jan/autoqa/tests/migration/assistants/setup-chat-with-assistant.txt

76 lines
3.0 KiB
Plaintext
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

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 setting up a chat thread using a custom assistant in the OLD version of the Jan application.
PHASE: SETUP CHAT THREAD (OLD VERSION)
Step-by-step instructions:
1. Open the Jan application (OLD version).
2. Download the model:
- In the bottom-left corner, click **Hub**.
- Find and download the model named: `jan-nano-gguf`.
- Wait for the download to complete (the button changes to **Use**).
- Click the **Use** button to return to the Chat UI.
3. Start a new chat using a custom assistant:
- In the main chat panel, click the assistant icon at the top (default is `Jan`).
- Select the custom assistant: `Python Tutor`.
4. Select the model:
- Click the **Select a model** button below the chat input.
- Choose: `jan-nano-gguf` under the `Llama.Cpp` section.
5. Send a test message:
- Type: `Hello world` and press Enter or click send message (button with right arrow). You should click at the center of the button.
- Wait up to 12 minutes for the model to load and respond.
6. Verify the model responds:
- If the model replies appropriately, and the thread is created successfully in the left sidebar under **No threads yet**, return:
{"result": True, "phase": "setup_complete"}
- If no response is received or the chat thread is not saved:
{"result": False, "phase": "setup_failed"}
5. Verify the model responds and return the result in the exact JSON format:
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 model replies appropriately, and the thread is created successfully in the left sidebar, return:
{"result": True, "phase": "setup_complete"}
- If no response is received:
{"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
"""