Dev (#151)

* fix * Chore/260 docs (#150) * wip * wip * wip * fix reload issue * fix broken links * improvements * improvements * improvements * wip * improvements * local model agent mode * new txt
2026-07-25 20:56:00 -04:00 · 2026-03-24 10:31:49 -06:00
parent 42e77796ea a81883727a
commit d98e6bdf80
93 changed files with 4473 additions and 3663 deletions
@@ -8,6 +8,7 @@ dist

 # Node dependencies
 node_modules
+.pnpm-store

 # Logs
 logs
@@ -1,5 +1,6 @@
 {
  "lockfileVersion": 1,
+  "configVersion": 0,
  "workspaces": {
    "": {
      "name": "shadcn-docs-nuxt-starter",
@@ -1,62 +1,67 @@
 ---
 title: Welcome to Msty Studio
 description: The complete guide to Msty Studio
+resources:
+  videos:
+    - TdGjKf4vRPo
+  blogs:
 previewImage: "/images/welcome-to-msty.png"
 ---

 ::callout{variant="primary"}
-**Looking for Msty App?**  
-If you're looking for the **Msty App 1.x** documentation instead, you can find it here: [**Go to Msty App Docs →**](http://docs.msty.app){target="\_blank"}
+**Looking for Msty App 1.x docs?**  
+Use the legacy documentation here: [**Go to Msty App Docs ->**](http://docs.msty.app){target="\_blank"}
 ::

-[Msty Studio](https://msty.ai){target="\_blank"} is a [privacy-first](https://msty.ai/privacy-first){target="\_blank"} AI platform that empowers you to design and run advanced AI workflows using local and online models, directly from a web or desktop interface. Msty offers seamless integration with hundreds of top-tier models, powerful tools like Toolbox (MCP), Knowledge Stacks (RAG), Personas (Customized AI Assistants), and Turnstiles (Workflows), and fully local data storage, ensuring both sophistication and security in your AI processes.
+[Msty Studio](https://msty.ai){target="\_blank"} is a [privacy-first](https://msty.ai/privacy-first){target="\_blank"} AI platform for running local and online AI models from desktop and web.

+You can start for free with Msty Studio Desktop, then add online providers or advanced workflows when you are ready.

+## Getting Started Video Guide

-## Getting Started
+::YouTubePlayer{videoId="TdGjKf4vRPo"}
+::

-You can get started for free with [Msty Studio Desktop](/getting-started/desktop). 
+## Start Here
+
+You can get started for free with [Msty Studio Desktop](/getting-started/download).

 Aurum subscribers get full access to both Msty Studio Web and Msty Studio Desktop.

-See the [plan comparison](https://msty.ai/pricing#plan-comparison){target="_blank"} to view what features are available by plan type. 
+See the [plan comparison](https://msty.ai/pricing#plan-comparison){target="_blank"} to view what features are available by plan type.

 ::alert{type="info" icon="tabler:info-circle"}
-Data does not sync between devices. Data is stored locally on your device. Studio web stores data directly to your browser.
+Data does not sync between devices. Data is stored locally on your device. Studio Web stores data directly to your browser.
 ::

 ### Msty Studio Desktop

-Msty Studio Desktop is our Msty Desktop 2.0 app and is FREE to get started on. Check out our [Announcement](https://msty.ai/blog/announcing-studio-desktop){target="\_blank"} to learn more about our vision for Msty Studio Desktop.
+Msty Studio Desktop is free to get started on and is the recommended path for new users.

-To get started with Studio Desktop, please see the [Desktop](/getting-started/desktop) guide.
+1. Install from [Download](/getting-started/download)
+2. Follow the [Quick Start](/getting-started/quick-start) guide
+3. Use [Managing Models](/managing-models) to add providers and local models

 ### Msty Studio Web :aurum-tag

-Msty Studio Web is a web-based application that is capable of running the majority of features that Msty Studio Desktop offers. However, to unlock additional features, including Real-Time Data, Toolbox, and Local Models, Studio Web will need to connect to [Msty Studio Desktop](/features/remote-connections) or [Msty Sidecar](/how-tos/sidecar). Connecting Web to Desktop is the recommended approach for most users.
+Msty Studio Web supports most core features in the browser. For local models, Toolbox, and Real-Time Data, connect Studio Web to [Msty Studio Desktop](/settings/remote-connections) or [Msty Sidecar](/how-tos/sidecar).

-Even though Msty Studio Web is a web-based app, data is stored directly on your browser's local storage. This helps us maintain our Privacy-first policy and our commitment to keep your data in your control.
-
-#### Existing Msty App v1.x user?
-
-If you are an existing user of Msty App, please see the [Quick Start](/getting-started/quick-start) guide to get started.
-
-#### New to Msty Studio?
-
-If you are brand new to Msty Studio, please see the [Onboarding](/getting-started/onboarding) guide to get started.
+Even though Msty Studio Web is a web-based app, data is stored directly in your browser local storage. This helps keep your data in your control.

 ## Popular Topics

- [Managing Models](/getting-started/managing-models) - Learn how to add and configure AI models
- [Toolbox](/features/toolbox/tools) - Leverage powerful tools using MCP
- [Knowledge Stacks](/features/knowledge-stacks/overview) - RAG the right way
- [Workspaces](/features/workspaces) - Organize your projects and conversations
- [Environment Variables](/features/environment) - Configure your development environment
- [Data Backups](/features/data-backups) - Keep your data safe and synchronized
+- [Managing Models](/managing-models) - Learn how to add and configure AI models
+- [Toolbox](/toolbox/tools) - Leverage powerful tools using MCP
+- [Knowledge Stacks](/knowledge-stacks/overview) - RAG the right way
+- [Workspaces](/workspaces) - Organize your projects and conversations
+- [Crew Mode](/conversations/crew-chats) - Run collaborative chats with multiple personas
+- [Agent Mode](/agent-mode/agent-mode) - Complete multi-step tasks with agents
+- [Environment Variables](/workspaces/environment) - Configure your development environment
+- [Data Backups](/settings/data-backups) - Keep your data safe and synchronized

 ## Need Help?

- **Getting Started**: Check out our [Quick Start](/getting-started/quick-start) or [Onboarding](/getting-started/onboarding) guides
+- **Getting Started**: Check out our [Quick Start](/getting-started/quick-start) guide
 - **How-Tos**: Find step-by-step guides in our [How-Tos](/how-tos/manage-license) section
- **Whats new**: See what's new in Msty Studio by visiting our [Changelog](https://msty.ai/changelog){target="\_blank"}
+- **Whats new**: Visit the full [Changelog](https://msty.ai/changelog){target="\_blank"}
 - **Support**: Visit our [Discord](https://msty.ai/discord){target="\_blank"} for issues and discussions
@@ -8,217 +8,73 @@ resources:
 previewImage: "/images/welcome-to-msty.png"
 ---

-## Welcome to Msty Studio! 
+Quick Start is the fastest path for new users to go from install to first chat.

-Already have the **Aurum license** and **Msty App** installed? Awesome — you're all set to start using **Msty Studio**!
+## Choose Your Path

-These instructions are for those who actively used Msty App 1.x and have an Aurum subscription and will get you started quickly with Msty Studio. 
+- **Desktop (recommended):** Best path for most new users and supports local model workflows.
+- **Web (Aurum):** Use Msty Studio in the browser with remote providers or a Desktop/Sidecar connection.

-Before continuing, grab your license key, which you can do by going to [Lemon Squeezy](https://app.lemonsqueezy.com/my-orders/login).
-
-For Studio Desktop, you can migrate your data from Msty App v1.x to Studio Desktop. See the [Data Migration](#data-migration-for-msty-app-users) section for more details.
-
-## Quick Start Instructions for Msty Studio Web :aurum-tag
+## Msty Studio Desktop Quick Start (Recommended)

 ::steps

-1. Open the **Msty App**, go to **Settings → Local AI**.
-2. Scroll to **Allowed Network Origins** and add:
+1. [Download Msty Studio Desktop](/getting-started/download) and install it.
+2. Open Msty Studio Desktop.
+3. On first launch, choose your setup path:
+   - Use local models (recommended for most new users)
+   - Add a [remote provider with an API key](/how-tos/find-api-keys)
+4. Complete setup and click **Let's Go!**.
+5. Open a chat and send your first prompt.

-   ```
-   https://msty.studio
-   ```
-
-   This enables Msty Studio to connect with your Msty App and access your Local AI models. Keep Msty App open so that Studio can connect to it for a quick start to Studio.
-
-3. Head over to [**Msty Studio**](https://msty.studio)
-
-4. Paste in your license key and click **Next**.
-
-5. On the following screen, Msty Studio will detect your Msty App and list available Local AI models.
-
-6. Click **Let's Go!** — and you're in!
-
-![Quick Start Msty Studio](/images/welcome-to-msty.png)
 ::

 ::alert{type="info" icon="tabler:info-circle"}
-**Don’t have Msty App installed or running yet?**
-No worries — just head to the next section, and we’ll guide you through the full setup step by step.
+Msty stores your data locally on your device. Data does not sync automatically between devices.
 ::

-## Quick Start Instructions for Msty Studio Desktop :aurum-tag
-::steps
-
-1. [Download Msty Desktop](/getting-started/desktop) and install
-2. Enter your license key in **Settings → License and Access**
-3. Proceed to the following section if you'd like to migrate data from Msty App 1.x to Msty Studio Desktop
-
-::
-
-## Data Migration for Msty App Users
-
-Msty App v1.x free and Aurum users can migrate much of their data to Msty Studio Desktop. Before proceeding, please **backup** your data for BOTH Msty App and Msty Studio Desktop prior to migration.
-
 ::alert{type="info" icon="tabler:info-circle"}
-Data migration is only available for Msty Studio Desktop at this time. 
+Msty Studio can install and manage its own Ollama service during Local AI setup. If you prefer to use an existing Ollama setup independently, add Ollama as a Remote Provider instead.
 ::

-### Data Migration includes
+### Optional: Install Local AI Services From an Archive File

-You can migrate any of the following items from Msty App v1.x to Msty Studio Desktop:
- **Prompts**: All your workspace's Prompt Library prompts
- **Remote Model Providers**: All your workspace's remote providers and selected models from Msty App - **does NOT include API keys**, these will need to be re-entered for each provider
- **Conversations**: All your workspace's conversations 
- **Attachments**: All your workspace's attachments that you include in the zip file
+During setup (and later from **Settings > Local AI > Services Version**), you can install an earlier Ollama version instead of the latest default.

-Migrated conversations and prompts will be added to new project folders in Msty Studio. Your existing Msty Studio Desktop data will not be overwritten.
+![import ollama archive](/images/quick-start/import-ollama-archive.png)

-### Migration steps
+To install from an archive file:

-You can migrate data one workspace at a time. If you have multiple workspaces, you will need to repeat the migration steps for each workspace you intend to migrate data to.
+1. Download the correct archive for your OS from [Ollama Releases](https://github.com/ollama/ollama/releases){target="_blank"}.
+2. In setup, choose the archive file option.
+3. Select the downloaded archive file.
+
+::alert{type="info" icon="tabler:info-circle"}
+If Local AI setup fails with the default installer, archive install is a useful fallback.
+::
+
+## Msty Studio Web Quick Start :aurum-tag

 ::steps

-1. Locate the **msty.db** database and attachment files
+1. Purchase an [Aurum license](https://msty.ai/pricing){target="_blank"} and keep your license key handy.
+2. Open [https://msty.studio](https://msty.studio).
+3. Enter your license key and click **Next**.
+4. Add a model provider:
+   - Add a remote provider (OpenAI, Anthropic, Gemini, and others)
+   - Or connect Studio Web to [Msty Studio Desktop](/settings/remote-connections) or [Msty Sidecar](/how-tos/sidecar)
+5. Click **Let's Go!** and run your first prompt.

-To locate the **default workspace** database and attachments, follow these steps:
-  - Open Msty App and go to **Settings > General > Data Paths** and open location for **App Data**
-  - This will open the folder where the default workspace database file and attachments folder are stored
+::

-![Default Workspace Data Paths](/images/quick-start/default-data.png)
+::alert{type="info" icon="tabler:info-circle"}
+**Safari user?** Safari is not directly supported by Msty Studio. You can still connect through [Remote Connections](/settings/remote-connections) using tunneling.
+::

-To locate a **custom workspace** database and attachments, follow these steps:
-  - Right click on the workspace and then select option to **Reveal in Finder** (macOS) or **Open Folder** (Windows)
+## Next Steps

-![Default Workspace Data Paths](/images/quick-start/workspace-data.png)
-
-2. If you plan to migrate attachments, first zip the attachments folder 
-3. Open Msty Studio Desktop
-4. Ensure you are in the workspace you want to migrate data to
-   - If you are not in the correct workspace, switch to the desired workspace by clicking on the workspace icon
-5. Go to **Settings > Data > Data Migration** 
-6. Select the database file you want to import the items from
-7. Select the items you want to import from the database file
-9. Optionally select a zipped attachments file to import; attachments can also be imported later, after the database has been imported
-8. Click the **Migrate** button to migrate items from database file
-
-:: 
-
-You will see confirmation messages when data migration and attachment imports are complete. 
-
-#### Migration Workspace Issues
-
-Thank you to our Discord community members, if you are running into issues importing a Workspace, try the following steps: 
-
-
-##### Linux / Mac
-
-1. **Save the script**
-   - Create a new file called `optimize_db.sh` in the same folder as `msty.db`
-   - Paste the following script into it
-
-  ```bash
-      # Close the database properly first to merge WAL files
-      sqlite3 msty.db "PRAGMA wal_checkpoint(FULL);"
-
-      # Create a fresh export that includes all data
-      sqlite3 msty.db ".output msty_temp.sql" ".dump" ".exit"
-
-      # Create a completely new database from the dump
-      rm -f msty_copy.db msty_copy.db-shm msty_copy.db-wal
-      sqlite3 msty_copy.db ".read msty_temp.sql"
-      rm msty_temp.sql
-
-      # Optimize the new database
-      sqlite3 msty_copy.db "PRAGMA integrity_check;"
-      sqlite3 msty_copy.db "PRAGMA optimize;"
-      sqlite3 msty_copy.db "VACUUM;"
-
-      # Verify database access
-      echo "Verification:"
-      sqlite3 msty_copy.db "SELECT COUNT(*) FROM chat_session_folders;"
-
-      # Compare file sizes
-      echo "Original size:"
-      du -h msty.db
-      echo "Optimized copy size:"
-      du -h msty_copy.db
-
-      echo "Done! You can now import msty_copy.db"
-  ```
-
-2. **Open Terminal**
-   - Press `Cmd + Space` and type "Terminal"
-
-3. **Navigate to your folder**
-   - Type: `cd /path/to/your/folder`
-   - Replace `/path/to/your/folder` with the actual path
-
-4. **Make script executable**
-   - Type: `chmod +x optimize_db.sh`
-
-5. **Run the script**
-   - Type: `./optimize_db.sh`
-
-##### Windows
-1. **Install SQLite**
-   - Open Command Prompt (CMD)
-   - Run: `winget install SQLite.SQLite`
-
-2. **Save the script**
-   - Save the `fix-msty-db.ps1` script to: `C:\Users\YourUsername\AppData\Roaming\Msty`
-
-  ```bash
-      # Close the database properly first to merge WAL files
-      sqlite3 msty.db "PRAGMA wal_checkpoint(FULL);"
-
-      # Create a fresh export that includes all data
-      sqlite3 msty.db ".output msty_temp.sql" ".dump" ".exit"
-
-      # Create a completely new database from the dump
-      Remove-Item -Path msty_copy.db, msty_copy.db-shm, msty_copy.db-wal -ErrorAction SilentlyContinue
-      sqlite3 msty_copy.db ".read msty_temp.sql"
-      Remove-Item msty_temp.sql
-
-      # Optimize the new database
-      sqlite3 msty_copy.db "PRAGMA integrity_check;"
-      sqlite3 msty_copy.db "PRAGMA optimize;"
-      sqlite3 msty_copy.db "VACUUM;"
-
-      # Verify database access
-      Write-Host "Verification:" -ForegroundColor Green
-      sqlite3 msty_copy.db "SELECT COUNT(*) FROM chat_session_folders;"
-
-      # Compare file sizes
-      Write-Host "`nOriginal size:" -ForegroundColor Green
-      Get-Item msty.db | Select-Object Name, @{Name="Size";Expression={"{0:N2} MB" -f ($_.Length / 1MB)}}
-
-      Write-Host "`nOptimized copy size:" -ForegroundColor Green
-      Get-Item msty_copy.db | Select-Object Name, @{Name="Size";Expression={"{0:N2} MB" -f ($_.Length / 1MB)}}
-
-      Write-Host "`nDone! You can now import msty_copy.db" -ForegroundColor Green
-  ```
-
-  - Replace `YourUsername` with your actual Windows username
-
-3. **Open PowerShell**
-   - Press `Win + X` and select "Windows PowerShell"
-
-4. **Navigate to the Msty folder**
-   - Run: `cd ~\AppData\Roaming\Msty`
-
-5. **Run the script**
-   - Run: `.\fix-msty-db.ps1`
-
-##### If you get a script execution error
-
-Try one of these options:
-
-**Option 1: Run this single script only**
- Run: `powershell -ExecutionPolicy Bypass -File .\fix-msty-db.ps1`
-
-**Option 2: Enable PowerShell scripts permanently** (has security implications)
- Run: `Set-ExecutionPolicy -ExecutionPolicy RemoteSigned -Scope CurrentUser`
+- [Managing Models](/managing-models) to add and tune providers
+- [Settings](/settings/settings) to customize behavior and defaults
+- [Remote Connections](/settings/remote-connections) to connect Web and Desktop

 ::Resources
@@ -136,7 +136,7 @@ sudo chmod 4755 /opt/MstyStudio/chrome-sandbox


  #### GPU Version
-  Optimized for systems with a [compatible AMD or NVIDIA GPU](/getting-started/gpus-support), offering improved performance.
+  Optimized for systems with a [compatible AMD or NVIDIA GPU](https://docs.msty.app/getting-started/gpus-support){target="_blank"}, offering improved performance.

