feat: switch managed browser provider from Browserbase to Browser Use (#5750)

* feat: switch managed browser provider from Browserbase to Browser Use

The Nous subscription tool gateway now routes browser automation through
Browser Use instead of Browserbase. This commit:

- Adds managed Nous gateway support to BrowserUseProvider (idempotency
  keys, X-BB-API-Key auth header, external_call_id persistence)
- Removes managed gateway support from BrowserbaseProvider (now
  direct-only via BROWSERBASE_API_KEY/BROWSERBASE_PROJECT_ID)
- Updates browser_tool.py fallback: prefers Browser Use over Browserbase
- Updates nous_subscription.py: gateway vendor 'browser-use', auto-config
  sets cloud_provider='browser-use' for new subscribers
- Updates tools_config.py: Nous Subscription entry now uses Browser Use
- Updates setup.py, cli.py, status.py, prompt_builder.py display strings
- Updates all affected tests to match new behavior

Browserbase remains fully functional for users with direct API credentials.
The change only affects the managed/subscription path.

* chore: remove redundant Browser Use hint from system prompt

* fix: upgrade Browser Use provider to v3 API

- Base URL: api/v2 -> api/v3 (v2 is legacy)
- Unified all endpoints to use native Browser Use paths:
  - POST /browsers (create session, returns cdpUrl)
  - PATCH /browsers/{id} with {action: stop} (close session)
- Removed managed-mode branching that used Browserbase-style
  /v1/sessions paths — v3 gateway now supports /browsers directly
- Removed unused managed_mode variable in close_session

* fix(browser-use): use X-Browser-Use-API-Key header for managed mode

The managed gateway expects X-Browser-Use-API-Key, not X-BB-API-Key
(which is a Browserbase-specific header). Using the wrong header caused
a 401 AUTH_ERROR on every managed-mode browser session create.

Simplified _headers() to always use X-Browser-Use-API-Key regardless
of direct vs managed mode.

* fix(nous_subscription): browserbase explicit provider is direct-only

Since managed Nous gateway now routes through Browser Use, the
browserbase explicit provider path should not check managed_browser_available
(which resolves against the browser-use gateway). Simplified to direct-only
with managed=False.

* fix(browser-use): port missing improvements from PR #5605

- CDP URL normalization: resolve HTTP discovery URLs to websocket after
  cloud provider create_session() (prevents agent-browser failures)
- Managed session payload: send timeout=5 and proxyCountryCode=us for
  gateway-backed sessions (prevents billing overruns)
- Update prompt builder, browser_close schema, and module docstring to
  replace remaining Browserbase references with Browser Use
- Dynamic /browser status detection via _get_cloud_provider() instead
  of hardcoded env var checks (future-proof for new providers)
- Rename post_setup key from 'browserbase' to 'agent_browser'
- Update setup hint to mention Browser Use alongside Browserbase
- Add tests: CDP normalization, browserbase direct-only guard,
  managed browser-use gateway, direct browserbase fallback

---------

Co-authored-by: rob-maron <132852777+rob-maron@users.noreply.github.com>
This commit is contained in:
Ben Barclay
2026-04-07 22:40:22 +10:00
committed by GitHub
parent 8b861b77c1
commit b2f477a30b
16 changed files with 429 additions and 258 deletions

