79 lines
3.2 KiB
Plaintext
79 lines
3.2 KiB
Plaintext
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 disabling specific Model Providers in the Jan application to verify they are hidden from the sidebar list.
|
|
|
|
TARGET PROVIDERS TO DISABLE: Llama.cpp, OpenAI, Anthropic
|
|
|
|
Step-by-step instructions:
|
|
|
|
1. Open the Jan application.
|
|
- 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. Disable selected providers:
|
|
- For each of the following providers on the right panel (Llama.cpp, OpenAI, Anthropic):
|
|
- Locate the provider row.
|
|
- On the right side of the row, find the enable/disable chip/toggle (enabled by default).
|
|
- If it is enabled, click the chip/toggle to disable it.
|
|
- Immediately call `wait()` once to allow the UI to update and the next screenshot to be captured for the model.
|
|
- If it is already disabled, leave it as is (no click). Still call `wait()` once to confirm state in the next screenshot.
|
|
|
|
4. Verify providers are hidden in the sidebar list:
|
|
- Call `wait()` once more to ensure the sidebar reflects the latest state.
|
|
- Check the left sidebar list under **Model Providers**.
|
|
- Confirm that the entries for **Llama.cpp**, **OpenAI**, and **Anthropic** are not visible in the sidebar after disabling.
|
|
|
|
5. Return result:
|
|
- If all three providers (Llama.cpp, OpenAI, Anthropic) are disabled and not visible in the sidebar list, return:
|
|
{"result": True}
|
|
- If any of the three providers is still visible in the sidebar list after being disabled, return:
|
|
{"result": False}
|
|
|
|
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
|
|
|
|
- On success, return:
|
|
{"result": True}
|
|
- On failure, return:
|
|
{"result": False}
|
|
|
|
IMPORTANT:
|
|
- Your response must be ONLY the JSON above
|
|
- Do NOT add any other text before or after the JSON
|
|
"""
|
|
|