mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-05-29 06:31:32 +00:00
refactor(browser): delete tools/browser_providers/ directory; migrate tests
The four files in tools/browser_providers/ (base.py, browserbase.py,
browser_use.py, firecrawl.py) have been migrated into
plugins/browser/<vendor>/provider.py over the previous commits. No
in-tree code references them anymore — the legacy class names
(BrowserbaseProvider / BrowserUseProvider / FirecrawlProvider) are
re-exported from tools.browser_tool as aliases to the plugin classes,
so existing test patches keep working.
Updates tests/tools/test_managed_browserbase_and_modal.py:
- Adds _load_plugin_module() helper next to _load_tool_module().
- Reroutes five _load_tool_module('tools.browser_providers.X', ...)
calls to _load_plugin_module('plugins.browser.X.provider', ...).
- Renames BrowserbaseProvider/BrowserUseProvider -> the new plugin
class names (BrowserbaseBrowserProvider / BrowserUseBrowserProvider).
- Updates is_configured() -> is_available() on the one assertion that
cared about the rename (the others stay on is_configured() via the
BrowserProvider ABC's backward-compat alias).
Net diff: -630 / +39 lines (tests + dead-code deletion). Verified
23/23 tests in test_browser_cloud_*.py + test_managed_browserbase_and_modal.py
still pass.
Closes the file-tree mismatch portion of #25214. Remaining work:
new plugin-level test coverage under tests/plugins/browser/, behaviour
parity subprocess sweep vs origin/main, and full tests/tools/ regression
sweep before opening the PR.
This commit is contained in:
parent
1b9c539c6e
commit
250caebeb1
6 changed files with 39 additions and 650 deletions
|
|
@ -10,7 +10,9 @@ from unittest.mock import patch
|
|||
import pytest
|
||||
|
||||
|
||||
TOOLS_DIR = Path(__file__).resolve().parents[2] / "tools"
|
||||
REPO_ROOT = Path(__file__).resolve().parents[2]
|
||||
TOOLS_DIR = REPO_ROOT / "tools"
|
||||
PLUGINS_DIR = REPO_ROOT / "plugins"
|
||||
|
||||
|
||||
def _load_tool_module(module_name: str, filename: str):
|
||||
|
|
@ -22,6 +24,21 @@ def _load_tool_module(module_name: str, filename: str):
|
|||
return module
|
||||
|
||||
|
||||
def _load_plugin_module(module_name: str, relpath: str):
|
||||
"""Load a plugin module by file path from ``plugins/``.
|
||||
|
||||
Mirror of :func:`_load_tool_module` for the plugin tree. Used by tests
|
||||
that exercise the per-vendor browser plugins' session-lifecycle
|
||||
behaviour after the PR #25214 migration.
|
||||
"""
|
||||
spec = spec_from_file_location(module_name, PLUGINS_DIR / relpath)
|
||||
assert spec and spec.loader
|
||||
module = module_from_spec(spec)
|
||||
sys.modules[module_name] = module
|
||||
spec.loader.exec_module(module)
|
||||
return module
|
||||
|
||||
|
||||
def _reset_modules(prefixes: tuple[str, ...]):
|
||||
for name in list(sys.modules):
|
||||
if name.startswith(prefixes):
|
||||
|
|
@ -200,13 +217,13 @@ def test_browserbase_does_not_use_gateway_only_configuration():
|
|||
})
|
||||
|
||||
with patch.dict(os.environ, env, clear=True):
|
||||
browserbase_module = _load_tool_module(
|
||||
"tools.browser_providers.browserbase",
|
||||
"browser_providers/browserbase.py",
|
||||
browserbase_module = _load_plugin_module(
|
||||
"plugins.browser.browserbase.provider",
|
||||
"browser/browserbase/provider.py",
|
||||
)
|
||||
provider = browserbase_module.BrowserbaseProvider()
|
||||
provider = browserbase_module.BrowserbaseBrowserProvider()
|
||||
|
||||
assert provider.is_configured() is False
|
||||
assert provider.is_available() is False
|
||||
|
||||
|
||||
