---
name: docxology/infrastructure-sia
source: https://app.decimal.ai/s/docxology-infrastructure-sia@1/SKILL.md
source_sha256: e40c7bfdefdd
---

# SIA Harness

Deterministic harness for Meta → Target → Feedback generation loops with
public/private task splits. Implements contracts inspired by
[hexo-ai/sia](https://github.com/hexo-ai/sia); does not vendor upstream code.

## Commands

```bash
uv run python -m infrastructure.sia.cli validate projects/templates/template_sia/tasks/mini_classify
uv run python -m infrastructure.sia.cli inspect-run RUN_SUMMARY_JSON [--json]
uv run python scripts/pipeline/stage_02_analysis.py --project templates/template_sia
```

## Public API

```python
from infrastructure.sia import (
    RunConfig,
    TaskLayout,
    load_agent_execution,
    run_evaluation,
    run_sia_loop,
    validate_task_dir,
)
```

## Task layout

Each task directory exposes:

- `data/public/` — agent-visible inputs
  - `data/public/task.md` — required task description (`validate_task_dir` hard-fails if absent)
  - `data/public/evaluate.py` — writes `results.json` with `metric_name`, `metric_value`, `n_samples`
- `data/private/` — evaluation-only labels
- `reference/` — baseline target agent (`reference/reference_target_agent.py` required)

## Exemplar project

[`projects/templates/template_sia/`](../../projects/templates/template_sia/) runs
fixture replay by default (`live=False`). Pass `--live-sia` on
`scripts/run_sia_loop.py` for opt-in Ollama-backed feedback (not CI) — the
feedback note is illustrative, not applied; live mode performs no code mutation
and uses no sandbox, so cross-generation improvement is shown only via fixtures.