update setting page

- Add _language_instruction() to deep_agent.py, reads language from core memory
- Append language directive to all 4 run_* functions (task/project/checkpoint/note)
- Minor fixes: alembic env, route imports, test cleanup

.env.example

@@ -2,7 +2,7 @@
 ENV=dev
 
 # ── Database ──────────────────────────────────────────────────────────────────
-DATABASE_URL=postgresql+asyncpg://postgres:postgres@localhost:5432/adiuva
+DATABASE_URL=postgresql+asyncpg://postgres:postgres@localhost:5432/adiuvai
 
 # ── Auth ──────────────────────────────────────────────────────────────────────
 JWT_SECRET=replace-with-a-long-random-secret
@@ -13,38 +13,57 @@ JWT_REFRESH_TOKEN_EXPIRE_DAYS=30
 # ── LLM ───────────────────────────────────────────────────────────────────────
 # LiteLLM model identifiers — change to swap providers without code changes.
 # Examples: gpt-4o, anthropic/claude-sonnet-4-20250514, gemini/gemini-pro, ollama/llama3
+#
+# API keys — only the key(s) matching your chosen provider(s) are required.
+# The correct key is picked automatically from the model prefix (e.g.
+# "anthropic/..." → ANTHROPIC_API_KEY, "gemini/..." → GOOGLE_API_KEY).
 OPENAI_API_KEY=
 ANTHROPIC_API_KEY=
 GOOGLE_API_KEY=
-LLM_MODEL=gpt-4o
-LLM_ROUTER_MODEL=gpt-4o-mini
+CEREBRAS_API_KEY=
+
+# Default model used by any agent that does not have a specific override below.
+LLM_MODEL=gpt-5-mini
+LLM_EMBED_MODEL=text-embedding-3-small
+
+# GitHub Copilot — leave empty to use the LiteLLM default token directory.
+# In Docker, point this to a named-volume path so tokens survive restarts.
+# GITHUB_COPILOT_TOKEN_DIR=
+
+# ── Per-agent model overrides ─────────────────────────────────────────────────
+# Leave a value empty to fall back to LLM_MODEL.
+# Each agent resolves its API key from the model prefix automatically.
+#
+# Intent classifier — routes user messages to the right domain agent.
+# A small/fast model (e.g. gpt-4o-mini) is usually sufficient here.
+LLM_MODEL_CLASSIFIER=
+
+# Home-agent — handles chat from the home screen (all tools available).
+LLM_MODEL_HOME_AGENT=
+
+# Floating-agent — handles contextual chat triggered from a task/project/note.
+LLM_MODEL_FLOATING_AGENT=
+
+# Unified-processor — processes local directory files (local agent runner).
+LLM_MODEL_UNIFIED_PROCESSOR=
+
+# Cloud-processor — fetches and processes data from cloud connectors.
+LLM_MODEL_CLOUD_PROCESSOR=
+
+# Setup-agent — guided journey to build an AgentConfig via WebSocket chat.
+LLM_MODEL_SETUP_AGENT=
 
 # ── Stripe (leave empty to stub billing) ──────────────────────────────────────
 STRIPE_SECRET_KEY=
 STRIPE_WEBHOOK_SECRET=
 
-# ── AWS / S3 ──────────────────────────────────────────────────────────────────
-S3_BUCKET=adiuva
-S3_REGION=us-east-1
-S3_ENDPOINT_URL=
-AWS_ACCESS_KEY_ID=
-AWS_SECRET_ACCESS_KEY=
-# For MinIO (homelab): S3_ENDPOINT_URL=http://minio:9000
-
-# ── Vector Store ──────────────────────────────────────────────────────────────
-# Pinecone is used when PINECONE_API_KEY is set; otherwise falls back to Qdrant.
-PINECONE_API_KEY=
-PINECONE_INDEX=adiuva
-QDRANT_URL=
-QDRANT_API_KEY=
-# For local Qdrant (homelab): QDRANT_URL=http://qdrant:6333
 
 # ── Langfuse (leave empty to disable observability) ───────────────────────────
 LANGFUSE_SECRET_KEY=
 LANGFUSE_PUBLIC_KEY=
-# LANGFUSE_HOST=https://cloud.langfuse.com        # EU (default)
-# LANGFUSE_HOST=https://us.cloud.langfuse.com     # US
-# LANGFUSE_HOST=http://localhost:3000             # Self-hosted
+# LANGFUSE_BASE_URL=https://cloud.langfuse.com        # EU (default)
+# LANGFUSE_BASE_URL=https://us.cloud.langfuse.com     # US
+# LANGFUSE_BASE_URL=http://localhost:3000             # Self-hosted
 
 # ── CORS ──────────────────────────────────────────────────────────────────────
 # Comma-separated list parsed by Settings (override default if needed)

.gitea/workflows/deploy.yaml

@@ -48,23 +48,23 @@ jobs:
           key: ${{ secrets.SSH_KEY }}
           script: |
             set -e
-            DEPLOY_DIR="/opt/adiuva-api"
+            DEPLOY_DIR="/opt/adiuvai-api"
             REPO_URL="http://10.0.0.119:3000/${{ gitea.repository }}.git"
             TAG="${{ gitea.ref_name }}"
 
             # ── Pull latest code ──
-            cd /tmp && rm -rf adiuva-api-deploy
-            git clone --depth 1 --branch "${TAG}" "${REPO_URL}" adiuva-api-deploy
+            cd /tmp && rm -rf adiuvai-api-deploy
+            git clone --depth 1 --branch "${TAG}" "${REPO_URL}" adiuvai-api-deploy
 
             # ── Sync source (preserve .env) ──
-            cp -rf /tmp/adiuva-api-deploy/app/ \
-                   /tmp/adiuva-api-deploy/alembic/ \
-                   /tmp/adiuva-api-deploy/alembic.ini \
-                   /tmp/adiuva-api-deploy/Dockerfile \
-                   /tmp/adiuva-api-deploy/docker-compose.yml \
-                   /tmp/adiuva-api-deploy/requirements.txt \
+            cp -rf /tmp/adiuvai-api-deploy/app/ \
+                   /tmp/adiuvai-api-deploy/alembic/ \
+                   /tmp/adiuvai-api-deploy/alembic.ini \
+                   /tmp/adiuvai-api-deploy/Dockerfile \
+                   /tmp/adiuvai-api-deploy/docker-compose.yml \
+                   /tmp/adiuvai-api-deploy/requirements.txt \
                    "$DEPLOY_DIR/"
-            rm -rf /tmp/adiuva-api-deploy
+            rm -rf /tmp/adiuvai-api-deploy
 
             # ── Verify .env ──
             if [ ! -f "$DEPLOY_DIR/.env" ]; then

.github/workflows/ci.yml

@@ -58,7 +58,7 @@ jobs:
       - uses: actions/checkout@v4
 
       - name: Build image
-        run: docker build -t adiuva-api:ci .
+        run: docker build -t adiuvai-api:ci .
 
       - name: Verify gunicorn installed
-        run: docker run --rm adiuva-api:ci gunicorn --version
+        run: docker run --rm adiuvai-api:ci gunicorn --version

.gitignore

@@ -21,6 +21,7 @@ env/
 .pytest_cache/
 htmlcov/
 .coverage
+tests/fixtures/private*/
 
 # Docker
 *.log

README.md

@@ -1,793 +0,0 @@
-# Adiuva Cloud API
-
-**AI-powered project management backend with E2E encrypted cloud storage, LLM orchestration, and a plugin marketplace.**
-
-Built with FastAPI · Python 3.12 · PostgreSQL · LangChain · Stripe · AWS S3
-
----
-
-## Table of Contents
-
-- [Overview](#overview)
-- [Architecture](#architecture)
-- [Key Features](#key-features)
-- [Tech Stack](#tech-stack)
-- [Getting Started](#getting-started)
-- [Docker Deployment](#docker-deployment)
-- [Environment Variables](#environment-variables)
-- [API Reference](#api-reference)
-- [Data Model](#data-model)
-- [AI Agent System](#ai-agent-system)
-- [Orchestration & Execution Plans](#orchestration--execution-plans)
-- [Middleware](#middleware)
-- [Storage Layer](#storage-layer)
-- [Billing & Tiers](#billing--tiers)
-- [Plugin Marketplace](#plugin-marketplace)
-- [Testing](#testing)
-- [Project Structure](#project-structure)
-- [License](#license)
-
----
-
-## Overview
-
-Adiuva Cloud API is the FastAPI backend that powers the **Adiuva Electron desktop app**. It provides LLM-powered chat orchestration, end-to-end encrypted cloud storage, a vector search engine, an encrypted backup system, a plugin marketplace with revenue sharing, and Stripe-based subscription billing across four tiers.
-
-### Design Principles
-
-1. **Never persist user data in plaintext** — the database stores only auth, billing, storage metadata, and marketplace data. All user content is E2E encrypted by the client before reaching the server.
-2. **Never expose prompts** — system prompts stay server-side; responses are sanitized to strip any leaked prompt fragments.
-3. **Never decrypt user blobs** — the backend performs only checksum verification; no decryption keys ever reach the server.
-4. **Stateless request handling** — all context comes from the client and JWT; no server-side session state.
-5. **Tier gates enforced server-side** — the server always reads the current tier from the database, never trusting client-reported values.
-
----
-
-## Architecture
-
-```
-┌──────────────┐      ┌────────────────────────────────────────────────────────┐
-│  Electron    │      │  FastAPI  (Uvicorn / Gunicorn)                         │
-│  Desktop App │────▶│                                                        │
-│  (Client)    │◀────│  Middleware: RateLimit → Sanitizer → CORS → Router     │
-└──────────────┘      │                                                        │
-                      │  ┌──────────────────┐  ┌────────────────────────────┐  │
-                      │  │  Auth Routes     │  │  Chat Routes               │  │
-                      │  │  Billing Routes  │  │    ↓                       │  │
-                      │  │  Storage Routes  │  │  Orchestrator (GPT-4o-mini)│  │
-                      │  │  Backup Routes   │  │    ↓ classify intent       │  │
-                      │  │  Plugin Routes   │  │  Agent Registry            │  │
-                      │  │  Vector Routes   │  │    ↓                       │  │
-                      │  │  Plans Routes    │  │  TaskAgent  | ProjectAgent │  │
-                      │  └──────────────────┘  │  NoteAgent  | CheckptAgent │  │
-                      │                        │  (GPT-4o + LangChain)      │  │
-                      │                        └────────────────────────────┘  │
-                      └────────────────────────────────────────────────────────┘
-                               │              │              │
-                      ┌────────▼───┐  ┌───────▼───────┐  ┌──▼─────────────┐
-                      │ PostgreSQL │  │  AWS S3       │  │ Pinecone /     │
-                      │ (Auth,     │  │  (E2E blobs,  │  │ Qdrant         │
-                      │  Billing,  │  │   backups)    │  │ (Vectors)      │
-                      │  Metadata) │  └───────────────┘  └────────────────┘
-                      └────────────┘
-                               │
-                      ┌────────▼───┐
-                      │  Stripe    │
-                      │  (Billing, │
-                      │   Connect) │
-                      └────────────┘
-```
-
----
-
-## Key Features
-
-1. **LLM-powered orchestration** — GPT-4o-mini classifies user intent and routes to the appropriate domain agent.
-2. **4 specialized AI agents** — Tasks (8 tools), Projects (6 tools), Timelines (4 tools), Notes (5 tools), all powered by GPT-4o via LangChain.
-3. **Execution plans & playbooks** — Server-side prompt template registry; clients receive only opaque template IDs, never raw prompts.
-4. **E2E encrypted cloud storage** — The backend never decrypts user data; SHA-256 checksum verification uses constant-time comparison to prevent timing attacks.
-5. **Cloud vector store** — Pinecone or Qdrant with user-isolated namespaces and encrypted blob payloads.
-6. **Encrypted backup system** — Tiered storage limits with `If-Modified-Since` support for efficient syncing.
-7. **Plugin marketplace** — Catalog, admin review/approval workflow, security checklist, and 70/30 revenue sharing via Stripe Connect.
-8. **Stripe billing** — Four-tier subscription model (Free / Pro / Power / Team) with checkout sessions and full webhook lifecycle handling.
-9. **JWT authentication** — Access + refresh tokens with bcrypt password hashing, SHA-256 token hashing, and automatic rotation.
-10. **Prompt IP protection** — Sanitizer middleware strips system prompts, reasoning markers, tool schemas, and agent routing metadata from all chat responses.
-11. **Tier-based rate limiting** — Sliding-window per-user limiter scaling from 20 to 200 requests/min by subscription tier.
-12. **Zero-trust data model** — User content is never stored in plaintext; the database holds only authentication, billing, and metadata records.
-13. **WebSocket streaming** — Real-time chat with 30-second heartbeat keep-alive and chunked text delivery.
-14. **Alembic migrations** — Versioned schema management with seed data for the plugin marketplace.
-15. **Comprehensive test suite** — In-memory SQLite + moto S3 mocks, per-tier test fixtures, and full API coverage without external dependencies.
-
----
-
-## Tech Stack
-
-| Package | Version | Purpose |
-|---|---|---|
-| `fastapi` | ≥ 0.115.0 | Web framework |
-| `uvicorn[standard]` | ≥ 0.34.0 | ASGI development server |
-| `gunicorn` | ≥ 22.0.0 | Production process manager |
-| `langchain` | ≥ 0.3.0 | LLM orchestration framework |
-| `langchain-openai` | ≥ 0.3.0 | OpenAI LLM provider integration |
-| `litellm` | ≥ 1.50.0 | Universal LLM gateway (100+ providers) |
-| `pydantic` | ≥ 2.10.0 | Data validation and serialization |
-| `pydantic-settings` | ≥ 2.7.0 | Environment-based configuration |
-| `python-jose[cryptography]` | ≥ 3.3.0 | JWT encoding and decoding |
-| `stripe` | ≥ 11.0.0 | Billing and payment integration |
-| `boto3` | ≥ 1.35.0 | AWS S3 client |
-| `slowapi` | ≥ 0.1.9 | Rate limiting utilities |
-| `sqlalchemy` | ≥ 2.0.0 | Async ORM and query builder |
-| `asyncpg` | ≥ 0.30.0 | PostgreSQL async driver |
-| `alembic` | ≥ 1.14.0 | Database migration management |
-| `bcrypt` | ≥ 4.2.0 | Password hashing |
-| `python-dotenv` | ≥ 1.0.0 | `.env` file loading |
-| `httpx` | ≥ 0.28.0 | Async HTTP client (used in tests) |
-| `websockets` | ≥ 14.0 | WebSocket protocol support |
-| `psycopg2-binary` | ≥ 2.9.0 | Synchronous PostgreSQL driver (Alembic) |
-| `pinecone` | ≥ 5.0.0 | Pinecone vector store client |
-| `qdrant-client` | ≥ 1.7.0 | Qdrant vector store client |
-| `pytest` | ≥ 8.0.0 | Test framework |
-| `pytest-asyncio` | ≥ 0.24.0 | Async test support |
-| `aiosqlite` | ≥ 0.20.0 | In-memory SQLite for tests |
-| `moto[s3]` | ≥ 5.0.0 | AWS S3 mock for tests |
-| `ruff` | ≥ 0.8.0 | Linter and formatter |
-
----
-
-## Getting Started
-
-### Prerequisites
-
-- Python 3.12+
-- PostgreSQL 16+
-- An OpenAI API key (for LLM features)
-- Stripe API keys (optional — billing stubs gracefully when unconfigured)
-- AWS credentials (optional — needed for S3 storage in production)
-
-### Installation
-
-```bash
-# Clone the repository
-git clone <repo-url> && cd adiuva-api
-
-# Create a virtual environment
-python -m venv .venv && source .venv/bin/activate
-
-# Install dependencies
-pip install -r requirements.txt
-
-# Configure environment
-cp .env.example .env
-# Edit .env with your DATABASE_URL, OPENAI_API_KEY, etc.
-```
-
-### Database Setup
-
-```bash
-# Start PostgreSQL (or use the Docker Compose database)
-docker compose up db -d
-
-# Run migrations
-alembic upgrade head
-```
-
-### Run the Development Server
-
-```bash
-uvicorn app.main:app --reload --host 0.0.0.0 --port 8000
-```
-
-Interactive API docs are available at [http://localhost:8000/docs](http://localhost:8000/docs) in development mode (`ENV=dev`). The `/docs` endpoint is disabled in production.
-
----
-
-## Docker Deployment
-
-### Quick Start
-
-```bash
-docker compose up --build
-```
-
-This starts two services:
-
-- **app** — FastAPI server on port `8000`
-- **db** — PostgreSQL 16 (Alpine) on port `5432` with a persistent volume and health checks
-
-The compose file also includes optional services for fully local deployments:
-
-- **minio** — S3-compatible object storage on ports `9000` (API) and `9001` (console)
-- **qdrant** — Vector search engine on ports `6333` (HTTP) and `6334` (gRPC)
-
-### Dockerfile Details
-
-The Dockerfile uses a multi-stage build:
-
-1. **Builder stage** — Installs Python dependencies into a virtual environment.
-2. **Runtime stage** — Copies only the venv, app source, and Alembic migrations. Runs as a non-root user (`appuser`).
-3. **Production server** — Gunicorn with 4 Uvicorn workers, 120-second timeout, listening on port 8000.
-
-```bash
-# Production command (run by the container)
-gunicorn app.main:app -k uvicorn.workers.UvicornWorker -w 4 --timeout 120 -b 0.0.0.0:8000
-```
-
----
-
-## Homelab / Self-Hosted Deployment
-
-You can run the entire stack locally on a homelab with **no cloud dependencies except the LLM provider**. The compose file includes MinIO (S3 replacement) and Qdrant (vector store) out of the box.
-
-### 1. Start all services
-
-```bash
-docker compose up -d
-```
-
-This starts PostgreSQL, MinIO, and Qdrant alongside the app.
-
-### 2. Create the MinIO bucket
-
-Open the MinIO console at [http://localhost:9001](http://localhost:9001) (login: `minioadmin` / `minioadmin`) and create a bucket named `adiuva`, or use the CLI:
-
-```bash
-docker compose exec minio mc alias set local http://localhost:9000 minioadmin minioadmin
-docker compose exec minio mc mb local/adiuva
-```
-
-### 3. Configure your `.env`
-
-```bash
-# Database (uses the compose PostgreSQL)
-DATABASE_URL=postgresql+asyncpg://postgres:postgres@db:5432/adiuva
-
-# S3 → MinIO
-S3_BUCKET=adiuva
-S3_REGION=us-east-1
-S3_ENDPOINT_URL=http://minio:9000
-AWS_ACCESS_KEY_ID=minioadmin
-AWS_SECRET_ACCESS_KEY=minioadmin
-
-# Vector store → local Qdrant (leave PINECONE_API_KEY empty)
-QDRANT_URL=http://qdrant:6333
-QDRANT_API_KEY=
-PINECONE_API_KEY=
-
-# Billing — leave empty to stub (no Stripe needed)
-STRIPE_SECRET_KEY=
-STRIPE_WEBHOOK_SECRET=
-
-# LLM — the only external service
-OPENAI_API_KEY=sk-...
-LLM_MODEL=gpt-4o
-LLM_ROUTER_MODEL=gpt-4o-mini
-
-# Auth
-JWT_SECRET=your-secret-here
-ENV=dev
-```
-
-### 4. Run migrations
-
-```bash
-docker compose exec app alembic upgrade head
-```
-
-### What runs where
-
-| Service | Runs on | Port | Notes |
-|---|---|---|---|
-| FastAPI app | Docker | 8000 | API server |
-| PostgreSQL | Docker | 5432 | Auth, billing, metadata |
-| MinIO | Docker | 9000 / 9001 | S3-compatible blob & backup storage |
-| Qdrant | Docker | 6333 / 6334 | Vector search (replaces Pinecone) |
-| Stripe | — | — | Stubbed when keys are empty |
-| OpenAI / LLM | Cloud | — | Only external dependency |
-
-> **Want fully offline AI too?** Set `LLM_MODEL=ollama/llama3` and `LLM_ROUTER_MODEL=ollama/llama3`, then add an Ollama container or point at a local Ollama instance. See the [LLM provider switching](#switching-llm-providers) section.
-
----
-
-## Environment Variables
-
-All variables are loaded from a `.env` file via Pydantic Settings. Source: `app/config/settings.py`
-
-| Variable | Type | Default | Description |
-|---|---|---|---|
-| `DATABASE_URL` | `str` | `postgresql+asyncpg://postgres:postgres@localhost:5432/adiuva` | Async SQLAlchemy connection string |
-| `JWT_SECRET` | `str` | `change-me-in-production` | HMAC secret for JWT signing |
-| `JWT_ALGORITHM` | `str` | `HS256` | JWT signing algorithm |
-| `JWT_ACCESS_TOKEN_EXPIRE_MINUTES` | `int` | `30` | Access token time-to-live |
-| `JWT_REFRESH_TOKEN_EXPIRE_DAYS` | `int` | `30` | Refresh token time-to-live |
-| `STRIPE_SECRET_KEY` | `str` | `""` | Stripe API key (empty = stub mode) |
-| `STRIPE_WEBHOOK_SECRET` | `str` | `""` | Stripe webhook signature secret |
-| `S3_BUCKET` | `str` | `""` | S3 bucket for encrypted blobs and backups |
-| `S3_REGION` | `str` | `us-east-1` | AWS region |
-| `S3_ENDPOINT_URL` | `str` | `""` | Custom S3 endpoint (e.g. `http://minio:9000` for MinIO). Leave empty for AWS. |
-| `AWS_ACCESS_KEY_ID` | `str` | `""` | AWS credentials |
-| `AWS_SECRET_ACCESS_KEY` | `str` | `""` | AWS credentials |
-| `PINECONE_API_KEY` | `str` | `""` | Pinecone API key (if set, Pinecone is used for vectors) |
-| `PINECONE_INDEX` | `str` | `adiuva` | Pinecone index name |
-| `QDRANT_URL` | `str` | `""` | Qdrant URL (used when Pinecone is not configured) |
-| `QDRANT_API_KEY` | `str` | `""` | Qdrant API key |
-| `OPENAI_API_KEY` | `str` | `""` | OpenAI key for LLM agent calls |
-| `LLM_MODEL` | `str` | `gpt-4o` | LiteLLM model identifier for agents (e.g. `anthropic/claude-3.5-sonnet`, `gemini/gemini-pro`, `ollama/llama3`) |
-| `LLM_ROUTER_MODEL` | `str` | `gpt-4o-mini` | Lighter model used for intent classification / routing |
-| `CORS_ORIGINS` | `list[str]` | `["app://.", "http://localhost:3000", "http://localhost:5173"]` | Allowed CORS origins |
-| `ENV` | `Literal` | `dev` | `dev` or `prod` — controls `/docs` visibility and SQL echo |
-
----
-
-## API Reference
-
-All routes are prefixed with `/api/v1`. **27 endpoints** total (25 REST + 1 WebSocket + 1 health check).
-
-### Health
-
-| Method | Path | Auth | Description |
-|---|---|---|---|
-| `GET` | `/api/v1/health` | No | Returns `{"status": "ok", "version": "0.1.0"}` |
-
-### Auth
-
-| Method | Path | Auth | Description |
-|---|---|---|---|
-| `POST` | `/api/v1/auth/register` | No | Create account with bcrypt-hashed password, returns `AuthTokens` |
-| `POST` | `/api/v1/auth/login` | No | Validate credentials, returns `AuthTokens` |
-| `POST` | `/api/v1/auth/refresh` | No | Rotate refresh token, returns new `AuthTokens` |
-| `GET` | `/api/v1/auth/me` | JWT | Returns `UserProfile` for the authenticated user |
-
-### Chat
-
-| Method | Path | Auth | Description |
-|---|---|---|---|
-| `POST` | `/api/v1/chat` | JWT | Route message through the orchestrator; returns `ChatResponse` or `ExecutionPlan` depending on execution mode |
-| `WS` | `/api/v1/chat/stream` | JWT (query param `?token=`) | Streaming chat — first frame is a `ChatRequest`, server yields text chunks, final frame is `{"done": true, "response": "...", "actions": [...]}`. 30-second heartbeat ping. |
-
-### Plans
-
-| Method | Path | Auth | Description |
-|---|---|---|---|
-| `GET` | `/api/v1/plans/playbook` | JWT | List all cached execution plan playbooks |
-| `GET` | `/api/v1/plans/playbook/{plan_id}` | JWT | Retrieve a specific playbook by ID |
-
-### Storage (Cloud Records)
-
-| Method | Path | Auth | Description |
-|---|---|---|---|
-| `POST` | `/api/v1/storage/records` | JWT | Upload an E2E encrypted record (verifies checksum, enforces storage quota) |
-| `GET` | `/api/v1/storage/records` | JWT | List record metadata with pagination (`?table`, `?page`, `?limit`); no blob bytes returned |
-| `GET` | `/api/v1/storage/records/{id}` | JWT | Download encrypted blob with `X-Checksum` response header |
-| `PUT` | `/api/v1/storage/records/{id}` | JWT | Replace an existing blob (verifies checksum, enforces quota) |
-| `DELETE` | `/api/v1/storage/records/{id}` | JWT | Delete a record and its S3 blob |
-
-### Vectors (Cloud Vector Store)
-
-| Method | Path | Auth | Description |
-|---|---|---|---|
-| `POST` | `/api/v1/storage/vectors/upsert` | JWT | Verify checksums and upsert encrypted vectors |
-| `POST` | `/api/v1/storage/vectors/search` | JWT | Search user-scoped vector namespace |
-| `DELETE` | `/api/v1/storage/vectors` | JWT | Delete vectors by ID list |
-
-### Backup
-
-| Method | Path | Auth | Description |
-|---|---|---|---|
-| `PUT` | `/api/v1/backup` | JWT | Upload encrypted backup blob with custom headers (`X-Backup-Version`, `X-Backup-Timestamp`, `X-Backup-Checksum`). Tier quota enforced. |
-| `GET` | `/api/v1/backup` | JWT | Download latest backup blob. Supports `If-Modified-Since`. |
-| `GET` | `/api/v1/backup/history` | JWT | List backup metadata (no blob content) |
-| `DELETE` | `/api/v1/backup/{backup_id}` | JWT | Delete a specific backup |
-
-### Plugins (Marketplace)
-
-| Method | Path | Auth | Description |
-|---|---|---|---|
-| `GET` | `/api/v1/plugins` | JWT (Power+) | Browse the marketplace (`?category`, `?q`, `?page`, `?sort=rating\|installs\|newest`) |
-| `GET` | `/api/v1/plugins/{id}` | JWT (Power+) | Plugin detail with install count and ratings |
-| `POST` | `/api/v1/plugins/{id}/install` | JWT (Power+) | Install plugin; triggers Stripe Connect revenue split for paid plugins |
-| `DELETE` | `/api/v1/plugins/{id}/install` | JWT | Uninstall plugin |
-
-### Billing
-
-| Method | Path | Auth | Description |
-|---|---|---|---|
-| `POST` | `/api/v1/billing/checkout` | JWT | Create a Stripe checkout session, returns `{"checkout_url": "..."}` |
-| `POST` | `/api/v1/billing/webhook` | Stripe signature | Handle Stripe events: `checkout.session.completed`, `customer.subscription.updated`, `customer.subscription.deleted`, `invoice.payment_failed` |
-| `GET` | `/api/v1/billing/subscription` | JWT | Get current subscription information |
-| `DELETE` | `/api/v1/billing/subscription` | JWT | Cancel subscription and revert to free tier |
-
----
-
-## Data Model
-
-9 tables managed by Alembic migrations. Source: `app/models.py`
-
-### Tables
-
-| Table | Primary Key | Key Columns | Purpose |
-|---|---|---|---|
-| `users` | `id` (UUID) | `email` (unique), `password_hash`, `tier`, `stripe_customer_id`, timestamps | User accounts |
-| `refresh_tokens` | `id` (UUID) | `user_id` (FK), `token_hash` (SHA-256, unique), `expires_at` | Hashed refresh tokens for rotation |
-| `subscriptions` | `id` (UUID) | `user_id` (FK, unique), `stripe_subscription_id`, `tier`, `status`, `current_period_end` | Stripe subscription records |
-| `storage_records` | `id` (UUID) | `user_id` (FK), `table_name`, `s3_key`, `checksum`, `size_bytes`, timestamps | S3 blob metadata (no plaintext content) |
-| `backup_metadata` | `id` (UUID) | `user_id` (FK), `s3_key`, `version`, `timestamp`, `checksum`, `size_bytes` | Backup manifests |
-| `plugins` | `id` (String) | `name`, `description`, `version`, `author_id` (FK), `category`, `price_cents`, `permissions` (JSON), `status`, `s3_package_key`, `install_count`, `avg_rating` | Marketplace plugin catalog |
-| `plugin_installations` | `id` (UUID) | `plugin_id` (FK), `user_id` (FK), unique constraint on (`plugin_id`, `user_id`) | Per-user install tracking |
-| `plugin_reviews` | `id` (UUID) | `plugin_id` (FK), `reviewer_id` (FK), `decision`, `notes`, `reviewed_at` | Admin review decisions |
-| `revenue_events` | `id` (UUID) | `plugin_id` (FK), `user_id` (FK), `amount_cents`, `developer_share_cents`, `stripe_transfer_id` | 70/30 revenue split ledger |
-
-### Enum Types
-
-| Enum | Values |
-|---|---|
-| `billing_tier` | `free`, `pro`, `power`, `team` |
-| `plugin_status` | `pending_review`, `approved`, `rejected` |
-| `review_decision` | `approved`, `rejected` |
-
-### Migrations
-
-| Version | Description |
-|---|---|
-| `001_initial_schema` | Creates all 9 tables with indexes and foreign key constraints |
-| `002_seed_plugins` | Seeds 3 approved plugins: GitHub Sync (free), Slack Notifier (€4.99), Time Tracker (€9.99) |
-
----
-
-## AI Agent System
-
-The agent system uses a registry pattern with LangChain tool-calling agents powered by GPT-4o. Source: `app/agents/`, `app/core/agent_registry.py`
-
-### Architecture
-
-- **`BaseAgent`** — Abstract base with `user_id`, `shared_memory`, and `vector_store_context`.
-- **`ChatAgent(BaseAgent)`** — Abstract `handle(query, context)` and `get_tools()` methods, plus a shared `_tool_loop(llm, messages, tools, max_iter=5)` for iterative tool calling.
-- **`AgentRegistry`** — Singleton registry with `@register` decorator, `get(name)`, `list_agents()`, and `call_agent(name, query, context)`.
-
-### Registered Agents
-
-| Agent | Registry Name | Tools | Description |
-|---|---|---|---|
-| **TaskAgent** | `task_agent` | 8 | Full task and comment CRUD. Status: `todo` / `in_progress` / `done`. Priority: `high` / `medium` / `low`. Tools: `list_tasks`, `create_task`, `update_task`, `delete_task`, `list_tasks_due_today`, `list_task_comments`, `add_task_comment`, `delete_task_comment` |
-| **ProjectAgent** | `project_agent` | 6 | Project lifecycle management. Status: `active` / `archived`. Prefers archiving over deletion. Tools: `list_projects`, `list_all_projects`, `get_project`, `create_project`, `update_project`, `delete_project` |
-| **TimelineAgent** | `timeline_agent` | 4 | Project milestones. Requires `project_id` for creation. Supports AI-suggestion and approval workflows. Tools: `list_timelines`, `create_timeline`, `update_timeline`, `delete_timeline` |
-| **NoteAgent** | `note_agent` | 5 | Markdown note management. Optionally linked to projects. Tools: `list_notes`, `get_note`, `create_note`, `update_note`, `delete_note` |
-
-All agents use the model configured by `LLM_MODEL` (default: GPT-4o) with `temperature=0` via LiteLLM. Tools return JSON action descriptors that the Electron client interprets and applies locally.
-
-### Switching LLM Providers
-
-The backend uses **LiteLLM** as a universal LLM gateway. All agents and the orchestrator instantiate models through a centralized factory in `app/core/llm.py`. To switch providers, change environment variables — no code changes required:
-
-```bash
-# OpenAI (default)
-LLM_MODEL=gpt-4o
-LLM_ROUTER_MODEL=gpt-4o-mini
-
-# Anthropic
-LLM_MODEL=anthropic/claude-3.5-sonnet
-LLM_ROUTER_MODEL=anthropic/claude-3-haiku
-
-# Google Gemini
-LLM_MODEL=gemini/gemini-pro
-LLM_ROUTER_MODEL=gemini/gemini-flash
-
-# Local Ollama
-LLM_MODEL=ollama/llama3
-LLM_ROUTER_MODEL=ollama/llama3
-
-# AWS Bedrock
-LLM_MODEL=bedrock/anthropic.claude-v2
-LLM_ROUTER_MODEL=bedrock/anthropic.claude-instant-v1
-```
-
-See the [LiteLLM provider docs](https://docs.litellm.ai/docs/providers) for the full list of 100+ supported providers and model naming conventions.
-
----
-
-## Orchestration & Execution Plans
-
-Source: `app/core/orchestrator.py`, `app/core/execution_plan.py`
-
-### Orchestrator
-
-1. **`classify_intent(message, context, registry)`** — Uses the router model (`LLM_ROUTER_MODEL`, default: GPT-4o-mini) to determine which agent should handle a message. Falls back to `task_agent` when classification is ambiguous.
-2. **`route_single(agent_name, message, context)`** — Routes to a single agent and returns a `ChatResponse`.
-3. **`route_pipeline(agent_names, message, context)`** — Executes agents sequentially; each receives `previous_results` from earlier agents. A final LLM synthesis step merges all results.
-4. **`orchestrate(request)`** — Main entry point. In `direct` mode, returns a `ChatResponse`. In `plan` mode, returns an `ExecutionPlan`.
-5. **`orchestrate_stream(request)`** — Streaming variant that yields 50-character text chunks with a final JSON frame.
-
-### Execution Plans
-
-- **`PromptTemplateRegistry`** — Maps template IDs to server-side prompt text. Clients only ever see opaque IDs, never raw prompts.
-- **`ExecutionPlanBuilder`** — Fluent builder API: `add_step()`, `add_llm_step(template_id, vars)`, `add_data_step(action, data_from_step)`. Validates step references on `build()`.
-- **`PlanCache`** — LRU cache (maxsize 1000) for storing plans as reusable playbooks.
-
-### Built-in Templates (6)
-
-`tpl_task_agent_default`, `tpl_timeline_agent_default`, `tpl_project_agent_default`, `tpl_note_agent_default`, `tpl_task_extract_from_project`, `tpl_note_weekly_summary`
-
-### Built-in Playbooks (2)
-
-| Playbook | Description |
-|---|---|
-| `create_tasks_from_project` | LLM extracts actionable tasks from project context, then creates task records |
-| `generate_weekly_note` | LLM generates a weekly summary, then creates a note record |
-
----
-
-## Middleware
-
-Middleware executes in this order on each request: **TierRateLimit → Sanitizer → CORS → Router**
-
-### JWT Authentication
-
-Source: `app/api/middleware/auth.py`
-
-- FastAPI dependency `get_current_user` validates the `Bearer` JWT and extracts `user_id` and `email`.
-- **Live tier lookup** — The current tier is fetched from the `subscriptions` table on every request (not cached in the JWT), so upgrades and downgrades take immediate effect.
-- Falls back to `free` when no subscription row exists.
-- Raises `401 Unauthorized` on invalid or expired tokens.
-- **Exempt paths:** `/api/v1/auth/register`, `/api/v1/auth/login`, `/api/v1/billing/webhook`
-
-### Tier-Based Rate Limiter
-
-Source: `app/api/middleware/rate_limit.py`
-
-- `TierRateLimitMiddleware` — Sliding-window in-process rate limiter (no Redis dependency).
-- Per-user 60-second window sized by subscription tier:
-
-| Tier | Requests / Minute |
-|---|---|
-| Free | 20 |
-| Pro | 60 |
-| Power | 120 |
-| Team | 200 |
-
-- Returns `429 Too Many Requests` with a `Retry-After` header when the limit is exceeded.
-- **Exempt paths:** register, login, webhook, health
-
-### Response Sanitizer
-
-Source: `app/api/middleware/sanitizer.py`
-
-- Runs only on `/api/v1/chat` endpoints.
-- Scans JSON response bodies and replaces leaked prompt IP fragments with `[REDACTED]`.
-- Detects: system prompt openers, agent routing metadata, LangChain tool schemas, internal reasoning markers (`<thinking>`, `[INST]`), and known prompt fingerprints.
-- Logs sanitization events as `WARNING`.
-- Binary responses (storage, backup) are never touched.
-
----
-
-## Storage Layer
-
-### Blob Store
-
-Source: `app/storage/blob_store.py`
-
-- S3-backed storage for E2E encrypted blobs.
-- Object keys follow the pattern: `{user_id}/{table}/{record_id}`
-- Server-side SSE-S3 encryption at rest (additional layer on top of client-side E2E encryption).
-- Methods: `upload()`, `download()`, `delete()` (idempotent), `list_keys()`
-- The backend **never inspects or decrypts blob content**.
-
-### Vector Store
-
-Source: `app/storage/vector_store.py`
-
-- Runtime-configurable: **Pinecone** (when `PINECONE_API_KEY` is set) or **Qdrant** (fallback).
-- User isolation: Pinecone uses `namespace=user_id`; Qdrant filters by `user_id` payload field.
-- 32-dimensional SHA-256-derived float vectors (deterministic, not semantically meaningful on encrypted data — a documented trade-off for privacy).
-- Encrypted blobs are stored as base64 in metadata/payload for verbatim retrieval.
-- Methods: `upsert()`, `search()`, `delete()`
-
-### Encryption Utilities
-
-Source: `app/storage/encryption.py`
-
-- `verify_checksum(blob, checksum)` — SHA-256 hash comparison using `hmac.compare_digest` (constant-time to prevent timing attacks).
-- `reject_if_tampered(blob, checksum)` — Raises HTTP 400 on checksum mismatch.
-- **No decryption key ever reaches the backend.**
-
----
-
-## Billing & Tiers
-
-Source: `app/billing/stripe_service.py`, `app/billing/tier_manager.py`
-
-### Feature Matrix
-
-| Feature | Free | Pro | Power | Team |
-|---|---|---|---|---|
-| AI Agents | 3 | Unlimited | Unlimited | Unlimited |
-| Batch Active | 2 | 10 | Unlimited | Unlimited |
-| Cloud Storage | 0 GB | 5 GB | 25 GB | Unlimited |
-| Backup Storage | 0 GB | 5 GB | 25 GB | Unlimited |
-| LLM Providers | 1 | Unlimited | Unlimited | Unlimited |
-| Batch Builder | — | — | ✓ | ✓ |
-| Plugin Marketplace | — | — | ✓ | ✓ |
-| SSO | — | — | — | ✓ |
-| Rate Limit | 20 req/min | 60 req/min | 120 req/min | 200 req/min |
-
-### Stripe Integration
-
-- **Checkout** — `create_checkout_session(user_id, tier)` creates a Stripe Checkout session. Returns a stub URL when Stripe is not configured.
-- **Webhooks** — Handles `checkout.session.completed`, `customer.subscription.updated`, `customer.subscription.deleted`, and `invoice.payment_failed`.
-- **Subscription management** — `get_subscription()` returns the current subscription record; `cancel_subscription()` cancels via the Stripe API and reverts the user to the free tier.
-- **Price IDs:** `price_pro_monthly`, `price_power_monthly`, `price_team_monthly`
-
-### Tier Manager
-
-- `get_tier(user_id)` — Returns the user's current billing tier.
-- `check_feature(tier, feature)` — Boolean feature gate check.
-- `require_feature(tier, feature)` — Raises HTTP 403 if the feature is not available.
-- `enforce_quota(user_id, tier)` / `enforce_backup_quota(user_id, tier)` — Raises HTTP 402 if storage limits are exceeded.
-
----
-
-## Plugin Marketplace
-
-Source: `app/marketplace/`
-
-### Plugin Registry
-
-- PostgreSQL-backed catalog of submitted and approved plugins.
-- `list_plugins(db, category, query, page, sort)` — Paginated listing (page size: 20) with optional filtering by category, text search, and sorting by `rating`, `installs`, or `newest`.
-- `get_plugin(db, plugin_id)` — Full manifest with install count and ratings.
-- `submit_plugin(db, manifest, s3_key)` — Submits a plugin with `pending_review` status.
-- `approve_plugin()` / `reject_plugin(reason)` — Admin workflow for plugin approval.
-- `record_install()` / `record_uninstall()` — Tracks per-user installations and updates install counts.
-
-### Review Queue
-
-- Automated security checklist before human review:
-  - Plugin ID must match `^[a-z0-9-]+$`
-  - Permissions must be from the allowed set only
-  - No binary blobs in the manifest
-- **Allowed permissions:** `read:tasks`, `write:tasks`, `read:projects`, `write:projects`, `read:notes`, `write:notes`, `read:timelines`, `write:timelines`, `read:calendar`, `write:calendar`
-- `get_pending(db)` — Lists plugins awaiting review.
-- `submit_review(db, plugin_id, reviewer_id, decision, notes)` — Records the review decision.
-
-### Revenue Sharing
-
-- **70% developer / 30% platform** split on all paid plugin sales.
-- `record_install(db, plugin_id, user_id, amount_cents)` — Records the revenue event and triggers a Stripe Connect transfer for the developer share.
-- `get_earnings(db, developer_id, period)` — Aggregated earnings report for plugin developers.
-- Gracefully stubs transfers when Stripe is not configured.
-
-### Seed Plugins
-
-| Plugin | Category | Price |
-|---|---|---|
-| GitHub Sync | Productivity | Free |
-| Slack Notifier | Communication | €4.99 |
-| Time Tracker | Productivity | €9.99 |
-
----
-
-## Testing
-
-### Running Tests
-
-```bash
-# Run all tests
-pytest
-
-# Run a specific test file
-pytest tests/test_auth.py
-
-# Run with verbose output
-pytest -v
-```
-
-### Test Infrastructure
-
-- **Database:** Async SQLite in-memory via `aiosqlite` + `StaticPool` — fast, no PostgreSQL needed.
-- **S3 mock:** `moto[s3]` with a fixture that patches `BlobStore` settings.
-- **Auth helpers:** `make_jwt(tier)` and `auth_header(tier)` generate per-tier test tokens.
-- **Seed data:** Auto-creates one `User` + `Subscription` per tier (free/pro/power/team) before each test.
-- **Plugin seeds:** Fixture adds 3 approved plugins for marketplace tests.
-- **FK enforcement:** SQLite `PRAGMA foreign_keys=ON`.
-- **No external dependencies** — all tests run fully offline.
-
-### Test Coverage
-
-| File | Coverage |
-|---|---|
-| `test_auth.py` | Register, login, token access, refresh, expiration |
-| `test_orchestrator.py` | Intent classification, single agent routing, pipeline, plan mode |
-| `test_agents.py` | Each agent with mocked LLM: registration, tools, handle method |
-| `test_storage.py` | Create, list, download, update, delete records; checksum rejection; quota enforcement |
-| `test_backup.py` | Upload, download, history, delete; tier-based storage limits |
-| `test_plugins.py` | List, install, uninstall, revenue events, tier gate enforcement |
-| `test_agent_registry.py` | Registry singleton, registration, lookup, listing |
-| `test_execution_plan.py` | Plan builder, template registry, plan cache |
-| `test_middleware.py` | Rate limiting by tier, sanitizer prompt leak detection |
-
----
-
-## Project Structure
-
-```
-adiuva-api/
-├── alembic.ini                  # Alembic configuration
-├── BACKEND_PLAN.md              # Architecture & design decisions
-├── docker-compose.yml           # Docker Compose (app + PostgreSQL)
-├── Dockerfile                   # Multi-stage production build
-├── requirements.txt             # Python dependencies
-│
-├── alembic/                     # Database migrations
-│   ├── env.py                   # Alembic environment config
-│   ├── script.py.mako           # Migration template
-│   └── versions/
-│       ├── 001_initial_schema.py    # Tables, indexes, FKs
-│       └── 002_seed_plugins.py      # Seed marketplace plugins
-│
-├── app/                         # Application source
-│   ├── main.py                  # FastAPI app factory, middleware, routes
-│   ├── db.py                    # Async SQLAlchemy engine & session
-│   ├── models.py                # SQLAlchemy ORM models (9 tables)
-│   ├── schemas.py               # Pydantic request/response schemas
-│   │
-│   ├── config/
-│   │   └── settings.py          # Pydantic Settings (env vars)
-│   │
-│   ├── agents/                  # LLM-powered domain agents
-│   │   ├── task_agent.py        # Task & comment CRUD (8 tools)
-│   │   ├── project_agent.py     # Project lifecycle (6 tools)
-│   │   ├── timeline_agent.py  # Milestones (4 tools)
-│   │   └── note_agent.py        # Markdown notes (5 tools)
-│   │
-│   ├── core/                    # Orchestration engine
-│   │   ├── agent_registry.py    # BaseAgent, ChatAgent, AgentRegistry
-│   │   ├── llm.py               # LiteLLM factory (get_llm, get_router_llm)
-│   │   ├── orchestrator.py      # Intent classification & routing
-│   │   └── execution_plan.py    # Plan builder, templates, cache
-│   │
-│   ├── api/                     # HTTP layer
-│   │   ├── deps.py              # Shared FastAPI dependencies
-│   │   ├── middleware/
-│   │   │   ├── auth.py          # JWT validation, live tier lookup
-│   │   │   ├── rate_limit.py    # Sliding-window tier rate limiter
-│   │   │   └── sanitizer.py     # Prompt IP leak protection
-│   │   └── routes/
-│   │       ├── auth.py          # Register, login, refresh, me
-│   │       ├── chat.py          # Chat + WebSocket streaming
-│   │       ├── plans.py         # Execution plan playbooks
-│   │       ├── storage.py       # E2E encrypted record CRUD
-│   │       ├── vectors.py       # Vector upsert, search, delete
-│   │       ├── backup.py        # Encrypted backup management
-│   │       ├── plugins.py       # Marketplace browse & install
-│   │       └── billing.py       # Stripe checkout & webhooks
-│   │
-│   ├── storage/                 # Storage backends
-│   │   ├── blob_store.py        # S3 blob storage
-│   │   ├── vector_store.py      # Pinecone / Qdrant vector store
-│   │   └── encryption.py        # Checksum verification utilities
-│   │
-│   ├── billing/                 # Subscription management
-│   │   ├── stripe_service.py    # Stripe API integration
-│   │   └── tier_manager.py      # Feature matrix & quota enforcement
-│   │
-│   └── marketplace/             # Plugin ecosystem
-│       ├── plugin_registry.py   # Catalog CRUD & search
-│       ├── plugin_review.py     # Security checklist & review queue
-│       └── revenue_share.py     # 70/30 split & Stripe Connect
-│
-└── tests/                       # Test suite
-    ├── conftest.py              # Fixtures: DB, S3, auth, seeds
-    ├── test_auth.py
-    ├── test_orchestrator.py
-    ├── test_agents.py
-    ├── test_storage.py
-    ├── test_backup.py
-    ├── test_plugins.py
-    ├── test_agent_registry.py
-    ├── test_execution_plan.py
-    └── test_middleware.py
-```
-
----
-
-## License
-
-*To be determined.*

