mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-04-25 00:51:20 +00:00
feat(browser): multi-provider cloud browser support + Browser Use integration
Introduce a cloud browser provider abstraction so users can switch between Local Browser, Browserbase, and Browser Use (or future providers) via hermes tools / hermes setup. Cloud browser providers are behind an ABC (tools/browser_providers/base.py) so adding a new provider is a single-file addition with no changes to browser_tool.py internals. Changes: - tools/browser_providers/ package with ABC, Browserbase extraction, and Browser Use provider - browser_tool.py refactored to use _PROVIDER_REGISTRY + _get_cloud_provider() (cached) instead of hardcoded _is_local_mode() / _create_browserbase_session() - tools_config.py: generic _is_provider_active() / _detect_active_provider_index() replace TTS-only logic; Browser Use added as third browser option - config.py: BROWSER_USE_API_KEY added to OPTIONAL_ENV_VARS + show_config + allowlist - subprocess pipe hang fix: agent-browser daemon inherits pipe fds, communicate() blocks. Replaced with Popen + temp files. Original PR: #1208 Co-authored-by: ShawnPana <shawnpana@users.noreply.github.com>
This commit is contained in:
parent
4768ea624d
commit
d44b6b7f1b
7 changed files with 567 additions and 303 deletions
10
tools/browser_providers/__init__.py
Normal file
10
tools/browser_providers/__init__.py
Normal file
|
|
@ -0,0 +1,10 @@
|
|||
"""Cloud browser provider abstraction.
|
||||
|
||||
Import the ABC so callers can do::
|
||||
|
||||
from tools.browser_providers import CloudBrowserProvider
|
||||
"""
|
||||
|
||||
from tools.browser_providers.base import CloudBrowserProvider
|
||||
|
||||
__all__ = ["CloudBrowserProvider"]
|
||||
59
tools/browser_providers/base.py
Normal file
59
tools/browser_providers/base.py
Normal file
|
|
@ -0,0 +1,59 @@
|
|||
"""Abstract base class for cloud browser providers."""
|
||||
|
||||
from abc import ABC, abstractmethod
|
||||
from typing import Dict
|
||||
|
||||
|
||||
class CloudBrowserProvider(ABC):
|
||||
"""Interface for cloud browser backends (Browserbase, Steel, etc.).
|
||||
|
||||
Implementations live in sibling modules and are registered in
|
||||
``browser_tool._PROVIDER_REGISTRY``. The user selects a provider via
|
||||
``hermes setup`` / ``hermes tools``; the choice is persisted as
|
||||
``config["browser"]["cloud_provider"]``.
|
||||
"""
|
||||
|
||||
@abstractmethod
|
||||
def provider_name(self) -> str:
|
||||
"""Short, human-readable name shown in logs and diagnostics."""
|
||||
|
||||
@abstractmethod
|
||||
def is_configured(self) -> bool:
|
||||
"""Return True when all required env vars / credentials are present.
|
||||
|
||||
Called at tool-registration time (``check_browser_requirements``) to
|
||||
gate availability. Must be cheap — no network calls.
|
||||
"""
|
||||
|
||||
@abstractmethod
|
||||
def create_session(self, task_id: str) -> Dict[str, object]:
|
||||
"""Create a cloud browser session and return session metadata.
|
||||
|
||||
Must return a dict with at least::
|
||||
|
||||
{
|
||||
"session_name": str, # unique name for agent-browser --session
|
||||
"bb_session_id": str, # provider session ID (for close/cleanup)
|
||||
"cdp_url": str, # CDP websocket URL
|
||||
"features": dict, # feature flags that were enabled
|
||||
}
|
||||
|
||||
``bb_session_id`` is a legacy key name kept for backward compat with
|
||||
the rest of browser_tool.py — it holds the provider's session ID
|
||||
regardless of which provider is in use.
|
||||
"""
|
||||
|
||||
@abstractmethod
|
||||
def close_session(self, session_id: str) -> bool:
|
||||
"""Release / terminate a cloud session by its provider session ID.
|
||||
|
||||
Returns True on success, False on failure. Should not raise.
