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.
110 lines
3.4 KiB
Python
110 lines
3.4 KiB
Python
"""Regression tests for HERMES_HOME override propagation onto the MCP loop.
|
|
|
|
Tasks scheduled via run_coroutine_threadsafe are created inside the MCP
|
|
event-loop thread, so they copy THAT thread's context — not the scheduling
|
|
thread's. A per-request profile scope (dashboard ?profile= endpoints, e.g.
|
|
the MCP "Test server" probe) would silently vanish for anything resolving
|
|
get_hermes_home() inside the coroutine, most visibly OAuth token-store
|
|
paths. _run_on_mcp_loop now wraps scheduled coroutines with the caller's
|
|
override (mcp_tool._wrap_with_home_override).
|
|
"""
|
|
import os
|
|
|
|
import pytest
|
|
|
|
|
|
@pytest.fixture
|
|
def mcp_loop():
|
|
import tools.mcp_tool as mcp_tool
|
|
|
|
mcp_tool._ensure_mcp_loop()
|
|
yield mcp_tool
|
|
mcp_tool._stop_mcp_loop()
|
|
|
|
|
|
def test_override_propagates_to_mcp_loop(tmp_path, monkeypatch, mcp_loop):
|
|
from hermes_constants import (
|
|
get_hermes_home,
|
|
reset_hermes_home_override,
|
|
set_hermes_home_override,
|
|
)
|
|
|
|
process_home = tmp_path / "proc-home"
|
|
profile_home = tmp_path / "profile-home"
|
|
process_home.mkdir()
|
|
profile_home.mkdir()
|
|
monkeypatch.setenv("HERMES_HOME", str(process_home))
|
|
|
|
async def read_home():
|
|
return str(get_hermes_home())
|
|
|
|
# Unscoped: the loop task sees the process home.
|
|
assert mcp_loop._run_on_mcp_loop(read_home(), timeout=10) == str(process_home)
|
|
|
|
# Scoped: the caller's override must reach the loop task.
|
|
token = set_hermes_home_override(str(profile_home))
|
|
try:
|
|
assert mcp_loop._run_on_mcp_loop(read_home(), timeout=10) == str(profile_home)
|
|
# Factory form must be wrapped too.
|
|
assert mcp_loop._run_on_mcp_loop(lambda: read_home(), timeout=10) == str(
|
|
profile_home
|
|
)
|
|
finally:
|
|
reset_hermes_home_override(token)
|
|
|
|
# The loop thread's default context is untouched afterwards.
|
|
assert mcp_loop._run_on_mcp_loop(read_home(), timeout=10) == str(process_home)
|
|
|
|
|
|
def test_concurrent_scopes_do_not_interfere(tmp_path, monkeypatch, mcp_loop):
|
|
"""Two threads carrying DIFFERENT overrides scheduling onto the same
|
|
loop must each see their own home — the wrapper is task-local."""
|
|
import threading
|
|
|
|
from hermes_constants import (
|
|
get_hermes_home,
|
|
reset_hermes_home_override,
|
|
set_hermes_home_override,
|
|
)
|
|
|
|
process_home = tmp_path / "proc-home"
|
|
home_a = tmp_path / "profile-a"
|
|
home_b = tmp_path / "profile-b"
|
|
for h in (process_home, home_a, home_b):
|
|
h.mkdir()
|
|
monkeypatch.setenv("HERMES_HOME", str(process_home))
|
|
|
|
async def read_home():
|
|
return str(get_hermes_home())
|
|
|
|
results: dict = {}
|
|
|
|
def scoped_call(key, home):
|
|
token = set_hermes_home_override(str(home))
|
|
try:
|
|
results[key] = mcp_loop._run_on_mcp_loop(read_home(), timeout=10)
|
|
finally:
|
|
reset_hermes_home_override(token)
|
|
|
|
threads = [
|
|
threading.Thread(target=scoped_call, args=("a", home_a)),
|
|
threading.Thread(target=scoped_call, args=("b", home_b)),
|
|
]
|
|
for t in threads:
|
|
t.start()
|
|
for t in threads:
|
|
t.join(timeout=15)
|
|
|
|
assert results == {"a": str(home_a), "b": str(home_b)}
|
|
|
|
|
|
def test_wrap_is_noop_without_override(mcp_loop):
|
|
"""No active override → the coroutine passes through unwrapped."""
|
|
|
|
async def trivial():
|
|
return 42
|
|
|
|
coro = trivial()
|
|
wrapped = mcp_loop._wrap_with_home_override(coro)
|
|
assert wrapped is coro
|
|
coro.close()
|