mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-04-25 00:51:20 +00:00
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).
335 lines
11 KiB
Python
335 lines
11 KiB
Python
"""Shared fixtures for the hermes-agent test suite.
|
|
|
|
Hermetic-test invariants enforced here (see AGENTS.md for rationale):
|
|
|
|
1. **No credential env vars.** All provider/credential-shaped env vars
|
|
(ending in _API_KEY, _TOKEN, _SECRET, _PASSWORD, _CREDENTIALS, etc.)
|
|
are unset before every test. Local developer keys cannot leak in.
|
|
2. **Isolated HERMES_HOME.** HERMES_HOME points to a per-test tempdir so
|
|
code reading ``~/.hermes/*`` via ``get_hermes_home()`` can't see the
|
|
real one. (We do NOT also redirect HOME — that broke subprocesses in
|
|
CI. Code using ``Path.home() / ".hermes"`` instead of the canonical
|
|
``get_hermes_home()`` is a bug to fix at the callsite.)
|
|
3. **Deterministic runtime.** TZ=UTC, LANG=C.UTF-8, PYTHONHASHSEED=0.
|
|
4. **No HERMES_SESSION_* inheritance** — the agent's current gateway
|
|
session must not leak into tests.
|
|
|
|
These invariants make the local test run match CI closely. Gaps that
|
|
remain (CPU count, xdist worker count) are addressed by the canonical
|
|
test runner at ``scripts/run_tests.sh``.
|
|
"""
|
|
|
|
import asyncio
|
|
import os
|
|
import re
|
|
import signal
|
|
import sys
|
|
import tempfile
|
|
from pathlib import Path
|
|
from unittest.mock import patch
|
|
|
|
import pytest
|
|
|
|
# Ensure project root is importable
|
|
PROJECT_ROOT = Path(__file__).parent.parent
|
|
if str(PROJECT_ROOT) not in sys.path:
|
|
sys.path.insert(0, str(PROJECT_ROOT))
|
|
|
|
|
|
# ── Credential env-var filter ──────────────────────────────────────────────
|
|
#
|
|
# Any env var in the current process matching ONE of these patterns is
|
|
# unset for every test. Developers' local keys cannot leak into assertions
|
|
# about "auto-detect provider when key present".
|
|
|
|
_CREDENTIAL_SUFFIXES = (
|
|
"_API_KEY",
|
|
"_TOKEN",
|
|
"_SECRET",
|
|
"_PASSWORD",
|
|
"_CREDENTIALS",
|
|
"_ACCESS_KEY",
|
|
"_SECRET_ACCESS_KEY",
|
|
"_PRIVATE_KEY",
|
|
"_OAUTH_TOKEN",
|
|
"_WEBHOOK_SECRET",
|
|
"_ENCRYPT_KEY",
|
|
"_APP_SECRET",
|
|
"_CLIENT_SECRET",
|
|
"_CORP_SECRET",
|
|
"_AES_KEY",
|
|
)
|
|
|
|
