Files
deer-flow/backend/packages/harness/deerflow/tools/tools.py
lhd 0091d9f071 feat(tools): add tool_search for deferred MCP tool loading (#1176)
* feat(tools): add tool_search for deferred MCP tool loading

When multiple MCP servers are enabled, total tool count can exceed 30-50,
causing context bloat and degraded tool selection accuracy. This adds a
deferred tool loading mechanism controlled by `tool_search.enabled` config.

- Add ToolSearchConfig with single `enabled` field
- Add DeferredToolRegistry with regex search (select:, +keyword, keyword)
- Add tool_search tool returning OpenAI-compatible function JSON
- Add DeferredToolFilterMiddleware to hide deferred schemas from bind_tools
- Add <available-deferred-tools> section to system prompt
- Enable MCP tool_name_prefix to prevent cross-server name collisions
- Add 34 unit tests covering registry, tool, prompt, and middleware

* fix: reset stale deferred registry and bump config_version

- Reset deferred registry upfront in get_available_tools() to prevent
  stale tool entries when MCP servers are disabled between calls
- Bump config_version to 2 for new tool_search config field

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix(tests): mock get_app_config in prompt section tests for CI

CI has no config.yaml, causing TestDeferredToolsPromptSection to fail
with FileNotFoundError. Add autouse fixture to mock get_app_config.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-17 20:43:55 +08:00

102 lines
4.2 KiB
Python

import logging
from langchain.tools import BaseTool
from deerflow.config import get_app_config
from deerflow.reflection import resolve_variable
from deerflow.tools.builtins import ask_clarification_tool, present_file_tool, task_tool, view_image_tool
from deerflow.tools.builtins.tool_search import reset_deferred_registry
logger = logging.getLogger(__name__)
BUILTIN_TOOLS = [
present_file_tool,
ask_clarification_tool,
]
SUBAGENT_TOOLS = [
task_tool,
# task_status_tool is no longer exposed to LLM (backend handles polling internally)
]
def get_available_tools(
groups: list[str] | None = None,
include_mcp: bool = True,
model_name: str | None = None,
subagent_enabled: bool = False,
) -> list[BaseTool]:
"""Get all available tools from config.
Note: MCP tools should be initialized at application startup using
`initialize_mcp_tools()` from deerflow.mcp module.
Args:
groups: Optional list of tool groups to filter by.
include_mcp: Whether to include tools from MCP servers (default: True).
model_name: Optional model name to determine if vision tools should be included.
subagent_enabled: Whether to include subagent tools (task, task_status).
Returns:
List of available tools.
"""
config = get_app_config()
loaded_tools = [resolve_variable(tool.use, BaseTool) for tool in config.tools if groups is None or tool.group in groups]
# Conditionally add tools based on config
builtin_tools = BUILTIN_TOOLS.copy()
# Add subagent tools only if enabled via runtime parameter
if subagent_enabled:
builtin_tools.extend(SUBAGENT_TOOLS)
logger.info("Including subagent tools (task)")
# If no model_name specified, use the first model (default)
if model_name is None and config.models:
model_name = config.models[0].name
# Add view_image_tool only if the model supports vision
model_config = config.get_model_config(model_name) if model_name else None
if model_config is not None and model_config.supports_vision:
builtin_tools.append(view_image_tool)
logger.info(f"Including view_image_tool for model '{model_name}' (supports_vision=True)")
# Get cached MCP tools if enabled
# NOTE: We use ExtensionsConfig.from_file() instead of config.extensions
# 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 loading MCP tools.
mcp_tools = []
# Reset deferred registry upfront to prevent stale state from previous calls
reset_deferred_registry()
if include_mcp:
try:
from deerflow.config.extensions_config import ExtensionsConfig
from deerflow.mcp.cache import get_cached_mcp_tools
extensions_config = ExtensionsConfig.from_file()
if extensions_config.get_enabled_mcp_servers():
mcp_tools = get_cached_mcp_tools()
if mcp_tools:
logger.info(f"Using {len(mcp_tools)} cached MCP tool(s)")
# When tool_search is enabled, register MCP tools in the
# deferred registry and add tool_search to builtin tools.
if config.tool_search.enabled:
from deerflow.tools.builtins.tool_search import DeferredToolRegistry, set_deferred_registry
from deerflow.tools.builtins.tool_search import tool_search as tool_search_tool
registry = DeferredToolRegistry()
for t in mcp_tools:
registry.register(t)
set_deferred_registry(registry)
builtin_tools.append(tool_search_tool)
logger.info(f"Tool search active: {len(mcp_tools)} tools deferred")
except ImportError:
logger.warning("MCP module not available. Install 'langchain-mcp-adapters' package to enable MCP tools.")
except Exception as e:
logger.error(f"Failed to get cached MCP tools: {e}")
logger.info(f"Total tools loaded: {len(loaded_tools)}, built-in tools: {len(builtin_tools)}, MCP tools: {len(mcp_tools)}")
return loaded_tools + builtin_tools + mcp_tools