148 lines
6.8 KiB
Plaintext
148 lines
6.8 KiB
Plaintext
# Instruction
|
||
- You are an expert in cleaning process data descriptions. Given a task, you are provided with a set of annotation description
|
||
data for a certain visual LLM related to human user operation videos. Plus, You are provided with full trace of playwright action,
|
||
whic includes action and url before and after the action.
|
||
- You need to analyze all the descriptive data and ultimately summarize a complete and reasonable user operation description that can accomplish the given task.
|
||
- For each strategy, give a clear list of the low level action sequence.
|
||
|
||
# Task
|
||
Today is 6/12/2023. Tell me how many fulfilled orders I have over the past three days, and the total amount of money I spent.
|
||
|
||
# Annotation description
|
||
### Step-by-Step Actions in the Video Segment
|
||
|
||
#### 1. **Action:** I click on the "My Account" link located at the top right corner of the webpage.
|
||
- **Page Changes:** The page transitions to the "My Account" section, displaying various account-related options such as "My Orders," "My Wish List," "Address Book," etc., on the left sidebar. The main content area shows a heading "My Account" with sections for "Account Information," "Contact Information," and "Newsletters."
|
||
- **Possible Purpose:** The likely intent is to access personal account settings and information, possibly to review orders, update account details, or manage preferences.
|
||
|
||
#### 2. **Action:** I click on the "My Orders" link in the left sidebar under the "My Account" section.
|
||
- **Page Changes:** The page updates to display a list of past orders under the "My Orders" heading. This list includes columns for "Order #," "Date," "Order Total," "Status," and "Action." Each order entry provides options to "View Order" and "Reorder."
|
||
- **Possible Purpose:** The purpose is to review previous purchase history, which could be for verifying past transactions, checking order statuses, or considering reordering items.
|
||
|
||
#### 3. **Action:** I hover over the "My Orders" heading.
|
||
- **Page Changes:** There are no significant changes to the page content, but the hovering action highlights the "My Orders" text, indicating it is an interactive element.
|
||
- **Possible Purpose:** Hovering might be to ensure the correct selection before clicking or to reveal any additional options or tooltips associated with the "My Orders" section.
|
||
|
||
#### 4. **Action:** I scroll down slightly within the "My Orders" section.
|
||
- **Page Changes:** The visible portion of the order list updates, showing more entries as I scroll. The top part of the list moves out of view, and new orders appear at the bottom of the list.
|
||
- **Possible Purpose:** Scrolling allows me to view additional orders that were initially not visible, providing a comprehensive overview of all past transactions.
|
||
|
||
### Summary
|
||
In this video segment, I navigate from the main webpage to the "My Account" section and then specifically to "My Orders." My actions include clicking on relevant links to access account information and order history, hovering to confirm selections, and scrolling to view more data. These steps suggest a focus on reviewing and managing past orders within the account.
