ai-provider-mock

Enterprise Part of the commercial Kumiko Enterprise offering — not in the open framework.

Registers a scriptable in-memory LLM as the "mock" provider in ai-foundation, for use in demos, sample apps, and integration tests that need the full ai-foundation roundtrip without a real API call. Call getMockProvider(tenantId).script(...) to pre-load responses before exercising a feature handler. Not for production — returns a placeholder message when no script is queued.

Build it yourself

This Enterprise implementation is optional. If you need a narrower or domain-specific version, you can build a provider adapter with Kumiko’s public extension points.

Use this package when you want the maintained implementation, its existing contracts, and the surrounding operational behavior. A custom implementation is not drop-in compatible automatically: your app owns its authorization, validation, provider integration, tests, security review, and production operations.

Start with Features and composition and the provider registration of AI foundation.

How it fits

What this feature needs to run (Requires).

flowchart TB
  n_ai_provider_mock["ai-provider-mock"]
  subgraph how_reqs["Requires"]
    n_ai_foundation["ai-foundation"]
  end
  n_ai_foundation --> n_ai_provider_mock

Dependencies

• Requires: ai-foundation
• Activation: always on (not toggleable)

Extensions & cross-feature APIs

• Registers extension: llmProvider → mock