shu/vpp-ai-platform
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
9 Commits 1 Branch 0 Tags 33 MiB
e7196bc88a
Commit Graph

9 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
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
stewart hu
80835138e9 Scaffold repo for implementation handoff 
- README: orientation, doc map, target package layout (pointers only,
  no duplicated architecture content)
- CLAUDE.md: agent operating manual — invariants as code-review rules,
  conventions, do-not list, task reading order
- ROADMAP: M1-M5 with verifiable acceptance criteria, phase-2 fence
- GLOSSARY: canonical Chinese-term → code-name mapping
- docs/adr/: eight ADRs recording settled decisions and rejected
  alternatives
- docs/open-questions.md: consolidated TODO(业务) tracker by owner and
  blocking milestone
- .gitignore; untrack .DS_Store

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 21:13:00 -04:00
stewart hu
26c3b13dbd Add risk assessment and failure-mode analysis (doc 13) 
Blast-radius-organized FMEA: ranked top-5 risks (approval complacency,
correlated extreme days, stale-profile overcommitment, rule drift,
external dependency slips), per-domain failure tables with detection
and mitigation, new mechanisms (loss circuit-breaker, commitment
buffer, lineage-propagated data-quality flags, drill samples), and a
five-level kill-switch hierarchy with quarterly drills.

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 21:06:55 -04:00
stewart hu
6c999186c0 Add evaluation architecture (doc 12) 
Four-layer eval design (LLM tasks / skills / safety chain / end-to-end
decision quality), datasets built on event-log replay (I7), change
gates mapping each change type to required evals — envelope widening
approvable only on shadow/online L4 data — and measurable definitions
for the proposal's core KPIs.

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 21:03:25 -04:00
stewart hu
9d2ef6e432 Add interfaces and contracts reference (doc 11) 
Consolidates plane-boundary ports, service/event contracts, and the
canonical domain-object table (merged with peer review §12), plus the
TS↔Python strategy: zod as schema source, committed JSON Schema
artifacts, generated pydantic models, golden-fixture contract tests
in both CIs, and cross-language data-representation rules.

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 20:52:14 -04:00
stewart hu
11f19a661a Integrate peer review findings into architecture docs 
- 01: add eight testable hard invariants (self-approval ban, duty
  separation, digest-bound approvals, permit-only effects, LLM-less
  degraded operation)
- 03: approval staleness model — proposal digest, FRESH_CHECK/STALE
  states, APPROVED→AUTHORIZED split with revocable ExecutionPermit;
  gateways accept permits, never bare plans
- 05: rules packaged as versioned, testable Policy Packs pinned in
  proposal lineage
- 02: approval workbench reshaped into a Case Desk (DecisionCase as
  the operator's accountability unit)
- 10 (new): cross-province federation boundary — signed artifacts
  only, plus three phase-1 no-rework reservations
- 08: add M5 shadow-run milestone as phase-1 acceptance form
- 00/04/07: object table, doc map, and walkthrough consistency updates
- add brainstorming.md (peer review source document)

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 20:44:12 -04:00
stewart hu
76d6072052 Add Runtime implementation design (Mastra mapping) 
Doc 09: thin-shell Runtime over Mastra workflows/agents/tools —
proposal-lifecycle as a single durable workflow with suspend/resume
approval gates, lineage-enforced tool outputs (P2), outbox event bus,
and repo module structure.

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 20:24:32 -04:00
stewart hu
ef39d43757 init check in 2026-09-01 19:46:59 -04:00