docs: update browser-automation guide with agent-browser as default#61
Conversation
- Change default tool from dev-browser to agent-browser - Add visual debugging section (screenshots, errors, console) - Add session persistence guide (cookies, localStorage, auth state) - Add multi-session with shared auth patterns - Add debugging checklist for self-diagnosis - Emphasize checking yourself before asking user
Summary of ChangesHello @marcusquinn, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed! This pull request significantly updates the browser automation guide by establishing Highlights
Using Gemini Code AssistThe full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips. Invoking Gemini You can request assistance from Gemini at any point by creating a comment using either
Customization To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a Limitations & Feedback Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here. You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension. Footnotes
|
|
🔍 Code Quality Report�[0;35m[MONITOR]�[0m Code Review Monitoring Report �[0;34m[INFO]�[0m Latest Quality Status: �[0;34m[INFO]�[0m Recent monitoring activity: 📈 Current Quality Metrics
Generated on: Mon Jan 12 01:05:32 UTC 2026 Generated by AI DevOps Framework Code Review Monitoring |
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request does a great job of updating the browser automation guide to establish agent-browser as the new default tool. The addition of detailed sections on visual debugging, session persistence, and a debugging checklist significantly improves the documentation's utility for developers. The refactoring of the alternative tools sections also enhances clarity and consistency. My review includes a few suggestions to improve the code examples for consistency and clarity.
| ```bash | ||
| # Setup (one-time) | ||
| bash ~/.aidevops/agents/scripts/dev-browser-helper.sh setup | ||
| ~/.aidevops/agents/scripts/agent-browser-helper.sh setup |
There was a problem hiding this comment.
For consistency with other script executions in this document (e.g., on lines 307, 350, 370) and to ensure the script runs correctly even if it doesn't have execute permissions, it's best to explicitly call it with bash.
| ~/.aidevops/agents/scripts/agent-browser-helper.sh setup | |
| bash ~/.aidevops/agents/scripts/agent-browser-helper.sh setup |
| # 1. Start server (if not running) | ||
| bash ~/.aidevops/agents/scripts/dev-browser-helper.sh start | ||
| # 1. Setup (one-time) | ||
| ~/.aidevops/agents/scripts/agent-browser-helper.sh setup |
There was a problem hiding this comment.
Similar to other script calls in this file, it's recommended to explicitly use bash to execute this setup script for consistency and robustness.
| ~/.aidevops/agents/scripts/agent-browser-helper.sh setup | |
| bash ~/.aidevops/agents/scripts/agent-browser-helper.sh setup |
| ```bash | ||
| # Quick setup | ||
| bash .agent/scripts/stagehand-python-helper.sh setup | ||
| # Setup | ||
| bash ~/.aidevops/agents/scripts/stagehand-helper.sh setup | ||
|
|
||
| # MCP integration | ||
| bash .agent/scripts/setup-mcp-integrations.sh stagehand-python | ||
| # Natural language actions | ||
| await stagehand.act("click the login button") | ||
| await stagehand.act("fill in the email field with user@example.com") | ||
|
|
||
| # Run examples | ||
| source ~/.aidevops/stagehand-python/.venv/bin/activate | ||
| python examples/basic_example.py | ||
| python examples/ecommerce_automation.py "wireless headphones" | ||
| # Structured extraction | ||
| const data = await stagehand.extract("get product prices", z.array(z.number())) | ||
| ``` |
There was a problem hiding this comment.
The code block is marked as bash, but lines 353, 354, and 357 contain JavaScript syntax (await, const). This is confusing as these are not valid shell commands. To improve clarity, I suggest splitting this into two separate code blocks: a bash block for the setup command, and a javascript block to showcase the API usage examples.
|
Caution Review failedThe pull request is closed. WalkthroughDocumentation overhaul for browser automation tooling, promoting agent-browser as the default tool. Adds comprehensive sections on session persistence, authentication state management, cookies, and multi-session workflows while updating all setup commands and example code blocks accordingly. Changes
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~22 minutes Possibly related PRs
Poem
📜 Recent review detailsConfiguration used: Path: .coderabbit.yaml Review profile: CHILL Plan: Pro 📒 Files selected for processing (1)
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. Comment |
🤖 Augment PR SummarySummary: Updates the browser automation guide to make Changes:
Technical Notes: Examples use 🤖 Was this summary useful? React with 👍 or 👎 |
![augmentcode[bot]](https://avatars.githubusercontent.com/in/1027498?s=60&v=4){kind=small}
| agent-browser cookies set "session_id" "abc123" | ||
|
|
||
| # Set cookie with options | ||
| agent-browser cookies set "auth_token" "xyz789" --domain ".example.com" --path "/" --secure |
There was a problem hiding this comment.
This example uses agent-browser cookies set with --domain/--path/--secure flags, but elsewhere in our docs it’s shown as cookies set <name> <val> only; if these flags aren’t supported they’ll be ignored and make debugging auth harder (also applies to the env-var cookie example below).
🤖 Was this useful? React with 👍 or 👎
| ```bash | ||
| # Start new session with saved auth | ||
| agent-browser open https://app.example.com | ||
| agent-browser state load ~/.aidevops/.agent-workspace/auth/example-com.json |
There was a problem hiding this comment.
agent-browser state load is presented as applying to the current session after open + reload; if state loading actually needs to happen at session/browser creation, this workflow won’t restore auth as written (also applies to the multi-session examples).
🤖 Was this useful? React with 👍 or 👎
| #### **Python Version** 🐍 **NEW** | ||
| **AI-powered browser automation with natural language control** | ||
|
|
||
| ```bash |
There was a problem hiding this comment.
This fenced block is labeled bash but contains JS/TS (await stagehand.act(...)), so copying it into a shell will fail; consider using a javascript/ts fence to match the other Stagehand docs.
🤖 Was this useful? React with 👍 or 👎
1 participant
Summary
Key Changes
Agent-Browser as Default
agent-browser is now the recommended first choice because:
Visual Debugging (Don't Ask User)
New section emphasizing AI should check itself before asking user:
Session Persistence
Comprehensive guide for:
Debugging Checklist
Ordered checklist for self-diagnosis before asking user:
Summary by CodeRabbit
✏️ Tip: You can customize this high-level summary in your review settings.