  :button-link[Download Msty (x64 GPU)]{left-icon="tabler:download" variant="outline" to="https://assets.msty.app/prod/latest/win/auto/Msty_x64.exe" self}
  ::
@@ -197,9 +197,9 @@ sudo chmod 4755 /opt/MstyStudio/chrome-sandbox
  ::
  ::div{label="Linux" icon="ph:linux-logo"}
  ### Linux
-  Read [how to install Msty on Linux.](/how-to-guides/install-msty-on-linux)
+  Read [how to install Msty on Linux.](https://docs.msty.app/how-to-guides/install-msty-on-linux){target="_blank"}
      ::
    ::
 ::

-::Resources
+::Resources
@@ -1,75 +0,0 @@
---
-title: Onboarding
-description: Get started with Msty Studio
-navTruncate: false
-resources:
-  videos:
-    - TdGjKf4vRPo
-  blogs:
-previewImage: "/images/quick-start/import-ollama-archive.png"
---
-
-These onboarding instructions are meant for new Msty Studio users. If you are an existing Msty App v1.x and Aurum subscriber, please check out the [Quick Start](/getting-started/quick-start) guide.
-
-## Getting Started Video Guide
-::YouTubePlayer{videoId="TdGjKf4vRPo"}
-::
-
-## Msty Studio Desktop Onboarding Instructions
-
-You can get started with Msty Studio Desktop for FREE. 
-
-::steps
-
-1. [Download Msty Studio Desktop](/getting-started/desktop) 
-
-2. On initial launch, you'll be asked how you'd like to proceed - either with using existing local models, setting up a new local model, or adding an API key for an online provider. The quickest way to get started is to proceed with a local model. You can add additional local and online models later. 
-
-3. Once you have your Remote or Local Provider set up, click on **Let's Go!**
-
-::
-
-::alert{type="info" icon="tabler:info-circle"}
-Msty Studio installs a separate instance of Ollama when setting up Local AI Services. This is to allow Msty Studio to have control over Ollama, allowing Msty to manage models, version updates, etc. If you have Ollama and do not want Msty Studio to manage Ollama, you can add Ollama as a Remote Provider (remote meaning separate from Msty, but may still be running on local machine) by selecting Ollama in the dropdown. This will allow you to use Ollama models you have setup without Msty having management access over Ollama. 
-::
-
-### Install Local AI From Archive file
-
-During onboarding (and from Settings > Local AI > Services Version) you choose to setup an earlier version of Ollama if you do not want to use the latest version, which is what Msty Studio will install when setting up Local AI Services. 
-
-![import ollama archive](/images/quick-start/import-ollama-archive.png)
-
-To install from an archive file, select the option as seen in the image above. 
-
-You'll want to have an archive file ready. You can download one from the [Ollama Version Archives](https://github.com/ollama/ollama/releases){target="_blank"} by downloading the appropriate file for your Operating System from the verion > assets section. 
-
-Select the archived file from the file selection window and Msty Studio will install using the selected file. 
-
-::alert{type="info" icon="tabler:info-circle"}
-If you see an error during Local AI Services setup, try this option as an alternative method to install Local AI Services.
-::
-
-## Msty Studio Web Onboarding Instructions :aurum-tag
-
-::steps
-
-1. [Purchase an Aurum license](https://msty.ai/pricing) if you haven't already and keep your license key handy
-
-2. Open a browser and navigate to Msty Studio at [https://msty.studio](https://msty.studio)
-
-3. Enter your license key and click **Next**
-
-4. You'll now have a few options on how you can proceed. In order to make use of Msty, you will need to add either a local or remote model provider.
-   ![Msty Studio Initial Setup](/images/initial-setup.png)
-   - To add a Remote Provider, click **Add Provider**. There are many available options, such as OpenAI, Claude, and Gemini. You will first need an API Key from the desired provider in order to add the remote provider to Msty.
-5. Once you have your Remote or Local Provider set up, click on **Let's Go!**
-
-## ![Quick Start Msty Studio](/images/welcome-to-msty.png)
-
-::
-
-::alert{type="info" icon="tabler:info-circle"}
-**Safari user?** Safari is not directly supported by Msty Studio however there is a workaround using [Remote Connections](/features/remote-connections) by leveraging the tunneling feature.
-::
-
-::Resources
@@ -1,122 +0,0 @@
---
-title: Managing Models
-description: Adding and managing AI Models in Msty Studio
-navTruncate: false
-resources:
-  videos:
-    - "CQtkVGItavA"
-    - "hQ8BcdpQwlw"
-    - "lwigyQ2whY0"
-    - "cmL1wgHkbno"
-    - "jUtla3fse_Y"
-    - "cmL1wgHkbno"
-  blogs:
-    - title: "Unleashing Local AI - Transform Your Coding Experience with Msty"
-      description: "Discover how to enhance your coding workflow using local AI models with Msty, GitHub Copilot, and Roo Code for personalized, offline support."
-      image: "https://msty.ai/blog/toolbox/unleash-local-ai.png"
-      url: "https://msty.ai/blog/local-ai-coding-assistants"
-    - title: "The AI Settings Dictionary"
-      description: "AI settings are a powerful way to customize your AI experience. Here is what they all mean and how to use them."
-      image: "https://msty.ai/blog/ai-settings-dictionary/ai-settings-dictionary.png"
-      url: "https://msty.ai/blog/the-ai-settings-dictionary"
-    - title: "5 Ways to Use Local Inference with Msty Studio"
-      description: "Explore five practical ways enterprises can run local AI inference with Msty Studio, keeping data private while giving teams a powerful, easy-to-manage front end for productivity."
-      image: "https://msty.ai/blog/enterprise/5-ways-to-use-local-inference.png"
-      url: "https://msty.ai/blog/top-5-local-inference-options"
-previewImage: "/images/model-hub.png"
---
-
-You can manage AI providers and models from **Model Hub**.
-
-![adding new models](/images/model-hub.png)
-
-## Model Matchmaker
-
-If you're unsure which model is the best for your needs, select **Match Maker** and adjust the scales according to what is most important.
-
-![msty matchmaker](/images/matchmaker.png)
-
-Matchmaker will consider what you are looking for against the strengths of available models, and provide recommendations for which models best match your criteria.
-
-![msty matchmaker ranked models](/images/ranked-models.png)
-
-Now, you have a starting point for which Model Providers and Models to consider using in Msty.
-
-Then, the real fun! Testing the models in Msty to see which one best encapsulates your needs.
-
-BTW - a big part of the charm of Msty is the ability to use multiple models. So, if one model doesn't quite cut it, then consider leveraging two (or more models) where each model provides complimentary skills. Check out [Split Chats](/features/conversations/split-chat) and [Turnstiles](/features/turnstiles) for more insights.
-
-## Model Providers
-
-You can edit and remove existing Cloud Providers from the **Model Providers** tab.
-
-You can also add new Providers and Models by selecting **Add Provider**.
-
-As these are mainly Cloud Providers, you will first need to set up and account with the desired provider, generate and copy their API Key, and then add the API Key to Msty when adding a New Provider.
-
-## Local AI Models
-
-You can add and remove Local Models from the **Local AI Models** tab.
-
-The **Featured Models** tab displays popular Local Models that are available for installation.
-
-The **Installed Models** tab displays the models currently installed on your device. You can remove models from this tab to uninstall.
-
-The **Ollama Models** and **Hugging Face Models** tabs allow you to search Ollama and Hugging Face for models that you can install onto your device. As long as the model is public and has an available GGUF (GPT-Generated Unified Format) file for download, then it typically is available to install.
-
-The **Import GGUF Model** tab allows you to Select a GGUF model file from your file system to import into Msty Local AI.
-
-## Import a GGUF Model
-To import a GGUF model that you have downloaded locally, navigate to the **Import GGUF** tab, select directory and then browse to the location of the GGUF file on your device.
-
-You can either establish a symlink to point Msty Studio to the GGUF file location, or you can copy the GGUF file into Msty Studio's models directory.
-
-## Import a Safetensors Model
-To import a Safetensors Model that you have downloaded locally, navigate to the **Import Safetensors** tab, select directory and then browse to the location of the Safetensors file on your device.
-
-## Model Squad
-
-Model Squad is a collection of specialized AI models to assist with Msty functionality.
-
-As opposed to generic or standard text summaries, you can have GenAI create conversation titles, context shield summaries, and and real-time prompt data synthesis.
-
-This allows you to use an AI that may be better at generating descriptions than the current model that you have selected.
-
-## Set A Default Model
-
-To set a default model, expand the model selection box in the Conversations toolbar and then select the star icon to set the model as the default.
-
-## Update Model Name
-
-From Model Providers, Local AI Models > Installed Models, or the model selector in the the Conversations toolbar, select the edit icon to update the model name.
-
-You can update the model name to be more descriptive of the model's purpose or the type of conversations that you are having with it.
-
-## Set Model's Purpose (tags)
-
-![model purpose](/images/model-purpose.png)
-
-Also, from the window that opens when you select the edit icon, you can set the model's purpose. These are tags that are used to categorize the model according to the standard use-cases they provide.
-
-### Model Purpose Types
-
- **Text**: General text generation and understanding. Typical applications include text classification, generation, translation, completion, and summarization.
- **Coding**: Assisting with code generation and debugging. Typical applications include code completion, generation, analysis, debugging, and summarization.
- **Tools**: Interfacing with external tools and APIs. These models can be used for Msty Tools feature (MCP).
- **Image**: Generate images. This will need to be set correctly according to model type, see [Image Generation](/features/image-gen).
- **Vision**: Analyzing and understanding visual content, such as if you were to add an image attachment to a chat. Typical applications include image classification, object detection, visual search, and image descriptions.
- **Embedding**: Creating and using embeddings for various tasks. The models are used for vectorization, similarity search, and clustering and are typically used for RAG - such as with Msty's Knowledge Stacks feature.
- **Streaming**: Handling real-time (or near real-time) data streams. Typical applications include real-time data processing, event detection, and anomaly detection.
- **Thinking**: Reasoning models will have additional configurations available in model parameters - such as for some models you can set thinking to a low, medium, high setting.
-
-## Provider and Model Logos
-
-You can customize the logo for a Provider or Model by selecting the edit icon in Model Hub and then selecting the image icon to upload a new logo.
-
-![change model logo](/images/change-provider-model-logo.png)
-
-## GPU support
-
-If your system has a compatible GPU, you can enable GPU support for models that support it by selecting the corresponding option in **Settings > Local AI > Service ellipsis menu**.
-
-::Resources
@@ -1,33 +0,0 @@
---
-title: MLX Models
-description: Adding and managing MLX Models in Msty Studio
-navTruncate: false
-resources:
-  blogs:
-    - title: "5 Reasons You Should Try MLX with Msty Studio"
-      description: "Discover how MLX and Msty Studio unlock fast, local AI on Apple Silicon Macs, letting you create, experiment, and explore powerful models effortlessly."
-      image: "https://msty.ai/blog/mlx/apple-m5-mlx.png"
-      url: "https://msty.ai/blog/mlx-top-5"
-previewImage: "/images/mlx/mlx-model-hub.png"
---
-
-MLX (Apple Machine Learning eXchange) is Apple’s machine learning framework optimized for Apple Silicon. It enables fast, efficient training and inference using GPU and CPU acceleration on macOS and iOS devices. **Msty Studio Desktop** supports MLX for running local models natively, making it ideal for private, high-performance AI workflows on your Mac.
-
-## Adding MLX Models
-Adding and managing MLX models is fundamentally similar to adding and managing other local models in Msty Studio. 
-
-In **Model Hub**, you can view featured MLX models and search for models on the MLX Hugging Face Community tab. 
-
-![mlx models](/images/mlx/mlx-model-hub.png)
-
-Please note that there are fewer models that currently support MLX.
-
-## Managing MLX Service
-
-You can manage and configure the MLX service in **Settings > MLX Service**. Here, you can start or stop the MLX service, which is required to run MLX models locally.
-
-![mlx service](/images/mlx/mlx-service.png)
-
-You can also view the service health, stop and start the service, view the endpoint, version, logs, and more.
-
-::Resources
@@ -1,62 +0,0 @@
---
-title: Llama.cpp Models
-description: Adding and managing Llama.cpp Models in Msty Studio
-navTruncate: false
-resources:
-previewImage: "/images/welcome-to-msty.png"
---
-
-llama.cpp is an open source C/C++ library that performs efficient inference on large language models with minimal setup and optimized performance across various hardware.
-
-This provides another option for a local inference engine in Msty Studio in addition to Ollama and MLX. 
-
-::alert{type="info" icon="tabler:info-circle"}
-Llama.cpp support is an experimental feature and you may encounter issues. Please report any problems you find on our Discord server to help us improve the experience. 
-::
-
-Llama.cpp can be installed during new user onboarding or from **Model Hub > Llama.cpp**. 
-
-## Adding Llama.cpp Models
-
-In **Model Hub**, you can view featured Llama.cpp models and search for models on the Llama.cpp Hugging Face Community tab. 
-
-Click on the download icon to download and install a model locally. 
-
-## Managing Llama.cpp Service
-
-You can manage and configure the Llama.cpp service in **Settings > Llama.cpp Service**. Here, you can start or stop the Llama.cpp service, which is required to run Llama.cpp models locally.
-
-You can also view the service health, stop and start the service, view the endpoint, version, logs, and more.
-
-### GPU support
-
-If your system has a compatible GPU, you can enable GPU support for Llama.cpp models by selecting the corresponding option under the Llama.cpp service ellipsis menu. 
-
-## Llama.cpp Model Parameters
-
-LLama.cpp provides a few features that can give them an edge when used during conversations. 
-
-Next to the model selection, when you have a Llama.cpp model selected, click on the **Model Parameters** icon.
-
-**Here, you will see options specific to Llama.cpp, including**:
-
-### Num ctx default to model max
-This is the context window where you can select the option to use the max amount of context for a mode. 
-
-The specific max value may not be known to Llama.cpp or Msty Studio; however, this option will set it to the max value. 
-
-Setting to the max will benefit conversations as more context will be held onto, which will result in fewer hallucinations and improved conversation continuity. 
-
-This does come at a cost in the form of your device's system performances being expended, which may result in decreased system performance. 
-
-### Truncation Strategy 
-
-As conversation get longer, you can set a truncation strategy so that you can continue conversations without getting a context limit reached message. 
-
-**Options**: 
- **Truncate Middle** this truncates the middle portions of the conversation. This setting is ideal when the first parts of the conversation are important to maintain the overall context. Use this if the first interaction set the stage for the overall conversation. 
- **Truncate Old** - this truncates the first messages of the conversation. This setting is idea for continued conversations where the first messages are not critical to the continuity of the conversation. Use this if the latest messages are the most critical for continuity. 
- **None** - this does not truncate any messages in an ongoing conversation. Use this setting if full historical context is needed. However, this does run the risk of context limits being exceeded. 
-
-
-::Resources
@@ -0,0 +1,95 @@
+---
+title: Settings
+description: Configure appearance, services, and app behavior in Msty Studio
+navTruncate: false
+resources:
+  videos:
+  blogs:
+previewImage: "/images/welcome-to-msty.png"
+---
+
+Use Settings to customize how Msty Studio looks and behaves.
+
+## General
+
+### Appearance
+You can control:
+
+- Theme preference (Light, Dark, or System)
+- Interface mood and color styling
+- Accent and base color preferences
+- [Mode](/settings/modes)
+- Font size and font style
+- Code theme
+- Rendering modules (Markdown, Mermaid, Math, GFM, code highlights, collapsible blocks, links)
+- RTL support
+
+### App Info
+- App version and update actions
+- Data paths for app data and logs
+- Reset app settings
+- Help links and support links
+- Optional web security override for specific CORS troubleshooting
+
+## Agent Mode
+
+Settings include:
+
+- Adapter update checks
+- Preferred editor selection
+- Vim mode toggle
+- Diff display preferences
+- Local provider enable or disable controls
+
+## Local AI Service
+
+If Local AI Service is installed, settings include:
+
+- Models path, health, endpoint, and service version
+- Start, stop, restart, update, and remove actions
+- Service configuration (port, parallel chats, loaded models, network access, logs)
+- Model-level configuration like keep-alive and advanced JSON options
+
+## MLX Service
+
+On Apple Silicon devices, MLX settings include:
+
+- Model path, health, endpoint, and service version
+- Update and remove actions
+- Network and logging options
+
+## Vibe CLI Proxy
+
+Vibe CLI Proxy settings include:
+
+- Service health, endpoint, and version
+- Network access, logs, port, and retries
+- Auth folder details
+- Provider authentication controls
+
+See [Vibe CLI Proxy](/managing-models/vibe-cli-proxy) for provider details.
+
+## Remote Service and Data
+
+- Remote connections: [Remote Connections](/settings/remote-connections)
+- Backups and restore: [Data Backups and Restoration](/settings/data-backups)
+- Data migration: [Quick Start data migration](/getting-started/quick-start#data-migration-for-msty-app-users)
+
+## Keyboard Shortcuts
+
+Manage shortcuts in **Settings > Keyboard Shortcuts**. This includes the Command Palette shortcut and Shiftcuts behavior.
+
+## Desktop Extras
+
+### Log Viewer
+View, filter, and copy logs, including live log streaming.
+
+### Notifications
+Review app events and errors in one place.
+
+### Always On Top
+For Desktop conversations, you can toggle **Always On Top** from the conversation actions menu.
+
+## License and Access
+
+Add your license key to unlock paid features.
@@ -0,0 +1,67 @@
+---
+title: Keyboard Shortcuts
+description: Customize keyboard controls in Msty Studio
+navTruncate: false
+resources:
+  videos:
+    - "IF026hpYWTw"
+  blogs:
+previewImage: "/images/shortcuts/keyboard-shortcuts.png"
+---
+
+Keyboard shortcuts help you move through Msty Studio faster.
+
+You can manage them in **Settings > Keyboard Shortcuts**.
+
+![keyboard shortcuts](/images/shortcuts/keyboard-shortcuts.png)
+
+## Useful Defaults
+
+- `Cmd/Ctrl + K` opens Command Palette
+- `Cmd/Ctrl + N` starts a new conversation
+- `Cmd/Ctrl + T` adds a split chat
+- `Cmd/Ctrl + 1` toggles the sidebar
+- `Cmd/Ctrl + 8` toggles the workspace tray
+- `Cmd/Ctrl + ,` opens settings
+- `Cmd/Ctrl + Shift + F` opens conversation search
+- `Cmd/Ctrl + W` enters split removal mode
+
+## Command Palette Shortcut
+
+Command Palette is the fastest way to run actions by name.
+
+- Press `Cmd/Ctrl + K`
+- Type the action you want
+- Press `Enter` to run it
+
+## Vim Motions (Agent Mode)
+
+If Vim Mode is enabled in **Settings > Agent Mode**, you can use:
+
+- `gg` to jump to the start
+- `G` to jump to the end
+
+## Shiftcuts
+
+Shiftcuts are quick actions triggered by pressing `Shift` twice, then a key.
+
+- `t` creates a new split chat tab
+- `n` creates a new conversation
+- `1` toggles the sidebar
+- `e` opens quick environment variable selection
+
+## Disable Shiftcuts
+
+::steps
+### Open Keyboard Shortcuts
+Go to **Settings > Keyboard Shortcuts**.
+
+### Disable Shiftcuts
+Turn off the Shiftcuts toggle at the top of the page.
+::
+
+::alert{type="info" icon="tabler:info-circle"}
+Studio Web behavior can depend on your browser shortcut rules.
+::
+
+::Resources
@@ -0,0 +1,41 @@
+---
+title: Command Palette
+description: Quickly run actions and navigate Msty Studio
+navTruncate: false
+resources:
+  videos:
+  blogs:
+previewImage: "/images/welcome-to-msty.png"
+---
+
+Command Palette gives you one searchable command surface for navigation, creation, settings, and desktop actions.
+
+Open it with **Cmd/Ctrl + K**.
+
+## Major Parts
+
+### Create commands
+Start new conversations, split chats, persona or crew chats, forge canvases, and workspaces.
+
+### Navigation commands
+Jump directly to Model Hub, Toolbox, Persona Studio, Prompt Studio, Knowledge Stacks, environments, and notifications.
+
+### Settings and appearance commands
+Open settings sections, toggle mini map, and quickly switch theme, mode, split width, accent, or base color.
+
+### Desktop commands
+On Desktop, run actions like checking for updates or opening the log viewer from the same interface.
+
+## Using Command Palette
+
+1. Press **Cmd/Ctrl + K**.
+2. Type what you want to do, such as `new`, `persona`, or `settings`.
+3. Move through results with arrow keys or `Tab`.
+4. Press `Enter` to run the selected command.
+5. Press `Esc` to close.
+
+[Image placeholder: Command Palette with search input and grouped command results]
+
+## Tip
+
+You can customize the Command Palette shortcut in **Settings > Keyboard Shortcuts**.
@@ -15,13 +15,18 @@ Default prompts are located in the Settings > Default Prompts section.
 ## Default Prompts

