Add `batch` command that reads a JSON array of commands from stdin
and executes them sequentially against the daemon. This avoids
per-command process startup overhead when AI agents run multi-step
browser workflows.
Supports --bail to stop on first error (default: continue all)
and --json for structured output as an array of results.
Co-authored-by: Matt Van Horn <455140+mvanhorn@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* fix: Windows auto-connect profiling (#835)
Fix three interrelated bugs causing `--auto-connect` to fail on Windows,
plus a UX issue where auto-connect hijacked existing tabs:
1. Stale DevToolsActivePort — add TCP port liveness check before returning
M144+ WebSocket URL; remove stale files when port is dead.
2. Missing Windows error codes — add os error 10061 (WSAECONNREFUSED) and
10054 (WSAECONNRESET) to is_transient_error() so daemon startup races
are retried on Windows.
3. --auto-connect not propagated to daemon — add auto_connect to
DaemonOptions, set AGENT_BROWSER_AUTO_CONNECT env var via
apply_daemon_env(), and guard the headed launch block so it doesn't
send a second launch that overrides the auto-connect.
4. Auto-connect opens a fresh tab — after connecting to an existing
Chrome, create a new about:blank tab and bring it to front so
navigations don't hijack the user's existing tabs.
Made-with: Cursor
* fix: address review feedback — cargo fmt, shared helper, Windows tests
- Run cargo fmt on is_port_reachable() formatting
- Extract duplicated auto-connect-with-fresh-tab logic into
connect_auto_with_fresh_tab() helper used by both handle_launch()
and auto_launch()
- Add unit tests for Windows WSAECONNREFUSED (os error 10061) and
WSAECONNRESET (os error 10054) in is_transient_error()
---------
Co-authored-by: ctate <366502+ctate@users.noreply.github.com>
* fix: propagate --cdp flag to daemon via AGENT_BROWSER_CDP env var
The --cdp flag was not being passed to the daemon process as an environment
variable, causing auto-reconnection to fail. The daemon's auto_launch()
function checks for AGENT_BROWSER_CDP, but this was never set when spawning
the daemon.
This commit adds:
- cdp field to DaemonOptions struct
- AGENT_BROWSER_CDP env var setting in apply_daemon_env()
- flags.cdp propagation in main.rs
This ensures reliable CDP connection recovery when using --cdp with external
browsers like Lightpanda, Electron apps, or remote Chrome instances.
Fixes reconnection issues with --cdp flag after connection drops.
* chore: remove changeset
---------
Co-authored-by: Jake Shore <jakeshore@Jakes-Mac-mini.local>
Co-authored-by: ctate <366502+ctate@users.noreply.github.com>
* feat: add --idle-timeout CLI flag for daemon auto-shutdown
Add user-friendly --idle-timeout flag that converts time strings
to milliseconds. Supports formats like '10s', '3m', '1h', or raw ms.
This addresses a common need for ephemeral/CI environments where
daemon processes can be orphaned if not explicitly closed, leading
to resource consumption from zombie chrome-headless-shell processes.
Co-authored-by: Hermes (via claude-sonnet-4-20250520) <agent@hermes.ai>
* fix: address idle-timeout review feedback
* fix: normalize idle-timeout parsing
---------
Co-authored-by: Merlin <merlin@rbeckner.com>
Co-authored-by: Hermes (via claude-sonnet-4-20250520) <agent@hermes.ai>
The comment said "Ignore SIGPIPE" but the code actually resets SIGPIPE
to SIG_DFL (default behavior = process termination), not SIG_IGN (ignore).
Updated the comment to accurately describe what the code does and why.
Co-authored-by: hyunjinee <leehj0110@kakao.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
When user explicitly sets --headed false, the CLI was ignoring this
flag because the launch condition only checked if flags.headed was
true. This meant that --headed false would not trigger a launch
command, and subsequent commands would auto-launch with default
headless=true.
The fix adds a cli_headed flag to track when the user explicitly
sets --headed (regardless of value), and includes this in the
launch condition check.
Fixes#743
Fix issue where Chrome extensions specified in the `extensions` field of `config.json` were not being loaded when launching the browser.
## Problem
Extensions configured via the `extensions` field in `config.json` were not being passed to the Chrome browser launch command, causing them to be ignored.
## Changes
- Added `!flags.extensions.is_empty()` to the launch trigger condition to ensure browser launch is triggered when extensions are configured
- Added extensions to the launch command JSON payload so they are properly passed to the browser
Fixes#726
When the daemon process crashes during startup (e.g., missing
Playwright), stderr was discarded via Stdio::null(), so users only
saw "Daemon failed to start (port: ...)" with no diagnostic info.
Now captures daemon stderr via Stdio::piped() and detects early process
exit with try_wait() during the startup polling loop. If the daemon
crashes, the actual error from stderr is shown to the user.
Also forwards --debug flag to the daemon process as AGENT_BROWSER_DEBUG
so debug logging works end-to-end.
Closes#56
* fix: suppress spurious --native warning when set via env var
When AGENT_BROWSER_NATIVE=1 is set via environment variable, every
command after the first would warn:
⚠ --native ignored: daemon already running.
This is a false positive — the daemon was already spawned in native
mode and inherited the env var. The warning should only fire when
--native is explicitly passed on the CLI to an already-running daemon.
