shu/vpp-ai-platform
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: trim architecture brief header and footer
Some checks are pending
ci / typescript (push) Waiting to run
Details
ci / python (push) Waiting to run
Details
ci / evals (push) Blocked by required conditions
Details

Browse Source 
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Bg6jx9vHNHzB91qyV64GQ7
This commit is contained in:
Thomas Bayes 2026-09-02 13:00:00 -04:00
parent 19d24893c2
commit 8fac456d65
1 changed files with 1 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
docs/external/architecture-brief.en.md vendored
View File

@ -1,9 +1,7 @@
# VPP AI Platform — Architecture Brief
# VPP AI Platform — Architecture
**Virtual Power Plant Multi-Timescale Intelligent Operations Platform, built on the GuangMing Power LLM**
*Condensed external edition · English · v0.1 · September 2026 · Full version: [system-architecture.en.md](system-architecture.en.md)*
---
The platform is an AI-assisted decision and controlled-execution system for a virtual power plant in Hubei. Five LLM agents propose market bids, dispatch plans and load-control plans. A deterministic safety chain governs everything before any external effect. Three commitments define the design:
@ -66,9 +64,3 @@ Hand-written zod schemas are the single source of truth. The build exports JSON
![Evaluation-driven development](img/07-eval-driven.png)
Because every decision is replayable from retained evidence, the audit trail is also the evaluation dataset. Four layers localise problems: L1 LLM tasks, L2 professional-model skills, L3 safety-chain correctness including one automated test per invariant, and L4 end-to-end decision quality through shadow runs and historical backtests. Evaluation is a change gate. Prompt changes require the L1 set and an L4 backtest. A backend switch requires the full L1 set and an L4 shadow comparison. Skill upgrades must update their committed L2 baseline in the same change. Policy-pack upgrades require all rule tests green. Envelope widening is approved only on L4 shadow or online evidence. Every review finding becomes a candidate evaluation case, so failures feed the next baseline.
---
**Status.** Milestones M1 to M4 are delivered: schemas and contract pipeline, deterministic services, Python skills with a committed evaluation baseline, the runtime with the full safety chain, resource dispatch and review workflows, and the Case Desk. All eight invariants have passing automated tests, including the LLM-down run and rejection of AI self-approval. M5, a shadow run on live data with all external effects simulated, is next. Business parameters such as market windows, envelope bounds and loss budgets are held as named configuration pending confirmation by the operations team.
*Diagrams are generated from `diagrams/gen.mjs` via `diagrams/render.sh`.*