refactor: split disabled models for endpoints mapping into chat completions endpoint-disabled and completions endpoint-enabled mappings #974
+62
−67
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Outdated suggestions cannot be applied.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.
Describe the change
This PR refactors model mapping logic by splitting the original
disabledModelsForEndpoints
map into two distinct maps:disabledModelsForChatCompletionsEndpoint
andenabledModelsForDeprecatedCompletionsEndpoint
.This improves clarity and simplifies future maintenance of model support across endpoints.
Provide OpenAI documentation link
Describe your solution
Created
disabledModelsForChatCompletionsEndpoint
to list models not supported by the chat completions endpoint. Maintaining a deny list is simpler since most new models are supported by chat completions by default.Created
enabledModelsForDeprecatedCompletionsEndpoint
to list models that are supported by the legacy completions endpoint. Maintaining an allow list is more appropriate here, since the completions endpoint is deprecated and no longer widely supported.Tests
Executed the verification command provided in the
CONTRIBUTING.md
file. All tests passed successfully and the refactor did not introduce any regressions.Issue: #972.