From 1af765a6aad7fd83cbc2383ed472001609b9e66b Mon Sep 17 00:00:00 2001 From: ZTatman Date: Fri, 27 Mar 2026 17:22:21 -0400 Subject: [PATCH] Add core Supabase schema migration --- NEW_PLAN.md | 970 ++++++++++++++++++ supabase/.gitignore | 8 + supabase/config.toml | 384 +++++++ .../20260327203405_core_diary_schema.sql | 145 +++ 4 files changed, 1507 insertions(+) create mode 100644 NEW_PLAN.md create mode 100644 supabase/.gitignore create mode 100644 supabase/config.toml create mode 100644 supabase/migrations/20260327203405_core_diary_schema.sql diff --git a/NEW_PLAN.md b/NEW_PLAN.md new file mode 100644 index 0000000..470bb04 --- /dev/null +++ b/NEW_PLAN.md @@ -0,0 +1,970 @@ +# Nadir — Supabase Setup & Architecture Guide + +> Complete reference for setting up Supabase, the data schema, storage buckets, authentication, and monetization for the Nadir voice mood diary app. +> Intended for use with coding agents — each section is a discrete, executable step. + +--- + +## Table of Contents + +1. [Project Overview](#1-project-overview) +2. [Tech Stack](#2-tech-stack) +3. [Supabase Project Setup](#3-supabase-project-setup) +4. [Environment Variables](#4-environment-variables) +5. [Database Schema](#5-database-schema) +6. [Storage Buckets](#6-storage-buckets) +7. [Row Level Security](#7-row-level-security) +8. [Python Dependencies](#8-python-dependencies) +9. [Python db.py — Supabase Client](#9-python-dbpy--supabase-client) +10. [Authentication Flow](#10-authentication-flow) +11. [Subscription Tiers](#11-subscription-tiers) +12. [Monetization — Stripe + RevenueCat](#12-monetization--stripe--revenuecat) +13. [AI Call Enforcement Pattern](#13-ai-call-enforcement-pattern) +14. [FastAPI Endpoints Reference](#14-fastapi-endpoints-reference) +15. [Full System Architecture](#15-full-system-architecture) +16. [Build Order](#16-build-order) + +--- + +## 1. Project Overview + +Nadir is a voice-first personal mood diary app. Users speak freely, their voice is transcribed by Whisper, AI extracts emotional metadata, and entries are stored in a vector database for RAG-powered pattern queries. + +**Core user flows:** + +- Record a voice entry → transcribe → auto-tag mood/triggers → save +- Ask questions about emotional patterns → RAG retrieves relevant entries → AI answers +- Weekly reflection digest generated from last 7 entries + +**Privacy:** All audio and diary data is private per-user. No entry is ever visible to other users. + +--- + +## 2. Tech Stack + +| Layer | Tool | Notes | +| ------------------- | --------------------- | ----------------------------------- | +| Mobile frontend | React Native + Expo | iOS + Android from one codebase | +| Backend API | FastAPI (Python) | Hosted on Railway or Render | +| Database | Supabase PostgreSQL | + pgvector extension for embeddings | +| File storage | Supabase Storage | Private buckets, signed URLs | +| Authentication | Supabase Auth | Email, Google, Apple sign-in | +| Voice transcription | OpenAI Whisper | Runs on server, not phone | +| Embeddings | sentence-transformers | `all-MiniLM-L6-v2`, runs locally | +| LLM (local dev) | Ollama `llama3.2:1b` | Free, runs on your machine | +| LLM (production) | OpenAI `gpt-4o-mini` | Swap when ready to deploy | +| Billing | Stripe + RevenueCat | RevenueCat handles iOS/Android IAP | + +--- + +## 3. Supabase Project Setup + +### Step 1 — Create project + +1. Go to `supabase.com` and sign in +2. Click **New Project** +3. Choose a name (e.g. `nadir-prod`) and a strong database password +4. Select the region closest to your users +5. Wait ~2 minutes for provisioning + +### Step 2 — Collect credentials + +Go to **Settings → API** and copy: + +``` +Project URL: https://xxxxxxxxxxxx.supabase.co +Anon key: eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9... +Service key: eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9... ← keep secret, server only +``` + +Go to **Settings → Database** and copy: + +``` +Connection string (URI): +postgresql://postgres:[PASSWORD]@db.xxxxxxxxxxxx.supabase.co:5432/postgres +``` + +--- + +## 4. Environment Variables + +Add all of these to your `.env` file. Never commit this file to Git. + +```env +# Supabase +SUPABASE_URL=https://xxxxxxxxxxxx.supabase.co +SUPABASE_ANON_KEY=eyJ... +SUPABASE_SERVICE_KEY=eyJ... # server-side only, never expose to client +DATABASE_URL=postgresql://postgres:[PASSWORD]@db.xxxxxxxxxxxx.supabase.co:5432/postgres + +# OpenAI (for production LLM calls) +OPENAI_API_KEY=sk-... + +# Stripe +STRIPE_SECRET_KEY=sk_live_... +STRIPE_WEBHOOK_SECRET=whsec_... + +# RevenueCat (optional, for mobile billing) +REVENUECAT_API_KEY=... +``` + +Your `.gitignore` should already contain `.env` — confirm before pushing to GitHub. + +--- + +## 5. Database Schema + +Run all of the following SQL in **Supabase → SQL Editor** in the order shown. + +### Step 1 — Enable extensions + +```sql +-- Vector similarity search +create extension if not exists vector; + +-- UUID generation +create extension if not exists "uuid-ossp"; +``` + +### Step 2 — profiles table + +Created automatically when a user signs up via a trigger on `auth.users`. + +```sql +create table public.profiles ( + id uuid primary key references auth.users(id) on delete cascade, + created_at timestamptz default now(), + display_name text, + avatar_url text +); + +-- Auto-create profile when user signs up +create or replace function public.handle_new_user() +returns trigger as $$ +begin + insert into public.profiles (id, display_name) + values (new.id, new.raw_user_meta_data->>'full_name'); + return new; +end; +$$ language plpgsql security definer; + +create trigger on_auth_user_created + after insert on auth.users + for each row execute procedure public.handle_new_user(); +``` + +### Step 3 — entries table + +```sql +create table public.entries ( + id uuid primary key default gen_random_uuid(), + user_id uuid not null references public.profiles(id) on delete cascade, + created_at timestamptz default now(), + transcript text not null, + audio_path text, -- pointer to Supabase Storage object path + duration_secs int, -- length of the voice recording + processing_status