Skip to Content
Aionis v0.3.2 is the current Runtime baseline for SDK/API hosts, MCP clients, plugins, Substrate-backed recall, and self-managed agent loops.

Measure

POST /v1/measure

Build an effect report from a guide loop, manual comparison, or product trace.

Measure is used for operator reporting, benchmark analysis, and admission policy evaluation. It does not execute tools.

Request body

Send either:

ShapeRequired fields
Manual pairbaseline and aionis observations.
Product traceproduct_trace with after_guide and either baseline or before_guide.

Optional fields:

FieldTypeDescription
tenant_id / scopestringIdentity boundary.
taskobjecttask_id, run_id, task_signature, task_family, workflow_signature.
minEffectDeltanumberMinimum effect delta for pass/fail scoring.
minAionisScorenumberMinimum Aionis score for scoring.
comparisonobjectComparison mode and run IDs.
evidence_idsstring[]Evidence IDs supporting the measurement.

Example

curl -s http://127.0.0.1:3001/v1/measure \ -H 'content-type: application/json' \ -d '{ "tenant_id": "default", "scope": "checkout-migration", "task": { "run_id": "run-001", "task_signature": "checkout-migration" }, "product_trace": { "baseline": { "label": "before-guide" }, "after_guide": { "agent_context": {}, "repeated_discovery_steps": 0 }, "forget_result": { "operation": "activate" }, "sufficient_evidence": true } }'

SDK

const measure = await aionis.measure({ task: { run_id: "run-001", task_signature: "checkout-migration", }, product_trace: { baseline: { label: "before-guide" }, after_guide: { agent_context: guide.agent_context, }, forget_result: feedback, sufficient_evidence: true, }, });

Response

FieldMeaning
contract_versionaionis_measure_result_v1.
measurement_inputNormalized input used by the evaluator.
effect_reportProduct-level effect report.
memory_decision_traceIncluded when measuring from product trace.
memory_decision_auditIncluded when measuring from product trace.
kernel_reportLow-level scoring output.