feat: add governed model registry and adapter routing - #11
Merged
Merged
Conversation
Adds ModelCard, AdapterProfile, BenchmarkRun, DeploymentRevision, and RoutePolicy records loaded from a declarative catalog. Production models require evaluation evidence, adapters with unresolved regressions cannot be promoted, and adapters must reference a known base revision.
Builds routing profiles, policy version, and cache fingerprint from the registry, selects the best measured LoRA adapter for a request domain, and reports model card, adapter, and deployment records through authenticated registry endpoints.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Implements sections 7.5, 8, and 11 of the design specification.
config/registry.yamlis the only source of servable models; requests can never introduce a model path, revision, or adapter.routing.domainselects the promoted adapter with the largest measured quality gain for the chosen base revision and task.Tests: 14 unit, 9 integration, 2 Playwright end-to-end. Local suite 68 passed.