mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-31 19:16:29 +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.
83 lines
3.1 KiB
Python
83 lines
3.1 KiB
Python
"""Tests for MCP server log notification handling (port of anomalyco/opencode#34529).
|
|
|
|
MCP servers can emit ``notifications/message`` logging notifications
|
|
(RFC 5424 syslog levels). The MCP SDK's default ``logging_callback``
|
|
silently discards them; Hermes now passes ``_make_logging_callback()``
|
|
to ``ClientSession`` so server-side diagnostics land in agent.log,
|
|
tagged with the server name.
|
|
"""
|
|
|
|
import logging
|
|
from types import SimpleNamespace
|
|
|
|
import pytest
|
|
|
|
from tools.mcp_tool import (
|
|
_MCP_LOG_LEVEL_MAP,
|
|
_MCP_LOGGING_CALLBACK_SUPPORTED,
|
|
MCPServerTask,
|
|
)
|
|
|
|
|
|
def _params(level="info", data="hello", logger_name=None):
|
|
return SimpleNamespace(level=level, data=data, logger=logger_name)
|
|
|
|
|
|
class TestLogLevelMap:
|
|
def test_all_mcp_levels_mapped(self):
|
|
# MCP spec (RFC 5424) defines these eight levels.
|
|
for lvl in ("debug", "info", "notice", "warning",
|
|
"error", "critical", "alert", "emergency"):
|
|
assert lvl in _MCP_LOG_LEVEL_MAP
|
|
|
|
def test_severity_ordering(self):
|
|
assert _MCP_LOG_LEVEL_MAP["debug"] == logging.DEBUG
|
|
assert _MCP_LOG_LEVEL_MAP["notice"] == logging.INFO
|
|
assert _MCP_LOG_LEVEL_MAP["warning"] == logging.WARNING
|
|
assert _MCP_LOG_LEVEL_MAP["emergency"] == logging.ERROR
|
|
|
|
|
|
class TestLoggingCallback:
|
|
@pytest.mark.asyncio
|
|
async def test_routes_to_hermes_logger_with_server_tag(self, caplog):
|
|
server = MCPServerTask("log_srv")
|
|
callback = server._make_logging_callback()
|
|
with caplog.at_level(logging.INFO, logger="tools.mcp_tool"):
|
|
await callback(_params(level="info", data="server started"))
|
|
assert any(
|
|
"MCP server log [log_srv]: server started" in rec.getMessage()
|
|
for rec in caplog.records
|
|
)
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_includes_sub_logger_name(self, caplog):
|
|
server = MCPServerTask("log_srv")
|
|
callback = server._make_logging_callback()
|
|
with caplog.at_level(logging.WARNING, logger="tools.mcp_tool"):
|
|
await callback(_params(level="warning", data="rate limited",
|
|
logger_name="http"))
|
|
assert any(
|
|
"MCP server log [log_srv/http]: rate limited" in rec.getMessage()
|
|
and rec.levelno == logging.WARNING
|
|
for rec in caplog.records
|
|
)
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_handler_never_raises(self):
|
|
server = MCPServerTask("log_srv")
|
|
callback = server._make_logging_callback()
|
|
# A params object missing every attribute must not blow up the
|
|
# SDK's notification dispatch loop.
|
|
await callback(object())
|
|
|
|
|
|
class TestSDKSupportGate:
|
|
def test_current_sdk_supports_logging_callback(self):
|
|
# The pinned MCP SDK in this repo supports logging_callback; if this
|
|
# starts failing after an SDK downgrade the feature silently degrades
|
|
# (by design), but we want to know.
|
|
import inspect
|
|
from mcp import ClientSession
|
|
expected = "logging_callback" in inspect.signature(ClientSession).parameters
|
|
assert _MCP_LOGGING_CALLBACK_SUPPORTED == expected
|