ReferenceDemonstrated real incidentv1.22.1
In plain English
This page is reference material: definitions, schemas, catalogs, templates, and implementation records.
- Why this matters: AI risk can come from the whole arrangement, not one obvious model.
- What to look for: data, memory, routes, adapters, tools, evaluators, updates, and rollback paths.
- Technical version below: the expert terminology remains available and is linked through the glossary.
Composition Manifest Schema
A composition manifestA machine-readable record of the exact runtime composition used for an evaluation, release, incident, or rollback. Open glossary definition records base model hash, adapters and load order, merge coefficients, router version, prompt-policy version, memory snapshot identifier, tool permission profile, evaluator version, inference configuration, quantization configuration, deployment environment, and UTC timestamp.
{
"manifest_version": "1.0.0",
"composition_id": "comp-2026-06-26-001",
"created_at_utc": "2026-06-26T00:00:00Z",
"base_model": {"name": "example-base", "hash": "sha256:..."},
"adapters": [],
"router_version": "router-1",
"prompt_policy_version": "policy-1",
"memory_snapshot_identifier": "memsnap-1",
"tool_permission_profile": "read-only",
"evaluator_version": "eval-1",
"runtime": {}
}