def test_browser_use_managed_gateway_adds_idempotency_key_and_persists_external_call_id():
|
||||
|
|
@ -231,13 +248,13 @@ def test_browser_use_managed_gateway_adds_idempotency_key_and_persists_external_
|
|||
}
|
||||
|
||||
with patch.dict(os.environ, env, clear=True):
|
||||
browser_use_module = _load_tool_module(
|
||||
"tools.browser_providers.browser_use",
|
||||
"browser_providers/browser_use.py",
|
||||
browser_use_module = _load_plugin_module(
|
||||
"plugins.browser.browser_use.provider",
|
||||
"browser/browser_use/provider.py",
|
||||
)
|
||||
|
||||
with patch.object(browser_use_module.requests, "post", return_value=_Response()) as post:
|
||||
provider = browser_use_module.BrowserUseProvider()
|
||||
provider = browser_use_module.BrowserUseBrowserProvider()
|
||||
session = provider.create_session("task-browser-use-managed")
|
||||
|
||||
sent_headers = post.call_args.kwargs["headers"]
|
||||
|
|
@ -271,11 +288,11 @@ def test_browser_use_managed_gateway_reuses_pending_idempotency_key_after_timeou
|
|||
}
|
||||
|
||||
with patch.dict(os.environ, env, clear=True):
|
||||
browser_use_module = _load_tool_module(
|
||||
"tools.browser_providers.browser_use",
|
||||
"browser_providers/browser_use.py",
|
||||
browser_use_module = _load_plugin_module(
|
||||
"plugins.browser.browser_use.provider",
|
||||
"browser/browser_use/provider.py",
|
||||
)
|
||||
provider = browser_use_module.BrowserUseProvider()
|
||||
provider = browser_use_module.BrowserUseBrowserProvider()
|
||||
timeout = browser_use_module.requests.Timeout("timed out")
|
||||
|
||||
with patch.object(
|
||||
|
|
@ -333,11 +350,11 @@ def test_browser_use_managed_gateway_preserves_pending_idempotency_key_for_in_pr
|
|||
}
|
||||
|
||||
with patch.dict(os.environ, env, clear=True):
|
||||
browser_use_module = _load_tool_module(
|
||||
"tools.browser_providers.browser_use",
|
||||
"browser_providers/browser_use.py",
|
||||
browser_use_module = _load_plugin_module(
|
||||
"plugins.browser.browser_use.provider",
|
||||
"browser/browser_use/provider.py",
|
||||
)
|
||||
provider = browser_use_module.BrowserUseProvider()
|
||||
provider = browser_use_module.BrowserUseBrowserProvider()
|
||||
|
||||
with patch.object(
|
||||
browser_use_module.requests,
|
||||
|
|
@ -380,11 +397,11 @@ def test_browser_use_managed_gateway_uses_new_idempotency_key_for_a_new_session_
|
|||
}
|
||||
|
||||
with patch.dict(os.environ, env, clear=True):
|
||||
browser_use_module = _load_tool_module(
|
||||
"tools.browser_providers.browser_use",
|
||||
"browser_providers/browser_use.py",
|
||||
browser_use_module = _load_plugin_module(
|
||||
"plugins.browser.browser_use.provider",
|
||||
"browser/browser_use/provider.py",
|
||||
)
|
||||
provider = browser_use_module.BrowserUseProvider()
|
||||
provider = browser_use_module.BrowserUseBrowserProvider()
|
||||
|
||||
with patch.object(browser_use_module.requests, "post", side_effect=[_Response(), _Response()]) as post:
|
||||
provider.create_session("task-browser-use-new")
|
||||
|
|
|
|||
|
|
@ -1,10 +0,0 @@
|
|||
"""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"]
|
||||
|
|
@ -1,59 +0,0 @@
|
|||
"""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.
|
||||
"""
|
||||
|
|
@ -1,225 +0,0 @@
|
|||
"""Browser Use cloud browser provider."""
|
||||
|
||||
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, prefers_gateway
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
_pending_create_keys: Dict[str, str] = {}
|
||||
_pending_create_keys_lock = threading.Lock()
|
||||
|
||||
_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):
|
||||
"""Browser Use (https://browser-use.com) cloud browser backend."""
