# CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

## Project Overview

Vaessl is an AI-powered integration bridge that accepts user text/image inputs, processes them through an LLM pipeline (via LiteLLM), and exports structured data to management systems (Homebox, WikiJS). The backend uses a provider pattern for extensibility, and the frontend is in early scaffolding stage.

## Commands

### Backend (Spring Boot + Gradle, inside `backend/`)
```bash
./gradlew build           # compile and package
./gradlew test            # run all tests
./gradlew test --tests com.vaessl.app.connection.ConnectionServiceTest  # single test class
```

### Frontend (React + Vite, inside `frontend/`)
```bash
npm run dev       # start dev server
npm run build     # TypeScript check + Vite build
npm run lint      # ESLint
npm run test      # Vitest watch mode
npm run test:ui   # Vitest visual dashboard
```

## Environment

Copy `.env.local` (not committed) into `backend/` with:
- `DB_URL`, `DB_TEST_URL`, `DB_USERNAME`, `DB_PASSWORD` — PostgreSQL (test container on port 5434)
- `OPENAI_KEY`, `OPENAI_BASE_URL` — LiteLLM gateway (provider-agnostic, configured for gpt-4o-mini)

## Architecture

### Backend (`backend/src/main/java/com/vaessl/app/`)

Three main modules:

**`connection/`** — core business logic
- `ConnectionProvider` interface: each integrated app (Homebox, WikiJS) implements `login()` and declares its `ServiceType`
- `ConnectionService`: auto-discovers providers via Spring injection, dispatches login by `ServiceType`
- Entity (`Connection`) uses **Single Table Inheritance** — one `connections` table with app-specific nullable columns
- DTOs use `Map<String, Object>` for flexible cross-app credential/result exchange

**`dto/`** — `ConnectionRequest` / `ConnectionResponse`

**`exception/`** — `GlobalExceptionHandler` via `@ControllerAdvice`

### Frontend (`frontend/src/`)

React 19 + TypeScript + Tailwind CSS, Vite 8 build. Currently basic scaffolding; no significant business logic yet.

### Data & AI

- PostgreSQL + pgvector (semantic search via embeddings)
- LiteLLM as a unified AI proxy; Spring AI OpenAI starter wired to it
- Processing pipeline (Phase 2): stage in DB → LLM inference → refine via UI → export to target app

### Testing Strategy

Integration tests spin up a **mirrored PostgreSQL container** on port 5434 (same schema as production). WireMock mocks external HTTP APIs (Homebox, WikiJS). Do not mock the database in integration tests — the mirrored container strategy exists specifically to catch schema/migration divergence.