 The Default Prompts section contains prompts for the following features:
+- **Attachment Prompt**: default prompt used when you send attachments without any additional user text
 - **Context Shield Summary**: used to summarize long context into shorter summaries so that you can save on context length and tokens
+- **Crew Mode**: background instructions applied to crew persona responses, including the crew roster and `@mention` handoffs
+- **Icon Finder**: selects the most appropriate icon based on a user description
 - **Knowledge Stack Context**: included when sending chunks from your Knowledge Stack to the model; this will provide instructions on how to use the context
 - **Knowledge Stack Simple Search**: this prompt is used to help the model generate search queries to find relevant documents in your Knowledge Stack
 - **Knowledge Stack Structured Search**: for a more semantic search, this prompt helps the model generate better search queries for your Knowledge Stack
+- **Live Context Default**: default instructions for using live context data in model responses
 - **Real-Time Data Query Synthesis**: creates queries to fetch real-time data in a format common to standard search engines
 - **Title Generation**: used to generate titles for chats based on the conversation content
- **Youtube Attachments**: provides context to model about how to use YouTube video transcripts when included as attachments in chats
+- **User Persona Memory Generation**: creates a structured memory draft from a selected conversation message for user persona memories
+- **YouTube Attachments**: provides context to the model about how to use YouTube video transcripts when included as attachments in chats

 ## Editing Default Prompts

@@ -31,4 +36,4 @@ Many of the default prompts include variables, such as `{input}` or `{content}`.

 At the bottom of the text editor, there are buttons to fetch a prompt from **Quick Prompts**, to **Clear Content**, and to **Reset to Default**.

-::Resources
+::Resources
@@ -0,0 +1,2 @@
+title: Settings
+icon: tabler:settings
@@ -13,7 +13,7 @@ previewImage: "/images/sidecar.png"

 Msty Sidecar is a companion desktop application that brings powerful local capabilities to Msty Studio Web, enabling features that go beyond what’s possible in a standard web app.

-**Before using Sidecar, first attempt to connect using Msty Studio Desktop as outlined in the [Remote Connections guide](/features/remote-connections).**
+**Before using Sidecar, first attempt to connect using Msty Studio Desktop as outlined in the [Remote Connections guide](/settings/remote-connections).**

 Using the Remote Connections feature with Msty Studio Desktop is the recommended approach for most users, as it provides a seamless and integrated experience.

@@ -22,7 +22,7 @@ Using the Remote Connections feature with Msty Studio Desktop is the recommended
 Sidecar unlocks the following features in Msty Studio Web:

 - Enables fetching Real-Time Data from the internet
- Enables setting up [Tools](/features/toolbox/tools) on your local machine
+- Enables setting up [Tools](/toolbox/tools) on your local machine
 - Enables local AI model management

 ::alert{type="info" icon="tabler:info-circle"}
@@ -84,7 +84,7 @@ Safari web browser unfortunately has constraints which do not allow for direct a

 However, you can still connect Safari using the following methods:

- [Using Remote Connections with tunneling](/features/remote-connections#connecting-remotely-to-local-ai-including-from-mobile-devices) **RECOMMENDED**
+- [Using Remote Connections with tunneling](/settings/remote-connections#connecting-remotely-to-local-ai-including-from-mobile-devices) **RECOMMENDED**
 - [Enabling Sidecar's Tunneling Feature](/how-tos/sidecar#connecting-remotely-to-local-ai-including-from-mobile-devices)
 - [Using Tailscale](/how-tos/setup-tailscale-for-sidecar)

@@ -85,7 +85,7 @@ Now that you have the URL, you can connect to Sidecar from another device that i

 On the other device, open a web browser and navigate to [Msty Studio](https://msty.studio).

-If this is the first time you are using the device to access Msty Studio, you'll need to enter your Aurum license key - see [Quick Start Guide](/quick-start) for more information.
+If this is the first time you are using the device to access Msty Studio, you'll need to enter your Aurum license key - see [Quick Start Guide](/getting-started/quick-start) for more information.

 In Msty Studio, click **Modes** on the left menu and select the Edit icon for editing the Sidecar connection.

@@ -5,7 +5,7 @@ navTruncate: false
 previewImage: "/images/welcome-to-msty.png"
 ---

-The [Live Contexts](/features/toolbox/live-contexts) feature lets you pull data from external endpoints to provide real-time context when interacting with Personas, LLMs, or other tools. 
+The [Live Contexts](/toolbox/live-contexts) feature lets you pull data from external endpoints to provide real-time context when interacting with Personas, LLMs, or other tools. 

 The list below provides example endpoints you can explore and test. **Please note:** these are third-party endpoints. We do not maintain them and cannot guarantee the accuracy, availability, or reliability of the data returned.  

