fix: pass through unrecognized model names on native endpoints (fixes #67)#68
Merged
Merged
Conversation
…d of falling back to default
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Problem
In v2.8.8, the native-anthropic endpoint's model name resolution incorrectly falls back to the default model (gpt4o) when it encounters an unrecognized model name. This causes requests with valid Anthropic model names (e.g.,
claude-sonnet-4-20250514) to be silently redirected to a completely different model.Fix
Added an
as_isparameter toresolve_model_name(). Whenas_is=True, unrecognized model names are passed through as-is instead of falling back to the default model. Both native-anthropic and native-openai endpoints now use this pass-through mode, since they should forward the exact model name the user specified.Changes
src/argoproxy/models.py: Addedas_isparameter toresolve_model_name()src/argoproxy/endpoints/native_anthropic.py: Useas_is=Truefor model resolutionsrc/argoproxy/endpoints/native_openai.py: Useas_is=Truefor model resolutionFixes #67