# CLAUDE.md

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

## Keeping This File Up to Date

Update this file whenever a lesson is learned during development. Specifically, update CLAUDE.md when:

- A non-obvious architectural decision is made or discovered
- A gotcha, footgun, or surprising behavior is encountered (and the fix/workaround)
- A new command, workflow, or tool is added to the project
- A convention is established that isn't obvious from reading the code
- An integration detail is clarified (e.g., how the IPC protocol actually behaves, edge cases in the agent tool call cycle)

Do **not** add things already derivable from reading the code, generic best practices, or ephemeral task notes — only durable, reusable knowledge.

## Repository Layout

This is a **monorepo with git submodules**. Each submodule is an independent repo with its own `.claude/CLAUDE.md` for detailed guidance.

| Directory | What | Submodule |
|-----------|------|-----------|
| **`adiuvAI/`** | Electron desktop app (TypeScript/React) | `git.muticolturano.com/adiuvAI/adiuvAI` |
| **`api/`** | FastAPI backend (Python) | `git.muticolturano.com/adiuvAI/api` |
| **`website/`** | Landing page (single `index.html`) | `git.muticolturano.com/adiuvAI/website` |
| **`docs/`** | Planning docs & working memory (not a submodule) | -- |

After cloning, run `git submodule update --init --recursive` to populate submodule contents.

---

## adiuvAI (Electron App)

> **Detailed docs**: `adiuvAI/.claude/CLAUDE.md` covers commands, architecture, AI subsystem, design context, and conventions in depth.

### Commands

```bash
cd adiuvAI
npm run start     # Start dev server (Electron + Vite)
npm run lint      # ESLint
npm run knip      # Dead code analysis
npm run make      # Build installers (Windows/Linux/macOS)
npm run package   # Package without creating installers
npx drizzle-kit generate  # Generate migration from schema changes
npx drizzle-kit push      # Push schema directly (dev only)
```

No test suite currently.

### Architecture

```
Renderer (React 19 + TanStack Router)
  ↓ custom ipcLink (NOT electron-trpc — incompatible with tRPC v11)
Preload (contextBridge: window.electronTRPC + window.electronAI)
  ↓ IPC channels
Main Process (Node.js)
  ├── tRPC router (all CRUD + AI procedures)
  ├── SQLite (better-sqlite3 + Drizzle ORM, WAL mode)
  ├── LanceDB (vector embeddings, 1536-dim text-embedding-3-small)
  └── LangGraph orchestrator (3 specialist agents, pluggable LLM providers)
```

**This is a local-first app.** All user data (tasks, notes, projects) lives in local SQLite. The AI system (LangGraph + LangChain) runs entirely in the Electron main process with pluggable providers (OpenAI, Anthropic, GitHub Copilot).

**IPC channels**:
- `'trpc'` — bidirectional tRPC request/response (all CRUD)
- `'ai:stream'` — one-way token streaming from main → renderer
- `'ai:action'` — AI side-effects (e.g., task auto-created by agent)

**Key source paths**:
- `src/main/ipc.ts` — Custom tRPC↔IPC bridge
- `src/main/router/index.ts` — All tRPC routers (~600 LOC)
- `src/main/ai/orchestrator.ts` — LangGraph intent routing + 3 agents (~991 LOC)
- `src/main/db/schema.ts` — 6 tables (clients, projects, tasks, checkpoints, notes, taskComments)
- `src/renderer/routes/` — File-based routing (TanStack Router auto-generates `routeTree.gen.ts`)
- `src/renderer/components/ui/` — shadcn/ui primitives (new-york theme, neutral colors)
- `src/main/auth/auth-manager.ts` — Login, register, logout, OAuth flow (singleton)
- `src/main/auth/backup-key.ts` — Device-specific AES-256 backup key (safeStorage, not password-derived)
- `src/main/ai/token.ts` — Two-tier token storage: safeStorage + electron-store fallback
- `src/main/auth/locale-defaults.ts` — Detects timezone, date/time format, language from OS locale
- `src/main/api/format-row.ts` — Formats timestamp columns in query results using user's FormatPrefs

**Non-obvious details**:
- `electron-trpc` is NOT used — custom IPC bridge in `ipc.ts` + `ipcLink.ts` because electron-trpc bundles tRPC v10 internals
- Vite configs use `.mts` extension to avoid ESM/CJS conflicts with electron-forge
- `forge.config.ts` has complex cross-compilation hooks (downloads platform-specific native binaries for better-sqlite3 and LanceDB)
- DB has no foreign key constraints — cascade deletes are implemented in tRPC procedures
- Timestamps are milliseconds (JavaScript `Date.getTime()`), not ISO strings
- Notes auto-embed to LanceDB on create/update (fire-and-forget, errors swallowed)

