Repository navigation
Conversation
…kend Hosted services that run open models in hardware enclaves and sign each response are a placement of the existing typed model capability, not a new provider. Record the two-step path: a configuration-only OpenAI-compatible offer beside the local one, then an adapter variant that verifies the attestation inside model-provider and records the verdict on the run. Hosted offers carry the privacy, cost, limit, and resolved-model facts docs/MODEL_PROVIDER.md already requires. Co-authored-by: Cursor <cursoragent@cursor.com>
Contributor
Author
|
Closing for now, as agreed. The attested hosted inference plan will come back reworked on the Runtime Inbox approval path. |
3 tasks
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
One paragraph under "AI and operator surfaces", docs only, stacked on
feat/0.7.1-integration@ 093b51c.Records the direction you and Rong converged on this week (NEAR/Venice-style enclave inference) as a planned
model-providerbackend rather than a new provider:open_ai_compatible_textoffer beside the local offer, so the Assistant treats local and attested-hosted placements as the same capability.docs/MODEL_PROVIDER.mdbefore publication; the external verifier is an audited dependency, not a trust root.No contract, code or schedule changes. Freeze-safe.
Made with Cursor
Part of #85.