feat(models): InferenceGateway intersection + Model Catalog/Leaderboard cockpit (gap #8) - #271
Merged
Merged
Conversation
…Leaderboard cockpit (gap #8) Start at the cloud∩local intersection, then fan out. InferenceGateway is the shared serving seam both prophet-platform (model-fabric) and agent-machine (local) adapt to, with the existing GatewayCallAudit as the shared per-call receipt; consent-gated fail-closed. Model Catalog & Leaderboard surface = the live cockpit screen: every foundation model + OS capability, cloud/local/both placement, sovereignty×governance-weighted board, and the SP-vs-Claude-Enterprise positioning (DRAFT/VERIFY-gated). Feed-driven + producer + tests.
This was referenced Aug 3, 2026
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Closes campaign gap #8 the way you asked — start at the intersection, then fan out (#267).
inference-gateway-intersection.md— the shared model-serving seam. Both the cloud plane (prophet-platformmodel-fabric) and the local plane (agent-machine/noetica) adapt to oneInferenceGatewaycontract, emitting the existingGatewayCallAudit(memory-mesh) on every call; consent-gated, fail-closed. Build the intersection first (open-weight models that run both = the client-owned LLM-stable), then fan out to cloud-only (Claude API) and local-only (on-node SLM).docs/surfaces/model-catalog.html— the live cockpit screen: every foundation model + OS capability, cloud∩local placement, a sovereignty × governance-weighted leaderboard (not raw capability alone — the thesis), and the SP-vs-Claude-Enterprise positioning (governs people vs governs agents, supplier/competitor/component, LLM-stable). Competitive claims marked DRAFT · VERIFY per the source doc's gates.data/model-catalog.json+ producer + LIVE/SAMPLE badge);build_surface_feed.pyextended (8 tests green).Each model/capability then fans out to a screen in prophet-platform · lattice · notebooks · leaderboards — all reading the same catalog + audit stream.
Verified: feed valid; 8 pytest pass; producer round-trips.