Bump opengradient floor to >=1.1.1 (surface current TEE models)#15
Merged
Merged
Conversation
The model list og-veil shows (and serves at /v1/models) is derived from the SDK's TEE_LLM enum. The lock pinned opengradient 1.1.0, whose enum predates deepseek-v4-pro -- so 'og-veil models' omitted a model the gateway actually serves. Bump the floor to 1.1.1 and regenerate the lock so the enum (and the listing) is current. Note: glm-5.2 is in the SDK's main but not yet released; once a release includes it, bump again to surface it here.
|
Review the following changes in direct dependencies. Learn more about Socket for GitHub.
|
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
og-veil modelsandGET /v1/modelsare derived from the SDK'sTEE_LLMenum (veil/server.py:35). The lockfile pinnedopengradient==1.1.0, whose enum predates deepseek-v4-pro -- soog-veil modelsomitted a model the gateway actually serves (verified live:deepseek-v4-proreturns a TEE-verified completion through the relay).Bump the floor to
opengradient>=1.1.1and regenerateuv.lockso the enum -- and the model listing -- is current.Note:
glm-5.2is already in the SDK'smain(GLM_5_2 = "zai/glm-5.2") but not in a published release yet, so it still won't appear until the SDK cuts a release that includes it; bump again then.