# arubinochan-bot

Misskey のタイムラインを読み、ローカル LLM で「あるびのちゃん」として投稿する bot です。

To install dependencies:

```bash
bun install
```

To run:

```bash
bun run index.ts
```

Dry run without posting:

```bash
bun run index.ts --test
```

Useful runtime options:

```bash
bun run index.ts --test --harness speaker --politeness auto --sampling creative
```

- `--harness speaker`: default. Starts generation with `あるびのちゃん:\n` and parses the following body.
- `--harness tagged`: wraps output in a lightweight `<post>` envelope.
- `--harness json`: legacy JSON grammar harness.
- `--politeness auto`: default. Rephrases once only when the generated text does not look polite enough.
- `--politeness always`: always runs the style converter.
- `--politeness never`: disables style conversion.
- `--sampling creative`: default. Keeps the more idiosyncratic tone used by the bot.
- `--sampling model-default`: uses model-card-like sampling parameters for supported models.

Environment variables:

```env
MISSKEY_ORIGIN=https://misskey.example.net
MISSKEY_CREDENTIAL=XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
MODEL="LiquidAI/LFM2-2.6B-GGUF:Q5_K_M"
HARNESS="speaker"
POLITENESS="auto"
SAMPLING="creative"
```

Evaluation without posting:

```bash
bun run evaluate.ts --all-env --candidates --runs 1 --output .evaluation-results.jsonl
```

Resume a crashed/interrupted evaluation:

```bash
bun run evaluate.ts --all-env --candidates --runs 1 --output .evaluation-results.jsonl --resume
```

See [EVALUATION.md](./EVALUATION.md) for the harness/model comparison and the current recommendation.