View File

@@ -2,16 +2,62 @@
import logging
import os
import threading
import uuid
from typing import Dict
from typing import Any, Dict, Optional
import requests
from tools.browser_providers.base import CloudBrowserProvider
from tools.managed_tool_gateway import resolve_managed_tool_gateway
from tools.tool_backend_helpers import managed_nous_tools_enabled
logger = logging.getLogger(__name__)
_pending_create_keys: Dict[str, str] = {}
_pending_create_keys_lock = threading.Lock()
_BASE_URL = "https://api.browser-use.com/api/v2"
_BASE_URL = "https://api.browser-use.com/api/v3"
_DEFAULT_MANAGED_TIMEOUT_MINUTES = 5
_DEFAULT_MANAGED_PROXY_COUNTRY_CODE = "us"
def _get_or_create_pending_create_key(task_id: str) -> str:
with _pending_create_keys_lock:
existing = _pending_create_keys.get(task_id)
if existing:
return existing
created = f"browser-use-session-create:{uuid.uuid4().hex}"
_pending_create_keys[task_id] = created
return created
def _clear_pending_create_key(task_id: str) -> None:
with _pending_create_keys_lock:
_pending_create_keys.pop(task_id, None)
def _should_preserve_pending_create_key(response: requests.Response) -> bool:
if response.status_code >= 500:
return True
if response.status_code != 409:
return False
try:
payload = response.json()
except Exception:
return False
if not isinstance(payload, dict):
return False
error = payload.get("error")
if not isinstance(error, dict):
return False
message = str(error.get("message") or "").lower()
return "already in progress" in message
class BrowserUseProvider(CloudBrowserProvider):
@@ -21,55 +67,120 @@ class BrowserUseProvider(CloudBrowserProvider):
return "Browser Use"
def is_configured(self) -> bool:
return bool(os.environ.get("BROWSER_USE_API_KEY"))
return self._get_config_or_none() is not None
# ------------------------------------------------------------------
# Config resolution (direct API key OR managed Nous gateway)
# ------------------------------------------------------------------
def _get_config_or_none(self) -> Optional[Dict[str, Any]]:
api_key = os.environ.get("BROWSER_USE_API_KEY")
if api_key:
return {
"api_key": api_key,
"base_url": _BASE_URL,
"managed_mode": False,
}
managed = resolve_managed_tool_gateway("browser-use")
if managed is None:
return None
return {
"api_key": managed.nous_user_token,
"base_url": managed.gateway_origin.rstrip("/"),
"managed_mode": True,
}
def _get_config(self) -> Dict[str, Any]:
config = self._get_config_or_none()
if config is None:
message = (
"Browser Use requires a direct BROWSER_USE_API_KEY credential."
)
if managed_nous_tools_enabled():
message = (
"Browser Use requires either a direct BROWSER_USE_API_KEY "
"credential or a managed Browser Use gateway configuration."
)
raise ValueError(message)
return config
# ------------------------------------------------------------------
# Session lifecycle
# ------------------------------------------------------------------
def _headers(self) -> Dict[str, str]:
api_key = os.environ.get("BROWSER_USE_API_KEY")
if not api_key:
raise ValueError(
"BROWSER_USE_API_KEY environment variable is required. "
"Get your key at https://browser-use.com"
)
return {
def _headers(self, config: Dict[str, Any]) -> Dict[str, str]:
headers = {
"Content-Type": "application/json",
"X-Browser-Use-API-Key": api_key,
"X-Browser-Use-API-Key": config["api_key"],
}
return headers
def create_session(self, task_id: str) -> Dict[str, object]:
config = self._get_config()
managed_mode = bool(config.get("managed_mode"))
headers = self._headers(config)
if managed_mode:
headers["X-Idempotency-Key"] = _get_or_create_pending_create_key(task_id)
# Keep gateway-backed sessions short so billing authorization does not
# default to a long Browser-Use timeout when Hermes only needs a task-
# scoped ephemeral browser.
payload = (
{
"timeout": _DEFAULT_MANAGED_TIMEOUT_MINUTES,
"proxyCountryCode": _DEFAULT_MANAGED_PROXY_COUNTRY_CODE,
}
if managed_mode
else {}
)
response = requests.post(
f"{_BASE_URL}/browsers",
headers=self._headers(),
json={},
f"{config['base_url']}/browsers",
headers=headers,
json=payload,
timeout=30,
)
if not response.ok:
if managed_mode and not _should_preserve_pending_create_key(response):
_clear_pending_create_key(task_id)
raise RuntimeError(
f"Failed to create Browser Use session: "
f"{response.status_code} {response.text}"
)
session_data = response.json()
if managed_mode:
_clear_pending_create_key(task_id)
session_name = f"hermes_{task_id}_{uuid.uuid4().hex[:8]}"
external_call_id = response.headers.get("x-external-call-id") if managed_mode else None
logger.info("Created Browser Use session %s", session_name)
cdp_url = session_data.get("cdpUrl") or session_data.get("connectUrl") or ""
return {
"session_name": session_name,
"bb_session_id": session_data["id"],
"cdp_url": session_data["cdpUrl"],
"cdp_url": cdp_url,
"features": {"browser_use": True},
"external_call_id": external_call_id,
}
def close_session(self, session_id: str) -> bool:
try:
config = self._get_config()
except ValueError:
logger.warning("Cannot close Browser Use session %s — missing credentials", session_id)
return False
try:
response = requests.patch(
f"{_BASE_URL}/browsers/{session_id}",
headers=self._headers(),
f"{config['base_url']}/browsers/{session_id}",
headers=self._headers(config),
json={"action": "stop"},
timeout=10,
)
@@ -89,17 +200,14 @@ class BrowserUseProvider(CloudBrowserProvider):
return False
def emergency_cleanup(self, session_id: str) -> None:
api_key = os.environ.get("BROWSER_USE_API_KEY")
if not api_key:
config = self._get_config_or_none()
if config is None:
logger.warning("Cannot emergency-cleanup Browser Use session %s — missing credentials", session_id)
return
try:
requests.patch(
f"{_BASE_URL}/browsers/{session_id}",
headers={
"Content-Type": "application/json",
"X-Browser-Use-API-Key": api_key,
},
f"{config['base_url']}/browsers/{session_id}",
headers=self._headers(config),
json={"action": "stop"},
timeout=5,
)