Add cli_native flag (consistent with existing cli_* pattern) to
distinguish CLI origin from env var origin.
* fix: add flag to test cfg
* fix: cli_native should track flag presence, not value
--native false on CLI should still warn when daemon is already
running, since the user is explicitly trying to change the mode.
* fix(windows): resolve daemon startup failures and Git Bash compatibility
Three root causes behind 27 open Windows issues:
1. Path::canonicalize() returns \\?\ prefixed paths on Windows that
Node.js cannot parse, preventing daemon startup. Strip the prefix
before passing to Node. (fixes#522, #390, #56, #25, #37, #89)
2. Git Bash/MSYS2 translates Unix-style paths and resolves node to
a shell wrapper script. Use node.exe explicitly and set
MSYS_NO_PATHCONV/MSYS2_ARG_CONV_EXCL to prevent argument mangling.
(fixes#148, #108, #171)
3. postinstall fixWindowsShims() hardcoded x64 arch and did not verify
the native binary exists before rewriting shims. Now detects arch
dynamically and validates the binary path. (fixes#262)
Also:
- Error messages now show TCP port on Windows instead of Unix socket path
- Windows CI expanded to test full daemon lifecycle (open, snapshot, close)
* fix(windows): strip \\?\ prefix in auth-cli path (fixes#579)
Same canonicalize() issue as the daemon spawn path, but in
run_auth_cli() which passes the script path to Node.js.
Per POSIX, kill(pid, 0) returns EPERM when the process exists but the
caller lacks permission to signal it, and ESRCH when it does not exist.
The daemon liveness checks in both the Rust CLI and TypeScript daemon
treated any kill failure as "not running", which is incorrect when
running inside a macOS sandbox that restricts signal delivery to
(target self). This caused the CLI to delete the real daemon's socket
and PID files, then spawn a duplicate daemon.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* add security hardening features
- Add authentication vault (`auth save/login/list/show/delete`) so credentials are stored locally and never exposed to the LLM (fixes Snyk W007)
- Add `--content-boundaries` flag to wrap page-sourced output in structural markers, helping LLMs distinguish tool output from untrusted page content (fixes Snyk W011)
- Add `--allowed-domains` flag to restrict browser navigation to trusted domains
- Add `--action-policy` for static allow/deny gating of action categories, with opt-in `--confirm-actions`/`--confirm-interactive` for orchestrator or human-in-the-loop confirmation
- Add `--max-output` flag to truncate large page outputs, preventing context flooding
- New docs page at /security, updated README, SKILL.md, CLI help text, and templates
* fixes
* fixes
* fixes
* fixes
* fixes
* fixes
* fixes
* docs
* feat: add --download-path option
Adds a `--download-path` flag (and `AGENT_BROWSER_DOWNLOAD_PATH` env / `downloadPath` config key) to set a default download directory for browser downloads.
Without this, Playwright stores downloads in a temp directory that is deleted when the browser closes. The new option passes through to Playwright's `downloadsPath` on `launch()` and `launchPersistentContext()`.
Fixes#507
* improvements
* fixes
* fixes
Fixes#519. Playwright defaults `colorScheme` to `light` on all new contexts, overriding the browser/OS dark mode setting. This is especially disruptive in CDP mode, where every reconnection resets the scheme. The `set media dark` command also didn't persist its choice to new tabs or pages.
- Add `--color-scheme <dark|light|no-preference>` flag, config key (`colorScheme`), and env var (`AGENT_BROWSER_COLOR_SCHEME`)
- Store the preference in `BrowserManager` and automatically apply it to all new contexts (via Playwright's context option) and all new pages (via `page.emulateMedia` in `setupPageTracking`)
- `set media dark/light` now also persists its choice for subsequent pages and tabs
## Summary
- Return a `ParseError` when `--headers` receives invalid JSON instead of silently dropping the headers and proceeding
- Reject `frame` commands that provide no `selector`, `name`, or `url` (previously returned `{ switched: true }` without doing anything)
- Add missing mutual exclusion check for `--cdp` + `--extension` (extensions require a local browser, not a CDP connection)
## Summary
- Fix `allowFileAccess` being silently stripped from launch commands by adding it to the Zod schema in `protocol.ts` (the `--allow-file-access` CLI flag was not reaching the browser)
- Fix `trace stop` requiring a path argument despite help text documenting it as optional -- now works with or without a path
- Fix `addscript`/`addstyle` silently succeeding when neither `content` nor `url` is provided -- now returns a validation error
- Replace hardcoded ANSI escape code with `color::error_indicator()` in `main.rs` to respect `NO_COLOR`
- Fix double-parse pattern and add descriptive expect messages in `commands.rs`
- Fix incomplete string escaping in `snapshot.ts` `buildSelector` (use `JSON.stringify` instead of manual quote escaping)
- Simplify redundant ternary in `snapshot.ts` cursor-interactive role assignment
- Sync docs changelog with CHANGELOG.md (v0.8.1 through v0.10.0)
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.
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 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>
* 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.
Add a centralized color module (cli/src/color.rs) that respects the
NO_COLOR environment variable per https://no-color.org/
Changes:
- Add color.rs module with helper functions for colored output
- Refactor all hardcoded ANSI escape codes to use the color module
- Add tests for color formatting functions
- Update AGENTS.md with color module usage guidelines
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
* 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.
* 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>
