automatic-oauth-vulnerabili.../browser-use/.github/ISSUE_TEMPLATE/1_element_detection_bug.yml
2025-05-18 21:57:54 +09:00

116 lines
4.2 KiB
YAML

name: 🎯 Agent Page Interaction Issue
description: Agent fails to detect, click, scroll, input, or otherwise interact with some type of element on some page(s)
labels: ["bug", "element-detection"]
body:
- type: markdown
attributes:
value: |
Thanks for taking the time to fill out this bug report! Please fill out the form below to help us reproduce and fix the issue.
- type: input
id: version
attributes:
label: Browser Use Version
description: What version of the `browser-use` library are you using? (Run `uv pip show browser-use` or `git log -n 1` to find out) **DO NOT JUST WRITE `latest version` or `main`**
placeholder: "e.g. 0.4.45 or 62760baaefd"
validations:
required: true
- type: dropdown
id: model
attributes:
label: LLM Model
description: Which LLM model(s) are you using?
multiple: true
options:
- gpt-4o
- gpt-4o-mini
- gpt-4
- gpt-4.1
- gpt-4.1-mini
- gpt-4.1-nano
- claude-3.7-sonnet
- claude-3.5-sonnet
- gemini-2.6-flash-preview
- gemini-2.5-pro
- gemini-2.0-flash
- gemini-2.0-flash-lite
- gemini-1.5-flash
- deepseek-chat
- Local Model (Specify model in description)
- Other (specify in description)
validations:
required: true
- type: textarea
id: prompt
attributes:
label: Screenshots, Description, and Task Prompt Given to Agent
description: The full task prompt you're giving the agent (redact any sensitive data) + a description of the issue and screenshots.
placeholder: |
1. go to https://example.com and click the xyz button...
2. type "abc" in the dropdown search to find the "abc" option <- agent fails to click dropdown here
3. Click the "Submit" button, then extract the result as JSON
...
include relevant URLs and/or redacted screenshots of the relevant page(s) if possible
validations:
required: true
- type: textarea
id: html
attributes:
label: HTML around where it's failing
description: A snippet of the HTML from the failing page around where the Agent is failing to interact.
render: html
placeholder: |
<form na-someform="abc">
<div class="element-to-click">
<div data-isbutton="true">Click me</div>
</div>
<input id="someinput" name="someinput" type="text" />
...
</form>
validations:
required: true
- type: input
id: os
attributes:
label: Operating System
description: What operating system are you using?
placeholder: "e.g., macOS 13.1, Windows 11, Ubuntu 22.04"
validations:
required: true
- type: textarea
id: code
attributes:
label: Python Code Sample
description: Include some python code that reproduces the issue
render: python
placeholder: |
from dotenv import load_dotenv
load_dotenv()
from browser_use import Agent, Browser, Controller
from langchain_openai import ChatOpenAI
llm = ChatOpenAI(model="gpt-4o")
browser = Browser(chrome_binary_path='/usr/bin/google-chrome')
agent = Agent(llm=llm, browser=browser))
...
- type: textarea
id: logs
attributes:
label: Full DEBUG Log Output
description: Please copy and paste the *full* log output *from the start of the run*. Make sure to set `BROWSER_USE_LOG_LEVEL=DEBUG` in your `.env` or shell environment.
render: shell
placeholder: |
$ python /app/browser-use/examples/browser/real_browser.py
DEBUG [browser] 🌎 Initializing new browser
DEBUG [agent] Version: 0.1.46-9-g62760ba, Source: git
INFO [agent] 🧠 Starting an agent with main_model=gpt-4o +tools +vision +memory, planner_model=None, extraction_model=gpt-4o
DEBUG [agent] Verifying the ChatOpenAI LLM knows the capital of France...
DEBUG [langsmith.client] Sending multipart request with context: trace=91282a01-6667-48a1-8cd7-21aa9337a580,id=91282a01-6667-48a1-8cd7-21aa9337a580
DEBUG [agent] 🪪 LLM API keys OPENAI_API_KEY work, ChatOpenAI model is connected & responding correctly.
...