381b6d3521
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
94 lines
2.7 KiB
Python
94 lines
2.7 KiB
Python
# generated by datamodel-codegen:
|
|
# filename: kpi_report.json
|
|
|
|
from __future__ import annotations
|
|
|
|
from enum import StrEnum
|
|
|
|
from pydantic import AwareDatetime, BaseModel, ConfigDict, Field, conint, constr
|
|
|
|
|
|
class Window(BaseModel):
|
|
model_config = ConfigDict(
|
|
extra='forbid',
|
|
)
|
|
from_: constr(pattern=r'^\d{4}-\d{2}-\d{2}$') | None = Field(..., alias='from')
|
|
to: constr(pattern=r'^\d{4}-\d{2}-\d{2}$') | None
|
|
days: conint(ge=0, le=9007199254740991)
|
|
|
|
|
|
class Id(StrEnum):
|
|
FORECAST_LOAD_MAPE = 'FORECAST_LOAD_MAPE'
|
|
FORECAST_PV_NRMSE = 'FORECAST_PV_NRMSE'
|
|
POTENTIAL_ACCURACY = 'POTENTIAL_ACCURACY'
|
|
DECISION_LATENCY_P95_MS = 'DECISION_LATENCY_P95_MS'
|
|
DISPATCH_SUCCESS_RATE = 'DISPATCH_SUCCESS_RATE'
|
|
REVENUE_UPLIFT_VS_HUMAN = 'REVENUE_UPLIFT_VS_HUMAN'
|
|
CROSS_REGION_MATCH = 'CROSS_REGION_MATCH'
|
|
|
|
|
|
class Comparator(StrEnum):
|
|
LTE = 'LTE'
|
|
GTE = 'GTE'
|
|
|
|
|
|
class Status(StrEnum):
|
|
MEET = 'MEET'
|
|
MISS = 'MISS'
|
|
NO_DATA = 'NO_DATA'
|
|
NOT_APPLICABLE = 'NOT_APPLICABLE'
|
|
|
|
|
|
class Kpi(BaseModel):
|
|
model_config = ConfigDict(
|
|
extra='forbid',
|
|
)
|
|
id: Id
|
|
value: constr(pattern=r'^-?\d+(\.\d+)?$') | None
|
|
unit: constr(min_length=1)
|
|
target: constr(pattern=r'^-?\d+(\.\d+)?$') | None
|
|
comparator: Comparator
|
|
samples: conint(ge=0, le=9007199254740991)
|
|
status: Status
|
|
definition: constr(min_length=1)
|
|
|
|
|
|
class Comparison(BaseModel):
|
|
model_config = ConfigDict(
|
|
extra='forbid',
|
|
)
|
|
shadow_yuan: constr(pattern=r'^-?\d+(\.\d+)?$')
|
|
human_yuan: constr(pattern=r'^-?\d+(\.\d+)?$') | None
|
|
hindsight_yuan: constr(pattern=r'^-?\d+(\.\d+)?$')
|
|
naive_yuan: constr(pattern=r'^-?\d+(\.\d+)?$')
|
|
capture_ratio: constr(pattern=r'^-?\d+(\.\d+)?$') | None
|
|
uplift_vs_naive: constr(pattern=r'^-?\d+(\.\d+)?$') | None
|
|
days_with_human_baseline: conint(ge=0, le=9007199254740991)
|
|
|
|
|
|
class Shadow(BaseModel):
|
|
model_config = ConfigDict(
|
|
extra='forbid',
|
|
)
|
|
days: conint(ge=0, le=9007199254740991)
|
|
complete_days: conint(ge=0, le=9007199254740991)
|
|
consecutive_complete_days: conint(ge=0, le=9007199254740991)
|
|
first_date: constr(pattern=r'^\d{4}-\d{2}-\d{2}$') | None
|
|
last_date: constr(pattern=r'^\d{4}-\d{2}-\d{2}$') | None
|
|
released_days: conint(ge=0, le=9007199254740991)
|
|
pending_days: conint(ge=0, le=9007199254740991)
|
|
widen_recommendations: conint(ge=0, le=9007199254740991)
|
|
breaker_trips: conint(ge=0, le=9007199254740991)
|
|
|
|
|
|
class KpiReport(BaseModel):
|
|
model_config = ConfigDict(
|
|
extra='forbid',
|
|
)
|
|
id: constr(min_length=1)
|
|
window: Window
|
|
kpis: list[Kpi]
|
|
comparison: Comparison
|
|
shadow: Shadow
|
|
generated_at: AwareDatetime
|