Add support for the OpenAI API by levigross · Pull Request #242 · google/adk-go

levigross · 2025-11-10T01:56:14Z

This PR enables basic support for OpenAI models (and endpoints that expose a OpenAI API compatible API interface).

I am stressing on basic support because we will leave tool calling to the next PR :)

gemini-code-assist · 2025-11-10T01:56:32Z

Summary of Changes

Hello @levigross, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request lays the groundwork for integrating OpenAI models into the system. It establishes the necessary components to send requests, process responses, and manage streaming interactions with OpenAI's API, ensuring compatibility with existing LLM interfaces. The current implementation focuses on core generation capabilities, with plans to extend support for advanced features like tool calling in future iterations.

Highlights

OpenAI API Integration: Introduced basic support for interacting with the OpenAI API, enabling the system to send requests to OpenAI models and compatible endpoints.
Dependency Management: Added the official github.com/openai/openai-go/v3 Go client library and several github.com/tidwall JSON utility libraries to go.mod and go.sum.
Core OpenAI Model Implementation: Created a new openai package under model/ with openAIModel implementing the model.LLM interface, handling both streaming and non-streaming content generation.
Request and Response Conversion: Developed comprehensive logic to convert generic LLMRequest objects into OpenAI-specific request parameters and to transform OpenAI API responses back into the generic genai.GenerateContentResponse format.
Streaming Event Handling: Implemented a streamTranslator to process and buffer OpenAI streaming events, particularly for accumulating function call arguments, ensuring proper reconstruction of streamed responses.
Error Handling and Constants: Defined specific error types (errors.go) and event type constants (consts.go) for the OpenAI integration to improve clarity and maintainability.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	`/gemini review`	Performs a code review for the current pull request in its current state.
Pull Request Summary	`/gemini summary`	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	`/gemini help`	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

gemini-code-assist

Code Review

This pull request introduces basic support for the OpenAI API by creating an adapter that conforms to the project's model.LLM interface. The implementation is well-structured, separating concerns like request building, response parsing, and stream handling into their own files. However, I've identified a few critical issues, including a couple of compilation errors and incorrect pointer semantics in the model constructor. I also found a potential race condition in stream handling and a gap in error handling for function call tracking. Addressing these points will significantly improve the robustness and correctness of this new integration.

model/openai/errors.go

model/openai/openai.go

model/openai/stream.go

model/openai/request.go

cpunion · 2025-11-11T14:31:48Z

model/openai/openai.go

+	return m.generate(ctx, params)
+}
+
+func (m *openAIModel) generate(ctx context.Context, params responses.ResponseNewParams) iter.Seq2[*model.LLMResponse, error] {


Could you please support chat completion? it's better for compatible with most providers.

This PR enables basic support for OpenAI models (and endpoints that expose a OpenAI API compatible API interface). I am stressing on *basic* support because we will leave tool calling to the next PR :)

levigross · 2025-11-12T16:17:10Z

@gemini-code-assist please rereview this code

gemini-code-assist

Code Review

This pull request introduces a comprehensive and well-structured adapter for the OpenAI API, implementing the model.LLM interface. The implementation covers request and response conversion, streaming support, and robust error handling for unsupported features. The code is well-tested with good unit and integration test coverage.

My main feedback is a critical issue in NewModel that will prevent compilation due to an attempt to access an unexported field on the openai.Client struct. I've provided suggestions to refactor this to use a pointer to the client, which is a more idiomatic and robust approach for validation in Go. Once this is addressed, the package should be in great shape.

gemini-code-assist · 2025-11-12T16:19:45Z

model/openai/openai.go

+func NewModel(_ context.Context, modelName string, client openai.Client) (model.LLM, error) {
+	// We drop the context because OpenAI doesn't take a context when creating a new Client
+	if modelName == "" {
+		return nil, ErrModelNameRequired
+	}
+	if len(client.Options) == 0 {
+		return nil, ErrClientRequired
+	}
+	return &openAIModel{
+		client: &client,
+		name:   modelName,
+	}, nil


To fix the compilation issue with client.Options and improve the function's contract, the signature of NewModel should be changed to accept a pointer to an openai.Client. This allows for a nil check to validate the client's presence.

Consequently, the openAIModel struct should store this pointer directly.

