# oO

> One tip. Right now. Feels like magic.

oO learns who you are from the apps you already use and surfaces **one** perfectly-timed suggestion — an advice or a todo — on a black page. No feed. No dashboard. One tip.

---

## Why

Everyone has too many tasks, too many apps, too much noise. What people actually need is a single, well-chosen nudge at the right moment. oO is that nudge, powered by a recommendation engine that gets smarter the more of your life it sees.

## Product principles

1. **One thing at a time.** The UI is a black page with one tip. That's the product.
2. **We don't own your data, we understand it.** Connect your apps; we read what we need, when we need it.
3. **Magic requires craft.** Precision, timing, and restraint matter more than features.
4. **Private by default.** Tokens are encrypted, models are per-user, deletion is one click.

## Prototype scope (Phase 0)

Three pages. That's it.

| Page | What it does |
|------|--------------|
| **Sign in** | Google / Apple OAuth. No passwords. |
| **Connect** | A list of integrations. Tap "Todoist" → OAuth flow → token stored. |
| **Tip** | Black page. One tip. Tap to dismiss / done / snooze. |

Under the hood the "pick a tip" call already routes through a `recommender` service with a pluggable policy — so v0 is literally "random Todoist task" but every other version slots into the same contract.

---

## Architecture at a glance

```
 ┌──────────┐   OAuth   ┌────────────┐
 │  Web /   │──────────▶│   auth     │
 │  Mobile  │           └─────┬──────┘
 │  client  │                 │ JWT
 │          │   REST/GraphQL  ▼
 │          │────────▶┌───────────────┐
 └──────────┘         │   gateway     │──┬──▶ profile
                      └───────┬───────┘  ├──▶ integrations ──▶ Todoist / Google / ...
                              │          └──▶ recommender ──▶ ml/serving (Python)
                              ▼
                      ┌───────────────┐
                      │    events     │ ◀── integrations emit normalized events
                      │  (Kafka/NATS) │ ──▶ ml/pipelines (features, training)
                      └───────────────┘
```

More detail in [`docs/architecture/`](docs/architecture/) and decisions in [`docs/adr/`](docs/adr/).

## Monorepo layout

See [`CLAUDE.md`](CLAUDE.md) for the full tree and conventions.

```
apps/        web, ios, android
services/    gateway, auth, profile, integrations, recommender, events, notifier
packages/    shared-types, sdk-js, ui
ml/          pipelines, features, registry, experiments, serving
infra/       docker, k8s, terraform, ci
docs/        architecture, adr, api
```

---

## AI stack

oO is AI-native. Domain-specialized agents pre-compute snippets describing the user's state from one angle each; an orchestrator LLM reasons over the assembled snippets and produces one tip (ADR-0013). The orchestrator iterates a registry, not a hardcoded list (ADR-0014) — adding an agent is a manifest change, nothing else.

### Three-tier layout

| Tier | Service | Purpose | Where |
|------|---------|---------|-------|
| Inference | **Ollama** | Local LLM + embedding; no data leaves the host | `localhost:11434` |
| Routing | **LiteLLM** | Unified OpenAI-compatible API; model aliases; cloud fallback | `llm.alogins.net` (Agap shared) |
| Testing | **OpenWebUI** | Prompt iteration, model comparison, manual evals | `ai.alogins.net` (Agap shared) |

### Tip generation pipeline (ADR-0013, M2)

```
User signals          Pre-compute agents (every 15 min)
(tasks, calendar,  ──▶ ml/agents/{overdue-task, momentum,        ──▶  agent_outputs
 patterns, time)        time-of-day, recent-patterns,                 (per-agent TTL)
                        focus-area, ...}
                                                                            │
                              Eligibility filter: required consents +       │
                              active context + per-user prefs (ADR-0014) ◀──┘
                                                ▼
                                  Orchestrator prompt (`v4-orchestrator`)
                                  = global prefs + active context + snippets
                                                ▼
                                    LiteLLM ──▶ Ollama (local) / cloud fallback
                                                ▼
                                         Tip shown to user
                                                ▼
                              User reaction (done / snooze / dismiss + dwell)
                                                ▼
                              Logged to tip_feedback for observability
                              (no online ML reward loop — see ADR-0013)
```

**Why LiteLLM as gateway:**  All LLM calls use a single `LITELLM_URL` env var. Swapping from qwen2.5 to llama3.2, or routing a fraction to Claude for A/B, is a config change in LiteLLM — zero code change in oO. The model name in `tip_scores` tells you exactly which model produced each tip.

