hermes-agent/tests/gateway/test_fast_command.py
Teknium 39975613b1
test: prune wave 2 + speed fixes — 28,106 → 19,757 test functions, suite wall 315s → 294s
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.
2026-07-29 13:39:40 -07:00

172 lines
5.5 KiB
Python

"""Tests for gateway /fast support and Priority Processing routing."""
import sys
import threading
import types
from types import SimpleNamespace
from unittest.mock import AsyncMock, MagicMock, patch
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
class _CapturingAgent:
last_init = None
last_run = None
def __init__(self, *args, **kwargs):
type(self).last_init = dict(kwargs)
self.tools = []
def run_conversation(
self,
user_message,
conversation_history=None,
task_id=None,
persist_user_message=None,
persist_user_timestamp=None,
):
type(self).last_run = {
"user_message": user_message,
"conversation_history": conversation_history,
"task_id": task_id,
"persist_user_message": persist_user_message,
"persist_user_timestamp": persist_user_timestamp,
}
return {
"final_response": "ok",
"messages": [],
"api_calls": 1,
"completed": True,
}
def _install_fake_agent(monkeypatch):
fake_run_agent = types.ModuleType("run_agent")
fake_run_agent.AIAgent = _CapturingAgent
monkeypatch.setitem(sys.modules, "run_agent", fake_run_agent)
def _make_runner():
runner = object.__new__(gateway_run.GatewayRunner)
runner.adapters = {}
runner._ephemeral_system_prompt = ""
runner._prefill_messages = []
runner._reasoning_config = None
runner._service_tier = None
runner._provider_routing = {}
runner._fallback_model = None
runner._running_agents = {}
runner._pending_model_notes = {}
runner._session_db = None
runner._agent_cache = {}
runner._agent_cache_lock = threading.Lock()
runner._session_model_overrides = {}
runner.hooks = SimpleNamespace(loaded_hooks=False)
runner.config = SimpleNamespace(streaming=None)
runner.session_store = SimpleNamespace(
get_or_create_session=lambda source: SimpleNamespace(session_id="session-1"),
load_transcript=lambda session_id: [],
)
runner._get_or_create_gateway_honcho = lambda session_key: (None, None)
runner._enrich_message_with_vision = AsyncMock(return_value="ENRICHED")
return runner
def _make_source() -> SessionSource:
return SessionSource(
platform=Platform.TELEGRAM,
chat_id="12345",
chat_type="dm",
user_id="user-1",
)
def _make_discord_auto_thread_source() -> SessionSource:
return SessionSource(
platform=Platform.DISCORD,
chat_id="999",
chat_type="thread",
user_id="user-1",
thread_id="999",
parent_chat_id="100",
auto_thread_created=True,
auto_thread_initial_name="raw user prompt",
)
def _make_event(text: str) -> MessageEvent:
return MessageEvent(text=text, source=_make_source(), message_id="m1")
def test_turn_route_injects_priority_processing_without_changing_runtime():
runner = _make_runner()
runner._service_tier = "priority"
runtime_kwargs = {
"api_key": "***",
"base_url": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"api_mode": "chat_completions",
"command": None,
"args": [],
"credential_pool": None,
}
route = gateway_run.GatewayRunner._resolve_turn_agent_config(runner, "hi", "gpt-5.4", runtime_kwargs)
assert route["runtime"]["provider"] == "openrouter"
assert route["runtime"]["api_mode"] == "chat_completions"
assert route["request_overrides"] == {"service_tier": "priority"}
@pytest.mark.asyncio
async def test_handle_fast_command_global_flag_persists_config(monkeypatch, tmp_path):
runner = _make_runner()
monkeypatch.setattr(gateway_run, "_hermes_home", tmp_path)
monkeypatch.setattr(gateway_run, "_load_gateway_config", lambda: {})
monkeypatch.setattr(gateway_run, "_resolve_gateway_model", lambda config=None: "gpt-5.4")
response = await runner._handle_fast_command(_make_event("/fast fast --global"))
assert "FAST" in response
assert runner._service_tier == "priority"
saved = yaml.safe_load((tmp_path / "config.yaml").read_text(encoding="utf-8"))
assert saved["agent"]["service_tier"] == "fast"
# Global write supersedes the session override.
assert not runner._session_service_tier_overrides
@pytest.mark.asyncio
async def test_session_fast_override_beats_config_default(monkeypatch, tmp_path):
"""A session /fast normal wins over agent.service_tier: fast in config."""
runner = _make_runner()
monkeypatch.setattr(gateway_run, "_hermes_home", tmp_path)
monkeypatch.setattr(gateway_run, "_load_gateway_config", lambda: {})
monkeypatch.setattr(
gateway_run,
"_load_gateway_runtime_config",
lambda: {"agent": {"service_tier": "fast"}},
)
monkeypatch.setattr(gateway_run, "_resolve_gateway_model", lambda config=None: "gpt-5.4")
event = _make_event("/fast normal")
session_key = runner._session_key_for_source(event.source)
response = await runner._handle_fast_command(event)
assert "NORMAL" in response
# Override stores explicit None (normal) and wins over config "fast".
assert session_key in runner._session_service_tier_overrides
assert runner._resolve_session_service_tier(session_key=session_key) is None
# A different session still gets the config default.
assert runner._resolve_session_service_tier(session_key="other-session") == "priority"