@@ -1,50 +0,0 @@
---
-title: Personas
-description: Get started with Personas in Msty
-navTruncate: false
-resources:
-  videos:
-    - "7KMM8x77DOk"
-    - "ym8Rm-PePtU"
-    - "icpxQH5S80Y"
-  blogs:
-    - title: "That Guy - Creating the Devils Advocate Persona"
-      description: "We all know one... Someone who has to always counter an argument, no matter what. This is how you can create the ultimate Devil's Advocate."
-      image: "https://msty.ai/blog/that-guy/the-goats.png"
-      url: "https://msty.ai/blog/that-guy"
-previewImage: "/images/personas.png"
---
-
-Personas is a powerful tool that allows you to create custom AI agents tailored to specific conversational contexts.
-
-![Msty Personas](/images/personas.png)
-
-## Create new Personas
-
-You can create new personas from the **Personas** section, accessible on the left sidebar menu. You don't need to start from scratch though.
-
-Select the down arrow next to **New Persona** and then select **Import Default Personas** to import a collection of Personas. You can edit any of these personas to customize them to fit your needs.
-
-### Add a new custom Persona
-
-::steps
-
-1. Select the **New Persona** button - this will display form fields for configuring your new persona
-2. Enter a **Name** you'd like to refer to your Persona by and select a corresponding icon
-3. Fill in the **System Prompt** for the Persona. Prompts are an important part of the equation for making the best use of AI chat conversations. Be clear and descriptive about what you are wanting for the desired output. Don't be afraid to provide examples of a quality output that you are looking for so that the AI can reference the example when crafting its response.
-4. Select whether you want to add the prompt before the system prompt, to replace the system prompts, or add after the system prompts.
-5. Enable any additional settings to:
-  - **Hide and isolate system prompt** which automatically hides and isolates user messages when sending Persona prompt
-  - **Isolate response** which automatically isolates the generated response, excluding it from being added as context in follow-up messages
-  - **Auto Response** which will automatically enable the Persona as an auto-responding persona 
-6. Enter a brief **Description** of the Persona
-7. Include **Add Ons** such as any relevant [attachments](/features/attachments), [real-time data](/features/real-time-data), related [toolsets](/features/toolbox/toolsets), context shield, desired model and any pertinent model parameters. Add-Ons add a ton of power and flexibility to your Persona and can take them from a simple canned prompt to a full-blown Agent.
-8. **Few-Shot Prompts** let you provide example prompts to guide the Persona's responses, helping it understand the desired style or context of replies based on previous examples.
-
-::
-
-## Using Personas in conversations
-
-[See how Personas are used in conversations](/features/conversations/main-chat#personas)
-
-::Resources
@@ -1,80 +0,0 @@
---
-title: Keyboard Shortcuts
-description: Customize actions with keyboard shortcuts and shiftcuts in Msty Studio
-navTruncate: false
-resources:
-  videos:
-    - "IF026hpYWTw"
-  blogs:
-previewImage: "/images/shortcuts/keyboard-shortcuts.png"
---
-
-## How to Use Keyboard Shortcuts
-In Msty Studio, you can customize shortcuts for various actions so that you can perform them quickly without needing to navigate through menus. This is particularly useful for power users who want to streamline their workflow.
-
-You can access the keyboard shortcuts settings in **Settings > Keyboard Shortcuts**. Here, you can view the current shortcuts and customize them to suit your preferences. You can also reset them to their default values if needed.
-
-![keyboard shortcuts](/images/shortcuts/keyboard-shortcuts.png)
-
-Some actions have a default shortcut assigned, which you can use that shortcut or customize to your liking.
-
-## Spell Check Toggle (Desktop)
-
-For Desktop users, Msty Studio provides an option to disable the built-in spell check feature. This is particularly useful for developers writing code or for users whose language isn't supported well by the spell checker. When disabled, the red underlines for unrecognized words will no longer appear.
-
-### How to Toggle Spell Check
-
-::steps
-### Open General Settings
-Go to **Settings > General**.
-
-### Find Spell Check Option
-Scroll down to locate the spell check toggle.
-
-### Change and Restart
-Switch the spell check setting as desired, then **restart the application** for the changes to take full effect.
-::
-
-::alert{type="info" icon="tabler:info-circle"}
-Studio Web can disable via the browser settings. For Studio Desktop, please note your OS settings may override this option.
-::
-
-## How to Use Shiftcuts
-
-Shiftcuts are a set of keyboard shortcuts that allow you to quickly access common tasks in Msty Studio. By pressing the shift key twice in quick succession, you can activate a mode that enables you to perform various actions without needing to navigate through menus or use the mouse.
-
-To activate Shiftcuts, simply **press the shift key twice quickly**. This will enable the Shiftcut mode, allowing you to use the following shortcuts. **You will then need to press the corresponding key** for the action you want to perform before the mode times out. When you double click the shift key, you will see a yellow up icon that displays - you'll have until this icon disappears to press the corresponding key for the action you want to perform.
-
-Press the following keys to perform the corresponding actions:
-
-### **t** - Create a new split chat tab
-
-This will open a new split chat tab, allowing you to have multiple conversations open at once. You can use this feature to compare responses from different models or to keep track of multiple discussions simultaneously.
-![shiftcut split chat](/images/shiftcuts/shiftcut-split.png)
-
-### **n** - Create a new conversation
-
-This will create a new conversation in the current tab, allowing you to start fresh without losing your previous discussions.
-![shiftcut new convo](/images/shiftcuts/shiftcut-new.gif)
-
-### **1** - Toggle sidebar
-
-This will toggle the visibility of the sidebar, allowing you to maximize your workspace or access the sidebar features as needed.
-![shiftcut toggle sidebar](/images/shiftcuts/shiftcut-toggle.gif)
-
-### **e** - Show Quick Select Environment Variable picker
-
-This will open a picker that allows you to quickly select an [environment variable](/features/environments). This is useful for inserting variables into your conversations or for quickly accessing specific information.
-![shiftcut env picker](/images/shiftcuts/shiftcut-env.png)
-
-## How to Disable ShiftCuts
-
-::steps
-### Open Keyboard Shortcuts Settings
-Navigate to **Settings > Keyboard Shortcuts**.
-
-### Toggle the Feature Off
-At the top of the keyboard shortcuts page, you'll find a switch to enable or disable the Shift Cut feature. Turn it off to deactivate the shortcut completely.
-::
-
-::Resources
@@ -1,113 +0,0 @@
---
-title: Settings
-description: Connect remotely to Msty Studio Desktop
-navTruncate: false
-resources:
-  videos:
-  blogs:
-previewImage: "/images/welcome-to-msty.png"
---
-
-The Settings section is where you can configure various aspects of Msty Studio to tailor the experience to your needs.
-
-## General
-
-### Appearance
-
-You can customize the appearance of Msty Studio by modifying the following settings:
-* Color preference - Light, Dark, or System Default
-* [Mode](/features/modes)
-* Font Size
-* Font Style
-* Code Theme - for code returned by models
-* Rendering Modules - enable/disable the following:
-    * Markdown - formats markdown content
-    * Mermaid Diagrams
-    * Math LaTeX
-    * GitHub Flavored Markdown
-    * Code Highlights
-    * Collapsing Tags
-    * Enable Links - links returned by models are disabled by default; to make them clickable, enable this setting
-* Right-To-Left (RTL) Support - for languages that require right-to-left text direction
-
-### Application Info
-* App Version - displays your installed version. You can select the overflow menu to check and install updates as well as enable/disable automatic updates
-* App Settings - reset to default
-* Data Paths - provides location of app data and app logs
-* Help and Discussions - links to these docs and [Discord](https://msty.ai/discord)
-* Disable Web Security - enable if your are experiencing CORS related issues; only recommended for specific use cases and you'll need to restart Msty Studio
-
-
-## Local AI Service
-Contains information about the local AI service if you have this installed. 
-
-* Models Path - file path to where models are stored
-* Service Health - displays current status with options to stop, start, and restart
-* Service Endpoint - endpoint if you'd like to connect other applications to the local AI service
-* Service Version - displays current version with options to check for updates, remove service, or [install from archive](/getting-started/onboarding#install-local-ai-from-archive-file)
-* Manage Local AI Models - links to Model Hub > Local AI Models
-* Service Configurations
-    * Configure port number
-    * Maximum Parallel Chats
-    * Maximum Loaded Models
-    * Enable Network Access - allow other devices on local network to connect
-    * Allow Access from Msty Studio Web - enable to allow Msty Studio Web to connect and use local AI services
-    * Allowed Network Origins - manage permitted external origins
-    * Capture Service Logs - enable local AI services logging
-    * Advanced Configurations - set local environment variables; in JSON format
-* Model Configurations
-    * Model Keep-Alive Timeout
-    * Advanced Configurations - enter valid JSON to pass additional parameters to models during chat sessions
-
-
-
-## MLX Service
-
-MLX is availble for Apple Silicon devices only. 
-
-* Model Path - file path to where models are stored
-* Service Health - displays current status with options to stop, start, and restart
-* Service Endpoint - endpoint if you'd like to connect other applications to the local AI service
-* Service Version - displays current version with options to check for updates and remove service
-* Manage MLX AI Models - links to Model Hub > MLX AI Models
-* Service Configurations
-    * Enable Network Access - allow other devices on local network to connect
-    * Capture Service Logs - enable local AI services logging
-
-## Vibe CLI Proxy
-
-Vibe CLI Proxy allows Msty Studio to connect to various CLI providers through a secure local proxy.
-
-* Service Health - displays current status with options to stop, start and restart
-* Service Endpoint - endpoint if you'd like to connect other applications to the vibe CLI proxy
-* Service Version - displays current version with options to check for updates and remove service
-* Service Configurations
-    * Enable Network Access - allow other devices on the network to reach the proxy
-    * Capture Service Logs - persist proxy logs for troubleshooting (may increase disk usage)
-    * Port - the local port where the proxy service listens for requests
-    * Retries - number of retry attempts for failed upstream requests
-    * Auth Folder - path where Vibe CLI Proxy stores OAuth tokens for connected providers. Managed automatically; not editable
-    * Authentication - securely link your AI accounts so Vibe CLI Proxy can call their APIs on your behalf. When you connect, a browser window opens for that provider where you complete sign-in, setup, and authorize [Vibe CLI Proxy providers](/features/vibe-cli-proxy)
-
-
-
-## Remote Service
-
-See [Remote Connections](/features/remote-connections) for more information.
-
-## Data
-See [Data Backups and Restoration](/features/data-backups) and [Data Migration](/getting-started/quick-start#data-migration-for-msty-app-users) for more information.
-
-## Keyboard Shortcuts
-See [Keyboard Shortcuts](/features/keyboard-shortcuts) for more information.
-
-## Log Viewer (Desktop Only)
-You can view application logs to help troubleshoot issues. You can filter by log level, search for specific terms, and copy log entries.
-
-You can even enable live logging to see log entries in real-time as they occur.
-
-## Notifications
-The Notifications section is an additional way to view alerts to help with troubleshooting issues. This section lists key app events, typically related to errors toasts you may have seen. 
-
-## License and Access
-Enter your License to unlock advanced features. 
@@ -1,2 +0,0 @@
-title: Features
-icon: tabler:sparkles
@@ -0,0 +1,105 @@
+---
+title: Managing Models
+description: Add and manage AI models in Msty Studio
+navTruncate: false
+resources:
+  videos:
+    - "CQtkVGItavA"
+    - "hQ8BcdpQwlw"
+    - "lwigyQ2whY0"
+    - "cmL1wgHkbno"
+    - "jUtla3fse_Y"
+    - "w346rl5gQo4"
+    - "hpoWWoT3kBA"
+  blogs:
+    - title: "Unleashing Local AI - Transform Your Coding Experience with Msty"
+      description: "Discover how to enhance your coding workflow using local AI models with Msty, GitHub Copilot, and Roo Code for personalized, offline support."
+      image: "https://msty.ai/blog/toolbox/unleash-local-ai.png"
+      url: "https://msty.ai/blog/local-ai-coding-assistants"
+    - title: "The AI Settings Dictionary"
+      description: "AI settings are a powerful way to customize your AI experience. Here is what they all mean and how to use them."
+      image: "https://msty.ai/blog/ai-settings-dictionary/ai-settings-dictionary.png"
+      url: "https://msty.ai/blog/the-ai-settings-dictionary"
+    - title: "5 Ways to Use Local Inference with Msty Studio"
+      description: "Explore five practical ways enterprises can run local AI inference with Msty Studio, keeping data private while giving teams a powerful, easy-to-manage front end for productivity."
+      image: "https://msty.ai/blog/enterprise/5-ways-to-use-local-inference.png"
+      url: "https://msty.ai/blog/top-5-local-inference-options"
+    - title: "5 Reasons You Should Try MLX with Msty Studio"
+      description: "Discover how MLX and Msty Studio unlock fast, local AI on Apple Silicon Macs, letting you create, experiment, and explore powerful models effortlessly."
+      image: "https://msty.ai/blog/mlx/apple-m5-mlx.png"
+      url: "https://msty.ai/blog/mlx-top-5"
+    - title: "Powerful, Local Inference with LLaMA.cpp"
+      description: "A focused guide to using LLaMA.cpp in Msty Studio, including quick setup, key settings, and why LLaMA.cpp is a strong local inference engine."
+      image: "https://msty.ai/blog/llamacpp/llama-cpp.png"
+      url: "https://msty.ai/blog/llama-cpp-in-msty-studio"
+previewImage: "/images/model-hub.png"
+---
+
+Model Hub is where you connect providers, install local models, and tune model behavior for chats.
+
+![adding new models](/images/model-hub.png)
+
+## Model Hub Workflow
+
+For most users, model setup follows this order:
+
+1. Choose between online providers, local models, or both
+2. Connect online providers, install local models, or do both
+3. Set defaults and model purpose tags
+4. Tune model-specific options as needed
+
+## Online and Local Models
+
+Msty Studio supports two model sources:
+
+- **Online Providers**: Hosted APIs that you connect with API keys
+- **Local Models**: Models you install and run on your own machine
+
+### Online Providers
+
+Use online providers when you want quick access to hosted models and managed infrastructure.
+
+Go to [Online Providers](/managing-models/online-providers) for supported providers, setup steps, and OpenAI-compatible bring-your-own endpoints.
+
+### Local Models
+
+Use local models when you want more control over privacy, offline access, and local performance tuning.
+
+Go to [Local Models](/managing-models/local-models) for install and import paths, plus MLX and Llama.cpp setup.
+
+## Find the Right Model Faster
+
+Use [Model Matchmaker](/managing-models/model-matchmaker) when you are unsure which model to start with.
+
+## Organize Models for Daily Use
+
+### Set a Default Model
+
+In the conversation model selector, click the star icon to set a default model.
+
+### Rename Models and Providers
+
+In Model Hub or the conversation model selector, click the edit icon to rename a provider or model.
+
+### Set Model Purpose Tags
+
+Purpose tags help categorize what each model is best at.
+
+![model purpose](/images/model-purpose.png)
+
+- **Text**: General text generation and understanding
+- **Coding**: Code generation, analysis, and debugging
+- **Tools**: Tool/API usage with Toolbox (MCP)
+- **Image**: Image generation models (see [Image Generation](/managing-models/image-gen))
+- **Vision**: Image understanding and analysis
+- **Embedding**: Retrieval and vector workflows, including Knowledge Stacks
+- **Streaming**: Near real-time data processing
+- **Thinking**: Reasoning models with extended thinking controls
+
+### Provider and Model Logos
+
+You can change provider and model logos from the edit dialog in Model Hub.
+
+![change model logo](/images/change-provider-model-logo.png)
+
+::Resources
@@ -0,0 +1,64 @@
+---
+title: Online Providers
+description: Connect hosted AI providers and manage cloud model access
+navTruncate: false
+previewImage: "/images/model-hub.png"
+---
+
+Online providers let you use hosted models with your API keys, without running model inference on your device.
+
+Need API key links? See [Find Online Model API Keys](/how-tos/find-api-keys).
+
+## Connect an Online Provider
+
+::steps
+### Open Model Providers
+Go to **Model Hub > Model Providers**.
+
+### Add Provider
+Select **Add Provider** and choose your provider.
+
+### Enter Credentials
+Add your API key (and any required endpoint details), then save. If you need key locations, use [Find Online Model API Keys](/how-tos/find-api-keys).
+
+### Test in Chat
+Open a conversation and select one of the provider's models.
+::
+
+## Supported Providers
+
+Msty Studio supports these online provider options:
+
+- Anthropic
+- Cohere
+- Gemini
+- Groq
+- Mistral AI
+- OpenAI
+- OpenRouter
+- Perplexity
+- Together AI
+- SambaNova
+- xAI
+- Azure OpenAI
+- Amazon Bedrock
+
+For key locations and endpoint references, see [Find Online Model API Keys](/how-tos/find-api-keys).
+
+## Bring Your Own Provider
+
+If your provider exposes an OpenAI-compatible API, you can connect it by using an OpenAI-compatible endpoint in Model Providers.
+
+This is useful for:
+
+- Self-hosted gateways
+- Enterprise AI platforms
+- Private inference endpoints that follow the OpenAI API format
+
+## Manage Provider Setup
+
+After connecting, you can:
+
+- Rename providers and models for readability
+- Set a default model in chat
+- Apply model purpose tags from [Managing Models](/managing-models)
@@ -0,0 +1,99 @@
+---
+title: Local Models
+description: Install, import, and run local AI models in Msty Studio Desktop
+navTruncate: false
+previewImage: "/images/model-hub.png"
+---
+
+Local models run on your own machine, giving you more control over privacy, performance, and offline workflows.
+
+## Local Model Options at a Glance
+
+Use this quick guide to decide where to start:
+
+- [Local AI (via Ollama)](/managing-models/local-models#local-ai-via-ollama): Best for fast setup, broad model availability, and day-to-day local usage.
+- [MLX Models (Apple Silicon)](/managing-models/local-models#mlx-models-apple-silicon): Best for Apple Silicon users who want optimized local performance with MLX-native models.
+- [Llama.cpp Models](/managing-models/local-models#llamacpp-models): Best for advanced local tuning, flexible hardware support, and low-level runtime controls.
+
+If you are unsure, start with Local AI first.
+
+If you are not sure which model to pick, use [Model Matchmaker](/managing-models/model-matchmaker).
+
+## Local AI (via Ollama)
+
+Msty Studio's Local AI backend is **Ollama**.
+
+Use Ollama when you want the easiest local model workflow for install, discovery, and everyday chat use.
+
+Go to **Model Hub > Local AI Models**.
+
+You can use:
+
+- **Featured Models** for curated installs
+- **Installed Models** to manage currently installed models
+- **Ollama Models** and **Hugging Face Models** to search and install
+- **Import GGUF Model** for local GGUF files
+- **Import Safetensors Model** for local Safetensors files
+
+### Import GGUF Model
+
+Open **Local AI Models > Import GGUF**, select your file, then choose whether to:
+
+- Symlink to the existing file location
+- Copy the file into Msty Studio's models directory
+
+### Import Safetensors Model
+
+Open **Local AI Models > Import Safetensors** and select your Safetensors file.
+
+## MLX Models (Apple Silicon)
+
+MLX is Apple's machine learning framework for Apple Silicon, supported in **Msty Studio Desktop**.
+
+Use MLX when you are on Apple Silicon and want strong local performance with MLX-optimized models.
+
+In Model Hub, browse featured MLX models or search the MLX Hugging Face community.
+
+![mlx models](/images/mlx/mlx-model-hub.png)
+
+### Manage MLX Service
+
+Use **Settings > MLX Service** to manage service health, endpoint, version, logs, and start or stop controls.
+
+![mlx service](/images/mlx/mlx-service.png)
+
+## Llama.cpp Models
+
+Llama.cpp is a local inference engine designed for efficient performance across different hardware.
+
+Use Llama.cpp when you want deeper inference controls and hardware-specific tuning options.
+
+You can set it up during onboarding or from **Model Hub > Llama.cpp**. In Model Hub, browse featured models or search the Llama.cpp Hugging Face community to install models.
+
+### Manage Llama.cpp Service
+
+Use **Settings > Llama.cpp Service** to manage health, endpoint, version, logs, and start or stop controls.
+
+### Llama.cpp GPU Support
+
+If your system has a compatible GPU, enable acceleration from the Llama.cpp service ellipsis menu.
+
+### Llama.cpp Model Parameters
+
+When a Llama.cpp model is selected in chat, open **Model Parameters** for Llama.cpp-specific settings.
+
+#### Num ctx default to model max
+
+Uses the maximum available context window, which can improve long-chat continuity at the cost of higher system usage.
+
+#### Truncation Strategy
+
+Controls how history is trimmed when context limits are reached.
+
+- **Truncate Middle**: Keeps early and recent context, trims middle content
+- **Truncate Old**: Trims oldest messages first
+- **None**: No trimming, with higher risk of hitting context limits
+
+## General GPU Support
+
+If your system has a compatible GPU, enable GPU support in **Settings > Local AI > Service ellipsis menu** for services that support acceleration.
@@ -0,0 +1,42 @@
+---
+title: Model Matchmaker
+description: Find the best model for your task using ranked recommendations
+navTruncate: false
+previewImage: "/images/matchmaker.png"
+---
+
+Model Matchmaker helps you choose a starting model when you are not sure which one to use.
+
+Set your priorities, review ranked suggestions, then test the top picks in real conversations.
+
+![msty matchmaker](/images/matchmaker.png)
+
+## When to Use Matchmaker
+
+Use Matchmaker when you:
+
+- Are adding a new provider and need a starting model
+- Need a fast recommendation instead of trial-and-error
+- Want to compare candidates before setting defaults
+
+## How Matchmaker Works
+
+::steps
+### Open Matchmaker
+Go to **Model Hub > Matchmaker**.
+
+### Set Priorities
+Choose what matters most for your task.
+
+### Review Ranked Models
+Matchmaker returns ordered suggestions based on your priorities.
+
+### Validate in Chat
+Test top models with real prompts in [Conversations](/conversations/main-chat), [Split Chat](/conversations/split-chat), or [Turnstiles](/add-ons/turnstiles).
+::
+
+![msty matchmaker ranked models](/images/ranked-models.png)
+
+## Recommended Follow-Up
+
+After choosing a model, set it as default or tag its purpose from [Managing Models](/managing-models).
@@ -14,7 +14,7 @@ Please note that these settings are _generally_ available across models; however

 ## Thinking Effort

-See the [Thinking Effort](/features/thinking-effort) docs for more information on how to use the thinking effort feature.
+See the [Thinking Effort](/managing-models/thinking-effort) docs for more information on how to use the thinking effort feature.


 ## Advanced Runtime Configurations
@@ -0,0 +1,40 @@
+---
+title: Context Explorer
+description: Understand context windows, memory usage, and model fit
+navTruncate: false
+resources:
+  videos:
+  blogs:
+previewImage: "/images/welcome-to-msty.png"
+---
+
+Context Explorer helps you understand how model context size, VRAM, concurrency, and engine behavior interact before you run real workloads.
+
+Open it from **Model Hub > Context Explorer**.
+
+## Major Parts
+
+### Guided modes
+Start with guided paths like **Fit**, **Serve**, and **Learn**, or jump directly into **Free Explorer**.
+
+### Interactive lessons
+Use short lessons to learn context budgeting, overflow behavior, and concurrency tradeoffs.
+
+### Engine behavior simulation
+Compare behavior across Ollama, vLLM, MLX, and llama.cpp, including overflow handling and context controls.
+
+### Scenario presets
+Load presets, adjust context length and concurrency, then simulate to see memory impact and fit status.
+
+## Using Context Explorer
+
+1. Pick an engine, model size, and hardware profile.
+2. Adjust context length, precision, and concurrency.
+3. Run simulations and inspect memory buckets.
+4. Check fit status before applying similar settings in production.
+
+[Image placeholder: Context Explorer showing memory bucket bar and engine controls]
+
+## Tip
+
+Use Context Explorer when tuning local models for multi-user or long-context workflows.
@@ -0,0 +1,2 @@
+title: Managing Models
+icon: lucide:brain
@@ -1,5 +1,5 @@
 ---
-title: Main Chat
+title: Conversations
 description: Conversations done right
 navTruncate: false
 resources:
@@ -12,19 +12,21 @@ previewImage: "/images/conversations/persona-mode-convo.png"

 Conversations in Msty Studio are designed to be intuitive and user-friendly, allowing you to engage with the selected model seamlessly.

+## Choose a Conversation Type
+
+Use this quick guide to decide where to start:
+
+- **Normal Conversations** ([Conversations](/conversations/main-chat)): Best for everyday chatting, drafting, Q&A, and iterative work with one model.
+- **Persona Conversations** ([Persona Conversations](/conversations/persona-conversations)): Best when you want a conversation guided by a specific role, voice, or expertise.
+- **Crew Mode Conversations** ([Crew Conversations](/conversations/crew-chats)): Best when you want multiple personas to respond to the same prompt so you can compare perspectives.
+- **Agent Mode Conversations** ([Agent Mode](/agent-mode/agent-mode)): Best for multi-step tasks where an agent plans, uses tools, and executes with less manual steering.
+
+If you are not sure where to begin, start with a normal conversation and move to Personas, Crew Mode, or Agent Mode as your task becomes more structured.
+
 ## Start a New conversation

 Select **New** button at the bottom of the Projects panel to start a new chat. This will open a new standard chat view. 

-### Persona Conversations
-To start a new Persona conversation, select the down arrow next to the **New** button and choose **New Persona Conversation**. This will open a new chat view with the selected Persona applied.
-
-![Persona Mode Convo](/images/conversations/persona-mode-convo.png)
-
-Persona conversations are a persona-first conversation where you can select a Persona and have a direct back-and-forth conversation with the persona acting as a true personalized assistant. 
-
-Since this is a Persona-first conversation, the Persona's prompt is always included in the context along with any system prompt you have set as well as any add-ons you've enabled for the Persona. This helps provide a consistent experience with the Persona. 
-
 ## Main Chat Features

 ![Conversations](/images/conversations.png)
@@ -35,13 +37,13 @@ Setting a **Sticky Prompt** can be accessed from the ellipsis icon menu. When a

 ### Attachments

-Attach files, images, websites, and YouTube links to enhance your conversation. Check out [Chat Attachments](/features/chat-attachments) for more details.
+Attach files, images, websites, and YouTube links to enhance your conversation. Check out [Chat Attachments](/add-ons/attachments) for more details.

 ### Real-time Data

-Have your model scan the web for real-time data. This feature is available when using [Remote Connections](/features/remote-connections) or [Msty Sidecar](/how-tos/sidecar).
+Have your model scan the web for real-time data. This feature is available when using [Remote Connections](/settings/remote-connections) or [Msty Sidecar](/how-tos/sidecar).

-Check out [Real-Time Data](/features/real-time-data) for more detail.
+Check out [Real-Time Data](/add-ons/real-time-data) for more detail.

 ### Personas

@@ -77,13 +79,13 @@ In the chat window, you can also type **/** to quick search for a prompt.

 ### Toolsets and Live contexts

-Include [Toolsets](/features/toolsets) and [Live Contexts](/features/live-contexts) in your conversation to amp up the power of your conversation.
+Include [Toolsets](/toolbox/toolsets) and [Live Contexts](/toolbox/live-contexts) in your conversation to amp up the power of your conversation.

 Tools add MCP capabilities to your conversations and Live Contexts allows you to incorporate data gathered from APIs.

 ### Turnstiles

-Include [Turnstiles](/features/turnstiles) to get into an Agent-like mode. This allows you to have a conversation with a model that is more focused on the task at hand, rather than just generating text.
+Include [Turnstiles](/add-ons/turnstiles) to get into an Agent-like mode. This allows you to have a conversation with a model that is more focused on the task at hand, rather than just generating text.