**Why Ollama first:**  Tips contain personal context. Local inference means no user data leaves the host for the inference path. Cloud models (Anthropic, OpenAI) are opt-in fallbacks for evaluation and simulation only, gated behind `ANTHROPIC_API_KEY`.

### Models (planned; routes through LiteLLM)

| Alias | Model | Task |
|-------|-------|------|
| `tip-generator` | qwen2.5:1.5b (default) | Generate typed tip candidates from user context; local-first via Ollama |
| `embedder` | nomic-embed-text | Task clustering, semantic similarity for dedup; local via Ollama |
| `judge` | claude-haiku-4-5 (cloud, eval-only) | Offline sim judge; rates tip quality for A/B (requires `ANTHROPIC_API_KEY`) |

All model calls route through **LiteLLM** at `llm.alogins.net` (or `LITELLM_URL` env var) using model aliases. This decouples tip generation from model selection — swap the backend model in LiteLLM config without code changes. See ADR-0008.

---

## Roadmap

Issues and open work are tracked in [Gitea milestones](http://localhost:3000/alvis/oO/milestones). Pick an issue, check its milestone (= phase), read the service's `README.md`, ship.

### Phase 0 — Walking skeleton  *(M0)* ✓ shipped
Single user signs in with Google, connects Todoist, sees one random task on a black page. Deletion works. Auth, integrations, recommender stub, PWA, feedback loop, ToS/privacy, metrics baseline.

### Phase 1 — Real signal + in-the-moment delivery  *(M1)* ✓ shipped
Tips are picked, not drawn from a hat. Event bus, Todoist sync, task features, ε-greedy policy (v1 + v2), web push, NATS JetStream bridge, shadow-policy registry, offline sim framework, per-user profile features, admin + ML ops console (`apps/admin`).

### Phase 2 — AI tips + multi-source signals  *(M2)* ✓ shipped
Tips are AI-generated from user context. Multi-agent pipeline (ADR-0013): five pre-compute agents (`overdue-task`, `momentum`, `time-of-day`, `recent-patterns`, `focus-area`) emit prompt snippets; orchestrator LLM produces one tip. Unified Profile + agent registry + auto-inference framework (ADR-0014). LLM output validation + fallback. LiteLLM gateway, model benchmarking, prompt research, MLflow tracing.

### Phase 3 — Native mobile  *(M3)*
iOS (SwiftUI + APNs) and Android (Compose + FCM). `notifier` service gains APNs + FCM channels. Auth migrated from Auth.js to dedicated OIDC provider. Decide-and-deliver scheduler. See [M3 milestone](http://localhost:3000/alvis/oO/milestone/3).

### Phase 4 — MLOps at scale  *(M4)*
Retraining pipeline, feature-to-prompt batch jobs, prompt optimization loop, LLM fine-tuning on reaction signals, modular-monolith import-boundary lint, online experiments framework, drift monitoring. See [M4 milestone](http://localhost:3000/alvis/oO/milestone/4).

### Phase 5 — Production hardening  *(M5)*
Audit logging, key rotation, k3s → k8s, multi-region, public integration SDK, billing. See [M5 milestone](http://localhost:3000/alvis/oO/milestone/5).

---

## Contributing

This repo is split into independent modules; most tickets belong to exactly one. Pick an issue from [Gitea](http://localhost:3000/alvis/oO/issues), read the service's `README.md`, ship.

Conventions and per-service guidance live in [`CLAUDE.md`](CLAUDE.md).

## License

All rights reserved — 2026. Contact the owner for licensing inquiries.
(We'll switch to an OSS license for non-sensitive packages once the public SDK lands in Phase 5.)