# Explicit names (for ones that don't fit the suffix pattern)
|
|
_CREDENTIAL_NAMES = frozenset({
|
|
"AWS_ACCESS_KEY_ID",
|
|
"AWS_SECRET_ACCESS_KEY",
|
|
"AWS_SESSION_TOKEN",
|
|
"ANTHROPIC_TOKEN",
|
|
"FAL_KEY",
|
|
"GH_TOKEN",
|
|
"GITHUB_TOKEN",
|
|
"OPENAI_API_KEY",
|
|
"OPENROUTER_API_KEY",
|
|
"NOUS_API_KEY",
|
|
"GEMINI_API_KEY",
|
|
"GOOGLE_API_KEY",
|
|
"GROQ_API_KEY",
|
|
"XAI_API_KEY",
|
|
"MISTRAL_API_KEY",
|
|
"DEEPSEEK_API_KEY",
|
|
"KIMI_API_KEY",
|
|
"MOONSHOT_API_KEY",
|
|
"GLM_API_KEY",
|
|
"ZAI_API_KEY",
|
|
"MINIMAX_API_KEY",
|
|
"OLLAMA_API_KEY",
|
|
"OPENVIKING_API_KEY",
|
|
"COPILOT_API_KEY",
|
|
"CLAUDE_CODE_OAUTH_TOKEN",
|
|
"BROWSERBASE_API_KEY",
|
|
"FIRECRAWL_API_KEY",
|
|
"PARALLEL_API_KEY",
|
|
"EXA_API_KEY",
|
|
"TAVILY_API_KEY",
|
|
"WANDB_API_KEY",
|
|
"ELEVENLABS_API_KEY",
|
|
"HONCHO_API_KEY",
|
|
"MEM0_API_KEY",
|
|
"SUPERMEMORY_API_KEY",
|
|
"RETAINDB_API_KEY",
|
|
"HINDSIGHT_API_KEY",
|
|
"HINDSIGHT_LLM_API_KEY",
|
|
"TINKER_API_KEY",
|
|
"DAYTONA_API_KEY",
|
|
"TWILIO_AUTH_TOKEN",
|
|
"TELEGRAM_BOT_TOKEN",
|
|
"DISCORD_BOT_TOKEN",
|
|
"SLACK_BOT_TOKEN",
|
|
"SLACK_APP_TOKEN",
|
|
"MATTERMOST_TOKEN",
|
|
"MATRIX_ACCESS_TOKEN",
|
|
"MATRIX_PASSWORD",
|
|
"MATRIX_RECOVERY_KEY",
|
|
"HASS_TOKEN",
|
|
"EMAIL_PASSWORD",
|
|
"BLUEBUBBLES_PASSWORD",
|
|
"FEISHU_APP_SECRET",
|
|
"FEISHU_ENCRYPT_KEY",
|
|
"FEISHU_VERIFICATION_TOKEN",
|
|
"DINGTALK_CLIENT_SECRET",
|
|
"QQ_CLIENT_SECRET",
|
|
"QQ_STT_API_KEY",
|
|
"WECOM_SECRET",
|
|
"WECOM_CALLBACK_CORP_SECRET",
|
|
"WECOM_CALLBACK_TOKEN",
|
|
"WECOM_CALLBACK_ENCODING_AES_KEY",
|
|
"WEIXIN_TOKEN",
|
|
"MODAL_TOKEN_ID",
|
|
"MODAL_TOKEN_SECRET",
|
|
"TERMINAL_SSH_KEY",
|
|
"SUDO_PASSWORD",
|
|
"GATEWAY_PROXY_KEY",
|
|
"API_SERVER_KEY",
|
|
"TOOL_GATEWAY_USER_TOKEN",
|
|
"TELEGRAM_WEBHOOK_SECRET",
|
|
"WEBHOOK_SECRET",
|
|
"AI_GATEWAY_API_KEY",
|
|
"VOICE_TOOLS_OPENAI_KEY",
|
|
"BROWSER_USE_API_KEY",
|
|
"CUSTOM_API_KEY",
|
|
"GATEWAY_PROXY_URL",
|
|
"GEMINI_BASE_URL",
|
|
"OPENAI_BASE_URL",
|
|
"OPENROUTER_BASE_URL",
|
|
"OLLAMA_BASE_URL",
|
|
"GROQ_BASE_URL",
|
|
"XAI_BASE_URL",
|
|
"AI_GATEWAY_BASE_URL",
|
|
"ANTHROPIC_BASE_URL",
|
|
})
|
|
|
|
|
|
def _looks_like_credential(name: str) -> bool:
|
|
"""True if env var name matches a credential-shaped pattern."""