text not null default 'recorded' + check (processing_status in ('recorded', 'transcribing', 'transcribed', 'analyzing', 'pending_review', 'confirmed', 'error')), + embedding vector(384), -- all-MiniLM-L6-v2 dimensions + summary text -- optional AI-generated summary +); + +-- Index for fast vector similarity search +create index on public.entries + using ivfflat (embedding vector_cosine_ops) + with (lists = 100); + +-- Index for fast user entry lookups +create index on public.entries (user_id, created_at desc); + +-- Index for queue-style lookups +create index on public.entries (user_id, processing_status, created_at desc); +``` + +### Step 4 — entry_analysis table + +```sql +create table public.entry_analysis ( + entry_id uuid primary key references public.entries(id) on delete cascade, + created_at timestamptz default now(), + updated_at timestamptz default now(), + valence double precision check (valence between -1.0 and 1.0), + arousal double precision check (arousal between 0.0 and 1.0), + intensity double precision check (intensity between 0.0 and 1.0), + confidence double precision check (confidence between 0.0 and 1.0), + dominant_mood text, + analysis_status text not null default 'proposed' + check (analysis_status in ('proposed', 'pending_review', 'confirmed', 'corrected')), + model_version text +); + +create index on public.entry_analysis (analysis_status); +create index on public.entry_analysis (created_at desc); +``` + +### Step 5 — entry_mood_signals table + +```sql +create table public.entry_mood_signals ( + id uuid primary key default gen_random_uuid(), + entry_id uuid not null references public.entries(id) on delete cascade, + mood text not null, + intensity double precision not null check (intensity between 0.0 and 1.0), + confidence double precision check (confidence between 0.0 and 1.0), + valence_weight double precision, + created_at timestamptz default now(), + unique (entry_id, mood) +); + +create index on public.entry_mood_signals (entry_id); +create index on public.entry_mood_signals (mood, entry_id); +``` + +### Step 6 — entry_tags table + +```sql +create table public.entry_tags ( + id uuid primary key default gen_random_uuid(), + entry_id uuid not null references public.entries(id) on delete cascade, + tag text not null, + confidence double precision check (confidence between 0.0 and 1.0), + created_at timestamptz default now(), + unique (entry_id, tag) +); + +create index on public.entry_tags (entry_id); +create index on public.entry_tags (tag, entry_id); +``` + +### Step 7 — entry_feedback table + +```sql +create table public.entry_feedback ( + id uuid primary key default gen_random_uuid(), + entry_id uuid not null references public.entries(id) on delete cascade, + user_id uuid not null references public.profiles(id) on delete cascade, + created_at timestamptz default now(), + field_name text not null, + old_value jsonb, + new_value jsonb, + reason text, + check (field_name in ('processing_status', 'analysis_status', 'valence', 'arousal', 'intensity', 'dominant_mood', 'mood_signals', 'tags', 'summary')) +); + +create index on public.entry_feedback (user_id, created_at desc); +create index on public.entry_feedback (entry_id); +``` + +### Step 8 — ai_usage_log table + +```sql +create table public.ai_usage_log ( + id uuid primary key default gen_random_uuid(), + user_id uuid not null references public.profiles(id) on delete cascade, + created_at timestamptz default now(), + call_type text not null + check (call_type in ('ask', 'extract', 'summarise')), + tokens_used int, + model text -- 'llama3.2:1b' | 'gpt-4o-mini' +); + +create index on public.ai_usage_log (user_id, created_at desc); +``` + +### Step 9 — subscriptions table + +```sql +create table public.subscriptions ( + user_id uuid primary key references public.profiles(id) on delete cascade, + created_at timestamptz default now(), + stripe_customer_id text unique, + stripe_sub_id text unique, + tier text not null default 'free', -- 'free' | 'pro' | 'unlimited' + status text not null default 'active' + check (status in ('active', 'cancelled', 'past_due')), + current_period_end date +); + +create index on public.subscriptions (stripe_customer_id); +``` + +### Step 10 — match_entries function (RAG vector search) + +```sql +create or replace function match_entries ( + query_embedding vector(384), + match_user_id uuid, + match_count int default 5 +) +returns table ( + id uuid, + transcript text, + summary text, + created_at timestamptz, + valence double precision, + arousal double precision, + intensity double precision, + dominant_mood text, + similarity float +) +language sql stable +as $$ + select + e.id, + e.transcript, + e.summary, + e.created_at, + a.valence, + a.arousal, + a.intensity, + a.dominant_mood, + 1 - (e.embedding <=> query_embedding) as similarity + from public.entries e + left join public.entry_analysis a on a.entry_id = e.id + where e.user_id = match_user_id + order by e.embedding <=> query_embedding + limit match_count; +$$; +``` + +### Step 11 — usage accounting + +```sql +-- Usage is tracked in ai_usage_log, so no profile counter reset is needed. +-- If limits are enforced in SQL later, add a dedicated usage summary table. +``` + +--- + +## 6. Storage Buckets + +Run in **Supabase → SQL Editor** or create manually in **Storage** dashboard. + +```sql +-- Recordings bucket (private) +insert into storage.buckets (id, name, public) +values ('recordings', 'recordings', false); + +-- Avatars bucket (private) +insert into storage.buckets (id, name, public) +values ('avatars', 'avatars', false); +``` + +### File path conventions + +``` +recordings/ +└── {user_id}/ + └── {YYYYMMDD_HHMMSS}.m4a + e.g. recordings/abc-123/20260316_143022.m4a + +avatars/ +└── {user_id}/ + └── avatar.jpg + e.g. avatars/abc-123/avatar.jpg +``` + +### Accessing files from Python (signed URL — expires in 1 hour) + +```python +url = supabase.storage.from_("recordings").create_signed_url( + path=f"{user_id}/{filename}", + expires_in=3600 +) +``` + +--- + +## 7. Row Level Security + +RLS ensures every user can only see and modify their own data. Run in **SQL