feat: Enable custom skills in JSON scenarios for Browser Use Agent #645
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This commit adds support for deterministic execution of JSON-based browser automation scenarios using custom skills in the Browser Use Agent. Key changes: - Dynamically register custom skills from src.custom_skills as controller actions - Fix Pydantic JSON schema errors by adding proper type annotations - Avoid leading underscores in function names to comply with Pydantic field naming rules - Add Wikipedia example scenario demonstrating cross-page data extraction - Create documentation explaining the integration approach and usage - Add integration tests to verify custom skills functionality - Update requirements.txt with lxml[html_clean] dependency This enables users to create deterministic browser automation scenarios using skills like goto, clickCss, waitFor, and waitForUrl directly in JSON format, rather than relying solely on natural language instructions.
|
|
|
feat: Enable custom skills in JSON scenarios for Browser Use Agent This commit adds support for deterministic execution of JSON-based browser automation scenarios using custom skills in the Browser Use Agent. Key changes:
This enables users to create deterministic browser automation scenarios using skills like goto, clickCss, waitFor, and waitForUrl directly in JSON format, rather than relying solely on natural language instructions. |
![cubic-dev-ai[bot]](https://avatars.githubusercontent.com/in/1082092?s=60&v=4){kind=small}
There was a problem hiding this comment.
cubic found 5 issues across 7 files. Review them in cubic.dev
React with 👍 or 👎 to teach cubic. Tag @cubic-dev-ai to give specific feedback.
- Pin lxml[html_clean] version to 4.9.3 in requirements.txt for deterministic builds - Fix timeout handling in wait_for_url and wait_for_selector (remove division by 1000) - Use correct state='detached' instead of 'hidden' for element removal detection - Add missing imports (BrowserContext, Dict) in documentation code snippet
|
fix: Address AI reviewer feedback on custom skills implementation
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This commit adds support for deterministic execution of JSON-based browser automation scenarios using custom skills in the Browser Use Agent.
Key changes:
This enables users to create deterministic browser automation scenarios using skills like goto, clickCss, waitFor, and waitForUrl directly in JSON format, rather than relying solely on natural language instructions.
Summary by cubic
Added support for using custom skills in JSON-based browser automation scenarios with the Browser Use Agent. Users can now define steps like goto, clickCss, waitFor, and waitForUrl directly in JSON for more reliable and deterministic automation.
New Features
Dependencies