|
|
if name in _CREDENTIAL_NAMES:
|
|
return True
|
|
return any(name.endswith(suf) for suf in _CREDENTIAL_SUFFIXES)
|
|
|
|
|
|
# HERMES_* vars that change test behavior by being set. Unset all of these
|
|
# unconditionally — individual tests that need them set do so explicitly.
|
|
_HERMES_BEHAVIORAL_VARS = frozenset({
|
|
"HERMES_YOLO_MODE",
|
|
"HERMES_INTERACTIVE",
|
|
"HERMES_QUIET",
|
|
"HERMES_TOOL_PROGRESS",
|
|
"HERMES_TOOL_PROGRESS_MODE",
|
|
"HERMES_MAX_ITERATIONS",
|
|
"HERMES_SESSION_PLATFORM",
|
|
"HERMES_SESSION_CHAT_ID",
|
|
"HERMES_SESSION_CHAT_NAME",
|
|
"HERMES_SESSION_THREAD_ID",
|
|
"HERMES_SESSION_SOURCE",
|
|
"HERMES_SESSION_KEY",
|
|
"HERMES_GATEWAY_SESSION",
|
|
"HERMES_PLATFORM",
|
|
"HERMES_INFERENCE_PROVIDER",
|
|
"HERMES_MANAGED",
|
|
"HERMES_DEV",
|
|
"HERMES_CONTAINER",
|
|
"HERMES_EPHEMERAL_SYSTEM_PROMPT",
|
|
"HERMES_TIMEZONE",
|
|
"HERMES_REDACT_SECRETS",
|
|
"HERMES_BACKGROUND_NOTIFICATIONS",
|
|
"HERMES_EXEC_ASK",
|
|
"HERMES_HOME_MODE",
|
|
})
|
|
|
|
|
|
@pytest.fixture(autouse=True)
|
|
def _hermetic_environment(tmp_path, monkeypatch):
|
|
"""Blank out all credential/behavioral env vars so local and CI match.
|
|
|
|
Also redirects HOME and HERMES_HOME to per-test tempdirs so code that
|
|
reads ``~/.hermes/*`` can't touch the real one, and pins TZ/LANG so
|
|
datetime/locale-sensitive tests are deterministic.
|
|
"""
|
|
# 1. Blank every credential-shaped env var that's currently set.
|
|
for name in list(os.environ.keys()):
|
|
if _looks_like_credential(name):
|
|
monkeypatch.delenv(name, raising=False)
|
|
|
|
# 2. Blank behavioral HERMES_* vars that could change test semantics.
|
|
for name in _HERMES_BEHAVIORAL_VARS:
|
|
monkeypatch.delenv(name, raising=False)
|
|
|
|
# 3. Redirect HERMES_HOME to a per-test tempdir. Code that reads
|
|
# ``~/.hermes/*`` via ``get_hermes_home()`` now gets the tempdir.
|
|
#
|
|
# NOTE: We do NOT also redirect HOME. Doing so broke CI because
|
|
# some tests (and their transitive deps) spawn subprocesses that
|
|
# inherit HOME and expect it to be stable. If a test genuinely
|
|
# needs HOME isolated, it should set it explicitly in its own
|
|
# fixture. Any code in the codebase reading ``~/.hermes/*`` via
|
|
# ``Path.home() / ".hermes"`` instead of ``get_hermes_home()``
|
|
# is a bug to fix at the callsite.
|
|
fake_hermes_home = tmp_path / "hermes_test"
|
|
fake_hermes_home.mkdir()
|
|
(fake_hermes_home / "sessions").mkdir()
|
|
(fake_hermes_home / "cron").mkdir()
|
|
(fake_hermes_home / "memories").mkdir()
|
|
(fake_hermes_home / "skills").mkdir()
|
|
monkeypatch.setenv("HERMES_HOME", str(fake_hermes_home))
|
|
|
|
# 4. Deterministic locale / timezone / hashseed. CI runs in UTC with
|
|
# C.UTF-8 locale; local dev often doesn't. Pin everything.
|
|
monkeypatch.setenv("TZ", "UTC")
|
|
monkeypatch.setenv("LANG", "C.UTF-8")
|
|
monkeypatch.setenv("LC_ALL", "C.UTF-8")
|
|
monkeypatch.setenv("PYTHONHASHSEED", "0")