alembic/env.py

@@ -16,7 +16,7 @@ import re
 from logging.config import fileConfig
 
 from alembic import context
-from sqlalchemy import engine_from_config, pool
+from sqlalchemy import pool
 from sqlalchemy.ext.asyncio import create_async_engine
 
 # Alembic Config object (gives access to alembic.ini values).

alembic/versions/001_initial_schema.py

@@ -1,5 +1,4 @@
-"""Initial schema: users, refresh_tokens, subscriptions, storage_records,
-backup_metadata, plugins, plugin_installations, plugin_reviews, revenue_events.
+"""Initial schema: users, refresh_tokens, subscriptions.
 
 Revision ID: 001
 Revises:
@@ -28,18 +27,6 @@ def upgrade() -> None:
         EXCEPTION WHEN duplicate_object THEN NULL;
         END $$;
     """)
-    op.execute("""
-        DO $$ BEGIN
-            CREATE TYPE plugin_status AS ENUM ('pending_review', 'approved', 'rejected');
-        EXCEPTION WHEN duplicate_object THEN NULL;
-        END $$;
-    """)
-    op.execute("""
-        DO $$ BEGIN
-            CREATE TYPE review_decision AS ENUM ('approved', 'rejected');
-        EXCEPTION WHEN duplicate_object THEN NULL;
-        END $$;
-    """)
 
     # ── users ─────────────────────────────────────────────────────────────
     op.create_table(
@@ -88,122 +75,10 @@ def upgrade() -> None:
     op.create_index("ix_subscriptions_user_id", "subscriptions", ["user_id"])
     op.create_index("ix_subscriptions_stripe_id", "subscriptions", ["stripe_subscription_id"])
 
-    # ── storage_records ───────────────────────────────────────────────────
-    op.create_table(
-        "storage_records",
-        sa.Column("id", postgresql.UUID(as_uuid=False), nullable=False),
-        sa.Column("user_id", postgresql.UUID(as_uuid=False), nullable=False),
-        sa.Column("table_name", sa.String(100), nullable=False),
-        sa.Column("s3_key", sa.String(500), nullable=False),
-        sa.Column("checksum", sa.String(64), nullable=False),
-        sa.Column("size_bytes", sa.Integer, nullable=False),
-        sa.Column("created_at", sa.DateTime(timezone=True), nullable=False, server_default=sa.text("now()")),
-        sa.Column("updated_at", sa.DateTime(timezone=True), nullable=False, server_default=sa.text("now()")),
-        sa.PrimaryKeyConstraint("id"),
-        sa.ForeignKeyConstraint(["user_id"], ["users.id"], ondelete="CASCADE"),
-    )
-    op.create_index("ix_storage_records_user_id", "storage_records", ["user_id"])
-
-    # ── backup_metadata ───────────────────────────────────────────────────
-    op.create_table(
-        "backup_metadata",
-        sa.Column("id", postgresql.UUID(as_uuid=False), nullable=False),
-        sa.Column("user_id", postgresql.UUID(as_uuid=False), nullable=False),
-        sa.Column("s3_key", sa.String(500), nullable=False),
-        sa.Column("version", sa.Integer, nullable=False),
-        sa.Column("timestamp", sa.BigInteger, nullable=False),
-        sa.Column("checksum", sa.String(64), nullable=False),
-        sa.Column("size_bytes", sa.Integer, nullable=False),
-        sa.Column("created_at", sa.DateTime(timezone=True), nullable=False, server_default=sa.text("now()")),
-        sa.PrimaryKeyConstraint("id"),
-        sa.ForeignKeyConstraint(["user_id"], ["users.id"], ondelete="CASCADE"),
-    )
-    op.create_index("ix_backup_metadata_user_id", "backup_metadata", ["user_id"])
-
-    # ── plugins ───────────────────────────────────────────────────────────
-    op.create_table(
-        "plugins",
-        sa.Column("id", sa.String(255), nullable=False),
-        sa.Column("name", sa.String(255), nullable=False),
-        sa.Column("description", sa.Text, nullable=False, server_default=""),
-        sa.Column("version", sa.String(50), nullable=False, server_default="1.0.0"),
-        sa.Column("author_id", postgresql.UUID(as_uuid=False), nullable=True),
-        sa.Column("author_name", sa.String(255), nullable=False, server_default=""),
-        sa.Column("category", sa.String(100), nullable=False, server_default=""),
-        sa.Column("price_cents", sa.Integer, nullable=False, server_default="0"),
-        sa.Column("permissions", sa.Text, nullable=False, server_default="[]"),
-        sa.Column("status", postgresql.ENUM("pending_review", "approved", "rejected", name="plugin_status", create_type=False), nullable=False, server_default="pending_review"),
-        sa.Column("s3_package_key", sa.String(500), nullable=True),
-        sa.Column("install_count", sa.Integer, nullable=False, server_default="0"),
-        sa.Column("avg_rating", sa.Float, nullable=False, server_default="0.0"),
-        sa.Column("rejection_reason", sa.Text, nullable=True),
-        sa.Column("submitted_at", sa.DateTime(timezone=True), nullable=False, server_default=sa.text("now()")),
-        sa.Column("created_at", sa.DateTime(timezone=True), nullable=False, server_default=sa.text("now()")),
-        sa.PrimaryKeyConstraint("id"),
-        sa.ForeignKeyConstraint(["author_id"], ["users.id"], ondelete="SET NULL"),
-    )
-
-    # ── plugin_installations ──────────────────────────────────────────────
-    op.create_table(
-        "plugin_installations",
-        sa.Column("id", postgresql.UUID(as_uuid=False), nullable=False),
-        sa.Column("plugin_id", sa.String(255), nullable=False),
-        sa.Column("user_id", postgresql.UUID(as_uuid=False), nullable=False),
-        sa.Column("installed_at", sa.DateTime(timezone=True), nullable=False, server_default=sa.text("now()")),
-        sa.PrimaryKeyConstraint("id"),
-        sa.ForeignKeyConstraint(["plugin_id"], ["plugins.id"], ondelete="CASCADE"),
-        sa.ForeignKeyConstraint(["user_id"], ["users.id"], ondelete="CASCADE"),
-        sa.UniqueConstraint("plugin_id", "user_id", name="uq_plugin_user"),
-    )
-    op.create_index("ix_plugin_installations_plugin_id", "plugin_installations", ["plugin_id"])
-    op.create_index("ix_plugin_installations_user_id", "plugin_installations", ["user_id"])
-
-    # ── plugin_reviews ────────────────────────────────────────────────────
-    op.create_table(
-        "plugin_reviews",
-        sa.Column("id", postgresql.UUID(as_uuid=False), nullable=False),
-        sa.Column("plugin_id", sa.String(255), nullable=False),
-        sa.Column("reviewer_id", postgresql.UUID(as_uuid=False), nullable=True),
-        sa.Column("decision", postgresql.ENUM("approved", "rejected", name="review_decision", create_type=False), nullable=False),
-        sa.Column("notes", sa.Text, nullable=True),
-        sa.Column("reviewed_at", sa.DateTime(timezone=True), nullable=False, server_default=sa.text("now()")),
-        sa.Column("created_at", sa.DateTime(timezone=True), nullable=False, server_default=sa.text("now()")),
-        sa.PrimaryKeyConstraint("id"),
-        sa.ForeignKeyConstraint(["plugin_id"], ["plugins.id"], ondelete="CASCADE"),
-        sa.ForeignKeyConstraint(["reviewer_id"], ["users.id"], ondelete="SET NULL"),
-    )
-    op.create_index("ix_plugin_reviews_plugin_id", "plugin_reviews", ["plugin_id"])
-
-    # ── revenue_events ────────────────────────────────────────────────────
-    op.create_table(
-        "revenue_events",
-        sa.Column("id", postgresql.UUID(as_uuid=False), nullable=False),
-        sa.Column("plugin_id", sa.String(255), nullable=False),
-        sa.Column("user_id", postgresql.UUID(as_uuid=False), nullable=False),
-        sa.Column("amount_cents", sa.Integer, nullable=False, server_default="0"),
-        sa.Column("developer_share_cents", sa.Integer, nullable=False, server_default="0"),
-        sa.Column("stripe_transfer_id", sa.String(255), nullable=True),
-        sa.Column("paid_at", sa.DateTime(timezone=True), nullable=True),
-        sa.Column("created_at", sa.DateTime(timezone=True), nullable=False, server_default=sa.text("now()")),
-        sa.PrimaryKeyConstraint("id"),
-        sa.ForeignKeyConstraint(["plugin_id"], ["plugins.id"], ondelete="CASCADE"),
-        sa.ForeignKeyConstraint(["user_id"], ["users.id"], ondelete="CASCADE"),
-    )
-    op.create_index("ix_revenue_events_plugin_id", "revenue_events", ["plugin_id"])
-    op.create_index("ix_revenue_events_user_id", "revenue_events", ["user_id"])
-
 
 def downgrade() -> None:
-    op.drop_table("revenue_events")
-    op.drop_table("plugin_reviews")
-    op.drop_table("plugin_installations")
-    op.drop_table("plugins")
-    op.drop_table("backup_metadata")
-    op.drop_table("storage_records")
     op.drop_table("subscriptions")
     op.drop_table("refresh_tokens")
     op.drop_table("users")
 
-    op.execute("DROP TYPE IF EXISTS review_decision")
-    op.execute("DROP TYPE IF EXISTS plugin_status")
     op.execute("DROP TYPE IF EXISTS billing_tier")

alembic/versions/002_seed_plugins.py

@@ -1,92 +0,0 @@
-"""Seed approved plugins: GitHub Sync, Slack Notifier, Time Tracker.
-
-Revision ID: 002
-Revises: 001
-Create Date: 2026-03-03
-"""
-
-from __future__ import annotations
-
-import json
-from datetime import datetime, timezone
-from typing import Sequence, Union
-
-import sqlalchemy as sa
-from alembic import op
-
-revision: str = "002"
-down_revision: Union[str, None] = "001"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-_SEED_PLUGINS = [
-    {
-        "id": "plugin-github-sync",
-        "name": "GitHub Sync",
-        "description": "Sync tasks with GitHub Issues and pull requests.",
-        "version": "1.0.0",
-        "author_name": "Adiuva",
-        "category": "productivity",
-        "price_cents": 0,
-        "permissions": json.dumps(["read:tasks", "write:tasks"]),
-        "status": "approved",
-        "s3_package_key": "plugins/plugin-github-sync/1.0.0/package.zip",
-        "install_count": 0,
-        "avg_rating": 0.0,
-    },
-    {
-        "id": "plugin-slack-notify",
-        "name": "Slack Notifier",
-        "description": "Post task and timeline updates to Slack channels.",
-        "version": "1.2.0",
-        "author_name": "Adiuva",
-        "category": "communication",
-        "price_cents": 499,
-        "permissions": json.dumps(["read:tasks", "read:timelines"]),
-        "status": "approved",
-        "s3_package_key": "plugins/plugin-slack-notify/1.2.0/package.zip",
-        "install_count": 0,
-        "avg_rating": 0.0,
-    },
-    {
-        "id": "plugin-time-tracker",
-        "name": "Time Tracker",
-        "description": "Track time spent on tasks with automatic reporting.",
-        "version": "0.9.1",
-        "author_name": "Third Party",
-        "category": "productivity",
-        "price_cents": 999,
-        "permissions": json.dumps(["read:tasks", "write:tasks"]),
-        "status": "approved",
-        "s3_package_key": "plugins/plugin-time-tracker/0.9.1/package.zip",
-        "install_count": 0,
-        "avg_rating": 0.0,
-    },
-]
-
-
-def upgrade() -> None:
-    plugins = sa.table(
-        "plugins",
-        sa.column("id", sa.String),
-        sa.column("name", sa.String),
-        sa.column("description", sa.Text),
-        sa.column("version", sa.String),
-        sa.column("author_name", sa.String),
-        sa.column("category", sa.String),
-        sa.column("price_cents", sa.Integer),
-        sa.column("permissions", sa.Text),
-        sa.column("status", sa.Enum("pending_review", "approved", "rejected", name="plugin_status")),
-        sa.column("s3_package_key", sa.String),
-        sa.column("install_count", sa.Integer),
-        sa.column("avg_rating", sa.Float),
-    )
-    op.bulk_insert(plugins, _SEED_PLUGINS)
-
-
-def downgrade() -> None:
-    op.execute(
-        "DELETE FROM plugins WHERE id IN ("
-        "'plugin-github-sync', 'plugin-slack-notify', 'plugin-time-tracker'"
-        ")"
-    )

alembic/versions/003_agent_tables.py

@@ -14,7 +14,7 @@ from alembic import op
 from sqlalchemy.dialects import postgresql
 
 revision: str = "003"
-down_revision: Union[str, None] = "002"
+down_revision: Union[str, None] = "001"
 branch_labels: Union[str, Sequence[str], None] = None
 depends_on: Union[str, Sequence[str], None] = None
 

alembic/versions/a3b9c0d1e2f3_add_agent_config_to_local_agents.py

@@ -1,4 +1,8 @@
-"""add agent_config to local_agent_configs
+"""Restore agent config tables and add agent_config column.
+
+9a1f2d0b6c7e dropped local_agent_configs and cloud_agent_configs, but both
+ORM models are still active. This migration recreates them with agent_config
+added to local_agent_configs.
 
 Revision ID: a3b9c0d1e2f3
 Revises: 9a1f2d0b6c7e
@@ -9,8 +13,9 @@ from __future__ import annotations
 
 from typing import Sequence, Union
 
-from alembic import op
 import sqlalchemy as sa
+from alembic import op
+from sqlalchemy.dialects import postgresql
 
 
 # revision identifiers, used by Alembic.
@@ -21,11 +26,82 @@ depends_on: Union[str, Sequence[str], None] = None
 
 
 def upgrade() -> None:
-    op.add_column(
+    # Recreate enum types (idempotent — they may already exist from migration 003)
+    op.execute("""
+        DO $$ BEGIN
+            CREATE TYPE agent_type AS ENUM ('local', 'cloud');
+        EXCEPTION WHEN duplicate_object THEN NULL;
+        END $$;
+    """)
+    op.execute("""
+        DO $$ BEGIN
+            CREATE TYPE agent_run_status AS ENUM ('running', 'success', 'error', 'partial');
+        EXCEPTION WHEN duplicate_object THEN NULL;
+        END $$;
+    """)
+    op.execute("""
+        DO $$ BEGIN
+            CREATE TYPE cloud_provider AS ENUM ('gmail', 'teams', 'outlook');
+        EXCEPTION WHEN duplicate_object THEN NULL;
+        END $$;
+    """)
+
+    bind = op.get_bind()
+    inspector = sa.inspect(bind)
+    existing = set(inspector.get_table_names())
+
+    # ── local_agent_configs (with agent_config column) ────────────────────
+    if "local_agent_configs" not in existing:
+        op.create_table(
             "local_agent_configs",
-        sa.Column("agent_config", sa.JSON(), nullable=True),
+            sa.Column("id", postgresql.UUID(as_uuid=False), nullable=False),
+            sa.Column("user_id", postgresql.UUID(as_uuid=False), nullable=False),
+            sa.Column("device_id", sa.String(255), nullable=False),
+            sa.Column("name", sa.String(255), nullable=False),
+            sa.Column("directory_paths", sa.JSON, nullable=False, server_default="[]"),
+            sa.Column("data_types", sa.JSON, nullable=False, server_default="[]"),
+            sa.Column("prompt_template", sa.Text, nullable=False, server_default=""),
+            sa.Column("agent_config", sa.JSON, nullable=True),
+            sa.Column("file_extensions", sa.JSON, nullable=False, server_default="[]"),
+            sa.Column("schedule_cron", sa.String(100), nullable=False, server_default="0 */6 * * *"),
+            sa.Column("enabled", sa.Boolean, nullable=False, server_default=sa.true()),
+            sa.Column("last_run_at", sa.DateTime(timezone=True), nullable=True),
+            sa.Column("created_at", sa.DateTime(timezone=True), nullable=False, server_default=sa.text("now()")),
+            sa.Column("updated_at", sa.DateTime(timezone=True), nullable=False, server_default=sa.text("now()")),
+            sa.PrimaryKeyConstraint("id"),
+            sa.ForeignKeyConstraint(["user_id"], ["users.id"], ondelete="CASCADE"),
         )
+        op.create_index("ix_local_agent_configs_user_id", "local_agent_configs", ["user_id"])
+
+    # ── cloud_agent_configs ───────────────────────────────────────────────
+    if "cloud_agent_configs" not in existing:
+        op.create_table(
+            "cloud_agent_configs",
+            sa.Column("id", postgresql.UUID(as_uuid=False), nullable=False),
+            sa.Column("user_id", postgresql.UUID(as_uuid=False), nullable=False),
+            sa.Column(
+                "provider",
+                postgresql.ENUM("gmail", "teams", "outlook", name="cloud_provider", create_type=False),
+                nullable=False,
+            ),
+            sa.Column("name", sa.String(255), nullable=False),
+            sa.Column("data_types", sa.JSON, nullable=False, server_default="[]"),
+            sa.Column("prompt_template", sa.Text, nullable=False, server_default=""),
+            sa.Column("oauth_token_encrypted", sa.Text, nullable=True),
+            sa.Column("filter_config", sa.JSON, nullable=True),
+            sa.Column("schedule_cron", sa.String(100), nullable=False, server_default="0 */6 * * *"),
+            sa.Column("enabled", sa.Boolean, nullable=False, server_default=sa.true()),
+            sa.Column("last_run_at", sa.DateTime(timezone=True), nullable=True),
+            sa.Column("created_at", sa.DateTime(timezone=True), nullable=False, server_default=sa.text("now()")),
+            sa.Column("updated_at", sa.DateTime(timezone=True), nullable=False, server_default=sa.text("now()")),
+            sa.PrimaryKeyConstraint("id"),
+            sa.ForeignKeyConstraint(["user_id"], ["users.id"], ondelete="CASCADE"),
+        )
+        op.create_index("ix_cloud_agent_configs_user_id", "cloud_agent_configs", ["user_id"])
 
 
 def downgrade() -> None:
-    op.drop_column("local_agent_configs", "agent_config")
+    op.drop_index("ix_cloud_agent_configs_user_id", table_name="cloud_agent_configs")
+    op.drop_table("cloud_agent_configs")
+    op.drop_index("ix_local_agent_configs_user_id", table_name="local_agent_configs")
+    op.drop_table("local_agent_configs")

alembic/versions/b4c0d1e2f3a4_add_oauth_and_avatar.py

@@ -0,0 +1,56 @@
+"""Add oauth_accounts table, nullable password_hash, avatar_url to users.
+
+Revision ID: b4c0d1e2f3a4
+Revises: a3b9c0d1e2f3
+Create Date: 2026-04-10 00:00:00.000000
+
+"""
+from __future__ import annotations
+
+from typing import Sequence, Union
+
+import sqlalchemy as sa
+from alembic import op
+from sqlalchemy.dialects import postgresql
+
+
+# revision identifiers, used by Alembic.
+revision: str = "b4c0d1e2f3a4"
+down_revision: Union[str, None] = "a3b9c0d1e2f3"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    # ── users: make password_hash nullable (social users have no password) ──
+    op.alter_column("users", "password_hash", existing_type=sa.String(255), nullable=True)
+
+    # ── users: add avatar_url ─────────────────────────────────────────────
+    op.add_column("users", sa.Column("avatar_url", sa.String(2048), nullable=True))
+
+    # ── oauth_accounts ────────────────────────────────────────────────────
+    op.create_table(
+        "oauth_accounts",
+        sa.Column("id", postgresql.UUID(as_uuid=False), nullable=False),
+        sa.Column("user_id", postgresql.UUID(as_uuid=False), nullable=False),
+        sa.Column("provider", sa.String(50), nullable=False),
+        sa.Column("provider_user_id", sa.String(255), nullable=False),
+        sa.Column("provider_email", sa.String(255), nullable=True),
+        sa.Column(
+            "created_at",
+            sa.DateTime(timezone=True),
+            nullable=False,
+            server_default=sa.text("now()"),
+        ),
+        sa.PrimaryKeyConstraint("id"),
+        sa.ForeignKeyConstraint(["user_id"], ["users.id"], ondelete="CASCADE"),
+        sa.UniqueConstraint("provider", "provider_user_id", name="uq_oauth_provider_user"),
+    )
+    op.create_index("ix_oauth_accounts_user_id", "oauth_accounts", ["user_id"])
+
+
+def downgrade() -> None:
+    op.drop_index("ix_oauth_accounts_user_id", table_name="oauth_accounts")
+    op.drop_table("oauth_accounts")
+    op.drop_column("users", "avatar_url")
+    op.alter_column("users", "password_hash", existing_type=sa.String(255), nullable=False)

alembic/versions/c5d1e2f3a4b5_add_onboarding_completed_at.py

@@ -0,0 +1,31 @@
+"""Add onboarding_completed_at column to users table.
+
+Revision ID: c5d1e2f3a4b5
+Revises: b4c0d1e2f3a4
+Create Date: 2026-04-11 00:00:00.000000
+
+"""
+from __future__ import annotations
+
+from typing import Sequence, Union
+
+import sqlalchemy as sa
+from alembic import op
+
+
+# revision identifiers, used by Alembic.
+revision: str = "c5d1e2f3a4b5"
+down_revision: Union[str, None] = "b4c0d1e2f3a4"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "users",
+        sa.Column("onboarding_completed_at", sa.DateTime(timezone=True), nullable=True),
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("users", "onboarding_completed_at")

alembic/versions/e04100e88ace_avatar_url_varchar_to_text.py

@@ -0,0 +1,34 @@
+"""avatar_url_varchar_to_text
+
+Revision ID: e04100e88ace
+Revises: c5d1e2f3a4b5
+Create Date: 2026-04-13 09:13:06.733674
+
+"""
+from __future__ import annotations
+
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision: str = 'e04100e88ace'
+down_revision: Union[str, None] = 'c5d1e2f3a4b5'
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    op.alter_column('users', 'avatar_url',
+               existing_type=sa.VARCHAR(length=2048),
+               type_=sa.Text(),
+               existing_nullable=True)
+
+
+def downgrade() -> None:
+    op.alter_column('users', 'avatar_url',
+               existing_type=sa.Text(),
+               type_=sa.VARCHAR(length=2048),
+               existing_nullable=True)

app/agents/filesystem_agent.py

@@ -7,12 +7,31 @@ handles actual disk I/O and responds with ``tool_result`` frames.
 
 from __future__ import annotations
 
+import os
+import re
+from pathlib import Path
 from typing import Any
 
 from langchain_core.tools import tool
 
 from app.core.ws_context import execute_on_client
 
+# Max characters returned by read_file_content in journey (exploration) tools.
+# The journey only needs to understand file structure, not full content.
+_JOURNEY_READ_MAX_CHARS: int = 4000
+
+
+def _resolve_path(path: str, base: str) -> str:
+    """Resolve *path* against *base* when *path* is relative.
+
+    The LLM often passes ``"."`` meaning "the configured directory".
+    Without this, Electron resolves ``"."`` relative to its own CWD instead
+    of the user's chosen directory.
+    """
+    if os.path.isabs(path):
+        return path
+    return str(Path(base) / path)
+
 
 @tool
 async def list_directory(path: str) -> str:
@@ -83,3 +102,93 @@ FILESYSTEM_TOOLS: list[Any] = [
     read_file_content,
     get_file_metadata,
 ]
+
+
+def make_directory_tools(base_directory: str) -> list[Any]:
+    """Return filesystem tools that resolve relative paths against *base_directory*.
+
+    Use this instead of ``FILESYSTEM_TOOLS`` whenever you know the user's target
+    directory upfront (e.g., journey setup sessions).  Relative paths like ``"."``
+    from the LLM are resolved to the correct absolute path before being sent to
+    the Electron client, preventing it from falling back to its own CWD.
+    """
+
+    def _compact_for_journey(raw: str) -> str:
+        """Strip HTML noise and truncate for journey exploration.
+
+        The journey LLM only needs to understand file structure (headers,
+        first paragraphs).  Full CSS/style blocks are pure noise that eat
+        up context window budget.
+        """
+        text = re.sub(r"<style[^>]*>.*?</style>", "", raw, flags=re.DOTALL | re.IGNORECASE)
+        text = re.sub(r"<script[^>]*>.*?</script>", "", text, flags=re.DOTALL | re.IGNORECASE)
+        text = re.sub(r"<!--.*?-->", "", text, flags=re.DOTALL)
+        if len(text) > _JOURNEY_READ_MAX_CHARS:
+            text = text[:_JOURNEY_READ_MAX_CHARS] + "\n[…truncated for exploration]"
+        return text
+
+    @tool
+    async def list_directory(path: str) -> str:  # noqa: F811
+        """List files and folders in a local directory on the user's device.
+
+        Returns a formatted listing of entries with name, type (file/directory),
+        and full path.
+        """
+        resolved = _resolve_path(path, base_directory)
+        result = await execute_on_client(
+            action="list_directory",
+            data={"path": resolved},
+        )
+        entries: list[dict[str, Any]] = result.get("entries", [])
+        if not entries:
+            return f"Directory '{resolved}' is empty or does not exist."
+        lines: list[str] = []
+        for entry in entries:
+            entry_type = entry.get("type", "unknown")
+            entry_name = entry.get("name", "")
+            entry_path = entry.get("path", "")
+            lines.append(f"- [{entry_type}] {entry_name}  ({entry_path})")
+        return f"Directory listing for '{resolved}' ({len(entries)} entries):\n" + "\n".join(lines)
+
+    @tool
+    async def read_file_content(path: str) -> str:  # noqa: F811
+        """Read the text content of a local file on the user's device.
+
+        Returns the file content as a string.  Large files may be truncated
+        by the Electron client.
+        """
+        resolved = _resolve_path(path, base_directory)
+        result = await execute_on_client(
+            action="read_file_content",
+            data={"path": resolved},
+        )
+        content: str = result.get("content", "")
+        if not content:
+            return f"File '{resolved}' is empty or could not be read."
+        return _compact_for_journey(content)
+
+    @tool
+    async def get_file_metadata(path: str) -> str:  # noqa: F811
+        """Get metadata for a local file: size, creation date, modification date, extension.
+
+        Returns a formatted summary of the file's metadata.
+        """
+        resolved = _resolve_path(path, base_directory)
+        result = await execute_on_client(
+            action="get_file_metadata",
+            data={"path": resolved},
+        )
+        size = result.get("size", "unknown")
+        created = result.get("createdAt", "unknown")
+        modified = result.get("modifiedAt", "unknown")
+        extension = result.get("extension", "unknown")
+        name = result.get("name", resolved)
+        return (
+            f"File: {name}\n"
+            f"  Extension: {extension}\n"
+            f"  Size: {size} bytes\n"
+            f"  Created: {created}\n"
+            f"  Modified: {modified}"
+        )
+
+    return [list_directory, read_file_content, get_file_metadata]

app/agents/note_agent.py

@@ -18,21 +18,6 @@ _UUID_RE = re.compile(
 def _is_uuid(value: str) -> bool:
     return bool(_UUID_RE.match(value))
 
-NOTE_SYSTEM_PROMPT = (
-    "You are a note-taking assistant. You help users create, retrieve, update,\n"
-    "and delete Markdown notes in their workspace.\n\n"
-    "Rules:\n"
-    "  - content is always Markdown; preserve formatting when updating\n"
-    "  - project_id is optional; link a note to a project when mentioned\n"
-    "  - When updating, call get_note first if you need to read existing content\n"
-    "    before appending or replacing sections\n"
-    "  - list_notes without project_id returns all notes; scope with project_id\n"
-    "    when the user is working within a specific project\n"
-    "  - project_id must be a UUID; if you only know a project name, do not pass it as project_id\n"
-    "  - Do not fabricate note content — reflect what the user provides or what\n"
-    "    is already in the note (retrieved via get_note)."
-)
-
 
 @tool
 async def list_notes(project_id: str = "") -> str:

app/agents/project_agent.py

@@ -8,22 +8,6 @@ from langchain_core.tools import tool
 
 from app.core.ws_context import execute_on_client
 
-PROJECT_SYSTEM_PROMPT = (
-    "You are a project management assistant. You help users create, find,\n"
-    "update, and archive projects in their workspace.\n\n"
-    "Rules:\n"
-    "  - status must be one of: active, archived\n"
-    "  - client_id is optional; link to a client only when explicitly mentioned\n"
-    "  - ai_summary is populated only when the user asks for a project summary;\n"
-    "    derive it from context data — do not fabricate content\n"
-    "  - Use list_projects for scoped queries; list_all_projects only when the\n"
-    "    user wants a complete cross-client view including archived projects\n"
-    "  - get_project requires a project UUID; resolve the ID first by calling\n"
-    "    list_projects if you only have a project name\n"
-    "  - Prefer archiving (update_project status=archived) over deletion;\n"
-    "    only call delete_project when the user explicitly confirms deletion."
-)
-
 
 @tool
 async def list_projects(

app/agents/task_agent.py

@@ -18,23 +18,6 @@ _UUID_RE = re.compile(
 def _is_uuid(value: str) -> bool:
     return bool(_UUID_RE.match(value))
 
-TASK_SYSTEM_PROMPT = (
-    "You are a task management assistant for a project workspace.\n"
-    "You create, update, list, and track tasks and their comments.\n\n"
-    "Rules:\n"
-    "  - status must be one of: todo, in_progress, done\n"
-    "  - priority must be one of: high, medium, low\n"
-    "  - due_date is a Unix timestamp in milliseconds; convert human dates\n"
-    "  - assignees is a JSON-encoded array of strings (e.g. '[\"Alice\",\"Bob\"]')\n"
-    "  - project_id is optional; link to a project when the user mentions one\n"
-    "  - is_ai_suggested: 1 only when proactively proposing a task the user\n"
-    "    did not explicitly request; 0 otherwise\n"
-    "  - is_ai_suggested: 1 only when proactively proposing a task the user did not explicitly request; 0 otherwise\n"
-    "  - Use list_tasks_due_today for 'what's due today' queries\n"
-    "  - For update_task, use -1 for integer fields you do not want to change\n"
-    "  - Always confirm the action in plain, user-friendly language."
-)
-
 
 # ── Task tools ────────────────────────────────────────────────────────
 

app/agents/timeline_agent.py

@@ -17,20 +17,6 @@ _UUID_RE = re.compile(
 def _is_uuid(value: str) -> bool:
     return bool(_UUID_RE.match(value))
 
-TIMELINE_SYSTEM_PROMPT = (
-    "You are a project timeline assistant. Timelines are milestone dates that\n"
-    "track progress on a project — they are not calendar events.\n\n"
-    "Rules:\n"
-    "  - project_id is REQUIRED for every create; confirm with the user if unknown\n"
-    "  - For listing, project_id must be a UUID; never pass plain names as project_id\n"
-    "  - date is a Unix timestamp in milliseconds; convert human-readable dates\n"
-    "  - is_ai_suggested: 1 when proactively proposing a timeline, 0 otherwise\n"
-    "  - is_ai_suggested: 1 when proactively proposing a timeline, 0 otherwise\n"
-    "  - For update_timeline, use -1 for integer fields you do not want to change\n"
-    "  - Listing without a project_id returns all timelines across projects\n"
-    "  - Always echo the title and formatted date in your confirmation."
-)
-
 
 @tool
 async def list_timelines(project_id: str = "") -> str:

app/api/middleware/auth.py

@@ -65,16 +65,39 @@ async def get_current_user(
     default_tier = "power" if settings.ENV == "dev" else "free"
     tier: str = result.scalar_one_or_none() or default_tier
 
-    # Fetch name/surname from user row.
+    # Fetch name/surname/avatar_url/onboarding_completed_at/password_hash from user row.
     user_result = await db.execute(
-        select(User.name, User.surname).where(User.id == user_id)
+        select(
+            User.name, User.surname, User.avatar_url, User.onboarding_completed_at,
+            User.password_hash,
+        ).where(User.id == user_id)
     )
     user_row = user_result.one_or_none()
 
+    # Convert onboarding_completed_at to epoch ms (int) or None.
+    onboarding_ms: int | None = None
+    if user_row and user_row.onboarding_completed_at is not None:
+        onboarding_ms = int(user_row.onboarding_completed_at.timestamp() * 1000)
+
+    # Load decrypted core memory.
+    from app.core.memory_middleware import MemoryMiddleware  # noqa: PLC0415
+
+    memory_dict: dict[str, str] = {}
+    try:
+        mw = MemoryMiddleware(db)
+        blocks = await mw.list_core_blocks(user_id)
+        memory_dict = {b["label"]: b["value"] for b in blocks}
+    except Exception:
+        pass  # Non-critical — return empty memory on failure
+
     return UserProfile(
         id=user_id,
         email=email,
         name=user_row.name if user_row else None,
         surname=user_row.surname if user_row else None,
+        avatar_url=user_row.avatar_url if user_row else None,
+        has_password=bool(user_row.password_hash) if user_row else False,
         tier=tier,
+        onboarding_completed_at=onboarding_ms,
+        memory=memory_dict,
     )  # type: ignore[arg-type]

app/api/middleware/sanitizer.py

@@ -8,8 +8,7 @@ that could reveal server-side prompt IP:
   - Internal reasoning markers (<thinking>, <reasoning>, [INST], …)
   - Exact-match known prompt fingerprints
 
-Binary responses (storage blobs, backup data) are never touched — the
-middleware only activates for paths under /api/v1/chat.
+The middleware only activates for paths under /api/v1/chat.
 
