Rebased and fixed implementation of PR #184 features on current main:
Session persistence:
- --session-name flag and AGENT_BROWSER_SESSION_NAME env var auto-save/restore
cookies and localStorage across browser restarts
- State files stored in ~/.agent-browser/sessions/ with owner-only permissions
- AES-256-GCM encryption via AGENT_BROWSER_ENCRYPTION_KEY env var
- Auto-expiration of old state files (AGENT_BROWSER_STATE_EXPIRE_DAYS, default 30)
State management commands:
- state list: list saved state files with metadata
- state show <file>: display state summary (cookies, origins, domains)
- state rename <old> <new>: rename state files
- state clear [name] [--all]: clear saved states
- state clean --older-than <days>: delete expired states
New --new-tab flag for click command:
- Opens link href in a new tab instead of navigating the current tab
Security hardening:
- Session name validation prevents path traversal (CLI + daemon)
- safeHeaderMerge prevents prototype pollution in header merging
- WebSocket stream server binds to 127.0.0.1 only
- State files written with 0o600 permissions
Fixes applied over the original PR:
- Use color.rs module instead of hardcoded ANSI escape codes
- Align CLI output field names with daemon response format
- Add CLI-level --session-name validation (not just daemon-side)
- Avoid adding "DOM" to tsconfig.json lib (use proper typing in evaluate)
- Keep version at 0.9.3 (matches current main)
- Centralize session name validation in daemon.ts helper
- Update all documentation (README, SKILL.md, docs site, --help output)
Co-authored-by: Chris Tate <chris@ctate.dev>
* cargo fmt
* fix: remove redundant `use libc` import (clippy::single_component_path_imports)
* fix: use `.first()` instead of `.get(0)` (clippy::get_first)
* fix: use `.copied()` instead of `.map(|s| *s)` (clippy::map_clone)
* fix: allow too_many_arguments on ensure_daemon (clippy::too_many_arguments)
* fix: use `then_some` instead of `then` with closure (clippy::unnecessary_lazy_evaluations)
* fix: use pattern match instead of redundant guard (clippy::redundant_guards)
* fix: use pattern match instead of redundant guard in commands.rs (clippy::redundant_guards)
* fix: use `contains()` instead of `iter().any()` for simple equality (clippy::manual_contains)
* Add changeset
* feat: add --allow-file-access flag for file:// URL support
Adds the ability to open and interact with local files using file:// URLs.
This enables use cases like viewing local PDFs, testing local HTML files,
and allowing JavaScript to access other local files via XHR.
The flag adds Chromium's --allow-file-access-from-files and --allow-file-access
launch arguments. Only supported in Chromium browsers.
Fixes#345
* fix: add cli_allow_file_access tracking to prevent spurious warning
When --allow-file-access is set via AGENT_BROWSER_ALLOW_FILE_ACCESS env var
(not CLI), don't warn about the flag being ignored when daemon is already running.
* fix: only warn about ignored flags when explicitly passed via CLI
The warning about launch-time options being ignored (when daemon is
already running) was incorrectly shown when options were set via
environment variables like AGENT_BROWSER_EXECUTABLE_PATH, even when
no CLI flag was passed.
Now the warning only appears when flags are explicitly passed on the
command line, not when values come solely from environment variables.
Fixes#372
* feat: add cursor-interactive element detection in snapshots
Add -C/--cursor flag to snapshot command that detects clickable elements
that don't have proper ARIA roles but are interactive based on:
- cursor: pointer CSS style
- onclick attribute/handler
- tabindex attribute
This helps with modern web apps that use custom divs/spans as buttons.
Fixes#366
* fix: add cursor option to getSnapshot type signature
The warning about launch-time options being ignored (when daemon is
already running) was incorrectly shown when options were set via
environment variables like AGENT_BROWSER_EXECUTABLE_PATH, even when
no CLI flag was passed.
Now the warning only appears when flags are explicitly passed on the
command line, not when values come solely from environment variables.
Fixes#372
* Add base64 input for eval command
Adds -b/--base64 flag to decode script from base64, avoiding shell escaping issues for AI agents.
* Document base64 eval in SKILL.md
* fix: add retry logic for transient socket errors
Fixes race condition when rapidly closing and opening browser sessions.
The daemon has a 100ms shutdown delay, which caused the CLI to detect
stale daemons as "running" and fail with EAGAIN errors.
Changes:
- Add retry logic (5 attempts, exponential backoff) for transient errors
including EAGAIN, EOF, connection reset, and connection refused
- Add 150ms verification delay in ensure_daemon to detect shutting-down daemons
- Add cleanup_stale_files to remove leftover socket/PID files before starting
a new daemon
Tested with 20 rapid close/open cycles and 100+ parallel commands.
