hermes-agent/tests/tools/test_mcp_dynamic_discovery.py
Teknium 39975613b1
test: prune wave 2 + speed fixes — 28,106 → 19,757 test functions, suite wall 315s → 294s
Second, deeper pass over tools/gateway/hermes_cli plus first pass over
the trees wave 1 missed (acp, acp_adapter, skills, computer_use, docker,
dashboard, conformance, monitoring, secret_sources, hermes_state,
providers). Same rubric as wave 1 (AGENTS.md test policy); security,
alternation/caching invariants, issue-number regressions, and E2E kept.

Real test-quality fixes found and rooted out along the way:
- tests/tools/test_command_guards.py made real auxiliary-LLM HTTPS calls
  (DEFAULT_CONFIG smart-approval leaked in) — pinned approval
  mode=manual via autouse fixture: 17.4s → 0.4s.
- test_model_switch_custom_providers.py / test_user_providers_model_switch.py
  silently probed live provider catalogs (~2s/test) — stubbed
  cached_provider_model_ids/provider_model_ids/fetch_api_models.
- test_telegram_noise_filter.py: 15-platform copy-paste matrix over
  shared gateway.run logic → 3 representative platforms (55s → 3.9s).
- test_gateway_shutdown.py: stop()'s 5s interrupt-deadline loop spun on
  MagicMock agents — interrupt.side_effect now clears _running_agents
  (22s → 1.0s).
- test_gateway_inactivity_timeout.py poll-harness timings shrunk 3-5x
  (24s → 1.1s); test_mcp_stability.py backoff/SIGTERM-grace sleeps
  patched (15.4s → 2.5s); test_async_delegation.py negative-drain wait
  5s → 0.5s.
- test_telegram_init_deadline.py: loop-block margin restored to 1.0s
  with rationale comment — the watchdog-dump assertion needs the loop
  blocked well past deadline+grace under parallel load (flaked once in
  the 40-worker verification run at a 0.2s margin).

Verification: full hermetic suite via scripts/run_tests.sh —
2,438 files, 21,718 tests passed, 0 failed, 293.9s wall.
Suite totals vs original baseline: 46,820 → 19,757 test functions
(−57.8%), wall 583.5s → 293.9s (−50%), subprocess CPU 13,564s → 11,623s.
2026-07-29 13:39:40 -07:00

129 lines
5.1 KiB
Python

"""Tests for MCP dynamic tool discovery (notifications/tools/list_changed)."""
import asyncio
from types import SimpleNamespace
from unittest.mock import AsyncMock, MagicMock, patch
import pytest
from tools.mcp_tool import MCPServerTask, _register_server_tools
from tools.registry import ToolRegistry
def _make_mcp_tool(name: str, desc: str = ""):
return SimpleNamespace(name=name, description=desc, inputSchema=None)
class TestRegisterServerTools:
"""Tests for the extracted _register_server_tools helper."""
@pytest.fixture
def mock_registry(self):
return ToolRegistry()
def test_exposes_live_server_aliases(self, mock_registry):
"""Registered MCP tools are reachable via live raw-server aliases."""
server = MCPServerTask("my_srv")
server._tools = [_make_mcp_tool("my_tool", "desc")]
server.session = MagicMock()
from toolsets import resolve_toolset, validate_toolset
with patch("tools.registry.registry", mock_registry):
registered = _register_server_tools("my_srv", server, {})
assert "mcp__my_srv__my_tool" in registered
assert "mcp__my_srv__my_tool" in mock_registry.get_all_tool_names()
assert validate_toolset("my_srv") is True
assert "mcp__my_srv__my_tool" in resolve_toolset("my_srv")
class TestRefreshTools:
"""Tests for MCPServerTask._refresh_tools nuke-and-repave cycle."""
@pytest.fixture
def mock_registry(self):
return ToolRegistry()
@pytest.mark.asyncio
async def test_nuke_and_repave(self, mock_registry):
"""Old tools are removed and new tools registered on refresh."""
server = MCPServerTask("live_srv")
server._refresh_lock = asyncio.Lock()
server._config = {}
from toolsets import resolve_toolset
# Seed initial state: one old tool registered
mock_registry.register(
name="mcp__live_srv__old_tool", toolset="mcp-live_srv", schema={},
handler=lambda x: x, check_fn=lambda: True, is_async=False,
description="", emoji="",
)
server._registered_tool_names = ["mcp__live_srv__old_tool"]
# New tool list from server
new_tool = _make_mcp_tool("new_tool", "new behavior")
server.session = SimpleNamespace(
list_tools=AsyncMock(
return_value=SimpleNamespace(tools=[new_tool])
)
)
with patch("tools.registry.registry", mock_registry):
await server._refresh_tools()
assert "mcp__live_srv__old_tool" not in mock_registry.get_all_tool_names()
assert "mcp__live_srv__old_tool" not in resolve_toolset("live_srv")
assert "mcp__live_srv__new_tool" in mock_registry.get_all_tool_names()
assert "mcp__live_srv__new_tool" in resolve_toolset("live_srv")
assert server._registered_tool_names == ["mcp__live_srv__new_tool"]
class TestMessageHandler:
"""Tests for MCPServerTask._make_message_handler dispatch."""
@pytest.mark.asyncio
async def test_dispatches_tool_list_changed(self):
from tools.mcp_tool import _MCP_NOTIFICATION_TYPES
if not _MCP_NOTIFICATION_TYPES:
pytest.skip("MCP SDK ToolListChangedNotification not available")
from mcp.types import ServerNotification, ToolListChangedNotification
server = MCPServerTask("notif_srv")
# Product now schedules the refresh as a background task (see
# _schedule_tools_refresh in mcp_tool.py ~L918) rather than awaiting
# it directly, to avoid wedging the stdio JSON-RPC stream. Patch at
# the scheduler seam so we can still assert dispatch happened without
# reaching into asyncio.create_task internals.
with patch.object(MCPServerTask, "_schedule_tools_refresh") as mock_schedule:
handler = server._make_message_handler()
notification = ServerNotification(
root=ToolListChangedNotification(method="notifications/tools/list_changed")
)
await handler(notification)
mock_schedule.assert_called_once()
@pytest.mark.asyncio
async def test_ignores_exceptions_and_other_messages(self):
server = MCPServerTask("notif_srv")
with patch.object(MCPServerTask, "_schedule_tools_refresh") as mock_schedule:
handler = server._make_message_handler()
# Exceptions should not trigger refresh
await handler(RuntimeError("connection dead"))
# Unknown message types should not trigger refresh
await handler({"jsonrpc": "2.0", "result": "ok"})
mock_schedule.assert_not_called()
class TestDeregister:
"""Tests for ToolRegistry.deregister."""
def test_removes_tool(self):
reg = ToolRegistry()
reg.register(name="foo", toolset="ts1", schema={}, handler=lambda x: x)
assert "foo" in reg.get_all_tool_names()
reg.deregister("foo")
assert "foo" not in reg.get_all_tool_names()
def test_noop_for_unknown_tool(self):
reg = ToolRegistry()
reg.deregister("nonexistent") # Should not raise