 Any sanitisation event is logged as a WARNING with the request path and the
 names of the fields that were modified.

app/api/routes/agent_setup.py

@@ -31,10 +31,9 @@ from typing import Any
 
 from langchain_core.messages import AIMessage, HumanMessage, SystemMessage, ToolMessage
 
-from app.agents.filesystem_agent import FILESYSTEM_TOOLS
-from app.config.settings import settings
-from app.core.langfuse_client import compile_prompt, extract_usage, get_langfuse, get_prompt_or_fallback
-from app.core.llm import get_llm
+from app.agents.filesystem_agent import make_directory_tools
+from app.core.langfuse_client import compile_prompt, extract_usage, get_langfuse, get_prompt_or_fallback, langfuse_context
+from app.core.llm import get_agent_llm, model_for_agent
 from app.schemas import AgentConfig
 
 logger = logging.getLogger(__name__)
@@ -257,15 +256,17 @@ async def _call_llm_with_tools(
         else:
             messages.append(AIMessage(content=turn["content"]))
 
-    llm = get_llm(model=None, temperature=0.4)
+    llm = get_agent_llm("setup", temperature=0.4)
     llm_with_tools = llm.bind_tools(tools)
     tool_map = {tool_def.name: tool_def for tool_def in tools}
 
+    _lf_ctx = langfuse_context(user_id=user_id or None, session_id=session_id or None)
+    _lf_ctx.__enter__()
+
     _span_ctx = (
         lf.start_as_current_observation(
             as_type="span",
             name="journey-setup",
-            metadata={"user_id": user_id or None, "session_id": session_id or None},
             input=history[-1]["content"] if history else "",
         )
         if lf else None
@@ -273,12 +274,12 @@ async def _call_llm_with_tools(
     _span = _span_ctx.__enter__() if _span_ctx else None
 
     try:
-        for _ in range(_MAX_TOOL_STEPS):
+        for step in range(_MAX_TOOL_STEPS):
             _gen_ctx = (
                 lf.start_as_current_observation(
                     as_type="generation",
                     name="journey-setup-llm",
-                    model=settings.LLM_MODEL,
+                    model=model_for_agent("setup"),
                     prompt=langfuse_prompt,
                     input=messages,
                 )
@@ -287,15 +288,27 @@ async def _call_llm_with_tools(
             _gen = _gen_ctx.__enter__() if _gen_ctx else None
             response: AIMessage = await llm_with_tools.ainvoke(messages)
             if _gen_ctx:
-                _gen.update(output=_as_text(response.content), usage=extract_usage(response))
+                _gen.update(output=_as_text(response.content), usage_details=extract_usage(response))
                 _gen_ctx.__exit__(None, None, None)
 
+            resp_text = _as_text(response.content)
+
+            # Guard against empty responses (e.g. model returned finish_reason
+            # 'error' which LiteLLM maps to 'stop' with empty content).
+            if not response.tool_calls and not resp_text.strip():
+                logger.warning(
+                    "agent_setup: journey LLM returned empty response at step %d — retrying",
+                    step,
+                )
+                # Drop the empty AIMessage so we don't pollute history, and retry.
+                continue
+
             messages.append(response)
 
             if not response.tool_calls:
                 if _span:
-                    _span.update(output=_as_text(response.content))
-                return _as_text(response.content)
+                    _span.update(output=resp_text)
+                return resp_text
 
             for call in response.tool_calls:
                 call_name = str(call.get("name", ""))
@@ -324,10 +337,14 @@ async def _call_llm_with_tools(
         final_text = _as_text(final.content)
         if _span:
             _span.update(output=final_text)
-        return final_text
+        return final_text or (
+            "Sorry, I had trouble processing the files. "
+            "Could you try again? If the issue persists, the files might be too large for me to analyse."
+        )
     finally:
         if _span_ctx:
             _span_ctx.__exit__(None, None, None)
+        _lf_ctx.__exit__(None, None, None)
         if lf:
             lf.flush()
 
@@ -372,7 +389,7 @@ async def handle_journey_start(
     ai_reply = await _call_llm_with_tools(
         system_prompt=system_prompt,
         history=seed_history,
-        tools=list(FILESYSTEM_TOOLS),
+        tools=make_directory_tools(directory),
         user_id=user_id,
         session_id=session_id,
         langfuse_prompt=langfuse_prompt,
@@ -436,10 +453,11 @@ async def handle_journey_message(
     session.history.append({"role": "user", "content": message})
 
     # Call the LLM with tools.
+    session_tools = make_directory_tools(session.directory)
     ai_reply = await _call_llm_with_tools(
         system_prompt=session.system_prompt,
         history=session.history,
-        tools=list(FILESYSTEM_TOOLS),
+        tools=session_tools,
         user_id=session.user_id,
         session_id=session_id,
         langfuse_prompt=session.langfuse_prompt,
@@ -464,7 +482,7 @@ async def handle_journey_message(
             nudge_reply = await _call_llm_with_tools(
                 system_prompt=session.system_prompt,
                 history=session.history,
-                tools=list(FILESYSTEM_TOOLS),
+                tools=session_tools,
                 user_id=session.user_id,
                 session_id=session_id,
                 langfuse_prompt=session.langfuse_prompt,

app/api/routes/agents.py

@@ -12,8 +12,11 @@ in backend agent-config tables.
 from __future__ import annotations
 
 import asyncio
+import logging
 import uuid
-from datetime import datetime, timedelta, timezone
+from datetime import datetime, timezone
+
+logger = logging.getLogger(__name__)
 
 from fastapi import APIRouter, Depends, HTTPException, status
 from sqlalchemy import func, select
@@ -177,6 +180,11 @@ async def trigger_agent_run(
     _enforce_agent_limit(current_user.tier, body.active_agents)
     await _enforce_run_frequency(current_user.tier, current_user.id, db)
 
+    last_run_dt = (
+        datetime.fromtimestamp(body.last_run_at / 1000, tz=timezone.utc)
+        if body.last_run_at
+        else None
+    )
     config = LocalAgentConfig(
         id=str(uuid.uuid4()),
         user_id=current_user.id,
@@ -184,10 +192,12 @@ async def trigger_agent_run(
         name="Local Directory Monitor",
         directory_paths=[body.directory],
         data_types=_to_data_types(body.what_to_extract),
-        prompt_template=body.custom_agent_prompt,
+        prompt_template=body.custom_agent_prompt or "",
+        agent_config=body.agent_config,
         file_extensions=[],
         schedule_cron=body.batch_interval,
         enabled=True,
+        last_run_at=last_run_dt,
     )
 
     # Use the FE's stable agent_id if provided, fall back to the ephemeral config id.

app/api/routes/auth.py

@@ -1,34 +1,68 @@
-"""Auth routes: register, login, refresh, me.
+"""Auth routes: register, login, refresh, me, OAuth social login, onboarding.
 
 Users and refresh tokens are persisted in PostgreSQL (users + refresh_tokens
 tables).  Passwords are hashed with bcrypt; refresh tokens are stored as
 SHA-256 hashes so plaintext never reaches the DB.
+
+OAuth (Google):
+  GET  /auth/oauth/{provider}/authorize  — returns consent-screen URL + state
+  POST /auth/oauth/{provider}/callback   — exchanges code, issues JWT tokens
 """
 
 from __future__ import annotations
 
 import hashlib
+import json
 import time
+import urllib.parse
 import uuid
 from datetime import datetime, timedelta, timezone
+from typing import Literal
 
 import bcrypt
 from cryptography.fernet import Fernet
 from fastapi import APIRouter, Depends, HTTPException, status
+from fastapi.responses import RedirectResponse
 from jose import jwt
-from pydantic import BaseModel
+from pydantic import BaseModel, Field
 from sqlalchemy import select
 from sqlalchemy.ext.asyncio import AsyncSession
 
 from app.api.deps import get_current_user
+from app.auth.oauth_providers import GoogleOAuthProvider, generate_pkce_pair
 from app.config.settings import settings
+from app.core.llm import get_llm
+from app.core.memory_middleware import MemoryMiddleware
 from app.db import get_session
-from app.models import RefreshToken, User
+from app.models import OAuthAccount, RefreshToken, User
 from app.schemas import AuthTokens, UserProfile
 
 router = APIRouter(prefix="/auth", tags=["auth"])
 
 
+# ── OAuth provider registry ───────────────────────────────────────────
+
+def _get_google_provider() -> GoogleOAuthProvider:
+    if not settings.GOOGLE_AUTH_CLIENT_ID or not settings.GOOGLE_AUTH_CLIENT_SECRET:
+        raise HTTPException(
+            status.HTTP_503_SERVICE_UNAVAILABLE,
+            "Google login is not configured on this server",
+        )
+    return GoogleOAuthProvider(
+        client_id=settings.GOOGLE_AUTH_CLIENT_ID,
+        client_secret=settings.GOOGLE_AUTH_CLIENT_SECRET,
+        redirect_uri=settings.OAUTH_REDIRECT_URI,
+    )
+
+
+_PROVIDERS = {"google": _get_google_provider}
+
+# In-memory state store: state → (code_verifier, expires_at_epoch_s)
+# Production note: replace with Redis for multi-process deployments.
+_pending_states: dict[str, tuple[str, float]] = {}
+_STATE_TTL_SECONDS = 600  # 10 minutes
+
+
 # ── Internal helpers ─────────────────────────────────────────────────
 
 
@@ -231,5 +265,531 @@ async def update_profile(
         email=user.email,
         name=user.name,
         surname=user.surname,
+        avatar_url=user.avatar_url,
         tier=current_user.tier,
     )
+
+
+# ── OAuth helpers ─────────────────────────────────────────────────────
+
+
+async def _issue_refresh_token(user: User, db: AsyncSession) -> tuple[str, AuthTokens]:
+    """Create a refresh token row and return (plain_token, AuthTokens)."""
+    plain_token = str(uuid.uuid4())
+    expires_at = datetime.now(timezone.utc) + timedelta(
+        days=settings.JWT_REFRESH_TOKEN_EXPIRE_DAYS
+    )
+    rt = RefreshToken(
+        user_id=user.id,
+        token_hash=_hash_token(plain_token),
+        expires_at=expires_at,
+    )
+    db.add(rt)
+    access_token, expires_at_ms = _make_access_token(user.id, user.email, user.tier)
+    return plain_token, AuthTokens(
+        access_token=access_token,
+        refresh_token=plain_token,
+        expires_at=expires_at_ms,
+    )
+
+
+# ── OAuth request/response schemas ───────────────────────────────────
+
+
+class _OAuthAuthorizeResponse(BaseModel):
+    url: str
+    state: str
+
+
+class _OAuthCallbackRequest(BaseModel):
+    code: str
+    state: str
+
+
+# ── OAuth routes ──────────────────────────────────────────────────────
+
+
+@router.get(
+    "/oauth/{provider}/web-callback",
+    summary="Web-facing OAuth redirect — bounces to the adiuvai:// deep link",
+    include_in_schema=False,
+)
+async def oauth_web_callback(
+    provider: Literal["google"],
+    code: str,
+    state: str,
+) -> RedirectResponse:
+    """Google redirects here after user consent.
+
+    This endpoint immediately redirects to the Electron deep-link URI so the
+    desktop app receives the authorization code.  It is intentionally simple —
+    no state validation here (the Electron app + backend callback do that).
+
+    Registered in Google Cloud Console as:
+      http://localhost:8000/api/v1/auth/oauth/google/web-callback  (dev)
+      https://api.adiuvai.com/api/v1/auth/oauth/google/web-callback  (prod)
+    """
+    params = urllib.parse.urlencode({"code": code, "state": state, "provider": provider})
+    deep_link = f"adiuvai://oauth/callback?{params}"
+    return RedirectResponse(url=deep_link, status_code=302)
+
+
+@router.get(
+    "/oauth/{provider}/authorize",
+    response_model=_OAuthAuthorizeResponse,
+    summary="Start OAuth flow — returns the provider consent-screen URL",
+)
+async def oauth_authorize(
+    provider: Literal["google"],
+) -> _OAuthAuthorizeResponse:
+    """Generate a PKCE state + code_challenge and return the authorization URL.
+
+    The client opens this URL in the system browser.  After the user grants
+    consent, the provider redirects to the deep-link URI (adiuvai://oauth/callback)
+    with ``code`` and ``state`` query params.  The client then calls
+    ``POST /auth/oauth/{provider}/callback`` with those values.
+    """
+    provider_factory = _PROVIDERS.get(provider)
+    if provider_factory is None:
+        raise HTTPException(status.HTTP_400_BAD_REQUEST, f"Unknown provider: {provider}")
+
+    oauth_provider = provider_factory()
+    state = str(uuid.uuid4())
+    code_verifier, code_challenge = generate_pkce_pair()
+
+    # Purge expired states to prevent unbounded growth.
+    now = time.time()
+    expired = [s for s, (_, exp) in _pending_states.items() if exp < now]
+    for s in expired:
+        del _pending_states[s]
+
+    _pending_states[state] = (code_verifier, now + _STATE_TTL_SECONDS)
+
+    url = oauth_provider.get_authorization_url(state=state, code_challenge=code_challenge)
+    return _OAuthAuthorizeResponse(url=url, state=state)
+
+
+@router.post(
+    "/oauth/{provider}/callback",
+    response_model=AuthTokens,
+    summary="Complete OAuth flow — exchange code and issue JWT tokens",
+)
+async def oauth_callback(
+    provider: Literal["google"],
+    body: _OAuthCallbackRequest,
+    db: AsyncSession = Depends(get_session),
+) -> AuthTokens:
+    """Validate state, exchange the authorization code, and sign in (or register) the user.
+
+    Resolution order:
+      1. ``oauth_accounts`` row match → existing user, log in.
+      2. Email match + ``email_verified=True`` → link OAuth account to existing user.
+      3. No match → create new user (password_hash=None, avatar from provider).
+    """
+    provider_factory = _PROVIDERS.get(provider)
+    if provider_factory is None:
+        raise HTTPException(status.HTTP_400_BAD_REQUEST, f"Unknown provider: {provider}")
+
+    # Validate state (CSRF protection).
+    now = time.time()
+    entry = _pending_states.pop(body.state, None)
+    if entry is None or entry[1] < now:
+        raise HTTPException(status.HTTP_401_UNAUTHORIZED, "Invalid or expired OAuth state")
+
+    code_verifier, _ = entry
+
+    oauth_provider = provider_factory()
+
+    # Exchange code for tokens.
+    try:
+        token_data = await oauth_provider.exchange_code(
+            code=body.code,
+            code_verifier=code_verifier,
+            redirect_uri=settings.OAUTH_REDIRECT_URI,
+        )
+    except Exception:
+        raise HTTPException(
+            status.HTTP_400_BAD_REQUEST, "Failed to exchange authorization code"
+        )
+
+    access_token_google = token_data.get("access_token")
+    if not access_token_google:
+        raise HTTPException(status.HTTP_400_BAD_REQUEST, "No access token in provider response")
+
+    # Fetch user identity.
+    try:
+        userinfo = await oauth_provider.get_userinfo(access_token_google)
+    except Exception:
+        raise HTTPException(status.HTTP_400_BAD_REQUEST, "Failed to fetch user info from provider")
+
+    # ── Resolution order ──────────────────────────────────────────────
+
+    # 1. Existing OAuth link?
+    oauth_result = await db.execute(
+        select(OAuthAccount).where(
+            OAuthAccount.provider == provider,
+            OAuthAccount.provider_user_id == userinfo.provider_user_id,
+        )
+    )
+    oauth_account = oauth_result.scalar_one_or_none()
+
+    if oauth_account is not None:
+        user_result = await db.execute(select(User).where(User.id == oauth_account.user_id))
+        user = user_result.scalar_one()
+        # Backfill avatar if the user doesn't have one yet.
+        if user.avatar_url is None and userinfo.avatar_url:
+            user.avatar_url = userinfo.avatar_url
+            await db.commit()
+        plain_token, tokens = await _issue_refresh_token(user, db)
+        await db.commit()
+        return tokens
+
+    # 2. Email match with a verified Google email → link accounts.
+    if userinfo.email_verified:
+        email_result = await db.execute(select(User).where(User.email == userinfo.email))
+        existing_user = email_result.scalar_one_or_none()
+
+        if existing_user is not None:
+            new_link = OAuthAccount(
+                user_id=existing_user.id,
+                provider=provider,
+                provider_user_id=userinfo.provider_user_id,
+                provider_email=userinfo.email,
+            )
+            db.add(new_link)
+            if existing_user.avatar_url is None and userinfo.avatar_url:
+                existing_user.avatar_url = userinfo.avatar_url
+            plain_token, tokens = await _issue_refresh_token(existing_user, db)
+            await db.commit()
+            return tokens
+
+    # Guard: if the email is already taken but we couldn't auto-link (e.g.
+    # email_verified=False), refuse with 409 instead of hitting a DB constraint.
+    if not userinfo.email_verified:
+        conflict = await db.execute(select(User).where(User.email == userinfo.email))
+        if conflict.scalar_one_or_none() is not None:
+            raise HTTPException(
+                status.HTTP_409_CONFLICT,
+                "An account with this email already exists. "
+                "Please sign in with your password.",
+            )
+
+    # 3. New user — social-only account (no password).
+    new_user = User(
+        id=str(uuid.uuid4()),
+        email=userinfo.email,
+        name=userinfo.name,
+        password_hash=None,
+        avatar_url=userinfo.avatar_url,
+        tier="free",
+        encryption_key=Fernet.generate_key().decode(),
+    )
+    db.add(new_user)
+    await db.flush()  # populate new_user.id
+
+    new_oauth = OAuthAccount(
+        user_id=new_user.id,
+        provider=provider,
+        provider_user_id=userinfo.provider_user_id,
+        provider_email=userinfo.email,
+    )
+    db.add(new_oauth)
+
+    plain_token, tokens = await _issue_refresh_token(new_user, db)
+    await db.commit()
+    return tokens
+
+
+# ── Onboarding helpers ────────────────────────────────────────────────
+
+
+async def _build_profile(user_id: str, email: str, db: AsyncSession) -> UserProfile:
+    """Re-fetch and return a full UserProfile (reuses get_current_user logic)."""
+
+    # We can't call the FastAPI dependency directly, but we can replicate
+    # the core logic inline.  Instead, we just re-query the same way.
+    from app.models import Subscription  # noqa: PLC0415
+
+    result = await db.execute(
+        select(Subscription.tier).where(Subscription.user_id == user_id)
+    )
+    default_tier = "power" if settings.ENV == "dev" else "free"
+    tier: str = result.scalar_one_or_none() or default_tier
+
+    user_result = await db.execute(
+        select(
+            User.name, User.surname, User.avatar_url, User.onboarding_completed_at,
+            User.password_hash,
+        ).where(User.id == user_id)
+    )
+    user_row = user_result.one_or_none()
+
+    onboarding_ms: int | None = None
+    if user_row and user_row.onboarding_completed_at is not None:
+        onboarding_ms = int(user_row.onboarding_completed_at.timestamp() * 1000)
+
+    memory_dict: dict[str, str] = {}
+    try:
+        mw = MemoryMiddleware(db)
+        blocks = await mw.list_core_blocks(user_id)
+        memory_dict = {b["label"]: b["value"] for b in blocks}
+    except Exception:
+        pass
+
+    return UserProfile(
+        id=user_id,
+        email=email,
+        name=user_row.name if user_row else None,
+        surname=user_row.surname if user_row else None,
+        avatar_url=user_row.avatar_url if user_row else None,
+        has_password=bool(user_row.password_hash) if user_row else False,
+        tier=tier,
+        onboarding_completed_at=onboarding_ms,
+        memory=memory_dict,
+    )
+
+
+# ── Onboarding routes ────────────────────────────────────────────────
+
+
+class _UpdateMemoryRequest(BaseModel):
+    memory: dict[str, str] = Field(default_factory=dict)
+    mark_onboarded: bool = False
+
+
+@router.put("/me/memory", response_model=UserProfile)
+async def update_memory(
+    body: _UpdateMemoryRequest,
+    current_user: UserProfile = Depends(get_current_user),
+    db: AsyncSession = Depends(get_session),
+) -> UserProfile:
+    """Update core memory key/value pairs and optionally mark onboarding complete."""
+    mw = MemoryMiddleware(db)
+    for key, value in body.memory.items():
+        await mw.update_core(current_user.id, key, value)
+    if body.mark_onboarded:
+        result = await db.execute(select(User).where(User.id == current_user.id))
+        user = result.scalar_one()
+        user.onboarding_completed_at = datetime.now(timezone.utc)
+        await db.commit()
+    return await _build_profile(current_user.id, current_user.email, db)
+
+
+@router.post("/me/onboarding/reset")
+async def reset_onboarding(
+    current_user: UserProfile = Depends(get_current_user),
+    db: AsyncSession = Depends(get_session),
+):
+    """Reset onboarding so the wizard runs again on next login."""
+    result = await db.execute(select(User).where(User.id == current_user.id))
+    user = result.scalar_one()
+    user.onboarding_completed_at = None
+    await db.commit()
+    return {"status": "reset"}
+
+
+class _NormalizeRequest(BaseModel):
+    inputs: dict[str, str]
+
+
+class _NormalizeResponse(BaseModel):
+    normalized: dict[str, str]
+
+
+@router.post("/onboarding/normalize", response_model=_NormalizeResponse)
+async def normalize_onboarding(
+    body: _NormalizeRequest,
+    current_user: UserProfile = Depends(get_current_user),
+) -> _NormalizeResponse:
+    """One-shot LLM normalization for free-text onboarding answers."""
+    if not body.inputs:
+        return _NormalizeResponse(normalized={})
+    try:
+        llm = get_llm(model="gpt-4o-mini", temperature=0)
+        prompt = (
+            "You normalize user onboarding answers into clean, ≤3-word canonical labels.\n"
+            "Return a JSON object with the same keys and normalized values.\n"
+            "Examples: 'i build websites' → 'Web Developer', 'tech-ish stuff' → 'Technology'\n"
+            f"Input: {json.dumps(body.inputs)}"
+        )
+        response = await llm.ainvoke(
+            [
+                {"role": "system", "content": "You normalize user inputs. Return JSON only."},
+                {"role": "user", "content": prompt},
+            ],
+        )
+        normalized = json.loads(response.content)
+        return _NormalizeResponse(normalized=normalized)
+    except Exception:
+        # LLM failure must never block onboarding — return inputs unchanged
+        return _NormalizeResponse(normalized=body.inputs)
+
+
+# ── Password management ───────────────────────────────────────────────
+
+
+class _ChangePasswordRequest(BaseModel):
+    current_password: str = Field(min_length=1)
+    new_password: str = Field(min_length=8)
+
+
+@router.put("/me/password", status_code=status.HTTP_200_OK)
+async def change_password(
+    body: _ChangePasswordRequest,
+    current_user: UserProfile = Depends(get_current_user),
+    db: AsyncSession = Depends(get_session),
+) -> dict[str, bool]:
+    """Change the authenticated user's password.
+
+    Requires the current password for verification.
+    Returns 400 for social-only users (no password set).
+    """
+    result = await db.execute(select(User).where(User.id == current_user.id))
+    user = result.scalar_one()
+
+    if user.password_hash is None:
+        raise HTTPException(
+            status.HTTP_400_BAD_REQUEST,
+            "This account uses social login and has no password to change",
+        )
+
+    if not _verify_password(body.current_password, user.password_hash):
+        raise HTTPException(status.HTTP_400_BAD_REQUEST, "Current password is incorrect")
+
+    user.password_hash = _hash_password(body.new_password)
+    await db.commit()
+    return {"ok": True}
+
+
+# ── OAuth account management ─────────────────────────────────────────
+
+
+@router.get("/me/oauth-accounts", response_model=list[dict])
+async def list_oauth_accounts(
+    current_user: UserProfile = Depends(get_current_user),
+    db: AsyncSession = Depends(get_session),
+) -> list[dict]:
+    """List all OAuth providers linked to the authenticated user."""
+    result = await db.execute(
+        select(OAuthAccount).where(OAuthAccount.user_id == current_user.id)
+    )
+    accounts = result.scalars().all()
+    return [
+        {
+            "provider": a.provider,
+            "provider_email": a.provider_email,
+            "created_at": int(a.created_at.timestamp() * 1000),
+        }
+        for a in accounts
+    ]
+
+
+@router.delete("/me/oauth-accounts/{provider}", status_code=status.HTTP_200_OK)
+async def unlink_oauth_account(
+    provider: str,
+    current_user: UserProfile = Depends(get_current_user),
+    db: AsyncSession = Depends(get_session),
+) -> dict[str, bool]:
+    """Unlink an OAuth provider from the authenticated user.
+
+    Refuses if the user has no password and this is their only login method.
+    """
+    result = await db.execute(select(User).where(User.id == current_user.id))
+    user = result.scalar_one()
+
+    oauth_result = await db.execute(
+        select(OAuthAccount).where(
+            OAuthAccount.user_id == current_user.id,
+            OAuthAccount.provider == provider,
+        )
+    )
+    account = oauth_result.scalar_one_or_none()
+    if account is None:
+        raise HTTPException(status.HTTP_404_NOT_FOUND, f"No linked {provider} account found")
+
+    # Safety: don't let users lock themselves out.
+    all_oauth = await db.execute(
+        select(OAuthAccount).where(OAuthAccount.user_id == current_user.id)
+    )
+    oauth_count = len(all_oauth.scalars().all())
+
+    if user.password_hash is None and oauth_count <= 1:
+        raise HTTPException(
+            status.HTTP_400_BAD_REQUEST,
+            "Cannot unlink the only login method. Set a password first.",
+        )
+
+    await db.delete(account)
+    await db.commit()
+    return {"ok": True}
+
+
+# ── Avatar update ─────────────────────────────────────────────────────
+
+
+class _UpdateAvatarRequest(BaseModel):
+    avatar_url: str = Field(min_length=1)
+
+
+@router.put("/me/avatar", response_model=UserProfile)
+async def update_avatar(
+    body: _UpdateAvatarRequest,
+    current_user: UserProfile = Depends(get_current_user),
+    db: AsyncSession = Depends(get_session),
+) -> UserProfile:
+    """Update the authenticated user's avatar URL.
+
+    Accepts {"avatar_url": "https://..."} — the client uploads the image
+    to its own storage and passes the resulting URL here.
+    """
+    if not body.avatar_url.startswith(("https://", "http://", "data:image/")):
+        raise HTTPException(status.HTTP_400_BAD_REQUEST, "Invalid avatar URL")
+
+    result = await db.execute(select(User).where(User.id == current_user.id))
+    user = result.scalar_one()
+    user.avatar_url = body.avatar_url
+    await db.commit()
+
+    return await _build_profile(current_user.id, current_user.email, db)
+
+
+# ── Account deletion ─────────────────────────────────────────────────
+
+
+@router.delete("/me", status_code=status.HTTP_200_OK)
+async def delete_account(
+    current_user: UserProfile = Depends(get_current_user),
+    db: AsyncSession = Depends(get_session),
+) -> dict[str, bool]:
+    """Permanently delete the authenticated user's account.
+
+    Cascades: refresh tokens, OAuth accounts, subscription, and all memory
+    rows are deleted via SQLAlchemy relationship cascades.  Stripe subscription
+    is cancelled if active.
+    """
+    # Cancel Stripe subscription if present.
+    try:
+        from app.billing.stripe_service import stripe_service  # noqa: PLC0415
+        await stripe_service.cancel_subscription(current_user.id, db)
+    except HTTPException:
+        pass  # No subscription — that's fine
+
+    # Delete all memory rows (core, associative, episodic, proactive).
+    try:
+        from app.models import (  # noqa: PLC0415
+            MemoryAssociative, MemoryCore, MemoryEpisodic, MemoryProactive,
+        )
+        for model in (MemoryCore, MemoryAssociative, MemoryEpisodic, MemoryProactive):
+            await db.execute(
+                model.__table__.delete().where(model.user_id == current_user.id)
+            )
+    except Exception:
+        pass  # Non-critical — cascade on User will handle most
+
+    # Delete the user row — cascades handle refresh_tokens, oauth_accounts, subscription.
+    result = await db.execute(select(User).where(User.id == current_user.id))
+    user = result.scalar_one()
+    await db.delete(user)
+    await db.commit()
+
+    return {"ok": True}

app/api/routes/backup.py

@@ -1,171 +0,0 @@
-"""Backup routes: upload, download, history, and delete E2E-encrypted backups.
-
-Blobs are stored in S3 via BlobStore. Backup metadata is persisted in the
-PostgreSQL ``backup_metadata`` table.
-
-IMPORTANT: GET /history must be declared BEFORE GET / to avoid FastAPI
-treating "history" as a ``{backup_id}`` path parameter.
-"""
-
-from __future__ import annotations
-
-import uuid
-from email.utils import parsedate_to_datetime
-
-from fastapi import APIRouter, Depends, Header, HTTPException, Request, Response, status
-from sqlalchemy import func, select
-from sqlalchemy.ext.asyncio import AsyncSession
-
-from app.api.deps import get_current_user
-from app.billing.tier_manager import tier_manager
-from app.db import get_session
-from app.models import BackupMetadata as BackupMetadataModel
-from app.schemas import BackupMetadata, UserProfile
-from app.storage.blob_store import BlobStore
-from app.storage.encryption import reject_if_tampered
-
-router = APIRouter(prefix="/backup", tags=["backup"])
-
-_blob_store = BlobStore()
-
-
-async def _current_backup_bytes(user_id: str, db: AsyncSession) -> int:
-    """Return total backup bytes stored by *user_id*."""
-    result = await db.execute(
-        select(func.coalesce(func.sum(BackupMetadataModel.size_bytes), 0)).where(
-            BackupMetadataModel.user_id == user_id
-        )
-    )
-    return int(result.scalar_one())
-
-
-async def _check_backup_quota(
-    user: UserProfile, size_bytes: int, db: AsyncSession
-) -> None:
-    """Raise HTTP 402 if the upload would exceed the tier's backup limit."""
-    current = await _current_backup_bytes(user.id, db)
-    tier_manager.enforce_backup_quota(
-        user.tier, current_bytes=current, additional_bytes=size_bytes
-    )
-
-
-@router.put("")
-async def upload_backup(
-    request: Request,
-    x_backup_version: int = Header(..., alias="X-Backup-Version"),
-    x_backup_timestamp: int = Header(..., alias="X-Backup-Timestamp"),
-    x_backup_checksum: str = Header(..., alias="X-Backup-Checksum"),
-    current_user: UserProfile = Depends(get_current_user),
-    db: AsyncSession = Depends(get_session),
-) -> dict[str, bool]:
-    """Upload an E2E-encrypted backup blob.
-
-    Metadata is passed via custom headers; the raw body is the encrypted blob.
-    """
-    blob = await request.body()
-    reject_if_tampered(blob, x_backup_checksum)
-    await _check_backup_quota(current_user, len(blob), db)
-
-    s3_key = await _blob_store.upload(
-        current_user.id, "backup", str(x_backup_timestamp), blob, x_backup_checksum
-    )
-
-    row = BackupMetadataModel(
-        id=str(uuid.uuid4()),
-        user_id=current_user.id,
-        s3_key=s3_key,
-        version=x_backup_version,
-        timestamp=x_backup_timestamp,
-        checksum=x_backup_checksum,
-        size_bytes=len(blob),
-    )
-    db.add(row)
-    await db.commit()
-
-    return {"ok": True}
-
-
-@router.get("/history", response_model=list[BackupMetadata])
-async def backup_history(
-    current_user: UserProfile = Depends(get_current_user),
-    db: AsyncSession = Depends(get_session),
-) -> list[BackupMetadata]:
-    """Return backup metadata records for the authenticated user (no blob bytes)."""
-    result = await db.execute(
-        select(BackupMetadataModel)
-        .where(BackupMetadataModel.user_id == current_user.id)
-        .order_by(BackupMetadataModel.timestamp.desc())
-    )
-    rows = result.scalars().all()
-    return [
-        BackupMetadata(
-            version=r.version,
-            timestamp=r.timestamp,
-            checksum=r.checksum,
-            chunk_count=1,
-        )
-        for r in rows
-    ]
-
-
-@router.get("")
-async def download_backup(
-    request: Request,
-    current_user: UserProfile = Depends(get_current_user),
-    db: AsyncSession = Depends(get_session),
-) -> Response:
-    """Download the latest backup blob. Supports ``If-Modified-Since``."""
-    result = await db.execute(
-        select(BackupMetadataModel)
-        .where(BackupMetadataModel.user_id == current_user.id)
-        .order_by(BackupMetadataModel.timestamp.desc())
-        .limit(1)
-    )
-    latest = result.scalar_one_or_none()
-    if latest is None:
-        raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail="No backup found")
-
-    ims_header = request.headers.get("If-Modified-Since")
-    if ims_header:
-        try:
-            ims_dt = parsedate_to_datetime(ims_header)
-            ims_ms = int(ims_dt.timestamp() * 1000)
-            if latest.timestamp <= ims_ms:
-                return Response(status_code=status.HTTP_304_NOT_MODIFIED)
-        except Exception:
-            pass  # malformed header — ignore and serve the blob
-
-    blob = await _blob_store.download(current_user.id, latest.s3_key)
-    return Response(
-        content=blob,
-        media_type="application/octet-stream",
-        headers={
-            "X-Backup-Version": str(latest.version),
-            "X-Backup-Timestamp": str(latest.timestamp),
-            "X-Checksum": latest.checksum,
-        },
-    )
-
-
-@router.delete("/{backup_id}", response_model=dict)
-async def delete_backup(
-    backup_id: str,
-    current_user: UserProfile = Depends(get_current_user),
-    db: AsyncSession = Depends(get_session),
-) -> dict[str, bool]:
-    """Delete a specific backup by ID."""
-    result = await db.execute(
-        select(BackupMetadataModel).where(
-            BackupMetadataModel.id == backup_id,
-            BackupMetadataModel.user_id == current_user.id,
-        )
-    )
-    target = result.scalar_one_or_none()
-    if target is None:
-        raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail="Backup not found")
-
-    await _blob_store.delete(current_user.id, target.s3_key)
-    await db.delete(target)
-    await db.commit()
-
-    return {"ok": True}

app/api/routes/billing.py

@@ -83,3 +83,16 @@ async def cancel_subscription(
     """Cancel the active subscription."""
     await stripe_service.cancel_subscription(current_user.id, db)
     return {"ok": True}
+
+
+@router.get("/invoices", response_model=list[dict])
+async def list_invoices(
+    current_user: UserProfile = Depends(get_current_user),
+    db: AsyncSession = Depends(get_session),
+) -> list[dict[str, Any]]:
+    """Return billing history (invoices) from Stripe.
+
+    Returns an empty list when Stripe is not configured.
+    """
+    invoices = await stripe_service.list_invoices(current_user.id, db)
+    return invoices

app/api/routes/chat.py

@@ -1,4 +1,4 @@
-"""Chat routes: POST /chat (REST fallback).
+"""Chat routes: POST /chat (REST fallback) and POST /chat/embed (text → vector).
 
