mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-04-25 00:51:20 +00:00
3207b9bda0
Cuts shard-3 local runtime in half by neutralizing real wall-clock waits across three classes of slow test: ## 1. Retry backoff mocks - tests/run_agent/conftest.py (NEW): autouse fixture mocks jittered_backoff to 0.0 so the `while time.time() < sleep_end` busy-loop exits immediately. No global time.sleep mock (would break threading tests). - test_anthropic_error_handling, test_413_compression, test_run_agent_codex_responses, test_fallback_model: per-file fixtures mock time.sleep / asyncio.sleep for retry / compression paths. - test_retaindb_plugin: cap the retaindb module's bound time.sleep to 0.05s via a per-test shim (background writer-thread retries sleep 2s after errors; tests don't care about exact duration). Plus replace arbitrary time.sleep(N) waits with short polling loops bounded by deadline. ## 2. Subprocess sleeps in production code - test_update_gateway_restart: mock time.sleep. Production code does time.sleep(3) after `systemctl restart` to verify the service survived. Tests mock subprocess.run \u2014 nothing actually restarts \u2014 so the wait is dead time. ## 3. Network / IMDS timeouts (biggest single win) - tests/conftest.py: add AWS_EC2_METADATA_DISABLED=true plus AWS_METADATA_SERVICE_TIMEOUT=1 and ATTEMPTS=1. boto3 falls back to IMDS (169.254.169.254) when no AWS creds are set. Any test hitting has_aws_credentials() / resolve_aws_auth_env_var() (e.g. test_status, test_setup_copilot_acp, anything that touches provider auto-detect) burned ~2-4s waiting for that to time out. - test_exit_cleanup_interrupt: explicitly mock resolve_runtime_provider which was doing real network auto-detect (~4s). Tests don't care about provider resolution \u2014 the agent is already mocked. - test_timezone: collapse the 3-test "TZ env in subprocess" suite into 2 tests by checking both injection AND no-leak in the same subprocess spawn (was 3 \u00d7 3.2s, now 2 \u00d7 4s). ## Validation | Test | Before | After | |---|---|---| | test_anthropic_error_handling (8 tests) | ~80s | ~15s | | test_413_compression (14 tests) | ~18s | 2.3s | | test_retaindb_plugin (67 tests) | ~13s | 1.3s | | test_status_includes_tavily_key | 4.0s | 0.05s | | test_setup_copilot_acp_skips_same_provider_pool_step | 8.0s | 0.26s | | test_update_gateway_restart (5 tests) | ~18s total | ~0.35s total | | test_exit_cleanup_interrupt (2 tests) | 8s | 1.5s | | **Matrix shard 3 local** | **108s** | **50s** | No behavioral contract changed \u2014 tests still verify retry happens, service restart logic runs, etc.; they just don't burn real seconds waiting for it. Supersedes PR #11779 (those changes are included here).
91 lines
3.5 KiB
Python
91 lines
3.5 KiB
Python
"""Tests for KeyboardInterrupt handling in exit cleanup paths.
|
|
|
|
``except Exception`` does not catch ``KeyboardInterrupt`` (which inherits
|
|
from ``BaseException``). A second Ctrl+C during exit cleanup must not
|
|
abort remaining cleanup steps. These tests exercise the actual production
|
|
code paths — not a copy of the try/except pattern.
|
|
"""
|
|
|
|
import atexit
|
|
import weakref
|
|
from unittest.mock import MagicMock, patch, call
|
|
|
|
import pytest
|
|
|
|
|
|
@pytest.fixture(autouse=True)
|
|
def _mock_runtime_provider(monkeypatch):
|
|
"""run_job calls resolve_runtime_provider which can try real network
|
|
auto-detection (~4s of socket timeouts in hermetic CI). Mock it out
|
|
since these tests don't care about provider resolution — the agent
|
|
is mocked too."""
|
|
import hermes_cli.runtime_provider as rp
|
|
def _fake_resolve(*args, **kwargs):
|
|
return {
|
|
"provider": "openrouter",
|
|
"api_key": "test-key",
|
|
"base_url": "https://openrouter.ai/api/v1",
|
|
"model": "test/model",
|
|
"api_mode": "chat_completions",
|
|
}
|
|
monkeypatch.setattr(rp, "resolve_runtime_provider", _fake_resolve)
|
|
|
|
|
|
class TestCronJobCleanup:
|
|
"""cron/scheduler.py — end_session + close in the finally block."""
|
|
|
|
def test_keyboard_interrupt_in_end_session_does_not_skip_close(self):
|
|
"""If end_session raises KeyboardInterrupt, close() must still run."""
|
|
mock_db = MagicMock()
|
|
mock_db.end_session.side_effect = KeyboardInterrupt
|
|
|
|
from cron import scheduler
|
|
|
|
job = {
|
|
"id": "test-job-1",
|
|
"name": "test cleanup",
|
|
"prompt": "hello",
|
|
"schedule": "0 9 * * *",
|
|
"model": "test/model",
|
|
}
|
|
|
|
with patch("hermes_state.SessionDB", return_value=mock_db), \
|
|
patch.object(scheduler, "_build_job_prompt", return_value="hello"), \
|
|
patch.object(scheduler, "_resolve_origin", return_value=None), \
|
|
patch.object(scheduler, "_resolve_delivery_target", return_value=None), \
|
|
patch("dotenv.load_dotenv", return_value=None), \
|
|
patch("run_agent.AIAgent") as MockAgent:
|
|
# Make the agent raise immediately so we hit the finally block
|
|
MockAgent.return_value.run_conversation.side_effect = RuntimeError("boom")
|
|
scheduler.run_job(job)
|
|
|
|
mock_db.end_session.assert_called_once()
|
|
mock_db.close.assert_called_once()
|
|
|
|
def test_keyboard_interrupt_in_close_does_not_propagate(self):
|
|
"""If close() raises KeyboardInterrupt, it must not escape run_job."""
|
|
mock_db = MagicMock()
|
|
mock_db.close.side_effect = KeyboardInterrupt
|
|
|
|
from cron import scheduler
|
|
|
|
job = {
|
|
"id": "test-job-2",
|
|
"name": "test close interrupt",
|
|
"prompt": "hello",
|
|
"schedule": "0 9 * * *",
|
|
"model": "test/model",
|
|
}
|
|
|
|
with patch("hermes_state.SessionDB", return_value=mock_db), \
|
|
patch.object(scheduler, "_build_job_prompt", return_value="hello"), \
|
|
patch.object(scheduler, "_resolve_origin", return_value=None), \
|
|
patch.object(scheduler, "_resolve_delivery_target", return_value=None), \
|
|
patch("dotenv.load_dotenv", return_value=None), \
|
|
patch("run_agent.AIAgent") as MockAgent:
|
|
MockAgent.return_value.run_conversation.side_effect = RuntimeError("boom")
|
|
# Must not raise
|
|
scheduler.run_job(job)
|
|
|
|
mock_db.end_session.assert_called_once()
|
|
mock_db.close.assert_called_once()
|