|
||||
"""
|
||||
|
||||
@abstractmethod
|
||||
def emergency_cleanup(self, session_id: str) -> None:
|
||||
"""Best-effort session teardown during process exit.
|
||||
|
||||
Called from atexit / signal handlers. Must tolerate missing
|
||||
credentials, network errors, etc. — log and move on.
|
||||
"""
|
||||
107
tools/browser_providers/browser_use.py
Normal file
107
tools/browser_providers/browser_use.py
Normal file
|
|
@ -0,0 +1,107 @@
|
|||
"""Browser Use cloud browser provider."""
|
||||
|
||||
import logging
|
||||
import os
|
||||
import uuid
|
||||
from typing import Dict
|
||||
|
||||
import requests
|
||||
|
||||
from tools.browser_providers.base import CloudBrowserProvider
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
_BASE_URL = "https://api.browser-use.com/api/v2"
|
||||
|
||||
|
||||
class BrowserUseProvider(CloudBrowserProvider):
|
||||
"""Browser Use (https://browser-use.com) cloud browser backend."""
|
||||
|
||||
def provider_name(self) -> str:
|
||||
return "Browser Use"
|
||||
|
||||
def is_configured(self) -> bool:
|
||||
return bool(os.environ.get("BROWSER_USE_API_KEY"))
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# 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 {
|
||||
"Content-Type": "application/json",
|
||||
"X-Browser-Use-API-Key": api_key,
|
||||
}
|
||||
|
||||
def create_session(self, task_id: str) -> Dict[str, object]:
|
||||
response = requests.post(
|
||||
f"{_BASE_URL}/browsers",
|
||||
headers=self._headers(),
|
||||
json={},
|
||||
timeout=30,
|
||||
)
|
||||
|
||||
if not response.ok:
|
||||
raise RuntimeError(
|
||||
f"Failed to create Browser Use session: "
|
||||
f"{response.status_code} {response.text}"
|
||||
)
|
||||
|
||||
session_data = response.json()
|
||||
session_name = f"hermes_{task_id}_{uuid.uuid4().hex[:8]}"
|
||||
|
||||
logger.info("Created Browser Use session %s", session_name)
|
||||
|
||||
return {
|
||||
"session_name": session_name,
|
||||
"bb_session_id": session_data["id"],
|
||||
"cdp_url": session_data["cdpUrl"],
|
||||
"features": {"browser_use": True},
|
||||
}
|
||||
|
||||
def close_session(self, session_id: str) -> bool:
|
||||
try:
|
||||
response = requests.patch(
|
||||
f"{_BASE_URL}/browsers/{session_id}",
|
||||
headers=self._headers(),
|
||||
json={"action": "stop"},
|
||||
timeout=10,
|
||||
)
|
||||
if response.status_code in (200, 201, 204):
|
||||
logger.debug("Successfully closed Browser Use session %s", session_id)
|
||||
return True
|
||||
else:
|
||||
logger.warning(
|
||||
"Failed to close Browser Use session %s: HTTP %s - %s",
|
||||
session_id,
|
||||
response.status_code,
|
||||
response.text[:200],
|
||||
)
|
||||
return False
|
||||
except Exception as e:
|
||||
logger.error("Exception closing Browser Use session %s: %s", session_id, e)
|
||||
return False
|
||||
|
||||
def emergency_cleanup(self, session_id: str) -> None:
|
||||
api_key = os.environ.get("BROWSER_USE_API_KEY")
|
||||
if not api_key:
|
||||
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,
|
||||
},
|
||||
json={"action": "stop"},
|
||||
timeout=5,
|
||||
)
|
||||
except Exception as e:
|
||||
logger.debug("Emergency cleanup failed for Browser Use session %s: %s", session_id, e)
|
||||
206
tools/browser_providers/browserbase.py
Normal file
206
tools/browser_providers/browserbase.py
Normal file
|
|
@ -0,0 +1,206 @@
|
|||
"""Browserbase cloud browser provider."""
