prompt = """
You are verifying that model downloads and settings persist after Jan application upgrade.

PHASE 2 - VERIFICATION (NEW VERSION):
Step-by-step instructions for NEW version verification:

1. Given the Jan application is already opened (NEW version after upgrade).

2. Verify models in Hub:
   - Click the **Hub** menu in the bottom-left corner
   - Look for the models that were downloaded: **jan-nano-gguf** and others
   - Verify they show **Use** button instead of **Download** button
   - Click the **Downloaded** filter toggle on the right
   - Verify downloaded models appear in the filtered list
   - Turn off the Downloaded filter

3. Verify models are available in chat:
   - Click **New Chat**
   - Click on the model dropdown
   - Verify downloaded models appear in the selectable list
   - Select **jan-nano-gguf**
   - Send: "Are you working correctly after the app upgrade?"
   - Wait for response - should work normally

4. Verify model provider settings:
   - Go to **Settings** > **Model Providers**
   - Click on **Llama.cpp** section (in the left sidebar, NOT the toggle)
   - Verify downloaded models are listed in the Models section with correct names
   - Check that any previously configured settings are preserved

5. Test model management features:
   - In the Models list, verify you can see model details
   - Test that you can still start/stop models if applicable
   - Verify model functionality is intact

If all downloaded models are preserved, show correct status in Hub, work in chat, and model provider settings are maintained, return: {"result": True, "phase": "verification_complete"}, otherwise return: {"result": False, "phase": "verification_failed"}.

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