Initial commit: hardened DeerFlow factory
Vendored deer-flow upstream (bytedance/deer-flow) plus prompt-injection hardening: - New deerflow.security package: content_delimiter, html_cleaner, sanitizer (8 layers — invisible chars, control chars, symbols, NFC, PUA, tag chars, horizontal whitespace collapse with newline/tab preservation, length cap) - New deerflow.community.searx package: web_search, web_fetch, image_search backed by a private SearX instance, every external string sanitized and wrapped in <<<EXTERNAL_UNTRUSTED_CONTENT>>> delimiters - All native community web providers (ddg_search, tavily, exa, firecrawl, jina_ai, infoquest, image_search) replaced with hard-fail stubs that raise NativeWebToolDisabledError at import time, so a misconfigured tool.use path fails loud rather than silently falling back to unsanitized output - Native client back-doors (jina_client.py, infoquest_client.py) stubbed too - Native-tool tests quarantined under tests/_disabled_native/ (collect_ignore_glob via local conftest.py) - Sanitizer Layer 7 fix: only collapse horizontal whitespace, preserve newlines and tabs so list/table structure survives - Hardened runtime config.yaml references only the searx-backed tools - Factory overlay (backend/) kept in sync with deer-flow tree as a reference / source See HARDENING.md for the full audit trail and verification steps.
This commit is contained in:
200
deer-flow/backend/app/channels/service.py
Normal file
200
deer-flow/backend/app/channels/service.py
Normal file
@@ -0,0 +1,200 @@
|
||||
"""ChannelService — manages the lifecycle of all IM channels."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
import os
|
||||
from typing import Any
|
||||
|
||||
from app.channels.base import Channel
|
||||
from app.channels.manager import DEFAULT_GATEWAY_URL, DEFAULT_LANGGRAPH_URL, ChannelManager
|
||||
from app.channels.message_bus import MessageBus
|
||||
from app.channels.store import ChannelStore
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
# Channel name → import path for lazy loading
|
||||
_CHANNEL_REGISTRY: dict[str, str] = {
|
||||
"discord": "app.channels.discord:DiscordChannel",
|
||||
"feishu": "app.channels.feishu:FeishuChannel",
|
||||
"slack": "app.channels.slack:SlackChannel",
|
||||
"telegram": "app.channels.telegram:TelegramChannel",
|
||||
"wechat": "app.channels.wechat:WechatChannel",
|
||||
"wecom": "app.channels.wecom:WeComChannel",
|
||||
}
|
||||
|
||||
_CHANNELS_LANGGRAPH_URL_ENV = "DEER_FLOW_CHANNELS_LANGGRAPH_URL"
|
||||
_CHANNELS_GATEWAY_URL_ENV = "DEER_FLOW_CHANNELS_GATEWAY_URL"
|
||||
|
||||
|
||||
def _resolve_service_url(config: dict[str, Any], config_key: str, env_key: str, default: str) -> str:
|
||||
value = config.pop(config_key, None)
|
||||
if isinstance(value, str) and value.strip():
|
||||
return value
|
||||
env_value = os.getenv(env_key, "").strip()
|
||||
if env_value:
|
||||
return env_value
|
||||
return default
|
||||
|
||||
|
||||
class ChannelService:
|
||||
"""Manages the lifecycle of all configured IM channels.
|
||||
|
||||
Reads configuration from ``config.yaml`` under the ``channels`` key,
|
||||
instantiates enabled channels, and starts the ChannelManager dispatcher.
|
||||
"""
|
||||
|
||||
def __init__(self, channels_config: dict[str, Any] | None = None) -> None:
|
||||
self.bus = MessageBus()
|
||||
self.store = ChannelStore()
|
||||
config = dict(channels_config or {})
|
||||
langgraph_url = _resolve_service_url(config, "langgraph_url", _CHANNELS_LANGGRAPH_URL_ENV, DEFAULT_LANGGRAPH_URL)
|
||||
gateway_url = _resolve_service_url(config, "gateway_url", _CHANNELS_GATEWAY_URL_ENV, DEFAULT_GATEWAY_URL)
|
||||
default_session = config.pop("session", None)
|
||||
channel_sessions = {name: channel_config.get("session") for name, channel_config in config.items() if isinstance(channel_config, dict)}
|
||||
self.manager = ChannelManager(
|
||||
bus=self.bus,
|
||||
store=self.store,
|
||||
langgraph_url=langgraph_url,
|
||||
gateway_url=gateway_url,
|
||||
default_session=default_session if isinstance(default_session, dict) else None,
|
||||
channel_sessions=channel_sessions,
|
||||
)
|
||||
self._channels: dict[str, Any] = {} # name -> Channel instance
|
||||
self._config = config
|
||||
self._running = False
|
||||
|
||||
@classmethod
|
||||
def from_app_config(cls) -> ChannelService:
|
||||
"""Create a ChannelService from the application config."""