 ### Model selection

@@ -0,0 +1,37 @@
+---
+title: Persona Conversations
+description: Chat with a selected persona in a dedicated conversation
+navTruncate: false
+previewImage: "/images/conversations/persona-mode-convo.png"
+---
+
+Persona Conversations let you chat directly with one selected persona. This is useful when you want a consistent voice, role, or workflow across a full conversation.
+
+![Persona Mode Convo](/images/conversations/persona-mode-convo.png)
+
+## Start a Persona Conversation
+
+::steps
+
+1. Select the down arrow next to **New**.
+2. Choose **New Persona Conversation**.
+3. Select the persona you want to use.
+4. Start chatting.
+
+::
+
+## How Persona Conversations Work
+
+- The selected persona is applied for the full conversation.
+- The persona prompt is included with each turn.
+- Your active system prompt and enabled add-ons still apply.
+
+This gives you a reliable persona-first chat flow for tasks like role-based support, planning, writing, or coaching.
+
+## Tips
+
+- Build focused personas in [Persona Studio](/studios/persona-studio) for better results.
+- Use [System Prompt Modes](/conversations/system-prompts) to control how persona and system instructions combine.
+- Use [Crew Conversations](/conversations/crew-chats) when you need multiple personas in one chat.
+
+::Resources
@@ -26,7 +26,7 @@ See the examples section below for additional useful usages for Shadow Personas.
 ### Step 1 - Create the underlying Persona
 The underlying directives and capabilities of a Shadow Persona come from the underlying Persona. 

-See the [Personas](/features/personas) learn how to create a new persona.
+See [Persona Studio](/studios/persona-studio) to learn how to create a new persona.

 Shadow Personas adopt the following features of a Persona: 
 - **System Prompt** - the prompt provides the main directives that a Shadow Persona is tasked with
@@ -10,7 +10,7 @@ previewImage:

 Want to chat with multiple personas at the same time? That's what Crew Conversation is for! 

-With Crew Conversation, you'll first create [personas](/features/personas) that you want to include in the conversation. Then, start a new crew conversation, add personas to your crew, and chat away. 
+With Crew Conversation, you'll first create [personas](/studios/persona-studio) that you want to include in the conversation. Then, start a new crew conversation, add personas to your crew, and chat away. 

 ## Crew Conversation Examples

@@ -62,4 +62,6 @@ If a persona needs additional context, you can add the context, such as real-tim

 Crew Conversations do not allow for other features that you'd find in a the normal conversations, such as split chats and threads. Crew Conversations is more like a chat room with your crew. 

-::Resources
+The background prompt used for Crew Mode handoffs and persona coordination can be adjusted in [Settings > Default Prompts](/settings/default-prompts).
+
+::Resources
@@ -0,0 +1,2 @@
+title: Conversations
+icon: lucide:messages-square
@@ -0,0 +1,168 @@
+---
+title: Agent Mode
+description: Run coding agents in Msty Studio Desktop
+navTruncate: false
+resources:
+  videos:
+  blogs:
+previewImage: "/images/welcome-to-msty.png"
+---
+
+Agent Mode lets you run coding agents inside Msty Studio Desktop. You can chat with an agent, review plans, inspect diffs, and approve actions in one workspace-aware flow.
+
+## Setup (Desktop)
+
+::steps
+### Open Agent Mode settings
+Go to **Settings > Agent Mode**.
+
+### Install and sign in to an agent
+Install one supported CLI agent (Codex, Claude Code, or Gemini CLI), run it once in your terminal, then complete sign-in.
+
+### Refresh adapters
+Back in **Settings > Agent Mode**, run **Check updates** to refresh available agents.
+::
+
+## Install a CLI Agent
+
+If you start a new Agent Mode session and no coding agent is detected, Msty shows an onboarding screen with install steps. The flow is the same for each supported CLI:
+
+1. Install the CLI with `npm`.
+2. Run the CLI once in your terminal.
+3. Complete the sign-in flow.
+4. Return to Msty and select **Re-check for agents** or **Check updates** in Settings.
+
+If `npm` is not installed, install [Node.js](https://nodejs.org/en/download){target="_blank"} first. On Linux, you can also use the [Node.js package manager instructions](https://nodejs.org/en/download/package-manager){target="_blank"}.
+
+::tabs{variant="card" sync="agent-cli"}
+::div{label="Codex" icon="simple-icons:openai"}
+
+### Codex
+
+Codex is OpenAI's terminal coding agent and uses your ChatGPT account.
+
+#### Install
+
+```bash
+npm install -g @openai/codex
+```
+
+#### Run Once
+
+```bash
+codex
+```
+
+When Codex opens, choose **Sign in with ChatGPT**. After sign-in, return to Msty and re-check for agents.
+
+[Codex documentation](https://developers.openai.com/codex){target="_blank"}
+
+::
+
+::div{label="Gemini CLI" icon="simple-icons:google"}
+
+### Gemini CLI
+
+Gemini CLI is Google's open-source CLI agent and supports Google sign-in with a free tier.
+
+#### Install
+
+```bash
+npm install -g @google/gemini-cli
+```
+
+#### Run Once
+
+```bash
+gemini
+```
+
+When Gemini opens, choose **Sign in with Google**. After sign-in, return to Msty and re-check for agents.
+
+[Gemini CLI documentation](https://github.com/google-gemini/gemini-cli){target="_blank"}
+
+::
+
+::div{label="Claude Code" icon="simple-icons:anthropic"}
+
+### Claude Code
+
+Claude Code is Anthropic's CLI coding agent and requires a Claude subscription.
+
+#### Install
+
+```bash
+npm install -g @anthropic-ai/claude-code
+```
+
+#### Run Once
+
+```bash
+claude
+```
+
+Follow the sign-in prompts in your terminal. After sign-in, return to Msty and re-check for agents.
+
+[Claude Code quickstart](https://code.claude.com/docs/en/quickstart){target="_blank"}
+
+::
+::
+
+### Terminal Tips
+
+The onboarding screen also includes basic terminal guidance:
+
+- **macOS:** Open **Terminal** with `Command + Space`, type `Terminal`, then press `Return`.
+- **Windows:** Open **Windows Terminal** or **PowerShell** from the Start menu.
+- **Linux:** Open your preferred **Terminal** app from the applications menu.
+
+## Use Local AI Models
+
+Agent Mode can also use local inference servers as backends. Local providers are discovered from providers you have already configured in the Model Hub with a local-compatible inference endpoint, and each enabled provider appears as its own agent in the Agent selector.
+
+Examples include local or self-hosted providers such as Ollama-compatible servers, llama.cpp, MLX, and other OpenAI-compatible local inference servers.
+
+This setup currently requires **Claude Code CLI** to be installed. Local backends are also generally not ideal for every agent CLI workflow and usually work best when you have a strong local model and enough system resources.
+
+::steps
+### Configure a local provider in Model Hub
+Add or configure your local inference server in the Model Hub so it has a working inference endpoint.
+
+### Open Settings > Agent Mode
+Go to the **Local Providers** section in Agent Mode settings.
+
+### Enable the provider
+Turn on the local providers you want Agent Mode to expose.
+
+### Start or refresh an Agent session
+Enabled local providers appear as separate agents in the Agent selector. Refresh agents if needed.
+::
+
+## Major Parts
+
+### Sessions and workspaces
+Start an Agent session from the **New** menu or from Easy Access. Sessions can target a workspace repository, or run folderless for quick tasks.
+
+### Plans and approvals
+Agents can propose a plan before applying changes. Review each step and approve what should run.
+
+### Skills and slash commands
+Use slash commands and installed skills to speed up repeated workflows. To create, manage, and install skills, see [Skills Studio](/studios/skills-studio).
+
+### Diff and commit flow
+Review generated file diffs, then commit from the workspace diff panel when you are ready.
+
+## Using Agent Mode
+
+1. Start a new Agent session.
+2. Describe the change and include context.
+3. Review the proposed plan and approve actions.
+4. Inspect diffs and iterate with follow-up prompts.
+5. Commit when complete.
+
+[Image placeholder: Agent session showing plan panel, approvals, and workspace diff]
+
+## Notes
+
+- Agent Mode is currently available on **Msty Studio Desktop**.
+- If no agents appear, re-run your agent CLI setup in terminal and refresh adapters in settings.
@@ -0,0 +1,2 @@
+title: Agent Mode
+icon: lucide:bot
@@ -0,0 +1,93 @@
+---
+title: Persona Studio
+description: Build Assistant and User Personas in Persona Studio
+navTruncate: false
+resources:
+  videos:
+    - "7KMM8x77DOk"
+    - "ym8Rm-PePtU"
+    - "icpxQH5S80Y"
+  blogs:
+    - title: "That Guy - Creating the Devils Advocate Persona"
+      description: "We all know one... Someone who has to always counter an argument, no matter what. This is how you can create the ultimate Devil's Advocate."
+      image: "https://msty.ai/blog/that-guy/the-goats.png"
+      url: "https://msty.ai/blog/that-guy"
+previewImage: "/images/personas.png"
+---
+
+Persona Studio helps you create and manage custom assistants and user profiles for more consistent conversations.
+
+![Msty Personas](/images/personas.png)
+
+## Persona Types
+
+### Assistant Personas
+Assistant Personas define how an assistant responds. You can configure:
+
+- Name, icon, and description
+- System prompt behavior
+- Add-ons like toolsets, model settings, Knowledge Stacks, attachments, and real-time data
+- Few-shot examples
+- Auto-response behavior
+
+### User Personas
+User Personas define reusable user context and memory that can be applied across conversations.
+
+They are useful when you want models, personas, and other assistants in Msty to know important things about you without repeating that context every time. For example, you might want Msty to remember your role, writing preferences, goals, ongoing projects, technical background, or personal constraints.
+
+This can help responses feel more consistent and relevant across different workflows. Instead of re-explaining who you are or how you like to work in each conversation, you can keep that information in a User Persona and reuse it wherever needed.
+
+When you create memories from conversation messages, the default memory-generation prompt can be adjusted in [Settings > Default Prompts](/settings/default-prompts).
+
+::alert{type="info" icon="tabler:info-circle"}
+The title and summary portions of user persona memories are included directly in the prompt, so assistants can still see that context even without tool calling.
+
+To access the more detailed memory content, the assistant or persona agent must support tool calling.
+::
+
+## Create and Organize Personas
+
+::steps
+### Open Persona Studio
+Open **Persona Studio** from the left sidebar.
+
+### Choose persona type
+Create an **Assistant Persona** or a **User Persona**.
+
+### Configure and save
+Add prompt details, add-ons, tags, and folder location, then save.
+
+### Iterate
+Refine the persona with versions and sandbox testing.
+::
+
+## Versions and Sandbox
+
+Persona Studio includes version-aware editing and a sandbox for testing before rolling changes into your normal workflow.
+
+- Save versions as your persona evolves
+- Switch active versions when needed
+- Compare behavior in sandbox splits before promoting changes
+
+## Persona AI Tools :aurum-tag
+
+Persona Studio AI tools can help you:
+
+- Generate or improve system prompt drafts
+- Suggest tags
+- Draft few-shot examples
+
+## Use Personas in Conversations
+
+[See how Personas are used in conversations](/conversations/persona-conversations)
+
+- Start a Persona conversation from the **New** menu.
+- Use `@` to quickly select personas in chat.
+- Use persona controls above the message box to send persona prompts and tune context behavior.
+
+## Limits
+
+- Free plan: up to 2 Assistant Personas and 1 User Persona
+- Paid plans: higher limits and advanced persona tooling
+
+::Resources
@@ -1,5 +1,5 @@
 ---
-title: Prompts Studio
+title: Prompt Studio
 description: Prompt Studio helps you create, organize, and manage your prompts efficiently
 navTruncate: false
 previewImage: "/images/prompts-library.png"
@@ -32,11 +32,11 @@ Alternatively, click the **down arrow** next to **New Prompt** to:

 ## AI Assistant :aurum-tag

-Prompts Studio includes an AI Assistant to help you craft and refine prompts. 
+Prompt Studio includes an AI Assistant to help you craft and refine prompts. 

-To enable, select the **AI Assistant** button in the bottom of the Prompts Studio window.
+To enable, select the **AI Assistant** button in the bottom of the Prompt Studio window.

-![Prompts Studio AI Assistant](/images/prompts-studio/prompt-studio-ai-assistant.png)
+![Prompt Studio AI Assistant](/images/prompts-studio/prompt-studio-ai-assistant.png)

 After enabling, you use your AI Assistant to help you create a new prompt, improve and existing prompt, or to suggest tags.

@@ -56,7 +56,7 @@ Variables are placeholders in prompts that can be filled in later when using the
 ### Generate the Prompt
 Click **Generate Prompt** to have the AI Assistant create a prompt based on your selections.
 ### Review, Edit, and Apply
-You can then review the generated prompt, make any necessary edits, and click **Apply Prompt** to add it to your Prompts Studio library.
+You can then review the generated prompt, make any necessary edits, and click **Apply Prompt** to add it to your Prompt Studio library.
 ::


@@ -64,9 +64,9 @@ You can then review the generated prompt, make any necessary edits, and click **

 If you want to test and compare different prompt versions, the Prompt Studio Sandbox is a great tool.

-To access the Sandbox, open a prompt in Prompts Studio and click the **Sandbox** button at the top of the window.
+To access the Sandbox, open a prompt in Prompt Studio and click the **Sandbox** button at the top of the window.

-![Prompts Studio Sandbox](/images/prompts-studio/prompt-studio-sandbox.png)
+![Prompt Studio Sandbox](/images/prompts-studio/prompt-studio-sandbox.png)

 You can then set a model to use, the version of the prompt to test, include a system prompt, and even add in any variable values. 

@@ -0,0 +1,53 @@
+---
+title: Skills Studio
+description: Build, organize, and install agent skills
+navTruncate: false
+resources:
+  videos:
+  blogs:
+previewImage: "/images/welcome-to-msty.png"
+---
+
+Skills Studio is a dedicated workspace for creating and managing skills used by Agent Mode.
+
+## Setup
+
+::steps
+### Open Skills Studio
+Go to **Settings > Agent Mode > Skills Studio**.
+
+### Create or import skills
+Start from a new draft, import defaults, use templates, or add a GitHub repo in Discover.
+
+### Organize with folders
+Create folders and move skills into a structure that matches your workflow.
+::
+
+## Major Parts
+
+### Workshop
+Edit skill metadata and `SKILL.md` instructions, then save and iterate quickly.
+
+### Discover
+Browse connected repositories, inspect skills, install what you need, and rename custom repo labels for clearer navigation.
+
+### Folders and bulk management
+Use nested folders to organize skills and keep large collections manageable.
+
+### Templates and AI tools :aurum-tag
+Use templates and AI-assisted drafting to generate or improve skill descriptions and instructions.
+
+## Using Skills Studio
+
+1. Create a new skill in Workshop.
+2. Write a clear description and instructions.
+3. Add tags and place the skill in a folder.
+4. Test it in Agent Mode slash commands.
+5. Iterate or install additional skills from Discover.
+
+[Image placeholder: Skills Studio with folder tree, editor, and Discover tab]
+
+## Tips
+
+- Keep skill IDs simple and stable.
+- Use folders to separate personal, team, and experimental skills.
@@ -0,0 +1,2 @@
+title: Studios
+icon: lucide:sparkles
@@ -35,7 +35,7 @@ Here's what makes Next Gen worth switching to:
 - **File (Single Chunk) chunking** — A new chunking method that keeps each item as one whole chunk — perfect for pre-chunked documents or content that shouldn't be split up.
 - **A cleaner, more intuitive experience** — We've polished the UI and made things feel a lot smoother across the board.

-👉 [Learn more about Knowledge Stacks Next Gen →](/features/knowledge-stacks/next-gen)
+👉 [Learn more about Knowledge Stacks Next Gen →](/knowledge-stacks/next-gen)
 ::

 Knowledge Stacks are Msty Studio's take on Retrieval-Augmented Generation (RAG), designed to help you create, manage, and use collections of knowledge in a structured, flexible way. They let you organize your data for easy access in conversations, proving models with deep, domain-specific understanding.
@@ -61,7 +61,7 @@ When creating your Knowledge Stack, think of each stack as a category or topic t
 1. Click the Knowledge Stacks icon and select option to create a new stack
 2. Add a **Title** and **Description** for your stack
 3. Add **Files**, **Folders**, **Notes**, and/or **YouTube Links** to your stack
-4. Configure the **Compose Settings** - view [Compose Options](/features/knowledge-stacks/compose-options) for advanced configuration options
+4. Configure the **Compose Settings** - view [Compose Options](/knowledge-stacks/compose-options) for advanced configuration options
 5. **Compose** your Knowledge Stack
 ::

@@ -86,7 +86,7 @@ The model will have access to the knowledge in your selected stack, allowing it

 ![knowledge stacks chat response](/images/knowledge-stacks/sherlock-holmes-response.png)

-Check out [Query Settings](/features/knowledge-stacks/query-settings) for advanced query options that will help you improve search results.
+Check out [Query Settings](/knowledge-stacks/query-settings) for advanced query options that will help you improve search results.

 ## Import Default Knowledge Stacks

@@ -87,7 +87,7 @@ If you do not want personal identifiable information (PII) to be sent to the mod

 You will be asked to select a locally installed model that will be tasked with detecting any PII in the Knowledge Stack and to redact the information. 

-For best results and for added security, test PII Scrubbing in [Chunks Visualizer](/features/knowledge-stacks/chunks-visualizer) and [Chunks Console](/features/knowledge-stacks/chunks-console) prior to using Knowledge Stacks with online providers where PII is a concern. 
+For best results and for added security, test PII Scrubbing in [Chunks Visualizer](/knowledge-stacks/chunks-visualizer) and [Chunks Console](/knowledge-stacks/chunks-console) prior to using Knowledge Stacks with online providers where PII is a concern. 

 ![pii](/images/knowledge-stacks/pii.png)

@@ -29,7 +29,7 @@ In the above example, you can see how the chunks for this stack are defined and

 The Chunks Visualizer helps you fine-tune by showing overlaps, chunk boundaries, and how text flows between them.

-If the chunks are not meeting your expectations, see [Compose Options](/features/knowledge-stacks/compose-options) to learn how you can adjust chunk settings. 
+If the chunks are not meeting your expectations, see [Compose Options](/knowledge-stacks/compose-options) to learn how you can adjust chunk settings. 

