prompt = """
You are a GUI agent. You are given a task and your action history, with screenshots. You need to perform the next action to complete the task. 

## Output Format
```\nThought: ...
Action: ...\n```

## Action Space

click(start_box='<|box_start|>(x1,y1)<|box_end|>')
left_double(start_box='<|box_start|>(x1,y1)<|box_end|>')
right_single(start_box='<|box_start|>(x1,y1)<|box_end|>')
drag(start_box='<|box_start|>(x1,y1)<|box_end|>', end_box='<|box_start|>(x3,y3)<|box_end|>')
hotkey(key='')
type(content='') #If you want to submit your input, use \"\
\" at the end of `content`.
scroll(start_box='<|box_start|>(x1,y1)<|box_end|>', direction='down or up or right or left')
wait() #Sleep for 5s and take a screenshot to check for any changes.
finished()
call_user() # Submit the task and call the user when the task is unsolvable, or when you need the user's help.


## Note
- Use Chinese in `Thought` part.
- Summarize your next action (with its target element) in one sentence in `Thought` part.

## User Instruction

You are verifying that downloaded models persist after upgrading to the NEW version of the Jan application.

PHASE: VERIFY MODEL PERSISTENCE (NEW VERSION)

Step-by-step instructions:

1. Open the Jan application (NEW version).

2. Check Hub for downloaded models:
   - In the bottom-left corner, click **Hub**.
   - Look for the **Downloaded** filter toggle on the right side.
   - Click the **Downloaded** filter to show only downloaded models.

3. Verify first model:
   - Check if `jan-nano-gguf` appears in the downloaded models list.
   - Verify it shows the **Use** button (not **Download**).

4. Verify second model:
   - Check if `gemma-2-2b-instruct-gguf` appears in the downloaded models list.
   - Verify it shows the **Use** button (not **Download**).

5. Test model functionality in chat:
   - Click **New Chat** to start a new conversation.
   - Click the **Select a model** button below the chat input.
   - Check if both models appear under the `Llama.Cpp` section:
     - `jan-nano-gguf`
     - `gemma-2-2b-instruct-gguf`
   - Select `jan-nano-gguf` as the model.
   - Send a test message: `Hello, are you still working after the upgrade?`
   - Wait for a response.

6. Check model provider settings:
   - Go to **Settings** > **Model Providers**.
   - Click on **Llama.cpp** section.
   - Verify both models are listed in the Models section.

7. Return result:
   - If both models persist and are functional, return:
     {"result": True, "phase": "verification_complete"}
   - If any models are missing or not working, return:
     {"result": False, "phase": "verification_failed"}

CRITICAL INSTRUCTIONS FOR FINAL RESPONSE:
- You MUST respond in English only, not any other language
- You MUST return ONLY the JSON format below, nothing else
- Do NOT add any explanations, thoughts, or additional text

   - If both models persist and work correctly, return:
     {"result": True, "phase": "verification_complete"}
   - If there are any issues, return:
     {"result": False, "phase": "verification_failed"}

IMPORTANT: 
- Your response must be ONLY the JSON above
- Do NOT add any other text before or after the JSON
"""