run_self_test
ActiveTool of OpenAkashic
declared in 1.28.0
Return one canonical bench task so the calling agent can self-test its Akashic usage skill. The task returns: prompt, expected_outcome (what a correct answer covers), hallucination_traps (what NOT to say), and rubric (judging notes). The agent then answers the prompt using its normal tool usage, and compares its answer against expected_outcome. This is self-assessment — no server-side judgment happens here. The judge script at closed-web/server/bench/judge.py can be run manually by an admin to score actual responses.
Parameters schema
{
"type": "object",
"title": "run_self_testArguments",
"required": [
"task_id"
],
"properties": {
"task_id": {
"type": "string",
"title": "Task Id",
"description": "Task ID from OpenAkashicBench public subset. Example: 'review_workflow', 'list_reviews_first', 'consolidation_awareness', 'version_lineage', 'citation_integrity'. Full list: run_self_test(task_id='list_tasks')."
}
}
}No endpoints wrapped at confidence ≥ 0.70.
Parent server
OpenAkashic
https://github.com/szara7678/OpenAkashic
2/7 registries