 WebSocket chat is handled by the unified device WS endpoint (/api/v1/ws/device).
 """
@@ -7,14 +7,30 @@ from __future__ import annotations
 
 from fastapi import APIRouter, Depends
 from fastapi.responses import JSONResponse
+from pydantic import BaseModel
 
 from app.api.deps import get_current_user
 from app.core.deep_agent import run_home
+from app.core.llm import embed
 from app.schemas import ChatRequest, UserProfile
 
 router = APIRouter(prefix="/chat", tags=["chat"])
 
 
+# ── Embed helpers ─────────────────────────────────────────────────────────
+
+
+class _EmbedRequest(BaseModel):
+    text: str
+
+
+class _EmbedResponse(BaseModel):
+    vector: list[float]
+
+
+# ── Endpoints ─────────────────────────────────────────────────────────────
+
+
 @router.post("")
 async def chat(
     body: ChatRequest,
@@ -27,3 +43,17 @@ async def chat(
         context=body.context.model_dump(),
     )
     return JSONResponse(content={"response": response})
+
+
+@router.post("/embed", response_model=_EmbedResponse)
+async def embed_text(
+    body: _EmbedRequest,
+    current_user: UserProfile = Depends(get_current_user),
+) -> _EmbedResponse:
+    """Generate a 1536-dim embedding vector for the given text.
+
+    Uses ``text-embedding-3-small`` via OpenAI.  Auth required (JWT).
+    Used by Electron (vectordb.ts) for local note search.
+    """
+    vector = await embed(body.text)
+    return _EmbedResponse(vector=vector)

app/api/routes/plugins.py

@@ -1,148 +0,0 @@
-"""Plugins routes: browse and install plugins from the marketplace.
-
-Backed by ``PluginRegistry`` and ``RevenueShare`` service classes that
-persist data in the PostgreSQL ``plugins`` and ``revenue_events`` tables.
-"""
-
-from __future__ import annotations
-
-from typing import Any, Literal
-
-from fastapi import APIRouter, Depends, HTTPException, Query, status
-from pydantic import BaseModel
-from sqlalchemy import select
-from sqlalchemy.ext.asyncio import AsyncSession
-
-from app.api.deps import get_current_user
-from app.db import get_session
-from app.marketplace.plugin_registry import registry
-from app.marketplace.revenue_share import revenue_share
-from app.models import PluginInstallation, PluginReview as PluginReviewModel
-from app.schemas import PluginInstallRequest, PluginListResponse, PluginManifest, UserProfile
-
-router = APIRouter(prefix="/plugins", tags=["plugins"])
-
-
-# ── Tier gate ─────────────────────────────────────────────────────────
-
-def _require_plugin_tier(user: UserProfile) -> None:
-    """Raise HTTP 403 for users below Power tier."""
-    if user.tier not in ("power", "team"):
-        raise HTTPException(
-            status_code=status.HTTP_403_FORBIDDEN,
-            detail="Plugin marketplace requires Power tier or above",
-        )
-
-
-# ── Local detail schema ────────────────────────────────────────────────
-
-class _PluginDetail(BaseModel):
-    plugin: PluginManifest
-    install_count: int
-    ratings: list[Any]
-
-
-# ── Routes ────────────────────────────────────────────────────────────
-
-@router.get("", response_model=PluginListResponse)
-async def list_plugins(
-    category: str | None = Query(default=None),
-    q: str | None = Query(default=None),
-    page: int = Query(default=1, ge=1),
-    sort: Literal["rating", "installs", "newest"] = Query(default="newest"),
-    current_user: UserProfile = Depends(get_current_user),
-    db: AsyncSession = Depends(get_session),
-) -> PluginListResponse:
-    """Browse the plugin marketplace. Requires Power tier or above."""
-    _require_plugin_tier(current_user)
-    return await registry.list_plugins(db, category=category, query=q, page=page, sort=sort)
-
-
-@router.get("/{plugin_id}", response_model=_PluginDetail)
-async def get_plugin(
-    plugin_id: str,
-    current_user: UserProfile = Depends(get_current_user),
-    db: AsyncSession = Depends(get_session),
-) -> _PluginDetail:
-    """Get full plugin details including install count. Requires Power tier or above."""
-    _require_plugin_tier(current_user)
-    entry = await registry.get_plugin(db, plugin_id)
-    if entry is None:
-        raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail="Plugin not found")
-
-    # Fetch review ratings for this plugin
-    review_result = await db.execute(
-        select(PluginReviewModel).where(PluginReviewModel.plugin_id == plugin_id)
-    )
-    reviews = review_result.scalars().all()
-    ratings = [
-        {
-            "reviewer_id": r.reviewer_id,
-            "decision": r.decision,
-            "notes": r.notes,
-            "reviewed_at": int(r.reviewed_at.timestamp() * 1000) if r.reviewed_at else None,
-        }
-        for r in reviews
-    ]
-
-    return _PluginDetail(
-        plugin=entry["manifest"],
-        install_count=entry["install_count"],
-        ratings=ratings,
-    )
-
-
-@router.post("/{plugin_id}/install", response_model=dict)
-async def install_plugin(
-    plugin_id: str,
-    body: PluginInstallRequest,  # noqa: ARG001 — reserved for future fields
-    current_user: UserProfile = Depends(get_current_user),
-    db: AsyncSession = Depends(get_session),
-) -> dict[str, Any]:
-    """Install a plugin. Triggers Stripe Connect revenue split for paid plugins.
-
-    Requires Power tier or above.
-    """
-    _require_plugin_tier(current_user)
-    entry = await registry.get_plugin(db, plugin_id)
-    if entry is None:
-        raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail="Plugin not found")
-
-    # Record the installation in plugin_installations
-    installation = PluginInstallation(
-        plugin_id=plugin_id,
-        user_id=current_user.id,
-    )
-    db.add(installation)
-    await db.flush()
-
-    await revenue_share.record_install(
-        db,
-        plugin_id=plugin_id,
-        user_id=current_user.id,
-        amount_cents=entry["manifest"].price_cents,
-    )
-
-    download_url = f"https://cdn.adiuva.app/plugins/{plugin_id}/package.zip"
-    return {"ok": True, "download_url": download_url}
-
-
-@router.delete("/{plugin_id}/install", response_model=dict)
-async def uninstall_plugin(
-    plugin_id: str,
-    current_user: UserProfile = Depends(get_current_user),
-    db: AsyncSession = Depends(get_session),
-) -> dict[str, bool]:
-    """Unregister a plugin installation."""
-    result = await db.execute(
-        select(PluginInstallation).where(
-            PluginInstallation.plugin_id == plugin_id,
-            PluginInstallation.user_id == current_user.id,
-        )
-    )
-    installation = result.scalar_one_or_none()
-    if installation is not None:
-        await db.delete(installation)
-        await db.commit()
-    await registry.record_uninstall(db, plugin_id)
-    return {"ok": True}

app/api/routes/storage.py

@@ -1,195 +0,0 @@
-"""Storage routes: CRUD for E2E-encrypted cloud records.
-
-Blobs are stored in S3 via BlobStore. Record metadata is persisted in the
-PostgreSQL ``storage_records`` table.
-"""
-
-from __future__ import annotations
-
-import uuid
-
-from fastapi import APIRouter, Depends, HTTPException, Query, Response, status
-from pydantic import BaseModel
-from sqlalchemy import func, select
-from sqlalchemy.ext.asyncio import AsyncSession
-
-from app.api.deps import get_current_user
-from app.billing.tier_manager import tier_manager
-from app.db import get_session
-from app.models import StorageRecord
-from app.schemas import StorageRecordCreate, StorageRecordUpdate, UserProfile
-from app.storage.blob_store import BlobStore
-from app.storage.encryption import reject_if_tampered
-
-router = APIRouter(prefix="/storage", tags=["storage"])
-
-_blob_store = BlobStore()
-
-
-# ── Local response schemas ─────────────────────────────────────────────
-
-class _CreateResponse(BaseModel):
-    id: str
-    created_at: int
-
-
-class _RecordMeta(BaseModel):
-    id: str
-    table: str
-    checksum: str
-    created_at: int
-    updated_at: int
-
-
-# ── Helpers ────────────────────────────────────────────────────────────
-
-async def _current_usage_bytes(user_id: str, db: AsyncSession) -> int:
-    """Return total bytes stored by *user_id*."""
-    result = await db.execute(
-        select(func.coalesce(func.sum(StorageRecord.size_bytes), 0)).where(
-            StorageRecord.user_id == user_id
-        )
-    )
-    return int(result.scalar_one())
-
-
-async def _check_quota(user: UserProfile, additional_bytes: int, db: AsyncSession) -> None:
-    """Raise HTTP 402 if adding *additional_bytes* would exceed the tier limit."""
-    current = await _current_usage_bytes(user.id, db)
-    tier_manager.enforce_quota(user.tier, current_bytes=current, additional_bytes=additional_bytes)
-
-
-async def _get_record_for_user(
-    record_id: str, user_id: str, db: AsyncSession
-) -> StorageRecord:
-    """Look up a record and verify ownership. Returns 404 on mismatch
-    to prevent user enumeration attacks."""
-    result = await db.execute(
-        select(StorageRecord).where(
-            StorageRecord.id == record_id, StorageRecord.user_id == user_id
-        )
-    )
-    record = result.scalar_one_or_none()
-    if record is None:
-        raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail="Record not found")
-    return record
-
-
-# ── Routes ─────────────────────────────────────────────────────────────
-
-@router.post("/records", response_model=_CreateResponse, status_code=status.HTTP_201_CREATED)
-async def create_record(
-    body: StorageRecordCreate,
-    current_user: UserProfile = Depends(get_current_user),
-    db: AsyncSession = Depends(get_session),
-) -> _CreateResponse:
-    """Upload a new E2E-encrypted blob. Verifies checksum before storing."""
-    reject_if_tampered(body.blob, body.checksum)
-    await _check_quota(current_user, len(body.blob), db)
-
-    record_id = str(uuid.uuid4())
-
-    s3_key = await _blob_store.upload(
-        current_user.id, body.table, record_id, body.blob, body.checksum
-    )
-
-    record = StorageRecord(
-        id=record_id,
-        user_id=current_user.id,
-        table_name=body.table,
-        s3_key=s3_key,
-        checksum=body.checksum,
-        size_bytes=len(body.blob),
-    )
-    db.add(record)
-    await db.commit()
-    await db.refresh(record)
-
-    created_at_ms = int(record.created_at.timestamp() * 1000)
-    return _CreateResponse(id=record_id, created_at=created_at_ms)
-
-
-@router.get("/records", response_model=list[_RecordMeta])
-async def list_records(
-    table: str | None = Query(default=None),
-    page: int = Query(default=1, ge=1),
-    limit: int = Query(default=50, ge=1, le=200),
-    current_user: UserProfile = Depends(get_current_user),
-    db: AsyncSession = Depends(get_session),
-) -> list[_RecordMeta]:
-    """List record metadata for the authenticated user. Blob bytes are never returned."""
-    query = select(StorageRecord).where(StorageRecord.user_id == current_user.id)
-    if table is not None:
-        query = query.where(StorageRecord.table_name == table)
-    query = query.offset((page - 1) * limit).limit(limit)
-
-    result = await db.execute(query)
-    rows = result.scalars().all()
-
-    return [
-        _RecordMeta(
-            id=r.id,
-            table=r.table_name,
-            checksum=r.checksum,
-            created_at=int(r.created_at.timestamp() * 1000),
-            updated_at=int(r.updated_at.timestamp() * 1000),
-        )
-        for r in rows
-    ]
-
-
-@router.get("/records/{record_id}")
-async def download_record(
-    record_id: str,
-    current_user: UserProfile = Depends(get_current_user),
-    db: AsyncSession = Depends(get_session),
-) -> Response:
-    """Download an E2E-encrypted blob. Returns raw bytes with ``X-Checksum`` header."""
-    record = await _get_record_for_user(record_id, current_user.id, db)
-    blob = await _blob_store.download(current_user.id, record.s3_key)
-    return Response(
-        content=blob,
-        media_type="application/octet-stream",
-        headers={"X-Checksum": record.checksum},
-    )
-
-
-@router.put("/records/{record_id}", response_model=dict)
-async def update_record(
-    record_id: str,
-    body: StorageRecordUpdate,
-    current_user: UserProfile = Depends(get_current_user),
-    db: AsyncSession = Depends(get_session),
-) -> dict[str, bool]:
-    """Replace the blob for an existing record. Verifies checksum before storing."""
-    record = await _get_record_for_user(record_id, current_user.id, db)
-    reject_if_tampered(body.blob, body.checksum)
-
-    delta = len(body.blob) - record.size_bytes
-    if delta > 0:
-        await _check_quota(current_user, delta, db)
-
-    s3_key = await _blob_store.upload(
-        current_user.id, record.table_name, record_id, body.blob, body.checksum
-    )
-
-    record.s3_key = s3_key
-    record.checksum = body.checksum
-    record.size_bytes = len(body.blob)
-    await db.commit()
-
-    return {"ok": True}
-
-
-@router.delete("/records/{record_id}", response_model=dict)
-async def delete_record(
-    record_id: str,
-    current_user: UserProfile = Depends(get_current_user),
-    db: AsyncSession = Depends(get_session),
-) -> dict[str, bool]:
-    """Delete a record and its S3 blob."""
-    record = await _get_record_for_user(record_id, current_user.id, db)
-    await _blob_store.delete(current_user.id, record.s3_key)
-    await db.delete(record)
-    await db.commit()
-    return {"ok": True}

app/api/routes/vectors.py

@@ -1,79 +0,0 @@
-"""Vectors routes: upsert, search, delete cloud vector store entries, and embed text."""
-
-from __future__ import annotations
-
-from fastapi import APIRouter, Depends
-from pydantic import BaseModel
-
-from app.api.deps import get_current_user
-from app.core.llm import embed
-from app.schemas import (
-    UserProfile,
-    VectorSearchRequest,
-    VectorSearchResponse,
-    VectorUpsertRequest,
-)
-from app.storage.encryption import reject_if_tampered
-from app.storage.vector_store import VectorStore
-
-router = APIRouter(prefix="/storage", tags=["vectors"])
-
-_vector_store = VectorStore()
-
-
-class _VectorDeleteRequest(BaseModel):
-    ids: list[str]
-
-
-class _EmbedRequest(BaseModel):
-    text: str
-
-
-class _EmbedResponse(BaseModel):
-    vector: list[float]
-
-
-@router.post("/vectors/upsert", response_model=dict)
-async def upsert_vectors(
-    body: VectorUpsertRequest,
-    current_user: UserProfile = Depends(get_current_user),
-) -> dict[str, int]:
-    """Verify checksums and store encrypted vectors in the user-scoped namespace."""
-    for item in body.vectors:
-        reject_if_tampered(item.blob, item.checksum)
-    await _vector_store.upsert(current_user.id, body.vectors)
-    return {"upserted": len(body.vectors)}
-
-
-@router.post("/vectors/search", response_model=VectorSearchResponse)
-async def search_vectors(
-    body: VectorSearchRequest,
-    current_user: UserProfile = Depends(get_current_user),
-) -> VectorSearchResponse:
-    """Search the user-scoped vector namespace with an encrypted query blob."""
-    results = await _vector_store.search(current_user.id, body.query_blob, body.top_k)
-    return VectorSearchResponse(results=results)
-
-
-@router.delete("/vectors", response_model=dict)
-async def delete_vectors(
-    body: _VectorDeleteRequest,
-    current_user: UserProfile = Depends(get_current_user),
-) -> dict[str, bool]:
-    """Delete vectors by ID, scoped to the authenticated user."""
-    await _vector_store.delete(current_user.id, body.ids)
-    return {"ok": True}
-
-
-@router.post("/vectors/embed", response_model=_EmbedResponse)
-async def embed_text(
-    body: _EmbedRequest,
-    current_user: UserProfile = Depends(get_current_user),
-) -> _EmbedResponse:
-    """Generate a 1536-dim embedding vector for the given text.
-
-    Uses ``text-embedding-3-small`` via OpenAI.  Auth required (JWT).
-    Used by backend tools (note_agent) and Electron (vectordb.ts) alike.
-    """
-    vector = await embed(body.text)
-    return _EmbedResponse(vector=vector)

app/auth/__init__.py

@@ -0,0 +1 @@
+"OAuth provider abstractions and utilities."

app/auth/oauth_providers.py

@@ -0,0 +1,135 @@
+"""OAuth 2.0 + PKCE provider abstractions.
+
+Each provider implements a three-step flow designed for a desktop (public) client:
+
+  1. get_authorization_url(state, code_challenge) → str
+       Build the provider's consent-screen URL.  State and code_challenge are
+       generated server-side; the client opens this URL in the system browser.
+
+  2. exchange_code(code, code_verifier, redirect_uri) → dict
+       Exchange the short-lived authorization code for an access token.
+       The code_verifier proves ownership of the PKCE challenge.
+
+  3. get_userinfo(access_token) → OAuthUserInfo
+       Fetch the canonical user identity from the provider.
+
+Currently supported providers:
+  - GoogleOAuthProvider  (scope: openid email profile)
+
+Adding a new provider:
+  - Implement the three methods above.
+  - Register in _PROVIDERS inside routes/auth.py.
+"""
+
+from __future__ import annotations
+
+import base64
+import hashlib
+import os
+import urllib.parse
+from dataclasses import dataclass
+
+import httpx
+
+
+# ── Data transfer objects ─────────────────────────────────────────────
+
+
+@dataclass
+class OAuthUserInfo:
+    """Normalized user identity returned by any provider."""
+
+    provider_user_id: str
+    email: str
+    email_verified: bool
+    avatar_url: str | None
+    name: str | None
+
+
+# ── PKCE helpers ──────────────────────────────────────────────────────
+
+
+def generate_pkce_pair() -> tuple[str, str]:
+    """Generate a (code_verifier, code_challenge) pair for PKCE S256.
+
+    The code_verifier is a random 32-byte URL-safe base64 string.
+    The code_challenge is SHA-256(code_verifier) base64url-encoded (no padding).
+    """
+    code_verifier = base64.urlsafe_b64encode(os.urandom(32)).rstrip(b"=").decode()
+    digest = hashlib.sha256(code_verifier.encode()).digest()
+    code_challenge = base64.urlsafe_b64encode(digest).rstrip(b"=").decode()
+    return code_verifier, code_challenge
+
+
+# ── Google provider ───────────────────────────────────────────────────
+
+
+class GoogleOAuthProvider:
+    """Google OAuth 2.0 provider (openid email profile scope).
+
+    Uses Google's standard authorization endpoint with PKCE S256.
+    Does NOT use google-auth-oauthlib to keep the flow generic and async.
+    """
+
+    name = "google"
+
+    _AUTH_URL = "https://accounts.google.com/o/oauth2/v2/auth"
+    _TOKEN_URL = "https://oauth2.googleapis.com/token"
+    _USERINFO_URL = "https://www.googleapis.com/oauth2/v3/userinfo"
+
+    def __init__(self, client_id: str, client_secret: str, redirect_uri: str) -> None:
+        self.client_id = client_id
+        self.client_secret = client_secret
+        self.redirect_uri = redirect_uri
+
+    def get_authorization_url(self, state: str, code_challenge: str) -> str:
+        """Build the Google consent-screen URL."""
+        params = {
+            "client_id": self.client_id,
+            "redirect_uri": self.redirect_uri,
+            "response_type": "code",
+            "scope": "openid email profile",
+            "state": state,
+            "code_challenge": code_challenge,
+            "code_challenge_method": "S256",
+            "access_type": "offline",
+            "prompt": "select_account",
+        }
+        return f"{self._AUTH_URL}?{urllib.parse.urlencode(params)}"
+
+    async def exchange_code(
+        self, code: str, code_verifier: str, redirect_uri: str
+    ) -> dict:
+        """Exchange authorization code for an access token."""
+        async with httpx.AsyncClient() as client:
+            response = await client.post(
+                self._TOKEN_URL,
+                data={
+                    "client_id": self.client_id,
+                    "client_secret": self.client_secret,
+                    "code": code,
+                    "code_verifier": code_verifier,
+                    "grant_type": "authorization_code",
+                    "redirect_uri": redirect_uri,
+                },
+            )
+        response.raise_for_status()
+        return response.json()
+
+    async def get_userinfo(self, access_token: str) -> OAuthUserInfo:
+        """Fetch the authenticated user's identity from Google."""
+        async with httpx.AsyncClient() as client:
+            response = await client.get(
+                self._USERINFO_URL,
+                headers={"Authorization": f"Bearer {access_token}"},
+            )
+        response.raise_for_status()
+        data = response.json()
+
+        return OAuthUserInfo(
+            provider_user_id=data["sub"],
+            email=data["email"],
+            email_verified=data.get("email_verified", False),
+            avatar_url=data.get("picture"),
+            name=data.get("name"),
+        )

app/billing/stripe_service.py

@@ -43,8 +43,8 @@ class StripeService:
         self,
         user_id: str,
         tier: str,
-        success_url: str = "https://app.adiuva.app/billing/success?session_id={CHECKOUT_SESSION_ID}",
-        cancel_url: str = "https://app.adiuva.app/billing/cancel",
+        success_url: str = "https://app.adiuvai.app/billing/success?session_id={CHECKOUT_SESSION_ID}",
+        cancel_url: str = "https://app.adiuvai.app/billing/cancel",
     ) -> str:
         """Create a Stripe checkout session and return the URL.
 
@@ -200,6 +200,45 @@ class StripeService:
         sub.status = "canceled"
         await db.commit()
 
+    async def list_invoices(
+        self, user_id: str, db: AsyncSession, limit: int = 24
+    ) -> list[dict[str, Any]]:
+        """Return recent invoices for the user from Stripe.
+
+        Returns an empty list when Stripe is not configured or the user has
+        no ``stripe_customer_id``.
+        """
+        if not self._configured():
+            return []
+
+        from app.models import User  # noqa: PLC0415
+
+        result = await db.execute(
+            select(User.stripe_customer_id).where(User.id == user_id)
+        )
+        customer_id = result.scalar_one_or_none()
+        if not customer_id:
+            return []
+
+        try:
+            s = self._client()
+            invoices = s.Invoice.list(customer=customer_id, limit=limit)
+            return [
+                {
+                    "id": inv.id,
+                    "amount_due": inv.amount_due,
+                    "amount_paid": inv.amount_paid,
+                    "currency": inv.currency,
+                    "status": inv.status,
+                    "created": inv.created * 1000,  # epoch ms
+                    "invoice_url": inv.hosted_invoice_url,
+                    "invoice_pdf": inv.invoice_pdf,
+                }
+                for inv in invoices.auto_paging_iter()
+            ]
+        except Exception:
+            return []
+
     # ── Private DB helpers ───────────────────────────────────────────────
 
     async def _upsert_subscription(

app/billing/tier_manager.py

@@ -22,44 +22,32 @@ FEATURES: dict[str, dict[str, Any]] = {
         "agents": 3,
         "batch_active": 2,
         "batch_runs_per_day": 5,
-        "cloud_storage_gb": 0,
-        "backup_gb": 0,
         "providers": 1,
         "batch_builder": False,
-        "plugin_marketplace": False,
         "sso": False,
     },
     "pro": {
         "agents": -1,           # unlimited
         "batch_active": 10,
         "batch_runs_per_day": 50,
-        "cloud_storage_gb": 5,
-        "backup_gb": 5,
         "providers": -1,
         "batch_builder": False,
-        "plugin_marketplace": False,
         "sso": False,
     },
     "power": {
         "agents": -1,
         "batch_active": -1,     # unlimited
         "batch_runs_per_day": -1,  # unlimited
-        "cloud_storage_gb": 25,
-        "backup_gb": 25,
         "providers": -1,
         "batch_builder": True,
-        "plugin_marketplace": True,
         "sso": False,
     },
     "team": {
         "agents": -1,
         "batch_active": -1,
         "batch_runs_per_day": -1,  # unlimited
-        "cloud_storage_gb": -1,  # unlimited
-        "backup_gb": -1,         # unlimited
         "providers": -1,
         "batch_builder": True,
-        "plugin_marketplace": True,
         "sso": True,
     },
 }
@@ -125,71 +113,6 @@ class TierManager:
         """Return the requests-per-minute limit for ``tier``."""
         return RATE_LIMITS.get(tier, RATE_LIMITS["free"])
 
-    # ── Storage quota ────────────────────────────────────────────────────
-
-    def enforce_quota(
-        self,
-        tier: BillingTier,
-        current_bytes: int = 0,
-        additional_bytes: int = 0,
-    ) -> None:
-        """Raise ``HTTP 402`` if the user would exceed their cloud storage quota.
-
-        ``tier`` is the caller's current tier (from ``current_user.tier``).
-        ``current_bytes`` is the total bytes already stored (queried by caller).
-        """
-        limit_gb: int = FEATURES[tier]["cloud_storage_gb"]
-        if limit_gb == 0:
-            raise HTTPException(
-                status_code=status.HTTP_402_PAYMENT_REQUIRED,
-                detail=f"Cloud storage is not available on the '{tier}' tier",
-            )
-        if limit_gb == -1:
-            return  # unlimited
-        limit_bytes = limit_gb * 1024 ** 3
-        if current_bytes + additional_bytes > limit_bytes:
-            raise HTTPException(
-                status_code=status.HTTP_402_PAYMENT_REQUIRED,
-                detail=f"Storage quota exceeded for tier '{tier}'",
-            )
-
-    def enforce_backup_quota(
-        self,
-        tier: BillingTier,
-        current_bytes: int = 0,
-        additional_bytes: int = 0,
-    ) -> None:
-        """Raise ``HTTP 402`` if the user would exceed their backup quota."""
-        limit_gb: int = FEATURES[tier]["backup_gb"]
-        if limit_gb == 0:
-            raise HTTPException(
-                status_code=status.HTTP_402_PAYMENT_REQUIRED,
-                detail=f"Backup is not available on the '{tier}' tier",
-            )
-        if limit_gb == -1:
-            return  # unlimited
-        limit_bytes = limit_gb * 1024 ** 3
-        if current_bytes + additional_bytes > limit_bytes:
-            raise HTTPException(
-                status_code=status.HTTP_402_PAYMENT_REQUIRED,
-                detail=f"Backup quota exceeded for tier '{tier}'",
-            )
-
-    def check_quota(
-        self,
-        tier: BillingTier,
-        current_bytes: int = 0,
-        additional_bytes: int = 0,
-    ) -> bool:
-        """Return ``True`` if the user can store ``additional_bytes`` more data."""
-        limit_gb: int = FEATURES[tier]["cloud_storage_gb"]
-        if limit_gb == 0:
-            return False
-        if limit_gb == -1:
-            return True
-        limit_bytes = limit_gb * 1024 ** 3
-        return current_bytes + additional_bytes <= limit_bytes
-
 
 # Module-level singleton shared across the app.
 tier_manager = TierManager()

app/config/settings.py

@@ -3,7 +3,7 @@ from pydantic_settings import BaseSettings, SettingsConfigDict
 
 
 class Settings(BaseSettings):
-    DATABASE_URL: str = "postgresql+asyncpg://postgres:postgres@localhost:5432/adiuva"
+    DATABASE_URL: str = "postgresql+asyncpg://postgres:postgres@localhost:5432/adiuvai"
     JWT_SECRET: str = "change-me-in-production"
     JWT_ALGORITHM: str = "HS256"
     JWT_ACCESS_TOKEN_EXPIRE_MINUTES: int = 30
@@ -12,26 +12,22 @@ class Settings(BaseSettings):
     STRIPE_SECRET_KEY: str = ""
     STRIPE_WEBHOOK_SECRET: str = ""
 
-    S3_BUCKET: str = ""
-    S3_REGION: str = "us-east-1"
-    S3_ENDPOINT_URL: str = ""
-    AWS_ACCESS_KEY_ID: str = ""
-    AWS_SECRET_ACCESS_KEY: str = ""
-
-    PINECONE_API_KEY: str = ""
-    PINECONE_INDEX: str = "adiuva"
-    QDRANT_URL: str = ""
-    QDRANT_API_KEY: str = ""
-
     OPENAI_API_KEY: str = ""
     ANTHROPIC_API_KEY: str = ""
     GOOGLE_API_KEY: str = ""
     CEREBRAS_API_KEY: str = ""
 
     LLM_MODEL: str = "gpt-4o"
-    LLM_ROUTER_MODEL: str = "gpt-4o-mini"
     LLM_EMBED_MODEL: str = "text-embedding-3-small"
 
+    # Per-agent model overrides. Leave empty to fall back to LLM_MODEL.
+    LLM_MODEL_CLASSIFIER: str = ""        # _infer_floating_domain (intent routing)
+    LLM_MODEL_HOME_AGENT: str = ""        # home-agent (run_single_agent / stream)
+    LLM_MODEL_FLOATING_AGENT: str = ""    # floating-agent (contextual chat)
+    LLM_MODEL_UNIFIED_PROCESSOR: str = "" # unified-processor (agent_runner)
+    LLM_MODEL_CLOUD_PROCESSOR: str = ""   # cloud-processor (agent_runner)
+    LLM_MODEL_SETUP_AGENT: str = ""       # agent-setup journey
+
     # GitHub Copilot OAuth token storage directory.
     # Leave empty to use the LiteLLM default (~/.config/litellm/github_copilot).
     # In Docker, set this to a path backed by a named volume so tokens survive restarts.
@@ -45,16 +41,33 @@ class Settings(BaseSettings):
     # MS_TENANT_ID: set to 'common' to allow multi-tenant (personal + work accounts).
     MS_TENANT_ID: str = "common"
 
+    # Google Login OAuth credentials — scope: openid email profile.
+    # Separate from GMAIL_CLIENT_ID/SECRET (which uses gmail.readonly scope).
+    GOOGLE_AUTH_CLIENT_ID: str = ""
+    GOOGLE_AUTH_CLIENT_SECRET: str = ""
+    # The redirect URI registered in Google Cloud Console.
+    # Google redirects here after consent; this backend route then bounces to
+    # the adiuvai:// deep link so the Electron app receives the code.
+    # Dev:  http://localhost:8000/api/v1/auth/oauth/google/web-callback
+    # Prod: https://api.adiuvai.com/api/v1/auth/oauth/google/web-callback
+    OAUTH_REDIRECT_URI: str = "http://localhost:8000/api/v1/auth/oauth/google/web-callback"
+
     # Fernet key (URL-safe base64, 32-byte key) for at-rest encryption of OAuth
     # tokens stored in cloud_agent_configs.oauth_token_encrypted.
     # Generate with: from cryptography.fernet import Fernet; Fernet.generate_key()
     OAUTH_ENCRYPTION_KEY: str = ""
 
-    CORS_ORIGINS: list[str] = ["app://.", "http://localhost:3000", "http://localhost:5173"]
+    CORS_ORIGINS: list[str] = [
+        "app://.",
+        "http://localhost:3000",
+        "http://localhost:5173",
+        "http://localhost:4173",      # Vite preview (web SPA)
+        "https://app.adiuvai.com",    # Production web portal
+    ]
 
     LANGFUSE_SECRET_KEY: str = ""
     LANGFUSE_PUBLIC_KEY: str = ""
-    LANGFUSE_HOST: str = "https://cloud.langfuse.com"
+    LANGFUSE_BASE_URL: str = "https://cloud.langfuse.com"
 
     ENV: Literal["dev", "prod"] = "dev"
 

app/core/agent_runner.py

@@ -30,7 +30,6 @@ import asyncio
 import json
 import logging
 import os
-import uuid
 from datetime import datetime, timedelta, timezone
 from typing import Any
 
@@ -43,10 +42,9 @@ from app.agents.note_agent import NOTE_TOOLS
 from app.agents.project_agent import PROJECT_TOOLS
 from app.agents.task_agent import TASK_TOOLS
 from app.agents.timeline_agent import TIMELINE_TOOLS
-from app.config.settings import settings
 from app.core.device_manager import DeviceConnectionManager
-from app.core.langfuse_client import compile_prompt, extract_usage, get_langfuse, get_prompt_or_fallback
-from app.core.llm import get_llm
+from app.core.langfuse_client import compile_prompt, extract_usage, get_langfuse, get_prompt_or_fallback, langfuse_context
+from app.core.llm import get_agent_llm, model_for_agent
 from app.core.preprocessors import detect_content_type, preprocess
 from app.core.ws_context import clear_client_executor, execute_on_client, set_client_executor
 from app.db import async_session
@@ -74,13 +72,13 @@ _MAX_PROCESSING_STEPS: int = 12
 _MAX_SCAN_DEPTH: int = 5
 
 # ── Data-type to tool mapping ─────────────────────────────────────────────
-# NOTE: "projects" is intentionally excluded — project creation/assignment is
-# handled in code by the runner, never delegated to the Step 2 LLM.
 
 _DATA_TYPE_TOOLS: dict[str, list[Any]] = {
     "tasks": TASK_TOOLS,
     "notes": NOTE_TOOLS,
     "timelines": TIMELINE_TOOLS,
+    "timelineEvents": TIMELINE_TOOLS,
+    "projects": PROJECT_TOOLS,
 }
 
 # ── V2: Unified processing prompt (hot-swappable via Langfuse "unified_processing") ──
@@ -228,6 +226,7 @@ async def _run_agent_with_tools(
     tools: list[Any],
     max_steps: int,
     user_id: str = "",
+    session_id: str = "",
     langfuse_prompt: Any = None,
     agent_name: str = "batch-agent",
     _tool_calls_out: list[str] | None = None,
@@ -238,7 +237,7 @@ async def _run_agent_with_tools(
     run is appended to it (used by the caller to count ``create_*`` calls).
     """
     lf = get_langfuse()
-    llm = get_llm()
+    llm = get_agent_llm(agent_name)
     llm_with_tools = llm.bind_tools(tools)
     messages: list[Any] = [
         SystemMessage(content=system_prompt),
@@ -247,6 +246,9 @@ async def _run_agent_with_tools(
 
     tool_map = {tool_def.name: tool_def for tool_def in tools}
 
+    _lf_ctx = langfuse_context(user_id=user_id or None, session_id=session_id or None)
+    _lf_ctx.__enter__()
+
     _span_ctx = (
         lf.start_as_current_observation(
             as_type="span",
@@ -264,7 +266,7 @@ async def _run_agent_with_tools(
                 lf.start_as_current_observation(
                     as_type="generation",
                     name=f"{agent_name}-llm",
-                    model=settings.LLM_MODEL,
+                    model=model_for_agent(agent_name),
                     prompt=langfuse_prompt,
                     input=messages,
                 )
@@ -273,7 +275,7 @@ async def _run_agent_with_tools(
             _gen = _gen_ctx.__enter__() if _gen_ctx else None
             response: AIMessage = await llm_with_tools.ainvoke(messages)
             if _gen_ctx:
-                _gen.update(output=_as_text(response.content), usage=extract_usage(response))
+                _gen.update(output=_as_text(response.content), usage_details=extract_usage(response))
                 _gen_ctx.__exit__(None, None, None)
 
             messages.append(response)
@@ -318,6 +320,7 @@ async def _run_agent_with_tools(
     finally:
         if _span_ctx:
             _span_ctx.__exit__(None, None, None)
+        _lf_ctx.__exit__(None, None, None)
         if lf:
             lf.flush()
 
@@ -386,7 +389,8 @@ async def _scan_directories(
     for file_path in all_files:
         try:
             meta = await execute_on_client(action="get_file_metadata", data={"path": file_path})
-            modified_at = meta.get("modifiedAt")
+            # FE sends snake_case keys on the wire (toSnakeCase transform)
+            modified_at = meta.get("modified_at") or meta.get("modifiedAt")
             if modified_at is None:
                 filtered.append(file_path)
                 continue
@@ -607,7 +611,6 @@ async def run_local_agent(
 
     try:
         # ── Code: scan directories ───────────────────────────────────
-        logger.info("agent_runner: run=%s scanning directories user=%s", run_id, user_id)
         file_paths = await _scan_directories(
             paths=config.directory_paths,
             extensions=config.file_extensions or [],
@@ -686,6 +689,7 @@ async def run_local_agent(
                     tools=processing_tools,
                     max_steps=_MAX_PROCESSING_STEPS,
                     user_id=user_id,
+                    session_id=run_id,
                     langfuse_prompt=prompt_obj,
                     agent_name="unified-processor",
                     _tool_calls_out=file_tool_calls,
@@ -696,6 +700,12 @@ async def run_local_agent(
                 )
                 items_created += file_created
 
+                # Refresh project list when a project was created so
+                # subsequent files see it in the prompt context.
+                if "create_project" in file_tool_calls:
+                    projects = await _fetch_projects()
+                    projects_block = _format_projects(projects)
+
                 logger.info(
                     "agent_runner: run=%s file=%r created=%d result=%s",
                     run_id, file_path, file_created, result_text[:200],
@@ -911,6 +921,7 @@ async def run_cloud_agent(
                     tools=processing_tools,
                     max_steps=_MAX_PROCESSING_STEPS,
                     user_id=user_id,
+                    session_id=run_id,
                     langfuse_prompt=cloud_prompt_obj,
                     agent_name="cloud-processor",
                 )

app/core/deep_agent.py

@@ -16,9 +16,8 @@ from app.agents.note_agent import NOTE_TOOLS
 from app.agents.project_agent import PROJECT_TOOLS
 from app.agents.task_agent import TASK_TOOLS
 from app.agents.timeline_agent import TIMELINE_TOOLS
-from app.core.langfuse_client import extract_usage, get_langfuse, get_prompt_or_fallback
-from app.core.llm import get_llm
-from app.config.settings import settings
+from app.core.langfuse_client import extract_usage, get_langfuse, get_prompt_or_fallback, langfuse_context
+from app.core.llm import get_agent_llm, model_for_agent
 from app.core.memory_middleware import MemoryMiddleware
 from app.core.ws_context import clear_tool_result_collector, execute_on_client, set_tool_result_collector
 from app.db import async_session
@@ -28,6 +27,34 @@ logger = logging.getLogger(__name__)
 FloatingDomainType = Literal["task", "timeline", "project", "node"]
 FloatingDomainSection = Literal["task", "timeline", "note"]
 
+# Mapping of core-memory language values to natural-language names for prompts.
+_LANGUAGE_NAMES: dict[str, str] = {
+    "en": "English", "it": "Italian", "es": "Spanish",
+    "fr": "French", "de": "German",
+    "english": "English", "italian": "Italian", "italiano": "Italian",
+    "spanish": "Spanish", "español": "Spanish",
+    "french": "French", "français": "French",
+    "german": "German", "deutsch": "German",
+}
+
+
+def _language_instruction(context: dict[str, Any]) -> str:
+    """Return a system-prompt suffix that tells the LLM to respond in the user's language.
+
+    Returns an empty string when the language is English or unknown — saves tokens.
+    """
+    core = context.get("core_memory") or {}
+    raw = (core.get("language") or "").strip().lower()
+    if not raw:
+        return ""
+    lang = _LANGUAGE_NAMES.get(raw, raw.title())  # best-effort capitalisation
+    if lang.lower() == "english":
+        return ""
+    return (
+        f"\n\nIMPORTANT: Always respond in {lang}. "
+        f"All your output text must be written in {lang}."
+    )
+
 _HOME_SYSTEM_PROMPT = (
     "You are the home assistant with direct access to all tools: tasks, projects, notes, timelines, and memory tools. "
     "Always use tools for factual data retrieval before answering. "
@@ -149,6 +176,15 @@ def _trace_id_from_context(context: dict[str, Any]) -> str | None:
     return None
 
 
+def _session_id_from_context(context: dict[str, Any]) -> str | None:
+    debug = context.get("_debug")
+    if isinstance(debug, dict):
+        session_id = debug.get("session_id")
+        if isinstance(session_id, str) and session_id:
+            return session_id
+    return None
+
+
 def _context_for_model(context: dict[str, Any]) -> dict[str, Any]:
     sanitized = dict(context)
     sanitized.pop("_debug", None)
@@ -537,7 +573,7 @@ async def _infer_floating_domain(message: str, context: dict[str, Any]) -> dict[
     }
 
     try:
-        llm = get_llm()
+        llm = get_agent_llm("classifier")
         classifier_messages = [
             SystemMessage(content=_FLOATING_DOMAIN_CLASSIFIER_PROMPT),
             HumanMessage(
@@ -551,16 +587,23 @@ async def _infer_floating_domain(message: str, context: dict[str, Any]) -> dict[
         _, classifier_prompt_obj = get_prompt_or_fallback(
             "floating_domain_classifier", _FLOATING_DOMAIN_CLASSIFIER_PROMPT
         )
+
+        # Extract user/session from context for Langfuse attribution
+        _debug = context.get("_debug") if isinstance(context, dict) else None
+        _lf_user = (_debug or {}).get("user_id") if isinstance(_debug, dict) else None
+        _lf_session = (_debug or {}).get("session_id") if isinstance(_debug, dict) else None
+
+        with langfuse_context(user_id=_lf_user, session_id=_lf_session):
             if lf:
                 with lf.start_as_current_observation(
                     as_type="generation",
                     name="floating-classifier",
-                model=settings.LLM_MODEL,
+                    model=model_for_agent("classifier"),
                     prompt=classifier_prompt_obj,
                     input=classifier_messages,
                 ) as gen:
                     response = await llm.ainvoke(classifier_messages)
-                gen.update(output=_as_text(response.content), usage=extract_usage(response))
+                    gen.update(output=_as_text(response.content), usage_details=extract_usage(response))
             else:
                 response = await llm.ainvoke(classifier_messages)
         parsed = _parse_json_object(_as_text(response.content))
@@ -591,8 +634,9 @@ async def _run_single_agent(
     agent_name: str = "agent",
 ) -> str:
     trace_id = _trace_id_from_context(context)
+    session_id = _session_id_from_context(context)
     lf = get_langfuse()
-    llm = get_llm()
+    llm = get_agent_llm(agent_name)
     tools = _all_tools_for_user(user_id, trace_id)
     model_context = _context_for_model(context)
     logger.info("deep_agent: run_single_agent_start trace=%s user=%s", trace_id or "-", user_id)
@@ -611,6 +655,9 @@ async def _run_single_agent(
     collected: list[dict[str, Any]] = []
     set_tool_result_collector(collected)
 
+    _lf_ctx = langfuse_context(user_id=user_id, session_id=session_id)
+    _lf_ctx.__enter__()
+
     _span_ctx = (
         lf.start_as_current_observation(
             as_type="span",
@@ -628,7 +675,7 @@ async def _run_single_agent(
                 lf.start_as_current_observation(
                     as_type="generation",
                     name=f"{agent_name}-llm",
-                    model=settings.LLM_MODEL,
+                    model=model_for_agent(agent_name),
                     prompt=langfuse_prompt,
                     input=messages,
                 )
@@ -637,7 +684,7 @@ async def _run_single_agent(
             _gen = _gen_ctx.__enter__() if _gen_ctx else None
             response: AIMessage = await llm_with_tools.ainvoke(messages)
             if _gen_ctx:
-                _gen.update(output=_as_text(response.content), usage=extract_usage(response))
+                _gen.update(output=_as_text(response.content), usage_details=extract_usage(response))
                 _gen_ctx.__exit__(None, None, None)
 
             messages.append(response)
@@ -699,6 +746,7 @@ async def _run_single_agent(
         clear_tool_result_collector()
         if _span_ctx:
             _span_ctx.__exit__(None, None, None)
+        _lf_ctx.__exit__(None, None, None)
         if lf:
             lf.flush()
 
@@ -714,8 +762,9 @@ async def _run_single_agent_stream(
     agent_name: str = "agent",
 ) -> AsyncGenerator[tuple[str, Any], None]:
     trace_id = _trace_id_from_context(context)
+    session_id = _session_id_from_context(context)
     lf = get_langfuse()
-    llm = get_llm()
+    llm = get_agent_llm(agent_name)
     tools = _all_tools_for_user(user_id, trace_id)
     model_context = _context_for_model(context)
     logger.info("deep_agent: run_single_agent_stream_start trace=%s user=%s", trace_id or "-", user_id)
@@ -735,6 +784,9 @@ async def _run_single_agent_stream(
     collected: list[dict[str, Any]] = []
     set_tool_result_collector(collected)
 
+    _lf_ctx = langfuse_context(user_id=user_id, session_id=session_id)
+    _lf_ctx.__enter__()
+
     _span_ctx = (
         lf.start_as_current_observation(
             as_type="span",
@@ -753,7 +805,7 @@ async def _run_single_agent_stream(
                 lf.start_as_current_observation(
                     as_type="generation",
                     name=f"{agent_name}-llm",
-                    model=settings.LLM_MODEL,
+                    model=model_for_agent(agent_name),
                     prompt=langfuse_prompt,
                     input=messages,
                 )
@@ -762,7 +814,7 @@ async def _run_single_agent_stream(
             _gen = _gen_ctx.__enter__() if _gen_ctx else None
             response: AIMessage = await llm_with_tools.ainvoke(messages)
             if _gen_ctx:
-                _gen.update(output=_as_text(response.content), usage=extract_usage(response))
+                _gen.update(output=_as_text(response.content), usage_details=extract_usage(response))
                 _gen_ctx.__exit__(None, None, None)
 
             messages.append(response)
@@ -842,6 +894,7 @@ async def _run_single_agent_stream(
         clear_tool_result_collector()
         if _span_ctx:
             _span_ctx.__exit__(None, None, None)
+        _lf_ctx.__exit__(None, None, None)
         if lf:
             lf.flush()
 
@@ -851,6 +904,7 @@ async def run_home(user_id: str, message: str, context: dict[str, Any]) -> str:
     system_prompt, langfuse_prompt = get_prompt_or_fallback(
         "home_system", _HOME_SYSTEM_PROMPT
     )
+    system_prompt += _language_instruction(context)
     response = await _run_single_agent(
         user_id=user_id,
         system_prompt=system_prompt,
@@ -868,6 +922,7 @@ async def run_floating(user_id: str, message: str, context: dict[str, Any]) -> t
     system_prompt, langfuse_prompt = get_prompt_or_fallback(
         "floating_system", _FLOATING_SYSTEM_PROMPT
     )
+    system_prompt += _language_instruction(context)
     response = await _run_single_agent(
         user_id=user_id,
         system_prompt=system_prompt,
@@ -891,6 +946,7 @@ async def run_home_stream(
     system_prompt, langfuse_prompt = get_prompt_or_fallback(
         "home_system", _HOME_SYSTEM_PROMPT
     )
+    system_prompt += _language_instruction(context)
     text_chunks: list[str] = []
     async for event in _run_single_agent_stream(
         user_id=user_id,
@@ -923,6 +979,7 @@ async def run_floating_stream(
     system_prompt, langfuse_prompt = get_prompt_or_fallback(
         "floating_system", _FLOATING_SYSTEM_PROMPT
     )
+    system_prompt += _language_instruction(context)
     sanitizer = _FloatingStreamSanitizer()
     emitted_sanitized = False
     raw_chunks: list[str] = []

app/core/langfuse_client.py

@@ -39,8 +39,10 @@ Linking a prompt to a generation::
 
 from __future__ import annotations
 
+import hashlib
 import logging
-from typing import Any
+from contextlib import contextmanager
+from typing import Any, Generator
 
 logger = logging.getLogger(__name__)
 
@@ -67,9 +69,9 @@ def get_langfuse() -> Any | None:
         _client = Langfuse(
             secret_key=settings.LANGFUSE_SECRET_KEY,
             public_key=settings.LANGFUSE_PUBLIC_KEY,
-            host=settings.LANGFUSE_HOST,
+            host=settings.LANGFUSE_BASE_URL,
         )
-        logger.info("langfuse: client initialized host=%s", settings.LANGFUSE_HOST)
+        logger.info("langfuse: client initialized host=%s", settings.LANGFUSE_BASE_URL)
     except Exception as exc:
         logger.warning("langfuse: failed to initialize: %s", exc)
         _client = None
@@ -145,3 +147,44 @@ def extract_usage(response: Any) -> dict[str, int]:
         "output": int(meta.get("output_tokens", 0)),
         "total": int(meta.get("total_tokens", 0)),
     }
+
+
+def hash_user_id(user_id: str) -> str:
+    """Return a SHA-256 hash of *user_id* for use as Langfuse ``user_id``.
+
+    This avoids sending raw database UUIDs to external observability services
+    while still providing a stable, deterministic identifier for per-user
+    metrics in the Langfuse dashboard.
+    """
+    return hashlib.sha256(user_id.encode()).hexdigest()
+
+
+@contextmanager
+def langfuse_context(
+    user_id: str | None = None,
+    session_id: str | None = None,
+) -> Generator[None, None, None]:
+    """Propagate ``user_id`` (hashed) and ``session_id`` to all Langfuse observations.
+
+    No-op when Langfuse is not configured or parameters are empty.
+    """
+    lf = get_langfuse()
+    if lf is None or (not user_id and not session_id):
+        yield
+        return
+
+    try:
+        from langfuse import propagate_attributes
+    except ImportError:
+        logger.debug("langfuse: propagate_attributes not available — skipping context")
+        yield
+        return
+
+    attrs: dict[str, str] = {}
+    if user_id:
+        attrs["user_id"] = hash_user_id(user_id)
+    if session_id:
+        attrs["session_id"] = session_id
+
+    with propagate_attributes(**attrs):
+        yield

app/core/llm.py

@@ -1,6 +1,6 @@
 """LLM factory — centralised model instantiation via LiteLLM.
 
