Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fix Issue #601 - add function to close intermediate tabs #613

Closed

Conversation

k-w-lee
Copy link
Contributor

@k-w-lee k-w-lee commented Feb 7, 2025

Resolves: #601 Fix: Ensure intermediate tabs are properly closed before opening new ones

This PR resolves #601

Issue Description

The agent was expected to close intermediate tabs before opening new ones, but logs showed that no tabs were actually closed. This caused multiple unused tabs to remain open, potentially leading to performance issues and resource leaks.

Reproduction Steps

  1. Run the agent with multiple tabs opening in sequence.
  2. Observe that intermediate tabs are not being closed.
  3. Expectation: The agent should close all but the last opened tab before proceeding.
  4. Actual Result: Tabs remain open despite logs indicating closures.

Fix Details

  • Implemented close_intermediate_tabs method.
  • Retrieves the current browser session and context.
  • Ensures all but the last opened tab are closed.
  • Added a safeguard to check if a tab is already closed before attempting to close it.
  • Logs successful closures and warnings on failures.

Affected File

  • browser-use/browser_use/browser/context.py

Looking forward to feedback! 🚀

@k-w-lee k-w-lee changed the title add function to close intermediate tabs Fix Issue - add function to close intermediate tabs Feb 7, 2025
@k-w-lee k-w-lee changed the title Fix Issue - add function to close intermediate tabs Fix Issue #601 - add function to close intermediate tabs Feb 7, 2025
Copy link
Contributor

codebeaver-ai bot commented Feb 7, 2025

I opened a Pull Request with the following:

🔄 1 test added.
🐛 No bugs detected in your changes
🛠️ 1/8 tests passed

🔄 Test Updates

I've added 1 tests. They all pass ☑️
New Tests:

  • tests/test_context.py

No existing tests required updates.

🐛 Bug Detection

No bugs detected in your changes. Good job!

🛠️ Test Results

1/8 tests passed ⚠️

tests/test_dropdown.py

View error
tests/test_dropdown.py:20: in <module>
    llm = ChatOpenAI(model='gpt-4o')
/usr/local/lib/python3.11/site-packages/langchain_core/load/serializable.py:125: in __init__
    super().__init__(*args, **kwargs)
/usr/local/lib/python3.11/site-packages/langchain_openai/chat_models/base.py:622: in validate_environment
    self.root_client = openai.OpenAI(**client_params, **sync_specific)  # type: ignore[arg-type]
/usr/local/lib/python3.11/site-packages/openai/_client.py:110: in __init__
    raise OpenAIError(
E   openai.OpenAIError: The api_key client option must be set either by passing api_key to the client or by setting the OPENAI_API_KEY environment variable

tests/test_dropdown.py

tests/test_dropdown_complex.py

View error
tests/test_dropdown_complex.py:20: in <module>
    llm = ChatOpenAI(model='gpt-4o')
/usr/local/lib/python3.11/site-packages/langchain_core/load/serializable.py:125: in __init__
    super().__init__(*args, **kwargs)
/usr/local/lib/python3.11/site-packages/langchain_openai/chat_models/base.py:622: in validate_environment
    self.root_client = openai.OpenAI(**client_params, **sync_specific)  # type: ignore[arg-type]
/usr/local/lib/python3.11/site-packages/openai/_client.py:110: in __init__
    raise OpenAIError(
E   openai.OpenAIError: The api_key client option must be set either by passing api_key to the client or by setting the OPENAI_API_KEY environment variable

tests/test_dropdown_complex.py

tests/test_dropdown_error.py

View error
tests/test_dropdown_error.py:20: in <module>
    llm = ChatOpenAI(model='gpt-4o')
/usr/local/lib/python3.11/site-packages/langchain_core/load/serializable.py:125: in __init__
    super().__init__(*args, **kwargs)
/usr/local/lib/python3.11/site-packages/langchain_openai/chat_models/base.py:622: in validate_environment
    self.root_client = openai.OpenAI(**client_params, **sync_specific)  # type: ignore[arg-type]
/usr/local/lib/python3.11/site-packages/openai/_client.py:110: in __init__
    raise OpenAIError(
E   openai.OpenAIError: The api_key client option must be set either by passing api_key to the client or by setting the OPENAI_API_KEY environment variable

