# VPP AI Platform · 虚拟电厂多时空协同智能运营平台

AI-assisted operations platform for a virtual power plant (VPP) in Hubei, China:
five LLM agents propose market bids, resource dispatch, and load-control plans;
a deterministic safety chain (rule check → simulation → envelope/human approval →
execution permit) governs everything before any external effect. **The LLM never
computes numbers and never touches the second-level control loop.**

**Status: M1–M5 implemented (phase 1 feature-complete).** Design docs 00–14 are complete;
implementation follows [ROADMAP.md](ROADMAP.md). Present today:

- `packages/domain` — zod schemas for every business and safety-chain object, exported to
  `contracts/` and regenerated as pydantic models (`skills-py/vpp_contracts`).
- `packages/services` — deterministic services: ledger (with the P7 cascade), snapshot,
  time-series, relational and ingestion stores; policy engine + `hubei-spot-bidding` pack;
  envelope gate; authority (fresh check, permits, revocation); file-export gateway;
  event store/bus; lineage recorder + P2 assembler; revenue-scenario simulation; Case Desk.
- `skills-py/vpp_skills` — Python skill service: load/PV/price forecasts with calibrated
  quantiles, bid-optimization MILP, report generator.
- `packages/evals` — L2 eval harness with a committed baseline (on a **synthetic** dataset).
- `packages/runtime` — Mastra runtime: `proposal-lifecycle` (the safety chain, suspend/resume
  for human approval, durable across restarts), `day-ahead-situation`, `day-ahead-bid`;
  `award-decomposition` (resource agent: potential assessment → dispatch optimization →
  DISPATCH_PLAN through the same chain to a simulation gateway), `review` (D+1
  plan-vs-actual attribution → ReviewFinding → semantic memory + reliability writebacks +
  envelope change requests), `envelope-review` (the only path that changes an envelope,
  human-approved); envelope deviation-streak suspension; trigger service (scheduled / event /
  manual via router agent); provider-abstracted LLM port with an LLM-down mode; Case Desk
  HTTP API incl. AI insight cards. Bid release is a file export for manual upload (degraded
  channel by design) or, in shadow mode, a recorded-never-submitted receipt.
- **Shadow run (M5, the phase-1 acceptance form)**: `VPP_MODE=SHADOW` runs the full loop on
  live data with every external effect simulated — bids recorded, never submitted; the
  market's answer simulated from the actual clearing price; dispatch to the simulation
  gateway; D+1 review — and scores every day shadow-vs-human-vs-hindsight (`ShadowDayRecord`)
  with lineage-completeness audit, plus an auto-generated docs/12 §4 KPI report. Kill-switch
  hierarchy L0–L4 (`BreakerService`: permit revocation, envelope suspension, loss breaker,
  channel breaker, AI-off) with the abnormal-day protocol and an auditable drill
  (`POST /breakers/drill`). Replay driver: `npm run shadow -w @vpp/runtime -- --days 21`.

All eight docs/01 invariants have automated tests (`packages/services/test/chain.test.ts`,
`packages/runtime/test/lifecycle.test.ts`); the docs/07 D-1 16:00 and D+1 sections run in
`packages/runtime/test/m4.test.ts`; the ROADMAP M5 acceptance (21 consecutive shadow days with
complete lineage, KPI report, one widening recommendation not acted on) and the kill-switch
drill run in `packages/runtime/test/m5.test.ts`. Storage is file-backed reference semantics;
Postgres/Timescale adapters and the programmatic trading-platform channel are later work.
Next: run the shadow period on real Hubei data and close the business parameters in
`docs/open-questions.md`.