 ## Show Stitched

@@ -39,7 +39,7 @@ With Msty Studio’s Knowledge Stacks, models can either retrieve relevant chunk

 ## Chunks Console

-Chunk Console lets you perform queries against the Knowledge Stack and view results. See [Chunk Console](/features/knowledge-stacks/chunks-console) for more information. 
+Chunk Console lets you perform queries against the Knowledge Stack and view results. See [Chunk Console](/knowledge-stacks/chunks-console) for more information. 



@@ -10,11 +10,11 @@ previewImage: "/images/knowledge-stacks/chunks-console.png"

 With the Chunks Console, you can test how chunks can be queried and what results return. Using the Chunks Console is a key way to refine the accuracy of Knowledge Stacks to help ensure the appropriate data is being made available to models. 

-You can test different [Query Settings](/features/knowledge-stacks/query-settings) to see what is returned. 
+You can test different [Query Settings](/knowledge-stacks/query-settings) to see what is returned. 

 ![chunks console](/images/knowledge-stacks/chunks-console.png)

-If you see unexpected results, then you can modify either the Query Settings or the [Compose Options](features/knowledge-stacks/query-settings) to better refine your stacks. 
+If you see unexpected results, then you can modify either the Query Settings or the [Compose Options](/knowledge-stacks/compose-options) to better refine your stacks. 

 ## Remove Chunks
 If chunks are returned that you do not want to be included in query results and conversations with models, select the trashcan icon to remove the chunk. 
@@ -31,4 +31,4 @@ This is a great way to help prevent unwanted PII being sent to online models.

 The Chunks Console makes it easier to verify that PII has been scrubbed by using various queries and verifying PII is being redacted. 

-::Resources
+::Resources
@@ -4,6 +4,7 @@ description: Explore the next generation of Knowledge Stacks in Msty Studio with
 navTruncate: false
 resources:
  videos:
+   - "0zoDQr6xiLs"
  blogs:
 previewImage: "/images/welcome-to-msty.png"
 ---
@@ -0,0 +1,2 @@
+title: Knowledge Stacks
+icon: lucide:layers-3
@@ -36,7 +36,7 @@ Msty Studio supports local MCP server that run on your machine as well as remote
 Please note the SSE protocol has been deprecated in favor of Streamable HTTP for remote MCP server connections. Studio's implementation came after the deprecation, and as such, SSE is not supported. However, you can use a local proxy such as mcp-remote to connect to SSE-based MCP servers if needed.
 ::

-To utilize the Toolbox features with Msty Studio Web, you must have Studio Web connected to Studio Desktop using [Remote Connections](/features/remote-connections) or [Sidecar](/how-tos/sidecar).
+To utilize the Toolbox features with Msty Studio Web, you must have Studio Web connected to Studio Desktop using [Remote Connections](/settings/remote-connections) or [Sidecar](/how-tos/sidecar).

 ![Msty Studio Tools](/images/tools.png)

@@ -15,7 +15,7 @@ Toolsets are a collection of tools with defined parameters. You can create a too

 1. Select **Add New Toolset** to add a new toolset
 2. Enable the tools you want to include in the Toolset
-3. Select the asterisk (**\***) icon next to the tool to define the [parameters](/features/toolbox/tools#set-tools-default-parameters) the tool should use with this Toolset
+3. Select the asterisk (**\***) icon next to the tool to define the [parameters](/toolbox/tools#set-tools-default-parameters) the tool should use with this Toolset
 4. Add any **Notes** to help you remember the purpose of the toolset and any other information you may need to remember
 5. Give the toolset a unique **Name**
 6. Select **Add** to add the toolset to your toolbox
@@ -0,0 +1,2 @@
+title: Toolbox
+icon: lucide:wrench
@@ -19,7 +19,7 @@ You are able to sort the order of entries by selecting the touch icon and draggi

 To edit or further configure an entry, expand the entry by clicking on the chevron icon.

-In addition to the prompt, you can further empower your entry by adding [attachments](/features/attachments), [tools](/features/toolbox/toolsets), enabling [Real-Time Data](/features/real-time-data), and even select which exact model you want to run for the entry. This turbocharges the power of your Turnstile.
+In addition to the prompt, you can further empower your entry by adding [attachments](/add-ons/attachments), [tools](/toolbox/toolsets), enabling [Real-Time Data](/add-ons/real-time-data), and even select which exact model you want to run for the entry. This turbocharges the power of your Turnstile.

 ### Advanced Messaging Commands

@@ -27,7 +27,7 @@ previewImage: "/images/welcome-to-msty.png"

 Enable Real-Time Data (RTD) integration to instantly enhance your conversations with current information, weather updates, sports scores, news headlines, and more.

-Real-Time Data is built into Msty Studio Desktop. However, Studio Web cannot access RTD natively but can be connected to an instance of Msty Studio Desktop by using the [Remote Connections](/features/remote-connections) feature or by using [Msty Sidecar](/how-tos/sidecar).
+Real-Time Data is built into Msty Studio Desktop. However, Studio Web cannot access RTD natively but can be connected to an instance of Msty Studio Desktop by using the [Remote Connections](/settings/remote-connections) feature or by using [Msty Sidecar](/how-tos/sidecar).

 ## How RTD Works

@@ -0,0 +1,2 @@
+title: Add Ons
+icon: lucide:puzzle
@@ -0,0 +1,2 @@
+title: Workspaces
+icon: lucide:folder-open
@@ -1,9 +1,40 @@
+const watchIgnored = [
+  "**/.git/**",
+  "**/.nuxt/**",
+  "**/.output/**",
+  "**/.data/**",
+  "**/dist/**",
+  "**/node_modules/**",
+  "**/.pnpm-store/**",
+];
+
 // https://nuxt.com/docs/api/configuration/nuxt-config
 export default defineNuxtConfig({
  devtools: { enabled: true },
  extends: ["shadcn-docs-nuxt"],
  compatibilityDate: "2024-09-19",

+  content: {
+    watch: false,
+  },
+
+  components: {
+    dirs: [
+      {
+        path: "./node_modules/shadcn-docs-nuxt/components",
+        ignore: ["ui/**", "**/*.ts"],
+      },
+      {
+        path: "~/components",
+      },
+      "~/components/ui",
+      {
+        path: "~/components/content",
+        prefix: "",
+      },
+    ],
+  },
+
  routeRules: {
    "/": {
      redirect: "/getting-started",
@@ -14,15 +45,22 @@ export default defineNuxtConfig({
    preset: "cloudflare_pages",
  },

-  components: {
-    dirs: [
-      "~/components",
-      "~/components/ui",
-      {
-        path: "~/components/content",
-        prefix: "",
+  watchers: {
+    chokidar: {
+      ignored: watchIgnored,
+      usePolling: true,
+      interval: 250,
+    },
+  },
+
+  vite: {
+    server: {
+      watch: {
+        ignored: watchIgnored,
+        usePolling: true,
+        interval: 250,
      },
-    ],
+    },
  },

  alias: {
@@ -10,16 +10,16 @@ importers:
    dependencies:
      '@nuxthub/core':
        specifier: 0.8.24
-        version: 0.8.24(db0@0.3.4)(ioredis@5.8.2)(magicast@0.5.1)(vite@7.2.2(@types/node@24.10.1)(jiti@1.21.7)(terser@5.44.1)(yaml@2.8.1))
+        version: 0.8.24(db0@0.3.4)(ioredis@5.8.2)(magicast@0.5.1)(vite@7.2.2(@types/node@24.10.1)(jiti@2.6.1)(terser@5.44.1)(yaml@2.8.1))
      '@nuxtjs/mdc':
        specifier: ^0.17.0
        version: 0.17.4(magicast@0.5.1)
      nuxt:
        specifier: ^3.16.0
-        version: 3.20.1(@parcel/watcher@2.5.1)(@types/node@24.10.1)(@vue/compiler-sfc@3.5.24)(db0@0.3.4)(ioredis@5.8.2)(magicast@0.5.1)(ms@2.1.3)(rollup@4.53.3)(terser@5.44.1)(typescript@5.9.3)(vite@7.2.2(@types/node@24.10.1)(jiti@1.21.7)(terser@5.44.1)(yaml@2.8.1))(yaml@2.8.1)
+        version: 3.20.1(@parcel/watcher@2.5.1)(@types/node@24.10.1)(@vue/compiler-sfc@3.5.24)(db0@0.3.4)(ioredis@5.8.2)(magicast@0.5.1)(ms@2.1.3)(rollup@4.53.3)(terser@5.44.1)(typescript@5.9.3)(vite@7.2.2(@types/node@24.10.1)(jiti@2.6.1)(terser@5.44.1)(yaml@2.8.1))(yaml@2.8.1)
      shadcn-docs-nuxt:
        specifier: ^0.8.21
-        version: 0.8.21(@parcel/watcher@2.5.1)(@types/node@24.10.1)(@unhead/vue@2.0.19(vue@3.5.24(typescript@5.9.3)))(@vue/compiler-sfc@3.5.24)(db0@0.3.4)(h3@1.15.4)(ioredis@5.8.2)(magicast@0.5.1)(ms@2.1.3)(rollup@4.53.3)(tailwindcss@3.4.18(yaml@2.8.1))(terser@5.44.1)(unstorage@1.17.2(db0@0.3.4)(ioredis@5.8.2))(vite@7.2.2(@types/node@24.10.1)(jiti@1.21.7)(terser@5.44.1)(yaml@2.8.1))(yaml@2.8.1)
+        version: 0.8.21(@parcel/watcher@2.5.1)(@types/node@24.10.1)(@unhead/vue@2.0.19(vue@3.5.24(typescript@5.9.3)))(@vue/compiler-sfc@3.5.24)(db0@0.3.4)(h3@1.15.4)(ioredis@5.8.2)(magicast@0.5.1)(ms@2.1.3)(rollup@4.53.3)(tailwindcss@3.4.18(yaml@2.8.1))(terser@5.44.1)(unstorage@1.17.2(db0@0.3.4)(ioredis@5.8.2))(vite@7.2.2(@types/node@24.10.1)(jiti@2.6.1)(terser@5.44.1)(yaml@2.8.1))(yaml@2.8.1)
      vue:
        specifier: ^3.5.13
        version: 3.5.24(typescript@5.9.3)
@@ -1676,8 +1676,9 @@ packages:
  base64-js@1.5.1:
    resolution: {integrity: sha512-AKpaYlHn8t4SVbOHCy+b5+KKgvR4vrsD8vbvrbiQJps7fKDTkjkDry6ji0rUJjC0kzbNePLwzxq8iypo41qeWA==}

-  baseline-browser-mapping@2.8.29:
-    resolution: {integrity: sha512-sXdt2elaVnhpDNRDz+1BDx1JQoJRuNk7oVlAlbGiFkLikHCAQiccexF/9e91zVi6RCgqspl04aP+6Cnl9zRLrA==}
+  baseline-browser-mapping@2.10.9:
+    resolution: {integrity: sha512-OZd0e2mU11ClX8+IdXe3r0dbqMEznRiT4TfbhYIbcRPZkqJ7Qwer8ij3GZAmLsRKa+II9V1v5czCkvmHH3XZBg==}
+    engines: {node: '>=6.0.0'}
    hasBin: true

  binary-extensions@2.3.0:
@@ -1762,8 +1763,8 @@ packages:
  caniuse-api@3.0.0:
    resolution: {integrity: sha512-bsTwuIg/BZZK/vreVTYYbSWoe2F+71P7K5QGEX+pT250DZbfU1MQ5prOKpPR+LL6uWKK3KMwMCAS74QB3Um1uw==}

-  caniuse-lite@1.0.30001756:
-    resolution: {integrity: sha512-4HnCNKbMLkLdhJz3TToeVWHSnfJvPaq6vu/eRP0Ahub/07n484XHhBF5AJoSGHdVrS8tKFauUQz8Bp9P7LVx7A==}
+  caniuse-lite@1.0.30001780:
+    resolution: {integrity: sha512-llngX0E7nQci5BPJDqoZSbuZ5Bcs9F5db7EtgfwBerX9XGtkkiO4NwfDDIRzHTTwcYC8vC7bmeUEPGrKlR/TkQ==}

  ccount@2.0.1:
    resolution: {integrity: sha512-eyrF0jiFpY+3drT6383f1qhkbGsLSifNAjA61IUjZjmLCWjItY6LB9ft9YhoDgwfmclB2zhu51Lc7+95b8NRAg==}
@@ -5294,13 +5295,13 @@ snapshots:
    transitivePeerDependencies:
      - magicast

-  '@nuxt/content@2.13.4(db0@0.3.4)(ioredis@5.8.2)(magicast@0.5.1)(nuxt@3.20.1(@parcel/watcher@2.5.1)(@types/node@24.10.1)(@vue/compiler-sfc@3.5.24)(db0@0.3.4)(ioredis@5.8.2)(magicast@0.5.1)(ms@2.1.3)(rollup@4.53.3)(terser@5.44.1)(typescript@5.9.3)(vite@7.2.2(@types/node@24.10.1)(jiti@1.21.7)(terser@5.44.1)(yaml@2.8.1))(yaml@2.8.1))(vue@3.5.24(typescript@5.9.3))':
+  '@nuxt/content@2.13.4(db0@0.3.4)(ioredis@5.8.2)(magicast@0.5.1)(nuxt@3.20.1(@parcel/watcher@2.5.1)(@types/node@24.10.1)(@vue/compiler-sfc@3.5.24)(db0@0.3.4)(ioredis@5.8.2)(magicast@0.5.1)(ms@2.1.3)(rollup@4.53.3)(terser@5.44.1)(typescript@5.9.3)(vite@7.2.2(@types/node@24.10.1)(jiti@2.6.1)(terser@5.44.1)(yaml@2.8.1))(yaml@2.8.1))(vue@3.5.24(typescript@5.9.3))':
    dependencies:
      '@nuxt/kit': 3.20.1(magicast@0.5.1)
      '@nuxtjs/mdc': 0.9.5(magicast@0.5.1)
      '@vueuse/core': 11.3.0(vue@3.5.24(typescript@5.9.3))
      '@vueuse/head': 2.0.0(vue@3.5.24(typescript@5.9.3))
-      '@vueuse/nuxt': 11.3.0(magicast@0.5.1)(nuxt@3.20.1(@parcel/watcher@2.5.1)(@types/node@24.10.1)(@vue/compiler-sfc@3.5.24)(db0@0.3.4)(ioredis@5.8.2)(magicast@0.5.1)(ms@2.1.3)(rollup@4.53.3)(terser@5.44.1)(typescript@5.9.3)(vite@7.2.2(@types/node@24.10.1)(jiti@1.21.7)(terser@5.44.1)(yaml@2.8.1))(yaml@2.8.1))(vue@3.5.24(typescript@5.9.3))
+      '@vueuse/nuxt': 11.3.0(magicast@0.5.1)(nuxt@3.20.1(@parcel/watcher@2.5.1)(@types/node@24.10.1)(@vue/compiler-sfc@3.5.24)(db0@0.3.4)(ioredis@5.8.2)(magicast@0.5.1)(ms@2.1.3)(rollup@4.53.3)(terser@5.44.1)(typescript@5.9.3)(vite@7.2.2(@types/node@24.10.1)(jiti@2.6.1)(terser@5.44.1)(yaml@2.8.1))(yaml@2.8.1))(vue@3.5.24(typescript@5.9.3))
      consola: 3.4.2
      defu: 6.1.4
      destr: 2.0.5
@@ -5353,7 +5354,7 @@ snapshots:

  '@nuxt/devalue@2.0.2': {}

-  '@nuxt/devtools-kit@2.7.0(magicast@0.5.1)(vite@7.2.2(@types/node@24.10.1)(jiti@1.21.7)(terser@5.44.1)(yaml@2.8.1))':
+  '@nuxt/devtools-kit@2.7.0(magicast@0.5.1)(vite@7.2.2(@types/node@24.10.1)(jiti@2.6.1)(terser@5.44.1)(yaml@2.8.1))':
    dependencies:
      '@nuxt/kit': 3.20.1(magicast@0.5.1)
      execa: 8.0.1
@@ -5361,7 +5362,7 @@ snapshots:
    transitivePeerDependencies:
      - magicast

-  '@nuxt/devtools-kit@3.1.0(magicast@0.5.1)(vite@7.2.2(@types/node@24.10.1)(jiti@1.21.7)(terser@5.44.1)(yaml@2.8.1))':
+  '@nuxt/devtools-kit@3.1.0(magicast@0.5.1)(vite@7.2.2(@types/node@24.10.1)(jiti@2.6.1)(terser@5.44.1)(yaml@2.8.1))':
    dependencies:
      '@nuxt/kit': 4.2.1(magicast@0.5.1)
      execa: 8.0.1
@@ -5380,12 +5381,12 @@ snapshots:
      prompts: 2.4.2
      semver: 7.7.3

