trace_synthesis/summary/118_prompt_debug.txt
yuyr a84d51a101 1. 增加r1生成综合策略代码和输出;
2. 增加tasks;
3. 增加analysis部分,对策略进行归纳分类,然后进行评测。
2025-04-17 17:40:15 +08:00

137 lines
5.7 KiB
Plaintext
Raw Permalink 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.

# 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
I have jaw bruxism problem, show me something that could alleviate the problem.
# Annotation description
### Step-by-Step Actions:
1. **Action:** I click on the search bar at the top of the webpage.
- **Page Changes:** The search bar becomes active, and a blinking cursor appears inside it, indicating that it is ready for text input.
- **Possible Purpose:** The likely intent is to initiate a search query on the website by entering specific keywords.
2. **Action:** I type "jaw bruxism" into the search bar.
- **Page Changes:** As I type, the text "jaw bruxism" appears in the search bar. No other immediate changes occur on the page until the search is executed.
- **Possible Purpose:** The purpose is to find products or information related to "jaw bruxism" on the website.
3. **Action:** I press the Enter key or click the search icon next to the search bar.
- **Page Changes:** The webpage transitions to display search results for "jaw bruxism." The header now shows "Search results for: 'jaw bruxism'" and lists various products related to the query.
- **Possible Purpose:** The intent is to view and explore the products or information available that match the search term "jaw bruxism."
4. **Action:** I scroll down the page slightly to view more of the search results.
- **Page Changes:** Additional products related to "jaw bruxism" become visible as I scroll.
- **Possible Purpose:** The purpose is to get a better overview of the available options and potentially find a suitable product.
### Summary:
In this video segment, I interact with the website by using the search functionality. I activate the search bar, enter the term "jaw bruxism," execute the search, and then scroll through the resulting page to view the available products. Each action is aimed at finding and exploring items related to "jaw bruxism" on the website.
# Playwright action
[
{
"action_uid": "action_0",
"idx": 0,
"action_repr": "frame.clickget_by_placeholder(\"Search entire store here...\")",
"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": "action_1",
"idx": 1,
"action_repr": "frame.pressget_by_placeholder(\"Search entire store here...\")Enter",
"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/"
}
}
]
# 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" : [
]
}]
```