mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-31 19:16:29 +00:00
39975613b1
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.
104 lines
3.3 KiB
Python
104 lines
3.3 KiB
Python
"""OTLP exporter tests: config resolution, span mapping, streaming subscriber.
|
|
|
|
No SQLite involved — monitoring is an egress path, so the exporter consumes
|
|
emitter batches directly. Uses the in-memory OTel span exporter; skipped when
|
|
the optional otlp extra is not installed.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import pytest
|
|
|
|
otel = pytest.importorskip("opentelemetry.sdk.trace", reason="otlp extra not installed")
|
|
|
|
import agent.monitoring.otlp_exporter as OE
|
|
from agent.monitoring.emitter import MonitoringEmitter
|
|
|
|
|
|
def _mem_provider():
|
|
from opentelemetry.sdk.trace import TracerProvider
|
|
from opentelemetry.sdk.trace.export import SimpleSpanProcessor
|
|
from opentelemetry.sdk.trace.export.in_memory_span_exporter import InMemorySpanExporter
|
|
|
|
exporter = InMemorySpanExporter()
|
|
provider = TracerProvider()
|
|
provider.add_span_processor(SimpleSpanProcessor(exporter))
|
|
return provider, exporter
|
|
|
|
|
|
def test_gateway_health_event_maps_to_span_with_attrs():
|
|
provider, mem = _mem_provider()
|
|
n = OE.export_batch(provider, [{
|
|
"event": "gateway_health", "name": "gateway.lifecycle",
|
|
"old_state": "starting", "new_state": "running",
|
|
"active_agents": 2, "pid": 4242,
|
|
}])
|
|
assert n == 1
|
|
spans = mem.get_finished_spans()
|
|
assert spans[0].name == "hermes.gateway_health"
|
|
attrs = dict(spans[0].attributes or {})
|
|
assert attrs["hermes.old_state"] == "starting"
|
|
assert attrs["hermes.new_state"] == "running"
|
|
assert attrs["hermes.active_agents"] == 2
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_headers_resolve_from_env_not_value(monkeypatch):
|
|
monkeypatch.setenv("DD_KEY_ENV", "secret-value")
|
|
resolved = OE._resolve_headers({"DD-API-KEY": "DD_KEY_ENV", "X-Missing": "NOPE_ENV"})
|
|
assert resolved == {"DD-API-KEY": "secret-value"}
|
|
|
|
|
|
|
|
|
|
def test_trace_resource_includes_stable_hashed_instance():
|
|
attrs = OE._resource_attributes(
|
|
{"monitoring": {"install_id": "private-install-id"}}
|
|
)
|
|
|
|
assert attrs["service.name"] == "hermes-gateway"
|
|
assert attrs["service.instance.id"].startswith("sha256:")
|
|
assert len(attrs["service.instance.id"]) == len("sha256:") + 24
|
|
assert "private-install-id" not in str(attrs)
|
|
assert attrs["telemetry.scope"] == "gateway_monitoring"
|
|
|
|
|
|
|
|
|
|
def test_streamer_receives_events_and_respects_filter(monkeypatch):
|
|
provider, mem = _mem_provider()
|
|
monkeypatch.setattr(OE, "_make_provider", lambda cfg: (provider, None))
|
|
streamer = OE.OTLPStreamer(
|
|
{}, event_filter=lambda ev: ev.get("event") == "gateway_health")
|
|
|
|
em = MonitoringEmitter()
|
|
em.subscribe(streamer)
|
|
em.emit({"event": "gateway_health", "name": "gateway.health_snapshot"})
|
|
em.emit({"event": "model_call", "provider": "anthropic"}) # filtered out
|
|
em.flush()
|
|
em.close()
|
|
|
|
spans = mem.get_finished_spans()
|
|
assert [s.name for s in spans] == ["hermes.gateway_health"]
|
|
assert streamer.exported == 1
|
|
|
|
|
|
def test_failing_streamer_never_breaks_emitter(monkeypatch):
|
|
def boom(cfg):
|
|
raise RuntimeError("no provider")
|
|
|
|
em = MonitoringEmitter()
|
|
|
|
def bad_subscriber(batch):
|
|
raise RuntimeError("export down")
|
|
|
|
seen: list = []
|
|
em.subscribe(bad_subscriber)
|
|
em.subscribe(lambda batch: seen.extend(batch))
|
|
em.emit({"event": "gateway_health", "name": "gateway.lifecycle"})
|
|
em.flush()
|
|
em.close()
|
|
assert len(seen) == 1
|