-Every agent and the orchestrator call ``get_llm()`` or ``get_router_llm()``
+Every agent and the orchestrator call ``get_llm()``
 instead of directly constructing a provider-specific class.  The model string
 follows the `LiteLLM model naming convention
 <https://docs.litellm.ai/docs/providers>`_:
@@ -11,7 +11,7 @@ follows the `LiteLLM model naming convention
 * Ollama:     ``ollama/llama3``
 * Bedrock:    ``bedrock/anthropic.claude-v2``
 
-Switch providers by changing **LLM_MODEL** / **LLM_ROUTER_MODEL** in ``.env``
+Switch providers by changing **LLM_MODEL** in ``.env``
 — no code changes required.
 """
 
@@ -19,6 +19,7 @@ from __future__ import annotations
 
 import os
 import warnings
+from collections.abc import Callable
 
 from openai import AsyncOpenAI
 import litellm
@@ -95,12 +96,33 @@ def get_llm(
     )
 
 
-def get_router_llm(
+_AGENT_MODEL_SETTINGS: dict[str, Callable[[], str]] = {
+    "classifier":          lambda: settings.LLM_MODEL_CLASSIFIER or settings.LLM_MODEL,
+    "home-agent":          lambda: settings.LLM_MODEL_HOME_AGENT or settings.LLM_MODEL,
+    "floating-agent":      lambda: settings.LLM_MODEL_FLOATING_AGENT or settings.LLM_MODEL,
+    "unified-processor":   lambda: settings.LLM_MODEL_UNIFIED_PROCESSOR or settings.LLM_MODEL,
+    "cloud-processor":     lambda: settings.LLM_MODEL_CLOUD_PROCESSOR or settings.LLM_MODEL,
+    "setup":               lambda: settings.LLM_MODEL_SETUP_AGENT or settings.LLM_MODEL,
+}
+
+
+def model_for_agent(agent_name: str) -> str:
+    """Return the resolved model string for *agent_name* (for Langfuse tracking)."""
+    return _AGENT_MODEL_SETTINGS.get(agent_name, lambda: settings.LLM_MODEL)()
+
+
+def get_agent_llm(
+    agent_name: str,
     *,
     temperature: float = 0,
 ) -> ChatOpenAI | ChatLiteLLM:
-    """Return the lighter model used for intent classification / routing."""
-    return get_llm(model=settings.LLM_ROUTER_MODEL, temperature=temperature)
+    """Return an LLM configured for *agent_name*, respecting per-agent overrides.
+
+    Falls back to ``settings.LLM_MODEL`` for unknown agent names or when the
+    per-agent override is left empty in ``.env``.
+    """
+    model = model_for_agent(agent_name)
+    return get_llm(model=model, temperature=temperature)
 
 
 async def embed(text: str) -> list[float]:

app/integrations/ms_graph.py

@@ -25,7 +25,7 @@ from __future__ import annotations
 
 import logging
 import re
-from datetime import datetime, timedelta, timezone
+from datetime import datetime, timezone
 from typing import Any
 
 import httpx

app/main.py

@@ -30,7 +30,7 @@ async def lifespan(app: FastAPI):
 
 def create_app() -> FastAPI:
     app = FastAPI(
-        title="Adiuva Cloud API",
+        title="AdiuvAI Cloud API",
         version="0.1.0",
         docs_url="/docs" if settings.ENV == "dev" else None,
         redoc_url=None,
@@ -50,14 +50,10 @@ def create_app() -> FastAPI:
     app.add_middleware(SanitizerMiddleware)
     app.add_middleware(TierRateLimitMiddleware)
 
-    from app.api.routes import agents, auth, backup, billing, chat, device_ws, plugins, storage, vectors
+    from app.api.routes import agents, auth, billing, chat, device_ws
 
     app.include_router(auth.router,       prefix="/api/v1")
     app.include_router(chat.router,       prefix="/api/v1")
-    app.include_router(storage.router,    prefix="/api/v1")
-    app.include_router(vectors.router,    prefix="/api/v1")
-    app.include_router(backup.router,     prefix="/api/v1")
-    app.include_router(plugins.router,    prefix="/api/v1")
     app.include_router(billing.router,    prefix="/api/v1")
     app.include_router(agents.router,     prefix="/api/v1")
     app.include_router(device_ws.router,  prefix="/api/v1")

app/marketplace/__init__.py

@@ -1,7 +0,0 @@
-"""Plugin marketplace package.
-
-Three service classes introduced in Step 10:
-  - ``PluginRegistry``  — catalog, submit/approve/reject, install counts
-  - ``ReviewQueue``     — approval workflow + security checklist
-  - ``RevenueShare``    — 70/30 split tracking and Stripe Connect payouts
-"""

app/marketplace/plugin_registry.py

@@ -1,212 +0,0 @@
-"""Plugin catalog registry backed by PostgreSQL.
-
-Maintains the authoritative list of plugins, their review status, and
-aggregate install counts.  All data is persisted in the ``plugins`` table.
-
-Module-level singleton::
-
-    from app.marketplace.plugin_registry import registry
-"""
-
-from __future__ import annotations
-
-import json
-from typing import Any, Literal
-
-from sqlalchemy import select, func
-from sqlalchemy.ext.asyncio import AsyncSession
-
-from app.models import Plugin
-from app.schemas import PluginListResponse, PluginManifest
-
-_PAGE_SIZE = 20
-
-
-def _plugin_to_manifest(p: Plugin) -> PluginManifest:
-    """Convert an ORM ``Plugin`` row to a Pydantic ``PluginManifest``."""
-    try:
-        permissions = json.loads(p.permissions) if p.permissions else []
-    except (json.JSONDecodeError, TypeError):
-        permissions = []
-    return PluginManifest(
-        id=p.id,
-        name=p.name,
-        description=p.description,
-        version=p.version,
-        author=p.author_name,
-        permissions=permissions,
-        category=p.category,
-        price_cents=p.price_cents,
-    )
-
-
-class PluginRegistry:
-    """PostgreSQL-backed plugin catalog.
-
-    All methods accept an ``AsyncSession`` parameter so the calling route
-    controls the session lifecycle.
-    """
-
-    # ── Queries ──────────────────────────────────────────────────────
-
-    async def list_plugins(
-        self,
-        db: AsyncSession,
-        category: str | None = None,
-        query: str | None = None,
-        page: int = 1,
-        sort: Literal["rating", "installs", "newest"] = "newest",
-    ) -> PluginListResponse:
-        """Return a page of approved plugins, optionally filtered and sorted."""
-        base = select(Plugin).where(Plugin.status == "approved")
-
-        if category:
-            base = base.where(Plugin.category == category)
-        if query:
-            pattern = f"%{query}%"
-            base = base.where(
-                Plugin.name.ilike(pattern) | Plugin.description.ilike(pattern)
-            )
-
-        # Count
-        count_q = select(func.count()).select_from(base.subquery())
-        total = (await db.execute(count_q)).scalar_one()
-
-        # Sort
-        if sort == "installs":
-            base = base.order_by(Plugin.install_count.desc())
-        elif sort == "rating":
-            base = base.order_by(Plugin.avg_rating.desc())
-        else:  # newest
-            base = base.order_by(Plugin.created_at.desc())
-
-        base = base.offset((page - 1) * _PAGE_SIZE).limit(_PAGE_SIZE)
-        rows = (await db.execute(base)).scalars().all()
-
-        return PluginListResponse(
-            plugins=[_plugin_to_manifest(r) for r in rows],
-            total=total,
-            page=page,
-        )
-
-    async def get_plugin(self, db: AsyncSession, plugin_id: str) -> dict[str, Any] | None:
-        """Return ``{manifest, status, install_count, avg_rating}`` or ``None``."""
-        result = await db.execute(select(Plugin).where(Plugin.id == plugin_id))
-        p = result.scalar_one_or_none()
-        if p is None:
-            return None
-        return {
-            "manifest": _plugin_to_manifest(p),
-            "status": p.status,
-            "install_count": p.install_count,
-            "avg_rating": p.avg_rating,
-        }
-
-    # ── Mutations ────────────────────────────────────────────────────
-
-    async def submit_plugin(
-        self,
-        db: AsyncSession,
-        manifest: PluginManifest,
-        package_s3_key: str,
-    ) -> str:
-        """Add *manifest* to the catalog with ``status='pending_review'``.
-
-        Returns the plugin_id.  If a plugin with the same id already exists
-        it is overwritten (re-submission after rejection).
-        """
-        plugin_id = manifest.id
-        existing = await db.execute(select(Plugin).where(Plugin.id == plugin_id))
-        row = existing.scalar_one_or_none()
-
-        if row is not None:
-            row.name = manifest.name
-            row.description = manifest.description
-            row.version = manifest.version
-            row.author_name = manifest.author
-            row.category = manifest.category
-            row.price_cents = manifest.price_cents
-            row.permissions = json.dumps(manifest.permissions)
-            row.status = "pending_review"
-            row.s3_package_key = package_s3_key
-            row.rejection_reason = None
-        else:
-            row = Plugin(
-                id=plugin_id,
-                name=manifest.name,
-                description=manifest.description,
-                version=manifest.version,
-                author_name=manifest.author,
-                category=manifest.category,
-                price_cents=manifest.price_cents,
-                permissions=json.dumps(manifest.permissions),
-                status="pending_review",
-                s3_package_key=package_s3_key,
-                install_count=0,
-                avg_rating=0.0,
-            )
-            db.add(row)
-        await db.commit()
-        return plugin_id
-
-    async def approve_plugin(self, db: AsyncSession, plugin_id: str) -> None:
-        """Set *plugin_id* status to ``'approved'``.
-
-        Raises ``KeyError`` if the plugin is not found.
-        """
-        result = await db.execute(select(Plugin).where(Plugin.id == plugin_id))
-        row = result.scalar_one_or_none()
-        if row is None:
-            raise KeyError(f"Plugin not found: {plugin_id}")
-        row.status = "approved"
-        row.rejection_reason = None
-        await db.commit()
-
-    async def reject_plugin(self, db: AsyncSession, plugin_id: str, reason: str) -> None:
-        """Set *plugin_id* status to ``'rejected'`` and record the reason.
-
-        Raises ``KeyError`` if the plugin is not found.
-        """
-        result = await db.execute(select(Plugin).where(Plugin.id == plugin_id))
-        row = result.scalar_one_or_none()
-        if row is None:
-            raise KeyError(f"Plugin not found: {plugin_id}")
-        row.status = "rejected"
-        row.rejection_reason = reason
-        await db.commit()
-
-    async def record_install(self, db: AsyncSession, plugin_id: str) -> None:
-        """Increment the install count for *plugin_id* (no-op if not found)."""
-        result = await db.execute(select(Plugin).where(Plugin.id == plugin_id))
-        row = result.scalar_one_or_none()
-        if row is not None:
-            row.install_count = row.install_count + 1
-            await db.commit()
-
-    async def record_uninstall(self, db: AsyncSession, plugin_id: str) -> None:
-        """Decrement the install count for *plugin_id*, floored at 0."""
-        result = await db.execute(select(Plugin).where(Plugin.id == plugin_id))
-        row = result.scalar_one_or_none()
-        if row is not None:
-            row.install_count = max(0, row.install_count - 1)
-            await db.commit()
-
-    # ── Internal helpers used by ReviewQueue ─────────────────────────
-
-    async def get_pending_entries(self, db: AsyncSession) -> list[dict[str, Any]]:
-        """Return all entries with status='pending_review'."""
-        result = await db.execute(
-            select(Plugin).where(Plugin.status == "pending_review")
-        )
-        rows = result.scalars().all()
-        return [
-            {
-                "manifest": _plugin_to_manifest(r),
-                "submitted_at": int(r.submitted_at.timestamp()) if r.submitted_at else 0,
-            }
-            for r in rows
-        ]
-
-
-# Module-level singleton
-registry = PluginRegistry()

app/marketplace/plugin_review.py

@@ -1,125 +0,0 @@
-"""Plugin review workflow backed by PostgreSQL.
-
-Manages the approval queue for newly submitted plugins and enforces a
-security checklist before any plugin is made visible in the marketplace.
-
-Module-level singleton::
-
-    from app.marketplace.plugin_review import review_queue
-"""
-
-from __future__ import annotations
-
-import re
-from typing import Any, Literal
-
-from sqlalchemy.ext.asyncio import AsyncSession
-
-from app.marketplace.plugin_registry import registry
-from app.models import PluginReview as PluginReviewModel
-from app.schemas import PluginManifest
-
-# ── Security policy ───────────────────────────────────────────────────
-
-ALLOWED_PERMISSIONS: frozenset[str] = frozenset(
-    {
-        "read:tasks",
-        "write:tasks",
-        "read:projects",
-        "write:projects",
-        "read:notes",
-        "write:notes",
-        "read:timelines",
-        "write:timelines",
-        "read:calendar",
-        "write:calendar",
-    }
-)
-
-_PLUGIN_ID_RE = re.compile(r"^[a-z0-9-]+$")
-
-
-def validate_manifest(manifest: PluginManifest) -> None:
-    """Enforce the plugin security checklist.
-
-    Raises:
-        ``ValueError`` on the first violation found.  Callers should catch
-        this and return HTTP 422 / reject the submission.
-
-    Checks:
-      1. Plugin id matches ``^[a-z0-9-]+$``
-      2. All declared permissions are in ``ALLOWED_PERMISSIONS``
-      3. No manifest field contains raw binary data
-    """
-    if not _PLUGIN_ID_RE.match(manifest.id):
-        raise ValueError(
-            f"Invalid plugin id format: '{manifest.id}'. "
-            "Only lowercase letters, digits, and hyphens are allowed."
-        )
-
-    for perm in manifest.permissions:
-        if perm not in ALLOWED_PERMISSIONS:
-            raise ValueError(
-                f"Unknown permission: '{perm}'. "
-                f"Allowed permissions: {sorted(ALLOWED_PERMISSIONS)}"
-            )
-
-    for field_name, value in manifest.model_dump().items():
-        if isinstance(value, (bytes, bytearray)):
-            raise ValueError(
-                f"Binary content is not allowed in manifest field '{field_name}'."
-            )
-
-
-class ReviewQueue:
-    """Approval queue for pending plugin submissions.
-
-    Delegates status changes to the shared ``PluginRegistry`` singleton.
-    Review records are persisted in the ``plugin_reviews`` table.
-    """
-
-    async def get_pending(self, db: AsyncSession) -> list[dict[str, Any]]:
-        """Return all plugins currently awaiting review.
-
-        Each item is ``{plugin_id, manifest, submitted_at}``.
-        """
-        entries = await registry.get_pending_entries(db)
-        return [
-            {
-                "plugin_id": e["manifest"].id,
-                "manifest": e["manifest"],
-                "submitted_at": e["submitted_at"],
-            }
-            for e in entries
-        ]
-
-    async def submit_review(
-        self,
-        db: AsyncSession,
-        plugin_id: str,
-        reviewer_id: str,
-        decision: Literal["approved", "rejected"],
-        notes: str = "",
-    ) -> None:
-        """Record a review decision and update the plugin's status.
-
-        Raises:
-            ``KeyError`` if *plugin_id* is not found in the registry.
-        """
-        if decision == "approved":
-            await registry.approve_plugin(db, plugin_id)
-        else:
-            await registry.reject_plugin(db, plugin_id, reason=notes)
-
-        review = PluginReviewModel(
-            plugin_id=plugin_id,
-            reviewer_id=reviewer_id,
-            decision=decision,
-            notes=notes,
-        )
-        db.add(review)
-        await db.commit()
-
-
-# Module-level singleton
-review_queue = ReviewQueue()

app/marketplace/revenue_share.py

@@ -1,233 +0,0 @@
-"""Revenue share tracking and Stripe Connect payouts backed by PostgreSQL.
-
-Records every plugin installation as a revenue event and facilitates
-70 % / 30 % payouts to developers via Stripe Connect.  Data is persisted
-in the ``revenue_events`` table.
-
-Module-level singleton::
-
-    from app.marketplace.revenue_share import revenue_share
-"""
-
-from __future__ import annotations
-
-import logging
-from datetime import datetime, timezone
-from typing import Any
-
-import stripe as stripe_lib
-from sqlalchemy import extract, func, select
-from sqlalchemy.ext.asyncio import AsyncSession
-
-from app.config.settings import settings
-from app.marketplace.plugin_registry import registry
-from app.models import Plugin, RevenueEvent
-
-logger = logging.getLogger(__name__)
-
-# ── Revenue split constants ───────────────────────────────────────────
-
-DEVELOPER_SHARE: float = 0.70
-PLATFORM_SHARE: float = 0.30
-
-
-class RevenueShare:
-    """Records installation revenue events and coordinates developer payouts.
-
-    Stripe Connect calls are gracefully stubbed when ``STRIPE_SECRET_KEY``
-    is not configured, consistent with the rest of the billing layer.
-    """
-
-    # ── Helpers ──────────────────────────────────────────────────────
-
-    @staticmethod
-    def _stripe_configured() -> bool:
-        return bool(settings.STRIPE_SECRET_KEY)
-
-    @staticmethod
-    def _stripe() -> Any:
-        stripe_lib.api_key = settings.STRIPE_SECRET_KEY
-        return stripe_lib
-
-    # ── Core operations ──────────────────────────────────────────────
-
-    async def record_install(
-        self,
-        db: AsyncSession,
-        plugin_id: str,
-        user_id: str,
-        amount_cents: int,
-    ) -> None:
-        """Record a plugin installation and trigger a Stripe Connect charge if paid.
-
-        For free plugins (``amount_cents == 0``) no payment is initiated but
-        the event is still recorded for analytics.
-
-        For paid plugins the developer receives 70 % via a Stripe Connect
-        destination charge.  If Stripe is not configured or the charge fails
-        the installation still succeeds (the event is recorded and the install
-        count is incremented) — a warning is logged for monitoring.
-        """
-        developer_share_cents = int(amount_cents * DEVELOPER_SHARE)
-        stripe_transfer_id: str | None = None
-
-        if amount_cents > 0 and self._stripe_configured():
-            # Look up the plugin's author Stripe account from the DB
-            result = await db.execute(select(Plugin).where(Plugin.id == plugin_id))
-            plugin_row = result.scalar_one_or_none()
-            developer_stripe_account: str | None = None
-            if plugin_row and plugin_row.author_id:
-                # Future: look up user.stripe_connect_account_id
-                developer_stripe_account = None  # no real account yet
-
-            if developer_stripe_account:
-                try:
-                    s = self._stripe()
-                    transfer = s.Transfer.create(
-                        amount=developer_share_cents,
-                        currency="eur",
-                        destination=developer_stripe_account,
-                        description=f"Revenue share for plugin {plugin_id}",
-                        metadata={"plugin_id": plugin_id, "user_id": user_id},
-                    )
-                    stripe_transfer_id = transfer["id"]
-                except Exception as exc:
-                    logger.warning(
-                        "Stripe Connect transfer failed for plugin %s: %s",
-                        plugin_id,
-                        exc,
-                    )
-            else:
-                logger.debug(
-                    "No Stripe account on file for plugin %s developer; "
-                    "skipping transfer.",
-                    plugin_id,
-                )
-
-        event = RevenueEvent(
-            plugin_id=plugin_id,
-            user_id=user_id,
-            amount_cents=amount_cents,
-            developer_share_cents=developer_share_cents,
-            stripe_transfer_id=stripe_transfer_id,
-        )
-        db.add(event)
-        await db.commit()
-
-        await registry.record_install(db, plugin_id)
-
-    async def get_earnings(
-        self,
-        db: AsyncSession,
-        developer_id: str,
-        period: str | None = None,
-    ) -> dict[str, Any]:
-        """Return aggregated earnings for *developer_id*.
-
-        ``period`` is an optional ``YYYY-MM`` string to restrict the window.
-
-        Returns::
-
-            {
-                "developer_id": str,
-                "period": str | None,
-                "total_installs": int,
-                "total_revenue_cents": int,
-                "developer_share_cents": int,
-            }
-        """
-        # Find plugin ids belonging to this developer (by author_name match)
-        plugin_q = select(Plugin.id).where(Plugin.author_name == developer_id)
-        plugin_result = await db.execute(plugin_q)
-        developer_plugin_ids = [row[0] for row in plugin_result.all()]
-
-        if not developer_plugin_ids:
-            return {
-                "developer_id": developer_id,
-                "period": period,
-                "total_installs": 0,
-                "total_revenue_cents": 0,
-                "developer_share_cents": 0,
-            }
-
-        query = select(
-            func.count().label("total_installs"),
-            func.coalesce(func.sum(RevenueEvent.amount_cents), 0).label("total_revenue"),
-            func.coalesce(func.sum(RevenueEvent.developer_share_cents), 0).label("dev_share"),
-        ).where(RevenueEvent.plugin_id.in_(developer_plugin_ids))
-
-        if period:
-            # Filter by YYYY-MM: extract year and month from created_at
-            try:
-                year, month = period.split("-")
-                query = query.where(
-                    extract("year", RevenueEvent.created_at) == int(year),
-                    extract("month", RevenueEvent.created_at) == int(month),
-                )
-            except ValueError:
-                pass  # invalid period format — return all
-
-        result = await db.execute(query)
-        row = result.one()
-
-        return {
-            "developer_id": developer_id,
-            "period": period,
-            "total_installs": row.total_installs,
-            "total_revenue_cents": row.total_revenue,
-            "developer_share_cents": row.dev_share,
-        }
-
-    async def payout_developer(self, db: AsyncSession, plugin_id: str, period: str) -> None:
-        """Aggregate unpaid revenue for *period* and issue a Stripe Transfer.
-
-        Marks processed events with ``paid_at`` timestamp.
-        Stubs gracefully when Stripe is not configured.
-        """
-        try:
-            year, month = period.split("-")
-            year_int, month_int = int(year), int(month)
-        except ValueError:
-            logger.warning("Invalid period format: %s", period)
-            return
-
-        result = await db.execute(
-            select(RevenueEvent).where(
-                RevenueEvent.plugin_id == plugin_id,
-                RevenueEvent.paid_at.is_(None),
-                extract("year", RevenueEvent.created_at) == year_int,
-                extract("month", RevenueEvent.created_at) == month_int,
-            )
-        )
-        unpaid = list(result.scalars().all())
-
-        total_dev_share = sum(e.developer_share_cents for e in unpaid)
-        if total_dev_share <= 0 or not unpaid:
-            logger.debug("Nothing to pay out for plugin %s in period %s", plugin_id, period)
-            return
-
-        if self._stripe_configured():
-            plugin_result = await db.execute(select(Plugin).where(Plugin.id == plugin_id))
-            plugin_row = plugin_result.scalar_one_or_none()
-            developer_stripe_account: str | None = None  # Future: fetch from DB
-            if plugin_row and developer_stripe_account:
-                try:
-                    s = self._stripe()
-                    s.Transfer.create(
-                        amount=total_dev_share,
-                        currency="eur",
-                        destination=developer_stripe_account,
-                        description=f"Payout for plugin {plugin_id} period {period}",
-                    )
-                except Exception as exc:
-                    logger.warning("Payout transfer failed for plugin %s: %s", plugin_id, exc)
-                    return
-
-        paid_ts = datetime.now(timezone.utc)
-        for event in unpaid:
-            event.paid_at = paid_ts
-        await db.commit()
-
-
-# Module-level singleton
-revenue_share = RevenueShare()

app/models.py

@@ -1,19 +1,15 @@
 """SQLAlchemy ORM models for all persistent tables.
 
-Only auth, billing, storage metadata, and marketplace data live here.
-User content (notes, tasks, etc.) is NEVER persisted server-side —
-it lives in E2E-encrypted blobs in S3, referenced by storage_records.
+Only auth, billing, agent config, and memory data live here.
+User content (notes, tasks, etc.) lives exclusively on the client.
 
 Table inventory:
   users               — account credentials + tier
   refresh_tokens      — hashed refresh token store
   subscriptions       — Stripe subscription records
-  storage_records     — S3 blob metadata (no plaintext)
-  backup_metadata     — encrypted backup manifests
-  plugins             — marketplace plugin catalog
-  plugin_installations — per-user install records
-  plugin_reviews      — admin review decisions
-  revenue_events      — Stripe Connect 70/30 split ledger
+  local_agent_configs — per-device batch agent configs
+  cloud_agent_configs — OAuth-backed cloud agent configs
+  agent_run_logs      — execution history for all agents
   memory_core         — per-user persistent key/value preferences (encrypted)
   memory_associative  — per-user semantic memory with embeddings (encrypted)
   memory_episodic     — per-user session summaries (encrypted)
@@ -26,7 +22,6 @@ import uuid
 from datetime import datetime, timezone
 
 from sqlalchemy import (
-    BigInteger,
     Boolean,
     DateTime,
     Enum,
@@ -36,7 +31,6 @@ from sqlalchemy import (
     JSON,
     String,
     Text,
-    UniqueConstraint,
     Uuid,
     func,
 )
@@ -58,8 +52,6 @@ def _now() -> datetime:
 # ── Enum types ────────────────────────────────────────────────────────────
 
 TierEnum = Enum("free", "pro", "power", "team", name="billing_tier")
-PluginStatusEnum = Enum("pending_review", "approved", "rejected", name="plugin_status")
-ReviewDecisionEnum = Enum("approved", "rejected", name="review_decision")
 AgentTypeEnum = Enum("local", "cloud", name="agent_type")
 AgentStatusEnum = Enum("running", "success", "error", "partial", name="agent_run_status")
 CloudProviderEnum = Enum("gmail", "teams", "outlook", name="cloud_provider")
@@ -77,7 +69,8 @@ class User(Base):
     email: Mapped[str] = mapped_column(String(255), unique=True, nullable=False, index=True)
     name: Mapped[str | None] = mapped_column(String(100), nullable=True)
     surname: Mapped[str | None] = mapped_column(String(100), nullable=True)
-    password_hash: Mapped[str] = mapped_column(String(255), nullable=False)
+    password_hash: Mapped[str | None] = mapped_column(String(255), nullable=True)
+    avatar_url: Mapped[str | None] = mapped_column(Text, nullable=True)
     tier: Mapped[str] = mapped_column(TierEnum, nullable=False, default="free")
     stripe_customer_id: Mapped[str | None] = mapped_column(String(255), nullable=True)
     # Per-user Fernet key (base64-urlsafe, 44 chars). Generated on registration.
@@ -86,6 +79,9 @@ class User(Base):
     created_at: Mapped[datetime] = mapped_column(
         DateTime(timezone=True), nullable=False, server_default=func.now()
     )
+    onboarding_completed_at: Mapped[datetime | None] = mapped_column(
+        DateTime(timezone=True), nullable=True, default=None
+    )
     updated_at: Mapped[datetime] = mapped_column(
         DateTime(timezone=True), nullable=False, server_default=func.now(), onupdate=func.now()
     )
@@ -96,6 +92,9 @@ class User(Base):
     subscription: Mapped[Subscription | None] = relationship(
         back_populates="user", uselist=False, cascade="all, delete-orphan"
     )
+    oauth_accounts: Mapped[list[OAuthAccount]] = relationship(
+        back_populates="user", cascade="all, delete-orphan"
+    )
 
 
 class RefreshToken(Base):
@@ -116,6 +115,25 @@ class RefreshToken(Base):
     user: Mapped[User] = relationship(back_populates="refresh_tokens")
 
 
+class OAuthAccount(Base):
+    __tablename__ = "oauth_accounts"
+
+    id: Mapped[str] = mapped_column(
+        Uuid(as_uuid=False), primary_key=True, default=_uuid
+    )
+    user_id: Mapped[str] = mapped_column(
+        Uuid(as_uuid=False), ForeignKey("users.id", ondelete="CASCADE"), nullable=False, index=True
+    )
+    provider: Mapped[str] = mapped_column(String(50), nullable=False)
+    provider_user_id: Mapped[str] = mapped_column(String(255), nullable=False)
+    provider_email: Mapped[str | None] = mapped_column(String(255), nullable=True)
+    created_at: Mapped[datetime] = mapped_column(
+        DateTime(timezone=True), nullable=False, server_default=func.now()
+    )
+
+    user: Mapped[User] = relationship(back_populates="oauth_accounts")
+
+
 class Subscription(Base):
     __tablename__ = "subscriptions"
 
@@ -137,151 +155,6 @@ class Subscription(Base):
     user: Mapped[User] = relationship(back_populates="subscription")
 
 
-class StorageRecord(Base):
-    __tablename__ = "storage_records"
-
-    id: Mapped[str] = mapped_column(
-        Uuid(as_uuid=False), primary_key=True, default=_uuid
-    )
-    user_id: Mapped[str] = mapped_column(
-        Uuid(as_uuid=False), ForeignKey("users.id", ondelete="CASCADE"), nullable=False, index=True
-    )
-    table_name: Mapped[str] = mapped_column(String(100), nullable=False)
-    s3_key: Mapped[str] = mapped_column(String(500), nullable=False)
-    checksum: Mapped[str] = mapped_column(String(64), nullable=False)
-    size_bytes: Mapped[int] = mapped_column(Integer, nullable=False)
-    created_at: Mapped[datetime] = mapped_column(
-        DateTime(timezone=True), nullable=False, server_default=func.now()
-    )
-    updated_at: Mapped[datetime] = mapped_column(
-        DateTime(timezone=True), nullable=False, server_default=func.now(), onupdate=func.now()
-    )
-
-
-class BackupMetadata(Base):
-    __tablename__ = "backup_metadata"
-
-    id: Mapped[str] = mapped_column(
-        Uuid(as_uuid=False), primary_key=True, default=_uuid
-    )
-    user_id: Mapped[str] = mapped_column(
-        Uuid(as_uuid=False), ForeignKey("users.id", ondelete="CASCADE"), nullable=False, index=True
-    )
-    s3_key: Mapped[str] = mapped_column(String(500), nullable=False)
-    version: Mapped[int] = mapped_column(Integer, nullable=False)
-    timestamp: Mapped[int] = mapped_column(BigInteger, nullable=False)
-    checksum: Mapped[str] = mapped_column(String(64), nullable=False)
-    size_bytes: Mapped[int] = mapped_column(Integer, nullable=False)
-    created_at: Mapped[datetime] = mapped_column(
-        DateTime(timezone=True), nullable=False, server_default=func.now()
-    )
-
-
-class Plugin(Base):
-    __tablename__ = "plugins"
-
-    id: Mapped[str] = mapped_column(String(255), primary_key=True)
-    name: Mapped[str] = mapped_column(String(255), nullable=False)
-    description: Mapped[str] = mapped_column(Text, nullable=False, default="")
-    version: Mapped[str] = mapped_column(String(50), nullable=False, default="1.0.0")
-    # nullable until developer account system is built
-    author_id: Mapped[str | None] = mapped_column(
-        Uuid(as_uuid=False), ForeignKey("users.id", ondelete="SET NULL"), nullable=True
-    )
-    author_name: Mapped[str] = mapped_column(String(255), nullable=False, default="")
-    category: Mapped[str] = mapped_column(String(100), nullable=False, default="")
-    price_cents: Mapped[int] = mapped_column(Integer, nullable=False, default=0)
-    permissions: Mapped[str] = mapped_column(Text, nullable=False, default="[]")  # JSON list
-    status: Mapped[str] = mapped_column(PluginStatusEnum, nullable=False, default="pending_review")
-    s3_package_key: Mapped[str | None] = mapped_column(String(500), nullable=True)
-    install_count: Mapped[int] = mapped_column(Integer, nullable=False, default=0)
-    avg_rating: Mapped[float] = mapped_column(Float, nullable=False, default=0.0)
-    rejection_reason: Mapped[str | None] = mapped_column(Text, nullable=True)
-    submitted_at: Mapped[datetime] = mapped_column(
-        DateTime(timezone=True), nullable=False, server_default=func.now()
-    )
-    created_at: Mapped[datetime] = mapped_column(
-        DateTime(timezone=True), nullable=False, server_default=func.now()
-    )
-
-    installations: Mapped[list[PluginInstallation]] = relationship(
-        back_populates="plugin", cascade="all, delete-orphan"
-    )
-    reviews: Mapped[list[PluginReview]] = relationship(
-        back_populates="plugin", cascade="all, delete-orphan"
-    )
-    revenue_events: Mapped[list[RevenueEvent]] = relationship(
-        back_populates="plugin", cascade="all, delete-orphan"
-    )
-
-
-class PluginInstallation(Base):
-    __tablename__ = "plugin_installations"
-    __table_args__ = (UniqueConstraint("plugin_id", "user_id", name="uq_plugin_user"),)
-
-    id: Mapped[str] = mapped_column(
-        Uuid(as_uuid=False), primary_key=True, default=_uuid
-    )
-    plugin_id: Mapped[str] = mapped_column(
-        String(255), ForeignKey("plugins.id", ondelete="CASCADE"), nullable=False, index=True
-    )
-    user_id: Mapped[str] = mapped_column(
-        Uuid(as_uuid=False), ForeignKey("users.id", ondelete="CASCADE"), nullable=False, index=True
-    )
-    installed_at: Mapped[datetime] = mapped_column(
-        DateTime(timezone=True), nullable=False, server_default=func.now()
-    )
-
-    plugin: Mapped[Plugin] = relationship(back_populates="installations")
-
-
-class PluginReview(Base):
-    __tablename__ = "plugin_reviews"
-
-    id: Mapped[str] = mapped_column(
-        Uuid(as_uuid=False), primary_key=True, default=_uuid
-    )
-    plugin_id: Mapped[str] = mapped_column(
-        String(255), ForeignKey("plugins.id", ondelete="CASCADE"), nullable=False, index=True
-    )
-    reviewer_id: Mapped[str | None] = mapped_column(
-        Uuid(as_uuid=False), ForeignKey("users.id", ondelete="SET NULL"), nullable=True
-    )
-    decision: Mapped[str] = mapped_column(ReviewDecisionEnum, nullable=False)
-    notes: Mapped[str | None] = mapped_column(Text, nullable=True)
-    reviewed_at: Mapped[datetime] = mapped_column(
-        DateTime(timezone=True), nullable=False, server_default=func.now()
-    )
-    created_at: Mapped[datetime] = mapped_column(
-        DateTime(timezone=True), nullable=False, server_default=func.now()
-    )
-
-    plugin: Mapped[Plugin] = relationship(back_populates="reviews")
-
-
-class RevenueEvent(Base):
-    __tablename__ = "revenue_events"
-
-    id: Mapped[str] = mapped_column(
-        Uuid(as_uuid=False), primary_key=True, default=_uuid
-    )
-    plugin_id: Mapped[str] = mapped_column(
-        String(255), ForeignKey("plugins.id", ondelete="CASCADE"), nullable=False, index=True
-    )
-    user_id: Mapped[str] = mapped_column(
-        Uuid(as_uuid=False), ForeignKey("users.id", ondelete="CASCADE"), nullable=False, index=True
-    )
-    amount_cents: Mapped[int] = mapped_column(Integer, nullable=False, default=0)
-    developer_share_cents: Mapped[int] = mapped_column(Integer, nullable=False, default=0)
-    stripe_transfer_id: Mapped[str | None] = mapped_column(String(255), nullable=True)
-    paid_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True), nullable=True)
-    created_at: Mapped[datetime] = mapped_column(
-        DateTime(timezone=True), nullable=False, server_default=func.now()
-    )
-
-    plugin: Mapped[Plugin] = relationship(back_populates="revenue_events")
-
-
 class LocalAgentConfig(Base):
     __tablename__ = "local_agent_configs"
 

app/schemas.py

@@ -30,6 +30,16 @@ class UserProfile(BaseModel):
     name: str | None = None
     surname: str | None = None
     tier: BillingTier
+    avatar_url: str | None = None
+    has_password: bool = True
+    onboarding_completed_at: int | None = None  # epoch ms, null = not onboarded
+    memory: dict[str, str] = Field(default_factory=dict)  # decrypted core memory k/v
+
+
+class OAuthAccountInfo(BaseModel):
+    provider: str
+    provider_email: str | None = None
+    created_at: int  # epoch ms
 
