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>
This commit is contained in:
lhd
2026-03-17 20:43:55 +08:00
committed by GitHub
parent f29db80be7
commit 0091d9f071
10 changed files with 721 additions and 26 deletions

View File

@@ -240,6 +240,11 @@ def _build_middlewares(config: RunnableConfig, model_name: str | None, agent_nam
if model_config is not None and model_config.supports_vision:
middlewares.append(ViewImageMiddleware())
# Add DeferredToolFilterMiddleware to hide deferred tool schemas from model binding
if app_config.tool_search.enabled:
from deerflow.agents.middlewares.deferred_tool_filter_middleware import DeferredToolFilterMiddleware
middlewares.append(DeferredToolFilterMiddleware())
# Add SubagentLimitMiddleware to truncate excess parallel task calls
subagent_enabled = config.get("configurable", {}).get("subagent_enabled", False)
if subagent_enabled:
@@ -314,13 +319,11 @@ def make_lead_agent(config: RunnableConfig):
if is_bootstrap:
# Special bootstrap agent with minimal prompt for initial custom agent creation flow
system_prompt = apply_prompt_template(subagent_enabled=subagent_enabled, max_concurrent_subagents=max_concurrent_subagents, available_skills=set(["bootstrap"]))
return create_agent(
model=create_chat_model(name=model_name, thinking_enabled=thinking_enabled),
tools=get_available_tools(model_name=model_name, subagent_enabled=subagent_enabled) + [setup_agent],
middleware=_build_middlewares(config, model_name=model_name),
system_prompt=system_prompt,
system_prompt=apply_prompt_template(subagent_enabled=subagent_enabled, max_concurrent_subagents=max_concurrent_subagents, available_skills=set(["bootstrap"])),
state_schema=ThreadState,
)