Previously only suggested --full, but --remote-only is a lighter-weight
option when users only need cloud browser support.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Rename tunnel_manager.py to tunnel.py
- Remove dead code: commands/tunnel.py (session-scoped implementation never reached)
- Remove TunnelInfo dataclass and tunnels field from sessions.py
- Remove tunnel routing from server.py (unreachable code path)
- Update imports in main.py, doctor.py, setup.py, and tests
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Update all references from browser-use.com/install.sh to
browser-use.com/cli/install.sh across documentation and code.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Reverts changes to browser_use/llm/browser_use/chat.py to keep
CLI changes isolated. Browser-use models are now hardcoded in
agent.py instead of importing from chat.py.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Forward all cloud-only flags in _handle_remote_run_with_wait
Previously only forwarded 6 params; now includes session_id, vision,
metadata, secrets, allowed_domains, skill_ids, structured_output,
judge, judge_ground_truth, plus session creation for profile/proxy
- Use asyncio.to_thread for blocking SDK call in poll_until_complete
Prevents client.tasks.get_task from blocking the event loop while
polling for task completion
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Use asyncio.to_thread() for poll_until_complete to prevent time.sleep()
from blocking the async event loop when --wait is used.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Replace custom HTTP client with browser-use-sdk for tasks and sessions,
completing the SDK migration started in 8a992229.
## SDK Migration
- Add `sdk.py` with singleton client factory (`get_sdk_client()`)
- Rewrite `cloud_task.py` to use SDK (-300 lines)
- All functions return typed SDK models (TaskView, SessionView, etc.)
- Add `_filter_none()` to omit None values (SDK sends null, API rejects)
## No Client-Side Defaults
- Remove hardcoded defaults from CLI (max_steps, proxy_country, etc.)
- Let API use its own defaults (documented at docs.cloud.browser-use.com)
- Only pass values user explicitly sets
## New CLI Features
- `session create` - create session without task
- `session share <id>` - create/delete public share URLs
- `task list --session <id>` - filter tasks by session
- New task flags: --metadata, --secret, --allowed-domain, --skill-id,
--structured-output, --judge, --judge-ground-truth, --start-url
## Async by Default
- Change `--no-wait` to `--wait` (flip default behavior)
- Tasks return immediately with task_id by default
- Use `--wait` to block until completion
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Replace raw urllib HTTP calls with the official browser-use-sdk client
for all cloud profile API operations. This provides:
- Type-safe responses (ProfileView, ProfileListResponse)
- Cleaner error handling via SDK exceptions
- Consistent SDK usage pattern (matches skills/service.py)
- Removes 40 lines of manual HTTP/auth handling from main.py
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Use asyncio.to_thread() with thread pool to stop multiple cloud
sessions concurrently instead of sequentially. Results in ~3.5x
speedup (3.8s vs 13.3s for 5 sessions).
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The previous implementation tried to handle various event loop edge
cases but had a bug: if run_until_complete started a coroutine and
then raised RuntimeError, it would try to re-run the same consumed
coroutine with asyncio.run(), causing "cannot reuse already awaited
coroutine" errors.
For CLI code, asyncio.run() is the correct approach as it creates
a fresh event loop. This simplification fixes the confusing error
message when users pass truncated task IDs.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- setup.py: Add noqa comment for intentional import check (F401)
- tunnel_manager.py: Add noqa for blocking open in async context (ASYNC230)
- profile.py, setup.py: Auto-format with ruff
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- agent.py: Move API key check inside remote mode block only, allowing
local mode to work with OPENAI/ANTHROPIC keys without BROWSER_USE_API_KEY
- tunnel_manager.py: Close log file handle on success path to prevent
file descriptor leak
- profile.py: Use stderr for progress messages when --json flag is set;
add cleanup_cloud_profile() to delete orphaned cloud profiles on sync failure
- install.sh: Add guard for --api-key requiring a value; warn on unknown
arguments instead of silently ignoring; fix read -p with < /dev/tty
for piped install (curl | bash)
- test_setup_command.py: Remove all unittest.mock usage per repo guidelines,
replace with real function calls that verify structure and logic
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Default task status shows only latest step (token efficient for agents)
- Add --compact/-c flag to show all steps with reasoning
- Add --verbose/-v flag to show all steps with URLs + actions
- Add --last/-n, --reverse/-r, --step/-s flags for navigating long tasks
- Display duration for tasks (e.g., "18s", "5m 13s") and sessions
- Format proxy cost to 2 decimal places in session output
- Update SKILL.md docs with recommended monitoring workflow
- Remove pycloudflared dependency from pyproject.toml
- Simplify tunnel_manager.py to just use shutil.which('cloudflared')
- Add install_cloudflared() to install.sh that downloads binary from
official Cloudflare GitHub releases based on platform/arch
- Update SKILL.md with manual cloudflared install instructions
- Update setup.py messages for missing cloudflared
install.sh supported platforms:
- Linux (x86_64, arm64) - full support, downloads binary to ~/.local/bin
- macOS (Intel, Apple Silicon) - full support, uses brew or direct download
- Windows WSL - works (treated as Linux)
- Native Windows - not supported (bash script), use manual install
- New `tunnel` command: expose localhost ports via Cloudflare quick tunnels
(`bu tunnel 3000` → trycloudflare.com URL, idempotent, auto-cleanup on session close)
- New `skills/remote-browser/SKILL.md`: guides sandboxed agents through
cloud browser + tunnel workflow
- TunnelInfo dataclass on SessionInfo for tunnel lifecycle management
- Tunnel dispatch in both SessionServer and CLI arg parser
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Remove invalid cdp_url parameter from create_browser_session calls
- Replace deleted GetCookiesEvent with direct _cdp_get_cookies() call
- Add type assertion for cookies_file after error check
- Use unique variable names for CDP results to avoid type conflicts
- Add type ignores for CDP typed return values used as dicts
Move all CLI-specific CDP logic directly into browser.py command
handlers instead of using events and watchdogs. This keeps the CLI
self-contained and avoids adding CLI-specific code to the core library.
- Remove 14 CLI-specific events from events.py
- Remove 3 watchdog files (cookies, interactions, wait)
- Remove watchdog registrations from session.py
- Implement direct CDP calls in browser.py for cookies, wait, hover,
dblclick, rightclick, and get commands
- Add cloud profile commands: list, create, get, update, delete
- Add profile sync command to sync local Chrome cookies to cloud
- Add profile cookies command to list cookies by domain
- Add cookies export/import commands for bulk transfer
- Optimize cookie import using Network.setCookies (bulk API)
- Real browser now runs headless by default (use --headed for visible)
- Support --domain flag for syncing specific domain cookies only
- Update SKILL.md with cloud profile workflow documentation
Adds information retrieval commands to the browser-use CLI:
- get title: page title
- get html: full page or element HTML via selector
- get text: text content of element by index
- get value: input/textarea value by index
- get attributes: all attributes of element by index
- get bbox: bounding box (x, y, width, height) of element
Adds mouse interaction commands to the browser-use CLI:
- hover: move mouse over element (triggers CSS :hover effects)
- dblclick: double-click element
- rightclick: right-click element (context menu)
Adds wait conditions to the browser-use CLI with two subcommands:
- wait selector: wait for CSS selector with state options (visible, hidden, attached, detached)
- wait text: wait for text to appear on the page
Both support custom timeout in milliseconds.
Adds cookie management to the browser-use CLI with three subcommands:
- cookies get: retrieve all cookies or filter by URL
- cookies set: create cookies with domain, path, secure, httpOnly options
- cookies clear: remove all cookies or filter by URL
The CLI 'run' command now supports BROWSER_USE_API_KEY as an LLM option,
using ChatBrowserUse which is optimized for browser automation tasks.
This aligns the CLI behavior with the documented supported models at
https://docs.browser-use.com/supported-models which shows ChatBrowserUse
as a valid LLM option using BROWSER_USE_API_KEY.
Changes:
- Add ChatBrowserUse as first LLM option in get_llm() when BROWSER_USE_API_KEY is set
- Update error message to mention BROWSER_USE_API_KEY
- State command outputs same format that browser-use agents see
- Added aliases: bu, browser (all work the same)
- Headed mode now correctly shows browser window
Laith Weinberger