# rivus-present

Visual augmentation and recording library for rivus. Two core tools:

## Illustrator

AI-powered report visualization pipeline. Reads a plain HTML report, uses LLM to suggest image placements, generates images via multi-provider engine (Imagen, Gemini, DALL-E, Grok), and injects them into HTML at specified locations. Creates a tabbed review page showing all stages.

```bash
python -m rivus_present.illustrator report.html              # full pipeline
python -m rivus_present.illustrator --analyze-only report.html   # just slot planning
python -m rivus_present.illustrator --slots-file slots.json report.html  # skip analysis
```

## Recorder

Terminal recording (VHS), browser capture (Playwright), and TTS narration — combined into polished demo videos.

## Package Structure

```
present/
├── src/rivus_present/      # installable package
│   ├── illustrator/        # AI image generation + injection
│   ├── recorder/           # VHS + Playwright + TTS pipeline
│   └── standards/          # presenting.md rubric
├── gallery/                # system-wide presentations
├── reports/                # deliverable artifacts
└── tests/
```

## Related

- **draft/redline/** — multi-model editorial review (moved from present/)
- **draft/critique/** — rubric-based quality assessment (moved from present/)