# Jobhunt Platform

An AI-assisted job-hunt platform where **you stay in control**. The system discovers jobs, scores them against your profile, drafts application material and prepares sends — but nothing external ever happens without your explicit approval.

Open source. Self-hosted. Single-user first, multi-user later.

## Core ideas

1. **Approval gate, architecturally enforced.** Every external action (send email, submit application) requires a server-side confirmed `Approval` referencing the exact artifact hash. No approval row, no send. This is a hard constraint, not a style guide.
2. **State machine owns the flow, LLM answers questions inside it.** Pipeline transitions live in a table. The LLM scores, extracts, critiques and suggests — it never picks the next step. Deterministic orchestration, probabilistic judgment.
3. **Per-task model routing with token budgets.** Cheap model for extraction/scoring, strong model for prose review, budgets enforced per task so the bill stays boring.
4. **The user drafts, the system reviews.** Measured reality: human-drafted prose outperforms full AI drafts. Default cover-letter flow is user-writes, AI-reviews with tracked suggestions.

## Architecture

```
apps/web          Vue 3 + Vite + Tailwind — tabs: CV editor, Research, Applications (kanban), Application detail
apps/api          FastAPI + PostgreSQL — REST API, state machine, scheduler, approval enforcement
packages/
  llm-gateway/    Model routing, per-task budgets, structured JSON IO, retry/fallback policy
  connectors/     Job source adapters -> normalized JobPosting (LinkedIn read-focused, jobindex, paste-a-URL)
  artifacts/      CV + cover-letter generation: Jinja templates -> PDF (fpdf2), versioning, hashing
docs/             ADRs, data model, API contract, worker task cards
```

## Pipeline

```
discovered -> scored -> approved -> drafting -> sent -> interviewing -> offer -> closed
                    \-> rejected (by user)      \-> expired
```

External comms are only possible from `approved`/`drafting` states, and only with a matching confirmed `Approval`.

## Quick start (POC)

```bash
cp .env.example .env   # add LLM provider keys (no key = mock mode, deterministic)

# Backend tests + live API (DinD-safe: everything runs inside the compose network)
docker compose run --rm api-test                                    # 47 pytest tests
docker rm -f jobhunt-api-poc 2>/dev/null; \
docker compose run -d --name jobhunt-api-poc \
  --entrypoint "uvicorn app.main:app --host 0.0.0.0 --port 8000" api-test
docker exec jobhunt-api-poc curl -s localhost:8000/api/health       # {"status":"ok"}

# Frontend (host): Vue dev server proxies to the API
cd apps/web && npm install && VITE_API_BASE=http://localhost:8000/api npm run dev

# Packages (host, no DB needed): artifacts + llm-gateway unit tests
cd packages/artifacts && uv venv && . .venv/bin/activate && uv pip install -e ".[dev]" && pytest -q
cd packages/llm-gateway && uv venv && . .venv/bin/activate && uv pip install -e ".[dev]" && pytest -q
```

Note: in sandboxed Docker-in-Docker environments host port publishing may not work; run curl/docker exec against the `jobhunt-api-poc` container directly, as above.

## Status

POC scaffolding in progress. See `docs/` for the design.

## Screenshots

Screenshots will be added here as the UI stabilizes.

| View | Description | Screenshot |
|------|-------------|------------|
| Today | Daily digest with top matches, nudge cards, and cost summary | _placeholder_ |
| Onboarding Wizard | Welcome, CV import, postings fetch, done steps | _placeholder_ |
| CV Editor | Profile form, sections list, AI assist, PDF render | _placeholder_ |
| Research | Postings table with fetch form, scam column, and scoring | _placeholder_ |
| Applications Kanban | Drag-and-drop board with red-flag badges and nudge dots | _placeholder_ |
| Application Detail | Posting info, interview prep modal, cover letter, approval gate | _placeholder_ |