mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-04-25 00:51:20 +00:00
Three fixes that close the remaining structural sources of CI flakes after PR #13363. ## 1. Per-test reset of module-level singletons and ContextVars Python modules are singletons per process, and pytest-xdist workers are long-lived. Module-level dicts/sets and ContextVars persist across tests on the same worker. A test that sets state in `tools.approval._session_approved` and doesn't explicitly clear it leaks that state to every subsequent test on the same worker. New `_reset_module_state` autouse fixture in `tests/conftest.py` clears: - tools.approval: _session_approved, _session_yolo, _permanent_approved, _pending, _gateway_queues, _gateway_notify_cbs, _approval_session_key - tools.interrupt: _interrupted_threads - gateway.session_context: 10 session/cron ContextVars (reset to _UNSET) - tools.env_passthrough: _allowed_env_vars_var (reset to empty set) - tools.credential_files: _registered_files_var (reset to empty dict) - tools.file_tools: _read_tracker, _file_ops_cache This was the single biggest remaining class of CI flakes. `test_command_guards::test_warn_session_approved` and `test_combined_cli_session_approves_both` were failing 12/15 recent main runs specifically because `_session_approved` carried approvals from a prior test's session into these tests' `"default"` session lookup. ## 2. Unset platform allowlist env vars in hermetic fixture `TELEGRAM_ALLOWED_USERS`, `DISCORD_ALLOWED_USERS`, and 20 other `*_ALLOWED_USERS` / `*_ALLOW_ALL_USERS` vars are now unset per-test in the same place credential env vars already are. These aren't credentials but they change gateway auth behavior; if set from any source (user shell, leaky test, CI env) they flake button-authorization tests. Fixes three `test_telegram_approval_buttons` tests that were failing across recent runs of the full gateway directory. ## 3. Two specific tests with module-level captured state - `test_signal::TestSignalPhoneRedaction`: `agent.redact._REDACT_ENABLED` is captured at module import from `HERMES_REDACT_SECRETS`, not read per-call. `monkeypatch.delenv` at test time is too late. Added `monkeypatch.setattr("agent.redact._REDACT_ENABLED", True)` per skill xdist-cross-test-pollution Pattern 5. - `test_internal_event_bypass_pairing::test_non_internal_event_without_user_triggers_pairing`: `gateway.pairing.PAIRING_DIR` is captured at module import from HERMES_HOME, so per-test HERMES_HOME redirection in conftest doesn't retroactively move it. Test now monkeypatches PAIRING_DIR directly to its tmp_path, preventing rate-limit state from prior xdist workers from letting the pairing send-call be suppressed. ## Validation - tests/tools/: 3494 pass (0 fail) including test_command_guards - tests/gateway/: 3504 pass (0 fail) across repeat runs - tests/agent/ + tests/hermes_cli/ + tests/run_agent/ + tests/tools/: 8371 pass, 37 skipped, 0 fail — full suite across directories No production code changed.
463 lines
16 KiB
Python
463 lines
16 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",
|
|
"BROWSER_CDP_URL",
|
|
"CAMOFOX_URL",
|
|
# Platform allowlists — not credentials, but if set from any source
|
|
# (user shell, earlier leaky test, CI env), they change gateway auth
|
|
# behavior and flake button-authorization tests.
|
|
"TELEGRAM_ALLOWED_USERS",
|
|
"DISCORD_ALLOWED_USERS",
|
|
"WHATSAPP_ALLOWED_USERS",
|
|
"SLACK_ALLOWED_USERS",
|
|
"SIGNAL_ALLOWED_USERS",
|
|
"SIGNAL_GROUP_ALLOWED_USERS",
|
|
"EMAIL_ALLOWED_USERS",
|
|
"SMS_ALLOWED_USERS",
|
|
"MATTERMOST_ALLOWED_USERS",
|
|
"MATRIX_ALLOWED_USERS",
|
|
"DINGTALK_ALLOWED_USERS",
|
|
"FEISHU_ALLOWED_USERS",
|
|
"WECOM_ALLOWED_USERS",
|
|
"GATEWAY_ALLOWED_USERS",
|
|
"GATEWAY_ALLOW_ALL_USERS",
|
|
"TELEGRAM_ALLOW_ALL_USERS",
|
|
"DISCORD_ALLOW_ALL_USERS",
|
|
"WHATSAPP_ALLOW_ALL_USERS",
|
|
"SLACK_ALLOW_ALL_USERS",
|
|
"SIGNAL_ALLOW_ALL_USERS",
|
|
"EMAIL_ALLOW_ALL_USERS",
|
|
"SMS_ALLOW_ALL_USERS",
|
|
})
