vpp-ai-platform/skills-py/tests/test_report.py

64 lines
2.5 KiB
Python
Raw Permalink Normal View History

M2: skill contracts, Python skill service, L2 eval harness with baseline - packages/domain: ForecastRequest, BidOptimizationRequest/Result, ReportRequest, SkillReport (+ golden and invalid fixtures, exported to contracts/ and regenerated as pydantic models). - skills-py/vpp_skills: FastAPI service with versioned registry; load/PV/ price forecasts (same-day-type EWM point forecast, conformal residual quantiles — coverage test as acceptance gate); bid-optimization MILP on HiGHS (binary block participation, hard ledger energy bounds, exact Decimal fit of the rounded curve inside the bounds, revenue distribution over quantile paths); report generator whose every figure is a {tool_call_id, path} reference, with a verifier. 48 tests incl. hypothesis property test that bids respect ledger constraints. - packages/services: LedgerService.dayAheadBounds (the P7 cascade band handed to the optimizer); Decimal resolved once for CJS/ESM interop. - packages/evals: L2 metrics (MAPE, nRMSE, coverage, direction accuracy, naive/hindsight revenue baselines), HTTP skill client, rolling-origin harness that pushes each bid through the real ledger, CLI with --check/--write-baseline; committed baseline on the SYNTHETIC dataset (no historical Hubei data yet — baselines measure the harness, not KPI). - CI: evals job boots the skill service and fails on baseline digest drift. - docs/open-questions: A6 (flexibility marginal cost = offer floor); A4/B6 wired as placeholders. README/CLAUDE.md status → M2 done, M3 next. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01UoYoGYzHkFyv3ALenkRPhA
2026-09-02 06:29:08 -04:00
from __future__ import annotations
from datetime import datetime, timezone
from vpp_contracts.report_request import ReportRequest
from vpp_skills.report import generate_report, resolve, verify_report
CLOCK = lambda: datetime(2026, 3, 14, 8, 30, tzinfo=timezone.utc) # noqa: E731
SOLVER_OUTPUT = {
"market_date": "2026-03-15",
"prices_yuan_per_mwh": {"interval_minutes": 15, "date": "2026-03-15", "values": ["1.0"] * 96},
"daily_energy_mwh": "1200.000",
"expected_revenue_yuan": "510600.00",
"revenue_distribution_yuan": {"p10": "432000.00", "p50": "510600.00", "p90": "588000.00"},
"solver": {"name": "highs", "status": "OPTIMAL", "objective_value": "487020.00", "wall_time_ms": 12},
"binding_constraints": ["daily_energy_max"],
}
def _req(kind="DAY_AHEAD_BID_SUMMARY") -> ReportRequest:
return ReportRequest.model_validate(
{
"kind": kind,
"market_date": "2026-03-15",
"sources": [{"tool_call_id": "tc-001", "tool": "bid-optimization-milp", "version": "1.0.0", "output": SOLVER_OUTPUT}],
}
)
def test_every_metric_is_a_reference_that_resolves_to_its_value():
req = _req()
rep = generate_report(req, CLOCK)
names = {m.name for m in rep.sections[0].metrics}
assert {"expected_revenue_yuan", "daily_energy_mwh", "revenue_distribution_yuan.p10", "solver.objective_value"} <= names
assert "prices_yuan_per_mwh" not in " ".join(names) # curves are not inlined
assert verify_report(rep, req) == []
for m in rep.sections[0].metrics:
assert m.value == resolve(SOLVER_OUTPUT, m.ref.path)
assert m.ref.tool_call_id == "tc-001"
def test_units_inferred_from_field_names():
rep = generate_report(_req(), CLOCK)
units = {m.name: m.unit for m in rep.sections[0].metrics}
assert units["expected_revenue_yuan"] == "yuan"
assert units["daily_energy_mwh"] == "mwh"
assert units["revenue_distribution_yuan.p90"] == "yuan"
def test_notes_carry_solver_status_and_binding_constraints():
rep = generate_report(_req(), CLOCK)
notes = " | ".join(rep.sections[0].notes)
assert "solver status: OPTIMAL" in notes and "daily_energy_max" in notes
def test_deterministic_id_and_verify_catches_tampering():
req = _req()
a, b = generate_report(req, CLOCK), generate_report(req, CLOCK)
assert a.id == b.id and a.id.startswith("rep-day_ahead_bid_summary-2026-03-15-")
tampered = a.model_copy(deep=True)
tampered.sections[0].metrics[0].value = "999999.00"
assert verify_report(tampered, req)