Editor**. + +```sql +-- ── profiles ── +alter table public.profiles enable row level security; + +create policy "Users can view own profile" + on public.profiles for select + using ((select auth.uid()) = id); + +create policy "Users can update own profile" + on public.profiles for update + using ((select auth.uid()) = id); + +-- ── entries ── +alter table public.entries enable row level security; + +create policy "Users can view own entries" + on public.entries for select + using ((select auth.uid()) = user_id); + +create policy "Users can insert own entries" + on public.entries for insert + with check ((select auth.uid()) = user_id); + +create policy "Users can delete own entries" + on public.entries for delete + using ((select auth.uid()) = user_id); + +-- ── entry_analysis ── +alter table public.entry_analysis enable row level security; + +create policy "Users can view own analysis" + on public.entry_analysis for select + using ( + exists ( + select 1 + from public.entries e + where e.id = entry_id + and e.user_id = (select auth.uid()) + ) + ); + +-- ── entry_mood_signals ── +alter table public.entry_mood_signals enable row level security; + +create policy "Users can view own mood signals" + on public.entry_mood_signals for select + using ( + exists ( + select 1 + from public.entries e + where e.id = entry_id + and e.user_id = (select auth.uid()) + ) + ); + +-- ── entry_tags ── +alter table public.entry_tags enable row level security; + +create policy "Users can view own tags" + on public.entry_tags for select + using ( + exists ( + select 1 + from public.entries e + where e.id = entry_id + and e.user_id = (select auth.uid()) + ) + ); + +-- ── entry_feedback ── +alter table public.entry_feedback enable row level security; + +create policy "Users can view own feedback" + on public.entry_feedback for select + using ((select auth.uid()) = user_id); + +create policy "Users can insert own feedback" + on public.entry_feedback for insert + with check ( + (select auth.uid()) = user_id + and exists ( + select 1 + from public.entries e + where e.id = entry_id + and e.user_id = (select auth.uid()) + ) + ); + +create policy "Users can update own feedback" + on public.entry_feedback for update + using ( + (select auth.uid()) = user_id + and exists ( + select 1 + from public.entries e + where e.id = entry_id + and e.user_id = (select auth.uid()) + ) + ); + +create policy "Users can delete own feedback" + on public.entry_feedback for delete + using ( + (select auth.uid()) = user_id + and exists ( + select 1 + from public.entries e + where e.id = entry_id + and e.user_id = (select auth.uid()) + ) + ); + +-- ── ai_usage_log ── +alter table public.ai_usage_log enable row level security; + +create policy "Users can view own usage" + on public.ai_usage_log for select + using ((select auth.uid()) = user_id); + +-- ── subscriptions ── +alter table public.subscriptions enable row level security; + +create policy "Users can view own subscription" + on public.subscriptions for select + using ((select auth.uid()) = user_id); + +-- ── Storage: recordings ── +create policy "Users can upload own recordings" + on storage.objects for insert + with check ( + bucket_id = 'recordings' + and (select auth.uid())::text = (storage.foldername(name))[1] + ); + +create policy "Users can view own recordings" + on storage.objects for select + using ( + bucket_id = 'recordings' + and (select auth.uid())::text = (storage.foldername(name))[1] + ); + +create policy "Users can delete own recordings" + on storage.objects for delete + using ( + bucket_id = 'recordings' + and (select auth.uid())::text = (storage.foldername(name))[1] + ); + +-- ── Storage: avatars ── +create policy "Users can manage own avatar" + on storage.objects for all + using ( + bucket_id = 'avatars' + and (select auth.uid())::text = (storage.foldername(name))[1] + ); +``` + +--- + +## 8. Python Dependencies + +```bash +# Remove ChromaDB, add Supabase stack +uv remove chromadb + +uv add supabase +uv add sentence-transformers +uv add vecs +uv add stripe +uv add python-jose # JWT token verification +uv add fastapi uvicorn +``` + +Full `pyproject.toml` dependencies section: + +```toml +dependencies = [ + "fastapi>=0.115.0", + "uvicorn>=0.30.0", + "supabase>=2.0.0", + "sentence-transformers>=3.0.0", + "vecs>=0.4.0", + "openai>=2.0.0", + "openai-whisper>=20250625", + "sounddevice>=0.5.0", + "scipy>=1.17.0", + "pydantic>=2.0.0", + "python-dotenv>=1.0.0", + "python-jose>=3.3.0", + "stripe>=10.0.0", + "python-multipart>=0.0.9", +] +``` + +--- + +## 9. Python db.py — Supabase Client + +Replace your existing `db.py` entirely with this: + +```python +""" +db.py — Supabase client and embedding model +Imported by store.py, query.py, and main.py +""" + +import os +from dotenv import load_dotenv +from supabase import create_client, Client +from sentence_transformers import SentenceTransformer + +load_dotenv() + +# ── Supabase client ─────────────────────────────────────────────────────────── + +def get_supabase() -> Client: + """Returns authenticated Supabase client using the service key.""" + url = os.environ["SUPABASE_URL"] + key = os.environ["SUPABASE_SERVICE_KEY"] # service key for server-side ops + return create_client(url, key) + +def get_storage(): + """Shortcut to the recordings storage bucket.""" + return get_supabase().storage.from_("recordings") + +# ── Embedding model ─────────────────────────────────────────────────────────── +# Downloads ~80MB on first run, cached locally after that + +_model = None + +def get_embedding_model() -> SentenceTransformer: + global _model + if _model is None: + _model = SentenceTransformer("all-MiniLM-L6-v2") + return _model + +def embed(text: str) -> list[float]: + """Convert a string to a 384-dimensional embedding vector.""" + model = get_embedding_model() + return model.encode(text).tolist() +``` + +--- + +## 10. Authentication Flow + +Supabase Auth handles everything. Your FastAPI server verifies the JWT token on every request. + +### How it works + +``` +1. User signs in on mobile app via Supabase Auth SDK +2. Supabase returns a JWT access token +3. Mobile app sends JWT in every API request header: + Authorization: Bearer eyJ... +4. FastAPI verifies the JWT using Supabase's public key +5. FastAPI extracts user_id from the token +6. All database queries are scoped to that user_id +``` + +### FastAPI JWT verification + +```python +from fastapi import Depends, HTTPException, Header +from python_jose import jwt, JWTError +import os + +SUPABASE_JWT_SECRET = os.environ["SUPABASE_JWT_SECRET"] # from Supabase dashboard + +def get_current_user(authorization: str = Header(...)) -> str: + """Extract and verify user_id from JWT. Use as a FastAPI dependency.""" + try: + token = authorization.replace("Bearer ", "") + payload = jwt.decode(token, SUPABASE_JWT_SECRET, algorithms=["HS256"]) + user_id = payload.get("sub") + if not user_id: + raise HTTPException(401, "Invalid token") + return user_id + except JWTError: + raise HTTPException(401, "Could not validate token") + +# Usage in any endpoint: +@app.post("/entries/save") +def save_entry(data: EntryRequest, user_id: str = Depends(get_current_user)): + # user_id is verified and safe to use + ... +``` + +--- + +## 11. Subscription Tiers + +| Tier | Price | AI asks/month | AI extractions | Weekly digest | Storage | +| --------- | -------- | ------------- | -------------- | ------------- | ------- | +| Free | $0 | 30 | 30 | No | 100 MB | +| Pro | $4.99/mo | 500 | Unlimited | No | 2 GB | +| Unlimited | $9.99/mo | Unlimited | Unlimited | Yes | 10 GB | + +### Tier limits by subscription tier + +These limits live in application logic or a dedicated billing table, not `profiles`. + +| Tier | Monthly ask limit | Extraction limit | Weekly digest | +| --------- | ----------------- | ----------------- | ------------- | +| free | 30 | 30 | No | +| pro | 500 | Unlimited | No | +| unlimited | Unlimited | Unlimited | Yes | + +### What counts as an AI call + +| Action | Call type | Counts against limit? | +| ----------------------------- | ----------- | --------------------- | +| User asks a question | `ask` | Yes | +| Auto-extract metadata on save | `extract` | Yes (free), No (pro+) | +| Weekly reflection summary | `summarise` | Unlimited only | +| Transcription (Whisper) | n/a | No — flat server cost | + +--- + +## 12. Monetization — Stripe + RevenueCat + +### Why RevenueCat + +Apple App Store and Google Play both require in-app purchases for subscriptions sold inside a mobile app. RevenueCat abstracts both platforms plus web (Stripe) into one API. Without it you'd manage three separate billing integrations. + +### Setup steps + +1. Create a RevenueCat account at `revenuecat.com` +2. Create products in App Store Connect and Google Play Console +3. Link those products to RevenueCat entitlements +4. RevenueCat sends webhooks to your FastAPI server on subscription events + +### FastAPI webhook handler + +```python +@app.post("/webhooks/revenuecat") +async def revenuecat_webhook(request: Request): + payload = await request.json() + event_type = payload["event"]["type"] + user_id = payload["event"]["app_user_id"] + product_id = payload["event"].get("product_id", "") + + # Map product ID to tier + tier_map = { + "nadir_pro_monthly": "pro", + "nadir_unlimited_monthly": "unlimited", + } + tier = tier_map.get(product_id, "free") + + if event_type in ("INITIAL_PURCHASE", "RENEWAL"): + supabase.table("subscriptions").upsert({ + "user_id": user_id, + "tier": tier, + "status": "active", + }).execute() + + elif event_type in ("CANCELLATION", "EXPIRATION"): + supabase.table("subscriptions").update({ + "status": "cancelled", + "tier": "free", + }).eq("user_id", user_id).execute() + + return {"status": "ok"} +``` + +--- + +## 13. AI Call Enforcement Pattern + +Add this check to every FastAPI endpoint that calls an LLM. + +```python +def check_ai_limit(user_id: str, call_type: str): + """ + Raises HTTP 429 if user has exceeded their monthly AI limit for this call type. + Logs the call if allowed. + """ + supabase = get_supabase() + + # Fetch current subscription tier + result = supabase.table("subscriptions")\ + .select("tier, status")\ + .eq("user_id", user_id)\ + .limit(1)\ + .execute() + + subscription = result.data[0] if result.data else None + tier = subscription["tier"] if subscription and subscription["status"] == "active" else "free" + + # Call-type limits are enforced in application logic. + # The database only stores the event log. + limit_map = { + "free": {"ask": 30, "extract": 30, "summarise": 0}, + "pro": {"ask": 500, "extract": 999999, "summarise": 0}, + "unlimited": {"ask": 999999, "extract": 999999, "summarise": 999999}, + } + limit = limit_map.get(tier, limit_map["free"]).get(call_type, 0) + + if limit == 0: + raise HTTPException( + status_code=429, + detail={ + "error": "This AI action is not available on your tier", + "tier": tier, + "call_type": call_type, + "upgrade_url": "https://yourapp.com/upgrade" + } + ) + + # Count usage for the current month and call type from the log table. + # This keeps the profiles table identity-only. + month_start = datetime.now().replace(day=1, hour=0, minute=0, second=0, microsecond=0) + usage = supabase.table("ai_usage_log")\ + .select("id", count="exact")\ + .eq("user_id", user_id)\ + .eq("call_type", call_type)\ + .gte("created_at", month_start.isoformat())\ + .execute() + + used = usage.count or 0 + + if used >= limit: + raise HTTPException( + status_code=429, + detail={ + "error": f"Monthly AI limit reached for {call_type}", + "used": used, + "limit": limit, + "tier": tier, + "upgrade_url": "https://yourapp.com/upgrade" + } + ) + + # Log the call + supabase.table("ai_usage_log").insert({ + "user_id": user_id, + "call_type": call_type, + "model": "gpt-4o-mini", + }).execute() +``` + +### Usage in endpoints + +```python +@app.post("/ask") +def ask_question(data: AskRequest, user_id: str = Depends(get_current_user)): + check_ai_limit(user_id, "ask") # ← call this before any LLM call + # ... rest of RAG logic +``` + +--- + +## 14. FastAPI Endpoints Reference + +| Method | Path | Auth | Description | +| -------- | ----------------------- | -------- | -------------------------------------------- | +| `POST` | `/entries/upload-audio` | Required | Upload .m4a → transcribe → return transcript | +| `POST` | `/entries/save` | Required | Save transcript + analysis + signals + embedding | +| `GET` | `/entries` | Required | List user's recent entries | +| `GET` | `/entries/{id}` | Required | Get single entry | +| `DELETE` | `/entries/{id}` | Required | Delete entry + audio file | +| `POST` | `/ask` | Required | RAG question → AI answer | +| `GET` | `/profile` | Required | Get user profile + subscription info | +| `POST` | `/webhooks/revenuecat` | None | Handle billing events | +| `GET` | `/health` | None | Server health check | + +### POST /entries/upload-audio + +```python +@app.post("/entries/upload-audio") +async def upload_audio( + audio: UploadFile, + user_id: str = Depends(get_current_user) +): + audio_bytes = await audio.read() + filename = f"{user_id}/{datetime.now().strftime('%Y%m%d_%H%M%S')}.m4a" + audio_path = filename + + # Upload to Supabase Storage + get_storage().upload( + path=filename, + file=audio_bytes, + file_options={"content-type": "audio/m4a"} + ) + + # Transcribe with Whisper (temp file on disk) + with tempfile.NamedTemporaryFile(suffix=".m4a", delete=False) as tmp: + tmp.write(audio_bytes) + tmp_path = tmp.name + + transcript = transcribe(tmp_path) # your transcribe.py function + os.unlink(tmp_path) + + return {"transcript": transcript, "audio_path": audio_path} +``` + +--- + +## 15. Full System Architecture + +``` +┌─────────────────┐ ┌──────────────────────┐ ┌─────────────────────────┐ +│ Phone app │ │ FastAPI server │ │ Supabase │ +│ React Native │ │ main.py │ │ │ +│ │ │ │ │ PostgreSQL │ +│ Microphone ────┼─────────┼→ POST /upload-audio │ │ ┌──────────────────┐ │ +│ Temp .m4a │ │ transcribe.py │ │ │ profiles │ │ +│ Chat UI ←────┼─────────┼─ Whisper → text ───┼────────┼→ │ entries │ │ +│ │ │ store.py │ │ │ entry_analysis │ │ +│ │─────────┼→ POST /ask │ │ │ entry_mood_signals│ │ +│ │ │ query.py │ │ │ entry_tags │ │ +│ │ │ embed → pgvector │ │ │ entry_feedback │ │ +│ │ │ Ollama / OpenAI │ │ │ ai_usage_log │ │ +│ │ │ POST /webhooks/ │ │ │ subscriptions │ │ +│ RevenueCat ────┼─────────┼→ revenuecat │ │ └──────────────────┘ │ +│ │ │ update tier │ │ │ +│ │ │ │ │ Storage │ +│ │ │ │ │ ┌──────────────────┐ │ +│ │ │ │ │ │ recordings/ │ │ +│ │ │ │ │ │ avatars/ │ │ +│ │ │ │ │ └──────────────────┘ │ +└─────────────────┘ └──────────────────────┘ └─────────────────────────┘ +``` + +--- + +## 16. Build Order + +Work through these phases in order. Each phase has a clear done-when checkpoint. + +### Phase 1 — Supabase foundation + +- [ ] Create Supabase project +- [ ] Run all SQL from Section 5 in SQL Editor +- [ ] Create storage buckets (Section 6) +- [ ] Apply RLS policies (Section 7) +- [ ] Add credentials to `.env` +- [ ] Install Python dependencies (Section 8) +- [ ] Write and test `db.py` (Section 9) + +**Done when:** `python db.py` runs without errors and connects to Supabase + +### Phase 2 — Rewrite store.py and query.py for Supabase + +- [ ] Rewrite `store.py` to insert into `entries` table with embeddings +- [ ] Rewrite `query.py` to use `match_entries` RPC function +- [ ] Test: save an entry, run a vector search, get results back + +**Done when:** You can save an entry and ask a question with results from Supabase + +### Phase 3 — Voice recording + +- [ ] Write `record.py` — mic capture → `.m4a` file +- [ ] Write `transcribe.py` — Whisper → text +- [ ] Test both independently from terminal + +**Done when:** `python record.py` saves a file, `python transcribe.py recording.m4a` returns text + +### Phase 4 — FastAPI server + +- [ ] Write `main.py` with all endpoints from Section 14 +- [ ] Add JWT auth middleware (Section 10) +- [ ] Add AI call enforcement (Section 13) +- [ ] Test all endpoints with Bruno or Postman + +**Done when:** All endpoints return correct responses when called with a valid JWT + +### Phase 5 — Mobile frontend + +- [ ] Set up React Native + Expo project +- [ ] Integrate Supabase Auth SDK for sign-in +- [ ] Build record screen — calls `POST /entries/upload-audio` +- [ ] Build reflect screen — calls `POST /ask` +- [ ] Build entry list screen — calls `GET /entries` + +**Done when:** Full flow works on a real device — record, save, ask, get answer + +### Phase 6 — Billing + +- [ ] Set up RevenueCat account and products +- [ ] Add webhook endpoint (Section 12) +- [ ] Test subscription flow end to end +- [ ] Verify tier enforcement works correctly + +**Done when:** Subscribing to Pro updates the row in `subscriptions` and leaves `profiles` untouched + +--- + +_Last updated: March 2026 — Nadir v0.1_ diff --git a/supabase/.gitignore b/supabase/.gitignore new file mode 100644 index 0000000..ad9264f --- /dev/null +++ b/supabase/.gitignore @@ -0,0 +1,8 @@ +# Supabase +.branches +.temp + +# dotenvx +.env.keys +.env.local +.env.*.local diff --git a/supabase/config.toml b/supabase/config.toml new file mode 100644 index 0000000..caa6e9c --- /dev/null +++ b/supabase/config.toml @@ -0,0 +1,384 @@ +# For detailed configuration reference documentation, visit: +# https://supabase.com/docs/guides/local-development/cli/config +# A string used to distinguish different Supabase projects on the same host. Defaults to the +# working directory name when running `supabase init`. +project_id = "Nadir" + +[api] +enabled = true +# Port to use for the API URL. +port = 54321 +# Schemas to expose in your API. Tables, views and stored procedures in this schema will get API +# endpoints. `public` and `graphql_public` schemas are included by default. +schemas = ["public", "graphql_public"] +# Extra schemas to add to the search_path of every request. +extra_search_path = ["public", "extensions"] +# The maximum number of rows returns from a view, table, or stored procedure. Limits payload size +# for accidental or malicious requests. +max_rows = 1000 + +[api.tls] +# Enable HTTPS endpoints locally using a self-signed certificate. +enabled = false +# Paths to self-signed certificate pair. +# cert_path = "../certs/my-cert.pem" +# key_path = "../certs/my-key.pem" + +[db] +# Port to use for the local database URL. +port = 54322 +# Port used by db diff command to initialize the shadow database. +shadow_port = 54320 +# Maximum amount of time to wait for health check when starting the local database. +health_timeout = "2m" +# The database major version to use. This has to be the same as your remote database's. Run `SHOW +# server_version;` on the remote database to check. +major_version = 17 + +[db.pooler] +enabled = false +# Port to use for the local connection pooler. +port = 54329 +# Specifies when a server connection can be reused by other clients. +# Configure one of the supported pooler modes: `transaction`, `session`. +pool_mode = "transaction" +# How many server connections to allow per user/database pair. +default_pool_size = 20 +# Maximum number of client connections allowed. +max_client_conn = 100 + +# [db.vault] +# secret_key = "env(SECRET_VALUE)" + +[db.migrations] +# If disabled, migrations will be skipped during a db push or reset. +enabled = true +# Specifies an ordered list of schema files that describe your database. +# Supports glob patterns relative to supabase directory: "./schemas/*.sql" +schema_paths = [] + +[db.seed] +# If enabled, seeds the database after migrations during a db reset. +enabled = true +# Specifies an ordered list of seed files to load during db reset. +# Supports glob patterns relative to supabase directory: "./seeds/*.sql" +sql_paths = ["./seed.sql"] + +[db.network_restrictions] +# Enable management of network restrictions. +enabled = false +# List of IPv4 CIDR blocks allowed to connect to the database. +# Defaults to allow all IPv4 connections. Set empty array to block all IPs. +allowed_cidrs = ["0.0.0.0/0"] +# List of IPv6 CIDR blocks allowed to connect to the database. +# Defaults to allow all IPv6 connections. Set empty array to block all IPs. +allowed_cidrs_v6 = ["::/0"] + +[realtime] +enabled = true +# Bind realtime via either IPv4 or IPv6. (default: IPv4) +# ip_version = "IPv6" +# The maximum length in bytes of HTTP request headers. (default: 4096) +# max_header_length = 4096 + +[studio] +enabled = true +# Port to use for Supabase Studio. +port = 54323 +# External URL of the API server that frontend connects to. +api_url = "http://127.0.0.1" +# OpenAI API Key to use for Supabase AI in the Supabase Studio. +openai_api_key = "env(OPENAI_API_KEY)" + +# Email testing server. Emails sent with the local dev setup are not actually sent - rather, they +# are monitored, and you can view the emails that would have been sent from the web interface. +[inbucket] +enabled = true +# Port to use for the email testing server web interface. +port = 54324 +# Uncomment to expose additional ports for testing user applications that send emails. +# smtp_port = 54325 +# pop3_port = 54326 +# admin_email = "admin@email.com" +# sender_name = "Admin" + +[storage] +enabled = true +# The maximum file size allowed (e.g. "5MB", "500KB"). +file_size_limit = "50MiB" + +# Uncomment to configure local storage buckets +# [storage.buckets.images] +# public = false +# file_size_limit = "50MiB" +# allowed_mime_types = ["image/png", "image/jpeg"] +# objects_path = "./images" + +# Allow connections via S3 compatible clients +[storage.s3_protocol] +enabled = true + +# Image transformation API is available to Supabase Pro plan. +# [storage.image_transformation] +# enabled = true + +# Store analytical data in S3 for running ETL jobs over Iceberg Catalog +# This feature is only available on the hosted platform. +[storage.analytics] +enabled = false +max_namespaces = 5 +max_tables = 10 +max_catalogs = 2 + +# Analytics Buckets is available to Supabase Pro plan. +# [storage.analytics.buckets.my-warehouse] + +# Store vector embeddings in S3 for large and durable datasets +# This feature is only available on the hosted platform. +[storage.vector] +enabled = false +max_buckets = 10 +max_indexes = 5 + +# Vector Buckets is available to Supabase Pro plan. +# [storage.vector.buckets.documents-openai] + +[auth] +enabled = true +# The base URL of your website. Used as an allow-list for redirects and for constructing URLs used +# in emails. +site_url = "http://127.0.0.1:3000" +# A list of *exact* URLs that auth providers are permitted to redirect to post authentication. +additional_redirect_urls = ["https://127.0.0.1:3000"] +# How long tokens are valid for, in seconds. Defaults to 3600 (1 hour), maximum 604,800 (1 week). +jwt_expiry = 3600 +# JWT issuer URL. If not set, defaults to the local API URL (http://127.0.0.1:/auth/v1). +# jwt_issuer = "" +# Path to JWT signing key. DO NOT commit your signing keys file to git. +# signing_keys_path = "./signing_keys.json" +# If disabled, the refresh token will never expire. +enable_refresh_token_rotation = true +# Allows refresh tokens to be reused after expiry, up to the specified interval in seconds. +# Requires enable_refresh_token_rotation = true. +refresh_token_reuse_interval = 10 +# Allow/disallow new user signups to your project. +enable_signup = true +# Allow/disallow anonymous sign-ins to your project. +enable_anonymous_sign_ins = false +# Allow/disallow testing manual linking of accounts +enable_manual_linking = false +# Passwords shorter than this value will be rejected as weak. Minimum 6, recommended 8 or more. +minimum_password_length = 6 +# Passwords that do not meet the following requirements will be rejected as weak. Supported values +# are: `letters_digits`, `lower_upper_letters_digits`, `lower_upper_letters_digits_symbols` +password_requirements = "" + +[auth.rate_limit] +# Number of emails that can be sent per hour. Requires auth.email.smtp to be enabled. +email_sent = 2 +# Number of SMS messages that can be sent per hour. Requires auth.sms to be enabled. +sms_sent = 30 +# Number of anonymous sign-ins that can be made per hour per IP address. Requires enable_anonymous_sign_ins = true. +anonymous_users = 30 +# Number of sessions that can be refreshed in a 5 minute interval per IP address. +token_refresh = 150 +# Number of sign up and sign-in requests that can be made in a 5 minute interval per IP address (excludes anonymous users). +sign_in_sign_ups = 30 +# Number of OTP / Magic link verifications that can be made in a 5 