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

794 B

Raw Blame History

ADR-0003: Provider-abstracted LLM

Status: accepted · 2026-09

Context: Production mandates 光明电力大模型 (on-prem, spec unknown at design time); development can't wait for access.

Decision: All LLM calls go through a capability-oriented abstraction with a model router: commercial API in dev, local open model in preprod, GuangMing adapter in prod. Conservative assumptions until spec arrives: OpenAI-compatible, 8K context, no native tool calling (degrade to prompt+JSON+retry). Backend swap is gated by the L1 eval suite plus L4 shadow comparison (docs/12 §3), not judgment.

Consequences: No vendor-specific features in agent code; prompts and tool definitions maintained provider-portable; phase-1 acceptance must not depend on GuangMing access (docs/13 §7).

794 B Raw Blame History

ADR-0003: Provider-abstracted LLM

794 B

Raw Blame History