-  '@nuxt/devtools@3.1.0(vite@7.2.2(@types/node@24.10.1)(jiti@1.21.7)(terser@5.44.1)(yaml@2.8.1))(vue@3.5.24(typescript@5.9.3))':
+  '@nuxt/devtools@3.1.0(vite@7.2.2(@types/node@24.10.1)(jiti@2.6.1)(terser@5.44.1)(yaml@2.8.1))(vue@3.5.24(typescript@5.9.3))':
    dependencies:
-      '@nuxt/devtools-kit': 3.1.0(magicast@0.5.1)(vite@7.2.2(@types/node@24.10.1)(jiti@1.21.7)(terser@5.44.1)(yaml@2.8.1))
+      '@nuxt/devtools-kit': 3.1.0(magicast@0.5.1)(vite@7.2.2(@types/node@24.10.1)(jiti@2.6.1)(terser@5.44.1)(yaml@2.8.1))
      '@nuxt/devtools-wizard': 3.1.0
      '@nuxt/kit': 4.2.1(magicast@0.5.1)
-      '@vue/devtools-core': 8.0.5(vite@7.2.2(@types/node@24.10.1)(jiti@1.21.7)(terser@5.44.1)(yaml@2.8.1))(vue@3.5.24(typescript@5.9.3))
+      '@vue/devtools-core': 8.0.5(vite@7.2.2(@types/node@24.10.1)(jiti@2.6.1)(terser@5.44.1)(yaml@2.8.1))(vue@3.5.24(typescript@5.9.3))
      '@vue/devtools-kit': 8.0.5
      birpc: 2.8.0
      consola: 3.4.2
@@ -5411,8 +5412,8 @@ snapshots:
      structured-clone-es: 1.0.0
      tinyglobby: 0.2.15
      vite: 7.2.2(@types/node@24.10.1)(jiti@1.21.7)(terser@5.44.1)(yaml@2.8.1)
-      vite-plugin-inspect: 11.3.3(@nuxt/kit@4.2.1(magicast@0.5.1))(vite@7.2.2(@types/node@24.10.1)(jiti@1.21.7)(terser@5.44.1)(yaml@2.8.1))
-      vite-plugin-vue-tracer: 1.1.3(vite@7.2.2(@types/node@24.10.1)(jiti@1.21.7)(terser@5.44.1)(yaml@2.8.1))(vue@3.5.24(typescript@5.9.3))
+      vite-plugin-inspect: 11.3.3(@nuxt/kit@4.2.1(magicast@0.5.1))(vite@7.2.2(@types/node@24.10.1)(jiti@2.6.1)(terser@5.44.1)(yaml@2.8.1))
+      vite-plugin-vue-tracer: 1.1.3(vite@7.2.2(@types/node@24.10.1)(jiti@2.6.1)(terser@5.44.1)(yaml@2.8.1))(vue@3.5.24(typescript@5.9.3))
      which: 5.0.0
      ws: 8.18.3
    transitivePeerDependencies:
@@ -5421,13 +5422,13 @@ snapshots:
      - utf-8-validate
      - vue

-  '@nuxt/icon@1.15.0(magicast@0.5.1)(vite@7.2.2(@types/node@24.10.1)(jiti@1.21.7)(terser@5.44.1)(yaml@2.8.1))(vue@3.5.24(typescript@5.9.3))':
+  '@nuxt/icon@1.15.0(magicast@0.5.1)(vite@7.2.2(@types/node@24.10.1)(jiti@2.6.1)(terser@5.44.1)(yaml@2.8.1))(vue@3.5.24(typescript@5.9.3))':
    dependencies:
      '@iconify/collections': 1.0.619
      '@iconify/types': 2.0.0
      '@iconify/utils': 2.3.0
      '@iconify/vue': 5.0.0(vue@3.5.24(typescript@5.9.3))
-      '@nuxt/devtools-kit': 2.7.0(magicast@0.5.1)(vite@7.2.2(@types/node@24.10.1)(jiti@1.21.7)(terser@5.44.1)(yaml@2.8.1))
+      '@nuxt/devtools-kit': 2.7.0(magicast@0.5.1)(vite@7.2.2(@types/node@24.10.1)(jiti@2.6.1)(terser@5.44.1)(yaml@2.8.1))
      '@nuxt/kit': 3.20.1(magicast@0.5.1)
      consola: 3.4.2
      local-pkg: 1.1.2
@@ -5533,7 +5534,7 @@ snapshots:
    transitivePeerDependencies:
      - magicast

-  '@nuxt/nitro-server@3.20.1(db0@0.3.4)(ioredis@5.8.2)(magicast@0.5.1)(nuxt@3.20.1(@parcel/watcher@2.5.1)(@types/node@24.10.1)(@vue/compiler-sfc@3.5.24)(db0@0.3.4)(ioredis@5.8.2)(magicast@0.5.1)(ms@2.1.3)(rollup@4.53.3)(terser@5.44.1)(typescript@5.9.3)(vite@7.2.2(@types/node@24.10.1)(jiti@1.21.7)(terser@5.44.1)(yaml@2.8.1))(yaml@2.8.1))(typescript@5.9.3)':
+  '@nuxt/nitro-server@3.20.1(db0@0.3.4)(ioredis@5.8.2)(magicast@0.5.1)(nuxt@3.20.1(@parcel/watcher@2.5.1)(@types/node@24.10.1)(@vue/compiler-sfc@3.5.24)(db0@0.3.4)(ioredis@5.8.2)(magicast@0.5.1)(ms@2.1.3)(rollup@4.53.3)(terser@5.44.1)(typescript@5.9.3)(vite@7.2.2(@types/node@24.10.1)(jiti@2.6.1)(terser@5.44.1)(yaml@2.8.1))(yaml@2.8.1))(typescript@5.9.3)':
    dependencies:
      '@nuxt/devalue': 2.0.2
      '@nuxt/kit': 3.20.1(magicast@0.5.1)
@@ -5551,7 +5552,7 @@ snapshots:
      klona: 2.0.6
      mocked-exports: 0.1.1
      nitropack: 2.12.9
-      nuxt: 3.20.1(@parcel/watcher@2.5.1)(@types/node@24.10.1)(@vue/compiler-sfc@3.5.24)(db0@0.3.4)(ioredis@5.8.2)(magicast@0.5.1)(ms@2.1.3)(rollup@4.53.3)(terser@5.44.1)(typescript@5.9.3)(vite@7.2.2(@types/node@24.10.1)(jiti@1.21.7)(terser@5.44.1)(yaml@2.8.1))(yaml@2.8.1)
+      nuxt: 3.20.1(@parcel/watcher@2.5.1)(@types/node@24.10.1)(@vue/compiler-sfc@3.5.24)(db0@0.3.4)(ioredis@5.8.2)(magicast@0.5.1)(ms@2.1.3)(rollup@4.53.3)(terser@5.44.1)(typescript@5.9.3)(vite@7.2.2(@types/node@24.10.1)(jiti@2.6.1)(terser@5.44.1)(yaml@2.8.1))(yaml@2.8.1)
      pathe: 2.0.3
      pkg-types: 2.3.0
      radix3: 1.1.2
@@ -5665,12 +5666,12 @@ snapshots:
    transitivePeerDependencies:
      - magicast

-  '@nuxt/vite-builder@3.20.1(@types/node@24.10.1)(magicast@0.5.1)(ms@2.1.3)(nuxt@3.20.1(@parcel/watcher@2.5.1)(@types/node@24.10.1)(@vue/compiler-sfc@3.5.24)(db0@0.3.4)(ioredis@5.8.2)(magicast@0.5.1)(ms@2.1.3)(rollup@4.53.3)(terser@5.44.1)(typescript@5.9.3)(vite@7.2.2(@types/node@24.10.1)(jiti@1.21.7)(terser@5.44.1)(yaml@2.8.1))(yaml@2.8.1))(rollup@4.53.3)(terser@5.44.1)(typescript@5.9.3)(vue@3.5.24(typescript@5.9.3))(yaml@2.8.1)':
+  '@nuxt/vite-builder@3.20.1(@types/node@24.10.1)(magicast@0.5.1)(ms@2.1.3)(nuxt@3.20.1(@parcel/watcher@2.5.1)(@types/node@24.10.1)(@vue/compiler-sfc@3.5.24)(db0@0.3.4)(ioredis@5.8.2)(magicast@0.5.1)(ms@2.1.3)(rollup@4.53.3)(terser@5.44.1)(typescript@5.9.3)(vite@7.2.2(@types/node@24.10.1)(jiti@2.6.1)(terser@5.44.1)(yaml@2.8.1))(yaml@2.8.1))(rollup@4.53.3)(terser@5.44.1)(typescript@5.9.3)(vue@3.5.24(typescript@5.9.3))(yaml@2.8.1)':
    dependencies:
      '@nuxt/kit': 3.20.1(magicast@0.5.1)
      '@rollup/plugin-replace': 6.0.3(rollup@4.53.3)
-      '@vitejs/plugin-vue': 6.0.2(vite@7.2.2(@types/node@24.10.1)(jiti@1.21.7)(terser@5.44.1)(yaml@2.8.1))(vue@3.5.24(typescript@5.9.3))
-      '@vitejs/plugin-vue-jsx': 5.1.2(vite@7.2.2(@types/node@24.10.1)(jiti@1.21.7)(terser@5.44.1)(yaml@2.8.1))(vue@3.5.24(typescript@5.9.3))
+      '@vitejs/plugin-vue': 6.0.2(vite@7.2.2(@types/node@24.10.1)(jiti@2.6.1)(terser@5.44.1)(yaml@2.8.1))(vue@3.5.24(typescript@5.9.3))
+      '@vitejs/plugin-vue-jsx': 5.1.2(vite@7.2.2(@types/node@24.10.1)(jiti@2.6.1)(terser@5.44.1)(yaml@2.8.1))(vue@3.5.24(typescript@5.9.3))
      autoprefixer: 10.4.22(postcss@8.5.6)
      consola: 3.4.2
      cssnano: 7.1.2(postcss@8.5.6)
@@ -5686,7 +5687,7 @@ snapshots:
      magic-string: 0.30.21
      mlly: 1.8.0
      mocked-exports: 0.1.1
-      nuxt: 3.20.1(@parcel/watcher@2.5.1)(@types/node@24.10.1)(@vue/compiler-sfc@3.5.24)(db0@0.3.4)(ioredis@5.8.2)(magicast@0.5.1)(ms@2.1.3)(rollup@4.53.3)(terser@5.44.1)(typescript@5.9.3)(vite@7.2.2(@types/node@24.10.1)(jiti@1.21.7)(terser@5.44.1)(yaml@2.8.1))(yaml@2.8.1)
+      nuxt: 3.20.1(@parcel/watcher@2.5.1)(@types/node@24.10.1)(@vue/compiler-sfc@3.5.24)(db0@0.3.4)(ioredis@5.8.2)(magicast@0.5.1)(ms@2.1.3)(rollup@4.53.3)(terser@5.44.1)(typescript@5.9.3)(vite@7.2.2(@types/node@24.10.1)(jiti@2.6.1)(terser@5.44.1)(yaml@2.8.1))(yaml@2.8.1)
      ohash: 2.0.11
      pathe: 2.0.3
      perfect-debounce: 2.0.0
@@ -5697,9 +5698,9 @@ snapshots:
      std-env: 3.10.0
      ufo: 1.6.1
      unenv: 2.0.0-rc.24
-      vite: 7.2.2(@types/node@24.10.1)(jiti@2.6.1)(terser@5.44.1)(yaml@2.8.1)
+      vite: 7.2.2(@types/node@24.10.1)(jiti@1.21.7)(terser@5.44.1)(yaml@2.8.1)
      vite-node: 5.2.0(@types/node@24.10.1)(jiti@2.6.1)(ms@2.1.3)(terser@5.44.1)(yaml@2.8.1)
-      vite-plugin-checker: 0.11.0(typescript@5.9.3)(vite@7.2.2(@types/node@24.10.1)(jiti@1.21.7)(terser@5.44.1)(yaml@2.8.1))
+      vite-plugin-checker: 0.11.0(typescript@5.9.3)(vite@7.2.2(@types/node@24.10.1)(jiti@2.6.1)(terser@5.44.1)(yaml@2.8.1))
      vue: 3.5.24(typescript@5.9.3)
      vue-bundle-renderer: 2.2.0
    transitivePeerDependencies:
@@ -5728,10 +5729,10 @@ snapshots:
      - vue-tsc
      - yaml

-  '@nuxthub/core@0.8.24(db0@0.3.4)(ioredis@5.8.2)(magicast@0.5.1)(vite@7.2.2(@types/node@24.10.1)(jiti@1.21.7)(terser@5.44.1)(yaml@2.8.1))':
+  '@nuxthub/core@0.8.24(db0@0.3.4)(ioredis@5.8.2)(magicast@0.5.1)(vite@7.2.2(@types/node@24.10.1)(jiti@2.6.1)(terser@5.44.1)(yaml@2.8.1))':
    dependencies:
      '@cloudflare/workers-types': 4.20251119.0
-      '@nuxt/devtools-kit': 2.7.0(magicast@0.5.1)(vite@7.2.2(@types/node@24.10.1)(jiti@1.21.7)(terser@5.44.1)(yaml@2.8.1))
+      '@nuxt/devtools-kit': 2.7.0(magicast@0.5.1)(vite@7.2.2(@types/node@24.10.1)(jiti@2.6.1)(terser@5.44.1)(yaml@2.8.1))
      '@nuxt/kit': 3.20.1(magicast@0.5.1)
      '@uploadthing/mime-types': 0.3.6
      citty: 0.1.6
@@ -6586,7 +6587,7 @@ snapshots:
      - rollup
      - supports-color

-  '@vitejs/plugin-vue-jsx@5.1.2(vite@7.2.2(@types/node@24.10.1)(jiti@1.21.7)(terser@5.44.1)(yaml@2.8.1))(vue@3.5.24(typescript@5.9.3))':
+  '@vitejs/plugin-vue-jsx@5.1.2(vite@7.2.2(@types/node@24.10.1)(jiti@2.6.1)(terser@5.44.1)(yaml@2.8.1))(vue@3.5.24(typescript@5.9.3))':
    dependencies:
      '@babel/core': 7.28.5
      '@babel/plugin-syntax-typescript': 7.27.1(@babel/core@7.28.5)
@@ -6598,7 +6599,7 @@ snapshots:
    transitivePeerDependencies:
      - supports-color

-  '@vitejs/plugin-vue@6.0.2(vite@7.2.2(@types/node@24.10.1)(jiti@1.21.7)(terser@5.44.1)(yaml@2.8.1))(vue@3.5.24(typescript@5.9.3))':
+  '@vitejs/plugin-vue@6.0.2(vite@7.2.2(@types/node@24.10.1)(jiti@2.6.1)(terser@5.44.1)(yaml@2.8.1))(vue@3.5.24(typescript@5.9.3))':
    dependencies:
      '@rolldown/pluginutils': 1.0.0-beta.50
      vite: 7.2.2(@types/node@24.10.1)(jiti@1.21.7)(terser@5.44.1)(yaml@2.8.1)
@@ -6681,14 +6682,14 @@ snapshots:

  '@vue/devtools-api@6.6.4': {}

-  '@vue/devtools-core@8.0.5(vite@7.2.2(@types/node@24.10.1)(jiti@1.21.7)(terser@5.44.1)(yaml@2.8.1))(vue@3.5.24(typescript@5.9.3))':
+  '@vue/devtools-core@8.0.5(vite@7.2.2(@types/node@24.10.1)(jiti@2.6.1)(terser@5.44.1)(yaml@2.8.1))(vue@3.5.24(typescript@5.9.3))':
    dependencies:
      '@vue/devtools-kit': 8.0.5
      '@vue/devtools-shared': 8.0.5
      mitt: 3.0.1
      nanoid: 5.1.6
      pathe: 2.0.3
-      vite-hot-client: 2.1.0(vite@7.2.2(@types/node@24.10.1)(jiti@1.21.7)(terser@5.44.1)(yaml@2.8.1))
+      vite-hot-client: 2.1.0(vite@7.2.2(@types/node@24.10.1)(jiti@2.6.1)(terser@5.44.1)(yaml@2.8.1))
      vue: 3.5.24(typescript@5.9.3)
    transitivePeerDependencies:
      - vite
@@ -6784,13 +6785,13 @@ snapshots:

  '@vueuse/metadata@13.9.0': {}

-  '@vueuse/nuxt@11.3.0(magicast@0.5.1)(nuxt@3.20.1(@parcel/watcher@2.5.1)(@types/node@24.10.1)(@vue/compiler-sfc@3.5.24)(db0@0.3.4)(ioredis@5.8.2)(magicast@0.5.1)(ms@2.1.3)(rollup@4.53.3)(terser@5.44.1)(typescript@5.9.3)(vite@7.2.2(@types/node@24.10.1)(jiti@1.21.7)(terser@5.44.1)(yaml@2.8.1))(yaml@2.8.1))(vue@3.5.24(typescript@5.9.3))':
+  '@vueuse/nuxt@11.3.0(magicast@0.5.1)(nuxt@3.20.1(@parcel/watcher@2.5.1)(@types/node@24.10.1)(@vue/compiler-sfc@3.5.24)(db0@0.3.4)(ioredis@5.8.2)(magicast@0.5.1)(ms@2.1.3)(rollup@4.53.3)(terser@5.44.1)(typescript@5.9.3)(vite@7.2.2(@types/node@24.10.1)(jiti@2.6.1)(terser@5.44.1)(yaml@2.8.1))(yaml@2.8.1))(vue@3.5.24(typescript@5.9.3))':
    dependencies:
      '@nuxt/kit': 3.20.1(magicast@0.5.1)
      '@vueuse/core': 11.3.0(vue@3.5.24(typescript@5.9.3))
      '@vueuse/metadata': 11.3.0
      local-pkg: 0.5.1
-      nuxt: 3.20.1(@parcel/watcher@2.5.1)(@types/node@24.10.1)(@vue/compiler-sfc@3.5.24)(db0@0.3.4)(ioredis@5.8.2)(magicast@0.5.1)(ms@2.1.3)(rollup@4.53.3)(terser@5.44.1)(typescript@5.9.3)(vite@7.2.2(@types/node@24.10.1)(jiti@1.21.7)(terser@5.44.1)(yaml@2.8.1))(yaml@2.8.1)
+      nuxt: 3.20.1(@parcel/watcher@2.5.1)(@types/node@24.10.1)(@vue/compiler-sfc@3.5.24)(db0@0.3.4)(ioredis@5.8.2)(magicast@0.5.1)(ms@2.1.3)(rollup@4.53.3)(terser@5.44.1)(typescript@5.9.3)(vite@7.2.2(@types/node@24.10.1)(jiti@2.6.1)(terser@5.44.1)(yaml@2.8.1))(yaml@2.8.1)
      vue-demi: 0.14.10(vue@3.5.24(typescript@5.9.3))
    transitivePeerDependencies:
      - '@vue/composition-api'
@@ -6903,7 +6904,7 @@ snapshots:
  autoprefixer@10.4.22(postcss@8.5.6):
    dependencies:
      browserslist: 4.28.0
-      caniuse-lite: 1.0.30001756
+      caniuse-lite: 1.0.30001780
      fraction.js: 5.3.4
      normalize-range: 0.1.2
      picocolors: 1.1.1
@@ -6957,7 +6958,7 @@ snapshots:

  base64-js@1.5.1: {}

-  baseline-browser-mapping@2.8.29: {}
+  baseline-browser-mapping@2.10.9: {}

  binary-extensions@2.3.0: {}

@@ -6991,8 +6992,8 @@ snapshots:

  browserslist@4.28.0:
    dependencies:
-      baseline-browser-mapping: 2.8.29
-      caniuse-lite: 1.0.30001756
+      baseline-browser-mapping: 2.10.9
+      caniuse-lite: 1.0.30001780
      electron-to-chromium: 1.5.256
      node-releases: 2.0.27
      update-browserslist-db: 1.1.4(browserslist@4.28.0)
@@ -7057,11 +7058,11 @@ snapshots:
  caniuse-api@3.0.0:
    dependencies:
      browserslist: 4.28.0
-      caniuse-lite: 1.0.30001756
+      caniuse-lite: 1.0.30001780
      lodash.memoize: 4.1.2
      lodash.uniq: 4.5.0