minute interval per IP address. +token_verifications = 30 +# Number of Web3 logins that can be made in a 5 minute interval per IP address. +web3 = 30 + +# Configure one of the supported captcha providers: `hcaptcha`, `turnstile`. +# [auth.captcha] +# enabled = true +# provider = "hcaptcha" +# secret = "" + +[auth.email] +# Allow/disallow new user signups via email to your project. +enable_signup = true +# If enabled, a user will be required to confirm any email change on both the old, and new email +# addresses. If disabled, only the new email is required to confirm. +double_confirm_changes = true +# If enabled, users need to confirm their email address before signing in. +enable_confirmations = false +# If enabled, users will need to reauthenticate or have logged in recently to change their password. +secure_password_change = false +# Controls the minimum amount of time that must pass before sending another signup confirmation or password reset email. +max_frequency = "1s" +# Number of characters used in the email OTP. +otp_length = 6 +# Number of seconds before the email OTP expires (defaults to 1 hour). +otp_expiry = 3600 + +# Use a production-ready SMTP server +# [auth.email.smtp] +# enabled = true +# host = "smtp.sendgrid.net" +# port = 587 +# user = "apikey" +# pass = "env(SENDGRID_API_KEY)" +# admin_email = "admin@email.com" +# sender_name = "Admin" + +# Uncomment to customize email template +# [auth.email.template.invite] +# subject = "You have been invited" +# content_path = "./supabase/templates/invite.html" + +# Uncomment to customize notification email template +# [auth.email.notification.password_changed] +# enabled = true +# subject = "Your password has been changed" +# content_path = "./templates/password_changed_notification.html" + +[auth.sms] +# Allow/disallow new user signups via SMS to your project. +enable_signup = false +# If enabled, users need to confirm their phone number before signing in. +enable_confirmations = false +# Template for sending OTP to users +template = "Your code is {{ .Code }}" +# Controls the minimum amount of time that must pass before sending another sms otp. +max_frequency = "5s" + +# Use pre-defined map of phone number to OTP for testing. +# [auth.sms.test_otp] +# 4152127777 = "123456" + +# Configure logged in session timeouts. +# [auth.sessions] +# Force log out after the specified duration. +# timebox = "24h" +# Force log out if the user has been inactive longer than the specified duration. +# inactivity_timeout = "8h" + +# This hook runs before a new user is created and allows developers to reject the request based on the incoming user object. +# [auth.hook.before_user_created] +# enabled = true +# uri = "pg-functions://postgres/auth/before-user-created-hook" + +# This hook runs before a token is issued and allows you to add additional claims based on the authentication method used. +# [auth.hook.custom_access_token] +# enabled = true +# uri = "pg-functions:////" + +# Configure one of the supported SMS providers: `twilio`, `twilio_verify`, `messagebird`, `textlocal`, `vonage`. +[auth.sms.twilio] +enabled = false +account_sid = "" +message_service_sid = "" +# DO NOT commit your Twilio auth token to git. Use environment variable substitution instead: +auth_token = "env(SUPABASE_AUTH_SMS_TWILIO_AUTH_TOKEN)" + +# Multi-factor-authentication is available to Supabase Pro plan. +[auth.mfa] +# Control how many MFA factors can be enrolled at once per user. +max_enrolled_factors = 10 + +# Control MFA via App Authenticator (TOTP) +[auth.mfa.totp] +enroll_enabled = false +verify_enabled = false + +# Configure MFA via Phone Messaging +[auth.mfa.phone] +enroll_enabled = false +verify_enabled = false +otp_length = 6 +template = "Your code is {{ .Code }}" +max_frequency = "5s" + +# Configure MFA via WebAuthn +# [auth.mfa.web_authn] +# enroll_enabled = true +# verify_enabled = true + +# Use an external OAuth provider. The full list of providers are: `apple`, `azure`, `bitbucket`, +# `discord`, `facebook`, `github`, `gitlab`, `google`, `keycloak`, `linkedin_oidc`, `notion`, `twitch`, +# `twitter`, `x`, `slack`, `spotify`, `workos`, `zoom`. +[auth.external.apple] +enabled = false +client_id = "" +# DO NOT commit your OAuth provider secret to git. Use environment variable substitution instead: +secret = "env(SUPABASE_AUTH_EXTERNAL_APPLE_SECRET)" +# Overrides the default auth redirectUrl. +redirect_uri = "" +# Overrides the default auth provider URL. Used to support self-hosted gitlab, single-tenant Azure, +# or any other third-party OIDC providers. +url = "" +# If enabled, the nonce check will be skipped. Required for local sign in with Google auth. +skip_nonce_check = false +# If enabled, it will allow the user to successfully authenticate when the provider does not return an email address. +email_optional = false + +# Allow Solana wallet holders to sign in to your project via the Sign in with Solana (SIWS, EIP-4361) standard. +# You can configure "web3" rate limit in the [auth.rate_limit] section and set up [auth.captcha] if self-hosting. +[auth.web3.solana] +enabled = false + +# Use Firebase Auth as a third-party provider alongside Supabase Auth. +[auth.third_party.firebase] +enabled = false +# project_id = "my-firebase-project" + +# Use Auth0 as a third-party provider alongside Supabase Auth. +[auth.third_party.auth0] +enabled = false +# tenant = "my-auth0-tenant" +# tenant_region = "us" + +# Use AWS Cognito (Amplify) as a third-party provider alongside Supabase Auth. +[auth.third_party.aws_cognito] +enabled = false +# user_pool_id = "my-user-pool-id" +# user_pool_region = "us-east-1" + +# Use Clerk as a third-party provider alongside Supabase Auth. +[auth.third_party.clerk] +enabled = false +# Obtain from https://clerk.com/setup/supabase +# domain = "example.clerk.accounts.dev" + +# OAuth server configuration +[auth.oauth_server] +# Enable OAuth server functionality +enabled = false +# Path for OAuth consent flow UI +authorization_url_path = "/oauth/consent" +# Allow dynamic client registration +allow_dynamic_registration = false + +[edge_runtime] +enabled = true +# Supported request