feat(isolation): wire user_id through all Paths and memory callsites

Pass user_id=get_effective_user_id() at every callsite that invokes
Paths methods or memory functions, enabling per-user filesystem isolation
throughout the harness and app layers.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
rayhpeng
2026-04-12 15:16:23 +08:00
parent 9af2f3e73c
commit 7ce9333200
24 changed files with 137 additions and 70 deletions
@@ -519,12 +519,13 @@ def _get_memory_context(agent_name: str | None = None) -> str:
try:
from deerflow.agents.memory import format_memory_for_injection, get_memory_data
from deerflow.config.memory_config import get_memory_config
from deerflow.runtime.user_context import get_effective_user_id
config = get_memory_config()
if not config.enabled or not config.injection_enabled:
return ""
memory_data = get_memory_data(agent_name)
memory_data = get_memory_data(agent_name, user_id=get_effective_user_id())
memory_content = format_memory_for_injection(memory_data, max_tokens=config.max_injection_tokens)
if not memory_content.strip():
@@ -8,6 +8,7 @@ from langgraph.runtime import Runtime
from deerflow.agents.thread_state import ThreadDataState
from deerflow.config.paths import Paths, get_paths
from deerflow.runtime.user_context import get_effective_user_id
logger = logging.getLogger(__name__)
@@ -46,32 +47,34 @@ class ThreadDataMiddleware(AgentMiddleware[ThreadDataMiddlewareState]):
self._paths = Paths(base_dir) if base_dir else get_paths()
self._lazy_init = lazy_init
def _get_thread_paths(self, thread_id: str) -> dict[str, str]:
def _get_thread_paths(self, thread_id: str, user_id: str | None = None) -> dict[str, str]:
"""Get the paths for a thread's data directories.
Args:
thread_id: The thread ID.
user_id: Optional user ID for per-user path isolation.
Returns:
Dictionary with workspace_path, uploads_path, and outputs_path.
"""
return {
"workspace_path": str(self._paths.sandbox_work_dir(thread_id)),
"uploads_path": str(self._paths.sandbox_uploads_dir(thread_id)),
"outputs_path": str(self._paths.sandbox_outputs_dir(thread_id)),
"workspace_path": str(self._paths.sandbox_work_dir(thread_id, user_id=user_id)),
"uploads_path": str(self._paths.sandbox_uploads_dir(thread_id, user_id=user_id)),
"outputs_path": str(self._paths.sandbox_outputs_dir(thread_id, user_id=user_id)),
}
def _create_thread_directories(self, thread_id: str) -> dict[str, str]:
def _create_thread_directories(self, thread_id: str, user_id: str | None = None) -> dict[str, str]:
"""Create the thread data directories.
Args:
thread_id: The thread ID.
user_id: Optional user ID for per-user path isolation.
Returns:
Dictionary with the created directory paths.
"""
self._paths.ensure_thread_dirs(thread_id)
return self._get_thread_paths(thread_id)
self._paths.ensure_thread_dirs(thread_id, user_id=user_id)
return self._get_thread_paths(thread_id, user_id=user_id)
@override
def before_agent(self, state: ThreadDataMiddlewareState, runtime: Runtime) -> dict | None:
@@ -84,12 +87,14 @@ class ThreadDataMiddleware(AgentMiddleware[ThreadDataMiddlewareState]):
if thread_id is None:
raise ValueError("Thread ID is required in runtime context or config.configurable")
user_id = get_effective_user_id()
if self._lazy_init:
# Lazy initialization: only compute paths, don't create directories
paths = self._get_thread_paths(thread_id)
paths = self._get_thread_paths(thread_id, user_id=user_id)
else:
# Eager initialization: create directories immediately
paths = self._create_thread_directories(thread_id)
paths = self._create_thread_directories(thread_id, user_id=user_id)
logger.debug("Created thread data directories for thread %s", thread_id)