|
|
|
|
|
|
@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
|
|
|
|
|
|
# ── Module-level state reset ───────────────────────────────────────────────
|
|
#
|
|
# Python modules are singletons per process, and pytest-xdist workers are
|
|
# long-lived. Module-level dicts/sets (tool registries, approval state,
|
|
# interrupt flags) and ContextVars persist across tests in the same worker,
|
|
# causing tests that pass alone to fail when run with siblings.
|
|
#
|
|
# Each entry in this fixture clears state that belongs to a specific module.
|
|
# New state buckets go here too — this is the single gate that prevents
|
|
# "works alone, flakes in CI" bugs from state leakage.
|
|
#
|
|
# The skill `test-suite-cascade-diagnosis` documents the concrete patterns
|
|
# this closes; the running example was `test_command_guards` failing 12/15
|
|
# CI runs because ``tools.approval._session_approved`` carried approvals
|
|
# from one test's session into another's.
|
|
|
|
@pytest.fixture(autouse=True)
|
|
def _reset_module_state():
|
|
"""Clear module-level mutable state and ContextVars between tests.
|
|
|
|
Keeps state from leaking across tests on the same xdist worker. Modules
|
|
that don't exist yet (test collection before production import) are
|
|
skipped silently — production import later creates fresh empty state.
|
|
"""
|
|
# --- tools.approval — the single biggest source of cross-test pollution ---
|
|
try:
|
|
from tools import approval as _approval_mod
|
|
_approval_mod._session_approved.clear()
|
|
_approval_mod._session_yolo.clear()
|
|
_approval_mod._permanent_approved.clear()
|
|
_approval_mod._pending.clear()
|
|
_approval_mod._gateway_queues.clear()
|
|
_approval_mod._gateway_notify_cbs.clear()
|
|
# ContextVar: reset to empty string so get_current_session_key()
|
|
# falls through to the env var / default path, matching a fresh
|
|
# process.
|
|
_approval_mod._approval_session_key.set("")
|
|
except Exception:
|
|
pass
|
|
|
|
# --- tools.interrupt — per-thread interrupt flag set ---
|
|
try:
|
|
from tools import interrupt as _interrupt_mod
|
|
with _interrupt_mod._lock:
|
|
_interrupt_mod._interrupted_threads.clear()
|
|
except Exception:
|
|
pass
|
|
|
|
# --- gateway.session_context — 9 ContextVars that represent
|
|
# the active gateway session. If set in one test and not reset,
|
|
# the next test's get_session_env() reads stale values.
|
|
try:
|
|
from gateway import session_context as _sc_mod
|
|
for _cv in (
|
|
_sc_mod._SESSION_PLATFORM,
|
|
_sc_mod._SESSION_CHAT_ID,
|
|
_sc_mod._SESSION_CHAT_NAME,
|
|
_sc_mod._SESSION_THREAD_ID,
|
|
_sc_mod._SESSION_USER_ID,
|
|
_sc_mod._SESSION_USER_NAME,
|
|
_sc_mod._SESSION_KEY,
|
|
_sc_mod._CRON_AUTO_DELIVER_PLATFORM,
|
|
_sc_mod._CRON_AUTO_DELIVER_CHAT_ID,
|
|
_sc_mod._CRON_AUTO_DELIVER_THREAD_ID,
|
|
):
|
|
_cv.set(_sc_mod._UNSET)
|
|
except Exception:
|
|
pass
|
|
|
|
# --- tools.env_passthrough — ContextVar<set[str]> with no default ---
|
|
# LookupError is normal if the test never set it. Setting it to an
|
|
# empty set unconditionally normalizes the starting state.
|
|
try:
|
|
from tools import env_passthrough as _envp_mod
|
|
_envp_mod._allowed_env_vars_var.set(set())
|
|
except Exception:
|
|
pass
|
|
|
|
# --- tools.credential_files — ContextVar<dict> ---
|
|
try:
|
|
from tools import credential_files as _credf_mod
|
|
_credf_mod._registered_files_var.set({})
|
|
except Exception:
|
|
pass
|
|
|
|
# --- tools.file_tools — per-task read history + file-ops cache ---
|
|
# _read_tracker accumulates per-task_id read history for loop detection,
|
|
# capped by _READ_HISTORY_CAP. If entries from a prior test persist, the
|
|
# cap is hit faster than expected and capacity-related tests flake.
|
|
try:
|
|
from tools import file_tools as _ft_mod
|
|
with _ft_mod._read_tracker_lock:
|
|
_ft_mod._read_tracker.clear()
|
|
with _ft_mod._file_ops_lock:
|
|
_ft_mod._file_ops_cache.clear()
|
|
except Exception:
|
|
pass
|
|
|
|
yield
|
|
|
|
|
|
@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)
|