|
||||
|
||||
import logging
|
||||
import os
|
||||
import uuid
|
||||
from typing import Dict
|
||||
|
||||
import requests
|
||||
|
||||
from tools.browser_providers.base import CloudBrowserProvider
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class BrowserbaseProvider(CloudBrowserProvider):
|
||||
"""Browserbase (https://browserbase.com) cloud browser backend."""
|
||||
|
||||
def provider_name(self) -> str:
|
||||
return "Browserbase"
|
||||
|
||||
def is_configured(self) -> bool:
|
||||
return bool(
|
||||
os.environ.get("BROWSERBASE_API_KEY")
|
||||
and os.environ.get("BROWSERBASE_PROJECT_ID")
|
||||
)
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Session lifecycle
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
def _get_config(self) -> Dict[str, str]:
|
||||
api_key = os.environ.get("BROWSERBASE_API_KEY")
|
||||
project_id = os.environ.get("BROWSERBASE_PROJECT_ID")
|
||||
if not api_key or not project_id:
|
||||
raise ValueError(
|
||||
"BROWSERBASE_API_KEY and BROWSERBASE_PROJECT_ID environment "
|
||||
"variables are required. Get your credentials at "
|
||||
"https://browserbase.com"
|
||||
)
|
||||
return {"api_key": api_key, "project_id": project_id}
|
||||
|
||||
def create_session(self, task_id: str) -> Dict[str, object]:
|
||||
config = self._get_config()
|
||||
|
||||
# Optional env-var knobs
|
||||
enable_proxies = os.environ.get("BROWSERBASE_PROXIES", "true").lower() != "false"
|
||||
enable_advanced_stealth = os.environ.get("BROWSERBASE_ADVANCED_STEALTH", "false").lower() == "true"
|
||||
enable_keep_alive = os.environ.get("BROWSERBASE_KEEP_ALIVE", "true").lower() != "false"
|
||||
custom_timeout_ms = os.environ.get("BROWSERBASE_SESSION_TIMEOUT")
|
||||
|
||||
features_enabled = {
|
||||
"basic_stealth": True,
|
||||
"proxies": False,
|
||||
"advanced_stealth": False,
|
||||
"keep_alive": False,
|
||||
"custom_timeout": False,
|
||||
}
|
||||
|
||||
session_config: Dict[str, object] = {"projectId": config["project_id"]}
|
||||
|
||||
if enable_keep_alive:
|
||||
session_config["keepAlive"] = True
|
||||
|
||||
if custom_timeout_ms:
|
||||
try:
|
||||
timeout_val = int(custom_timeout_ms)
|
||||
if timeout_val > 0:
|
||||
session_config["timeout"] = timeout_val
|
||||
except ValueError:
|
||||
logger.warning("Invalid BROWSERBASE_SESSION_TIMEOUT value: %s", custom_timeout_ms)
|
||||
|
||||
if enable_proxies:
|
||||
session_config["proxies"] = True
|
||||
|
||||
if enable_advanced_stealth:
|
||||
session_config["browserSettings"] = {"advancedStealth": True}
|
||||
|
||||
# --- Create session via API ---
|
||||
headers = {
|
||||
"Content-Type": "application/json",
|
||||
"X-BB-API-Key": config["api_key"],
|
||||
}
|
||||
response = requests.post(
|
||||
"https://api.browserbase.com/v1/sessions",
|
||||
headers=headers,
|
||||
json=session_config,
|
||||
timeout=30,
|
||||
)
|
||||
|
||||
proxies_fallback = False
|
||||
keepalive_fallback = False
|
||||
|
||||
# Handle 402 — paid features unavailable
|
||||
if response.status_code == 402:
|
||||
if enable_keep_alive:
|
||||
keepalive_fallback = True
|
||||
logger.warning(
|
||||
"keepAlive may require paid plan (402), retrying without it. "
|
||||
"Sessions may timeout during long operations."
|
||||
)
|
||||
session_config.pop("keepAlive", None)
|
||||
response = requests.post(
|
||||
"https://api.browserbase.com/v1/sessions",
|
||||
headers=headers,
|
||||
json=session_config,
|
||||
timeout=30,
|
||||
)
|
||||
|
||||
if response.status_code == 402 and enable_proxies:
|
||||
proxies_fallback = True
|
||||
logger.warning(
|
||||
"Proxies unavailable (402), retrying without proxies. "
|
||||
"Bot detection may be less effective."