* test: add unit tests for transient error detection
Extracts is_transient_error() function and adds 14 unit tests covering:
- EAGAIN errors (macOS os error 35, Linux os error 11)
- WouldBlock and Resource temporarily unavailable
- EOF and empty JSON response errors
- Connection reset (macOS os error 54, Linux os error 104)
- Broken pipe errors
- Socket not found (os error 2)
- Connection refused (macOS os error 61, Linux os error 111)
- Non-transient errors (verifies they are NOT retried)
Update sync-version.js to also run `cargo update -p agent-browser` after
updating Cargo.toml, keeping Cargo.lock in sync. Also update pre-commit
hook to stage Cargo.lock along with Cargo.toml.
This commit also brings Cargo.lock up to date (was stuck at 0.7.6).
* fix(cli): save screenshots to tmp dir when no path provided
Instead of outputting base64 to stdout (which is not useful for most CLI use cases),
screenshots without a path now save to ~/.agent-browser/tmp/screenshots/ with a
generated filename and return the path.
This makes the behavior more ergonomic for AI agents and CLI users alike.
* cleanup
* cleanup
* just revert the cargo.lock version for now
* refactor: extract getAppDir() from getSocketDir()
* docs: improve screenshot help text consistency
* Add CLI flags for cookie URL, domain, path, httpOnly, secure, and expires
Extends the `cookies set` command to support setting cookies with additional parameters before loading a page, solving authentication workflows where cookies need to be set for different domains.
**Key changes:**
- Added CLI flags: `--url`, `--domain`, `--path`, `--httpOnly`, `--secure`, `--sameSite`, `--expires`
- Added comprehensive test coverage for all new flags and combinations
- Updated help documentation with usage examples
- No daemon changes needed - it already supported these parameters
**Example usage:**
```bash
agent-browser cookies set session_id "abc123" --url https://app.example.com --httpOnly --secure
```
This allows setting cookies for a URL before opening the page, eliminating the need for workarounds in cross-domain authentication scenarios.
Fixes#261
* Update lock
* Fix compilation error
* 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
* fix: download artifacts to temp directory to avoid naming conflict
The download-artifact action creates directories named after each artifact.
When downloading to bin/, this caused conflicts because the artifact directory
names matched the binary names (e.g., bin/agent-browser-darwin-arm64/agent-browser-darwin-arm64).
Fix by downloading to artifacts/ first, then using find to move the binaries to bin/.
* fix docs
* fix(screenshot): support refs and improve error messages
* fix(cli): support selector argument in screenshot command
* Fix CSS class selectors being treated as file paths
* fix(test): update screenshot test assertions
---------
Co-authored-by: Chris Tate <chris@ctate.dev>
* feat: add download and waitfordownload CLI commands
Add CLI support for the existing download functionality in the daemon:
- `download <selector> <path>`: Click an element to trigger download
and save to specified path
- `wait --download [path] [--timeout ms]`: Wait for any download to
complete, optionally save to path with configurable timeout
Includes comprehensive unit tests and help documentation.
* fix: download command ref support and output message
- Fix handleDownload to use browser.getLocator() for ref selector support
- Fix CLI output to show "Downloaded to" instead of "Screenshot saved"
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Chris Tate <chris@ctate.dev>
* 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>
* fix: use ~/.agent-browser for socket files instead of TMPDIR
This fixes issue #163 where different TMPDIR values (common with
tmux/screen/VSCode/IntelliJ) caused the CLI and daemon to use
different socket paths.
Socket directory priority:
1. AGENT_BROWSER_SOCKET_DIR (explicit override)
2. $XDG_RUNTIME_DIR/agent-browser (Linux standard)
3. ~/.agent-browser (fallback, like Docker Desktop)
Both CLI (Rust) and daemon (Node.js) now use the same logic.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: session list now looks in correct socket directory
- Make get_socket_dir() public in connection.rs
- Update session list to use get_socket_dir() instead of temp_dir()
- Update pid file pattern from agent-browser-{session}.pid to {session}.pid
- Add tmpdir fallback to daemon.ts when homedir is unavailable
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* test: add unit tests for socket directory resolution
Add comprehensive tests for get_socket_dir/getSocketDir to verify:
- AGENT_BROWSER_SOCKET_DIR takes priority
- Empty strings are ignored (fixes Rust/TypeScript consistency)
- XDG_RUNTIME_DIR fallback works correctly
- Home directory fallback when env vars unset
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
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.
Adds a `connect <port>` command that establishes a CDP connection
to a running browser. The daemon remembers the connection, so
subsequent commands work without needing --cdp on every call.
Example:
agent-browser connect 9222
agent-browser snapshot # works without --cdp
agent-browser tab
agent-browser close
* fix: support libasound2t64 on newer Ubuntu versions
Updates the install logic to check if `libasound2t64` is available using
`apt-cache` before falling back to `libasound2`. This fixes installation
on Ubuntu 24.04 and other systems affected by the 64-bit time_t transition.
* Update cli/src/install.rs
Co-authored-by: vercel[bot] <35613825+vercel[bot]@users.noreply.github.com>
---------
Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com>
Co-authored-by: vercel[bot] <35613825+vercel[bot]@users.noreply.github.com>