## Development

Requires Node 24 and Python 3.11 (`skills-py/.python-version`; the generated
pydantic models use `StrEnum` and PEP 604 unions).

```sh
npm ci
npm run check            # typecheck, re-export contracts, run TS tests
npm run eval -w @vpp/evals -- --check   # L2 harness vs baseline (needs the skill service below)
npm run start -w @vpp/runtime            # runtime + Case Desk API on :4100 (VPP_MODE=SHADOW default; VPP_LLM_MODEL unset = LLM-down mode)
npm run shadow -w @vpp/runtime -- --days 21   # replay 21 shadow days from the dataset through the live skill service

cd skills-py
uv venv --python 3.11 .venv && uv pip install -r requirements.txt   # or python3.11 -m venv
source .venv/bin/activate
bash scripts/generate_models.sh   # regenerate pydantic models (committed, never hand-edited)
python -m pytest -q
python -m uvicorn vpp_skills.app:app --port 8000   # skill service for the eval harness
```

CI (`.github/workflows/ci.yml`) runs both sides and fails if `contracts/` or
`skills-py/vpp_contracts` are not regenerated after a schema change.

## Orientation

| You are… | Start with |
|---|---|
| A coding agent about to implement | [CLAUDE.md](CLAUDE.md), then docs/00, 01, 09, 11 |
| New to the project | [docs/00-overview.md](docs/00-overview.md) → [docs/07-scenario-walkthrough.md](docs/07-scenario-walkthrough.md) (the end-to-end reference scenario) |
| Reviewing the business case | [proposal.md](proposal.md) (申报材料, source of requirements) |
| Looking for a settled decision | [docs/adr/](docs/adr/) |
| Wondering what's still undecided | [docs/open-questions.md](docs/open-questions.md) |

## Document map (docs are in Chinese; implementation-facing files in English)

| Doc | Content |
|---|---|
| [00-overview](docs/00-overview.md) | System context, two-plane architecture, business objects |
| [01-principles](docs/01-principles.md) | 9 principles + 8 hard invariants (binding for all code) |
| [02-cognitive-plane](docs/02-cognitive-plane.md) | Five agents, Runtime, memory, Case Desk |
| [03-safety-chain](docs/03-safety-chain.md) | Proposal state machine, envelopes, permits, staleness |
| [04-control-plane](docs/04-control-plane.md) | Execution engine, edge autonomy, time/space cascades |
| [05-skills-and-data](docs/05-skills-and-data.md) | Skill contracts, five-store data layer, policy packs |
| [06-integration](docs/06-integration.md) | External system boundaries and degraded channels |
| [14-shadow-run-runbook](docs/14-shadow-run-runbook.md) | Shadow-run operations, kill-switch levels (trigger / authority / recovery), KPI definitions as implemented |
| [07-scenario-walkthrough](docs/07-scenario-walkthrough.md) | Day-ahead spot bidding, D-1 → D → D+1 |
| [08-implementation](docs/08-implementation.md) | Stack, LLM abstraction, deployment, milestones |
| [09-runtime-implementation](docs/09-runtime-implementation.md) | Runtime on Mastra: workflows, suspend/resume, lineage |
| [10-federation](docs/10-federation.md) | Cross-province boundary: signed artifacts only |
| [11-contracts](docs/11-contracts.md) | Ports, canonical objects, TS↔Python contract pipeline |
| [12-evaluation](docs/12-evaluation.md) | Four-layer evals, change gates, KPI definitions |
| [13-risks-failure-modes](docs/13-risks-failure-modes.md) | FMEA, top-5 risks, kill-switch hierarchy |

Supporting: [brainstorming.md](brainstorming.md) is an independent peer review
whose findings were integrated (see docs/01 invariants note);
[GLOSSARY.md](GLOSSARY.md) maps Chinese domain terms to canonical code names.

## Target repository layout (from docs/09 §7)

```
packages/
├── domain/       # zod schemas — single source of truth for all business objects
├── runtime/      # Mastra instance, workflows, agents, tool registry, triggers
├── services/     # deterministic services: policy engine, envelopes, ledger, authority
├── adapters/     # anti-corruption layers: trading platform, dispatch, metering
├── evals/        # eval harness, datasets, judges (docs/12 §5)
└── skills-py/    # Python skill services (forecasting, MILP optimization, simulation)
contracts/        # generated JSON Schema + golden fixtures (cross-language contract)
```