|
|
|
|
# 4b. Disable AWS IMDS lookups. Without this, any test that ends up
|
|
# calling has_aws_credentials() / resolve_aws_auth_env_var()
|
|
# (e.g. provider auto-detect, status command, cron run_job) burns
|
|
# ~2s waiting for the metadata service at 169.254.169.254 to time
|
|
# out. Tests don't run on EC2 — IMDS is always unreachable here.
|
|
monkeypatch.setenv("AWS_EC2_METADATA_DISABLED", "true")
|
|
monkeypatch.setenv("AWS_METADATA_SERVICE_TIMEOUT", "1")
|
|
monkeypatch.setenv("AWS_METADATA_SERVICE_NUM_ATTEMPTS", "1")
|
|
|
|
# 5. Reset plugin singleton so tests don't leak plugins from
|
|
# ~/.hermes/plugins/ (which, per step 3, is now empty — but the
|
|
# singleton might still be cached from a previous test).
|
|
try:
|
|
import hermes_cli.plugins as _plugins_mod
|
|
monkeypatch.setattr(_plugins_mod, "_plugin_manager", None)
|
|
except Exception:
|
|
pass
|
|
|
|
|
|
# Backward-compat alias — old tests reference this fixture name. Keep it
|
|
# as a no-op wrapper so imports don't break.
|
|
@pytest.fixture(autouse=True)
|
|
def _isolate_hermes_home(_hermetic_environment):
|
|
"""Alias preserved for any test that yields this name explicitly."""
|
|
return None
|
|
|
|
|
|
@pytest.fixture()
|
|
def tmp_dir(tmp_path):
|
|
"""Provide a temporary directory that is cleaned up automatically."""
|
|
return tmp_path
|
|
|
|
|
|
@pytest.fixture()
|
|
def mock_config():
|
|
"""Return a minimal hermes config dict suitable for unit tests."""
|
|
return {
|
|
"model": "test/mock-model",
|
|
"toolsets": ["terminal", "file"],
|
|
"max_turns": 10,
|
|
"terminal": {
|
|
"backend": "local",
|
|
"cwd": "/tmp",
|
|
"timeout": 30,
|
|
},
|
|
"compression": {"enabled": False},
|
|
"memory": {"memory_enabled": False, "user_profile_enabled": False},
|
|
"command_allowlist": [],
|
|
}
|
|
|
|
|
|
# ── Global test timeout ─────────────────────────────────────────────────────
|
|
# Kill any individual test that takes longer than 30 seconds.
|
|
# Prevents hanging tests (subprocess spawns, blocking I/O) from stalling the
|
|
# entire test suite.
|
|
|
|
def _timeout_handler(signum, frame):
|
|
raise TimeoutError("Test exceeded 30 second timeout")
|
|
|
|
@pytest.fixture(autouse=True)
|
|
def _ensure_current_event_loop(request):
|
|
"""Provide a default event loop for sync tests that call get_event_loop().
|
|
|
|
Python 3.11+ no longer guarantees a current loop for plain synchronous tests.
|
|
A number of gateway tests still use asyncio.get_event_loop().run_until_complete(...).
|
|
Ensure they always have a usable loop without interfering with pytest-asyncio's
|
|
own loop management for @pytest.mark.asyncio tests.
|
|
"""
|
|
if request.node.get_closest_marker("asyncio") is not None:
|
|
yield
|
|
return
|
|
|
|
try:
|
|
loop = asyncio.get_event_loop_policy().get_event_loop()
|
|
except RuntimeError:
|
|
loop = None
|
|
|
|
created = loop is None or loop.is_closed()
|
|
if created:
|
|
loop = asyncio.new_event_loop()
|
|
asyncio.set_event_loop(loop)
|
|
|
|
try:
|
|
yield
|
|
finally:
|
|
if created and loop is not None:
|
|
try:
|
|
loop.close()
|
|
finally:
|
|
asyncio.set_event_loop(None)
|
|
|
|
|
|
@pytest.fixture(autouse=True)
|
|
def _enforce_test_timeout():
|
|
"""Kill any individual test that takes longer than 30 seconds.
|
|
SIGALRM is Unix-only; skip on Windows."""
|
|
if sys.platform == "win32":
|
|
yield
|
|
return
|
|
old = signal.signal(signal.SIGALRM, _timeout_handler)
|
|
signal.alarm(30)
|
|
yield
|
|
signal.alarm(0)
|
|
signal.signal(signal.SIGALRM, old)
|