**Settings Page (shared between Electron and Web)**:
- The Settings page is designed to run in **both** the Electron app and a standalone web SPA (future landing-page user portal). The same React components are used — no duplication.
- **Platform Adapter pattern**: `PlatformProvider` context (`src/renderer/lib/platform.tsx`) exposes `isElectron`/`isWeb`/`hasLocalAgents`/`hasFileDialog` flags. Components use `usePlatform()` to conditionally render Electron-only features (device ID, local agent filesystem) or disable them on web.
- **6 sections**: Profile, AI Preferences, Account, Billing, Appearance, Agents. Sidebar nav with icons in `types.ts` (`SECTIONS` array).
- **Web build**: `vite.web.config.mts` builds a standalone SPA to `dist-web/`. Entry: `web.html` → `src/renderer/web-main.tsx` (uses `httpBatchLink` via `src/renderer/lib/httpLink.ts` instead of `ipcLink`). Scripts: `npm run dev:web`, `npm run build:web`, `npm run preview:web`.
- **Electron-only gating**: Device ID card and local agent filesystem features are gated behind `platform.isElectron`. On web, local agents are visible but disabled (not hidden).
- **Gotcha**: Do NOT add Electron-specific settings (e.g. server URL, native file pickers) without wrapping in `platform.isElectron`. The same component tree renders on web.

**Onboarding Wizard**:
- First-run wizard collects 5 fields: `job_role`, `industry`, `primary_use_case`, `tone_preference`, `language`. Plus `user_name` derived from profile `name`+`surname`.
- All fields stored as encrypted core memory (backend `MemoryMiddleware`), not local electron-store.
- `onboarding_completed_at` on the `users` table (nullable TIMESTAMPTZ) gates the flow — `null` = show wizard, non-null = skip.
- `AppShell.tsx` gates: if `profile.onboardingCompletedAt == null` → render `<OnboardingFlow>` instead of the app.
- `auth.status` tRPC procedure auto-seeds `language` and `user_name` into MemoryCore if missing (fire-and-forget `.catch(() => {})`).
- Format prefs (timezone, dateFormat, timeFormat) are stored in electron-store (`FormatPrefs`), not core memory — they're device-specific.
- `drizzle-executor.ts` wraps all query results through `formatRow()`/`formatRows()` using the user's FormatPrefs.
- Settings > Profile section allows post-onboarding editing of all fields + format prefs.
- **Gotcha — shadcn Button `outline` variant in dark mode**: The variant defines `dark:bg-input/30 dark:border-input dark:hover:bg-input/50` which overrides any custom `className` background. Fix: switch between `variant="default"` and `variant="outline"` instead of adding className overrides.
- **Gotcha — locale codes vs human names**: `app.getLocale()` and `navigator.language` return codes like `en-US`. Use `Intl.DisplayNames(undefined, { type: 'language' })` to convert to "English". This must be done in both the main process (`locale-defaults.ts`) and renderer (`OnboardingFlow.tsx`).

**i18n (Internationalization)**:
- Uses `i18next` + `react-i18next` with bundled JSON translations (no lazy loading).
- Config in `src/renderer/i18n.ts`. 5 languages: EN, IT, ES, FR, DE. `SUPPORTED_LANGUAGES` array exported for UI selectors.
- Translation files: `src/renderer/locales/{en,it,es,fr,de}/translation.json`. Namespaces: `nav`, `auth`, `tasks`, `settings`, `common`, `errors`, `home`, `timeline`, `projects`, `agents`.
- **`common.*` namespace** holds shared labels (`save`, `cancel`, `delete`, `edit`, `add`, `rename`, `saving`, `deleting`, `creating`, `renameDescription`, `deleteTitle`). Before adding a new key, check if `common.*` already has it.
- Pluralization uses i18next `_one`/`_other` suffixes (e.g. `tasksDueToday_one`, `tasksDueToday_other`).
- `LanguageSync` component in `src/renderer/index.tsx` reads persisted `uiLanguage` from electron-store via tRPC on startup and syncs to i18next.
- Language selector lives in `GeneralSection.tsx` (Settings > General). On change it: (1) calls `i18n.changeLanguage()`, (2) persists to electron-store via `setUiLanguage` mutation, (3) writes to backend core memory so AI responds in the same language.
- `getUiLanguage()` exported from `src/main/store.ts` — used by `orchestrator.ts` to append language hint to daily brief prompt.
- Static data arrays that need translation use `labelKey` pattern (not `label`): store a translation key, call `t(labelKey)` at render time. Used in `NAV_ITEMS`, `COLUMNS`, `SECTIONS`, `SUGGESTION_CHIPS`.
- When adding new translated text: add the key to **all 5** JSON files. Keep `common.*` keys consistent across all languages.