tests/test_dropdown_error.py

tests/test_gif_path.py

View error
tests/test_gif_path.py:19: in <module>
    llm = ChatOpenAI(model='gpt-4o')
/usr/local/lib/python3.11/site-packages/langchain_core/load/serializable.py:125: in __init__
    super().__init__(*args, **kwargs)
/usr/local/lib/python3.11/site-packages/langchain_openai/chat_models/base.py:622: in validate_environment
    self.root_client = openai.OpenAI(**client_params, **sync_specific)  # type: ignore[arg-type]
/usr/local/lib/python3.11/site-packages/openai/_client.py:110: in __init__
    raise OpenAIError(
E   openai.OpenAIError: The api_key client option must be set either by passing api_key to the client or by setting the OPENAI_API_KEY environment variable

tests/test_gif_path.py

tests/test_models.py

View error
tests/test_models.py:54: in <module>
    ChatOpenAI(
/usr/local/lib/python3.11/site-packages/langchain_core/load/serializable.py:125: in __init__
    super().__init__(*args, **kwargs)
/usr/local/lib/python3.11/site-packages/langchain_openai/chat_models/base.py:622: in validate_environment
    self.root_client = openai.OpenAI(**client_params, **sync_specific)  # type: ignore[arg-type]
/usr/local/lib/python3.11/site-packages/openai/_client.py:110: in __init__
    raise OpenAIError(
E   openai.OpenAIError: The api_key client option must be set either by passing api_key to the client or by setting the OPENAI_API_KEY environment variable

tests/test_models.py

tests/test_react_dropdown.py

View error
tests/test_react_dropdown.py:20: in <module>
    llm = ChatOpenAI(model='gpt-4o')
/usr/local/lib/python3.11/site-packages/langchain_core/load/serializable.py:125: in __init__
    super().__init__(*args, **kwargs)
/usr/local/lib/python3.11/site-packages/langchain_openai/chat_models/base.py:622: in validate_environment
    self.root_client = openai.OpenAI(**client_params, **sync_specific)  # type: ignore[arg-type]
/usr/local/lib/python3.11/site-packages/openai/_client.py:110: in __init__
    raise OpenAIError(
E   openai.OpenAIError: The api_key client option must be set either by passing api_key to the client or by setting the OPENAI_API_KEY environment variable

tests/test_react_dropdown.py

tests/test_vision.py

View error
tests/test_vision.py:25: in <module>
    llm = ChatOpenAI(model='gpt-4o')
/usr/local/lib/python3.11/site-packages/langchain_core/load/serializable.py:125: in __init__
    super().__init__(*args, **kwargs)
/usr/local/lib/python3.11/site-packages/langchain_openai/chat_models/base.py:622: in validate_environment
    self.root_client = openai.OpenAI(**client_params, **sync_specific)  # type: ignore[arg-type]
/usr/local/lib/python3.11/site-packages/openai/_client.py:110: in __init__
    raise OpenAIError(
E   openai.OpenAIError: The api_key client option must be set either by passing api_key to the client or by setting the OPENAI_API_KEY environment variable

tests/test_vision.py

☂️ Coverage Improvements

Coverage improvements by file:

  • tests/test_context.py

    New coverage: 40.04%
    Improvement: +40.04%

🎨 Final Touches

  • I ran the hooks included in the pre-commit config.

Settings | Logs | CodeBeaver

@MagMueller
Copy link
Collaborator

Awesome, and then do you use custom functions to call this? What happens if the model opens 5 tabs, then switches to tab 3, and then we close tabs with your function? Does it break or work as intended? You want to close all tabs except the current one, right? Maybe you could have a parameter to specify which tabs to close, or all except the current one.

@CLAassistant
Copy link

CLA assistant check
Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you sign our Contributor License Agreement before we can accept your contribution.
You have signed the CLA already but the status is still pending? Let us recheck it.

@pirate
Copy link
Member

pirate commented Mar 26, 2025

Thanks for your work on this @k-w-lee, I added a simpler solution here: #1162 to just expose tab closing to the agent as an action, so if you want it to close tabs put it in your task prompt.

@pirate pirate closed this Mar 26, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

Agent not closing intermediate tabs
4 participants