 
 # ── Chat ─────────────────────────────────────────────────────────────
@@ -50,88 +60,6 @@ class ChatResponse(BaseModel):
     response: str
 
 
-# ── Backup ───────────────────────────────────────────────────────────
-
-class BackupMetadata(BaseModel):
-    version: int
-    timestamp: int
-    checksum: str
-    chunk_count: int
-
-
-# ── Cloud Storage (E2E encrypted blobs) ──────────────────────────────
-
-class StorageRecord(BaseModel):
-    id: str
-    user_id: str
-    table: str
-    blob: bytes
-    checksum: str
-    created_at: int
-    updated_at: int
-
-
-class StorageRecordCreate(BaseModel):
-    table: str
-    blob: bytes
-    checksum: str
-
-
-class StorageRecordUpdate(BaseModel):
-    blob: bytes
-    checksum: str
-
-
-# ── Cloud Vector Store (E2E encrypted vectors) ────────────────────────
-
-class VectorItem(BaseModel):
-    id: str
-    blob: bytes   # encrypted vector + metadata — backend never decrypts
-    checksum: str
-
-
-class VectorUpsertRequest(BaseModel):
-    vectors: list[VectorItem]
-
-
-class VectorSearchRequest(BaseModel):
-    query_blob: bytes   # encrypted query — backend never decrypts
-    top_k: int = 10
-
-
-class VectorSearchResult(BaseModel):
-    id: str
-    score: float
-    blob: bytes
-
-
-class VectorSearchResponse(BaseModel):
-    results: list[VectorSearchResult]
-
-
-# ── Plugin Marketplace ────────────────────────────────────────────────
-
-class PluginManifest(BaseModel):
-    id: str
-    name: str
-    description: str
-    version: str
-    author: str
-    permissions: list[str]
-    category: str
-    price_cents: int = 0
-
-
-class PluginListResponse(BaseModel):
-    plugins: list[PluginManifest]
-    total: int
-    page: int
-
-
-class PluginInstallRequest(BaseModel):
-    plugin_id: str
-
-
 # ── WebSocket Frame Protocol ──────────────────────────────────────────
 
 class WsFrameType(str, Enum):
@@ -318,10 +246,11 @@ class AgentTriggerRequest(BaseModel):
     device_id: str = Field(default="")
     agent_id: str | None = None  # FE stable agent ID (electron-store UUID)
     what_to_extract: list[str] = Field(min_length=1)
-    actions_by_type: dict[str, list[str]] | None = None
     batch_interval: str = Field(min_length=1)
-    custom_agent_prompt: str = Field(min_length=1)
+    custom_agent_prompt: str | None = None
+    agent_config: dict | None = None
     active_agents: int = Field(ge=0, default=0)
+    last_run_at: int | None = None  # epoch ms from FE — enables incremental scanning
 
 
 # ── Agent Run Log ─────────────────────────────────────────────────────

app/storage/__init__.py

@@ -1 +0,0 @@
-"""Cloud storage layer — E2E encrypted blobs and vectors."""

app/storage/blob_store.py

@@ -1,106 +0,0 @@
-"""S3-backed store for E2E-encrypted blobs.
-
-Keys are structured as ``{user_id}/{table}/{record_id}``.
-The backend never inspects blob content — it stores and retrieves opaque bytes.
-"""
-
-from __future__ import annotations
-
-from typing import Any
-
-import boto3
-
-from app.config.settings import settings
-
-
-class BlobStore:
-    """Thin wrapper around boto3 S3.
-
-    All blobs must be E2E encrypted by the client before upload.
-    The backend adds SSE-S3 as an extra layer of at-rest encryption
-    but cannot decrypt the inner client-side payload.
-    """
-
-    def _client(self) -> Any:
-        kwargs: dict[str, Any] = {
-            "region_name": settings.S3_REGION,
-            "aws_access_key_id": settings.AWS_ACCESS_KEY_ID,
-            "aws_secret_access_key": settings.AWS_SECRET_ACCESS_KEY,
-        }
-        if settings.S3_ENDPOINT_URL and isinstance(settings.S3_ENDPOINT_URL, str):
-            kwargs["endpoint_url"] = settings.S3_ENDPOINT_URL
-        return boto3.client("s3", **kwargs)
-
-    @staticmethod
-    def _key(user_id: str, table: str, record_id: str) -> str:
-        return f"{user_id}/{table}/{record_id}"
-
-    async def upload(
-        self,
-        user_id: str,
-        table: str,
-        record_id: str,
-        blob: bytes,
-        checksum: str,
-    ) -> str:
-        """Store *blob* in S3 and return the S3 key.
-
-        Args:
-            user_id:   Owner of the blob (used as key prefix).
-            table:     Logical table name (e.g. ``"tasks"``).
-            record_id: Record UUID.
-            blob:      Raw bytes (pre-encrypted by client).
-            checksum:  SHA-256 hex digest supplied by the client; stored as
-                       object metadata for download-time verification.
-
-        Returns:
-            The S3 key under which the blob was stored.
-        """
-        key = self._key(user_id, table, record_id)
-        self._client().put_object(
-            Bucket=settings.S3_BUCKET,
-            Key=key,
-            Body=blob,
-            ServerSideEncryption="AES256",  # SSE-S3 at rest
-            Metadata={"checksum": checksum},
-        )
-        return key
-
-    async def download(self, user_id: str, s3_key: str) -> bytes:
-        """Retrieve the blob stored at *s3_key*.
-
-        *user_id* is retained in the signature so higher-level code can
-        enforce ownership without re-parsing the key.
-
-        Raises:
-            ``botocore.exceptions.ClientError`` with code ``NoSuchKey`` if the
-            object does not exist.
-        """
-        response = self._client().get_object(
-            Bucket=settings.S3_BUCKET,
-            Key=s3_key,
-        )
-        return response["Body"].read()
-
-    async def delete(self, user_id: str, s3_key: str) -> None:
-        """Delete the object at *s3_key*.
-
-        S3 ``delete_object`` is idempotent — it succeeds even if the key does
-        not exist.
-        """
-        self._client().delete_object(
-            Bucket=settings.S3_BUCKET,
-            Key=s3_key,
-        )
-
-    async def list_keys(self, user_id: str, table: str) -> list[str]:
-        """Return all S3 keys for a given user + table combination.
-
-        Uses the prefix ``{user_id}/{table}/`` to scope the listing.
-        """
-        prefix = f"{user_id}/{table}/"
-        response = self._client().list_objects_v2(
-            Bucket=settings.S3_BUCKET,
-            Prefix=prefix,
-        )
-        return [obj["Key"] for obj in response.get("Contents", [])]

app/storage/encryption.py

@@ -1,32 +0,0 @@
-"""Integrity verification only — the backend NEVER decrypts user data."""
-
-from __future__ import annotations
-
-import hashlib
-import hmac
-
-from fastapi import HTTPException
-
-
-def verify_checksum(blob: bytes, checksum: str) -> bool:
-    """Return ``True`` if SHA-256(blob) matches *checksum*.
-
-    Uses ``hmac.compare_digest`` for constant-time comparison to prevent
-    timing-based side-channel attacks.
-    """
-    computed = hashlib.sha256(blob).hexdigest()
-    return hmac.compare_digest(computed, checksum)
-
-
-def reject_if_tampered(blob: bytes, checksum: str) -> None:
-    """Raise ``HTTP 400`` if the blob does not match its checksum.
-
-    Call this before storing or forwarding any client-provided blob.
-    The backend never holds decryption keys — this check only verifies
-    that the opaque bytes arrived intact.
-    """
-    if not verify_checksum(blob, checksum):
-        raise HTTPException(
-            status_code=400,
-            detail="Checksum mismatch: blob integrity check failed",
-        )

app/storage/vector_store.py

@@ -1,205 +0,0 @@
-"""Cloud vector store — wraps Pinecone (default) or Qdrant.
-
-Vectors are pre-encrypted blobs from the client.  The backend stores them
-alongside a deterministic 32-dim float representation derived from the blob's
-SHA-256 hash.  Semantic ANN search is not meaningful on encrypted data — this
-is a known trade-off documented in the backend plan.
-
-Isolation: Pinecone uses ``namespace=user_id``; Qdrant filters by
-``user_id`` payload field on a shared collection.
-"""
-
-from __future__ import annotations
-
-import base64
-import hashlib
-from typing import Any
-
-from pinecone import Pinecone
-from qdrant_client import QdrantClient
-from qdrant_client.models import FieldCondition, Filter, MatchValue, PointIdsList, PointStruct
-
-from app.config.settings import settings
-from app.schemas import VectorItem, VectorSearchResult
-
-_QDRANT_COLLECTION = "adiuva_vectors"
-
-
-def _blob_to_vector(blob: bytes) -> list[float]:
-    """Derive a 32-dim float vector from *blob* for storage purposes only.
-
-    Uses SHA-256 to produce a deterministic 32-byte fingerprint, then
-    normalises each byte to the range [-1.0, 1.0].  This vector carries no
-    semantic meaning on encrypted data.
-    """
-    return [(b - 128) / 128.0 for b in hashlib.sha256(blob).digest()]
-
-
-class VectorStore:
-    """Thin wrapper around Pinecone or Qdrant.
-
-    The backend to use is selected at runtime:
-    - Pinecone: when ``settings.PINECONE_API_KEY`` is non-empty.
-    - Qdrant: otherwise (requires ``settings.QDRANT_URL``).
-    """
-
-    def _use_pinecone(self) -> bool:
-        return bool(settings.PINECONE_API_KEY)
-
-    # ── Pinecone helpers ──────────────────────────────────────────────
-
-    def _pinecone_index(self) -> Any:
-        pc = Pinecone(api_key=settings.PINECONE_API_KEY)
-        return pc.Index(settings.PINECONE_INDEX)
-
-    # ── Qdrant helpers ────────────────────────────────────────────────
-
-    def _qdrant_client(self) -> Any:
-        return QdrantClient(
-            url=settings.QDRANT_URL,
-            api_key=settings.QDRANT_API_KEY or None,
-        )
-
-    # ── Public API ────────────────────────────────────────────────────
-
-    async def upsert(self, user_id: str, vectors: list[VectorItem]) -> None:
-        """Store encrypted vectors in the backend.
-
-        Each ``VectorItem.blob`` is base64-encoded and kept in metadata/payload
-        so it can be returned verbatim during search.
-
-        Args:
-            user_id: Used as Pinecone namespace or Qdrant payload field.
-            vectors: List of encrypted vector items from the client.
-        """
-        if self._use_pinecone():
-            await self._pinecone_upsert(user_id, vectors)
-        else:
-            await self._qdrant_upsert(user_id, vectors)
-
-    async def search(
-        self,
-        user_id: str,
-        query_blob: bytes,
-        top_k: int,
-    ) -> list[VectorSearchResult]:
-        """Query the vector store and return encrypted result blobs.
-
-        The query vector is derived from *query_blob* using the same
-        deterministic mapping as upsert.
-
-        Args:
-            user_id:    Scopes the search to this user's namespace.
-            query_blob: Encrypted query from the client.
-            top_k:      Maximum number of results to return.
-
-        Returns:
-            List of ``VectorSearchResult`` with ``id``, ``score``, and ``blob``.
-        """
-        if self._use_pinecone():
-            return await self._pinecone_search(user_id, query_blob, top_k)
-        return await self._qdrant_search(user_id, query_blob, top_k)
-
-    async def delete(self, user_id: str, vector_ids: list[str]) -> None:
-        """Remove vectors by ID, scoped to *user_id*.
-
-        Args:
-            user_id:    Namespace / payload filter to prevent cross-user deletion.
-            vector_ids: List of vector IDs to remove.
-        """
-        if self._use_pinecone():
-            await self._pinecone_delete(user_id, vector_ids)
-        else:
-            await self._qdrant_delete(user_id, vector_ids)
-
-    # ── Pinecone implementation ───────────────────────────────────────
-
-    async def _pinecone_upsert(self, user_id: str, vectors: list[VectorItem]) -> None:
-        index = self._pinecone_index()
-        records = [
-            {
-                "id": v.id,
-                "values": _blob_to_vector(v.blob),
-                "metadata": {
-                    "blob": base64.b64encode(v.blob).decode(),
-                    "checksum": v.checksum,
-                    "user_id": user_id,
-                },
-            }
-            for v in vectors
-        ]
-        index.upsert(vectors=records, namespace=user_id)
-
-    async def _pinecone_search(
-        self, user_id: str, query_blob: bytes, top_k: int
-    ) -> list[VectorSearchResult]:
-        index = self._pinecone_index()
-        query_vector = _blob_to_vector(query_blob)
-        response = index.query(
-            vector=query_vector,
-            top_k=top_k,
-            namespace=user_id,
-            include_metadata=True,
-        )
-        results: list[VectorSearchResult] = []
-        for match in response.get("matches", []):
-            blob_bytes = base64.b64decode(match["metadata"]["blob"])
-            results.append(
-                VectorSearchResult(
-                    id=match["id"],
-                    score=match["score"],
-                    blob=blob_bytes,
-                )
-            )
-        return results
-
-    async def _pinecone_delete(self, user_id: str, vector_ids: list[str]) -> None:
-        index = self._pinecone_index()
-        index.delete(ids=vector_ids, namespace=user_id)
-
-    # ── Qdrant implementation ─────────────────────────────────────────
-
-    async def _qdrant_upsert(self, user_id: str, vectors: list[VectorItem]) -> None:
-        client = self._qdrant_client()
-        points = [
-            PointStruct(
-                id=v.id,
-                vector=_blob_to_vector(v.blob),
-                payload={
-                    "blob": base64.b64encode(v.blob).decode(),
-                    "checksum": v.checksum,
-                    "user_id": user_id,
-                },
-            )
-            for v in vectors
-        ]
-        client.upsert(collection_name=_QDRANT_COLLECTION, points=points)
-
-    async def _qdrant_search(
-        self, user_id: str, query_blob: bytes, top_k: int
-    ) -> list[VectorSearchResult]:
-        client = self._qdrant_client()
-        query_vector = _blob_to_vector(query_blob)
-        hits = client.search(
-            collection_name=_QDRANT_COLLECTION,
-            query_vector=query_vector,
-            query_filter=Filter(
-                must=[FieldCondition(key="user_id", match=MatchValue(value=user_id))]
-            ),
-            limit=top_k,
-        )
-        return [
-            VectorSearchResult(
-                id=str(hit.id),
-                score=hit.score,
-                blob=base64.b64decode(hit.payload["blob"]),
-            )
-            for hit in hits
-        ]
-
-    async def _qdrant_delete(self, user_id: str, vector_ids: list[str]) -> None:
-        client = self._qdrant_client()
-        client.delete(
-            collection_name=_QDRANT_COLLECTION,
-            points_selector=PointIdsList(points=vector_ids),
-        )

docker-compose.yml

@@ -7,7 +7,7 @@ services:
       - path: .env
         required: false
     environment:
-      DATABASE_URL: postgresql+asyncpg://postgres:postgres@db:5432/adiuva
+      DATABASE_URL: postgresql+asyncpg://postgres:postgres@db:5432/adiuvai
       GITHUB_COPILOT_TOKEN_DIR: /root/.config/litellm/github_copilot
     volumes:
       - copilot_tokens:/root/.config/litellm/github_copilot
@@ -21,7 +21,7 @@ services:
     environment:
       POSTGRES_USER: postgres
       POSTGRES_PASSWORD: postgres
-      POSTGRES_DB: adiuva
+      POSTGRES_DB: adiuvai
     volumes:
       - postgres_data:/var/lib/postgresql/data
     healthcheck:
@@ -36,37 +36,6 @@ services:
   #   image: redis:7-alpine
   #   restart: unless-stopped
 
-  # ── Local S3-compatible storage (MinIO) ──
-  minio:
-    image: minio/minio:latest
-    command: server /data --console-address ":9001"
-    ports:
-      - "9000:9000"
-      - "9001:9001"
-    environment:
-      MINIO_ROOT_USER: minioadmin
-      MINIO_ROOT_PASSWORD: minioadmin
-    volumes:
-      - minio_data:/data
-    healthcheck:
-      test: ["CMD", "mc", "ready", "local"]
-      interval: 5s
-      timeout: 5s
-      retries: 5
-    restart: unless-stopped
-
-  # ── Local vector store (Qdrant) ──
-  qdrant:
-    image: qdrant/qdrant:latest
-    ports:
-      - "6333:6333"
-      - "6334:6334"
-    volumes:
-      - qdrant_data:/qdrant/storage
-    restart: unless-stopped
-
 volumes:
   postgres_data:
-  minio_data:
-  qdrant_data:
   copilot_tokens:

docs/MICROSERVICES_ARCHITECTURE.md

@@ -1,941 +0,0 @@
-# Adiuva — Architettura Microservizi (MVP)
-
-## Panoramica
-
-Il monolite viene suddiviso in **4 servizi MVP** + un **API Gateway (Traefik)**, orchestrati con Docker Compose su un singolo VPS raggiungibile via Cloudflare.
-
-> **Fuori dall'MVP**: Storage Service (S3/backup CRUD) e Plugin Service (marketplace). Verranno aggiunti come servizi indipendenti in una fase successiva.
-
-```
-                          ┌──────────────┐
-                          │  Cloudflare  │
-                          │  (DNS + CDN) │
-                          └──────┬───────┘
-                                 │ HTTPS / WSS
-                          ┌──────▼───────┐
-                          │   Traefik    │
-                          │ API Gateway  │
-                          │  (routing,   │
-                          │   TLS, rate  │
-                          │   limiting)  │
-                          └──────┬───────┘
-                                 │
-          ┌──────────┬───────────┼───────────┐
-          │          │           │           │
-    ┌─────▼────┐ ┌───▼───┐ ┌────▼────┐ ┌────▼───┐
-    │  Auth    │ │  Chat │ │  Agent  │ │Billing │
-    │ Service  │ │Service│ │ Service │ │Service │
-    └─────┬────┘ └───┬───┘ └────┬────┘ └────┬───┘
-          │          │          │           │
-    ┌─────▼──────────▼──────────▼───────────▼────┐
-    │              Infrastruttura                 │
-    │  PostgreSQL  │  Redis  │  Qdrant            │
-    └─────────────────────────────────────────────┘
-```
-
----
-
-## 1. Suddivisione dei Servizi
-
-### 1.1 Auth Service (`auth-service`)
-
-**Responsabilità**: Registrazione, login, refresh token, profilo utente, encryption key.
-
-| Endpoint originale | Metodo |
-|---|---|
-| `/api/v1/auth/register` | POST |
-| `/api/v1/auth/login` | POST |
-| `/api/v1/auth/refresh` | POST |
-| `/api/v1/auth/me` | GET / PUT |
-
-**Database**: Tabelle `users`, `refresh_tokens` (PostgreSQL condiviso, schema `auth`).
-
-**Modifica chiave — JWT con RS256**:
-Il monolite usa un `SECRET_KEY` simmetrico (HS256). Con i microservizi, passare a **RS256** (asimmetrico):
-- L'Auth Service firma i JWT con la **chiave privata**.
-- Tutti gli altri servizi verificano i JWT con la **chiave pubblica** senza mai contattare l'Auth Service.
-- La chiave pubblica viene esposta via `GET /api/v1/auth/.well-known/jwks.json` oppure montata come volume condiviso.
-
-```python
-# auth-service/app/auth/jwt.py
-from cryptography.hazmat.primitives.asymmetric import rsa
-from jose import jwt
-
-PRIVATE_KEY = ...  # Da env/secret
-PUBLIC_KEY = ...   # Derivata o da env
-
-def create_access_token(user_id: str, tier: str) -> str:
-    return jwt.encode(
-        {"sub": user_id, "tier": tier, "exp": ...},
-        PRIVATE_KEY,
-        algorithm="RS256",
-    )
-```
-
-```python
-# shared/auth.py  (usato da tutti gli altri servizi)
-from jose import jwt
-
-PUBLIC_KEY = ...  # Volume montato o fetched da JWKS endpoint
-
-def verify_token(token: str) -> dict:
-    return jwt.decode(token, PUBLIC_KEY, algorithms=["RS256"])
-```
-
-**Scaling**: 2 repliche sufficienti, stateless. Rate-limit dedicato su `/login` e `/register`.
-
----
-
-### 1.2 Chat Service (`chat-service`) ⭐ Real-time
-
-**Responsabilità**: WebSocket device connection, home chat, floating chat, memory middleware, streaming LLM responses verso il client.
-
-Questo servizio gestisce la **connessione persistente** con l'app Electron e le interazioni **real-time** dell'utente (chat home, floating chat). È il proprietario della WebSocket.
-
-| Endpoint | Tipo |
-|---|---|
-| `/api/v1/ws/device` | WebSocket (connessione persistente) |
-| `/api/v1/chat` | POST (REST fallback) |
-
-**Moduli inclusi**: `deep_agent`, `memory_middleware`, `ws_context`, `device_manager` (Redis-backed), `output_formatter`, `llm`, tutti gli agent tools (`task_agent`, `project_agent`, `note_agent`, `timeline_agent`).
-
-**Perché separato dall'Agent Service**: Il Chat Service tiene la WebSocket aperta e risponde in tempo reale (streaming). Scalare aggiungendo repliche è semplice con sticky sessions + Redis pub/sub per il cross-instance routing dei tool_call.
-
-**Scaling**: 2–N repliche. Sticky cookies per le WS + Redis per cross-instance.
-
----
-
-### 1.3 Agent Service (`agent-service`) ⭐ Batch
-
-**Responsabilità**: Batch agent processing (directory scanning, file classification, entity extraction), agent setup journeys, agent configuration CRUD.
-
-Questo servizio gestisce i processi **long-running** e **CPU-intensive**: scansione filesystem, classificazione file con LLM, estrazione entità in batch. Non possiede la WebSocket — comunica con il device dell'utente tramite **Redis pub/sub** passando per il Chat Service.
-
-| Endpoint | Tipo |
-|---|---|
-| `/api/v1/agents/catalog` | GET |
-| `/api/v1/agents/can-create` | POST |
-| `/api/v1/agents/trigger` | POST |
-| `/api/v1/agents/journey/start` | POST (o WS relay) |
-| `/api/v1/agents/journey/message` | POST (o WS relay) |
-
-**Moduli inclusi**: `agent_runner`, `agent_registry`, `filesystem_agent`, `llm`.
-
-**Flusso tool-call cross-service** (l'Agent Service non ha la WS):
-
-```
-┌──────────────┐            ┌──────────────┐            ┌──────────┐
-│ Agent Service│            │    Redis     │            │  Chat    │
-│ (batch run)  │            │              │            │ Service  │
-│              │            │              │            │ (ha WS)  │
-│ 1. Needs to  │  PUBLISH   │              │ SUBSCRIBE  │          │
-│    read file ├───────────►│tool_call:u123├───────────►│ 2. Invia │
-│    from      │            │              │            │    al    │
-│    device    │            │              │            │    device│
-│              │            │              │            │    via WS│
-│              │  SUBSCRIBE │              │  PUBLISH   │          │
-│ 4. Riceve   ◄────────────┤tool_result:id│◄───────────┤ 3. Device│
-│    risultato │            │              │            │    reply │
-└──────────────┘            └──────────────┘            └──────────┘
-```
-
-**Scaling**: 1–N repliche. Completamente stateless, scala indipendentemente dalla chat. Ogni replica processa batch job diversi. Può essere scalato a 0 se non ci sono agent attivi (risparmio risorse).
-
-**Vantaggio dello split**: Se 50 utenti triggerano agenti batch contemporaneamente, il Chat Service non ne risente — le risposte real-time rimangono veloci.
-
----
-
-### 1.4 Billing Service (`billing-service`)
-
-**Responsabilità**: Stripe checkout, webhook, subscription management.
-
-| Endpoint originale | Metodo |
-|---|---|
-| `/api/v1/billing/checkout` | POST |
-| `/api/v1/billing/webhook` | POST |
-| `/api/v1/billing/subscription` | GET / DELETE |
-
-**Database**: Tabelle `subscriptions` (schema `billing`).
-
-**Comunicazione inter-servizio**: Quando Stripe invia un webhook e il tier cambia, il Billing Service pubblica un evento su **Redis pub/sub** channel `tier_changed:{user_id}`. L'Auth Service aggiorna il campo `tier` nella tabella users. Al prossimo token refresh il JWT conterrà il tier aggiornato.
-
-**Scaling**: 1 replica sufficiente. Basso traffico.
-
----
-
-### 1.5 Servizi esclusi dall'MVP
-
-I seguenti servizi verranno aggiunti post-MVP come servizi indipendenti:
-
-| Servizio | Responsabilità | Note |
-|---|---|---|
-| **Storage Service** | S3 blobs CRUD, vector ops, backup | Le funzionalità vector/embed possono restare nel Chat Service per il MVP |
-| **Plugin Service** | Marketplace, install, revenue split | Feature non critica per il lancio |
-
----
-
-## 2. Tier Check — Dove e Come
-
-Il tier dell'utente (free/pro/power/team) determina rate-limiting, quote e accesso a funzionalità. Con i microservizi, **ogni servizio controlla il tier autonomamente** senza chiamare l'Auth Service.
-
-### Strategia: Tier nel JWT
-
-L'Auth Service include il `tier` come claim nel JWT al momento del login/refresh:
-
-```json
-{
-  "sub": "user_123",
-  "tier": "pro",
-  "exp": 1742515200,
-  "iat": 1742511600
-}
-```
-
-Ogni servizio:
-1. Decodifica il JWT con la chiave pubblica (già lo fa per l'auth)
-2. Legge `payload["tier"]` — **zero chiamate extra**
-3. Applica le sue regole di enforcement localmente
-
-```python
-# shared/auth.py — dependency FastAPI condivisa
-from fastapi import Depends, HTTPException, Request
-from jose import jwt
-
-PUBLIC_KEY = ...
-
-class CurrentUser:
-    def __init__(self, user_id: str, tier: str):
-        self.user_id = user_id
-        self.tier = tier
-
-async def get_current_user(request: Request) -> CurrentUser:
-    token = request.headers.get("Authorization", "").removeprefix("Bearer ")
-    payload = jwt.decode(token, PUBLIC_KEY, algorithms=["RS256"])
-    return CurrentUser(user_id=payload["sub"], tier=payload["tier"])
-
-def require_tier(*allowed_tiers: str):
-    """Dependency che blocca se il tier non è tra quelli ammessi."""
-    async def check(user: CurrentUser = Depends(get_current_user)):
-        if user.tier not in allowed_tiers:
-            raise HTTPException(403, "Tier insufficient")
-        return user
-    return check
-```
-
-### Cosa succede quando il tier cambia (upgrade/downgrade)?
-
-```
-┌──────────┐  Stripe webhook   ┌──────────┐  tier_changed   ┌──────────┐
-│  Stripe  │ ─────────────────►│ Billing  │ ───────────────►│   Auth   │
-│          │                    │ Service  │  (Redis pub/sub) │ Service  │
-└──────────┘                    └──────────┘                  └────┬─────┘
-                                                                   │
-                                                          UPDATE users
-                                                          SET tier = 'power'
-                                                                   │
-                                                    Al prossimo /refresh
-                                                    il JWT conterrà tier='power'
-```
-
-**Latenza del cambio**: Il tier si propaga al prossimo token refresh (tipicamente 15–30 min, o il client può forzare un refresh immediato dopo il checkout). Per il billing webhook, il downgrade può essere forzato invalidando il refresh token su Redis → il client è obbligato a ri-autenticarsi.
-
-### Dove si applica in ciascun servizio
-
-| Servizio | Enforcement |
-|---|---|
-| **Auth Service** | Nessuno (è lui che scrive il tier) |
-| **Chat Service** | Rate-limit per tier (req/min), quota messaggi |
-| **Agent Service** | Max agent configs, max runs/day, max concurrent batches |
-| **Billing Service** | Nessuno (gestisce i tier, non li consuma) |
-
-### Rate-limit distribuito via Redis
-
-Poiché ogni servizio ha le sue repliche, il rate-limiting deve essere **condiviso** via Redis:
-
-```python
-# shared/middleware/rate_limit.py
-import redis.asyncio as aioredis
-
-class DistributedRateLimiter:
-    def __init__(self, redis: aioredis.Redis):
-        self._redis = redis
-
-    async def check(self, user_id: str, tier: str, service: str) -> bool:
-        limits = {"free": 20, "pro": 60, "power": 120, "team": 200}
-        max_req = limits.get(tier, 20)
-        key = f"rate:{service}:{user_id}"
-
-        pipe = self._redis.pipeline()
-        pipe.incr(key)
-        pipe.expire(key, 60)
-        count, _ = await pipe.execute()
-
-        return count <= max_req
-```
-
----
-
-## 3. WebSocket con Scaling Orizzontale — Il Problema Chiave
-
-`DeviceConnectionManager` è un **singleton in-memory**:
-
-```python
-class DeviceConnectionManager:
-    def __init__(self):
-        self._connections: dict[str, DeviceConnection] = {}  # ← In-memory!
-```
-
-Con N istanze del Chat Service, il device si connette a **una sola** istanza. Quando un'altra istanza deve inviare un `tool_call` a quel device (es. un agent trigger da un'API call), non trova la connessione.
-
-### La soluzione: Redis Pub/Sub + Registry
-
-```
-┌──────────────────────────────────────────────────────────────┐
-│                     Redis                                    │
-│                                                              │
-│  Hash: ws:connections                                        │
-│    user_123 → instance_A                                     │
-│    user_456 → instance_B                                     │
-│                                                              │
-│  Pub/Sub channels:                                           │
-│    tool_call:{user_id}  → tool call payloads                 │
-│    tool_result:{call_id} → tool result payloads              │
-│    stream:{user_id}     → text_chunk streaming               │
-└──────────────────────────────────────────────────────────────┘
-
- Instance A (ha WS di user_123)     Instance B (deve chiamare tool su user_123)
- ┌───────────────────────┐          ┌───────────────────────┐
- │  1. Sottoscrive a     │          │  1. Lookup Redis Hash │
- │     tool_call:user_123│          │     → user_123 è su A │
- │                       │          │                       │
- │  2. Riceve tool_call  │◄─────────│  2. PUBLISH           │
- │     da Redis channel  │          │    tool_call:user_123 │
- │                       │          │    {id, action, ...}  │
- │  3. Invia al device   │          │                       │
- │     via WS            │          │  4. SUBSCRIBE         │
- │                       │          │    tool_result:{id}   │
- │  4. Device risponde   │          │                       │
- │     tool_result       │──────────│► 5. Riceve risultato  │
- │                       │          │                       │
- │  5. PUBLISH           │          │                       │
- │    tool_result:{id}   │          │                       │
- └───────────────────────┘          └───────────────────────┘
-```
-
-### Implementazione: `RedisDeviceManager`
-
-```python
-# chat-service/app/core/device_manager.py
-
-import asyncio
-import json
-import os
-import redis.asyncio as aioredis
-from dataclasses import dataclass, field
-from fastapi import WebSocket
-
-INSTANCE_ID = os.environ.get("INSTANCE_ID", os.urandom(8).hex())
-
-@dataclass
-class LocalConnection:
-    ws: WebSocket
-    device_id: str
-    pending_calls: dict[str, asyncio.Future[dict]] = field(default_factory=dict)
-
-
-class RedisDeviceManager:
-    """Device manager backed by Redis for cross-instance communication."""
-
-    def __init__(self, redis_url: str = "redis://redis:6379"):
-        self._redis = aioredis.from_url(redis_url)
-        self._pubsub = self._redis.pubsub()
-        self._local: dict[str, LocalConnection] = {}  # Solo connessioni locali
-        self._remote_futures: dict[str, asyncio.Future[dict]] = {}
-
-    async def start(self):
-        """Avvia il listener Redis per tool_call in arrivo."""
-        asyncio.create_task(self._listen_tool_calls())
-
-    # ── Registrazione ──
-
-    async def register(self, user_id: str, device_id: str, ws: WebSocket):
-        # Registra localmente
-        self._local[user_id] = LocalConnection(ws=ws, device_id=device_id)
-        # Registra in Redis quale istanza ha la connessione
-        await self._redis.hset("ws:connections", user_id, INSTANCE_ID)
-        # Sottoscrivi ai tool_call per questo utente
-        await self._pubsub.subscribe(f"tool_call:{user_id}")
-
-    async def unregister(self, user_id: str):
-        conn = self._local.pop(user_id, None)
-        if conn:
-            for fut in conn.pending_calls.values():
-                if not fut.done():
-                    fut.cancel()
-        await self._redis.hdel("ws:connections", user_id)
-        await self._pubsub.unsubscribe(f"tool_call:{user_id}")
-
-    # ── Presenza ──
-
-    async def is_online(self, user_id: str) -> bool:
-        return await self._redis.hexists("ws:connections", user_id)
-
-    # ── Tool-call round-trip (cross-instance) ──
-
-    async def execute_tool_call(self, user_id: str, payload: dict) -> dict:
-        """
-        Invia un tool_call al device dell'utente.
-        Funziona sia che la WS sia locale che su un'altra istanza.
-        """
-        call_id = payload["id"]
-
-        # Caso 1: connessione locale → invio diretto
-        if user_id in self._local:
-            conn = self._local[user_id]
-            loop = asyncio.get_event_loop()
-            fut: asyncio.Future[dict] = loop.create_future()
-            conn.pending_calls[call_id] = fut
-            await conn.ws.send_text(json.dumps({"type": "tool_call", **payload}))
-            return await asyncio.wait_for(fut, timeout=30.0)
-
-        # Caso 2: connessione remota → Redis pub/sub
-        loop = asyncio.get_event_loop()
-        fut = loop.create_future()
-        self._remote_futures[call_id] = fut
-
-        # Sottoscrivi al canale di risposta
-        result_channel = f"tool_result:{call_id}"
-        await self._pubsub.subscribe(result_channel)
-
-        # Pubblica il tool_call
-        await self._redis.publish(
-            f"tool_call:{user_id}",
-            json.dumps(payload),
-        )
-
-        try:
-            return await asyncio.wait_for(fut, timeout=30.0)
-        finally:
-            self._remote_futures.pop(call_id, None)
-            await self._pubsub.unsubscribe(result_channel)
-
-    # ── Risoluzione tool_result (da WS locale) ──
-
-    def resolve_local(self, user_id: str, call_id: str, result: dict):
-        conn = self._local.get(user_id)
-        if conn:
-            fut = conn.pending_calls.pop(call_id, None)
-            if fut and not fut.done():
-                fut.set_result(result)
-
-    async def resolve_and_publish(self, user_id: str, call_id: str, result: dict):
-        """Chiamato quando il device locale invia un tool_result."""
-        self.resolve_local(user_id, call_id, result)
-        # Pubblica anche su Redis per l'istanza remota che aspetta
-        await self._redis.publish(
-            f"tool_result:{call_id}",
-            json.dumps(result),
-        )
-
-    # ── Listener Redis ──
-
-    async def _listen_tool_calls(self):
-        """Loop che ascolta i tool_call in arrivo da altre istanze."""
-        async for message in self._pubsub.listen():
-            if message["type"] != "message":
-                continue
-            channel = message["channel"]
-            if isinstance(channel, bytes):
-                channel = channel.decode()
-
-            data = json.loads(message["data"])
-
-            if channel.startswith("tool_call:"):
-                # Un'altra istanza vuole che inviamo un tool_call al nostro device
-                user_id = channel.split(":", 1)[1]
-                conn = self._local.get(user_id)
-                if conn:
-                    await conn.ws.send_text(json.dumps({"type": "tool_call", **data}))
-
-            elif channel.startswith("tool_result:"):
-                # Risposta a un tool_call che abbiamo inviato tramite Redis
-                call_id = channel.split(":", 1)[1]
-                fut = self._remote_futures.pop(call_id, None)
-                if fut and not fut.done():
-                    fut.set_result(data)
-
-    # ── Stream cross-instance ──
-
-    async def publish_stream_chunk(self, user_id: str, chunk: dict):
-        """Pubblica un chunk di streaming su Redis (per REST→WS relay)."""
-        await self._redis.publish(f"stream:{user_id}", json.dumps(chunk))
-```
-
----
-
-## 4. Struttura Directory Proposta (MVP)
-
-```
-adiuva-api/
-├── docker-compose.yml          # Orchestrazione completa
-├── docker-compose.dev.yml      # Override per sviluppo locale
-├── shared/                     # Codice condiviso (montato come volume)
-│   ├── auth.py                 # JWT verification (chiave pubblica)
-│   ├── schemas.py              # Pydantic schemas condivisi
-│   ├── middleware/
-│   │   ├── rate_limit.py       # DistributedRateLimiter (Redis)
-│   │   └── sanitizer.py
-│   └── models/
-│       └── base.py             # SQLAlchemy base condivisa
-│
-├── auth-service/
-│   ├── Dockerfile
-│   ├── requirements.txt
-│   └── app/
-│       ├── main.py
-│       ├── config.py
-│       ├── db.py
-│       ├── models.py           # users, refresh_tokens
-│       ├── routes/
-│       │   └── auth.py
-│       └── services/
-│           ├── jwt_service.py  # RS256 signing
-│           └── user_service.py
-│
-├── chat-service/
-│   ├── Dockerfile
-│   ├── requirements.txt
-│   └── app/
-│       ├── main.py
-│       ├── config.py
-│       ├── db.py
-│       ├── models.py           # memory_*
-│       ├── routes/
-│       │   ├── device_ws.py    # WS connection owner
-│       │   └── chat.py         # REST fallback
-│       ├── core/
-│       │   ├── device_manager.py   # RedisDeviceManager
-│       │   ├── deep_agent.py       # Home + floating chat
-│       │   ├── memory_middleware.py
-│       │   ├── ws_context.py
-│       │   ├── output_formatter.py
-│       │   └── llm.py
-│       └── agents/                 # Tool definitions (used by deep_agent)
-│           ├── task_agent.py
-│           ├── project_agent.py
-│           ├── note_agent.py
-│           └── timeline_agent.py
-│
-├── agent-service/
-│   ├── Dockerfile
-│   ├── requirements.txt
-│   └── app/
-│       ├── main.py
-│       ├── config.py
-│       ├── db.py
-│       ├── models.py           # agent_run_logs, local/cloud_agent_configs
-│       ├── routes/
-│       │   ├── agents.py       # catalog, can-create, trigger
-│       │   └── agent_setup.py  # journey start/message
-│       ├── core/
-│       │   ├── agent_runner.py     # Batch classify → process
-│       │   ├── agent_registry.py
-│       │   ├── redis_executor.py   # execute_on_client via Redis pub/sub
-│       │   └── llm.py
-│       └── agents/
-│           ├── task_agent.py       # Tool definitions (batch context)
-│           ├── project_agent.py
-│           ├── note_agent.py
-│           ├── timeline_agent.py
-│           └── filesystem_agent.py
-│
-├── billing-service/
-│   ├── Dockerfile
-│   ├── requirements.txt
-│   └── app/
-│       ├── main.py
-│       ├── config.py
-│       ├── db.py
-│       ├── models.py           # subscriptions
-│       ├── routes/
-│       │   └── billing.py
-│       └── services/
-│           ├── stripe_service.py
-│           └── tier_manager.py
-│
-└── infra/
-    ├── traefik/
-    │   └── traefik.yml
-    ├── keys/
-    │   ├── jwt_private.pem     # Solo auth-service
-    │   └── jwt_public.pem      # Tutti i servizi
-    └── alembic/                # Migrazioni condivise o per-servizio
-```
-
----
-
-## 5. Docker Compose — Configurazione MVP
-
-```yaml
-# docker-compose.yml
-
-services:
-
-  # ══════════════════════════════════════════════════════════
-  # API Gateway
-  # ══════════════════════════════════════════════════════════
-  traefik:
-    image: traefik:v3.2
-    command:
-      - "--api.insecure=true"
-      - "--providers.docker=true"
-      - "--providers.docker.exposedbydefault=false"
-      - "--entrypoints.web.address=:80"
-      - "--entrypoints.websecure.address=:443"
-      - "--entrypoints.web.http.redirections.entrypoint.to=websecure"
-    ports:
-      - "80:80"
-      - "443:443"
-      - "8080:8080"   # Dashboard Traefik (disabilitare in prod)
-    volumes:
-      - /var/run/docker.sock:/var/run/docker.sock:ro
-      - ./infra/certs:/certs:ro
-    restart: unless-stopped
-
-  # ══════════════════════════════════════════════════════════
-  # Auth Service (2 repliche)
-  # ══════════════════════════════════════════════════════════
-  auth-service:
-    build: ./auth-service
-    deploy:
-      replicas: 2
-    env_file: .env
-    environment:
-      DATABASE_URL: postgresql+asyncpg://postgres:postgres@db:5432/adiuva
-      REDIS_URL: redis://redis:6379
-      JWT_PRIVATE_KEY_FILE: /run/secrets/jwt_private_key
-      SERVICE_NAME: auth
-    secrets:
-      - jwt_private_key
-      - jwt_public_key
-    labels:
-      - "traefik.enable=true"
-      - "traefik.http.routers.auth.rule=PathPrefix(`/api/v1/auth`)"
-      - "traefik.http.services.auth.loadbalancer.server.port=8000"
-    depends_on:
-      db:
-        condition: service_healthy
-      redis:
-        condition: service_healthy
-
-  # ══════════════════════════════════════════════════════════
-  # Chat Service — Real-time WS + Chat (scalabile)
-  # ══════════════════════════════════════════════════════════
-  chat-service:
-    build: ./chat-service
-    deploy:
-      replicas: 2
-    env_file: .env
-    environment:
-      DATABASE_URL: postgresql+asyncpg://postgres:postgres@db:5432/adiuva
-      REDIS_URL: redis://redis:6379
-      JWT_PUBLIC_KEY_FILE: /run/secrets/jwt_public_key
-      SERVICE_NAME: chat
-    secrets:
-      - jwt_public_key
-    labels:
-      - "traefik.enable=true"
-      # REST chat endpoint
-      - "traefik.http.routers.chat.rule=PathPrefix(`/api/v1/chat`)"
-      - "traefik.http.services.chat.loadbalancer.server.port=8000"
-      # WebSocket route con sticky session
-      - "traefik.http.routers.ws.rule=PathPrefix(`/api/v1/ws`)"
-      - "traefik.http.routers.ws.service=chat-ws"
-      - "traefik.http.services.chat-ws.loadbalancer.server.port=8000"
-      - "traefik.http.services.chat-ws.loadbalancer.sticky.cookie.name=ws_affinity"
-      - "traefik.http.services.chat-ws.loadbalancer.sticky.cookie.httpOnly=true"
-    depends_on:
-      db:
-        condition: service_healthy
-      redis:
-        condition: service_healthy
-
-  # ══════════════════════════════════════════════════════════
-  # Agent Service — Batch processing (scalabile indipendentemente)
-  # ══════════════════════════════════════════════════════════
-  agent-service:
-    build: ./agent-service
-    deploy:
-      replicas: 2
-    env_file: .env
-    environment:
-      DATABASE_URL: postgresql+asyncpg://postgres:postgres@db:5432/adiuva
-      REDIS_URL: redis://redis:6379
-      JWT_PUBLIC_KEY_FILE: /run/secrets/jwt_public_key
-      SERVICE_NAME: agent
-    secrets:
-      - jwt_public_key
-    labels:
-      - "traefik.enable=true"
-      - "traefik.http.routers.agents.rule=PathPrefix(`/api/v1/agents`)"
-      - "traefik.http.services.agents.loadbalancer.server.port=8000"
-    depends_on:
-      db:
-        condition: service_healthy
-      redis:
-        condition: service_healthy
-
-  # ══════════════════════════════════════════════════════════
-  # Billing Service (1 replica)
-  # ══════════════════════════════════════════════════════════
-  billing-service:
-    build: ./billing-service
-    deploy:
-      replicas: 1
-    env_file: .env
-    environment:
-      DATABASE_URL: postgresql+asyncpg://postgres:postgres@db:5432/adiuva
-      REDIS_URL: redis://redis:6379
-      JWT_PUBLIC_KEY_FILE: /run/secrets/jwt_public_key
-      SERVICE_NAME: billing
-    secrets:
-      - jwt_public_key
-    labels:
-      - "traefik.enable=true"
-      - "traefik.http.routers.billing.rule=PathPrefix(`/api/v1/billing`)"
-      - "traefik.http.services.billing.loadbalancer.server.port=8000"
-    depends_on:
-      db:
-        condition: service_healthy
-      redis:
-        condition: service_healthy
-
-  # ══════════════════════════════════════════════════════════
-  # Infrastruttura
-  # ══════════════════════════════════════════════════════════
-  db:
-    image: pgvector/pgvector:pg16
-    environment:
-      POSTGRES_USER: postgres
-      POSTGRES_PASSWORD: postgres
-      POSTGRES_DB: adiuva
-    volumes:
-      - postgres_data:/var/lib/postgresql/data
-    healthcheck:
-      test: ["CMD-SHELL", "pg_isready -U postgres"]
-      interval: 5s
-      timeout: 5s
-      retries: 5
-    restart: unless-stopped
-
-  redis:
-    image: redis:7-alpine
-    command: redis-server --maxmemory 256mb --maxmemory-policy allkeys-lru
-    volumes:
-      - redis_data:/data
-    healthcheck:
-      test: ["CMD", "redis-cli", "ping"]
-      interval: 5s
-      timeout: 3s
-      retries: 5
-    restart: unless-stopped
-
-  qdrant:
-    image: qdrant/qdrant:latest
-    volumes:
-      - qdrant_data:/qdrant/storage
-    restart: unless-stopped
-
-secrets:
-  jwt_private_key:
-    file: ./infra/keys/jwt_private.pem
-  jwt_public_key:
-    file: ./infra/keys/jwt_public.pem
-
-volumes:
-  postgres_data:
-  redis_data:
-  qdrant_data:
-```
-
----
-
-## 6. Configurazione Cloudflare + VPS
-
-### 6.1 DNS
-
-```
-api.tuodominio.com  →  A record  →  IP del VPS
-                    →  Proxy: ON (orange cloud)
-```
-
-### 6.2 Cloudflare Settings
-
-| Setting | Valore | Motivo |
-|---------|--------|--------|
-| SSL/TLS mode | **Full (Strict)** | Cloudflare ↔ VPS con certificato valido |
-| WebSocket | **ON** | Necessario per `/api/v1/ws/device` |
-| Proxy timeout | **100s** (Enterprise) o default | Le LLM calls possono durare 30s+ |
-| Under Attack Mode | Off (attivare se necessario) | |
-
-### 6.3 TLS sul VPS
-
-Due opzioni:
-- **Opzione A (consigliata)**: Cloudflare Origin Certificate → montato in Traefik
-- **Opzione B**: Let's Encrypt via Traefik (con DNS challenge Cloudflare)
-
-```yaml
-# traefik.yml — con Cloudflare Origin Certificate
-entryPoints:
-  websecure:
-    address: ":443"
-
-tls:
-  certificates:
-    - certFile: /certs/origin.pem
-      keyFile: /certs/origin-key.pem
-```
-
-### 6.4 Rete VPS
-
-```bash
-# UFW firewall — solo Cloudflare può raggiungere le porte 80/443
-# https://www.cloudflare.com/ips/
-ufw default deny incoming
-ufw allow from 173.245.48.0/20 to any port 443
-ufw allow from 103.21.244.0/22 to any port 443
-# ... (tutti gli IP range di Cloudflare)
-ufw allow ssh
-ufw enable
-```
-
----
-
-## 7. Comunicazione Inter-Servizio
-
-### 7.1 Redis Pub/Sub — Event Bus
-
-```
-┌──────────┐  tier_changed:user_123   ┌──────────┐
-│ Billing  │ ────────────────────────► │   Auth   │
-│ Service  │                           │ Service  │
-└──────────┘                           └──────────┘
-
-┌──────────┐  tool_call:user_123      ┌──────────┐
-│  Agent   │ ────────────────────────► │   Chat   │
-│ Service  │                           │ Service  │
-│ (batch)  │ ◄────────────────────────│ (ha WS)  │
-└──────────┘  tool_result:{call_id}    └──────────┘
-```
-
-### 7.2 Health Checks e Service Discovery
-
-Traefik gestisce automaticamente il service discovery via Docker labels. I servizi non devono conoscersi tra loro — comunicano solo via:
-- **Redis pub/sub** (tool-call cross-instance, tier events)
-- **Redis hash** (stato condiviso: `ws:connections`, rate-limit counters)
-- **PostgreSQL** (dati persistenti condivisi)
-
----
-
-## 8. Piano di Migrazione Incrementale (MVP)
-
-### Fase 1 — Preparazione (nel monolite attuale)
-1. Aggiungere Redis al `docker-compose.yml` attuale
-2. Migrare JWT da HS256 → RS256 (backward-compatible: accetta entrambi per un periodo)
-3. Implementare `RedisDeviceManager` come drop-in replacement del singleton in-memory
-4. Estrarre `shared/` con auth verification, schemas, middleware
-
-### Fase 2 — Auth Service (primo split)
-1. Estrarre `auth.py` routes + models in `auth-service/`
-2. Verificare che i JWT firmati da `auth-service` vengano validati dal monolite
-3. Aggiungere Traefik e routare `/api/v1/auth/*` al nuovo servizio
-4. Il monolite continua a servire tutto il resto
-
-### Fase 3 — Billing Service
-1. Estrarre billing routes, Stripe service, tier manager
-2. Configurare Redis pub/sub per `tier_changed` events
-3. Routare via Traefik
-
-### Fase 4 — Split Chat + Agent (il più delicato)
-1. Il monolite residuo contiene WS + chat + agents
-2. Separare Agent Service: estrarre `agent_runner`, `agent_registry`, `agent_setup`, route `/agents/*`
-3. Implementare `redis_executor.py` nell'Agent Service per tool-call via Redis
-4. Il Chat Service resta proprietario della WS e sottoscrive i canali `tool_call:{user_id}`
-5. Testare: trigger agent dall'Agent Service → tool_call via Redis → Chat Service → WS → device → risposta
-
-### Fase 5 — Scaling test
-1. Scalare Chat Service a 2 repliche, verificare sticky sessions
-2. Scalare Agent Service a 2 repliche, verificare batch processing distribuito
-3. Monitoring (Prometheus + Grafana) per ogni servizio
-
----
-
-## 9. Monitoraggio e Logging
-
-```yaml
-# Aggiungere al docker-compose.yml
-
-  prometheus:
-    image: prom/prometheus:latest
-    volumes:
-      - ./infra/prometheus/prometheus.yml:/etc/prometheus/prometheus.yml
-    restart: unless-stopped
-
-  grafana:
-    image: grafana/grafana:latest
-    ports:
-      - "3000:3000"
-    volumes:
-      - grafana_data:/var/lib/grafana
-    restart: unless-stopped
-
-  loki:
-    image: grafana/loki:latest
-    restart: unless-stopped
-```
-
-Ogni servizio espone `/metrics` (Prometheus) e scrive log strutturati (JSON) raccolti da Loki.
-
----
-
-## 10. Sizing VPS Minimo Consigliato (MVP)
-
-| Componente | CPU | RAM | Note |
-|---|---|---|---|
-| Traefik | 0.25 | 128MB | |
-| Auth Service ×2 | 0.25 ×2 | 128MB ×2 | Stateless, leggero |
-| Chat Service ×2 | 1.0 ×2 | 1GB ×2 | WS + streaming LLM |
-| Agent Service ×2 | 0.75 ×2 | 512MB ×2 | Batch LLM, CPU-bound |
-| Billing Service | 0.25 | 128MB | |
-| PostgreSQL | 1.0 | 1GB | |
-| Redis | 0.25 | 256MB | |
-| Qdrant | 0.5 | 512MB | |
-| **Totale MVP** | **~5.5 vCPU** | **~5 GB** | |
-
-**Raccomandazione**: VPS con **8 vCPU / 16 GB RAM** per avere margine. Hetzner CPX41 (~€30/mese) o equivalente. Senza Storage/Plugin si risparmia ~1 vCPU e 512MB rispetto alla versione completa.
-
----
-
-## Riepilogo Architettura MVP
-
-| Servizio | Repliche | Proprietario di |
-|---|---|---|
-| **Traefik** | 1 | Routing, TLS, sticky sessions |
-| **Auth Service** | 2 | JWT RS256, registrazione, login, profilo |
-| **Chat Service** | 2–N | WebSocket, home/floating chat, streaming |
-| **Agent Service** | 2–N | Batch processing, directory scan, agent setup |
-| **Billing Service** | 1 | Stripe, subscriptions, tier management |
-
-| Decisione | Scelta | Motivazione |
-|---|---|---|
-| API Gateway | Traefik | Nativo Docker, WebSocket support, service discovery automatico |
-| JWT | RS256 (asimmetrico) | Verifica distribuita senza contattare Auth Service |
-| Tier check | Claim nel JWT | Ogni servizio verifica localmente, zero roundtrip |
-| WebSocket scaling | Redis pub/sub + sticky cookies | Cross-instance tool-call routing |
-| Chat ↔ Agent split | Servizi separati | Batch CPU-bound non impatta real-time chat |
-| Agent → Device comms | Redis pub/sub via Chat Service | Agent non possiede la WS, usa un relay |
-| Rate limiting | Redis contatori distribuiti | Sliding window condivisa tra repliche |
-| Database | PostgreSQL condiviso | Semplicità MVP; split DB futuro facile |
-| TLS | Cloudflare Origin Certificate | Zero maintenance |
-| Orchestrazione | Docker Compose | Sufficiente per un singolo VPS |
-| Storage / Plugin | Post-MVP | Non critici per il lancio |