**Google OAuth (adiuvAI side)**:
- `adiuvai://` is NOT accepted by Google as a redirect URI — Google only accepts `http://localhost` or `https://`. The API backend exposes `GET /auth/oauth/google/web-callback` which receives the Google redirect and immediately bounces to `adiuvai://oauth/callback?...`. The redirect URI registered in Google Cloud Console points to the backend, not the Electron app.
- `app.requestSingleInstanceLock()` is required for the `second-instance` event to fire on Windows/Linux. If it returns `false`, call `app.quit()` immediately (another instance is already running).
- In dev (`process.defaultApp === true`), `setAsDefaultProtocolClient('adiuvai')` must include `[path.resolve(process.argv[1])]` as the third argument so the OS protocol registration includes the entry script.
- `loginWithOAuth` uses `fetch()` directly (not `this.get()`) because the authorize endpoint is public — `get()` throws when not authenticated.
- The backup key in `backup-key.ts` is stored in `encryptedTokens` under the key `backup_key`, reusing `getToken/setToken` from `token.ts`. It is device-bound and never password-derived, so social-login users can use backup features without issue.

---

## api (FastAPI Backend)

### Commands

```bash
cd api

# Development
uvicorn app.main:app --reload --host 0.0.0.0 --port 8000

# Production
gunicorn app.main:app -k uvicorn.workers.UvicornWorker -w 4 --timeout 120

# Database migrations
alembic upgrade head

# Testing
pytest                           # all tests
pytest -v                        # verbose
pytest tests/test_agents.py      # single file
pytest tests/test_agents.py -k test_name  # single test

# Linting/formatting
ruff check .
ruff format .

# Docker (full stack: app + postgres + minio + qdrant)
docker compose up --build
```

### Architecture

```
FastAPI app (app/main.py)
├── Middleware: TierRateLimiter → Sanitizer → CORS
├── HTTP Routes (app/api/routes/)
│   ├── auth.py       — register, login, token refresh (bcrypt + HS256 JWT)
│   ├── chat.py       — POST /chat, WS /chat/stream
│   ├── plans.py      — execution plan playbooks
│   ├── storage.py    — E2E-encrypted cloud storage (S3)
│   ├── backup.py     — encrypted backup upload/download
│   ├── vectors.py    — encrypted vector upsert/search (Pinecone/Qdrant)
│   ├── plugins.py    — plugin marketplace (Power+ tier)
│   └── billing.py    — Stripe subscriptions
├── Agent System (app/agents/)
│   ├── task_agent.py       — 8 tools
│   ├── project_agent.py    — 6 tools
│   ├── checkpoint_agent.py — 4 tools
│   └── note_agent.py       — 5 tools
├── Orchestration (app/core/)
│   ├── orchestrator.py      — intent classification + agent routing
│   ├── agent_registry.py    — decorator-based agent registry
│   ├── execution_plan.py    — server-side prompt templates + plan builder
│   ├── llm.py               — LiteLLM factory (100+ providers)
│   └── memory_middleware.py
├── Billing (app/billing/)
│   ├── tier_manager.py      — feature matrix (Free/Pro/Power/Team)
│   └── stripe_service.py    — Stripe checkout + webhooks
├── Storage (app/storage/)     — S3 blob store, vector store, encryption
└── Marketplace (app/marketplace/) — plugin catalog, review, revenue sharing
```

**LLM routing**: `gpt-4o-mini` classifies intent → routes to domain agent → agent uses `gpt-4o` with tools → tool calls describe client-side operations (JSON) → Electron executes locally and returns results.

**Zero-trust data model**: The backend never stores or decrypts user content. PostgreSQL holds only auth, billing, plugin metadata, and storage record pointers. All user data is E2E-encrypted before leaving the Electron client.

**Key config**: `app/config/settings.py` — all env vars via Pydantic Settings. Copy `.env.example` to `.env` for local dev. Stripe and S3 gracefully stub when keys aren't configured.

**Database**: PostgreSQL with async SQLAlchemy 2.0 + asyncpg. 9 ORM models in `app/models.py`. Alembic migrations in `alembic/versions/`.

**Testing**: pytest + pytest-asyncio. Fixtures in `tests/conftest.py` create in-memory SQLite + moto-mocked S3. Test users seeded per tier (free/pro/power/team).

