tegwick
10b988fa1c
The backup is procured and proven, so the loop runs on real evidence. - data/actuals/2026-08.json: first real observation. database 0.6365 GB, stored 0.0066 GB over 8 objects, backup success 1/1, restore RTO 1.08 min. Five proxies null, each with a named owner in measurement_gaps. - data/thresholds/platform-audit-storage.json + tools/thresholds.py: budget variance, abnormal growth, stale backup, unused commitment. Fail-closed — an unmeasured value is reported as unmeasured, never as within. - financial_exchange.py gains a usage mode emitting technical_usage records to fin-hub, with measurement gaps carried through and no infrastructure amount: fin-hub owns the booked fact and a null is never sent as 0.00. - observation schema 0.2 allows null cost and usage proxies; variance.py fails closed rather than reporting a 100% favourable variance on a missing amount. - platform-audit-storage: ordered -> active, commissioned 2026-08-14, on operational fact rather than on the purchase. The optimization case is now approved by the founder. That needed a schema change: Host Europe never supplied written terms, so options gained excluded/exclusion_reason. Previously an unevaluable alternative blocked its case forever, leaving the record claiming no decision while the bucket was in production. An excluded option keeps its unknowns and must say what would bring it back. August produces no variance and should not: the decision forecast starts at 2026-09, so August is a commissioning baseline. Threshold run is 2 within, 1 not applicable, 6 unmeasured, 0 breaches. Also fixes a pre-existing test failure: reef-storage consumers_actual is now rapp-postgres, which the assertion still expected to be empty. 136 tests pass. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
128 lines
6 KiB
Python
128 lines
6 KiB
Python
import json
|
|
import sys
|
|
import unittest
|
|
from pathlib import Path
|
|
|
|
sys.path.insert(0, str(Path(__file__).parents[1] / "tools"))
|
|
from thresholds import evaluate, evaluate_threshold
|
|
|
|
ROOT = Path(__file__).parents[1]
|
|
CONFIG = json.loads((ROOT / "data" / "thresholds" / "platform-audit-storage.json").read_text())
|
|
OBSERVATION = json.loads((ROOT / "data" / "actuals" / "2026-08.json").read_text())
|
|
FORECAST = json.loads(
|
|
(ROOT / "data" / "forecasts" / "platform-audit-storage-scaleway-base-2026-08.json").read_text()
|
|
)
|
|
|
|
|
|
def threshold(**overrides):
|
|
result = {
|
|
"id": "t", "kind": "budget_variance", "metric": "infrastructure_eur",
|
|
"comparison": "absolute_percentage_error", "limit": 10, "action": "investigate",
|
|
}
|
|
result.update(overrides)
|
|
return result
|
|
|
|
|
|
def observed(**overrides):
|
|
result = {"period": "2026-09", "infrastructure_eur": 3.0, "backup_success_pct": 100, "measurement_gaps": []}
|
|
result.update(overrides)
|
|
return result
|
|
|
|
|
|
class ThresholdVerdictTest(unittest.TestCase):
|
|
def test_variance_within_limit_passes(self):
|
|
compared = {"infrastructure_eur": {"absolute_percentage_error": 4.0, "error": 0.11}}
|
|
self.assertEqual("within", evaluate_threshold(threshold(), observed(), compared)["verdict"])
|
|
|
|
def test_variance_above_limit_breaches(self):
|
|
compared = {"infrastructure_eur": {"absolute_percentage_error": 42.0, "error": 1.2}}
|
|
result = evaluate_threshold(threshold(), observed(), compared)
|
|
self.assertEqual("breach", result["verdict"])
|
|
self.assertEqual(42.0, result["measured"])
|
|
|
|
def test_absolute_error_comparison_uses_magnitude_not_sign(self):
|
|
spec = threshold(metric="internal_labor_hours", comparison="absolute_error", limit=1)
|
|
compared = {"internal_labor_hours": {"error": -2.5, "absolute_percentage_error": 250.0}}
|
|
result = evaluate_threshold(spec, observed(internal_labor_hours=1.5), compared)
|
|
self.assertEqual("breach", result["verdict"])
|
|
self.assertEqual(2.5, result["measured"])
|
|
|
|
def test_minimum_comparison_breaches_below_the_limit(self):
|
|
spec = threshold(id="backup", metric="backup_success_pct", comparison="minimum", limit=100)
|
|
self.assertEqual("breach", evaluate_threshold(spec, observed(backup_success_pct=99), None)["verdict"])
|
|
self.assertEqual("within", evaluate_threshold(spec, observed(), None)["verdict"])
|
|
|
|
def test_maximum_comparison_breaches_above_the_limit(self):
|
|
spec = threshold(id="rto", metric="restore_rto_minutes", comparison="maximum", limit=3.24)
|
|
self.assertEqual("breach", evaluate_threshold(spec, observed(restore_rto_minutes=9.0), None)["verdict"])
|
|
self.assertEqual("within", evaluate_threshold(spec, observed(restore_rto_minutes=1.08), None)["verdict"])
|
|
|
|
|
|
class FailClosedTest(unittest.TestCase):
|
|
"""An unmeasured value must never pass a threshold."""
