Skip to content

refactor: browser-primitive-actions #2514

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

Open
wants to merge 11 commits into
base: master
Choose a base branch
from

Conversation

nitpicker55555
Copy link
Collaborator

@nitpicker55555 nitpicker55555 commented May 29, 2025

Expose primitive browser actions (e.g., visit_page, scroll_page, click_element) as independent, callable tools And add a multi-tool scenario test

Fix #1969

Checklist
Go over all the following points, and put an x in all the boxes that apply.

  • I have read the CONTRIBUTION guide (required)
  • I have linked this PR to an issue using the Development section on the right sidebar or by adding Fixes #issue-number in the PR description (required)
  • I have checked if any dependencies need to be added or updated in pyproject.toml and uv lock
  • I have updated the tests accordingly (required for a bug fix or a new feature)
  • I have updated the documentation if needed:
  • I have added examples if this is a new feature

If you are unsure about any of these, don't hesitate to ask. We are here to help!

@nitpicker55555 nitpicker55555 changed the title update chore:browser-primitive-actions chore:browser-primitive-actions May 29, 2025
@Wendong-Fan Wendong-Fan changed the title chore:browser-primitive-actions refactor: browser-primitive-actions May 30, 2025
Copy link
Member

@Wendong-Fan Wendong-Fan left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

thanks @nitpicker55555 , left some comments below, we could also support browser console execution to add more flexibility, could you take 5 browser related tasks from GAIA to have a test comparing the performance between refactored browser toolkit with the original one, and write a short summary under this PR?

Comment on lines 1353 to 1355
def get_tools(self) -> List[FunctionTool]:
return [FunctionTool(self.browse_url)]
return [
FunctionTool(self.browse_url),
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

move this def get_tools to the bottom

Comment on lines 1353 to 1355
def get_tools(self) -> List[FunctionTool]:
return [FunctionTool(self.browse_url)]
return [
FunctionTool(self.browse_url),
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

should we still keep self.browse_url?


Args:
format (Literal["markdown", "html"]): Content format.
Defaults to "markdown".
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

docstring format for default value, same for other parts

Suggested change
Defaults to "markdown".
(default: :obj: `"markdown" `)

return "Browser session closed."
return "Browser session was not initialized or already closed."

def visit_page(self, url: str) -> str:
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

the current code could be simpified, now there are many layers, take this function as example:
visit_page-> visit_page -> wait_for_load, could we refactor functions like this to make it more straightforward?

await self._ensure_browser_initialized()
try:
if mark_interactive_elements:
_, file_path = await self.browser.async_get_som_screenshot(
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

seems the naming of async_get_som_screenshot is confusing, it's actually get_screenshot_with_marks instead of get multi-screenshot?

FunctionTool(self.get_page_content),
FunctionTool(self.download_file_by_element_id),
FunctionTool(self.capture_screenshot),
FunctionTool(self.ask_question_about_video),
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

is this necessary to add this in browser toolkit? I feel it would be better remove this function, make it more clear for the functionality of different toolkits

await self._ensure_browser_initialized()
return await self.browser.async_download_file_id(element_id)

async def capture_screenshot(
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

seems this function only get screenshot and didn't use VLM do further analysis?

@Wendong-Fan Wendong-Fan added Waiting for Update PR has been reviewed, need to be updated based on review comment and removed Review Required PR need to be reviewed labels Jun 5, 2025
Copy link
Contributor

coderabbitai bot commented Jun 5, 2025

Important

Review skipped

Auto reviews are disabled on this repository.

Please check the settings in the CodeRabbit UI or the .coderabbit.yaml file in this repository. To trigger a single review, invoke the @coderabbitai review command.

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.


Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share
🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

  • Review comments: Directly reply to a review comment made by CodeRabbit. Example:
    • I pushed a fix in commit <commit_id>, please review it.
    • Explain this complex logic.
    • Open a follow-up GitHub issue for this discussion.
  • Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
    • @coderabbitai explain this code block.
    • @coderabbitai modularize this function.
  • PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
    • @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
    • @coderabbitai read src/utils.ts and explain its main purpose.
    • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
    • @coderabbitai help me debug CodeRabbit configuration file.

Support

Need help? Create a ticket on our support page for assistance with any issues or questions.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (Invoked using PR comments)

  • @coderabbitai pause to pause the reviews on a PR.
  • @coderabbitai resume to resume the paused reviews.
  • @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
  • @coderabbitai full review to do a full review from scratch and review all the files again.
  • @coderabbitai summary to regenerate the summary of the PR.
  • @coderabbitai generate docstrings to generate docstrings for this PR.
  • @coderabbitai generate sequence diagram to generate a sequence diagram of the changes in this PR.
  • @coderabbitai resolve resolve all the CodeRabbit review comments.
  • @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
  • @coderabbitai help to get help.

Other keywords and placeholders

  • Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
  • Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
  • Add @coderabbitai anywhere in the PR title to generate the title automatically.

CodeRabbit Configuration File (.coderabbit.yaml)

  • You can programmatically configure CodeRabbit by adding a .coderabbit.yaml file to the root of your repository.
  • Please see the configuration documentation for more information.
  • If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json

Documentation and Community

  • Visit our Documentation for detailed information on how to use CodeRabbit.
  • Join our Discord Community to get help, request features, and share feedback.
  • Follow us on X/Twitter for updates and announcements.

@Wendong-Fan Wendong-Fan mentioned this pull request Jun 18, 2025
6 tasks
@nitpicker55555
Copy link
Collaborator Author

Sorry for the late update
I found that visual recognition is coupled within the web_agent of browser_toolkit, where it uses the observe method to construct a BaseMessage to read images:

message = BaseMessage.make_user_message(
    role_name='user', content=observe_prompt, image_list=[img]
)

However, ChatAgent does not support tool responses that return images. Even if a BaseMessage is constructed, it will be treated as a string, so visual recognition cannot be decoupled and used as an independent action like other tools.

I can achieve decoupling of web page recognition by returning DOM information in text form, in this PR: #2674.

@nitpicker55555 nitpicker55555 removed the Waiting for Update PR has been reviewed, need to be updated based on review comment label Jun 19, 2025
@nitpicker55555 nitpicker55555 added the Review Required PR need to be reviewed label Jun 19, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Review Required PR need to be reviewed
Projects
Status: No status
Development

Successfully merging this pull request may close these issues.

[Feature Request] Expose Browser Toolkit Primitive Actions as Independent Tools
3 participants