## Summary
Fixed an issue where the `tab list` command couldn't recognize new pages that were opened externally (e.g., via `target="_blank"` links or popup windows). The problem occurred because context-level page tracking wasn't properly set up for all browser launch methods, causing new pages created outside of explicit `newTab()` calls to go untracked.
## Changes
- Added `setupContextTracking(context)` calls to `launch()`, `launchIncognito()`, and other context creation methods to ensure all contexts listen for new page events
- Added duplicate page checks (`!this.pages.includes(page)`) in `setupContextTracking()`, `newTab()`, and `launchIncognito()` to prevent the same page from being tracked multiple times
- Fixed `activePageIndex` calculation in `launch()` to properly set the active page index
- Enhanced comments to clarify that `setupContextTracking()` handles externally created pages (popups, new tabs from links)
## Implementation Details
The fix ensures that when a user clicks an element that opens a new tab/window, the browser context's 'page' event listener will automatically detect and track the new page. The duplicate prevention logic handles cases where both the context listener and manual page creation might try to add the same page.
Fixes#273
Add Kernel (https://kernel.sh) as a third-party cloud browser provider,
following the same pattern as Browserbase and Browser Use integrations.
Features:
- Launch browser with `-p kernel` flag or `AGENT_BROWSER_PROVIDER=kernel`
- Configurable via environment variables:
- KERNEL_API_KEY (required)
- KERNEL_HEADLESS (default: false)
- KERNEL_STEALTH (default: true)
- KERNEL_TIMEOUT_SECONDS (default: 300)
- KERNEL_PROFILE_NAME (optional, for persistent sessions)
- Profile find-or-create: automatically creates profile if it doesn't exist
- Profile persistence: cookies/logins saved back to profile on session close
- Uses raw fetch() calls for API communication (no SDK dependency)
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
* feat: add support for ignoring HTTPS certificate errors
* fix: update warning message for already running daemon to include ignore HTTPS errors option
* docs: add documentation for --ignore-https-errors option in README and SKILL.md
* feat: initialize ignore_https_errors flag in command context
* fix: change launch_cmd to mutable for cdp value handling
* Add --profile flag for persistent browser profiles
Adds support for persistent browser profiles that preserve cookies,
localStorage, and login sessions across browser restarts.
Changes:
- Add --profile <path> CLI flag (flags.rs)
- Add AGENT_BROWSER_PROFILE environment variable support
- Add profile field to LaunchCommand type (types.ts)
- Use launchPersistentContext when profile is specified (browser.ts)
- Update help text and README with documentation
Usage:
agent-browser --profile ~/.myapp-profile open myapp.com
This enables AI agents to maintain authenticated sessions across
browser restarts without re-authenticating each time.
* Expand tilde in profile path to home directory
* fix: add missing profile field to test Flags struct
---------
Co-authored-by: Chris Tate <chris@ctate.dev>
Previously, the --cdp flag only accepted a port number and connected via
http://localhost:{port}. This made it impossible to connect to remote
browser services like Kernel, Browserless, etc. that provide WebSocket URLs.
The --cdp flag now accepts either:
- A port number (e.g., 9222) for local connections
- A full WebSocket URL (e.g., wss://...) for remote browser services
Changes:
- Added cdpUrl field to LaunchCommand type
- Updated protocol validation to accept URL format with scheme validation
- Modified connectViaCDP to detect and handle both formats
- Handle numeric strings for JSON serialization edge cases
- Updated CLI to send cdpUrl or cdpPort based on input format
- Updated README with examples for remote connections
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
* feat: add Browser Use cloud browser
integration
* feat: enhance Browser Use integration with provider flag support
- Updated README to reflect new usage instructions for enabling Browser Use with the `-p` flag.
- Modified CLI to parse and handle the `-p` flag for specifying the provider.
- Implemented logic in the main application to launch with the specified cloud provider.
- Adjusted BrowserManager to connect to Browser Use based on the provider flag or environment variable.
- Updated types and protocol schemas to include provider information.
* feat: add validation for mutually exclusive CLI options
- Implemented checks to prevent the use of both --cdp and --provider flags simultaneously.
- Added validation to ensure --extension cannot be used with the --provider flag.
- Enhanced error handling to provide clear feedback in both JSON and console output formats.
* Add Browserbase support for remote browser over CDP
When BROWSERBASE_API_KEY and BROWSERBASE_PROJECT_ID env vars are set,
connect to a Browserbase session via CDP instead of launching a local browser.
* Update URLs to browserbase repo
* Add Browserbase support for remote browser over CDP
When BROWSERBASE_API_KEY and BROWSERBASE_PROJECT_ID env vars are set,
connect to a Browserbase session via CDP instead of launching a local browser.
* Update link to Browserbase Dashboard in README
* bump browserbase sdk to latest version
* remove sdk as a dep
* change name back to vercel labs
* added try catch blocks, functions to close session
* revert package names
* remove extra if statement
---------
Co-authored-by: Kylejeong2 <kylejeong21@gmail.com>
When connecting to a browser via CDP, particularly on Android, tabs with an empty URL can cause Playwright commands to hang indefinitely. This leads to a timeout in agent-browser.
This commit fixes the issue by filtering out any pages that have an empty `page.url()` during the CDP connection process. This prevents agent-browser from attempting to interact with these problematic tabs, resolving the timeout while preserving normal pages.
Added a unit test to verify that pages with empty URLs are correctly ignored. Also increased the timeout for a flaky screencast test to improve test suite stability.
Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com>
Co-authored-by: sheing-google <231310897+sheing-google@users.noreply.github.com>
* feat: add video recording with Playwright native video
Adds `record start/stop` commands using Playwright's built-in video
recording. No external dependencies required (no FFmpeg).
Usage:
agent-browser record start ./demo.webm https://example.com
agent-browser click @e1
agent-browser record stop
Recording creates a fresh browser context with video enabled. For smooth
demos, explore the page first to plan actions, then start recording.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* feat: auto-capture URL and transfer state for recording
When starting a recording without a URL:
- Automatically captures current page URL
- Preserves cookies and localStorage from current session
This enables a seamless workflow:
agent-browser open https://app.example.com
agent-browser snapshot -i # explore, plan
agent-browser record start ./demo.webm # picks up URL + auth state
agent-browser click @e3
agent-browser record stop
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: error on non-webm recording path instead of silent coercion
Previously, specifying a non-.webm path like ./demo.mp4 would silently
change it to ./demo.webm. Now it throws a clear error telling the user
that Playwright native recording only supports WebM format.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: clean up recording temp directory after stopRecording
Previously the temp directory was created but never deleted, relying on
OS cleanup. Now we explicitly remove it after saving the video, in both
success and error paths.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* feat: add record restart command
Adds `record restart` command that stops the current recording (if any)
and starts a new one. Also improves the error message when trying to
start recording while already recording.
Changes:
- Add restartRecording method to BrowserManager
- Add recording_restart action to protocol, types, and actions
- Add CLI parsing for `record restart <path> [url]`
- Update help text and skill documentation
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* test: add CLI tests for record restart command
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Co-authored-by: Chris Tate <chris@ctate.dev>
* feat: add --proxy flag for browser proxy support
Add CLI flag to configure HTTP/SOCKS proxy for Playwright browser context.
Supports URL format with optional credentials: http://user:pass@host:port
* fix: improve proxy parsing error handling
- Handle malformed credentials (@ without :) by ignoring incomplete creds
- Replace unwrap() with expect() for better error messages
- Addresses Vercel bot code review suggestions
* Restaura cambios locales: soporte AGENT_BROWSER_HOME y timeout aumentado
- Agrega soporte para variable de entorno AGENT_BROWSER_HOME en connection.rs
- Aumenta timeout por defecto de 10s a 60s para conexiones más lentas
* feat: add --proxy flag for browser proxy configuration
Implements proxy support based on PR #16 with reviewer feedback:
Features:
- Parse proxy URLs: http://[user:pass@]host:port
- Support for HTTP, HTTPS, and SOCKS5 protocols
- Handle username-only auth (preserves username with empty password)
- Apply proxy to both standard and persistent contexts
Changes:
- cli/src/flags.rs: Add proxy flag parsing
- cli/src/main.rs: Add parse_proxy() with comprehensive tests
- cli/src/output.rs: Add --proxy to help output
- cli/src/commands.rs: Fix test helper to include proxy field
- src/types.ts: Add proxy to LaunchCommand interface
- src/protocol.ts: Add proxy validation schema
- src/browser.ts: Apply proxy to context creation
Tests:
- 7 unit tests for parse_proxy() covering all edge cases
- All Rust tests passing (69 tests)
- All TypeScript tests passing (168 tests)
- TypeScript typecheck passing
Resolves feedback from PR #16:
- Fixed username-only proxy handling (issue #2681046975)
- Added comprehensive unit tests
- Added --proxy to help documentation
- Used expect() instead of unwrap() for better error messages
* refactor: simplify parse_proxy function
- Remove redundant comments
- Extract server variable to reduce duplication
- Inline trivial username/password variables
All 7 proxy tests still passing.
2026-01-16 11:56:35 -06:00
Chris TateandVercel <vercel[bot]@users.noreply.github.com>
* feat: add CDP connection support for external browsers
Add --cdp flag to connect to browsers via Chrome DevTools Protocol.
This enables control of Electron apps, Chrome instances, or any browser
exposing a CDP endpoint.
- Add cdpPort option to launch command schema
- Implement connectViaCDP() using chromium.connectOverCDP()
- Track browser connection type for proper reconnection handling
- Collect all pages from all contexts for CDP connections
Usage: agent-browser --cdp 9222 snapshot
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* feat: enhance CDP connection handling and improve page tracking
* main.rs update
Co-authored-by: vercel[bot] <35613825+vercel[bot]@users.noreply.github.com>
* fix: verify CDP connection is alive before early return in launch()
Prevents misleading errors when the remote browser crashes by checking
isConnected() before reusing an existing browser reference.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: reconnect when CDP port changes instead of reusing existing browser
Ensures --cdp flag is respected even when a browser session already exists.
Adds tests for launch() reconnection behavior.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* Update src/browser.ts
Co-authored-by: vercel[bot] <35613825+vercel[bot]@users.noreply.github.com>
* fix: improve CDP connection handling and validation
* feat: add CDP connection validation to ensure browser context accessibility
* Update src/browser.ts
Co-authored-by: vercel[bot] <35613825+vercel[bot]@users.noreply.github.com>
* feat: enhance CDP connection handling and add reconnect logic
* fix: improve CDP connection handling during browser closure
* fix: reset cdpPort to null during browser initialization
* feat: enhance browser launch logic to handle CDP connection switching
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Co-authored-by: vercel[bot] <35613825+vercel[bot]@users.noreply.github.com>
Chris Tate