greatmengqi
edf345cd72
- Freeze all config models (AppConfig + 15 sub-configs) with frozen=True - Purify from_file() — remove 9 load_*_from_dict() side-effect calls - Replace mtime/reload/push/pop machinery with single ContextVar + init_app_config() - Delete 10 sub-module globals and their getters/setters/loaders - Migrate 50+ consumers from get_*_config() to get_app_config().xxx - Expand DeerFlowContext: app_config + thread_id + agent_name (frozen dataclass) - Wire into Gateway runtime (worker.py) and DeerFlowClient via context= parameter - Remove sandbox_id from runtime.context — flows through ThreadState.sandbox only - Middleware/tools access runtime.context directly via Runtime[DeerFlowContext] generic - resolve_context() retained at server entry points for LangGraph Server fallback
96 lines
3.3 KiB
Python
96 lines
3.3 KiB
Python
import logging
|
|
from typing import NotRequired, override
|
|
|
|
from langchain.agents import AgentState
|
|
from langchain.agents.middleware import AgentMiddleware
|
|
from langgraph.runtime import Runtime
|
|
|
|
from deerflow.agents.thread_state import ThreadDataState
|
|
from deerflow.config.deer_flow_context import DeerFlowContext
|
|
from deerflow.config.paths import Paths, get_paths
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
class ThreadDataMiddlewareState(AgentState):
|
|
"""Compatible with the `ThreadState` schema."""
|
|
|
|
thread_data: NotRequired[ThreadDataState | None]
|
|
|
|
|
|
class ThreadDataMiddleware(AgentMiddleware[ThreadDataMiddlewareState]):
|
|
"""Create thread data directories for each thread execution.
|
|
|
|
Creates the following directory structure:
|
|
- {base_dir}/threads/{thread_id}/user-data/workspace
|
|
- {base_dir}/threads/{thread_id}/user-data/uploads
|
|
- {base_dir}/threads/{thread_id}/user-data/outputs
|
|
|
|
Lifecycle Management:
|
|
- With lazy_init=True (default): Only compute paths, directories created on-demand
|
|
- With lazy_init=False: Eagerly create directories in before_agent()
|
|
"""
|
|
|
|
state_schema = ThreadDataMiddlewareState
|
|
|
|
def __init__(self, base_dir: str | None = None, lazy_init: bool = True):
|
|
"""Initialize the middleware.
|
|
|
|
Args:
|
|
base_dir: Base directory for thread data. Defaults to Paths resolution.
|
|
lazy_init: If True, defer directory creation until needed.
|
|
If False, create directories eagerly in before_agent().
|
|
Default is True for optimal performance.
|
|
"""
|
|
super().__init__()
|
|
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]:
|
|
"""Get the paths for a thread's data directories.
|
|
|
|
Args:
|
|
thread_id: The thread ID.
|
|
|
|
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)),
|
|
}
|
|
|
|
def _create_thread_directories(self, thread_id: str) -> dict[str, str]:
|
|
"""Create the thread data directories.
|
|
|
|
Args:
|
|
thread_id: The thread ID.
|
|
|
|
Returns:
|
|
Dictionary with the created directory paths.
|
|
"""
|
|
self._paths.ensure_thread_dirs(thread_id)
|
|
return self._get_thread_paths(thread_id)
|
|
|
|
@override
|
|
def before_agent(self, state: ThreadDataMiddlewareState, runtime: Runtime[DeerFlowContext]) -> dict | None:
|
|
thread_id = runtime.context.thread_id
|
|
|
|
if not thread_id:
|
|
raise ValueError("Thread ID is required in runtime context or config.configurable")
|
|
|
|
if self._lazy_init:
|
|
# Lazy initialization: only compute paths, don't create directories
|
|
paths = self._get_thread_paths(thread_id)
|
|
else:
|
|
# Eager initialization: create directories immediately
|
|
paths = self._create_thread_directories(thread_id)
|
|
logger.debug("Created thread data directories for thread %s", thread_id)
|
|
|
|
return {
|
|
"thread_data": {
|
|
**paths,
|
|
}
|
|
}
|