mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-05-22 16:06:50 +00:00
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).
163 lines
4.4 KiB
Plaintext
163 lines
4.4 KiB
Plaintext
---
|
||
title: 集成指南
|
||
description: DeerFlow Harness 不仅仅是一个独立应用程序——它是一个可以导入并在你自己的后端、API 服务器、自动化系统或多 Agent 协调器中使用的 Python 库。
|
||
---
|
||
|
||
import { Callout, Cards } from "nextra/components";
|
||
|
||
# 集成指南
|
||
|
||
<Callout type="info" emoji="🔌">
|
||
DeerFlow Harness 可以嵌入任何 Python 应用程序。本指南涵盖在你自己的系统中将 DeerFlow 作为库使用的集成模式。
|
||
</Callout>
|
||
|
||
DeerFlow Harness 不仅仅是一个独立应用程序——它是一个可以导入并在你自己的后端、API 服务器、自动化系统或多 Agent 协调器中使用的 Python 库。
|
||
|
||
## 嵌入 DeerFlowClient
|
||
|
||
主要集成点是 `DeerFlowClient`。它封装了 LangGraph 运行时,并提供一个简洁的 API,用于在任何 Python 应用中发送消息和流式传输响应。
|
||
|
||
```python
|
||
from deerflow.client import DeerFlowClient
|
||
from deerflow.config import load_config
|
||
|
||
# 加载配置(读取 config.yaml 或 DEER_FLOW_CONFIG_PATH)
|
||
load_config()
|
||
|
||
client = DeerFlowClient()
|
||
```
|
||
|
||
客户端是线程安全的,设计为实例化一次并在请求之间复用。
|
||
|
||
## 异步流式传输
|
||
|
||
推荐的集成模式是异步流式传输。这让你可以在 Agent 生成响应时实时访问每个 token 和事件:
|
||
|
||
```python
|
||
import asyncio
|
||
|
||
async def run_agent(thread_id: str, user_message: str):
|
||
async for event in client.astream(
|
||
thread_id=thread_id,
|
||
message=user_message,
|
||
config={
|
||
"configurable": {
|
||
"model_name": "gpt-4o",
|
||
"subagent_enabled": True,
|
||
}
|
||
},
|
||
):
|
||
# 处理每个流式事件
|
||
yield event
|
||
|
||
# 在 FastAPI 处理器中:
|
||
# from fastapi.responses import StreamingResponse
|
||
# return StreamingResponse(run_agent(thread_id, message), media_type="text/event-stream")
|
||
```
|
||
|
||
## 非流式调用
|
||
|
||
对于批处理或只需要最终结果的场景:
|
||
|
||
```python
|
||
async def run_agent_sync(thread_id: str, user_message: str) -> dict:
|
||
result = await client.ainvoke(
|
||
thread_id=thread_id,
|
||
message=user_message,
|
||
)
|
||
return result
|
||
```
|
||
|
||
## 线程管理
|
||
|
||
线程表示持久化对话。使用唯一线程 ID 隔离不同用户会话:
|
||
|
||
```python
|
||
import uuid
|
||
|
||
# 新对话
|
||
thread_id = str(uuid.uuid4())
|
||
|
||
# 继续已有对话(相同 thread_id)
|
||
# 如果配置了检查点,Agent 将看到完整历史
|
||
await client.ainvoke(thread_id=existing_thread_id, message="后续问题")
|
||
```
|
||
|
||
## 自定义 Agent 配置
|
||
|
||
通过创建命名 Agent 配置并在运行时传入 `agent_name` 来构建领域特定 Agent:
|
||
|
||
```python
|
||
# agents/research-assistant/config.yaml 必须存在并包含技能和工具配置
|
||
|
||
result = await client.ainvoke(
|
||
thread_id=thread_id,
|
||
message=user_message,
|
||
config={
|
||
"configurable": {
|
||
"agent_name": "research-assistant",
|
||
"model_name": "gpt-4o",
|
||
}
|
||
},
|
||
)
|
||
```
|
||
|
||
## 与 FastAPI 集成
|
||
|
||
DeerFlow Gateway 本身是一个 FastAPI 应用程序。你可以将其作为子应用程序挂载:
|
||
|
||
```python
|
||
from fastapi import FastAPI
|
||
from deerflow.config import load_config
|
||
|
||
load_config()
|
||
|
||
app = FastAPI()
|
||
|
||
# 挂载 DeerFlow Gateway
|
||
from deerflow.app.gateway.main import app as gateway_app
|
||
app.mount("/deerflow", gateway_app)
|
||
```
|
||
|
||
或者在你自己的 FastAPI 路由中直接使用 `DeerFlowClient` 进行流式传输:
|
||
|
||
```python
|
||
from fastapi import FastAPI
|
||
from fastapi.responses import StreamingResponse
|
||
from deerflow.client import DeerFlowClient
|
||
|
||
app = FastAPI()
|
||
client = DeerFlowClient()
|
||
|
||
@app.post("/chat/{thread_id}")
|
||
async def chat(thread_id: str, body: dict):
|
||
async def generate():
|
||
async for event in client.astream(thread_id=thread_id, message=body["message"]):
|
||
yield f"data: {event}\n\n"
|
||
return StreamingResponse(generate(), media_type="text/event-stream")
|
||
```
|
||
|
||
## 嵌入模式下的配置
|
||
|
||
当嵌入到另一个应用程序时,显式设置配置路径以避免歧义:
|
||
|
||
```python
|
||
import os
|
||
os.environ["DEER_FLOW_CONFIG_PATH"] = "/path/to/my-deerflow-config.yaml"
|
||
|
||
from deerflow.config import load_config
|
||
load_config()
|
||
```
|
||
|
||
或直接传递路径:
|
||
|
||
```python
|
||
from deerflow.config import load_config
|
||
load_config(config_path="/path/to/my-deerflow-config.yaml")
|
||
```
|
||
|
||
<Cards num={2}>
|
||
<Cards.Card title="自定义与扩展" href="/docs/harness/customization" />
|
||
<Cards.Card title="配置" href="/docs/harness/configuration" />
|
||
</Cards>
|