DATA
6de0bf9f5b
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.
55 lines
1.9 KiB
Python
55 lines
1.9 KiB
Python
from __future__ import annotations
|
|
|
|
from typing import Any
|
|
|
|
from deerflow.config import (
|
|
get_enabled_tracing_providers,
|
|
get_tracing_config,
|
|
validate_enabled_tracing_providers,
|
|
)
|
|
|
|
|
|
def _create_langsmith_tracer(config) -> Any:
|
|
from langchain_core.tracers.langchain import LangChainTracer
|
|
|
|
return LangChainTracer(project_name=config.project)
|
|
|
|
|
|
def _create_langfuse_handler(config) -> Any:
|
|
from langfuse import Langfuse
|
|
from langfuse.langchain import CallbackHandler as LangfuseCallbackHandler
|
|
|
|
# langfuse>=4 initializes project-specific credentials through the client
|
|
# singleton; the LangChain callback then attaches to that configured client.
|
|
Langfuse(
|
|
secret_key=config.secret_key,
|
|
public_key=config.public_key,
|
|
host=config.host,
|
|
)
|
|
return LangfuseCallbackHandler(public_key=config.public_key)
|
|
|
|
|
|
def build_tracing_callbacks() -> list[Any]:
|
|
"""Build callbacks for all explicitly enabled tracing providers."""
|
|
validate_enabled_tracing_providers()
|
|
enabled_providers = get_enabled_tracing_providers()
|
|
if not enabled_providers:
|
|
return []
|
|
|
|
tracing_config = get_tracing_config()
|
|
callbacks: list[Any] = []
|
|
|
|
for provider in enabled_providers:
|
|
if provider == "langsmith":
|
|
try:
|
|
callbacks.append(_create_langsmith_tracer(tracing_config.langsmith))
|
|
except Exception as exc: # pragma: no cover - exercised via tests with monkeypatch
|
|
raise RuntimeError(f"LangSmith tracing initialization failed: {exc}") from exc
|
|
elif provider == "langfuse":
|
|
try:
|
|
callbacks.append(_create_langfuse_handler(tracing_config.langfuse))
|
|
except Exception as exc: # pragma: no cover - exercised via tests with monkeypatch
|
|
raise RuntimeError(f"Langfuse tracing initialization failed: {exc}") from exc
|
|
|
|
return callbacks
|