|
||||
)
|
||||
session_config.pop("proxies", None)
|
||||
response = requests.post(
|
||||
"https://api.browserbase.com/v1/sessions",
|
||||
headers=headers,
|
||||
json=session_config,
|
||||
timeout=30,
|
||||
)
|
||||
|
||||
if not response.ok:
|
||||
raise RuntimeError(
|
||||
f"Failed to create Browserbase session: "
|
||||
f"{response.status_code} {response.text}"
|
||||
)
|
||||
|
||||
session_data = response.json()
|
||||
session_name = f"hermes_{task_id}_{uuid.uuid4().hex[:8]}"
|
||||
|
||||
if enable_proxies and not proxies_fallback:
|
||||
features_enabled["proxies"] = True
|
||||
if enable_advanced_stealth:
|
||||
features_enabled["advanced_stealth"] = True
|
||||
if enable_keep_alive and not keepalive_fallback:
|
||||
features_enabled["keep_alive"] = True
|
||||
if custom_timeout_ms and "timeout" in session_config:
|
||||
features_enabled["custom_timeout"] = True
|
||||
|
||||
feature_str = ", ".join(k for k, v in features_enabled.items() if v)
|
||||
logger.info("Created Browserbase session %s with features: %s", session_name, feature_str)
|
||||
|
||||
return {
|
||||
"session_name": session_name,
|
||||
"bb_session_id": session_data["id"],
|
||||
"cdp_url": session_data["connectUrl"],
|
||||
"features": features_enabled,
|
||||
}
|
||||
|
||||
def close_session(self, session_id: str) -> bool:
|
||||
try:
|
||||
config = self._get_config()
|
||||
except ValueError:
|
||||
logger.warning("Cannot close Browserbase session %s — missing credentials", session_id)
|
||||
return False
|
||||
|
||||
try:
|
||||
response = requests.post(
|
||||
f"https://api.browserbase.com/v1/sessions/{session_id}",
|
||||
headers={
|
||||
"X-BB-API-Key": config["api_key"],
|
||||
"Content-Type": "application/json",
|
||||
},
|
||||
json={
|
||||
"projectId": config["project_id"],
|
||||
"status": "REQUEST_RELEASE",
|
||||
},
|
||||
timeout=10,
|
||||
)
|
||||
if response.status_code in (200, 201, 204):
|
||||
logger.debug("Successfully closed Browserbase session %s", session_id)
|
||||
return True
|
||||
else:
|
||||
logger.warning(
|
||||
"Failed to close session %s: HTTP %s - %s",
|
||||
session_id,
|
||||
response.status_code,
|
||||
response.text[:200],
|
||||
)
|
||||
return False
|
||||
except Exception as e:
|
||||
logger.error("Exception closing Browserbase session %s: %s", session_id, e)
|
||||
return False
|
||||
|
||||
def emergency_cleanup(self, session_id: str) -> None:
|
||||
api_key = os.environ.get("BROWSERBASE_API_KEY")
|
||||
project_id = os.environ.get("BROWSERBASE_PROJECT_ID")
|
||||
if not api_key or not project_id:
|
||||
logger.warning("Cannot emergency-cleanup Browserbase session %s — missing credentials", session_id)
|
||||
return
|
||||
try:
|
||||
requests.post(
|
||||
f"https://api.browserbase.com/v1/sessions/{session_id}",
|
||||
headers={
|
||||
"X-BB-API-Key": api_key,
|
||||
"Content-Type": "application/json",
|
||||
},
|
||||
json={
|
||||
"projectId": project_id,
|
||||
"status": "REQUEST_RELEASE",
|
||||
},
|
||||
timeout=5,
|
||||
)
|
||||
except Exception as e:
|
||||
logger.debug("Emergency cleanup failed for Browserbase session %s: %s", session_id, e)
|
||||
Loading…
Add table
Add a link
Reference in a new issue