refactor(tool-search): consolidate MCP metadata tag and harden deferred-tool setup (#3370)

Follow-up to #3342 (deferred MCP tool loading). Maintainability cleanup plus
hardening of malformed/empty tool_search queries; no change to the deferral
mechanism or search ranking.

- Add deerflow/tools/mcp_metadata.py as the single source of truth for the
  "deerflow_mcp" tag (MCP_TOOL_METADATA_KEY + tag_mcp_tool + public
  is_mcp_tool). Removes the duplicated magic string and the private,
  cross-module _is_mcp_tool import.
- tool_search.search: never raise on model-generated input. Extract
  _compile_catalog_regex (shared compile-with-literal-fallback); return empty
  for empty/whitespace queries and a bare "+" instead of matching everything
  or raising IndexError.
- DeferredToolSetup: document the empty-vs-populated invariant.
- build_deferred_tool_setup: comment the two distinct empty-return branches.
- _assemble_deferred: add return type, rename local to deferred_setup, build
  the final list with an explicit append.
- Tests: use tag_mcp_tool instead of per-file tag helpers; cover empty and
  bare-"+" queries.
This commit is contained in:
AochenShen99
2026-06-05 15:21:41 +08:00
committed by GitHub
parent 28b1da2172
commit 2bbc7879fa
8 changed files with 123 additions and 47 deletions
@@ -18,7 +18,10 @@ middleware, and the async path inside ``TitleMiddleware``. Any new in-graph
``create_chat_model`` call must add to this list and pass the flag.
"""
from __future__ import annotations
import logging
from typing import TYPE_CHECKING
from langchain.agents import create_agent
from langchain.agents.middleware import AgentMiddleware
@@ -45,6 +48,11 @@ from deerflow.skills.tool_policy import filter_tools_by_skill_allowed_tools
from deerflow.skills.types import Skill
from deerflow.tracing import build_tracing_callbacks
if TYPE_CHECKING:
from langchain.tools import BaseTool
from deerflow.tools.builtins.tool_search import DeferredToolSetup
logger = logging.getLogger(__name__)
@@ -356,7 +364,7 @@ def _build_middlewares(
return middlewares
def _assemble_deferred(filtered_tools, *, enabled: bool):
def _assemble_deferred(filtered_tools: list[BaseTool], *, enabled: bool) -> tuple[list[BaseTool], DeferredToolSetup]:
"""Build the final tool list + deferred setup from a policy-filtered list.
Call AFTER tool-policy filtering so the deferred catalog never exposes a
@@ -364,13 +372,16 @@ def _assemble_deferred(filtered_tools, *, enabled: bool):
and MCP tools survived filtering but no deferred set was recovered, raise
rather than silently binding their full schemas to the model.
"""
from deerflow.tools.builtins.tool_search import _is_mcp_tool, build_deferred_tool_setup
from deerflow.tools.builtins.tool_search import build_deferred_tool_setup
from deerflow.tools.mcp_metadata import is_mcp_tool
setup = build_deferred_tool_setup(filtered_tools, enabled=enabled)
if enabled and not setup.deferred_names and any(_is_mcp_tool(t) for t in filtered_tools):
deferred_setup = build_deferred_tool_setup(filtered_tools, enabled=enabled)
if enabled and not deferred_setup.deferred_names and any(is_mcp_tool(t) for t in filtered_tools):
raise RuntimeError("tool_search enabled and MCP tools survived policy filtering, but no deferred set was recovered — refusing to bind MCP schemas (fail-closed).")
final_tools = list(filtered_tools) + ([setup.tool_search_tool] if setup.tool_search_tool else [])
return final_tools, setup
final_tools = list(filtered_tools)
if deferred_setup.tool_search_tool:
final_tools.append(deferred_setup.tool_search_tool)
return final_tools, deferred_setup
def _available_skill_names(agent_config, is_bootstrap: bool) -> set[str] | None: