feat: add new GPT-4.1 model variants to completion.go

[iktakahiro]

I've added new GPT-4.1 series.

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 85.41%. Comparing base (774fc9d) to head (97761ca).
Report is 89 commits behind head on master.

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.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

[zarifaziz]

@sashabaranov please review 🙏

[sashabaranov]

Thank you!

[sashabaranov]

we should flip this mapping to an inverse one, most of the models are not enabled for completion endpoint!

[Copilot]

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.

[Copilot]

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.

Suggested change

	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]

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.

Suggested change

	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)