the-menu-bar',
         'user-guide/getting-started/configure-settings',
         'user-guide/getting-started/connect-a-client',
       ],