tests/fixtures/journey_v2/cases.yaml

@@ -1,19 +1,11 @@
 # Journey V2 eval test cases — Step 4
 #
-# Each case simulates a complete journey session:
-#   1. handle_journey_start is called with directory + data_types
-#   2. handle_journey_message is called for each entry in user_messages
-#   3. Assertions are evaluated on the final reply
-#
-# directory_files: list of {path, content_file} — content_file is relative to data/
+# Only case 4.1 is kept as an automated eval. Cases 4.2–4.5 (multi-turn
+# conversations that expect the LLM to produce a complete AgentConfig)
+# are non-deterministic and tested manually — results tracked in Langfuse.
 #
 # Assertion keys:
 #   expect_question: true → first reply must contain "?"
-#   expect_done: true              → final reply must have done=True
-#   expect_valid_config: true      → agent_config must be parseable as AgentConfig with content_types > 0
-#   expect_content_type_id: <str>  → AgentConfig.content_types must contain an entry with this id
-#   expect_extraction_contains: <str> → first content_type extraction_prompt must contain this word
-#   expect_global_rules: true      → AgentConfig.global_rules must be non-empty
 
 - id: "4.1"
   description: "Journey start explores directory, first reply contains a question"
@@ -25,63 +17,3 @@
   user_messages: []
   score_name: "journey.start"
   expect_question: true
-
-- id: "4.2"
-  description: "Full 3-turn conversation produces a valid AgentConfig JSON"
-  directory: "/test/emails"
-  data_types: ["tasks", "notes", "timelines"]
-  directory_files:
-    - path: "/test/emails/email_backup.html"
-      content_file: "email_action.html"
-  user_messages:
-    - "These are email exports from Outlook in HTML format"
-    - "Create tasks for emails with direct action requests, notes for informational emails"
-    - "Yes, that looks correct. No other rules."
-  score_name: "journey.valid_json"
-  expect_done: true
-  expect_valid_config: true
-
-- id: "4.3"
-  description: "Journey detects email_html content type from directory exploration"
-  directory: "/test/emails"
-  data_types: ["tasks", "notes"]
-  directory_files:
-    - path: "/test/emails/message.html"
-      content_file: "email_action.html"
-  user_messages:
-    - "HTML email backups from my mail client, exported from Outlook"
-    - "Create tasks from emails that contain assignments or direct action items"
-    - "Correct, no other rules needed"
-  score_name: "journey.detect_email"
-  expect_done: true
-  expect_content_type_id: "email_html"
-
-- id: "4.4"
-  description: "Custom user rule (only notes, no tasks) reflected in extraction_prompt"
-  directory: "/test/emails"
-  data_types: ["notes"]
-  directory_files:
-    - path: "/test/emails/email.html"
-      content_file: "email_info.html"
-  user_messages:
-    - "HTML emails from my work inbox"
-    - "Create only notes from all emails — I do not want tasks or timelines to be created"
-    - "Yes, exactly"
-  score_name: "journey.custom_rules"
-  expect_done: true
-  expect_extraction_contains: "note"
-
-- id: "4.5"
-  description: "Global rule (no project = no entity) appears in AgentConfig.global_rules"
-  directory: "/test/emails"
-  data_types: ["tasks", "notes"]
-  directory_files:
-    - path: "/test/emails/email.html"
-      content_file: "email_action.html"
-  user_messages:
-    - "Email backups from Outlook"
-    - "Create tasks from action request emails, notes from informational emails"
-    - "If the email cannot be matched to any project, do not create any entity at all"
-  score_name: "journey.global_rules"
-  expect_done: true
-  expect_global_rules: true

tests/test_agent_runner.py

@@ -28,7 +28,6 @@ from datetime import datetime, timezone
 from unittest.mock import AsyncMock, MagicMock, patch
 
 import pytest
-import pytest_asyncio
 
 from app.core.agent_runner import (
     _extract_items_from_content,
@@ -597,7 +596,7 @@ async def test_run_cloud_agent_provider_fetch_error():
 @pytest.mark.asyncio
 async def test_run_cloud_agent_refreshed_token_persisted():
     """When the provider refreshes its token, the new ciphertext is written to DB."""
-    from app.integrations import EmailMessage, encrypt_token
+    from app.integrations import encrypt_token
     from cryptography.fernet import Fernet as _Fernet
 
     fernet_key = _Fernet.generate_key().decode()
@@ -791,7 +790,6 @@ async def test_trigger_run_local_agent_creates_run_log(client, db_session):
             json={
                 "directory": "/home/user/docs",
                 "what_to_extract": ["task", "note"],
-                "actions_by_type": {"task": ["add", "update"], "note": ["add"]},
                 "batch_interval": "0 */6 * * *",
                 "custom_agent_prompt": "Extract tasks and notes.",
                 "active_agents": 0,

tests/test_agent_runner_v2.py

@@ -40,7 +40,6 @@ from app.core.agent_runner import (
     _format_projects,
     _get_extraction_rules,
     _get_no_match_behavior,
-    _is_overdue,
     run_local_agent,
 )
 from app.core.device_manager import DeviceConnectionManager

tests/test_agent_setup.py

@@ -21,7 +21,6 @@ import time
 import uuid
 from unittest.mock import AsyncMock, patch
 
-import pytest
 from fastapi.testclient import TestClient
 from sqlalchemy.ext.asyncio import AsyncSession
 

tests/test_auth.py

@@ -1,4 +1,4 @@
-"""Tests for auth routes: register, login, refresh, me.
+"""Tests for auth routes: register, login, refresh, me, OAuth social login.
 
 Exercises the full auth lifecycle through the FastAPI TestClient against the
 in-memory SQLite test database seeded by ``conftest.py``.
@@ -7,9 +7,11 @@ in-memory SQLite test database seeded by ``conftest.py``.
 from __future__ import annotations
 
 import time
+from unittest.mock import AsyncMock, patch
 
 from jose import jwt
 
+from app.auth.oauth_providers import GoogleOAuthProvider, OAuthUserInfo
 from app.config.settings import settings
 from tests.conftest import auth_header, TEST_USER_IDS
 
@@ -204,3 +206,153 @@ class TestMe:
         token = jwt.encode(payload, "wrong-secret", algorithm="HS256")
         resp = client.get("/api/v1/auth/me", headers={"Authorization": f"Bearer {token}"})
         assert resp.status_code == 401
+
+
+# ── TestOAuth ─────────────────────────────────────────────────────────
+
+
+class TestOAuth:
+    """GET /auth/oauth/google/authorize and POST /auth/oauth/google/callback."""
+
+    FAKE_PROVIDER_USER_ID = "google-sub-12345"
+    FAKE_EMAIL = "oauth@example.com"
+    FAKE_AVATAR = "https://lh3.googleusercontent.com/photo.jpg"
+
+    def _patch_google(self, monkeypatch) -> None:
+        monkeypatch.setattr(settings, "GOOGLE_AUTH_CLIENT_ID", "fake-client-id")
+        monkeypatch.setattr(settings, "GOOGLE_AUTH_CLIENT_SECRET", "fake-client-secret")
+
+    def _userinfo(
+        self,
+        email: str | None = None,
+        email_verified: bool = True,
+    ) -> OAuthUserInfo:
+        return OAuthUserInfo(
+            provider_user_id=self.FAKE_PROVIDER_USER_ID,
+            email=email or self.FAKE_EMAIL,
+            email_verified=email_verified,
+            avatar_url=self.FAKE_AVATAR,
+            name="OAuth User",
+        )
+
+    def _authorize(self, client) -> str:
+        """Call /authorize and return the fresh state token."""
+        resp = client.get("/api/v1/auth/oauth/google/authorize")
+        assert resp.status_code == 200
+        return resp.json()["state"]
+
+    def _callback(self, client, state: str, userinfo: OAuthUserInfo):
+        """POST /callback with mocked provider exchange_code + get_userinfo."""
+        with (
+            patch.object(
+                GoogleOAuthProvider,
+                "exchange_code",
+                new=AsyncMock(return_value={"access_token": "google-access-tok"}),
+            ),
+            patch.object(
+                GoogleOAuthProvider,
+                "get_userinfo",
+                new=AsyncMock(return_value=userinfo),
+            ),
+        ):
+            return client.post(
+                "/api/v1/auth/oauth/google/callback",
+                json={"code": "auth-code", "state": state},
+            )
+
+    def _decode_sub(self, access_token: str) -> str:
+        return jwt.decode(
+            access_token, settings.JWT_SECRET, algorithms=[settings.JWT_ALGORITHM]
+        )["sub"]
+
+    # -- authorize --
+
+    def test_authorize_returns_url_and_state(self, client, monkeypatch) -> None:
+        self._patch_google(monkeypatch)
+        resp = client.get("/api/v1/auth/oauth/google/authorize")
+        assert resp.status_code == 200
+        data = resp.json()
+        assert "url" in data and "state" in data
+        assert "accounts.google.com" in data["url"]
+        assert len(data["state"]) > 0
+
+    def test_authorize_unconfigured_returns_503(self, client, monkeypatch) -> None:
+        monkeypatch.setattr(settings, "GOOGLE_AUTH_CLIENT_ID", "")
+        monkeypatch.setattr(settings, "GOOGLE_AUTH_CLIENT_SECRET", "")
+        resp = client.get("/api/v1/auth/oauth/google/authorize")
+        assert resp.status_code == 503
+
+    # -- callback --
+
+    def test_callback_state_mismatch_returns_401(self, client, monkeypatch) -> None:
+        self._patch_google(monkeypatch)
+        resp = client.post(
+            "/api/v1/auth/oauth/google/callback",
+            json={"code": "code", "state": "not-a-real-state"},
+        )
+        assert resp.status_code == 401
+
+    def test_callback_creates_new_user(self, client, monkeypatch) -> None:
+        """First-time Google login creates a new user and returns valid tokens."""
+        self._patch_google(monkeypatch)
+        state = self._authorize(client)
+        resp = self._callback(client, state, self._userinfo())
+
+        assert resp.status_code == 200
+        data = resp.json()
+        assert "access_token" in data and "refresh_token" in data
+        payload = jwt.decode(
+            data["access_token"], settings.JWT_SECRET, algorithms=[settings.JWT_ALGORITHM]
+        )
+        assert payload["email"] == self.FAKE_EMAIL
+
+    def test_callback_existing_oauth_link_logs_in(self, client, monkeypatch) -> None:
+        """Second Google login with the same account re-uses the existing user."""
+        self._patch_google(monkeypatch)
+        userinfo = self._userinfo()
+
+        # First login — creates user + oauth_accounts row
+        resp1 = self._callback(client, self._authorize(client), userinfo)
+        assert resp1.status_code == 200
+        sub1 = self._decode_sub(resp1.json()["access_token"])
+
+        # Second login — finds existing oauth_accounts row → same user
+        resp2 = self._callback(client, self._authorize(client), userinfo)
+        assert resp2.status_code == 200
+        sub2 = self._decode_sub(resp2.json()["access_token"])
+
+        assert sub1 == sub2
+
+    def test_callback_email_match_links_account(self, client, monkeypatch) -> None:
+        """Verified Google email matching an existing password user links the accounts."""
+        email = "link-target@example.com"
+        reg_resp = client.post(
+            "/api/v1/auth/register",
+            json={"email": email, "password": "TestPass123!"},
+        )
+        assert reg_resp.status_code == 201
+        orig_sub = self._decode_sub(reg_resp.json()["access_token"])
+
+        self._patch_google(monkeypatch)
+        state = self._authorize(client)
+        resp = self._callback(client, state, self._userinfo(email=email, email_verified=True))
+
+        assert resp.status_code == 200
+        oauth_sub = self._decode_sub(resp.json()["access_token"])
+        # OAuth login must resolve to the same user as the original registration
+        assert orig_sub == oauth_sub
+
+    def test_callback_unverified_email_conflict_returns_409(self, client, monkeypatch) -> None:
+        """Unverified Google email matching an existing account returns 409, not 500."""
+        email = "conflict@example.com"
+        reg_resp = client.post(
+            "/api/v1/auth/register",
+            json={"email": email, "password": "TestPass123!"},
+        )
+        assert reg_resp.status_code == 201
+
+        self._patch_google(monkeypatch)
+        state = self._authorize(client)
+        resp = self._callback(client, state, self._userinfo(email=email, email_verified=False))
+
+        assert resp.status_code == 409

tests/test_backup.py

@@ -1,243 +0,0 @@
-"""Tests for backup routes: upload, download, history, delete.
-
-Exercises the backup lifecycle through the FastAPI TestClient against the
-in-memory SQLite test database and moto-mocked S3 bucket.
-"""
-
-from __future__ import annotations
-
-import hashlib
-
-
-from tests.conftest import auth_header, TEST_USER_IDS
-
-
-# ── Helpers ───────────────────────────────────────────────────────────
-
-_BLOB = b"encrypted-backup-blob-opaque-bytes"
-_CHECKSUM = hashlib.sha256(_BLOB).hexdigest()
-_VERSION = 1
-_TIMESTAMP = 1700000000000  # arbitrary ms timestamp
-
-
-def _backup_headers(tier: str = "power", **overrides) -> dict[str, str]:
-    """Return auth + backup metadata headers."""
-    headers = auth_header(tier)
-    headers["X-Backup-Version"] = str(overrides.get("version", _VERSION))
-    headers["X-Backup-Timestamp"] = str(overrides.get("timestamp", _TIMESTAMP))
-    headers["X-Backup-Checksum"] = overrides.get("checksum", _CHECKSUM)
-    headers["Content-Type"] = "application/octet-stream"
-    return headers
-
-
-def _upload(client, tier="power", **overrides) -> "Response":  # noqa: F821
-    """Upload a backup blob and return the response."""
-    return client.put(
-        "/api/v1/backup",
-        content=overrides.pop("blob", _BLOB),
-        headers=_backup_headers(tier, **overrides),
-    )
-
-
-# ── TestUploadBackup ──────────────────────────────────────────────────
-
-
-class TestUploadBackup:
-    """PUT /api/v1/backup"""
-
-    def test_upload_success(self, client, s3_bucket) -> None:
-        resp = _upload(client, tier="power")
-        assert resp.status_code == 200
-        assert resp.json() == {"ok": True}
-
-    def test_upload_creates_history_entry(self, client, s3_bucket) -> None:
-        _upload(client, tier="power")
-        history = client.get(
-            "/api/v1/backup/history", headers=auth_header("power")
-        ).json()
-        assert len(history) == 1
-        assert history[0]["version"] == _VERSION
-        assert history[0]["timestamp"] == _TIMESTAMP
-        assert history[0]["checksum"] == _CHECKSUM
-
-    def test_upload_bad_checksum(self, client, s3_bucket) -> None:
-        resp = _upload(client, tier="power", checksum="0" * 64)
-        assert resp.status_code == 400
-
-    def test_upload_free_tier_blocked(self, client, s3_bucket) -> None:
-        """Free tier has backup_gb=0 → should return 402."""
-        resp = _upload(client, tier="free")
-        assert resp.status_code == 402
-
-    def test_upload_pro_tier_allowed(self, client, s3_bucket) -> None:
-        """Pro tier has backup_gb=5 → small blob succeeds."""
-        resp = _upload(client, tier="pro")
-        assert resp.status_code == 200
-
-
-# ── TestDownloadBackup ────────────────────────────────────────────────
-
-
-class TestDownloadBackup:
-    """GET /api/v1/backup"""
-
-    def test_download_latest(self, client, s3_bucket) -> None:
-        _upload(client, tier="power")
-        resp = client.get("/api/v1/backup", headers=auth_header("power"))
-        assert resp.status_code == 200
-        assert resp.content == _BLOB
-        assert resp.headers["X-Checksum"] == _CHECKSUM
-        assert resp.headers["X-Backup-Version"] == str(_VERSION)
-
-    def test_download_no_backup_returns_404(self, client, s3_bucket) -> None:
-        resp = client.get("/api/v1/backup", headers=auth_header("power"))
-        assert resp.status_code == 404
-
-    def test_download_if_modified_since_returns_304(self, client, s3_bucket) -> None:
-        """When If-Modified-Since is after the backup timestamp → 304."""
-        _upload(client, tier="power", timestamp=1700000000000)
-        resp = client.get(
-            "/api/v1/backup",
-            headers={
-                **auth_header("power"),
-                "If-Modified-Since": "Thu, 01 Jan 2099 00:00:00 GMT",
-            },
-        )
-        assert resp.status_code == 304
-
-    def test_download_if_modified_since_returns_200(self, client, s3_bucket) -> None:
-        """When If-Modified-Since is before the backup timestamp → serve blob."""
-        _upload(client, tier="power", timestamp=1700000000000)
-        resp = client.get(
-            "/api/v1/backup",
-            headers={
-                **auth_header("power"),
-                "If-Modified-Since": "Thu, 01 Jan 2000 00:00:00 GMT",
-            },
-        )
-        assert resp.status_code == 200
-        assert resp.content == _BLOB
-
-    def test_download_multiple_returns_latest(self, client, s3_bucket) -> None:
-        """When multiple backups exist, GET returns the one with the highest timestamp."""
-        _upload(client, tier="power", timestamp=1000)
-        blob2 = b"second-encrypted-backup"
-        checksum2 = hashlib.sha256(blob2).hexdigest()
-        _upload(client, tier="power", timestamp=2000, blob=blob2, checksum=checksum2)
-        resp = client.get("/api/v1/backup", headers=auth_header("power"))
-        assert resp.status_code == 200
-        assert resp.content == blob2
-
-
-# ── TestBackupHistory ─────────────────────────────────────────────────
-
-
-class TestBackupHistory:
-    """GET /api/v1/backup/history"""
-
-    def test_history_empty(self, client, s3_bucket) -> None:
-        resp = client.get("/api/v1/backup/history", headers=auth_header("power"))
-        assert resp.status_code == 200
-        assert resp.json() == []
-
-    def test_history_returns_entries(self, client, s3_bucket) -> None:
-        _upload(client, tier="power", timestamp=1000)
-        _upload(client, tier="power", timestamp=2000)
-        history = client.get(
-            "/api/v1/backup/history", headers=auth_header("power")
-        ).json()
-        assert len(history) == 2
-        # Ordered by timestamp descending
-        assert history[0]["timestamp"] == 2000
-        assert history[1]["timestamp"] == 1000
-
-    def test_history_isolated_per_user(self, client, s3_bucket) -> None:
-        """One user's backups should not appear in another user's history."""
-        _upload(client, tier="power")
-        resp = client.get("/api/v1/backup/history", headers=auth_header("team"))
-        assert resp.json() == []
-
-
-# ── TestDeleteBackup ──────────────────────────────────────────────────
-
-
-class TestDeleteBackup:
-    """DELETE /api/v1/backup/{backup_id}"""
-
-    def _get_backup_id(self, client, tier="power") -> str:
-        """Upload a backup and return its DB id from history."""
-        _upload(client, tier=tier)
-        client.get(
-            "/api/v1/backup/history", headers=auth_header(tier)
-        ).json()
-        # History returns BackupMetadata schema which doesn't have `id`.
-        # We need to look it up via a different means.
-        # Since there's only 1 backup, find via history length.
-        # Actually the schema doesn't return id — let's verify via re-download.
-        # We'll use a workaround: upload, then list history to confirm it exists,
-        # then try to delete — but we need the id...
-        # Let's check if history includes an id field.
-        # The schema is: version, timestamp, checksum, chunk_count — no id.
-        # We'll need to query the DB directly or use a known ID.
-        # For testing, we'll search history then use the DB.
-        return None  # pragma: no cover — overridden below
-
-    def test_delete_success(self, client, s3_bucket, db_session) -> None:
-        _upload(client, tier="power")
-
-        # Discover the backup_id via direct DB query
-        import asyncio
-        from sqlalchemy import select
-        from app.models import BackupMetadata
-
-        async def _get_id():
-            result = await db_session.execute(
-                select(BackupMetadata.id).where(
-                    BackupMetadata.user_id == TEST_USER_IDS["power"]
-                )
-            )
-            return result.scalar_one()
-
-        backup_id = asyncio.get_event_loop().run_until_complete(_get_id())
-
-        resp = client.delete(
-            f"/api/v1/backup/{backup_id}", headers=auth_header("power")
-        )
-        assert resp.status_code == 200
-        assert resp.json() == {"ok": True}
-
-        # History should now be empty
-        history = client.get(
-            "/api/v1/backup/history", headers=auth_header("power")
-        ).json()
-        assert history == []
-
-    def test_delete_nonexistent(self, client, s3_bucket) -> None:
-        resp = client.delete(
-            "/api/v1/backup/no-such-id", headers=auth_header("power")
-        )
-        assert resp.status_code == 404
-
-    def test_delete_other_users_backup(self, client, s3_bucket, db_session) -> None:
-        """Cannot delete another user's backup (ownership check returns 404)."""
-        _upload(client, tier="power")
-
-        import asyncio
-        from sqlalchemy import select
-        from app.models import BackupMetadata
-
-        async def _get_id():
-            result = await db_session.execute(
-                select(BackupMetadata.id).where(
-                    BackupMetadata.user_id == TEST_USER_IDS["power"]
-                )
-            )
-            return result.scalar_one()
-
-        backup_id = asyncio.get_event_loop().run_until_complete(_get_id())
-
-        # team user tries to delete power user's backup → 404
-        resp = client.delete(
-            f"/api/v1/backup/{backup_id}", headers=auth_header("team")
-        )
-        assert resp.status_code == 404

tests/test_device_ws.py

@@ -18,13 +18,12 @@ from datetime import datetime, timezone
 from unittest.mock import AsyncMock, MagicMock, patch
 
 import pytest
-import pytest_asyncio
 
-from app.core.device_manager import DeviceConnection, DeviceConnectionManager
+from app.core.device_manager import DeviceConnectionManager
 from app.db import get_session
 from app.main import app
 from app.models import AgentRunLog
-from tests.conftest import TEST_USER_IDS, auth_header, make_jwt
+from tests.conftest import TEST_USER_IDS, make_jwt
 
 # ---------------------------------------------------------------------------
 # Helpers

tests/test_integrations.py

@@ -40,11 +40,9 @@ Coverage:
 
 from __future__ import annotations
 
-import asyncio
 import json
-import uuid
 from datetime import datetime, timezone
-from unittest.mock import AsyncMock, MagicMock, Mock, PropertyMock, patch
+from unittest.mock import AsyncMock, MagicMock, PropertyMock, patch
 
 import pytest
 

tests/test_journey_v2.py

@@ -12,16 +12,17 @@ Unit tests (no LLM)
   4.6e  Session not found → done=True, agent_config=None
   4.6f  Nudge uses AGENT_CONFIG_START/END markers (not old PROMPT_TEMPLATE)
 
-Eval tests (real LLM + Langfuse scoring)
------------------------------------------
-Cases are defined in tests/fixtures/journey_v2/cases.yaml.
-Email HTML files live in tests/fixtures/journey_v2/data/.
-Use --journey-dir to point at a custom folder (same structure required).
+Eval test (real LLM + Langfuse scoring)
+----------------------------------------
+  4.1   Journey start explores directory → first reply contains a question
+
+Cases 4.2–4.5 (multi-turn conversations producing a full AgentConfig) are
+non-deterministic and tested manually — results tracked in Langfuse.
 