policies: `oneshot`, `per_worker`. +# `per_worker` (default) — enables hot reload during local development. +# `oneshot` — fallback mode if hot reload causes issues (e.g. in large repos or with symlinks). +policy = "per_worker" +# Port to attach the Chrome inspector for debugging edge functions. +inspector_port = 8083 +# The Deno major version to use. +deno_version = 2 + +# [edge_runtime.secrets] +# secret_key = "env(SECRET_VALUE)" + +[analytics] +enabled = true +port = 54327 +# Configure one of the supported backends: `postgres`, `bigquery`. +backend = "postgres" + +# Experimental features may be deprecated any time +[experimental] +# Configures Postgres storage engine to use OrioleDB (S3) +orioledb_version = "" +# Configures S3 bucket URL, eg. .s3-.amazonaws.com +s3_host = "env(S3_HOST)" +# Configures S3 bucket region, eg. us-east-1 +s3_region = "env(S3_REGION)" +# Configures AWS_ACCESS_KEY_ID for S3 bucket +s3_access_key = "env(S3_ACCESS_KEY)" +# Configures AWS_SECRET_ACCESS_KEY for S3 bucket +s3_secret_key = "env(S3_SECRET_KEY)" diff --git a/supabase/migrations/20260327203405_core_diary_schema.sql b/supabase/migrations/20260327203405_core_diary_schema.sql new file mode 100644 index 0000000..e7cf43a --- /dev/null +++ b/supabase/migrations/20260327203405_core_diary_schema.sql @@ -0,0 +1,145 @@ +create schema if not exists extensions; + +create extension if not exists vector with schema extensions; +create extension if not exists pgcrypto with schema extensions; + +-- ------------------------------------------------------------ +-- profiles +-- ------------------------------------------------------------ +create table public.profiles ( + id uuid primary key references auth.users(id) on delete cascade, + created_at timestamptz not null default now(), + display_name text, + avatar_url text +); + +-- ------------------------------------------------------------ +-- entries +-- ------------------------------------------------------------ +create table public.entries ( + id uuid primary key default gen_random_uuid(), + user_id uuid not null references public.profiles(id) on delete cascade, + created_at timestamptz not null default now(), + transcript text not null, + audio_path text, + duration_secs int, + processing_status text not null default 'recorded' + check ( + processing_status in ( + 'recorded', + 'transcribing', + 'transcribed', + 'analyzing', + 'pending_review', + 'confirmed', + 'error' + ) + ), + embedding vector(384), + summary text +); + +create index entries_user_created_at_idx + on public.entries (user_id, created_at desc); + +create index entries_user_status_created_at_idx + on public.entries (user_id, processing_status, created_at desc); + +create index entries_embedding_idx + on public.entries + using ivfflat (embedding vector_cosine_ops) + with (lists = 100); + +-- ------------------------------------------------------------ +-- entry_analysis +-- ------------------------------------------------------------ +create table public.entry_analysis ( + entry_id uuid primary key references public.entries(id) on delete cascade, + created_at timestamptz not null default now(), + updated_at timestamptz not null default now(), + valence double precision check (valence between -1.0 and 1.0), + arousal double precision check (arousal between 0.0 and 1.0), + intensity double precision check (intensity between 0.0 and 1.0), + confidence double precision check (confidence between 0.0 and 1.0), + dominant_mood text, + analysis_status text not null default 'proposed' + check (analysis_status in ('proposed', 'pending_review', 'confirmed', 'corrected')), + model_version text +); + +create index entry_analysis_status_idx + on public.entry_analysis (analysis_status); + +create index entry_analysis_created_at_idx + on public.entry_analysis (created_at desc); + +-- ------------------------------------------------------------ +-- entry_mood_signals +-- ------------------------------------------------------------ +create table public.entry_mood_signals ( + id uuid primary key default gen_random_uuid(), + entry_id uuid not null references public.entries(id) on delete cascade, + mood text not null, + intensity double precision not null check (intensity between 0.0 and 1.0), + confidence double precision check (confidence between 0.0 and 1.0), + valence_weight double precision, + created_at timestamptz not null default now(), + unique (entry_id, mood) +); + +create index entry_mood_signals_entry_id_idx + on public.entry_mood_signals (entry_id); + +create index entry_mood_signals_mood_entry_id_idx + on public.entry_mood_signals (mood, entry_id); + +-- ------------------------------------------------------------ +-- entry_tags +-- ------------------------------------------------------------ +create table public.entry_tags ( + id uuid primary key default gen_random_uuid(), + entry_id uuid not null references public.entries(id) on delete cascade, + tag text not null, + confidence double precision check (confidence between 0.0 and 1.0), + created_at timestamptz not null default now(), + unique (entry_id, tag) +); + +create index entry_tags_entry_id_idx + on public.entry_tags (entry_id); + +create index entry_tags_tag_entry_id_idx + on public.entry_tags (tag, entry_id); + +-- ------------------------------------------------------------ +-- entry_feedback +-- ------------------------------------------------------------ +create table public.entry_feedback ( + id uuid primary key default gen_random_uuid(), + entry_id uuid not null references public.entries(id) on delete cascade, + user_id uuid not null references public.profiles(id) on delete cascade, + created_at timestamptz not null default now(), + field_name text not null, + old_value jsonb, + new_value jsonb, + reason text, + check ( + field_name in ( + 'processing_status', + 'analysis_status', + 'valence', + 'arousal', + 'intensity', + 'dominant_mood', + 'mood_signals', + 'tags', + 'summary' + ) + ) +); + +create index entry_feedback_user_created_at_idx + on public.entry_feedback (user_id, created_at desc); + +create index entry_feedback_entry_id_idx + on public.entry_feedback (entry_id);