mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-31 19:16:29 +00:00
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.
59 lines
1.9 KiB
Python
59 lines
1.9 KiB
Python
"""Audit log for dashboard-auth events.
|
|
|
|
Profile-aware location: ``$HERMES_HOME/logs/dashboard-auth.log``.
|
|
Format: one JSON object per line. Token-like kwargs are dropped before
|
|
serialisation so we never leak refresh tokens or JWTs to disk.
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
import pytest
|
|
|
|
from hermes_cli.dashboard_auth.audit import audit_log, AuditEvent
|
|
|
|
|
|
@pytest.fixture
|
|
def profile_home(tmp_path, monkeypatch):
|
|
"""Redirect $HERMES_HOME and ~ to a tmp dir for the duration of the test."""
|
|
home = tmp_path / ".hermes"
|
|
home.mkdir()
|
|
monkeypatch.setenv("HERMES_HOME", str(home))
|
|
# Some code paths fall back to Path.home() — patch that too.
|
|
monkeypatch.setattr("pathlib.Path.home", lambda: tmp_path)
|
|
return home
|
|
|
|
|
|
def test_audit_writes_jsonlines(profile_home):
|
|
audit_log(AuditEvent.LOGIN_START, provider="nous", ip="1.2.3.4")
|
|
audit_log(
|
|
AuditEvent.LOGIN_SUCCESS,
|
|
provider="nous", user_id="u1",
|
|
email="a@b.com", ip="1.2.3.4",
|
|
)
|
|
|
|
path = profile_home / "logs" / "dashboard-auth.log"
|
|
assert path.exists(), f"audit log not created at {path}"
|
|
lines = path.read_text().strip().splitlines()
|
|
assert len(lines) == 2
|
|
|
|
second = json.loads(lines[1])
|
|
assert second["event"] == "login_success"
|
|
assert second["provider"] == "nous"
|
|
assert second["user_id"] == "u1"
|
|
assert second["email"] == "a@b.com"
|
|
assert "ts" in second # ISO-8601 timestamp
|
|
|
|
|
|
def test_audit_redacts_token_like_fields(profile_home):
|
|
audit_log(
|
|
AuditEvent.LOGIN_SUCCESS,
|
|
provider="nous", access_token="should-not-appear",
|
|
refresh_token="also-not", code="not-this", state="nope",
|
|
)
|
|
raw = (profile_home / "logs" / "dashboard-auth.log").read_text()
|
|
for forbidden in ("should-not-appear", "also-not", "not-this", "nope"):
|
|
assert forbidden not in raw, f"token-like value leaked into audit log: {forbidden}"
|
|
|
|
|
|
|
|
|