|
||
|
||
# Playwright action
|
||
[
|
||
{
|
||
"action_uid": "link_My Account",
|
||
"idx": 0,
|
||
"action_repr": "frame.clickget_by_role(\"link\", name=\"My Account\")",
|
||
"before": {
|
||
"url": "http://ec2-3-135-39-80.us-east-2.compute.amazonaws.com:7770/"
|
||
},
|
||
"after": {
|
||
"url": "http://ec2-3-135-39-80.us-east-2.compute.amazonaws.com:7770/"
|
||
}
|
||
},
|
||
{
|
||
"action_uid": "link_My Orders",
|
||
"idx": 1,
|
||
"action_repr": "frame.clickget_by_role(\"link\", name=\"My Orders\")",
|
||
"before": {
|
||
"url": "http://ec2-3-135-39-80.us-east-2.compute.amazonaws.com:7770/sales/order/history/"
|
||
},
|
||
"after": {
|
||
"url": "http://ec2-3-135-39-80.us-east-2.compute.amazonaws.com:7770/customer/account/"
|
||
}
|
||
},
|
||
{
|
||
"action_uid": "link_Page 2",
|
||
"idx": 2,
|
||
"action_repr": "frame.clickget_by_role(\"link\", name=\"Page 2\")",
|
||
"before": {
|
||
"url": "http://ec2-3-135-39-80.us-east-2.compute.amazonaws.com:7770/sales/order/history/"
|
||
},
|
||
"after": {
|
||
"url": "http://ec2-3-135-39-80.us-east-2.compute.amazonaws.com:7770/sales/order/history/"
|
||
}
|
||
}
|
||
]
|
||
|
||
# Output format
|
||
- 先总结整个任务的Objective，然后按照Strategy-SubStrategy-action三级层次来给出整个过程，
|
||
- 接着给出整个操作流程后的观察和有趣的发现，最后严格按照json格式输出三级层次的过程描述。
|
||
- 最后的输出json应该是包在```{json}```之间，最底层动作需要包含描述、对应的playwright动作指令顺序编号，以及具体指令内容。
|
||
|
||
# Example
|
||
### Complete User Operation Description to Display Labeled Issues in kkroening/ffmpeg-python
|
||
|
||
**Objective:** Filter and display all issues labeled as "question" in the kkroening/ffmpeg-python repository.
|
||
|
||
---
|
||
|
||
#### **Strategy 1: Navigate to the Repository**
|
||
**Low-Level Action Sequence:**
|
||
1. **Search for the user "kkroening"**
|
||
- Click the global search bar (placeholder: "Search GitLab").
|
||
- Type "kkroening" and press `Enter`.
|
||
2. **Select the user from results**
|
||
- Click the "Users" tab in search results.
|
||
- Click on "Karl Kroening @kkroening" in the user list.
|
||
3. **Access the repository**
|
||
- Navigate to the "Personal projects" section.
|
||
- Click on the "ffmpeg-python" project.
|
||
|
||
---
|
||
|
||
#### **Strategy 2: Filter Issues by Label**
|
||
**Low-Level Action Sequence:**
|
||
1. **Open the Issues tab**
|
||
- Scroll to the left sidebar menu.
|
||
- Click the "Issues" tab (displaying the count, e.g., "Issues 402").
|
||
2. **Apply label filtering**
|
||
- Click the search/filter bar in the issues list.
|
||
- Select the "Label" dropdown from the filter options.
|
||
- Type or select "question" from the label dropdown.
|
||
- Click the search/apply button to confirm the filter.
|
||
|
||
---
|
||
|
||
#### **Final Oberservation**
|
||
The issues list will refresh to show only issues with the "question" label. The URL will reflect the filter:
|
||
`.../ffmpeg-python/-/issues/?label_name[]=question`.
|
||
|
||
---
|
||
|
||
### Key Observations from Playwright Trace
|
||
- The final URL after filtering:
|
||
`http://ec2-3-135-39-80.../ffmpeg-python/-/issues/?label_name%5B%5D=question`
|
||
confirms the "question" label filter is applied.
|
||
- Critical interactions include selecting the "Label" dropdown and explicitly choosing "question" to refine results.
|
||
|
||
### Final output
|
||
```json
|
||
[{
|
||
"strategy" : "Navigate to the Repository",
|
||
"substrategies": [
|
||
{
|
||
"substrategy": "Search for the user \"kkroening\"",
|
||
"actions" : [
|
||
{
|
||
"description": "Click the global search bar (placeholder: \"Search GitLab\"). ",
|
||
"playwright_idx" : 18,
|
||
"playwright_instruction" : "frame.pressget_by_placeholder(\"Search GitLab\")Enter"
|
||
}
|
||
]
|
||
},
|
||
{
|
||
"substrategy": "Select the user from results",
|
||
"actions" : [
|
||
]
|
||
}
|
||
]
|
||
},
|
||
{
|
||
"strategy" : "Filter Issues by Label",
|
||
"substrategies" : [
|
||
]
|
||
}]
|
||
``` |