View File

@@ -1,63 +1,24 @@
"""Browserbase cloud browser provider."""
"""Browserbase cloud browser provider (direct credentials only)."""
import logging
import os
import threading
import uuid
from typing import Any, Dict, Optional
import requests
from tools.browser_providers.base import CloudBrowserProvider
from tools.managed_tool_gateway import resolve_managed_tool_gateway
from tools.tool_backend_helpers import managed_nous_tools_enabled
logger = logging.getLogger(__name__)
_pending_create_keys: Dict[str, str] = {}
_pending_create_keys_lock = threading.Lock()
def _get_or_create_pending_create_key(task_id: str) -> str:
with _pending_create_keys_lock:
existing = _pending_create_keys.get(task_id)
if existing:
return existing
created = f"browserbase-session-create:{uuid.uuid4().hex}"
_pending_create_keys[task_id] = created
return created
def _clear_pending_create_key(task_id: str) -> None:
with _pending_create_keys_lock:
_pending_create_keys.pop(task_id, None)
def _should_preserve_pending_create_key(response: requests.Response) -> bool:
if response.status_code >= 500:
return True
if response.status_code != 409:
return False
try:
payload = response.json()
except Exception:
return False
if not isinstance(payload, dict):
return False
error = payload.get("error")
if not isinstance(error, dict):
return False
message = str(error.get("message") or "").lower()
return "already in progress" in message
class BrowserbaseProvider(CloudBrowserProvider):
"""Browserbase (https://browserbase.com) cloud browser backend."""
"""Browserbase (https://browserbase.com) cloud browser backend.
This provider requires direct BROWSERBASE_API_KEY and BROWSERBASE_PROJECT_ID
credentials. Managed Nous gateway support has been removed — the Nous
subscription now routes through Browser Use instead.
"""
def provider_name(self) -> str:
return "Browserbase"
@@ -77,37 +38,20 @@ class BrowserbaseProvider(CloudBrowserProvider):
"api_key": api_key,
"project_id": project_id,
"base_url": os.environ.get("BROWSERBASE_BASE_URL", "https://api.browserbase.com").rstrip("/"),
"managed_mode": False,
}
managed = resolve_managed_tool_gateway("browserbase")
if managed is None:
return None
return {
"api_key": managed.nous_user_token,
"project_id": "managed",
"base_url": managed.gateway_origin.rstrip("/"),
"managed_mode": True,
}
return None
def _get_config(self) -> Dict[str, Any]:
config = self._get_config_or_none()
if config is None:
message = (
"Browserbase requires direct BROWSERBASE_API_KEY/BROWSERBASE_PROJECT_ID credentials."
raise ValueError(
"Browserbase requires BROWSERBASE_API_KEY and BROWSERBASE_PROJECT_ID "
"environment variables."
)
if managed_nous_tools_enabled():
message = (
"Browserbase requires either direct BROWSERBASE_API_KEY/BROWSERBASE_PROJECT_ID "
"credentials or a managed Browserbase gateway configuration."
)
raise ValueError(message)
return config
def create_session(self, task_id: str) -> Dict[str, object]:
config = self._get_config()
managed_mode = bool(config.get("managed_mode"))
# Optional env-var knobs
enable_proxies = os.environ.get("BROWSERBASE_PROXIES", "true").lower() != "false"
@@ -147,8 +91,6 @@ class BrowserbaseProvider(CloudBrowserProvider):
"Content-Type": "application/json",
"X-BB-API-Key": config["api_key"],
}
if managed_mode:
headers["X-Idempotency-Key"] = _get_or_create_pending_create_key(task_id)
response = requests.post(
f"{config['base_url']}/v1/sessions",
@@ -161,7 +103,7 @@ class BrowserbaseProvider(CloudBrowserProvider):
keepalive_fallback = False
# Handle 402 — paid features unavailable
if response.status_code == 402 and not managed_mode:
if response.status_code == 402:
if enable_keep_alive:
keepalive_fallback = True
logger.warning(
@@ -191,18 +133,13 @@ class BrowserbaseProvider(CloudBrowserProvider):
)
if not response.ok:
if managed_mode and not _should_preserve_pending_create_key(response):
_clear_pending_create_key(task_id)
raise RuntimeError(
f"Failed to create Browserbase session: "
f"{response.status_code} {response.text}"
)
session_data = response.json()
if managed_mode:
_clear_pending_create_key(task_id)
session_name = f"hermes_{task_id}_{uuid.uuid4().hex[:8]}"
external_call_id = response.headers.get("x-external-call-id") if managed_mode else None
if enable_proxies and not proxies_fallback:
features_enabled["proxies"] = True
@@ -221,7 +158,6 @@ class BrowserbaseProvider(CloudBrowserProvider):
"bb_session_id": session_data["id"],
"cdp_url": session_data["connectUrl"],
"features": features_enabled,
"external_call_id": external_call_id,
}
def close_session(self, session_id: str) -> bool:

View File

@@ -3,10 +3,10 @@
Browser Tool Module
This module provides browser automation tools using agent-browser CLI. It
supports two backends — **Browserbase** (cloud) and **local Chromium** — with
identical agent-facing behaviour. The backend is auto-detected: if
``BROWSERBASE_API_KEY`` is set the cloud service is used; otherwise a local
headless Chromium instance is launched automatically.
supports multiple backends — **Browser Use** (cloud, default for Nous
subscribers), **Browserbase** (cloud, direct credentials), and **local
Chromium** — with identical agent-facing behaviour. The backend is
auto-detected from config and available credentials.
The tool uses agent-browser's accessibility tree (ariaSnapshot) for text-based
page representation, making it ideal for LLM agents without vision capabilities.
@@ -17,8 +17,7 @@ Features:
``agent-browser install`` (downloads Chromium) or
``agent-browser install --with-deps`` (also installs system libraries for
Debian/Ubuntu/Docker).
- **Cloud mode**: Browserbase cloud execution with stealth features, proxies,
and CAPTCHA solving. Activated when BROWSERBASE_API_KEY is set.
- **Cloud mode**: Browserbase or Browser Use cloud execution when configured.
- Session isolation per task ID
- Text-based page snapshots using accessibility tree
- Element interaction via ref selectors (@e1, @e2, etc.)
@@ -26,8 +25,9 @@ Features:
- Automatic cleanup of browser sessions
Environment Variables:
- BROWSERBASE_API_KEY: API key for Browserbase (enables cloud mode)
- BROWSERBASE_PROJECT_ID: Project ID for Browserbase (required for cloud mode)
- BROWSERBASE_API_KEY: API key for direct Browserbase cloud mode
- BROWSERBASE_PROJECT_ID: Project ID for direct Browserbase cloud mode
- BROWSER_USE_API_KEY: API key for direct Browser Use cloud mode
- BROWSERBASE_PROXIES: Enable/disable residential proxies (default: "true")
- BROWSERBASE_ADVANCED_STEALTH: Enable advanced stealth mode with custom Chromium,
requires Scale Plan (default: "false")
@@ -280,23 +280,19 @@ def _get_cloud_provider() -> Optional[CloudBrowserProvider]:
logger.debug("Could not read cloud_provider from config: %s", e)
if _cached_cloud_provider is None:
fallback_provider = BrowserbaseProvider()
# Prefer Browser Use (managed Nous gateway or direct API key),
# fall back to Browserbase (direct credentials only).
fallback_provider = BrowserUseProvider()
if fallback_provider.is_configured():
_cached_cloud_provider = fallback_provider
else:
fallback_provider = BrowserbaseProvider()
if fallback_provider.is_configured():
_cached_cloud_provider = fallback_provider
return _cached_cloud_provider
def _get_browserbase_config_or_none() -> Optional[Dict[str, Any]]:
"""Return Browserbase direct or managed config, or None when unavailable."""
return BrowserbaseProvider()._get_config_or_none()
def _get_browserbase_config() -> Dict[str, Any]:
"""Return Browserbase config or raise when neither direct nor managed mode is available."""
return BrowserbaseProvider()._get_config()
def _is_local_mode() -> bool:
"""Return True when the browser tool will use a local browser backend."""
if _get_cdp_override():
@@ -615,7 +611,15 @@ BROWSER_TOOL_SCHEMAS = [
"required": ["key"]
}
},
{
"name": "browser_close",
"description": "Close the browser session and release resources. Call this when done with browser tasks to free up cloud browser session quota.",
"parameters": {
"type": "object",
"properties": {},
"required": []
}
},
{
"name": "browser_get_images",
"description": "Get a list of all images on the current page with their URLs and alt text. Useful for finding images to analyze with the vision tool. Requires browser_navigate to be called first.",
@@ -736,6 +740,11 @@ def _get_session_info(task_id: Optional[str] = None) -> Dict[str, str]:
session_info = _create_local_session(task_id)
else:
session_info = provider.create_session(task_id)
if session_info.get("cdp_url"):
# Some cloud providers (including Browser-Use v3) return an HTTP
# CDP discovery URL instead of a raw websocket endpoint.
session_info = dict(session_info)
session_info["cdp_url"] = _resolve_cdp_override(str(session_info["cdp_url"]))
with _cleanup_lock:
# Double-check: another thread may have created a session while we
@@ -1947,7 +1956,7 @@ def cleanup_browser(task_id: Optional[str] = None) -> None:
camofox_close(task_id)
except Exception as e:
logger.debug("Camofox cleanup for task %s: %s", task_id, e)
logger.debug("cleanup_browser called for task_id: %s", task_id)
logger.debug("Active sessions: %s", list(_active_sessions.keys()))