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
```
Thought: ...
Action: ...
```

## 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 configuring Model Providers in the OLD version of the Jan application to prepare for migration verification.

PHASE: SETUP MODEL PROVIDERS (OLD VERSION)

Desired state:
- Disabled: Llama.cpp, OpenAI, Anthropic
- Enabled: Cohere, OpenRouter, Mistral, Groq, Gemini, Hugging Face

Step-by-step instructions:

1. Open the Jan application (OLD version).
   - If a dialog appears in the bottom-right corner titled **"Help Us Improve Jan"**, click **Deny** to dismiss it before continuing.
   - If **New Version Available** popup appears on app launch (older versions), click **Remind Me Later** to dismiss it before continuing.

2. Navigate to Model Providers settings:
   - In the bottom-left menu, click **Settings**.
   - In the left sidebar, click **Model Providers**.

3. Set provider states:
   - For each provider in the right panel, use the chip/toggle on the right side of the row to set the desired state:
     - Llama.cpp: disable (toggle off if enabled), then call `wait()` once
     - OpenAI: disable (toggle off if enabled), then call `wait()` once
     - Anthropic: disable (toggle off if enabled), then call `wait()` once
     - Cohere: enable (toggle on if disabled), then call `wait()` once
     - OpenRouter: enable (toggle on if disabled), then call `wait()` once
     - Mistral: enable (toggle on if disabled), then call `wait()` once
     - Groq: enable (toggle on if disabled), then call `wait()` once
     - Gemini: enable (toggle on if disabled), then call `wait()` once
     - Hugging Face: enable (toggle on if disabled), then call `wait()` once

4. Return result:
   - If all providers are set to the desired states (Disabled: Llama.cpp, OpenAI, Anthropic; Enabled: Cohere, OpenRouter, Mistral, Groq, Gemini, Hugging Face), return:
     {"result": True, "phase": "setup_complete"}
   - If any provider cannot be set to the desired state, return:
     {"result": False, "phase": "setup_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 the configuration is successful, return:
     {"result": True, "phase": "setup_complete"}
   - If there are any issues, return:
     {"result": False, "phase": "setup_failed"}

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