return {
@@ -10,6 +10,7 @@ from langchain_core.messages import HumanMessage
from langgraph.runtime import Runtime
from deerflow.config.paths import Paths, get_paths
from deerflow.runtime.user_context import get_effective_user_id
from deerflow.utils.file_conversion import extract_outline
logger = logging.getLogger(__name__)
@@ -221,7 +222,7 @@ class UploadsMiddleware(AgentMiddleware[UploadsMiddlewareState]):
thread_id = get_config().get("configurable", {}).get("thread_id")
except RuntimeError:
pass # get_config() raises outside a runnable context (e.g. unit tests)
uploads_dir = self._paths.sandbox_uploads_dir(thread_id) if thread_id else None
uploads_dir = self._paths.sandbox_uploads_dir(thread_id, user_id=get_effective_user_id()) if thread_id else None
# Get newly uploaded files from the current message's additional_kwargs.files
new_files = self._files_from_kwargs(last_message, uploads_dir) or []
+7 -6
View File
@@ -40,6 +40,7 @@ from deerflow.config.app_config import get_app_config, reload_app_config
from deerflow.config.extensions_config import ExtensionsConfig, SkillStateConfig, get_extensions_config, reload_extensions_config
from deerflow.config.paths import get_paths
from deerflow.models import create_chat_model
from deerflow.runtime.user_context import get_effective_user_id
from deerflow.skills.installer import install_skill_from_archive
from deerflow.uploads.manager import (
claim_unique_filename,
@@ -769,19 +770,19 @@ class DeerFlowClient:
"""
from deerflow.agents.memory.updater import get_memory_data
return get_memory_data()
return get_memory_data(user_id=get_effective_user_id())
def export_memory(self) -> dict:
"""Export current memory data for backup or transfer."""
from deerflow.agents.memory.updater import get_memory_data
return get_memory_data()
return get_memory_data(user_id=get_effective_user_id())
def import_memory(self, memory_data: dict) -> dict:
"""Import and persist full memory data."""
from deerflow.agents.memory.updater import import_memory_data
return import_memory_data(memory_data)
return import_memory_data(memory_data, user_id=get_effective_user_id())
def get_model(self, name: str) -> dict | None:
"""Get a specific model's configuration by name.
@@ -956,13 +957,13 @@ class DeerFlowClient:
"""
from deerflow.agents.memory.updater import reload_memory_data
return reload_memory_data()
return reload_memory_data(user_id=get_effective_user_id())
def clear_memory(self) -> dict:
"""Clear all persisted memory data."""
from deerflow.agents.memory.updater import clear_memory_data
return clear_memory_data()
return clear_memory_data(user_id=get_effective_user_id())
def create_memory_fact(self, content: str, category: str = "context", confidence: float = 0.5) -> dict:
"""Create a single fact manually."""
@@ -1179,7 +1180,7 @@ class DeerFlowClient:
ValueError: If the path is invalid.
"""
try:
actual = get_paths().resolve_virtual_path(thread_id, path)
actual = get_paths().resolve_virtual_path(thread_id, path, user_id=get_effective_user_id())
except ValueError as exc:
if "traversal" in str(exc):
from deerflow.uploads.manager import PathTraversalError
@@ -27,6 +27,7 @@ except ImportError: # pragma: no cover - Windows fallback
from deerflow.config import get_app_config
from deerflow.config.paths import VIRTUAL_PATH_PREFIX, get_paths
from deerflow.runtime.user_context import get_effective_user_id
from deerflow.sandbox.sandbox import Sandbox
from deerflow.sandbox.sandbox_provider import SandboxProvider
@@ -260,15 +261,16 @@ class AioSandboxProvider(SandboxProvider):
mounted Docker socket (DooD), the host Docker daemon can resolve the paths.
