vpp-ai-platform/skills-py/tests/test_app.py
Thomas Bayes 8796faca63 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

61 lines
2.1 KiB
Python

"""HTTP contract: golden request fixtures go in, schema-valid responses come out."""
from __future__ import annotations
import json
from decimal import Decimal
from pathlib import Path
from fastapi.testclient import TestClient
from vpp_contracts.bid_optimization_result import BidOptimizationResult
from vpp_contracts.forecast_bundle import ForecastBundle
from vpp_contracts.skill_report import SkillReport
from vpp_skills.app import app
from .conftest import forecast_request
FIXTURES = Path(__file__).resolve().parents[2] / "contracts" / "fixtures"
client = TestClient(app)
def test_registry_lists_versions():
r = client.get("/v1/skills")
assert r.status_code == 200
ids = {s["id"]: s for s in r.json()}
assert ids["bid-optimization-milp"]["endpoint"] == "/v1/optimize/bid"
assert ids["load-forecast"]["version"] == "1.0.0"
def test_price_forecast_from_golden_fixture():
req = json.loads((FIXTURES / "forecast_request" / "price-da.json").read_text())
r = client.post("/v1/forecast/price", json=req)
assert r.status_code == 200, r.text
ForecastBundle.model_validate(r.json())
def test_kind_endpoint_mismatch_is_422(dataset):
r = client.post("/v1/forecast/pv", json=forecast_request(dataset, "LOAD", 30))
assert r.status_code == 422
def test_bid_optimization_from_golden_fixture():
req = json.loads((FIXTURES / "bid_optimization_request" / "da-basic.json").read_text())
r = client.post("/v1/optimize/bid", json=req)
assert r.status_code == 200, r.text
out = BidOptimizationResult.model_validate(r.json())
assert out.solver.status.value == "OPTIMAL"
assert Decimal("1140") <= Decimal(out.daily_energy_mwh) <= Decimal("1260")
def test_report_from_golden_fixture():
req = json.loads((FIXTURES / "report_request" / "da-bid-summary.json").read_text())
r = client.post("/v1/report", json=req)
assert r.status_code == 200, r.text
SkillReport.model_validate(r.json())
def test_schema_violation_is_422():
r = client.post("/v1/optimize/bid", json={"market_date": "2026-03-15"})
assert r.status_code == 422