mirror of
https://gitee.com/wanwujie/deer-flow
synced 2026-04-19 12:24:46 +08:00
refactor: split backend into harness (deerflow.*) and app (app.*) (#1131)
* refactor: extract shared utils to break harness→app cross-layer imports Move _validate_skill_frontmatter to src/skills/validation.py and CONVERTIBLE_EXTENSIONS + convert_file_to_markdown to src/utils/file_conversion.py. This eliminates the two reverse dependencies from client.py (harness layer) into gateway/routers/ (app layer), preparing for the harness/app package split. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * refactor: split backend/src into harness (deerflow.*) and app (app.*) Physically split the monolithic backend/src/ package into two layers: - **Harness** (`packages/harness/deerflow/`): publishable agent framework package with import prefix `deerflow.*`. Contains agents, sandbox, tools, models, MCP, skills, config, and all core infrastructure. - **App** (`app/`): unpublished application code with import prefix `app.*`. Contains gateway (FastAPI REST API) and channels (IM integrations). Key changes: - Move 13 harness modules to packages/harness/deerflow/ via git mv - Move gateway + channels to app/ via git mv - Rename all imports: src.* → deerflow.* (harness) / app.* (app layer) - Set up uv workspace with deerflow-harness as workspace member - Update langgraph.json, config.example.yaml, all scripts, Docker files - Add build-system (hatchling) to harness pyproject.toml - Add PYTHONPATH=. to gateway startup commands for app.* resolution - Update ruff.toml with known-first-party for import sorting - Update all documentation to reflect new directory structure Boundary rule enforced: harness code never imports from app. All 429 tests pass. Lint clean. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * chore: add harness→app boundary check test and update docs Add test_harness_boundary.py that scans all Python files in packages/harness/deerflow/ and fails if any `from app.*` or `import app.*` statement is found. This enforces the architectural rule that the harness layer never depends on the app layer. Update CLAUDE.md to document the harness/app split architecture, import conventions, and the boundary enforcement test. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat: add config versioning with auto-upgrade on startup When config.example.yaml schema changes, developers' local config.yaml files can silently become outdated. This adds a config_version field and auto-upgrade mechanism so breaking changes (like src.* → deerflow.* renames) are applied automatically before services start. - Add config_version: 1 to config.example.yaml - Add startup version check warning in AppConfig.from_file() - Add scripts/config-upgrade.sh with migration registry for value replacements - Add `make config-upgrade` target - Auto-run config-upgrade in serve.sh and start-daemon.sh before starting services - Add config error hints in service failure messages Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix comments * fix: update src.* import in test_sandbox_tools_security to deerflow.* Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: handle empty config and search parent dirs for config.example.yaml Address Copilot review comments on PR #1131: - Guard against yaml.safe_load() returning None for empty config files - Search parent directories for config.example.yaml instead of only looking next to config.yaml, fixing detection in common setups Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: correct skills root path depth and config_version type coercion - loader.py: fix get_skills_root_path() to use 5 parent levels (was 3) after harness split, file lives at packages/harness/deerflow/skills/ so parent×3 resolved to backend/packages/harness/ instead of backend/ - app_config.py: coerce config_version to int() before comparison in _check_config_version() to prevent TypeError when YAML stores value as string (e.g. config_version: "1") - tests: add regression tests for both fixes Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix: update test imports from src.* to deerflow.*/app.* after harness refactor Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
DanielWalnut
192
backend/app/gateway/app.py
Normal file
192
backend/app/gateway/app.py
Normal file
@@ -0,0 +1,192 @@
|
||||
import logging
|
||||
from collections.abc import AsyncGenerator
|
||||
from contextlib import asynccontextmanager
|
||||
|
||||
from fastapi import FastAPI
|
||||
|
||||
from app.gateway.config import get_gateway_config
|
||||
from app.gateway.routers import (
|
||||
agents,
|
||||
artifacts,
|
||||
channels,
|
||||
mcp,
|
||||
memory,
|
||||
models,
|
||||
skills,
|
||||
suggestions,
|
||||
uploads,
|
||||
)
|
||||
from deerflow.config.app_config import get_app_config
|
||||
|
||||
# Configure logging
|
||||
logging.basicConfig(
|
||||
level=logging.INFO,
|
||||
format="%(asctime)s - %(name)s - %(levelname)s - %(message)s",
|
||||
datefmt="%Y-%m-%d %H:%M:%S",
|
||||
)
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
@asynccontextmanager
|
||||
async def lifespan(app: FastAPI) -> AsyncGenerator[None, None]:
|
||||
"""Application lifespan handler."""
|
||||
|
||||
# Load config and check necessary environment variables at startup
|
||||
try:
|
||||
get_app_config()
|
||||
logger.info("Configuration loaded successfully")
|
||||
except Exception as e:
|
||||
error_msg = f"Failed to load configuration during gateway startup: {e}"
|
||||
logger.exception(error_msg)
|
||||
raise RuntimeError(error_msg) from e
|
||||
config = get_gateway_config()
|
||||
logger.info(f"Starting API Gateway on {config.host}:{config.port}")
|
||||
|
||||
# NOTE: MCP tools initialization is NOT done here because:
|
||||
# 1. Gateway doesn't use MCP tools - they are used by Agents in the LangGraph Server
|
||||
# 2. Gateway and LangGraph Server are separate processes with independent caches
|
||||
# MCP tools are lazily initialized in LangGraph Server when first needed
|
||||
|
||||
# Start IM channel service if any channels are configured
|
||||
try:
|
||||
from app.channels.service import start_channel_service
|
||||
|
||||
channel_service = await start_channel_service()
|
||||
logger.info("Channel service started: %s", channel_service.get_status())
|
||||
except Exception:
|
||||
logger.exception("No IM channels configured or channel service failed to start")
|
||||
|
||||
yield
|
||||
|
||||
# Stop channel service on shutdown
|
||||
try:
|
||||
from app.channels.service import stop_channel_service
|
||||
|
||||
await stop_channel_service()
|
||||
except Exception:
|
||||
logger.exception("Failed to stop channel service")
|
||||
logger.info("Shutting down API Gateway")
|
||||
|
||||
|
||||
def create_app() -> FastAPI:
|
||||
"""Create and configure the FastAPI application.
|
||||
|
||||
Returns:
|
||||
Configured FastAPI application instance.
|
||||
"""
|
||||
|
||||
app = FastAPI(
|
||||
title="DeerFlow API Gateway",
|
||||
description="""
|
||||
## DeerFlow API Gateway
|
||||
|
||||
API Gateway for DeerFlow - A LangGraph-based AI agent backend with sandbox execution capabilities.
|
||||
|
||||
### Features
|
||||
|
||||
- **Models Management**: Query and retrieve available AI models
|
||||
- **MCP Configuration**: Manage Model Context Protocol (MCP) server configurations
|
||||
- **Memory Management**: Access and manage global memory data for personalized conversations
|
||||
- **Skills Management**: Query and manage skills and their enabled status
|
||||
- **Artifacts**: Access thread artifacts and generated files
|
||||
- **Health Monitoring**: System health check endpoints
|
||||
|
||||
### Architecture
|
||||
|
||||
LangGraph requests are handled by nginx reverse proxy.
|
||||
This gateway provides custom endpoints for models, MCP configuration, skills, and artifacts.
|
||||
""",
|
||||
version="0.1.0",
|
||||
lifespan=lifespan,
|
||||
docs_url="/docs",
|
||||
redoc_url="/redoc",
|
||||
openapi_url="/openapi.json",
|
||||
openapi_tags=[
|
||||
{
|
||||
"name": "models",
|
||||
"description": "Operations for querying available AI models and their configurations",
|
||||
},
|
||||
{
|
||||
"name": "mcp",
|
||||
"description": "Manage Model Context Protocol (MCP) server configurations",
|
||||
},
|
||||
{
|
||||
"name": "memory",
|
||||
"description": "Access and manage global memory data for personalized conversations",
|
||||
},
|
||||
{
|
||||
"name": "skills",
|
||||
"description": "Manage skills and their configurations",
|
||||
},
|
||||
{
|
||||
"name": "artifacts",
|
||||
"description": "Access and download thread artifacts and generated files",
|
||||
},
|
||||
{
|
||||
"name": "uploads",
|
||||
"description": "Upload and manage user files for threads",
|
||||
},
|
||||
{
|
||||
"name": "agents",
|
||||
"description": "Create and manage custom agents with per-agent config and prompts",
|
||||
},
|
||||
{
|
||||
"name": "suggestions",
|
||||
"description": "Generate follow-up question suggestions for conversations",
|
||||
},
|
||||
{
|
||||
"name": "channels",
|
||||
"description": "Manage IM channel integrations (Feishu, Slack, Telegram)",
|
||||
},
|
||||
{
|
||||
"name": "health",
|
||||
"description": "Health check and system status endpoints",
|
||||
},
|
||||
],
|
||||
)
|
||||
|
||||
# CORS is handled by nginx - no need for FastAPI middleware
|
||||
|
||||
# Include routers
|
||||
# Models API is mounted at /api/models
|
||||
app.include_router(models.router)
|
||||
|
||||
# MCP API is mounted at /api/mcp
|
||||
app.include_router(mcp.router)
|
||||
|
||||
# Memory API is mounted at /api/memory
|
||||
app.include_router(memory.router)
|
||||
|
||||
# Skills API is mounted at /api/skills
|
||||
app.include_router(skills.router)
|
||||
|
||||
# Artifacts API is mounted at /api/threads/{thread_id}/artifacts
|
||||
app.include_router(artifacts.router)
|
||||
|
||||
# Uploads API is mounted at /api/threads/{thread_id}/uploads
|
||||
app.include_router(uploads.router)
|
||||
|
||||
# Agents API is mounted at /api/agents
|
||||
app.include_router(agents.router)
|
||||
|
||||
# Suggestions API is mounted at /api/threads/{thread_id}/suggestions
|
||||
app.include_router(suggestions.router)
|
||||
|
||||
# Channels API is mounted at /api/channels
|
||||
app.include_router(channels.router)
|
||||
|
||||
@app.get("/health", tags=["health"])
|
||||
async def health_check() -> dict:
|
||||
"""Health check endpoint.
|
||||
|
||||
Returns:
|
||||
Service health status information.
|
||||
"""
|
||||
return {"status": "healthy", "service": "deer-flow-gateway"}
|
||||
|
||||
return app
|
||||
|
||||
|
||||
# Create app instance for uvicorn
|
||||
app = create_app()
|
||||
Reference in New Issue
Block a user