"""
paths = get_paths()
paths.ensure_thread_dirs(thread_id)
user_id = get_effective_user_id()
paths.ensure_thread_dirs(thread_id, user_id=user_id)
return [
(paths.host_sandbox_work_dir(thread_id), f"{VIRTUAL_PATH_PREFIX}/workspace", False),
(paths.host_sandbox_uploads_dir(thread_id), f"{VIRTUAL_PATH_PREFIX}/uploads", False),
(paths.host_sandbox_outputs_dir(thread_id), f"{VIRTUAL_PATH_PREFIX}/outputs", False),
(paths.host_sandbox_work_dir(thread_id, user_id=user_id), f"{VIRTUAL_PATH_PREFIX}/workspace", False),
(paths.host_sandbox_uploads_dir(thread_id, user_id=user_id), f"{VIRTUAL_PATH_PREFIX}/uploads", False),
(paths.host_sandbox_outputs_dir(thread_id, user_id=user_id), f"{VIRTUAL_PATH_PREFIX}/outputs", False),
# ACP workspace: read-only inside the sandbox (lead agent reads results;
# the ACP subprocess writes from the host side, not from within the container).
(paths.host_acp_workspace_dir(thread_id), "/mnt/acp-workspace", True),
(paths.host_acp_workspace_dir(thread_id, user_id=user_id), "/mnt/acp-workspace", True),
]
@staticmethod
@@ -480,8 +482,9 @@ class AioSandboxProvider(SandboxProvider):
across multiple processes, preventing container-name conflicts.
"""
paths = get_paths()
paths.ensure_thread_dirs(thread_id)
lock_path = paths.thread_dir(thread_id) / f"{sandbox_id}.lock"
user_id = get_effective_user_id()
paths.ensure_thread_dirs(thread_id, user_id=user_id)
lock_path = paths.thread_dir(thread_id, user_id=user_id) / f"{sandbox_id}.lock"
with open(lock_path, "a", encoding="utf-8") as lock_file:
locked = False
@@ -200,8 +200,9 @@ def _get_acp_workspace_host_path(thread_id: str | None = None) -> str | None:
if thread_id is not None:
try:
from deerflow.config.paths import get_paths
from deerflow.runtime.user_context import get_effective_user_id
host_path = get_paths().acp_workspace_dir(thread_id)
host_path = get_paths().acp_workspace_dir(thread_id, user_id=get_effective_user_id())
if host_path.exists():
return str(host_path)
except Exception:
@@ -33,11 +33,12 @@ def _get_work_dir(thread_id: str | None) -> str:
An absolute physical filesystem path to use as the working directory.
"""
from deerflow.config.paths import get_paths
from deerflow.runtime.user_context import get_effective_user_id
paths = get_paths()
if thread_id:
try:
work_dir = paths.acp_workspace_dir(thread_id)
work_dir = paths.acp_workspace_dir(thread_id, user_id=get_effective_user_id())
except ValueError:
logger.warning("Invalid thread_id %r for ACP workspace, falling back to global", thread_id)
work_dir = paths.base_dir / "acp-workspace"
@@ -8,6 +8,7 @@ from langgraph.typing import ContextT
from deerflow.agents.thread_state import ThreadState
from deerflow.config.paths import VIRTUAL_PATH_PREFIX, get_paths
from deerflow.runtime.user_context import get_effective_user_id
OUTPUTS_VIRTUAL_PREFIX = f"{VIRTUAL_PATH_PREFIX}/outputs"
@@ -47,7 +48,7 @@ def _normalize_presented_filepath(
virtual_prefix = VIRTUAL_PATH_PREFIX.lstrip("/")
if stripped == virtual_prefix or stripped.startswith(virtual_prefix + "/"):
actual_path = get_paths().resolve_virtual_path(thread_id, filepath)
actual_path = get_paths().resolve_virtual_path(thread_id, filepath, user_id=get_effective_user_id())
else:
actual_path = Path(filepath).expanduser().resolve()
@@ -10,6 +10,7 @@ from pathlib import Path
from urllib.parse import quote
from deerflow.config.paths import VIRTUAL_PATH_PREFIX, get_paths
from deerflow.runtime.user_context import get_effective_user_id
class PathTraversalError(ValueError):
@@ -33,7 +34,7 @@ def validate_thread_id(thread_id: str) -> None:
def get_uploads_dir(thread_id: str) -> Path:
"""Return the uploads directory path for a thread (no side effects)."""
validate_thread_id(thread_id)
return get_paths().sandbox_uploads_dir(thread_id)
return get_paths().sandbox_uploads_dir(thread_id, user_id=get_effective_user_id())
def ensure_uploads_dir(thread_id: str) -> Path: