Agent OS · Component · companion-evaluation-contracts
Companion evaluations and API contracts
What it does
Provides scenario evaluations, domain regression tests and exported Zod/OpenAPI contracts for validating companion behavior and client integration.
Core pattern
Scenario and interface contract checks + behavior regression
- Input
- Scenario requests and expected behavior
- Output
- Evaluation results, contract failures and OpenAPI documentation
Key parameters
| Name | Type | Default | Values |
|---|---|---|---|
| operation | string | evaluate | evaluate · regress · export_openapi |
| cases | array | — | — |
| model_config | — | — | — |
| locale | — | — | — |
| base_url | — | — | — |
Maturity and limits
Dedicated eval script, broad domain tests and contract export tooling exist; tests were not executed for this inventory. Phase 2: source paths and implementation inspected statically; tests and external integrations were not executed. Maturity rates repository implementation, not a verified production deployment.
Passing scripted evaluations would not establish clinical safety or production reliability.
1 sentence citing source paths or vendor names omitted for publication.
Used in pipelines
Not part of a pipeline yet; available as a standalone component.
Industry tags
- Lifestyle & consumer appsSource-supported industry
For work involving opt-in interactions, digital services and personal preferences, use scenario and interface contract checks followed by behavior regression.
- EducationTransferable use
For sample acceptance checks before releasing a course question assistant, use scenario and interface contract checks followed by behavior regression.
Skills pack
Contract scaffold and deterministic mock
Download · 11KBSHA-256 b66899c278d354bae9eef12633fadc4d4c47a22ca3fb3580043bf85a8a67cd68
Related components
-
Local coding-agent execution governance
Pre-action policy decisions + human permission and audit
Working 1 pipeline -
Collaborative delivery, approvals and evidence gates
Draft and artifact versioning + human handoff approval
Working 4 pipelines -
Tenant identity, enterprise SSO, provisioning and access control
Organization membership sync + scoped role access
Working 1 pipeline