|
||||
|
||||
def provider_name(self) -> str:
|
||||
return "Browser Use"
|
||||
|
||||
def is_configured(self) -> bool:
|
||||
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 and not prefers_gateway("browser"):
|
||||
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, config: Dict[str, Any]) -> Dict[str, str]:
|
||||
headers = {
|
||||
"Content-Type": "application/json",
|
||||
"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 {}
|
||||
)
|
||||
|
||||
try:
|
||||
response = requests.post(
|
||||
f"{config['base_url']}/browsers",
|
||||
headers=headers,
|
||||
json=payload,
|
||||
timeout=30,
|
||||
)
|
||||
except requests.RequestException as exc:
|
||||
# Managed mode: propagate raw so callers can retry with the
|
||||
# preserved idempotency key. Direct mode: wrap network failures
|
||||
# into a clean RuntimeError for end users.
|
||||
if managed_mode:
|
||||
raise
|
||||
raise RuntimeError(
|
||||
f"Browser Use API connection failed: {exc}"
|
||||
) from exc
|
||||
|
||||
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": 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"{config['base_url']}/browsers/{session_id}",
|
||||
headers=self._headers(config),
|
||||
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:
|
||||
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"{config['base_url']}/browsers/{session_id}",
|
||||
headers=self._headers(config),
|
||||
json={"action": "stop"},
|
||||
timeout=5,
|
||||
)
|
||||
except Exception as e:
|
||||
logger.debug("Emergency cleanup failed for Browser Use session %s: %s", session_id, e)
|
||||
|
|
@ -1,222 +0,0 @@
|
|||
"""Browserbase cloud browser provider (direct credentials only)."""
|
||||
|
||||
import logging
|
||||
import os
|
||||
import uuid
|
||||
from typing import Any, Dict, Optional
|
||||
|
||||
import requests
|
||||
|
||||
from tools.browser_providers.base import CloudBrowserProvider
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class BrowserbaseProvider(CloudBrowserProvider):
|
||||
"""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"
|
||||
|
||||
def is_configured(self) -> bool:
|
||||
return self._get_config_or_none() is not None
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Session lifecycle
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
def _get_config_or_none(self) -> Optional[Dict[str, Any]]:
|
||||
api_key = os.environ.get("BROWSERBASE_API_KEY")
|
||||
project_id = os.environ.get("BROWSERBASE_PROJECT_ID")
|
||||
if api_key and project_id:
|
||||
return {
|
||||
"api_key": api_key,
|
||||
"project_id": project_id,
|
||||
"base_url": os.environ.get("BROWSERBASE_BASE_URL", "https://api.browserbase.com").rstrip("/"),
|
||||
}
|
||||
return None
|
||||
|
||||
def _get_config(self) -> Dict[str, Any]:
|
||||
config = self._get_config_or_none()
|
||||
if config is None:
|
||||
raise ValueError(
|
||||
"Browserbase requires BROWSERBASE_API_KEY and BROWSERBASE_PROJECT_ID "
|
||||
"environment variables."
|
||||
)
|
||||
return config
|
||||
|
||||
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"],
|
||||
}
|
||||
|
||||
try:
|
||||
response = requests.post(
|
||||
f"{config['base_url']}/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(
|
||||
f"{config['base_url']}/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(
|
||||
f"{config['base_url']}/v1/sessions",
|
||||
headers=headers,
|
||||
json=session_config,
|
||||
timeout=30,
|
||||
)
|
||||
except requests.RequestException as exc:
|
||||
raise RuntimeError(
|
||||
f"Browserbase API connection failed: {exc}"
|
||||
) from exc
|
||||
|
||||
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"{config['base_url']}/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:
|
||||
config = self._get_config_or_none()
|
||||
if config is None:
|
||||
logger.warning("Cannot emergency-cleanup Browserbase session %s — missing credentials", session_id)
|
||||
return
|
||||
try:
|
||||
requests.post(
|
||||
f"{config['base_url']}/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=5,
|
||||
)
|
||||
except Exception as e:
|
||||
logger.debug("Emergency cleanup failed for Browserbase session %s: %s", session_id, e)
|
||||
|
|
@ -1,112 +0,0 @@
|
|||
"""Firecrawl 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.firecrawl.dev"
|
||||
|
||||
|
||||
class FirecrawlProvider(CloudBrowserProvider):
|
||||
"""Firecrawl (https://firecrawl.dev) cloud browser backend."""
