mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-30 19:09:28 +00:00
39975613b1
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.
109 lines
4 KiB
Python
109 lines
4 KiB
Python
"""Tests for MCP tool structuredContent preservation."""
|
|
|
|
import asyncio
|
|
import json
|
|
from types import SimpleNamespace
|
|
from unittest.mock import AsyncMock, MagicMock, patch
|
|
|
|
import pytest
|
|
|
|
from tools import mcp_tool
|
|
|
|
|
|
class _FakeContentBlock:
|
|
"""Minimal content block with .text and .type attributes."""
|
|
|
|
def __init__(self, text: str, block_type: str = "text"):
|
|
self.text = text
|
|
self.type = block_type
|
|
|
|
|
|
class _FakeCallToolResult:
|
|
"""Minimal CallToolResult stand-in.
|
|
|
|
Uses camelCase ``structuredContent`` / ``isError`` to match the real
|
|
MCP SDK Pydantic model (``mcp.types.CallToolResult``).
|
|
"""
|
|
|
|
def __init__(self, content, is_error=False, structuredContent=None):
|
|
self.content = content
|
|
self.isError = is_error
|
|
self.structuredContent = structuredContent
|
|
|
|
|
|
def _fake_run_on_mcp_loop(coro_or_factory, timeout=30):
|
|
coro = coro_or_factory() if callable(coro_or_factory) else coro_or_factory
|
|
"""Run an MCP coroutine directly in a fresh event loop."""
|
|
loop = asyncio.new_event_loop()
|
|
try:
|
|
# `_rpc_lock` must be created inside the loop that awaits it, or asyncio
|
|
# raises "attached to a different loop". Build it here and attach it to
|
|
# whatever fake server is currently registered under _servers.
|
|
async def _install_lock_and_run():
|
|
for srv in list(mcp_tool._servers.values()):
|
|
if getattr(srv, "_rpc_lock", None) is None:
|
|
srv._rpc_lock = asyncio.Lock()
|
|
return await coro
|
|
return loop.run_until_complete(_install_lock_and_run())
|
|
finally:
|
|
loop.close()
|
|
|
|
|
|
@pytest.fixture
|
|
def _patch_mcp_server():
|
|
"""Patch _servers and the MCP event loop so _make_tool_handler can run."""
|
|
fake_session = MagicMock()
|
|
# `_rpc_lock` is acquired by _make_tool_handler's call path (mcp_tool.py
|
|
# ~L2008) to serialize JSON-RPC against the server — build it inside the
|
|
# fresh loop that _fake_run_on_mcp_loop spins up, not at fixture import.
|
|
fake_server = SimpleNamespace(session=fake_session, _rpc_lock=None)
|
|
with patch.dict(mcp_tool._servers, {"test-server": fake_server}), \
|
|
patch("tools.mcp_tool._run_on_mcp_loop", side_effect=_fake_run_on_mcp_loop):
|
|
yield fake_session
|
|
|
|
|
|
class TestStructuredContentPreservation:
|
|
"""Ensure structuredContent from CallToolResult is forwarded."""
|
|
|
|
def test_text_only_result(self, _patch_mcp_server):
|
|
"""When no structuredContent, result is text-only (existing behaviour)."""
|
|
session = _patch_mcp_server
|
|
session.call_tool = AsyncMock(
|
|
return_value=_FakeCallToolResult(
|
|
content=[_FakeContentBlock("hello")],
|
|
)
|
|
)
|
|
handler = mcp_tool._make_tool_handler("test-server", "my-tool", 30.0)
|
|
raw = handler({})
|
|
data = json.loads(raw)
|
|
assert data == {"result": "hello"}
|
|
|
|
|
|
def test_structured_content_none_falls_back_to_text(self, _patch_mcp_server):
|
|
"""When structuredContent is explicitly None, fall back to text."""
|
|
session = _patch_mcp_server
|
|
session.call_tool = AsyncMock(
|
|
return_value=_FakeCallToolResult(
|
|
content=[_FakeContentBlock("done")],
|
|
structuredContent=None,
|
|
)
|
|
)
|
|
handler = mcp_tool._make_tool_handler("test-server", "my-tool", 30.0)
|
|
raw = handler({})
|
|
data = json.loads(raw)
|
|
assert data == {"result": "done"}
|
|
|
|
def test_empty_text_with_structured_content(self, _patch_mcp_server):
|
|
"""When content blocks are empty but structuredContent exists."""
|
|
session = _patch_mcp_server
|
|
payload = {"status": "ok", "data": [1, 2, 3]}
|
|
session.call_tool = AsyncMock(
|
|
return_value=_FakeCallToolResult(
|
|
content=[],
|
|
structuredContent=payload,
|
|
)
|
|
)
|
|
handler = mcp_tool._make_tool_handler("test-server", "my-tool", 30.0)
|
|
raw = handler({})
|
|
data = json.loads(raw)
|
|
assert data["result"] == payload
|