feat: add HIL diagnostics and meter health handling

hil_tests/test_live_evidence.py

@@ -0,0 +1,54 @@
+import os
+import sys
+from pathlib import Path
+
+import pytest
+
+
+ROOT = Path(__file__).resolve().parents[1]
+sys.path.insert(0, str(ROOT / "tools" / "hil"))
+
+from hil_common import read_events
+from report import evaluate
+
+
+@pytest.mark.hil
+def test_captured_baseline_evidence():
+    artifact_text = os.environ.get("HIL_ARTIFACT", "")
+    if not artifact_text:
+        pytest.skip("set HIL_ARTIFACT to a completed artifacts/hil/<timestamp> directory")
+    artifact = Path(artifact_text)
+    checks = evaluate(read_events(artifact))
+    failures = [f"{check.name}: {check.detail}" for check in checks if check.status == "fail"]
+    assert not failures, "\n".join(failures)
+
+
+@pytest.mark.hil
+def test_captured_fault_recovery_evidence():
+    artifact_text = os.environ.get("HIL_ARTIFACT", "")
+    requested_fault = os.environ.get("HIL_FAULT", "")
+    if not artifact_text or not requested_fault:
+        pytest.skip("set HIL_ARTIFACT and HIL_FAULT to a completed fault-run artifact")
+    checks = evaluate(read_events(Path(artifact_text)), requested_fault)
+    fault_check = next(check for check in checks if check.name == f"fault {requested_fault}")
+    assert fault_check.status == "pass", fault_check.detail
+
+
+@pytest.mark.hil
+def test_meter_outage_is_counted_once_and_not_published():
+    artifact_text = os.environ.get("HIL_ARTIFACT", "")
+    expect_no_meter = os.environ.get("HIL_EXPECT_NO_METER", "") == "1"
+    if not artifact_text or not expect_no_meter:
+        pytest.skip("set HIL_ARTIFACT and HIL_EXPECT_NO_METER=1 for a no-meter capture")
+    events = read_events(Path(artifact_text))
+    sender = [event for event in events if event.get("source") == "sender"]
+    samples = [event for event in sender if event.get("event") == "meter_sample"]
+    active_faults = [event for event in sender
+                     if event.get("event") == "meter_fault" and event.get("state") == "active"]
+    assert samples, "no meter sample evidence captured"
+    assert all(event.get("ok") is False and event.get("classification") == "no_data"
+               for event in samples)
+    assert len(active_faults) == 1, active_faults
+    assert not [event for event in sender if event.get("event") == "batch_created"]
+    assert not [event for event in sender
+                if event.get("event") == "queue" and event.get("action") == "enqueue"]