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:
@@ -0,0 +1,9 @@
|
||||
from .async_provider import make_checkpointer
|
||||
from .provider import checkpointer_context, get_checkpointer, reset_checkpointer
|
||||
|
||||
__all__ = [
|
||||
"get_checkpointer",
|
||||
"reset_checkpointer",
|
||||
"checkpointer_context",
|
||||
"make_checkpointer",
|
||||
]
|
||||
@@ -0,0 +1,106 @@
|
||||
"""Async checkpointer factory.
|
||||
|
||||
Provides an **async context manager** for long-running async servers that need
|
||||
proper resource cleanup.
|
||||
|
||||
Supported backends: memory, sqlite, postgres.
|
||||
|
||||
Usage (e.g. FastAPI lifespan)::
|
||||
|
||||
from deerflow.agents.checkpointer.async_provider import make_checkpointer
|
||||
|
||||
async with make_checkpointer() as checkpointer:
|
||||
app.state.checkpointer = checkpointer # InMemorySaver if not configured
|
||||
|
||||
For sync usage see :mod:`deerflow.agents.checkpointer.provider`.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import asyncio
|
||||
import contextlib
|
||||
import logging
|
||||
from collections.abc import AsyncIterator
|
||||
|
||||
from langgraph.types import Checkpointer
|
||||
|
||||
from deerflow.agents.checkpointer.provider import (
|
||||
POSTGRES_CONN_REQUIRED,
|
||||
POSTGRES_INSTALL,
|
||||
SQLITE_INSTALL,
|
||||
)
|
||||
from deerflow.config.app_config import get_app_config
|
||||
from deerflow.runtime.store._sqlite_utils import ensure_sqlite_parent_dir, resolve_sqlite_conn_str
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Async factory
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
@contextlib.asynccontextmanager
|
||||
async def _async_checkpointer(config) -> AsyncIterator[Checkpointer]:
|
||||
"""Async context manager that constructs and tears down a checkpointer."""
|
||||
if config.type == "memory":
|
||||
from langgraph.checkpoint.memory import InMemorySaver
|
||||
|
||||
yield InMemorySaver()
|
||||
return
|
||||
|
||||
if config.type == "sqlite":
|
||||
try:
|
||||
from langgraph.checkpoint.sqlite.aio import AsyncSqliteSaver
|
||||
except ImportError as exc:
|
||||
raise ImportError(SQLITE_INSTALL) from exc
|
||||
|
||||
conn_str = resolve_sqlite_conn_str(config.connection_string or "store.db")
|
||||
await asyncio.to_thread(ensure_sqlite_parent_dir, conn_str)
|
||||
async with AsyncSqliteSaver.from_conn_string(conn_str) as saver:
|
||||
await saver.setup()
|
||||
yield saver
|
||||
return
|
||||
|
||||
if config.type == "postgres":
|
||||
try:
|
||||
from langgraph.checkpoint.postgres.aio import AsyncPostgresSaver
|
||||
except ImportError as exc:
|
||||
raise ImportError(POSTGRES_INSTALL) from exc
|
||||
|
||||
if not config.connection_string:
|
||||
raise ValueError(POSTGRES_CONN_REQUIRED)
|
||||
|
||||
async with AsyncPostgresSaver.from_conn_string(config.connection_string) as saver:
|
||||
await saver.setup()
|
||||
yield saver
|
||||
return
|
||||
|
||||
raise ValueError(f"Unknown checkpointer type: {config.type!r}")
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Public async context manager
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
@contextlib.asynccontextmanager
|
||||
async def make_checkpointer() -> AsyncIterator[Checkpointer]:
|
||||
"""Async context manager that yields a checkpointer for the caller's lifetime.
|
||||
Resources are opened on enter and closed on exit — no global state::
|
||||
|
||||
async with make_checkpointer() as checkpointer:
|
||||
app.state.checkpointer = checkpointer
|
||||
|
||||
Yields an ``InMemorySaver`` when no checkpointer is configured in *config.yaml*.
|
||||
"""
|
||||
|
||||
config = get_app_config()
|
||||
|
||||
if config.checkpointer is None:
|
||||
from langgraph.checkpoint.memory import InMemorySaver
|
||||
|
||||
yield InMemorySaver()
|
||||
return
|
||||
|
||||
async with _async_checkpointer(config.checkpointer) as saver:
|
||||
yield saver
|
||||
@@ -0,0 +1,191 @@
|
||||
"""Sync checkpointer factory.
|
||||
|
||||
Provides a **sync singleton** and a **sync context manager** for LangGraph
|
||||
graph compilation and CLI tools.
|
||||
|
||||
Supported backends: memory, sqlite, postgres.
|
||||
|
||||
Usage::
|
||||
|
||||
from deerflow.agents.checkpointer.provider import get_checkpointer, checkpointer_context
|
||||
|
||||
# Singleton — reused across calls, closed on process exit
|
||||
cp = get_checkpointer()
|
||||
|
||||
# One-shot — fresh connection, closed on block exit
|
||||
with checkpointer_context() as cp:
|
||||
graph.invoke(input, config={"configurable": {"thread_id": "1"}})
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import contextlib
|
||||
import logging
|
||||
from collections.abc import Iterator
|
||||
|
||||
from langgraph.types import Checkpointer
|
||||
|
||||
from deerflow.config.app_config import get_app_config
|
||||
from deerflow.config.checkpointer_config import CheckpointerConfig
|
||||
from deerflow.runtime.store._sqlite_utils import resolve_sqlite_conn_str
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Error message constants — imported by aio.provider too
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
SQLITE_INSTALL = "langgraph-checkpoint-sqlite is required for the SQLite checkpointer. Install it with: uv add langgraph-checkpoint-sqlite"
|
||||
POSTGRES_INSTALL = "langgraph-checkpoint-postgres is required for the PostgreSQL checkpointer. Install it with: uv add langgraph-checkpoint-postgres psycopg[binary] psycopg-pool"
|
||||
POSTGRES_CONN_REQUIRED = "checkpointer.connection_string is required for the postgres backend"
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Sync factory
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
@contextlib.contextmanager
|
||||
def _sync_checkpointer_cm(config: CheckpointerConfig) -> Iterator[Checkpointer]:
|
||||
"""Context manager that creates and tears down a sync checkpointer.
|
||||
|
||||
Returns a configured ``Checkpointer`` instance. Resource cleanup for any
|
||||
underlying connections or pools is handled by higher-level helpers in
|
||||
this module (such as the singleton factory or context manager); this
|
||||
function does not return a separate cleanup callback.
|
||||
"""
|
||||
if config.type == "memory":
|
||||
from langgraph.checkpoint.memory import InMemorySaver
|
||||
|
||||
logger.info("Checkpointer: using InMemorySaver (in-process, not persistent)")
|
||||
yield InMemorySaver()
|
||||
return
|
||||
|
||||
if config.type == "sqlite":
|
||||
try:
|
||||
from langgraph.checkpoint.sqlite import SqliteSaver
|
||||
except ImportError as exc:
|
||||
raise ImportError(SQLITE_INSTALL) from exc
|
||||
|
||||
conn_str = resolve_sqlite_conn_str(config.connection_string or "store.db")
|
||||
with SqliteSaver.from_conn_string(conn_str) as saver:
|
||||
saver.setup()
|
||||
logger.info("Checkpointer: using SqliteSaver (%s)", conn_str)
|
||||
yield saver
|
||||
return
|
||||
|
||||
if config.type == "postgres":
|
||||
try:
|
||||
from langgraph.checkpoint.postgres import PostgresSaver
|
||||
except ImportError as exc:
|
||||
raise ImportError(POSTGRES_INSTALL) from exc
|
||||
|
||||
if not config.connection_string:
|
||||
raise ValueError(POSTGRES_CONN_REQUIRED)
|
||||
|
||||
with PostgresSaver.from_conn_string(config.connection_string) as saver:
|
||||
saver.setup()
|
||||
logger.info("Checkpointer: using PostgresSaver")
|
||||
yield saver
|
||||
return
|
||||
|
||||
raise ValueError(f"Unknown checkpointer type: {config.type!r}")
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Sync singleton
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
_checkpointer: Checkpointer | None = None
|
||||
_checkpointer_ctx = None # open context manager keeping the connection alive
|
||||
|
||||
|
||||
def get_checkpointer() -> Checkpointer:
|
||||
"""Return the global sync checkpointer singleton, creating it on first call.
|
||||
|
||||
Returns an ``InMemorySaver`` when no checkpointer is configured in *config.yaml*.
|
||||
|
||||
Raises:
|
||||
ImportError: If the required package for the configured backend is not installed.
|
||||
ValueError: If ``connection_string`` is missing for a backend that requires it.
|
||||
"""
|
||||
global _checkpointer, _checkpointer_ctx
|
||||
|
||||
if _checkpointer is not None:
|
||||
return _checkpointer
|
||||
|
||||
# Ensure app config is loaded before checking checkpointer config
|
||||
# This prevents returning InMemorySaver when config.yaml actually has a checkpointer section
|
||||
# but hasn't been loaded yet
|
||||
from deerflow.config.app_config import _app_config
|
||||
from deerflow.config.checkpointer_config import get_checkpointer_config
|
||||
|
||||
config = get_checkpointer_config()
|
||||
|
||||
if config is None and _app_config is None:
|
||||
# Only load app config lazily when neither the app config nor an explicit
|
||||
# checkpointer config has been initialized yet. This keeps tests that
|
||||
# intentionally set the global checkpointer config isolated from any
|
||||
# ambient config.yaml on disk.
|
||||
try:
|
||||
get_app_config()
|
||||
except FileNotFoundError:
|
||||
# In test environments without config.yaml, this is expected.
|
||||
pass
|
||||
config = get_checkpointer_config()
|
||||
if config is None:
|
||||
from langgraph.checkpoint.memory import InMemorySaver
|
||||
|
||||
logger.info("Checkpointer: using InMemorySaver (in-process, not persistent)")
|
||||
_checkpointer = InMemorySaver()
|
||||
return _checkpointer
|
||||
|
||||
_checkpointer_ctx = _sync_checkpointer_cm(config)
|
||||
_checkpointer = _checkpointer_ctx.__enter__()
|
||||
|
||||
return _checkpointer
|
||||
|
||||
|
||||
def reset_checkpointer() -> None:
|
||||
"""Reset the sync singleton, forcing recreation on the next call.
|
||||
|
||||
Closes any open backend connections and clears the cached instance.
|
||||
Useful in tests or after a configuration change.
|
||||
"""
|
||||
global _checkpointer, _checkpointer_ctx
|
||||
if _checkpointer_ctx is not None:
|
||||
try:
|
||||
_checkpointer_ctx.__exit__(None, None, None)
|
||||
except Exception:
|
||||
logger.warning("Error during checkpointer cleanup", exc_info=True)
|
||||
_checkpointer_ctx = None
|
||||
_checkpointer = None
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Sync context manager
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
@contextlib.contextmanager
|
||||
def checkpointer_context() -> Iterator[Checkpointer]:
|
||||
"""Sync context manager that yields a checkpointer and cleans up on exit.
|
||||
|
||||
Unlike :func:`get_checkpointer`, this does **not** cache the instance —
|
||||
each ``with`` block creates and destroys its own connection. Use it in
|
||||
CLI scripts or tests where you want deterministic cleanup::
|
||||
|
||||
with checkpointer_context() as cp:
|
||||
graph.invoke(input, config={"configurable": {"thread_id": "1"}})
|
||||
|
||||
Yields an ``InMemorySaver`` when no checkpointer is configured in *config.yaml*.
|
||||
"""
|
||||
|
||||
config = get_app_config()
|
||||
if config.checkpointer is None:
|
||||
from langgraph.checkpoint.memory import InMemorySaver
|
||||
|
||||
yield InMemorySaver()
|
||||
return
|
||||
|
||||
with _sync_checkpointer_cm(config.checkpointer) as saver:
|
||||
yield saver
|
||||
Reference in New Issue
Block a user