### Non-obvious details

- **Tier from DB, not JWT**: `get_current_user` decodes JWT but fetches authoritative tier from `subscriptions` table — tier changes take effect immediately without re-login
- **Refresh tokens hashed**: Plaintext returned to client, stored as SHA-256 in DB — server can never retrieve the plaintext (intentional)
- **WebSocket auth via query param**: `?token=<jwt>` instead of Bearer header (WebSocket handshake limitation)
- **Prompt IP protection**: `PromptTemplateRegistry` keeps prompts server-side; clients receive opaque `template_id`. `SanitizerMiddleware` strips leaked fragments from responses
- **Agents don't execute operations**: Tools return JSON describing client-side ops — the Electron client executes against local SQLite
- **Alembic async/sync split**: App uses `postgresql+asyncpg`, Alembic CLI needs `postgresql+psycopg2` — `env.py` handles the URL conversion
- **Tool loop cap**: Agent `_tool_loop` stops after 5 iterations to prevent infinite loops
- **Route order matters**: `/backup/history` must be declared before `/backup/{backup_id}` to avoid path param shadowing
- **CORS includes `app://`**: Electron uses custom `app://` protocol, not http/https
- **Vector search on encrypted data is not semantic**: Backend derives deterministic 32-dim floats from blob SHA-256 for storage/search — a known trade-off

**Onboarding (API side)**:
- `PUT /auth/me/memory` — updates core memory k/v pairs and optionally marks onboarding complete (`mark_onboarded: true` sets `users.onboarding_completed_at`).
- `POST /auth/me/onboarding/reset` — nullifies `onboarding_completed_at` so the wizard re-runs.
- `POST /auth/onboarding/normalize` — LLM-normalizes free-text onboarding inputs via `gpt-4o-mini`; returns inputs unchanged on error.
- `get_current_user()` in `auth.py` middleware now decrypts core memory blocks and includes them in `UserProfile.memory` dict.
- `users.onboarding_completed_at` is a nullable TIMESTAMPTZ column — returned as epoch ms (int) in UserProfile schema.

**i18n (API side)**:
- `_language_instruction()` in `app/core/deep_agent.py` reads the user's `language` from `MemoryCore` and appends a system prompt directive ("Always respond in {language}") to all 4 `run_*` functions.
- The Electron client writes the user's chosen language to backend core memory on language change, so the API picks it up on the next agent call.

**Google OAuth (api side)**:
- OAuth routes live in `app/api/routes/auth.py`: `GET /auth/oauth/{provider}/authorize`, `POST /auth/oauth/{provider}/callback`, `GET /auth/oauth/{provider}/web-callback` (bounces to deep link, excluded from OpenAPI schema).
- Provider abstraction in `app/auth/oauth_providers.py` — `GoogleOAuthProvider` uses `httpx` directly (no `authlib`). PKCE S256 is implemented manually via `generate_pkce_pair()`.
- `_pending_states` dict in `routes/auth.py` is **in-memory** — works for single-process dev but does not survive restarts and does not scale to multiple workers. Replace with Redis in production.
- `users.password_hash` is **nullable** — social-only users have `password_hash=None`. `await db.flush()` is required before creating a linked `OAuthAccount` to populate `new_user.id` before commit.
- `OAUTH_REDIRECT_URI` must point to the **API backend** (e.g. `https://api.adiuvai.com/...`), not the website domain. `adiuvai.com` is a static site with no server-side routing.
- **Unverified email + existing account = 409**: if `email_verified=False` and the email is already registered, the callback returns 409. Without this guard, branch 3 would attempt to INSERT a duplicate email and crash with a DB constraint violation (500).
- **Testing OAuth routes**: mock `GoogleOAuthProvider.exchange_code` and `get_userinfo` with `patch.object(..., new=AsyncMock(...))` — works because FastAPI instantiates a new provider per request. Use `monkeypatch.setattr(settings, "GOOGLE_AUTH_CLIENT_ID", ...)` to simulate configured credentials without restarting the app.

### Tier System

| Feature | Free | Pro | Power | Team |
|---------|------|-----|-------|------|
| Rate limit | 20/min | 60/min | 120/min | 200/min |
| Agents | 3 | unlimited | unlimited | unlimited |
| Cloud storage | 0 GB | 5 GB | 25 GB | unlimited |
| Plugin marketplace | no | no | yes | yes |

Enforced in `app/api/middleware/rate_limit.py` (sliding window) and `app/billing/tier_manager.py` (feature checks + quota enforcement).

---

## Cross-Project Integration

The Electron app and FastAPI backend communicate via **WebSocket** (`/chat/stream`):

1. Electron connects with `?token=<jwt>` query param
2. Client sends `ChatRequest` JSON frame
3. Server streams text chunks, then a final frame: `{"done": true, "response": "...", "actions": []}`
4. Server sends `tool_call` frames → Electron executes against local SQLite → returns `tool_result`
5. Server pings every 30 seconds to keep connection alive

The Electron app also has a **fully local AI path** (LangGraph orchestrator in main process) that doesn't require the backend — this is the primary path for desktop use.

---

## MCP Servers

- **Langfuse Docs** (`https://langfuse.com/api/mcp`) — configured at workspace level for prompt management documentation
- **shadcn** (`npx shadcn@latest mcp`) — configured in `adiuvAI/` for UI component generation