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.
102 lines
3.6 KiB
Python
102 lines
3.6 KiB
Python
"""Tests that /new (and its /reset alias) clears session-scoped overrides."""
|
|
from datetime import datetime
|
|
from types import SimpleNamespace
|
|
from unittest.mock import AsyncMock, MagicMock
|
|
|
|
import pytest
|
|
|
|
from gateway.config import GatewayConfig, Platform, PlatformConfig
|
|
from gateway.platforms.base import MessageEvent
|
|
from gateway.session import SessionEntry, SessionSource, build_session_key
|
|
|
|
|
|
def _make_source() -> SessionSource:
|
|
return SessionSource(
|
|
platform=Platform.TELEGRAM,
|
|
user_id="u1",
|
|
chat_id="c1",
|
|
user_name="tester",
|
|
chat_type="dm",
|
|
)
|
|
|
|
|
|
def _make_event(text: str) -> MessageEvent:
|
|
return MessageEvent(text=text, source=_make_source(), message_id="m1")
|
|
|
|
|
|
def _make_runner():
|
|
from gateway.run import GatewayRunner
|
|
|
|
runner = object.__new__(GatewayRunner)
|
|
runner.config = GatewayConfig(
|
|
platforms={Platform.TELEGRAM: PlatformConfig(enabled=True, token="***")}
|
|
)
|
|
adapter = MagicMock()
|
|
adapter.send = AsyncMock()
|
|
runner.adapters = {Platform.TELEGRAM: adapter}
|
|
runner._voice_mode = {}
|
|
runner.hooks = SimpleNamespace(emit=AsyncMock(), loaded_hooks=False)
|
|
runner._session_model_overrides = {}
|
|
runner._session_reasoning_overrides = {}
|
|
runner._pending_model_notes = {}
|
|
runner._background_tasks = set()
|
|
|
|
session_key = build_session_key(_make_source())
|
|
session_entry = SessionEntry(
|
|
session_key=session_key,
|
|
session_id="sess-1",
|
|
created_at=datetime.now(),
|
|
updated_at=datetime.now(),
|
|
platform=Platform.TELEGRAM,
|
|
chat_type="dm",
|
|
)
|
|
runner.session_store = MagicMock()
|
|
runner.session_store.get_or_create_session.return_value = session_entry
|
|
runner.session_store.reset_session.return_value = session_entry
|
|
runner.session_store._entries = {session_key: session_entry}
|
|
runner.session_store._generate_session_key.return_value = session_key
|
|
runner._running_agents = {}
|
|
runner._pending_messages = {}
|
|
runner._pending_approvals = {}
|
|
runner._session_db = None
|
|
runner._agent_cache_lock = None # disables _evict_cached_agent lock path
|
|
runner._is_user_authorized = lambda _source: True
|
|
runner._format_session_info = lambda: ""
|
|
|
|
return runner
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_new_command_only_clears_own_session():
|
|
"""/new must only clear the override for the session that triggered it."""
|
|
runner = _make_runner()
|
|
session_key = build_session_key(_make_source())
|
|
other_key = "other_session_key"
|
|
|
|
runner._session_model_overrides[session_key] = {
|
|
"model": "gpt-4o",
|
|
"provider": "openai",
|
|
"api_key": "sk-test",
|
|
"base_url": "",
|
|
"api_mode": "openai",
|
|
}
|
|
runner._session_model_overrides[other_key] = {
|
|
"model": "claude-sonnet-4-6",
|
|
"provider": "anthropic",
|
|
"api_key": "***",
|
|
"base_url": "",
|
|
"api_mode": "anthropic",
|
|
}
|
|
runner._session_reasoning_overrides[session_key] = {"enabled": True, "effort": "high"}
|
|
runner._session_reasoning_overrides[other_key] = {"enabled": True, "effort": "low"}
|
|
runner._pending_model_notes[session_key] = "[Note: switched to gpt-4o.]"
|
|
runner._pending_model_notes[other_key] = "[Note: switched to claude-sonnet-4-6.]"
|
|
|
|
await runner._handle_reset_command(_make_event("/new"))
|
|
|
|
assert session_key not in runner._session_model_overrides
|
|
assert other_key in runner._session_model_overrides
|
|
assert session_key not in runner._session_reasoning_overrides
|
|
assert other_key in runner._session_reasoning_overrides
|
|
assert session_key not in runner._pending_model_notes
|
|
assert other_key in runner._pending_model_notes
|