-  caniuse-lite@1.0.30001756: {}
+  caniuse-lite@1.0.30001780: {}

  ccount@2.0.1: {}

@@ -8953,9 +8954,9 @@ snapshots:
    dependencies:
      boolbase: 1.0.0

-  nuxt-og-image@5.1.12(@unhead/vue@2.0.19(vue@3.5.24(typescript@5.9.3)))(h3@1.15.4)(magicast@0.5.1)(unstorage@1.17.2(db0@0.3.4)(ioredis@5.8.2))(vite@7.2.2(@types/node@24.10.1)(jiti@1.21.7)(terser@5.44.1)(yaml@2.8.1))(vue@3.5.24(typescript@5.9.3)):
+  nuxt-og-image@5.1.12(@unhead/vue@2.0.19(vue@3.5.24(typescript@5.9.3)))(h3@1.15.4)(magicast@0.5.1)(unstorage@1.17.2(db0@0.3.4)(ioredis@5.8.2))(vite@7.2.2(@types/node@24.10.1)(jiti@2.6.1)(terser@5.44.1)(yaml@2.8.1))(vue@3.5.24(typescript@5.9.3)):
    dependencies:
-      '@nuxt/devtools-kit': 2.7.0(magicast@0.5.1)(vite@7.2.2(@types/node@24.10.1)(jiti@1.21.7)(terser@5.44.1)(yaml@2.8.1))
+      '@nuxt/devtools-kit': 2.7.0(magicast@0.5.1)(vite@7.2.2(@types/node@24.10.1)(jiti@2.6.1)(terser@5.44.1)(yaml@2.8.1))
      '@nuxt/kit': 4.2.1(magicast@0.5.1)
      '@resvg/resvg-js': 2.6.2
      '@resvg/resvg-wasm': 2.6.2
@@ -9019,16 +9020,16 @@ snapshots:
      - magicast
      - vue

-  nuxt@3.20.1(@parcel/watcher@2.5.1)(@types/node@24.10.1)(@vue/compiler-sfc@3.5.24)(db0@0.3.4)(ioredis@5.8.2)(magicast@0.5.1)(ms@2.1.3)(rollup@4.53.3)(terser@5.44.1)(typescript@5.9.3)(vite@7.2.2(@types/node@24.10.1)(jiti@1.21.7)(terser@5.44.1)(yaml@2.8.1))(yaml@2.8.1):
+  nuxt@3.20.1(@parcel/watcher@2.5.1)(@types/node@24.10.1)(@vue/compiler-sfc@3.5.24)(db0@0.3.4)(ioredis@5.8.2)(magicast@0.5.1)(ms@2.1.3)(rollup@4.53.3)(terser@5.44.1)(typescript@5.9.3)(vite@7.2.2(@types/node@24.10.1)(jiti@2.6.1)(terser@5.44.1)(yaml@2.8.1))(yaml@2.8.1):
    dependencies:
      '@dxup/nuxt': 0.2.2(magicast@0.5.1)
      '@nuxt/cli': 3.30.0(magicast@0.5.1)
-      '@nuxt/devtools': 3.1.0(vite@7.2.2(@types/node@24.10.1)(jiti@1.21.7)(terser@5.44.1)(yaml@2.8.1))(vue@3.5.24(typescript@5.9.3))
+      '@nuxt/devtools': 3.1.0(vite@7.2.2(@types/node@24.10.1)(jiti@2.6.1)(terser@5.44.1)(yaml@2.8.1))(vue@3.5.24(typescript@5.9.3))
      '@nuxt/kit': 3.20.1(magicast@0.5.1)
-      '@nuxt/nitro-server': 3.20.1(db0@0.3.4)(ioredis@5.8.2)(magicast@0.5.1)(nuxt@3.20.1(@parcel/watcher@2.5.1)(@types/node@24.10.1)(@vue/compiler-sfc@3.5.24)(db0@0.3.4)(ioredis@5.8.2)(magicast@0.5.1)(ms@2.1.3)(rollup@4.53.3)(terser@5.44.1)(typescript@5.9.3)(vite@7.2.2(@types/node@24.10.1)(jiti@1.21.7)(terser@5.44.1)(yaml@2.8.1))(yaml@2.8.1))(typescript@5.9.3)
+      '@nuxt/nitro-server': 3.20.1(db0@0.3.4)(ioredis@5.8.2)(magicast@0.5.1)(nuxt@3.20.1(@parcel/watcher@2.5.1)(@types/node@24.10.1)(@vue/compiler-sfc@3.5.24)(db0@0.3.4)(ioredis@5.8.2)(magicast@0.5.1)(ms@2.1.3)(rollup@4.53.3)(terser@5.44.1)(typescript@5.9.3)(vite@7.2.2(@types/node@24.10.1)(jiti@2.6.1)(terser@5.44.1)(yaml@2.8.1))(yaml@2.8.1))(typescript@5.9.3)
      '@nuxt/schema': 3.20.1
      '@nuxt/telemetry': 2.6.6(magicast@0.5.1)
-      '@nuxt/vite-builder': 3.20.1(@types/node@24.10.1)(magicast@0.5.1)(ms@2.1.3)(nuxt@3.20.1(@parcel/watcher@2.5.1)(@types/node@24.10.1)(@vue/compiler-sfc@3.5.24)(db0@0.3.4)(ioredis@5.8.2)(magicast@0.5.1)(ms@2.1.3)(rollup@4.53.3)(terser@5.44.1)(typescript@5.9.3)(vite@7.2.2(@types/node@24.10.1)(jiti@1.21.7)(terser@5.44.1)(yaml@2.8.1))(yaml@2.8.1))(rollup@4.53.3)(terser@5.44.1)(typescript@5.9.3)(vue@3.5.24(typescript@5.9.3))(yaml@2.8.1)
+      '@nuxt/vite-builder': 3.20.1(@types/node@24.10.1)(magicast@0.5.1)(ms@2.1.3)(nuxt@3.20.1(@parcel/watcher@2.5.1)(@types/node@24.10.1)(@vue/compiler-sfc@3.5.24)(db0@0.3.4)(ioredis@5.8.2)(magicast@0.5.1)(ms@2.1.3)(rollup@4.53.3)(terser@5.44.1)(typescript@5.9.3)(vite@7.2.2(@types/node@24.10.1)(jiti@2.6.1)(terser@5.44.1)(yaml@2.8.1))(yaml@2.8.1))(rollup@4.53.3)(terser@5.44.1)(typescript@5.9.3)(vue@3.5.24(typescript@5.9.3))(yaml@2.8.1)
      '@unhead/vue': 2.0.19(vue@3.5.24(typescript@5.9.3))
      '@vue/shared': 3.5.24
      c12: 3.3.2(magicast@0.5.1)
@@ -10006,12 +10007,12 @@ snapshots:

  setprototypeof@1.2.0: {}

-  shadcn-docs-nuxt@0.8.21(@parcel/watcher@2.5.1)(@types/node@24.10.1)(@unhead/vue@2.0.19(vue@3.5.24(typescript@5.9.3)))(@vue/compiler-sfc@3.5.24)(db0@0.3.4)(h3@1.15.4)(ioredis@5.8.2)(magicast@0.5.1)(ms@2.1.3)(rollup@4.53.3)(tailwindcss@3.4.18(yaml@2.8.1))(terser@5.44.1)(unstorage@1.17.2(db0@0.3.4)(ioredis@5.8.2))(vite@7.2.2(@types/node@24.10.1)(jiti@1.21.7)(terser@5.44.1)(yaml@2.8.1))(yaml@2.8.1):
+  shadcn-docs-nuxt@0.8.21(@parcel/watcher@2.5.1)(@types/node@24.10.1)(@unhead/vue@2.0.19(vue@3.5.24(typescript@5.9.3)))(@vue/compiler-sfc@3.5.24)(db0@0.3.4)(h3@1.15.4)(ioredis@5.8.2)(magicast@0.5.1)(ms@2.1.3)(rollup@4.53.3)(tailwindcss@3.4.18(yaml@2.8.1))(terser@5.44.1)(unstorage@1.17.2(db0@0.3.4)(ioredis@5.8.2))(vite@7.2.2(@types/node@24.10.1)(jiti@2.6.1)(terser@5.44.1)(yaml@2.8.1))(yaml@2.8.1):
    dependencies:
      '@iconify-json/lucide': 1.2.73
      '@iconify-json/vscode-icons': 1.2.35
-      '@nuxt/content': 2.13.4(db0@0.3.4)(ioredis@5.8.2)(magicast@0.5.1)(nuxt@3.20.1(@parcel/watcher@2.5.1)(@types/node@24.10.1)(@vue/compiler-sfc@3.5.24)(db0@0.3.4)(ioredis@5.8.2)(magicast@0.5.1)(ms@2.1.3)(rollup@4.53.3)(terser@5.44.1)(typescript@5.9.3)(vite@7.2.2(@types/node@24.10.1)(jiti@1.21.7)(terser@5.44.1)(yaml@2.8.1))(yaml@2.8.1))(vue@3.5.24(typescript@5.9.3))
-      '@nuxt/icon': 1.15.0(magicast@0.5.1)(vite@7.2.2(@types/node@24.10.1)(jiti@1.21.7)(terser@5.44.1)(yaml@2.8.1))(vue@3.5.24(typescript@5.9.3))
+      '@nuxt/content': 2.13.4(db0@0.3.4)(ioredis@5.8.2)(magicast@0.5.1)(nuxt@3.20.1(@parcel/watcher@2.5.1)(@types/node@24.10.1)(@vue/compiler-sfc@3.5.24)(db0@0.3.4)(ioredis@5.8.2)(magicast@0.5.1)(ms@2.1.3)(rollup@4.53.3)(terser@5.44.1)(typescript@5.9.3)(vite@7.2.2(@types/node@24.10.1)(jiti@2.6.1)(terser@5.44.1)(yaml@2.8.1))(yaml@2.8.1))(vue@3.5.24(typescript@5.9.3))
+      '@nuxt/icon': 1.15.0(magicast@0.5.1)(vite@7.2.2(@types/node@24.10.1)(jiti@2.6.1)(terser@5.44.1)(yaml@2.8.1))(vue@3.5.24(typescript@5.9.3))
      '@nuxt/image': 1.11.0(db0@0.3.4)(ioredis@5.8.2)(magicast@0.5.1)
      '@nuxt/scripts': 0.11.13(@unhead/vue@2.0.19(vue@3.5.24(typescript@5.9.3)))(db0@0.3.4)(ioredis@5.8.2)(magicast@0.5.1)(typescript@5.9.3)(vue@3.5.24(typescript@5.9.3))
      '@nuxtjs/color-mode': 3.5.2(magicast@0.5.1)
@@ -10019,8 +10020,8 @@ snapshots:
      '@nuxtjs/tailwindcss': 6.14.0(magicast@0.5.1)(yaml@2.8.1)
      class-variance-authority: 0.7.1
      clsx: 2.1.1
-      nuxt: 3.20.1(@parcel/watcher@2.5.1)(@types/node@24.10.1)(@vue/compiler-sfc@3.5.24)(db0@0.3.4)(ioredis@5.8.2)(magicast@0.5.1)(ms@2.1.3)(rollup@4.53.3)(terser@5.44.1)(typescript@5.9.3)(vite@7.2.2(@types/node@24.10.1)(jiti@1.21.7)(terser@5.44.1)(yaml@2.8.1))(yaml@2.8.1)
-      nuxt-og-image: 5.1.12(@unhead/vue@2.0.19(vue@3.5.24(typescript@5.9.3)))(h3@1.15.4)(magicast@0.5.1)(unstorage@1.17.2(db0@0.3.4)(ioredis@5.8.2))(vite@7.2.2(@types/node@24.10.1)(jiti@1.21.7)(terser@5.44.1)(yaml@2.8.1))(vue@3.5.24(typescript@5.9.3))
+      nuxt: 3.20.1(@parcel/watcher@2.5.1)(@types/node@24.10.1)(@vue/compiler-sfc@3.5.24)(db0@0.3.4)(ioredis@5.8.2)(magicast@0.5.1)(ms@2.1.3)(rollup@4.53.3)(terser@5.44.1)(typescript@5.9.3)(vite@7.2.2(@types/node@24.10.1)(jiti@2.6.1)(terser@5.44.1)(yaml@2.8.1))(yaml@2.8.1)
+      nuxt-og-image: 5.1.12(@unhead/vue@2.0.19(vue@3.5.24(typescript@5.9.3)))(h3@1.15.4)(magicast@0.5.1)(unstorage@1.17.2(db0@0.3.4)(ioredis@5.8.2))(vite@7.2.2(@types/node@24.10.1)(jiti@2.6.1)(terser@5.44.1)(yaml@2.8.1))(vue@3.5.24(typescript@5.9.3))
      radix-vue: 1.9.17(vue@3.5.24(typescript@5.9.3))
      shadcn-nuxt: 1.0.3(magicast@0.5.1)
      tailwind-merge: 2.6.0
@@ -10738,13 +10739,13 @@ snapshots:
      '@types/unist': 3.0.3
      vfile-message: 4.0.3

-  vite-dev-rpc@1.1.0(vite@7.2.2(@types/node@24.10.1)(jiti@1.21.7)(terser@5.44.1)(yaml@2.8.1)):
+  vite-dev-rpc@1.1.0(vite@7.2.2(@types/node@24.10.1)(jiti@2.6.1)(terser@5.44.1)(yaml@2.8.1)):
    dependencies:
      birpc: 2.8.0
      vite: 7.2.2(@types/node@24.10.1)(jiti@1.21.7)(terser@5.44.1)(yaml@2.8.1)
-      vite-hot-client: 2.1.0(vite@7.2.2(@types/node@24.10.1)(jiti@1.21.7)(terser@5.44.1)(yaml@2.8.1))
+      vite-hot-client: 2.1.0(vite@7.2.2(@types/node@24.10.1)(jiti@2.6.1)(terser@5.44.1)(yaml@2.8.1))

-  vite-hot-client@2.1.0(vite@7.2.2(@types/node@24.10.1)(jiti@1.21.7)(terser@5.44.1)(yaml@2.8.1)):
+  vite-hot-client@2.1.0(vite@7.2.2(@types/node@24.10.1)(jiti@2.6.1)(terser@5.44.1)(yaml@2.8.1)):
    dependencies:
      vite: 7.2.2(@types/node@24.10.1)(jiti@1.21.7)(terser@5.44.1)(yaml@2.8.1)

@@ -10769,7 +10770,7 @@ snapshots:
      - tsx
      - yaml

-  vite-plugin-checker@0.11.0(typescript@5.9.3)(vite@7.2.2(@types/node@24.10.1)(jiti@1.21.7)(terser@5.44.1)(yaml@2.8.1)):
+  vite-plugin-checker@0.11.0(typescript@5.9.3)(vite@7.2.2(@types/node@24.10.1)(jiti@2.6.1)(terser@5.44.1)(yaml@2.8.1)):
    dependencies:
      '@babel/code-frame': 7.27.1
      chokidar: 4.0.3
@@ -10783,7 +10784,7 @@ snapshots:
    optionalDependencies:
      typescript: 5.9.3

-  vite-plugin-inspect@11.3.3(@nuxt/kit@4.2.1(magicast@0.5.1))(vite@7.2.2(@types/node@24.10.1)(jiti@1.21.7)(terser@5.44.1)(yaml@2.8.1)):
+  vite-plugin-inspect@11.3.3(@nuxt/kit@4.2.1(magicast@0.5.1))(vite@7.2.2(@types/node@24.10.1)(jiti@2.6.1)(terser@5.44.1)(yaml@2.8.1)):
    dependencies:
      ansis: 4.2.0
      debug: 4.4.3
@@ -10794,13 +10795,13 @@ snapshots:
      sirv: 3.0.2
      unplugin-utils: 0.3.1
      vite: 7.2.2(@types/node@24.10.1)(jiti@1.21.7)(terser@5.44.1)(yaml@2.8.1)
-      vite-dev-rpc: 1.1.0(vite@7.2.2(@types/node@24.10.1)(jiti@1.21.7)(terser@5.44.1)(yaml@2.8.1))
+      vite-dev-rpc: 1.1.0(vite@7.2.2(@types/node@24.10.1)(jiti@2.6.1)(terser@5.44.1)(yaml@2.8.1))
    optionalDependencies:
      '@nuxt/kit': 4.2.1(magicast@0.5.1)
    transitivePeerDependencies:
      - supports-color

-  vite-plugin-vue-tracer@1.1.3(vite@7.2.2(@types/node@24.10.1)(jiti@1.21.7)(terser@5.44.1)(yaml@2.8.1))(vue@3.5.24(typescript@5.9.3)):
+  vite-plugin-vue-tracer@1.1.3(vite@7.2.2(@types/node@24.10.1)(jiti@2.6.1)(terser@5.44.1)(yaml@2.8.1))(vue@3.5.24(typescript@5.9.3)):
    dependencies:
      estree-walker: 3.0.3
      exsolve: 1.0.8