Files
DATA 6de0bf9f5b 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.
2026-04-12 14:23:57 +02:00

150 lines
4.9 KiB
Python

import os
import threading
from pydantic import BaseModel, Field
_config_lock = threading.Lock()
class LangSmithTracingConfig(BaseModel):
"""Configuration for LangSmith tracing."""
enabled: bool = Field(...)
api_key: str | None = Field(...)
project: str = Field(...)
endpoint: str = Field(...)
@property
def is_configured(self) -> bool:
return self.enabled and bool(self.api_key)
def validate(self) -> None:
if self.enabled and not self.api_key:
raise ValueError("LangSmith tracing is enabled but LANGSMITH_API_KEY (or LANGCHAIN_API_KEY) is not set.")
class LangfuseTracingConfig(BaseModel):
"""Configuration for Langfuse tracing."""
enabled: bool = Field(...)
public_key: str | None = Field(...)
secret_key: str | None = Field(...)
host: str = Field(...)
@property
def is_configured(self) -> bool:
return self.enabled and bool(self.public_key) and bool(self.secret_key)
def validate(self) -> None:
if not self.enabled:
return
missing: list[str] = []
if not self.public_key:
missing.append("LANGFUSE_PUBLIC_KEY")
if not self.secret_key:
missing.append("LANGFUSE_SECRET_KEY")
if missing:
raise ValueError(f"Langfuse tracing is enabled but required settings are missing: {', '.join(missing)}")
class TracingConfig(BaseModel):
"""Tracing configuration for supported providers."""
langsmith: LangSmithTracingConfig = Field(...)
langfuse: LangfuseTracingConfig = Field(...)
@property
def is_configured(self) -> bool:
return bool(self.enabled_providers)
@property
def explicitly_enabled_providers(self) -> list[str]:
enabled: list[str] = []
if self.langsmith.enabled:
enabled.append("langsmith")
if self.langfuse.enabled:
enabled.append("langfuse")
return enabled
@property
def enabled_providers(self) -> list[str]:
enabled: list[str] = []
if self.langsmith.is_configured:
enabled.append("langsmith")
if self.langfuse.is_configured:
enabled.append("langfuse")
return enabled
def validate_enabled(self) -> None:
self.langsmith.validate()
self.langfuse.validate()
_tracing_config: TracingConfig | None = None
_TRUTHY_VALUES = {"1", "true", "yes", "on"}
def _env_flag_preferred(*names: str) -> bool:
"""Return the boolean value of the first env var that is present and non-empty."""
for name in names:
value = os.environ.get(name)
if value is not None and value.strip():
return value.strip().lower() in _TRUTHY_VALUES
return False
def _first_env_value(*names: str) -> str | None:
"""Return the first non-empty environment value from candidate names."""
for name in names:
value = os.environ.get(name)
if value and value.strip():
return value.strip()
return None
def get_tracing_config() -> TracingConfig:
"""Get the current tracing configuration from environment variables."""
global _tracing_config
if _tracing_config is not None:
return _tracing_config
with _config_lock:
if _tracing_config is not None:
return _tracing_config
_tracing_config = TracingConfig(
langsmith=LangSmithTracingConfig(
enabled=_env_flag_preferred("LANGSMITH_TRACING", "LANGCHAIN_TRACING_V2", "LANGCHAIN_TRACING"),
api_key=_first_env_value("LANGSMITH_API_KEY", "LANGCHAIN_API_KEY"),
project=_first_env_value("LANGSMITH_PROJECT", "LANGCHAIN_PROJECT") or "deer-flow",
endpoint=_first_env_value("LANGSMITH_ENDPOINT", "LANGCHAIN_ENDPOINT") or "https://api.smith.langchain.com",
),
langfuse=LangfuseTracingConfig(
enabled=_env_flag_preferred("LANGFUSE_TRACING"),
public_key=_first_env_value("LANGFUSE_PUBLIC_KEY"),
secret_key=_first_env_value("LANGFUSE_SECRET_KEY"),
host=_first_env_value("LANGFUSE_BASE_URL") or "https://cloud.langfuse.com",
),
)
return _tracing_config
def get_enabled_tracing_providers() -> list[str]:
"""Return the configured tracing providers that are enabled and complete."""
return get_tracing_config().enabled_providers
def get_explicitly_enabled_tracing_providers() -> list[str]:
"""Return tracing providers explicitly enabled by config, even if incomplete."""
return get_tracing_config().explicitly_enabled_providers
def validate_enabled_tracing_providers() -> None:
"""Validate that any explicitly enabled providers are fully configured."""
get_tracing_config().validate_enabled()
def is_tracing_enabled() -> bool:
"""Check if any tracing provider is enabled and fully configured."""
return get_tracing_config().is_configured