Files
deer-flow/backend/packages/harness/deerflow/mcp/tools.py

114 lines
4.4 KiB
Python
Raw Normal View History

"""Load MCP tools using langchain-mcp-adapters."""
import asyncio
import atexit
import concurrent.futures
import logging
from collections.abc import Callable
from typing import Any
from langchain_core.tools import BaseTool
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 - **App** (`app/`): unpublished application code with import prefix `app.*`.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>
2026-03-14 22:55:52 +08:00
from deerflow.config.extensions_config import ExtensionsConfig
from deerflow.mcp.client import build_servers_config
from deerflow.mcp.oauth import build_oauth_tool_interceptor, get_initial_oauth_headers
logger = logging.getLogger(__name__)
# Global thread pool for sync tool invocation in async environments
_SYNC_TOOL_EXECUTOR = concurrent.futures.ThreadPoolExecutor(max_workers=10, thread_name_prefix="mcp-sync-tool")
# Register shutdown hook for the global executor
atexit.register(lambda: _SYNC_TOOL_EXECUTOR.shutdown(wait=False))
def _make_sync_tool_wrapper(coro: Callable[..., Any], tool_name: str) -> Callable[..., Any]:
"""Build a synchronous wrapper for an asynchronous tool coroutine.
Args:
coro: The tool's asynchronous coroutine.
tool_name: Name of the tool (for logging).
Returns:
A synchronous function that correctly handles nested event loops.
"""
def sync_wrapper(*args: Any, **kwargs: Any) -> Any:
try:
loop = asyncio.get_running_loop()
except RuntimeError:
loop = None
try:
if loop is not None and loop.is_running():
# Use global executor to avoid nested loop issues and improve performance
future = _SYNC_TOOL_EXECUTOR.submit(asyncio.run, coro(*args, **kwargs))
return future.result()
else:
return asyncio.run(coro(*args, **kwargs))
except Exception as e:
logger.error(f"Error invoking MCP tool '{tool_name}' via sync wrapper: {e}", exc_info=True)
raise
return sync_wrapper
async def get_mcp_tools() -> list[BaseTool]:
"""Get all tools from enabled MCP servers.
Returns:
List of LangChain tools from all enabled MCP servers.
"""
try:
from langchain_mcp_adapters.client import MultiServerMCPClient
except ImportError:
logger.warning("langchain-mcp-adapters not installed. Install it to enable MCP tools: pip install langchain-mcp-adapters")
return []
# NOTE: We use ExtensionsConfig.from_file() instead of get_extensions_config()
# to always read the latest configuration from disk. This ensures that changes
# made through the Gateway API (which runs in a separate process) are immediately
# reflected when initializing MCP tools.
extensions_config = ExtensionsConfig.from_file()
2026-01-20 13:57:36 +08:00
servers_config = build_servers_config(extensions_config)
if not servers_config:
logger.info("No enabled MCP servers configured")
return []
try:
# Create the multi-server MCP client
logger.info(f"Initializing MCP client with {len(servers_config)} server(s)")
# Inject initial OAuth headers for server connections (tool discovery/session init)
initial_oauth_headers = await get_initial_oauth_headers(extensions_config)
for server_name, auth_header in initial_oauth_headers.items():
if server_name not in servers_config:
continue
if servers_config[server_name].get("transport") in ("sse", "http"):
existing_headers = dict(servers_config[server_name].get("headers", {}))
existing_headers["Authorization"] = auth_header
servers_config[server_name]["headers"] = existing_headers
tool_interceptors = []
oauth_interceptor = build_oauth_tool_interceptor(extensions_config)
if oauth_interceptor is not None:
tool_interceptors.append(oauth_interceptor)
client = MultiServerMCPClient(servers_config, tool_interceptors=tool_interceptors, tool_name_prefix=True)
# Get all tools from all servers
tools = await client.get_tools()
logger.info(f"Successfully loaded {len(tools)} tool(s) from MCP servers")
# Patch tools to support sync invocation, as deerflow client streams synchronously
for tool in tools:
if getattr(tool, "func", None) is None and getattr(tool, "coroutine", None) is not None:
tool.func = _make_sync_tool_wrapper(tool.coroutine, tool.name)
return tools
except Exception as e:
logger.error(f"Failed to load MCP tools: {e}", exc_info=True)
return []