mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-30 19:09:28 +00:00
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.
106 lines
3.6 KiB
Python
106 lines
3.6 KiB
Python
"""Tests for gateway /verbose command (config-gated tool progress cycling)."""
|
|
|
|
from unittest.mock import AsyncMock, MagicMock
|
|
|
|
import pytest
|
|
import yaml
|
|
|
|
import gateway.run as gateway_run
|
|
from gateway.config import Platform
|
|
from gateway.platforms.base import MessageEvent
|
|
from gateway.session import SessionSource
|
|
|
|
|
|
def _make_event(text="/verbose", platform=Platform.TELEGRAM, user_id="12345", chat_id="67890"):
|
|
"""Build a MessageEvent for testing."""
|
|
source = SessionSource(
|
|
platform=platform,
|
|
user_id=user_id,
|
|
chat_id=chat_id,
|
|
user_name="testuser",
|
|
)
|
|
return MessageEvent(text=text, source=source)
|
|
|
|
|
|
def _make_runner():
|
|
"""Create a bare GatewayRunner without calling __init__."""
|
|
runner = object.__new__(gateway_run.GatewayRunner)
|
|
runner.adapters = {}
|
|
runner._ephemeral_system_prompt = ""
|
|
runner._prefill_messages = []
|
|
runner._reasoning_config = None
|
|
runner._show_reasoning = False
|
|
runner._provider_routing = {}
|
|
runner._fallback_model = None
|
|
runner._running_agents = {}
|
|
runner.hooks = MagicMock()
|
|
runner.hooks.emit = AsyncMock()
|
|
runner.hooks.loaded_hooks = []
|
|
runner._session_db = None
|
|
runner._get_or_create_gateway_honcho = lambda session_key: (None, None)
|
|
return runner
|
|
|
|
|
|
class TestVerboseCommand:
|
|
"""Tests for _handle_verbose_command in the gateway."""
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_disabled_by_default(self, tmp_path, monkeypatch):
|
|
"""When tool_progress_command is false, /verbose returns an info message."""
|
|
hermes_home = tmp_path / "hermes"
|
|
hermes_home.mkdir()
|
|
config_path = hermes_home / "config.yaml"
|
|
config_path.write_text("display:\n tool_progress: all\n", encoding="utf-8")
|
|
|
|
monkeypatch.setattr(gateway_run, "_hermes_home", hermes_home)
|
|
|
|
runner = _make_runner()
|
|
result = await runner._handle_verbose_command(_make_event())
|
|
|
|
assert "not enabled" in result.lower()
|
|
assert "tool_progress_command" in result
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_enabled_cycles_mode(self, tmp_path, monkeypatch):
|
|
"""When enabled, /verbose cycles tool_progress mode per-platform."""
|
|
hermes_home = tmp_path / "hermes"
|
|
hermes_home.mkdir()
|
|
config_path = hermes_home / "config.yaml"
|
|
config_path.write_text(
|
|
"display:\n tool_progress_command: true\n tool_progress: all\n",
|
|
encoding="utf-8",
|
|
)
|
|
|
|
monkeypatch.setattr(gateway_run, "_hermes_home", hermes_home)
|
|
|
|
runner = _make_runner()
|
|
result = await runner._handle_verbose_command(_make_event())
|
|
|
|
# all -> verbose
|
|
assert "VERBOSE" in result
|
|
assert "telegram" in result.lower() # per-platform feedback
|
|
|
|
# Verify config was saved to display.platforms.telegram
|
|
saved = yaml.safe_load(config_path.read_text(encoding="utf-8"))
|
|
assert saved["display"]["platforms"]["telegram"]["tool_progress"] == "verbose"
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_quoted_false_keeps_command_disabled(self, tmp_path, monkeypatch):
|
|
"""Quoted false must not enable the /verbose gateway command."""
|
|
hermes_home = tmp_path / "hermes"
|
|
hermes_home.mkdir()
|
|
config_path = hermes_home / "config.yaml"
|
|
config_path.write_text(
|
|
'display:\n tool_progress_command: "false"\n tool_progress: all\n',
|
|
encoding="utf-8",
|
|
)
|
|
|
|
monkeypatch.setattr(gateway_run, "_hermes_home", hermes_home)
|
|
|
|
runner = _make_runner()
|
|
result = await runner._handle_verbose_command(_make_event())
|
|
|
|
assert "not enabled" in result.lower()
|
|
assert "tool_progress_command" in result
|
|
|
|
|