hermes-agent/tests/monitoring/test_gateway_health_export.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

120 lines
2.6 KiB
Python

from __future__ import annotations
import logging
import pytest
def test_otlp_attrs_redact_strings_and_never_export_profile():
from agent.monitoring.otlp_exporter import _span_attrs
attrs = _span_attrs({
"event": "gateway_health",
"name": "gateway.lifecycle",
"profile": "user@example.com",
"exit_reason": "Bearer top-secret-token for user@example.com",
})
assert "hermes.profile" not in attrs
assert "top-secret-token" not in str(attrs)
assert "user@example.com" not in str(attrs)
def test_resource_attributes_are_allowlisted_and_sanitized():
from agent.monitoring.gateway_health_export import _safe_resource_attributes
attrs = _safe_resource_attributes({
"service.name": "hermes-gateway",
"service.instance.id": "install-1",
"deployment.environment.name": "staging",
"user.email": "user@example.com",
"authorization": "Bearer top-secret-token",
"custom.request.id": "unbounded",
})
assert attrs == {
"service.name": "hermes-gateway",
"service.instance.id": attrs["service.instance.id"],
"deployment.environment.name": "staging",
}
assert attrs["service.instance.id"].startswith("sha256:")
assert "install-1" not in attrs["service.instance.id"]
def test_diagnostic_log_attributes_are_allowlisted_redacted_and_profile_free():
from agent.monitoring.gateway_health_export import _diagnostic_log_attributes
attrs = _diagnostic_log_attributes({
"event": "gateway_diagnostic",
"name": "platform.fatal",
"subsystem": "platform.slack",
"profile": "user@example.com",
"error_code": "Bearer top-secret-token",
"custom": "must-not-egress",
})
assert "hermes.profile" not in attrs
assert "hermes.custom" not in attrs
assert "top-secret-token" not in str(attrs)
def test_install_id_persists_across_calls(tmp_path, monkeypatch):
"""A minted install id must survive restarts (service.instance.id continuity)."""
monkeypatch.setenv("HERMES_HOME", str(tmp_path))
(tmp_path / "config.yaml").write_text("{}\n")
import hermes_cli.config as cfg_mod
from agent.monitoring.policy import ensure_install_id
first = ensure_install_id(cfg_mod.load_config())
assert first and first != "unknown"
# Persisted: a fresh load (simulating a new gateway process) returns the same id.
second = ensure_install_id(cfg_mod.load_config())
assert second == first
assert first in (tmp_path / "config.yaml").read_text()