prompt = """
You are testing comprehensive model functionality persistence across Jan application upgrade.

PHASE 1 - SETUP (OLD VERSION):
Step-by-step instructions for OLD version setup:

1. Given the Jan application is already opened (OLD version).

2. Download multiple models from Hub:
   - Click the **Hub** menu in the bottom-left corner
   - Find and download **jan-nano-gguf** model
   - Wait for download to complete (shows "Use" button)
   - Find and download **gemma-2-2b-instruct-gguf** model if available
   - Wait for second download to complete

3. Test downloaded models in Hub:
   - Verify both models show **Use** button instead of **Download**
   - Click the **Downloaded** filter toggle on the right
   - Verify both models appear in the downloaded models list
   - Turn off the Downloaded filter

4. Test models in chat:
   - Click **New Chat**
   - Select **jan-nano-gguf** from model dropdown
   - Send: "Hello, can you tell me what model you are?"
   - Wait for response
   
   - Create another new chat
   - Select the second model from dropdown
   - Send: "What's your model name and capabilities?"
   - Wait for response

5. Configure model provider settings:
   - Go to **Settings** > **Model Providers**
   - Click on **Llama.cpp** section
   - Verify downloaded models are listed in the Models section
   - Check that both models show correct names
   - Try enabling **Auto-Unload Old Models** option
   - Try adjusting **Context Length** for one of the models

6. Test model settings persistence:
   - Close Jan completely
   - Reopen Jan
   - Go to Settings > Model Providers > Llama.cpp
   - Verify the Auto-Unload setting is still enabled
   - Verify model settings are preserved

If all models download successfully, appear in Hub with "Use" status, work in chat, and settings are preserved, return: {"result": True, "phase": "setup_complete"}, otherwise return: {"result": False, "phase": "setup_failed"}.

In all your responses, use only plain ASCII characters. Do NOT use Unicode symbols.
"""