|
|
|
|
def test_missing_value_is_unmeasured_not_within(self):
|
|
result = evaluate_threshold(threshold(), observed(infrastructure_eur=None), None)
|
|
self.assertEqual("unmeasured", result["verdict"])
|
|
|
|
def test_unmeasured_result_carries_the_named_gap(self):
|
|
row = observed(
|
|
infrastructure_eur=None,
|
|
measurement_gaps=["infrastructure_eur: no invoice yet (owner: fin-hub)"],
|
|
)
|
|
result = evaluate_threshold(threshold(), row, None)
|
|
self.assertIn("owner: fin-hub", result["detail"])
|
|
|
|
def test_missing_forecast_row_is_unmeasured_not_within(self):
|
|
result = evaluate_threshold(threshold(), observed(), None)
|
|
self.assertEqual("unmeasured", result["verdict"])
|
|
self.assertIn("no forecast row", result["detail"])
|
|
|
|
def test_unknown_variance_entry_is_unmeasured(self):
|
|
compared = {"infrastructure_eur": {"forecast": 2.89, "actual": None, "status": "unknown"}}
|
|
self.assertEqual("unmeasured", evaluate_threshold(threshold(), observed(), compared)["verdict"])
|
|
|
|
def test_zero_forecast_does_not_pass_on_undefined_percentage(self):
|
|
compared = {"infrastructure_eur": {"absolute_percentage_error": None, "error": 3.0}}
|
|
result = evaluate_threshold(threshold(), observed(), compared)
|
|
self.assertEqual("unmeasured", result["verdict"])
|
|
self.assertIn("percentage error is undefined", result["detail"])
|
|
|
|
def test_not_applicable_threshold_is_distinct_from_passing(self):
|
|
spec = threshold(id="commitment", metric="commitment_utilization", comparison="minimum",
|
|
limit=None, status="not_applicable")
|
|
self.assertEqual("not_applicable", evaluate_threshold(spec, observed(), None)["verdict"])
|
|
|
|
|
|
class AugustObservationTest(unittest.TestCase):
|
|
"""The real first period: live for four hours, no invoice, no request metrics."""
|
|
|
|
@classmethod
|
|
def setUpClass(cls):
|
|
cls.report = evaluate(CONFIG, OBSERVATION, FORECAST, "2026-08")
|
|
|
|
def test_no_breach_and_no_false_pass(self):
|
|
self.assertEqual([], self.report["breaches"])
|
|
self.assertEqual(2, self.report["summary"]["within"])
|
|
self.assertEqual(6, self.report["summary"]["unmeasured"])
|
|
self.assertEqual(1, self.report["summary"]["not_applicable"])
|
|
|
|
def test_august_has_no_forecast_so_variance_thresholds_cannot_pass(self):
|
|
self.assertFalse(self.report["forecast_available"])
|
|
self.assertIn("abnormal-growth-stored", self.report["unmeasured"])
|
|
|
|
def test_what_was_actually_proven_reads_as_within(self):
|
|
within = [r["id"] for r in self.report["results"] if r["verdict"] == "within"]
|
|
self.assertEqual(["stale-backup", "restore-rto-regression"], within)
|
|
|
|
def test_commitment_threshold_is_not_applicable_without_a_commitment(self):
|
|
commitment = next(r for r in self.report["results"] if r["id"] == "unused-commitment")
|
|
self.assertEqual("not_applicable", commitment["verdict"])
|
|
|
|
def test_missing_period_is_an_error_not_an_empty_pass(self):
|
|
with self.assertRaises(ValueError):
|
|
evaluate(CONFIG, OBSERVATION, FORECAST, "2026-07")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|