mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-05-21 23:46:50 +00:00
greatmengqi
3e6a34297d
Squashes 25 PR commits onto current main. AppConfig becomes a pure value object with no ambient lookup. Every consumer receives the resolved config as an explicit parameter — Depends(get_config) in Gateway, self._app_config in DeerFlowClient, runtime.context.app_config in agent runs, AppConfig.from_file() at the LangGraph Server registration boundary. Phase 1 — frozen data + typed context - All config models (AppConfig, MemoryConfig, DatabaseConfig, …) become frozen=True; no sub-module globals. - AppConfig.from_file() is pure (no side-effect singleton loaders). - Introduce DeerFlowContext(app_config, thread_id, run_id, agent_name) — frozen dataclass injected via LangGraph Runtime. - Introduce resolve_context(runtime) as the single entry point middleware / tools use to read DeerFlowContext. Phase 2 — pure explicit parameter passing - Gateway: app.state.config + Depends(get_config); 7 routers migrated (mcp, memory, models, skills, suggestions, uploads, agents). - DeerFlowClient: __init__(config=...) captures config locally. - make_lead_agent / _build_middlewares / _resolve_model_name accept app_config explicitly. - RunContext.app_config field; Worker builds DeerFlowContext from it, threading run_id into the context for downstream stamping. - Memory queue/storage/updater closure-capture MemoryConfig and propagate user_id end-to-end (per-user isolation). - Sandbox/skills/community/factories/tools thread app_config. - resolve_context() rejects non-typed runtime.context. - Test suite migrated off AppConfig.current() monkey-patches. - AppConfig.current() classmethod deleted. Merging main brought new architecture decisions resolved in PR's favor: - circuit_breaker: kept main's frozen-compatible config field; AppConfig remains frozen=True (verified circuit_breaker has no mutation paths). - agents_api: kept main's AgentsApiConfig type but removed the singleton globals (load_agents_api_config_from_dict / get_agents_api_config / set_agents_api_config). 8 routes in agents.py now read via Depends(get_config). - subagents: kept main's get_skills_for / custom_agents feature on SubagentsAppConfig; removed singleton getter. registry.py now reads app_config.subagents directly. - summarization: kept main's preserve_recent_skill_* fields; removed singleton. - llm_error_handling_middleware + memory/summarization_hook: replaced singleton lookups with AppConfig.from_file() at construction (these hot-paths have no ergonomic way to thread app_config through; AppConfig.from_file is a pure load). - worker.py + thread_data_middleware.py: DeerFlowContext.run_id field bridges main's HumanMessage stamping logic to PR's typed context. Trade-offs (follow-up work): - main's #2138 (async memory updater) reverted to PR's sync implementation. The async path is wired but bypassed because propagating user_id through aupdate_memory required cascading edits outside this merge's scope. - tests/test_subagent_skills_config.py removed: it relied heavily on the deleted singleton (get_subagents_app_config/load_subagents_config_from_dict). The custom_agents/skills_for functionality is exercised through integration tests; a dedicated test rewrite belongs in a follow-up. Verification: backend test suite — 2560 passed, 4 skipped, 84 failures. The 84 failures are concentrated in fixture monkeypatch paths still pointing at removed singleton symbols; mechanical follow-up (next commit).
79 lines
3.1 KiB
Python
79 lines
3.1 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 SandboxState, ThreadDataState
|
|
from deerflow.config.deer_flow_context import DeerFlowContext
|
|
from deerflow.sandbox import get_sandbox_provider
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
class SandboxMiddlewareState(AgentState):
|
|
"""Compatible with the `ThreadState` schema."""
|
|
|
|
sandbox: NotRequired[SandboxState | None]
|
|
thread_data: NotRequired[ThreadDataState | None]
|
|
|
|
|
|
class SandboxMiddleware(AgentMiddleware[SandboxMiddlewareState]):
|
|
"""Create a sandbox environment and assign it to an agent.
|
|
|
|
Lifecycle Management:
|
|
- With lazy_init=True (default): Sandbox is acquired on first tool call
|
|
- With lazy_init=False: Sandbox is acquired on first agent invocation (before_agent)
|
|
- Sandbox is reused across multiple turns within the same thread
|
|
- Sandbox is NOT released after each agent call to avoid wasteful recreation
|
|
- Cleanup happens at application shutdown via SandboxProvider.shutdown()
|
|
"""
|
|
|
|
state_schema = SandboxMiddlewareState
|
|
|
|
def __init__(self, lazy_init: bool = True):
|
|
"""Initialize sandbox middleware.
|
|
|
|
Args:
|
|
lazy_init: If True, defer sandbox acquisition until first tool call.
|
|
If False, acquire sandbox eagerly in before_agent().
|
|
Default is True for optimal performance.
|
|
"""
|
|
super().__init__()
|
|
self._lazy_init = lazy_init
|
|
|
|
def _acquire_sandbox(self, thread_id: str, runtime: Runtime[DeerFlowContext]) -> str:
|
|
provider = get_sandbox_provider(runtime.context.app_config)
|
|
sandbox_id = provider.acquire(thread_id)
|
|
logger.info(f"Acquiring sandbox {sandbox_id}")
|
|
return sandbox_id
|
|
|
|
@override
|
|
def before_agent(self, state: SandboxMiddlewareState, runtime: Runtime[DeerFlowContext]) -> dict | None:
|
|
# Skip acquisition if lazy_init is enabled
|
|
if self._lazy_init:
|
|
return super().before_agent(state, runtime)
|
|
|
|
# Eager initialization (original behavior)
|
|
if "sandbox" not in state or state["sandbox"] is None:
|
|
thread_id = runtime.context.thread_id
|
|
if not thread_id:
|
|
return super().before_agent(state, runtime)
|
|
sandbox_id = self._acquire_sandbox(thread_id, runtime)
|
|
logger.info(f"Assigned sandbox {sandbox_id} to thread {thread_id}")
|
|
return {"sandbox": {"sandbox_id": sandbox_id}}
|
|
return super().before_agent(state, runtime)
|
|
|
|
@override
|
|
def after_agent(self, state: SandboxMiddlewareState, runtime: Runtime[DeerFlowContext]) -> dict | None:
|
|
sandbox = state.get("sandbox")
|
|
if sandbox is not None:
|
|
sandbox_id = sandbox["sandbox_id"]
|
|
logger.info(f"Releasing sandbox {sandbox_id}")
|
|
get_sandbox_provider(runtime.context.app_config).release(sandbox_id)
|
|
return None
|
|
|
|
# No sandbox to release
|
|
return super().after_agent(state, runtime)
|