|
||||
from deerflow.config.app_config import get_app_config
|
||||
|
||||
config = get_app_config()
|
||||
channels_config = {}
|
||||
# extra fields are allowed by AppConfig (extra="allow")
|
||||
extra = config.model_extra or {}
|
||||
if "channels" in extra:
|
||||
channels_config = extra["channels"]
|
||||
return cls(channels_config=channels_config)
|
||||
|
||||
async def start(self) -> None:
|
||||
"""Start the manager and all enabled channels."""
|
||||
if self._running:
|
||||
return
|
||||
|
||||
await self.manager.start()
|
||||
|
||||
for name, channel_config in self._config.items():
|
||||
if not isinstance(channel_config, dict):
|
||||
continue
|
||||
if not channel_config.get("enabled", False):
|
||||
logger.info("Channel %s is disabled, skipping", name)
|
||||
continue
|
||||
|
||||
await self._start_channel(name, channel_config)
|
||||
|
||||
self._running = True
|
||||
logger.info("ChannelService started with channels: %s", list(self._channels.keys()))
|
||||
|
||||
async def stop(self) -> None:
|
||||
"""Stop all channels and the manager."""
|
||||
for name, channel in list(self._channels.items()):
|
||||
try:
|
||||
await channel.stop()
|
||||
logger.info("Channel %s stopped", name)
|
||||
except Exception:
|
||||
logger.exception("Error stopping channel %s", name)
|
||||
self._channels.clear()
|
||||
|
||||
await self.manager.stop()
|
||||
self._running = False
|
||||
logger.info("ChannelService stopped")
|
||||
|
||||
async def restart_channel(self, name: str) -> bool:
|
||||
"""Restart a specific channel. Returns True if successful."""
|
||||
if name in self._channels:
|
||||
try:
|
||||
await self._channels[name].stop()
|
||||
except Exception:
|
||||
logger.exception("Error stopping channel %s for restart", name)
|
||||
del self._channels[name]
|
||||
|
||||
config = self._config.get(name)
|
||||
if not config or not isinstance(config, dict):
|
||||
logger.warning("No config for channel %s", name)
|
||||
return False
|
||||
|
||||
return await self._start_channel(name, config)
|
||||
|
||||
async def _start_channel(self, name: str, config: dict[str, Any]) -> bool:
|
||||
"""Instantiate and start a single channel."""
|
||||
import_path = _CHANNEL_REGISTRY.get(name)
|
||||
if not import_path:
|
||||
logger.warning("Unknown channel type: %s", name)
|
||||
return False
|
||||
|
||||
try:
|
||||
from deerflow.reflection import resolve_class
|
||||
|
||||
channel_cls = resolve_class(import_path, base_class=None)
|
||||
except Exception:
|
||||
logger.exception("Failed to import channel class for %s", name)
|
||||
return False
|
||||
|
||||
try:
|
||||
channel = channel_cls(bus=self.bus, config=config)
|
||||
await channel.start()
|
||||
self._channels[name] = channel
|
||||
logger.info("Channel %s started", name)
|
||||
return True
|
||||
except Exception:
|
||||
logger.exception("Failed to start channel %s", name)
|
||||
return False
|
||||
|
||||
def get_status(self) -> dict[str, Any]:
|
||||
"""Return status information for all channels."""
|
||||
channels_status = {}
|
||||
for name in _CHANNEL_REGISTRY:
|
||||
config = self._config.get(name, {})
|
||||
enabled = isinstance(config, dict) and config.get("enabled", False)
|
||||
running = name in self._channels and self._channels[name].is_running
|
||||
channels_status[name] = {
|
||||
"enabled": enabled,
|
||||
"running": running,
|
||||
}
|
||||
return {
|
||||
"service_running": self._running,
|
||||
"channels": channels_status,
|
||||
}
|
||||
|
||||
def get_channel(self, name: str) -> Channel | None:
|
||||
"""Return a running channel instance by name when available."""
|
||||
return self._channels.get(name)
|
||||
|
||||
|
||||
# -- singleton access -------------------------------------------------------
|
||||
|
||||
_channel_service: ChannelService | None = None
|
||||
|
||||
|
||||
def get_channel_service() -> ChannelService | None:
|
||||
"""Get the singleton ChannelService instance (if started)."""
|
||||
return _channel_service
|
||||
|
||||
|
||||
async def start_channel_service() -> ChannelService:
|
||||
"""Create and start the global ChannelService from app config."""
|
||||
global _channel_service
|
||||
if _channel_service is not None:
|
||||
return _channel_service
|
||||
_channel_service = ChannelService.from_app_config()
|
||||
await _channel_service.start()
|
||||
return _channel_service
|
||||
|
||||
|
||||
async def stop_channel_service() -> None:
|
||||
"""Stop the global ChannelService."""
|
||||
global _channel_service
|
||||
if _channel_service is not None:
|
||||
await _channel_service.stop()
|
||||
_channel_service = None
|
||||
Reference in New Issue
Block a user