Shadow run (ROADMAP M5, phase-1 acceptance form): SHADOW runtime mode records
bids without submitting them, simulates the market answer from the actual
day-ahead clearing price, dispatches to the simulation gateway, runs the D+1
review, and scores every day shadow-vs-human-vs-hindsight (ShadowDayRecord)
with a lineage-completeness audit. KpiReport regenerated after every day per
docs/12 §4 definitions (C1/C2 placeholders as named config).
Kill switches (docs/13 §8): BreakerService with L0 permit revocation, L1
envelope suspension, L2 loss breaker (mark-to-market, reduce-only bids),
L3 channel breaker (bids fall back to the file channel, dispatch BLOCKED),
L4 AI-off (templates run, no Proposal created); abnormal-day protocol on
EXTREME situations; per-level authority (B8 placeholder); auditable drill.
Runtime: shadow-close workflow, shadow schedule entries, live-data ingestion
through the quality gate, human-bid ingestion, breaker/KPI/shadow endpoints
and insight cards, replay CLI (npm run shadow). Ledger, time series and
streak counters are file-backed so a multi-week run survives restarts.
Domain: HumanBidRecord, ShadowDayRecord, KpiReport, BreakerRecord, SHADOW
receipt channel; contracts, fixtures and pydantic models regenerated.
Services: L2 metrics moved from evals so the shadow run and the harness
share one implementation.
Fixes: envelope/permit validity compared ISO timestamps as strings
('…00Z' vs '…00.000Z'); L2 baseline was stale since M4 (skill_versions only,
metrics unchanged) — rewritten from the live service.
Docs: docs/14 shadow-run runbook (timeline, breaker trigger/authority/
recovery, KPI definitions as implemented); README and CLAUDE.md status.
Tests: 21 consecutive shadow days with complete lineage, KPI report, WIDEN
recommendation produced but not acted on; restart durability; drill; L2/L3/L4
and abnormal-day paths; API.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017wrZgPL9LoKaD69BpEQU4v
- 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