 Run:
     pytest tests/test_journey_v2.py -v
     pytest tests/test_journey_v2.py -v -k "4_6"          # unit only
-    pytest tests/test_journey_v2.py -v -k "eval"          # LLM evals only
+    pytest tests/test_journey_v2.py -v -k "eval"          # single LLM eval
     pytest tests/test_journey_v2.py -v --journey-dir /p   # custom fixtures
 """
 
@@ -170,57 +171,6 @@ def _evaluate_case(case: dict, reply: dict) -> tuple[float, str]:
         has_q = "?" in reply.get("message", "")
         return (1.0 if has_q else 0.0), f"first_reply_has_question={has_q}"
 
-    if case.get("expect_done") and not reply.get("done"):
-        return 0.0, "expected done=True but journey did not complete"
-
-    agent_config_raw = reply.get("agent_config")
-
-    if case.get("expect_valid_config"):
-        if not agent_config_raw:
-            return 0.0, "agent_config is None"
-        try:
-            parsed = AgentConfig.model_validate_json(agent_config_raw)
-            valid = len(parsed.content_types) > 0
-            return (1.0 if valid else 0.0), f"content_types={len(parsed.content_types)}"
-        except Exception as exc:
-            return 0.0, f"parse error: {exc}"
-
-    if case.get("expect_content_type_id"):
-        expected_id = case["expect_content_type_id"]
-        if not agent_config_raw:
-            return 0.0, "agent_config is None"
-        try:
-            parsed = AgentConfig.model_validate_json(agent_config_raw)
-            ids = [ct.id for ct in parsed.content_types]
-            found = expected_id in ids
-            return (1.0 if found else 0.0), f"content_type_ids={ids}, expected={expected_id}"
-        except Exception as exc:
-            return 0.0, f"parse error: {exc}"
-
-    if case.get("expect_extraction_contains"):
-        keyword = case["expect_extraction_contains"].lower()
-        if not agent_config_raw:
-            return 0.0, "agent_config is None"
-        try:
-            parsed = AgentConfig.model_validate_json(agent_config_raw)
-            if not parsed.content_types:
-                return 0.0, "no content_types in config"
-            prompt = parsed.content_types[0].extraction_prompt.lower()
-            found = keyword in prompt
-            return (1.0 if found else 0.0), f"keyword='{keyword}' in extraction_prompt={found}"
-        except Exception as exc:
-            return 0.0, f"parse error: {exc}"
-
-    if case.get("expect_global_rules"):
-        if not agent_config_raw:
-            return 0.0, "agent_config is None"
-        try:
-            parsed = AgentConfig.model_validate_json(agent_config_raw)
-            has_rules = len(parsed.global_rules) > 0
-            return (1.0 if has_rules else 0.0), f"global_rules={parsed.global_rules}"
-        except Exception as exc:
-            return 0.0, f"parse error: {exc}"
-
     return 1.0, "no specific assertion"
 
 

tests/test_memory_middleware.py

@@ -19,7 +19,7 @@ import pytest_asyncio
 from cryptography.fernet import Fernet
 from sqlalchemy import select
 
-from app.core.memory_middleware import MemoryMiddleware, _PROACTIVE_CONFIDENCE_THRESHOLD
+from app.core.memory_middleware import MemoryMiddleware
 from app.db import get_session
 from app.main import app
 from app.models import (

tests/test_memory_models.py

@@ -7,10 +7,9 @@ column is stored as JSON in tests (SQLite-compatible).
 from __future__ import annotations
 
 import uuid
-from datetime import datetime, timezone
+from datetime import datetime
 
 import pytest
-import pytest_asyncio
 from cryptography.fernet import Fernet
 from sqlalchemy import select
 

tests/test_plugins.py

@@ -1,400 +0,0 @@
-"""Tests for Step 10+12: Plugin Marketplace (DB-backed).
-
-Covers:
-  - PluginRegistry: catalog management, filtering, sorting, install counts (PostgreSQL)
-  - ReviewQueue: pending queue, review decisions, manifest security checklist
-  - RevenueShare: install event recording, earnings aggregation (PostgreSQL)
-  - Route integration: tier gate, list/get/install/uninstall via TestClient
-"""
-
-from __future__ import annotations
-
-import uuid
-
-import pytest
-from sqlalchemy import select
-from sqlalchemy.ext.asyncio import AsyncSession
-
-from app.marketplace.plugin_registry import PluginRegistry
-from app.marketplace.plugin_review import ReviewQueue, validate_manifest
-from app.marketplace.revenue_share import RevenueShare
-from app.models import Plugin, PluginReview as PluginReviewModel, RevenueEvent
-from app.schemas import PluginManifest
-from tests.conftest import TEST_USER_IDS, auth_header
-
-# ---------------------------------------------------------------------------
-# Helpers
-# ---------------------------------------------------------------------------
-
-
-def _fresh_manifest(
-    plugin_id: str | None = None,
-    category: str = "productivity",
-    price_cents: int = 0,
-    permissions: list[str] | None = None,
-) -> PluginManifest:
-    pid = plugin_id or f"plugin-{uuid.uuid4().hex[:8]}"
-    return PluginManifest(
-        id=pid,
-        name=f"Plugin {pid}",
-        description=f"Description for {pid}",
-        version="1.0.0",
-        author="test-author",
-        permissions=permissions or ["read:tasks"],
-        category=category,
-        price_cents=price_cents,
-    )
-
-
-# ---------------------------------------------------------------------------
-# PluginRegistry (DB-backed)
-# ---------------------------------------------------------------------------
-
-
-class TestPluginRegistry:
-    """Each test uses the conftest db_session fixture with a fresh in-memory DB."""
-
-    @pytest.fixture
-    def reg(self) -> PluginRegistry:
-        return PluginRegistry()
-
-    @pytest.mark.asyncio
-    async def test_seed_plugins_are_listed(
-        self, reg: PluginRegistry, db_session: AsyncSession, seed_plugins: list[Plugin]
-    ) -> None:
-        result = await reg.list_plugins(db_session)
-        assert result.total == 3
-        assert all(p.id.startswith("plugin-") for p in result.plugins)
-
-    @pytest.mark.asyncio
-    async def test_list_approved_only(
-        self, reg: PluginRegistry, db_session: AsyncSession, seed_plugins: list[Plugin]
-    ) -> None:
-        manifest = _fresh_manifest()
-        await reg.submit_plugin(db_session, manifest, "plugins/key.zip")
-        result = await reg.list_plugins(db_session)
-        ids = [p.id for p in result.plugins]
-        assert manifest.id not in ids  # still pending
-
-    @pytest.mark.asyncio
-    async def test_list_filter_by_category(
-        self, reg: PluginRegistry, db_session: AsyncSession, seed_plugins: list[Plugin]
-    ) -> None:
-        result = await reg.list_plugins(db_session, category="communication")
-        assert result.total == 1
-        assert result.plugins[0].id == "plugin-slack-notify"
-
-    @pytest.mark.asyncio
-    async def test_list_filter_by_query(
-        self, reg: PluginRegistry, db_session: AsyncSession, seed_plugins: list[Plugin]
-    ) -> None:
-        result = await reg.list_plugins(db_session, query="time")
-        assert result.total == 1
-        assert result.plugins[0].id == "plugin-time-tracker"
-
-    @pytest.mark.asyncio
-    async def test_list_sort_by_installs(
-        self, reg: PluginRegistry, db_session: AsyncSession, seed_plugins: list[Plugin]
-    ) -> None:
-        await reg.record_install(db_session, "plugin-slack-notify")
-        await reg.record_install(db_session, "plugin-slack-notify")
-        result = await reg.list_plugins(db_session, sort="installs")
-        assert result.plugins[0].id == "plugin-slack-notify"
-
-    @pytest.mark.asyncio
-    async def test_get_plugin_found(
-        self, reg: PluginRegistry, db_session: AsyncSession, seed_plugins: list[Plugin]
-    ) -> None:
-        entry = await reg.get_plugin(db_session, "plugin-github-sync")
-        assert entry is not None
-        assert entry["manifest"].id == "plugin-github-sync"
-        assert "install_count" in entry
-
-    @pytest.mark.asyncio
-    async def test_get_plugin_not_found(
-        self, reg: PluginRegistry, db_session: AsyncSession
-    ) -> None:
-        entry = await reg.get_plugin(db_session, "no-such-plugin")
-        assert entry is None
-
-    @pytest.mark.asyncio
-    async def test_submit_sets_pending(
-        self, reg: PluginRegistry, db_session: AsyncSession
-    ) -> None:
-        manifest = _fresh_manifest()
-        plugin_id = await reg.submit_plugin(db_session, manifest, "key.zip")
-        assert plugin_id == manifest.id
-        result = await db_session.execute(select(Plugin).where(Plugin.id == plugin_id))
-        row = result.scalar_one()
-        assert row.status == "pending_review"
-
-    @pytest.mark.asyncio
-    async def test_approve_makes_visible(
-        self, reg: PluginRegistry, db_session: AsyncSession
-    ) -> None:
-        manifest = _fresh_manifest()
-        await reg.submit_plugin(db_session, manifest, "key.zip")
-        await reg.approve_plugin(db_session, manifest.id)
-        result = await reg.list_plugins(db_session)
-        assert manifest.id in [p.id for p in result.plugins]
-
-    @pytest.mark.asyncio
-    async def test_reject_stores_reason(
-        self, reg: PluginRegistry, db_session: AsyncSession
-    ) -> None:
-        manifest = _fresh_manifest()
-        await reg.submit_plugin(db_session, manifest, "key.zip")
-        await reg.reject_plugin(db_session, manifest.id, reason="Unsafe permissions")
-        result = await db_session.execute(select(Plugin).where(Plugin.id == manifest.id))
-        row = result.scalar_one()
-        assert row.status == "rejected"
-        assert row.rejection_reason == "Unsafe permissions"
-        listed = await reg.list_plugins(db_session)
-        assert manifest.id not in [p.id for p in listed.plugins]
-
-    @pytest.mark.asyncio
-    async def test_approve_unknown_raises_key_error(
-        self, reg: PluginRegistry, db_session: AsyncSession
-    ) -> None:
-        with pytest.raises(KeyError):
-            await reg.approve_plugin(db_session, "ghost-plugin")
-
-    @pytest.mark.asyncio
-    async def test_record_install_increments_count(
-        self, reg: PluginRegistry, db_session: AsyncSession, seed_plugins: list[Plugin]
-    ) -> None:
-        await reg.record_install(db_session, "plugin-github-sync")
-        entry = await reg.get_plugin(db_session, "plugin-github-sync")
-        assert entry is not None
-        assert entry["install_count"] == 1
-
-    @pytest.mark.asyncio
-    async def test_record_uninstall_decrements_count(
-        self, reg: PluginRegistry, db_session: AsyncSession, seed_plugins: list[Plugin]
-    ) -> None:
-        await reg.record_install(db_session, "plugin-github-sync")
-        await reg.record_install(db_session, "plugin-github-sync")
-        await reg.record_uninstall(db_session, "plugin-github-sync")
-        entry = await reg.get_plugin(db_session, "plugin-github-sync")
-        assert entry is not None
-        assert entry["install_count"] == 1
-
-    @pytest.mark.asyncio
-    async def test_record_uninstall_floors_at_zero(
-        self, reg: PluginRegistry, db_session: AsyncSession, seed_plugins: list[Plugin]
-    ) -> None:
-        await reg.record_uninstall(db_session, "plugin-github-sync")
-        entry = await reg.get_plugin(db_session, "plugin-github-sync")
-        assert entry is not None
-        assert entry["install_count"] == 0
-
-
-# ---------------------------------------------------------------------------
-# ReviewQueue (DB-backed)
-# ---------------------------------------------------------------------------
-
-
-class TestReviewQueue:
-    @pytest.fixture
-    def reg(self) -> PluginRegistry:
-        return PluginRegistry()
-
-    @pytest.fixture
-    def queue(self) -> ReviewQueue:
-        return ReviewQueue()
-
-    @pytest.mark.asyncio
-    async def test_get_pending_returns_submitted_plugins(
-        self, reg: PluginRegistry, queue: ReviewQueue, db_session: AsyncSession
-    ) -> None:
-        manifest = _fresh_manifest()
-        await reg.submit_plugin(db_session, manifest, "key.zip")
-        pending = await queue.get_pending(db_session)
-        assert any(p["plugin_id"] == manifest.id for p in pending)
-
-    @pytest.mark.asyncio
-    async def test_submit_review_approved(
-        self, reg: PluginRegistry, queue: ReviewQueue, db_session: AsyncSession
-    ) -> None:
-        manifest = _fresh_manifest()
-        await reg.submit_plugin(db_session, manifest, "key.zip")
-        await queue.submit_review(db_session, manifest.id, TEST_USER_IDS["power"], "approved", "Looks good")
-        result = await db_session.execute(select(Plugin).where(Plugin.id == manifest.id))
-        row = result.scalar_one()
-        assert row.status == "approved"
-        # Check review row was persisted
-        review_result = await db_session.execute(
-            select(PluginReviewModel).where(PluginReviewModel.plugin_id == manifest.id)
-        )
-        review = review_result.scalar_one()
-        assert review.decision == "approved"
-
-    @pytest.mark.asyncio
-    async def test_submit_review_rejected(
-        self, reg: PluginRegistry, queue: ReviewQueue, db_session: AsyncSession
-    ) -> None:
-        manifest = _fresh_manifest()
-        await reg.submit_plugin(db_session, manifest, "key.zip")
-        await queue.submit_review(
-            db_session, manifest.id, TEST_USER_IDS["power"], "rejected", "Bad permissions"
-        )
-        result = await db_session.execute(select(Plugin).where(Plugin.id == manifest.id))
-        row = result.scalar_one()
-        assert row.status == "rejected"
-
-    def test_validate_manifest_ok(self) -> None:
-        manifest = _fresh_manifest(permissions=["read:tasks", "write:notes"])
-        validate_manifest(manifest)  # should not raise
-
-    def test_validate_manifest_unknown_permission(self) -> None:
-        manifest = _fresh_manifest(permissions=["read:tasks", "read:secrets"])
-        with pytest.raises(ValueError, match="Unknown permission"):
-            validate_manifest(manifest)
-
-    def test_validate_manifest_invalid_id_format(self) -> None:
-        manifest = _fresh_manifest(plugin_id="Plugin_ID_Invalid")
-        with pytest.raises(ValueError, match="Invalid plugin id format"):
-            validate_manifest(manifest)
-
-    def test_validate_manifest_id_with_uppercase(self) -> None:
-        manifest = _fresh_manifest(plugin_id="UpperCase")
-        with pytest.raises(ValueError, match="Invalid plugin id format"):
-            validate_manifest(manifest)
-
-
-# ---------------------------------------------------------------------------
-# RevenueShare (DB-backed)
-# ---------------------------------------------------------------------------
-
-
-class TestRevenueShare:
-    @pytest.fixture
-    def rs(self) -> RevenueShare:
-        return RevenueShare()
-
-    @pytest.mark.asyncio
-    async def test_record_install_free_plugin(
-        self, rs: RevenueShare, db_session: AsyncSession, seed_plugins: list[Plugin]
-    ) -> None:
-        await rs.record_install(db_session, "plugin-github-sync", TEST_USER_IDS["power"], amount_cents=0)
-        result = await db_session.execute(
-            select(RevenueEvent).where(RevenueEvent.plugin_id == "plugin-github-sync")
-        )
-        event = result.scalar_one()
-        assert event.developer_share_cents == 0
-
-    @pytest.mark.asyncio
-    async def test_record_install_paid_plugin_no_stripe(
-        self, rs: RevenueShare, db_session: AsyncSession, seed_plugins: list[Plugin]
-    ) -> None:
-        await rs.record_install(
-            db_session, "plugin-slack-notify", TEST_USER_IDS["pro"], amount_cents=499
-        )
-        result = await db_session.execute(
-            select(RevenueEvent).where(RevenueEvent.plugin_id == "plugin-slack-notify")
-        )
-        event = result.scalar_one()
-        assert event.amount_cents == 499
-        assert event.developer_share_cents == int(499 * 0.70)
-
-    @pytest.mark.asyncio
-    async def test_record_install_increments_registry_count(
-        self, rs: RevenueShare, db_session: AsyncSession, seed_plugins: list[Plugin]
-    ) -> None:
-        reg = PluginRegistry()
-        await rs.record_install(db_session, "plugin-github-sync", TEST_USER_IDS["power"], amount_cents=0)
-        entry = await reg.get_plugin(db_session, "plugin-github-sync")
-        assert entry is not None
-        assert entry["install_count"] == 1
-
-    @pytest.mark.asyncio
-    async def test_get_earnings_empty(
-        self, rs: RevenueShare, db_session: AsyncSession
-    ) -> None:
-        result = await rs.get_earnings(db_session, "unknown-dev")
-        assert result["total_installs"] == 0
-        assert result["total_revenue_cents"] == 0
-        assert result["developer_share_cents"] == 0
-
-    @pytest.mark.asyncio
-    async def test_get_earnings_aggregates(
-        self, rs: RevenueShare, db_session: AsyncSession, seed_plugins: list[Plugin]
-    ) -> None:
-        await rs.record_install(db_session, "plugin-slack-notify", TEST_USER_IDS["power"], amount_cents=499)
-        await rs.record_install(db_session, "plugin-slack-notify", TEST_USER_IDS["pro"], amount_cents=499)
-        result = await rs.get_earnings(db_session, "Adiuva")
-        assert result["total_installs"] == 2
-        assert result["total_revenue_cents"] == 998
-        assert result["developer_share_cents"] == int(499 * 0.70) * 2
-
-
-# ---------------------------------------------------------------------------
-# Route integration tests
-# ---------------------------------------------------------------------------
-
-
-class TestPluginRoutes:
-    def test_list_plugins_requires_power_tier(self, client, seed_plugins) -> None:
-        resp = client.get("/api/v1/plugins", headers=auth_header("free"))
-        assert resp.status_code == 403
-
-    def test_list_plugins_pro_tier_blocked(self, client, seed_plugins) -> None:
-        resp = client.get("/api/v1/plugins", headers=auth_header("pro"))
-        assert resp.status_code == 403
-
-    def test_list_plugins_power_tier_ok(self, client, seed_plugins) -> None:
-        resp = client.get("/api/v1/plugins", headers=auth_header("power"))
-        assert resp.status_code == 200
-        data = resp.json()
-        assert "plugins" in data
-        assert data["total"] == 3
-
-    def test_list_plugins_team_tier_ok(self, client, seed_plugins) -> None:
-        resp = client.get("/api/v1/plugins", headers=auth_header("team"))
-        assert resp.status_code == 200
-
-    def test_get_plugin_found(self, client, seed_plugins) -> None:
-        resp = client.get("/api/v1/plugins/plugin-github-sync", headers=auth_header())
-        assert resp.status_code == 200
-        data = resp.json()
-        assert data["plugin"]["id"] == "plugin-github-sync"
-        assert "install_count" in data
-
-    def test_get_plugin_not_found(self, client, seed_plugins) -> None:
-        resp = client.get("/api/v1/plugins/no-such-plugin", headers=auth_header())
-        assert resp.status_code == 404
-
-    def test_install_plugin_free(self, client, seed_plugins) -> None:
-        resp = client.post(
-            "/api/v1/plugins/plugin-github-sync/install",
-            json={"plugin_id": "plugin-github-sync"},
-            headers=auth_header(),
-        )
-        assert resp.status_code == 200
-        data = resp.json()
-        assert data["ok"] is True
-        assert "download_url" in data
-
-    def test_install_plugin_not_found(self, client, seed_plugins) -> None:
-        resp = client.post(
-            "/api/v1/plugins/ghost/install",
-            json={"plugin_id": "ghost"},
-            headers=auth_header(),
-        )
-        assert resp.status_code == 404
-
-    def test_uninstall_plugin_ok(self, client, seed_plugins) -> None:
-        resp = client.delete(
-            "/api/v1/plugins/plugin-github-sync/install",
-            headers=auth_header(),
-        )
-        assert resp.status_code == 200
-        assert resp.json()["ok"] is True
-
-    def test_install_requires_power_tier(self, client, seed_plugins) -> None:
-        resp = client.post(
-            "/api/v1/plugins/plugin-github-sync/install",
-            json={"plugin_id": "plugin-github-sync"},
-            headers=auth_header("free"),
-        )
-        assert resp.status_code == 403

tests/test_preprocessors.py

@@ -12,7 +12,6 @@ from __future__ import annotations
 import re
 from pathlib import Path
 
-import pytest
 import yaml
 
 from app.core.preprocessors import detect_content_type, preprocess

tests/test_storage.py

@@ -1,562 +0,0 @@
-"""Tests for the storage layer: encryption, BlobStore, VectorStore, and storage routes."""
-
-from __future__ import annotations
-
-import base64
-import hashlib
-from unittest.mock import MagicMock, patch
-
-import boto3
-import pytest
-from botocore.exceptions import ClientError
-
-from app.storage.encryption import reject_if_tampered, verify_checksum
-from app.storage.blob_store import BlobStore
-from app.storage.vector_store import VectorStore, _blob_to_vector
-from app.schemas import VectorItem, VectorSearchResult
-from tests.conftest import auth_header, S3_TEST_BUCKET
-
-
-# ── Helpers ───────────────────────────────────────────────────────────
-
-_BLOB = b"encrypted-payload-opaque-to-server"
-_CHECKSUM = hashlib.sha256(_BLOB).hexdigest()
-_BUCKET = S3_TEST_BUCKET
-_REGION = "us-east-1"
-
-
-def _pinecone_mock():
-    """Return a mock Pinecone index with realistic return shapes."""
-    mock_index = MagicMock()
-    mock_index.query.return_value = {
-        "matches": [
-            {
-                "id": "v1",
-                "score": 0.95,
-                "metadata": {
-                    "blob": base64.b64encode(b"result-blob").decode(),
-                    "checksum": hashlib.sha256(b"result-blob").hexdigest(),
-                    "user_id": "u1",
-                },
-            }
-        ]
-    }
-    mock_pc = MagicMock()
-    mock_pc.return_value.Index.return_value = mock_index
-    return mock_pc, mock_index
-
-
-# ── TestEncryption ────────────────────────────────────────────────────
-
-
-class TestEncryption:
-    def test_verify_checksum_correct(self) -> None:
-        assert verify_checksum(_BLOB, _CHECKSUM) is True
-
-    def test_verify_checksum_wrong(self) -> None:
-        assert verify_checksum(_BLOB, "0" * 64) is False
-
-    def test_verify_checksum_empty_checksum(self) -> None:
-        assert verify_checksum(_BLOB, "") is False
-
-    def test_verify_checksum_empty_blob(self) -> None:
-        expected = hashlib.sha256(b"").hexdigest()
-        assert verify_checksum(b"", expected) is True
-
-    def test_verify_checksum_tampered_blob(self) -> None:
-        tampered = _BLOB + b"\x00"
-        assert verify_checksum(tampered, _CHECKSUM) is False
-
-    def test_reject_if_tampered_passes_when_valid(self) -> None:
-        # Should not raise
-        reject_if_tampered(_BLOB, _CHECKSUM)
-
-    def test_reject_if_tampered_raises_400_on_mismatch(self) -> None:
-        from fastapi import HTTPException
-
-        with pytest.raises(HTTPException) as exc_info:
-            reject_if_tampered(_BLOB, "bad" * 20)
-        assert exc_info.value.status_code == 400
-
-    def test_reject_if_tampered_detail_mentions_checksum(self) -> None:
-        from fastapi import HTTPException
-
-        with pytest.raises(HTTPException) as exc_info:
-            reject_if_tampered(_BLOB, "bad" * 20)
-        assert "checksum" in exc_info.value.detail.lower()
-
-    def test_checksum_is_sha256_hex(self) -> None:
-        cs = hashlib.sha256(_BLOB).hexdigest()
-        assert len(cs) == 64
-        assert all(c in "0123456789abcdef" for c in cs)
-
-
-# ── TestBlobStore ─────────────────────────────────────────────────────
-
-
-class TestBlobStore:
-    @pytest.mark.asyncio
-    async def test_upload_returns_correct_key(self, s3_bucket: str) -> None:
-        store = BlobStore()
-        key = await store.upload("u1", "tasks", "r1", _BLOB, _CHECKSUM)
-        assert key == "u1/tasks/r1"
-
-    @pytest.mark.asyncio
-    async def test_upload_object_exists_in_s3(self, s3_bucket: str) -> None:
-        store = BlobStore()
-        await store.upload("u1", "tasks", "r1", _BLOB, _CHECKSUM)
-        # Verify by downloading — no exception means object exists
-        retrieved = await store.download("u1", "u1/tasks/r1")
-        assert retrieved == _BLOB
-
-    @pytest.mark.asyncio
-    async def test_download_retrieves_same_bytes(self, s3_bucket: str) -> None:
-        store = BlobStore()
-        await store.upload("u1", "notes", "n1", b"note-data", hashlib.sha256(b"note-data").hexdigest())
-        result = await store.download("u1", "u1/notes/n1")
-        assert result == b"note-data"
-
-    @pytest.mark.asyncio
-    async def test_delete_removes_object(self, s3_bucket: str) -> None:
-        store = BlobStore()
-        await store.upload("u1", "tasks", "r1", _BLOB, _CHECKSUM)
-        await store.delete("u1", "u1/tasks/r1")
-        with pytest.raises(ClientError) as exc_info:
-            await store.download("u1", "u1/tasks/r1")
-        assert exc_info.value.response["Error"]["Code"] == "NoSuchKey"
-
-    @pytest.mark.asyncio
-    async def test_delete_is_idempotent(self, s3_bucket: str) -> None:
-        store = BlobStore()
-        # Delete a key that never existed — should not raise
-        await store.delete("u1", "u1/tasks/nonexistent")
-
-    @pytest.mark.asyncio
-    async def test_list_keys_returns_correct_keys(self, s3_bucket: str) -> None:
-        store = BlobStore()
-        await store.upload("u1", "tasks", "r1", _BLOB, _CHECKSUM)
-        await store.upload("u1", "tasks", "r2", _BLOB, _CHECKSUM)
-        keys = await store.list_keys("u1", "tasks")
-        assert set(keys) == {"u1/tasks/r1", "u1/tasks/r2"}
-
-    @pytest.mark.asyncio
-    async def test_list_keys_scoped_to_table(self, s3_bucket: str) -> None:
-        store = BlobStore()
-        await store.upload("u1", "tasks", "r1", _BLOB, _CHECKSUM)
-        await store.upload("u1", "notes", "n1", _BLOB, _CHECKSUM)
-        keys = await store.list_keys("u1", "tasks")
-        assert "u1/notes/n1" not in keys
-        assert "u1/tasks/r1" in keys
-
-    @pytest.mark.asyncio
-    async def test_list_keys_no_cross_user_leakage(self, s3_bucket: str) -> None:
-        store = BlobStore()
-        await store.upload("u1", "tasks", "r1", _BLOB, _CHECKSUM)
-        await store.upload("u2", "tasks", "r1", _BLOB, _CHECKSUM)
-        keys_u1 = await store.list_keys("u1", "tasks")
-        assert "u2/tasks/r1" not in keys_u1
-
-    @pytest.mark.asyncio
-    async def test_list_keys_empty_table(self, s3_bucket: str) -> None:
-        store = BlobStore()
-        keys = await store.list_keys("u1", "tasks")
-        assert keys == []
-
-    @pytest.mark.asyncio
-    async def test_upload_uses_sse_s3_encryption(self, s3_bucket: str) -> None:
-        store = BlobStore()
-        await store.upload("u1", "tasks", "r1", _BLOB, _CHECKSUM)
-        # Verify S3 metadata was set — check via head_object
-        with patch("app.storage.blob_store.settings") as mock_settings:
-            mock_settings.S3_BUCKET = _BUCKET
-            mock_settings.S3_REGION = _REGION
-            mock_settings.AWS_ACCESS_KEY_ID = "testing"
-            mock_settings.AWS_SECRET_ACCESS_KEY = "testing"
-            client = boto3.client("s3", region_name=_REGION)
-            response = client.head_object(Bucket=_BUCKET, Key="u1/tasks/r1")
-            assert response.get("ServerSideEncryption") == "AES256"
-
-    @pytest.mark.asyncio
-    async def test_upload_stores_checksum_in_metadata(self, s3_bucket: str) -> None:
-        store = BlobStore()
-        await store.upload("u1", "tasks", "r1", _BLOB, _CHECKSUM)
-        client = boto3.client("s3", region_name=_REGION)
-        response = client.head_object(Bucket=_BUCKET, Key="u1/tasks/r1")
-        assert response["Metadata"]["checksum"] == _CHECKSUM
-
-
-# ── _blob_to_vector helper ────────────────────────────────────────────
-
-
-class TestBlobToVector:
-    def test_returns_32_floats(self) -> None:
-        v = _blob_to_vector(b"test")
-        assert len(v) == 32
-
-    def test_all_values_in_range(self) -> None:
-        v = _blob_to_vector(b"test")
-        assert all(-1.0 <= x <= 1.0 for x in v)
-
-    def test_deterministic(self) -> None:
-        assert _blob_to_vector(b"same") == _blob_to_vector(b"same")
-
-    def test_different_blobs_different_vectors(self) -> None:
-        assert _blob_to_vector(b"aaa") != _blob_to_vector(b"bbb")
-
-
-# ── TestVectorStorePinecone ───────────────────────────────────────────
-
-
-class TestVectorStorePinecone:
-    def _store(self) -> VectorStore:
-        store = VectorStore()
-        store._use_pinecone = lambda: True  # type: ignore[method-assign]
-        return store
-
-    @pytest.mark.asyncio
-    async def test_upsert_calls_index_upsert(self) -> None:
-        mock_pc, mock_index = _pinecone_mock()
-        with patch("app.storage.vector_store.Pinecone", mock_pc):
-            store = self._store()
-            items = [VectorItem(id="v1", blob=b"enc-blob", checksum=hashlib.sha256(b"enc-blob").hexdigest())]
-            await store.upsert("u1", items)
-        mock_index.upsert.assert_called_once()
-        call_kwargs = mock_index.upsert.call_args[1]
-        assert call_kwargs.get("namespace") == "u1"
-
-    @pytest.mark.asyncio
-    async def test_upsert_encodes_blob_as_base64_in_metadata(self) -> None:
-        mock_pc, mock_index = _pinecone_mock()
-        with patch("app.storage.vector_store.Pinecone", mock_pc):
-            store = self._store()
-            items = [VectorItem(id="v1", blob=b"secret", checksum=hashlib.sha256(b"secret").hexdigest())]
-            await store.upsert("u1", items)
-        vectors_arg = mock_index.upsert.call_args[1]["vectors"]
-        assert vectors_arg[0]["metadata"]["blob"] == base64.b64encode(b"secret").decode()
-
-    @pytest.mark.asyncio
-    async def test_search_calls_index_query(self) -> None:
-        mock_pc, mock_index = _pinecone_mock()
-        with patch("app.storage.vector_store.Pinecone", mock_pc):
-            store = self._store()
-            await store.search("u1", b"query-blob", top_k=5)
-        mock_index.query.assert_called_once()
-        query_kwargs = mock_index.query.call_args[1]
-        assert query_kwargs.get("namespace") == "u1"
-        assert query_kwargs.get("top_k") == 5
-        assert query_kwargs.get("include_metadata") is True
-
-    @pytest.mark.asyncio
-    async def test_search_returns_vector_search_results(self) -> None:
-        mock_pc, mock_index = _pinecone_mock()
-        with patch("app.storage.vector_store.Pinecone", mock_pc):
-            store = self._store()
-            results = await store.search("u1", b"query", top_k=10)
-        assert len(results) == 1
-        assert isinstance(results[0], VectorSearchResult)
-        assert results[0].id == "v1"
-        assert results[0].score == 0.95
-        assert results[0].blob == b"result-blob"
-
-    @pytest.mark.asyncio
-    async def test_search_uses_derived_query_vector(self) -> None:
-        mock_pc, mock_index = _pinecone_mock()
-        with patch("app.storage.vector_store.Pinecone", mock_pc):
-            store = self._store()
-            await store.search("u1", b"query-blob", top_k=3)
-        expected_vector = _blob_to_vector(b"query-blob")
-        actual_vector = mock_index.query.call_args[1].get("vector")
-        assert actual_vector == expected_vector
-
-    @pytest.mark.asyncio
-    async def test_delete_calls_index_delete(self) -> None:
-        mock_pc, mock_index = _pinecone_mock()
-        with patch("app.storage.vector_store.Pinecone", mock_pc):
-            store = self._store()
-            await store.delete("u1", ["v1", "v2"])
-        mock_index.delete.assert_called_once()
-        delete_kwargs = mock_index.delete.call_args[1]
-        assert delete_kwargs.get("namespace") == "u1"
-        assert set(delete_kwargs.get("ids", [])) == {"v1", "v2"}
-
-
-# ── TestVectorStoreQdrant ─────────────────────────────────────────────
-
-
-class TestVectorStoreQdrant:
-    def _store(self) -> VectorStore:
-        store = VectorStore()
-        store._use_pinecone = lambda: False  # type: ignore[method-assign]
-        return store
-
-    def _qdrant_mock(self) -> MagicMock:
-        mock_hit = MagicMock()
-        mock_hit.id = "v1"
-        mock_hit.score = 0.88
-        mock_hit.payload = {
-            "blob": base64.b64encode(b"qdrant-result").decode(),
-            "user_id": "u1",
-        }
-        mock_client = MagicMock()
-        mock_client.search.return_value = [mock_hit]
-        return mock_client
-
-    @pytest.mark.asyncio
-    async def test_upsert_calls_client_upsert(self) -> None:
-        mock_client = MagicMock()
-        with patch("app.storage.vector_store.QdrantClient", return_value=mock_client):
-            store = self._store()
-            items = [VectorItem(id="v1", blob=b"enc", checksum=hashlib.sha256(b"enc").hexdigest())]
-            await store.upsert("u1", items)
-        mock_client.upsert.assert_called_once()
-
-    @pytest.mark.asyncio
-    async def test_upsert_uses_correct_collection(self) -> None:
-        mock_client = MagicMock()
-        with patch("app.storage.vector_store.QdrantClient", return_value=mock_client):
-            store = self._store()
-            items = [VectorItem(id="v1", blob=b"enc", checksum=hashlib.sha256(b"enc").hexdigest())]
-            await store.upsert("u1", items)
-        call_kwargs = mock_client.upsert.call_args[1]
-        assert call_kwargs["collection_name"] == "adiuva_vectors"
-
-    @pytest.mark.asyncio
-    async def test_search_calls_client_search(self) -> None:
-        mock_client = self._qdrant_mock()
-        with patch("app.storage.vector_store.QdrantClient", return_value=mock_client):
-            store = self._store()
-            await store.search("u1", b"query", top_k=5)
-        mock_client.search.assert_called_once()
-
-    @pytest.mark.asyncio
-    async def test_search_passes_limit(self) -> None:
-        mock_client = self._qdrant_mock()
-        with patch("app.storage.vector_store.QdrantClient", return_value=mock_client):
-            store = self._store()
-            await store.search("u1", b"query", top_k=7)
-        call_kwargs = mock_client.search.call_args[1]
-        assert call_kwargs.get("limit") == 7
-
-    @pytest.mark.asyncio
-    async def test_search_returns_vector_search_results(self) -> None:
-        mock_client = self._qdrant_mock()
-        with patch("app.storage.vector_store.QdrantClient", return_value=mock_client):
-            store = self._store()
-            results = await store.search("u1", b"query", top_k=5)
-        assert len(results) == 1
-        assert isinstance(results[0], VectorSearchResult)
-        assert results[0].id == "v1"
-        assert results[0].score == 0.88
-        assert results[0].blob == b"qdrant-result"
-
-    @pytest.mark.asyncio
-    async def test_delete_calls_client_delete(self) -> None:
-        mock_client = MagicMock()
-        with patch("app.storage.vector_store.QdrantClient", return_value=mock_client):
-            store = self._store()
-            await store.delete("u1", ["v1", "v2"])
-        mock_client.delete.assert_called_once()
-
-    @pytest.mark.asyncio
-    async def test_delete_uses_correct_collection(self) -> None:
-        mock_client = MagicMock()
-        with patch("app.storage.vector_store.QdrantClient", return_value=mock_client):
-            store = self._store()
-            await store.delete("u1", ["v1"])
-        call_kwargs = mock_client.delete.call_args[1]
-        assert call_kwargs["collection_name"] == "adiuva_vectors"
-
-
-# ── TestStorageRoutes (integration) ───────────────────────────────────
-
-
-class TestStorageRoutes:
-    """Integration tests for POST/GET/PUT/DELETE /api/v1/storage/records.
-
-    Pydantic v2 converts JSON string → bytes via ``str.encode('utf-8')``.
-    So "hello" in JSON becomes ``b"hello"`` on the server.  We use plain
-    ASCII strings as blob values and compute checksums accordingly.
-    """
-
-    _BLOB_STR = "encrypted-payload-opaque-to-server"
-    _BLOB_BYTES = _BLOB_STR.encode()
-    _BLOB_CHECKSUM = hashlib.sha256(_BLOB_BYTES).hexdigest()
-
-    @classmethod
-    def _create_payload(cls, blob_str: str | None = None) -> dict:
-        blob_str = blob_str or cls._BLOB_STR
-        checksum = hashlib.sha256(blob_str.encode()).hexdigest()
-        return {
-            "table": "tasks",
-            "blob": blob_str,
-            "checksum": checksum,
-        }
-
-    def _create_record(self, client, tier="power", blob_str=None):
-        payload = self._create_payload(blob_str)
-        return client.post(
-            "/api/v1/storage/records",
-            json=payload,
-            headers=auth_header(tier),
-        )
-
-    # ── Create ────────────────────────────────────────────────────────
-
-    def test_create_record(self, client, s3_bucket) -> None:
-        resp = self._create_record(client)
-        assert resp.status_code == 201
-        data = resp.json()
-        assert "id" in data
-        assert "created_at" in data
-
-    def test_create_record_bad_checksum(self, client, s3_bucket) -> None:
-        payload = {
-            "table": "tasks",
-            "blob": self._BLOB_STR,
-            "checksum": "0" * 64,
-        }
-        resp = client.post(
-            "/api/v1/storage/records",
-            json=payload,
-            headers=auth_header("power"),
-        )
-        assert resp.status_code == 400
-
-    def test_create_record_free_tier_blocked(self, client, s3_bucket) -> None:
-        """Free tier has cloud_storage_gb=0 → 402."""
-        resp = self._create_record(client, tier="free")
-        assert resp.status_code == 402
-
-    def test_create_record_pro_tier_allowed(self, client, s3_bucket) -> None:
-        """Pro tier has cloud_storage_gb=5 → succeeds for small blob."""
-        resp = self._create_record(client, tier="pro")
-        assert resp.status_code == 201
-
-    # ── List ──────────────────────────────────────────────────────────
-
-    def test_list_records(self, client, s3_bucket) -> None:
-        self._create_record(client)
-        self._create_record(client, blob_str="second-blob")
-        resp = client.get(
-            "/api/v1/storage/records",
-            headers=auth_header("power"),
-        )
-        assert resp.status_code == 200
-        data = resp.json()
-        assert len(data) == 2
-        # Each entry has metadata, no blob bytes
-        for item in data:
-            assert "id" in item
-            assert "table" in item
-            assert "checksum" in item
-            assert "blob" not in item
-
-    def test_list_records_filter_by_table(self, client, s3_bucket) -> None:
-        self._create_record(client)
-        # Create in a different table
-        note_blob = "note-blob"
-        payload = {
-            "table": "notes",
-            "blob": note_blob,
-            "checksum": hashlib.sha256(note_blob.encode()).hexdigest(),
-        }
-        client.post(
-            "/api/v1/storage/records",
-            json=payload,
-            headers=auth_header("power"),
-        )
-        resp = client.get(
-            "/api/v1/storage/records?table=notes",
-            headers=auth_header("power"),
-        )
-        assert resp.status_code == 200
-        data = resp.json()
-        assert len(data) == 1
-        assert data[0]["table"] == "notes"
-
-    def test_list_records_isolated_per_user(self, client, s3_bucket) -> None:
-        """One user's records should not appear in another user's list."""
-        self._create_record(client, tier="power")
-        resp = client.get(
-            "/api/v1/storage/records",
-            headers=auth_header("team"),
-        )
-        assert resp.json() == []
-
-    # ── Download ──────────────────────────────────────────────────────
-
-    def test_download_record(self, client, s3_bucket) -> None:
-        create_resp = self._create_record(client)
-        record_id = create_resp.json()["id"]
-        resp = client.get(
-            f"/api/v1/storage/records/{record_id}",
-            headers=auth_header("power"),
-        )
-        assert resp.status_code == 200
-        assert resp.content == self._BLOB_BYTES
-        assert resp.headers["X-Checksum"] == self._BLOB_CHECKSUM
-
-    def test_download_record_not_found(self, client, s3_bucket) -> None:
-        resp = client.get(
-            "/api/v1/storage/records/nonexistent-id",
-            headers=auth_header("power"),
-        )
-        assert resp.status_code == 404
-
-    # ── Update ────────────────────────────────────────────────────────
-
-    def test_update_record(self, client, s3_bucket) -> None:
-        create_resp = self._create_record(client)
-        record_id = create_resp.json()["id"]
-        new_blob_str = "updated-encrypted-payload"
-        new_checksum = hashlib.sha256(new_blob_str.encode()).hexdigest()
-        resp = client.put(
-            f"/api/v1/storage/records/{record_id}",
-            json={"blob": new_blob_str, "checksum": new_checksum},
-            headers=auth_header("power"),
-        )
-        assert resp.status_code == 200
-        assert resp.json() == {"ok": True}
-
-        # Verify download returns the updated blob
-        dl = client.get(
-            f"/api/v1/storage/records/{record_id}",
-            headers=auth_header("power"),
-        )
-        assert dl.content == new_blob_str.encode()
-
-    def test_update_record_bad_checksum(self, client, s3_bucket) -> None:
-        create_resp = self._create_record(client)
-        record_id = create_resp.json()["id"]
-        resp = client.put(
-            f"/api/v1/storage/records/{record_id}",
-            json={"blob": "some-data", "checksum": "0" * 64},
-            headers=auth_header("power"),
-        )
-        assert resp.status_code == 400
-
-    # ── Delete ────────────────────────────────────────────────────────
-
-    def test_delete_record(self, client, s3_bucket) -> None:
-        create_resp = self._create_record(client)
-        record_id = create_resp.json()["id"]
-        resp = client.delete(
-            f"/api/v1/storage/records/{record_id}",
-            headers=auth_header("power"),
-        )
-        assert resp.status_code == 200
-        assert resp.json() == {"ok": True}
-
-        # Subsequent GET should return 404
-        dl = client.get(
-            f"/api/v1/storage/records/{record_id}",
-            headers=auth_header("power"),
-        )
-        assert dl.status_code == 404
-
-    def test_delete_record_not_found(self, client, s3_bucket) -> None:
-        resp = client.delete(
-            "/api/v1/storage/records/nonexistent",
-            headers=auth_header("power"),
-        )
-        assert resp.status_code == 404