feat: add new GPT-4.1 model variants to completion.go #966
Conversation
Codecov ReportAll modified and coverable lines are covered by tests ✅
Additional details and impacted files@@ Coverage Diff @@
## master #966 +/- ##
===========================================
- Coverage 98.46% 85.41% -13.05%
===========================================
Files 24 43 +19
Lines 1364 2263 +899
===========================================
+ Hits 1343 1933 +590
- Misses 15 308 +293
- Partials 6 22 +16 ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
|
@sashabaranov please review 🙏 |
|
Thank you! |
| GPT4Dot1Mini: true, | ||
| GPT4Dot1Mini20250414: true, | ||
| GPT4Dot1Nano: true, | ||
| GPT4Dot1Nano20250414: true, |
There was a problem hiding this comment.
we should flip this mapping to an inverse one, most of the models are not enabled for completion endpoint!
There was a problem hiding this comment.
Pull Request Overview
This pull request adds support for new GPT-4.1 series model variants by declaring new constants and updating the disabled models map in completion.go, along with adding corresponding tests in completion_test.go to ensure the completion endpoint does not support these models.
- Added new GPT-4.1 series model constants in completion.go.
- Updated the disabledModelsForEndpoints map to disable the new GPT-4.1 models.
- Introduced tests in completion_test.go to verify that requests using GPT-4.1 variants return the expected error.
Reviewed Changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated 2 comments.
| File | Description |
|---|---|
| completion.go | New model constants and updates to the disabled models map. |
| completion_test.go | Added tests to verify that GPT-4.1 series and related models are unsupported. |
| t.Run(model, func(t *testing.T) { | ||
| _, err := client.CreateCompletion( | ||
| context.Background(), | ||
| openai.CompletionRequest{ | ||
| MaxTokens: 5, | ||
| Model: model, | ||
| }, | ||
| ) | ||
| if !errors.Is(err, openai.ErrCompletionUnsupportedModel) { | ||
| t.Fatalf("CreateCompletion should return ErrCompletionUnsupportedModel for %s model, but returned: %v", model, err) |
There was a problem hiding this comment.
When using t.Run inside a loop, the loop variable 'model' may be captured by reference, which could lead to unexpected behavior. Consider assigning the loop variable to a local variable (e.g., 'm := model') before invoking t.Run.
| t.Run(model, func(t *testing.T) { | |
| _, err := client.CreateCompletion( | |
| context.Background(), | |
| openai.CompletionRequest{ | |
| MaxTokens: 5, | |
| Model: model, | |
| }, | |
| ) | |
| if !errors.Is(err, openai.ErrCompletionUnsupportedModel) { | |
| t.Fatalf("CreateCompletion should return ErrCompletionUnsupportedModel for %s model, but returned: %v", model, err) | |
| m := model // Create a new local variable to capture the current value of model | |
| t.Run(m, func(t *testing.T) { | |
| _, err := client.CreateCompletion( | |
| context.Background(), | |
| openai.CompletionRequest{ | |
| MaxTokens: 5, | |
| Model: m, | |
| }, | |
| ) | |
| if !errors.Is(err, openai.ErrCompletionUnsupportedModel) { | |
| t.Fatalf("CreateCompletion should return ErrCompletionUnsupportedModel for %s model, but returned: %v", m, err) |
Copilot uses AI. Check for mistakes.
| t.Run(model, func(t *testing.T) { | ||
| _, err := client.CreateCompletion( | ||
| context.Background(), | ||
| openai.CompletionRequest{ | ||
| MaxTokens: 5, | ||
| Model: model, | ||
| }, | ||
| ) | ||
| if !errors.Is(err, openai.ErrCompletionUnsupportedModel) { | ||
| t.Fatalf("CreateCompletion should return ErrCompletionUnsupportedModel for %s model, but returned: %v", model, err) |
There was a problem hiding this comment.
When using t.Run inside a loop, the loop variable 'model' may be captured by reference, which could lead to unexpected behavior. Consider assigning the loop variable to a local variable (e.g., 'm := model') before invoking t.Run.
| t.Run(model, func(t *testing.T) { | |
| _, err := client.CreateCompletion( | |
| context.Background(), | |
| openai.CompletionRequest{ | |
| MaxTokens: 5, | |
| Model: model, | |
| }, | |
| ) | |
| if !errors.Is(err, openai.ErrCompletionUnsupportedModel) { | |
| t.Fatalf("CreateCompletion should return ErrCompletionUnsupportedModel for %s model, but returned: %v", model, err) | |
| m := model // Assign loop variable to a local variable | |
| t.Run(m, func(t *testing.T) { | |
| _, err := client.CreateCompletion( | |
| context.Background(), | |
| openai.CompletionRequest{ | |
| MaxTokens: 5, | |
| Model: m, | |
| }, | |
| ) | |
| if !errors.Is(err, openai.ErrCompletionUnsupportedModel) { | |
| t.Fatalf("CreateCompletion should return ErrCompletionUnsupportedModel for %s model, but returned: %v", m, err) |
Copilot uses AI. Check for mistakes.
I've added new GPT-4.1 series.