Commit Graph

5 Commits

Author SHA1 Message Date
Thomas Bayes
23fdf49ff2 M4: resource agent, envelopes live, review loop, insight cards
Some checks are pending
ci / typescript (push) Waiting to run
ci / python (push) Waiting to run
ci / evals (push) Blocked by required conditions
- packages/domain: AwardNotice, DISPATCH_PLAN proposal payload, ExecutionReport,
  MeteringRecord, potential-assessment and dispatch-optimization contracts,
  ReviewFinding (+ typed writebacks), SemanticMemoryEntry,
  EnvelopeChangeRequest, InsightCard — exported with fixtures on both sides.
- skills-py: potential-assessment (certified × rolling fulfilment, evidence
  days) and dispatch-optimization (per-interval LP on HiGHS, shortfall
  reported) skills + routes + tests.
- packages/services: dispatch rules in the policy pack (over-allocation,
  award anchor, lineage integrity for allocations); PowerBalanceSimulator;
  SimulationGateway (permit-only, idempotent, seeded execute → ExecutionReports);
  envelope deviation-streak suspension + apply(); ReviewService (attribution,
  reliability EWMA writeback, semantic memory, envelope recommendations as
  change requests); dispatch assembler; skill client methods.
- packages/runtime: resource agent; award-decomposition, review and
  envelope-review workflows; lifecycle selects simulator/gateway by proposal
  type; trigger hooks for awards, execution reports, metering; decide()
  resumes either lifecycle or envelope-review runs; insight cards API.
- Tests: docs/07 D-1 16:00 and D+1 end to end; reliability score 0.9 → 0.880
  and the next assessment de-rates capacity; envelope suspension on a seeded
  3-day streak; WIDEN request applied only by a human. 184 TS + 80 Python.
- docs/open-questions: B10 (reliability/potential parameters). README and
  CLAUDE.md status → M4 done, M5 next.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01UoYoGYzHkFyv3ALenkRPhA
2026-09-02 19:31:12 -04:00
Thomas Bayes
1cc21e0dc6 M3: Mastra runtime, safety chain, two agents, Case Desk v1
Some checks are pending
ci / typescript (push) Waiting to run
ci / python (push) Waiting to run
ci / evals (push) Blocked by required conditions
- 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
2026-09-02 06:55:55 -04:00
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
Thomas Bayes
e7196bc88a M1: close gaps — CI, time-series/relational stores, ingestion skeleton, Python 3.11 pin
- .github/workflows/ci.yml: TS job (typecheck, re-export contracts, drift
  check, vitest) and Python job (3.11, regenerate pydantic models, drift
  check, pytest) — the dual-side contract test now actually runs in CI.
- packages/services: MemoryTimeSeriesStore (append-only daily-curve
  revisions), MemoryRepository + ResourceRegistry (schema-validated,
  optimistic versioning), IngestionPipeline (snapshot → quality gate →
  store or quarantine). In-memory reference semantics; persistent adapters
  arrive with M3 like the ledger.
- skills-py: .python-version + pyproject requires-python >=3.11; codegen
  script asserts interpreter version and runs the generator as a module.
- typecheck scripts per package and in root `check`; README status and dev
  setup; CLAUDE.md current-phase note.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01UoYoGYzHkFyv3ALenkRPhA
2026-09-01 21:58:49 -04:00
stewart hu
f681e134cc M1: domain schemas, contracts pipeline, ledger and snapshot services
- packages/domain: zod schemas for the 07-scenario object set with a
  schemaRegistry driving schema export, fixture generation, and Python
  module naming; decimal-string/sha256/curve primitives enforce the
  docs/11 §3.3 representation rules at the type layer
- contracts/: 12 JSON Schemas (draft 2020-12), 12 golden fixtures, 3
  invalid fixtures crafted to fail on both sides (float money, bad
  digest, missing concurrency version)
- skills-py: generated pydantic models (committed, never hand-edited),
  regeneration script, mirror pytest using JSON-mode validation —
  dual-side contract tests agree on all 15 fixtures
- packages/services: content-addressed immutable snapshot store
  (memory + fs, rejects floats), LedgerService v1 with optimistic
  concurrency and the P7 constraint cascade (monthly position bounds
  day-ahead bids; no-anchor bids rejected), quality-gate stub
- cascade band shape is an OPEN-QUESTION A5 placeholder (pro-rata
  daily share ±band) — see ledger.ts checkCascade

All green: tsc typecheck, 41 TS tests, 15 Python tests.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_019u5SLNweVio6ozJX7yfxQr

🔮 View transcript: https://logs.lojong.info/s/e8u90k3t33w590r7b5y7yzqh
2026-09-01 21:50:22 -04:00