dtoro
f1c4566576
Sets up the Socrata project repo with: docs/ — strategy and design documents - idea.md: full product vision - implementation-plan.md: Phase 0 + Phase 1 MVP plan - phase-0-validation.md: 2-week validation experiment strategy - phase-0-plan.md: concrete Phase 0 build plan - phase-0-results.md: Phase 0 gate outcome — GO for MVP - sysml-modeling.md: metamodel + SE discipline + validation rules - socrates.md: agent character, surfaces, modes, prompts, lifecycle - sync.md: bidirectional text↔diagram sync engineering - design-source/: HTML/CSS/JS handoff bundle from Claude Design phase-0/ — validated harness (CLI, no UI, no DB) - LM Studio (local OpenAI-compatible) generation + detection + judge - PlantUML rendering for SysML model visualization - 10-seed corpus (8 working + 2 holdouts) - 5 corpus runs with iteration history in reports/ - Final gate: 10/10 pass, mean 4.32/5, holdouts validated Phase 1 MVP scope and milestones documented in implementation-plan.md.
1.5 KiB
1.5 KiB
Socrata · Phase 0 Validation Harness
Validation experiment for the Socrata project. Runs a corpus of seed ideas through: seed → SysML model generation → PlantUML render → Socrates analysis (assumptions, risks, inconsistencies) → conversation → scoring.
See ../docs/phase-0-validation.md and ../docs/phase-0-plan.md for context.
Setup
pnpm install
cp .env.example .env.local # then fill in your LM Studio config
LM Studio must be running locally with a model loaded. Default endpoint: http://localhost:1234/v1.
Usage
pnpm phase0 hello # smoke test — round-trip a chat to LM Studio
pnpm phase0 render-test # render the Aristotle reference model as PlantUML PNG
pnpm phase0 run <seed-id> # full pipeline on one seed
pnpm phase0 corpus # all seeds (excluding holdouts)
Layout
src/
cli.ts entrypoint
types.ts shared types
llm/ LM Studio client + messages helper
generate/ seed → SysML model
socrates/ detect / converse / propose
render/ PlantUML serialization + rendering
eval/ rubric scoring + reports
prompts/ versioned prompt files (.md)
seeds/ corpus of test seed ideas (JSON)
outputs/ generated artifacts (gitignored)
reports/ committed run reports