| name | infrastructure-sia |
| description | Skill for the Self-Improvement Agent (SIA) harness contract. Use when validating task public/private layouts, generation artifact trees, evaluation runners, fixture replay loops, or opt-in live Meta→Target→Feedback cycles in template projects. |
SIA Harness
Deterministic harness for Meta → Target → Feedback generation loops with
public/private task splits. Implements contracts inspired by
hexo-ai/sia; does not vendor upstream code.
Commands
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
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 labelsreference/ — baseline target agent (reference/reference_target_agent.py required)
Exemplar project
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.
