- packages/domain: safety-chain objects (ValidationResult, SimulationResult, EnvelopeMatch, StaleDenial, ExecutionReceipt, LineageRef/BidProposalDraft, RouterDecision, BidExportFile) + fixtures on both sides. - packages/services: proposal digest; PolicyEngine + hubei-spot-bidding pack (digest-valid, bid-format, price-limits, quantity-non-negative, ledger-consistency, lineage-integrity, originator-permission — each with pass/fail tests); EnvelopeService; AuthorityService (fresh check, permits, revoke, gateway validate); FileExportGateway (idempotent receipts); Memory/File EventBus; LineageRecorder + P2 assembler; RevenueScenario simulator; CaseDeskService; FsRepository; skill HTTP client moved here. - packages/runtime: createRuntime (LibSQL storage, per-runtime workflow factories), proposal-lifecycle (rule check → simulation → envelope gate with suspend/resume → fresh check + permit → release), day-ahead-situation, day-ahead-bid, TriggerService (scheduled/event/manual), LlmPort (Mastra/Scripted/Null), Case Desk HTTP API, dev entry point. - Tests: all eight docs/01 invariants, docs/07 06:00→08:30 end to end with LLM down, restart survival of a suspended approval, permit expiry and revocation, replay of a released proposal, trigger scheduling. 141 TS + 60 Python tests. - Known gaps: ledger not yet persisted (replayed on restart); STALE ends the run instead of looping to rule check; synthetic data stands in for historical replay. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01UoYoGYzHkFyv3ALenkRPhA
85 lines
4.8 KiB
Markdown
85 lines
4.8 KiB
Markdown
# CLAUDE.md — agent operating manual
|
||
|
||
Design docs live in `docs/` (00–13, Chinese). They are the specification; this
|
||
file distills what is **binding** when writing code. When code and docs conflict,
|
||
docs win — or write an ADR changing the doc first.
|
||
|
||
## Current phase
|
||
|
||
Docs complete; M1–M3 implemented: schemas + contracts pipeline; deterministic
|
||
services (ledger, stores, policy engine, envelope, authority/permits, gateway,
|
||
events, lineage assembler, simulation, Case Desk); Python skill service; L2 eval
|
||
harness with committed baseline (synthetic data); Mastra runtime with the
|
||
proposal-lifecycle safety chain (durable suspend/resume), situation and bid
|
||
workflows, trigger service, LLM port with LLM-down mode, Case Desk API. Storage
|
||
is file-backed reference semantics — Postgres/Timescale adapters later. Next is
|
||
M4. Build order is ROADMAP.md (M1→M5). A skill change that moves an L2 metric
|
||
must update the baseline in the same change (`npm run eval -w @vpp/evals -- --write-baseline`).
|
||
Workflows are per-runtime factories (`createProposalLifecycle(ctx)` etc.) — never
|
||
module singletons, or a second Mastra instance steals their context.
|
||
Do not start a milestone's work before its predecessor's acceptance criteria are
|
||
testable, and do not build phase-2 items (edge control links, federation,
|
||
interaction/load-control agents) unless explicitly asked.
|
||
|
||
## Hard rules (from docs/01 invariants — treat as review criteria)
|
||
|
||
1. **LLM never computes numbers.** Any numeric field in a `Proposal` payload must
|
||
be a `{toolCallId, path}` reference into recorded tool-call lineage,
|
||
dereferenced by the assembler. If you find yourself parsing a number out of
|
||
LLM text into a payload, stop — that's the architecture's one forbidden move.
|
||
2. **No LLM in any control path.** Nothing under `services/` or the execution
|
||
path may import or await an LLM call. Periodic workflows must run with the
|
||
LLM backend down (invariant I6 — there is a test for this).
|
||
3. **External effects only via `(Proposal, ExecutionPermit)`.** Gateways/adapters
|
||
never accept a bare plan. Permits are short-lived and revocable.
|
||
4. **AI cannot approve.** No code path may transition a Proposal to
|
||
APPROVED/AUTHORIZED without either a matched envelope + passing checks, or a
|
||
human `resume()` with an approver identity distinct from the origination chain.
|
||
5. **Everything auditable.** State transitions, tool calls, approvals, permits,
|
||
and gateway receipts are event-sourced. Snapshots referenced by lineage are
|
||
immutable.
|
||
6. **Schemas live in `packages/domain` only.** Python models are generated from
|
||
`contracts/*.schema.json` — never hand-edit generated files, never define a
|
||
business object schema anywhere else.
|
||
|
||
## Conventions
|
||
|
||
- **Naming**: use the canonical code names in GLOSSARY.md. Do not invent new
|
||
English names for domain terms that already have one.
|
||
- **Language**: architecture docs Chinese; code, identifiers, comments, commit
|
||
messages, ADRs English.
|
||
- **Data representation** (docs/11 §3.3): money/energy/prices as fixed-point
|
||
decimal **strings**; units in field names (`power_mw`, `price_yuan_per_mwh`);
|
||
timestamps ISO8601 UTC; market intervals as `{date, interval_index}` with
|
||
`interval_minutes` explicit; all IDs strings; enums UPPER_SNAKE string literals.
|
||
- **Mastra**: do not trust memorized APIs — check `node_modules/@mastra/*/dist/docs/`
|
||
(or the mastra skill) against the installed version before writing framework code.
|
||
- **Testing floor**: every invariant above has at least one automated test;
|
||
schema changes run golden-fixture validation on both TS and Python sides;
|
||
policy pack changes require their rule tests green.
|
||
|
||
## Do not
|
||
|
||
- Do not invent business parameters (market deadlines, envelope bounds, loss
|
||
budgets, buffer coefficients). Check `docs/open-questions.md`; if a needed
|
||
parameter is listed there, wire it as named config with a placeholder value
|
||
and a `// OPEN-QUESTION:` comment, and say so in your summary.
|
||
- Do not relitigate decisions recorded in `docs/adr/`. If a decision must
|
||
change, propose a superseding ADR.
|
||
- Do not create root-level summary docs that duplicate `docs/` content
|
||
(no architecture.md / tech-stack.md — README points to the sources of truth).
|
||
- Do not add a sixth agent, merge the safety chain into business workflows, or
|
||
bypass the proposal lifecycle for "internal" effects — these were considered
|
||
and rejected (see ADRs 0005–0007).
|
||
|
||
## Reading order for common tasks
|
||
|
||
| Task | Read first |
|
||
|---|---|
|
||
| Domain schemas / contracts | docs/11, docs/00 §4, GLOSSARY.md |
|
||
| Runtime, workflows, agents | docs/09, docs/02 |
|
||
| Safety chain, approvals, permits | docs/03, docs/01 invariants |
|
||
| Skill services (Python) | docs/05 §1–2, docs/11 §3 |
|
||
| Anything touching money or bids | docs/07 (scenario), docs/13 §1 |
|
||
| Eval harness | docs/12 |
|