|
||||
|
||||
def provider_name(self) -> str:
|
||||
return "Firecrawl"
|
||||
|
||||
def is_configured(self) -> bool:
|
||||
return bool(os.environ.get("FIRECRAWL_API_KEY"))
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Session lifecycle
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
def _api_url(self) -> str:
|
||||
return os.environ.get("FIRECRAWL_API_URL", _BASE_URL)
|
||||
|
||||
def _headers(self) -> Dict[str, str]:
|
||||
api_key = os.environ.get("FIRECRAWL_API_KEY")
|
||||
if not api_key:
|
||||
raise ValueError(
|
||||
"FIRECRAWL_API_KEY environment variable is required. "
|
||||
"Get your key at https://firecrawl.dev"
|
||||
)
|
||||
return {
|
||||
"Content-Type": "application/json",
|
||||
"Authorization": f"Bearer {api_key}",
|
||||
}
|
||||
|
||||
def create_session(self, task_id: str) -> Dict[str, object]:
|
||||
ttl = int(os.environ.get("FIRECRAWL_BROWSER_TTL", "300"))
|
||||
|
||||
body: Dict[str, object] = {"ttl": ttl}
|
||||
|
||||
try:
|
||||
response = requests.post(
|
||||
f"{self._api_url()}/v2/browser",
|
||||
headers=self._headers(),
|
||||
json=body,
|
||||
timeout=30,
|
||||
)
|
||||
except requests.RequestException as exc:
|
||||
raise RuntimeError(
|
||||
f"Firecrawl API connection failed: {exc}"
|
||||
) from exc
|
||||
|
||||
if not response.ok:
|
||||
raise RuntimeError(
|
||||
f"Failed to create Firecrawl browser session: "
|
||||
f"{response.status_code} {response.text}"
|
||||
)
|
||||
|
||||
data = response.json()
|
||||
session_name = f"hermes_{task_id}_{uuid.uuid4().hex[:8]}"
|
||||
|
||||
logger.info("Created Firecrawl browser session %s", session_name)
|
||||
|
||||
return {
|
||||
"session_name": session_name,
|
||||
"bb_session_id": data["id"],
|
||||
"cdp_url": data["cdpUrl"],
|
||||
"features": {"firecrawl": True},
|
||||
}
|
||||
|
||||
def close_session(self, session_id: str) -> bool:
|
||||
try:
|
||||
response = requests.delete(
|
||||
f"{self._api_url()}/v2/browser/{session_id}",
|
||||
headers=self._headers(),
|
||||
timeout=10,
|
||||
)
|
||||
if response.status_code in {200, 201, 204}:
|
||||
logger.debug("Successfully closed Firecrawl session %s", session_id)
|
||||
return True
|
||||
else:
|
||||
logger.warning(
|
||||
"Failed to close Firecrawl session %s: HTTP %s - %s",
|
||||
session_id,
|
||||
response.status_code,
|
||||
response.text[:200],
|
||||
)
|
||||
return False
|
||||
except Exception as e:
|
||||
logger.error("Exception closing Firecrawl session %s: %s", session_id, e)
|
||||
return False
|
||||
|
||||
def emergency_cleanup(self, session_id: str) -> None:
|
||||
try:
|
||||
requests.delete(
|
||||
f"{self._api_url()}/v2/browser/{session_id}",
|
||||
headers=self._headers(),
|
||||
timeout=5,
|
||||
)
|
||||
except ValueError:
|
||||
logger.warning("Cannot emergency-cleanup Firecrawl session %s — missing credentials", session_id)
|
||||
except Exception as e:
|
||||
logger.debug("Emergency cleanup failed for Firecrawl session %s: %s", session_id, e)
|
||||
Loading…
Add table
Add a link
Reference in a new issue