fix(opencode-config): parse all model capabilities from schema - #917
Open
mihado wants to merge 5 commits into
Open
fix(opencode-config): parse all model capabilities from schema#917mihado wants to merge 5 commits into
mihado wants to merge 5 commits into
Conversation
The JSON serializer doesn't preserve map insertion order — models come back in key-sorted order. Sort before comparing.
|
@mihado is attempting to deploy a commit to the Caspian's Team Team on Vercel. A member of the Team first needs to authorize it. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
I was using Helmor with a custom OpenAI compatible server and found out that Helmor does not preserve the capabilities provided from the server. The opencode config got replaced with the default values as defined in the source code.
I'm making this draft PR for early feedback (working extensively with Minimax & GPT-5.4 and using CI for tests). If this is the right direction I'll setup proper toolchain and test locally.
This change:
CustomProviderModelto carry OpenCode capability fields through the provider pipeline/v1/modelsparser to read those fieldsBehavior
reasoning→ fallbacktruetool_call→ fallbackfalsetemperature→ fallbackfalseattachment→ fallbackfalse