Suggested change

func NewModel(_ context.Context, modelName string, client openai.Client) (model.LLM, error) {

// We drop the context because OpenAI doesn't take a context when creating a new Client

if modelName == "" {

return nil, ErrModelNameRequired

}

if len(client.Options) == 0 {

return nil, ErrClientRequired

}

return &openAIModel{

client: &client,

name: modelName,

}, nil

func NewModel(_ context.Context, modelName string, client *openai.Client) (model.LLM, error) {

// We drop the context because OpenAI doesn't take a context when creating a new Client

if modelName == "" {

return nil, ErrModelNameRequired

}

if client == nil {

return nil, ErrClientRequired

}

return &openAIModel{

client: client,

name: modelName,

}, nil

}

gemini-code-assist · 2025-11-12T16:19:46Z

model/openai/openai_test.go

+		option.WithBaseURL(server.URL+"/v1"),
+	)
+
+	llm, err := NewModel(t.Context(), openai.ChatModelGPT4oMini, client)


To align with the proposed change of NewModel accepting a pointer to openai.Client, you need to pass the address of the client here.

Suggested change

llm, err := NewModel(t.Context(), openai.ChatModelGPT4oMini, client)

llm, err := NewModel(t.Context(), openai.ChatModelGPT4oMini, &client)

gemini-code-assist · 2025-11-12T16:19:46Z

model/openai/openai_test.go

+	tests := []struct {
+		name      string
+		modelName openai.ChatModel
+		client    openai.Client
+		wantErr   error
+	}{
+		{
+			name:      "missing model name",
+			modelName: "",
+			client:    client,
+			wantErr:   ErrModelNameRequired,
+		},
+		{
+			name:      "missing client",
+			modelName: openai.ChatModelGPT4o,
+			client:    openai.Client{},
+			wantErr:   ErrClientRequired,
+		},
+	}


Following the suggested change in openai.go to use a pointer for the openai.Client, this test table needs to be updated to reflect the new signature of NewModel. The client field in the test struct should be a pointer, and the test cases should be adjusted accordingly. For the "missing client" case, nil should be passed to trigger ErrClientRequired.

Suggested change

tests := []struct {

name string

modelName openai.ChatModel

client openai.Client

wantErr error

}{

{

name: "missing model name",

modelName: "",

client: client,

wantErr: ErrModelNameRequired,

},

{

name: "missing client",

modelName: openai.ChatModelGPT4o,

client: openai.Client{},

wantErr: ErrClientRequired,

},

}

tests := []struct {

name string

modelName openai.ChatModel

client *openai.Client

wantErr error

}{

{

name: "missing model name",

modelName: "",

client: &client,

wantErr: ErrModelNameRequired,

},

{

name: "missing client",

modelName: openai.ChatModelGPT4o,

client: nil,

wantErr: ErrClientRequired,

},

}

levigross · 2025-11-18T21:14:08Z

@dpasiukevich What do I need to do to get this PR reviewed? 😀

YouChenJun · 2025-12-02T10:31:44Z

Thank you for contributing this PR to add support for the OpenAI API! This is a highly valuable feature that will greatly improve the flexibility of the project.
We noticed there are some merge conflicts now. Could you please help resolve them when you have time? This will help move the PR forward for merging.
Let us know if you need any support from our side. Thanks again for your great work! @levigross

YouChenJun · 2025-12-02T10:31:44Z

Thank you for contributing this PR to add support for the OpenAI API! This is a highly valuable feature that will greatly improve the flexibility of the project.
We noticed there are some merge conflicts now. Could you please help resolve them when you have time? This will help move the PR forward for merging.
Let us know if you need any support from our side. Thanks again for your great work! @levigross

dangkaka · 2025-12-16T17:02:53Z

hi, any updates on this?

yafengio · 2026-01-21T01:17:09Z

hi, any updates ?

wjkoh · 2026-01-28T14:58:19Z

There are currently two PRs under review and one third-party implementation:

Since the review process for both PRs seems to be lagging, could we merge a basic feature set first and improve it incrementally later? I realize that achieving full OpenAI API compatibility is a significant undertaking, and starting with a core version might be more efficient. @byebyebruce

dpasiukevich · 2026-01-28T15:00:51Z

Folks, sry for the lack of reply here.

We're a bit not sure on the best mechanism for long-term support of ecosystem models, let's redirect this to adk-go-community repo to unblock for now.

dpasiukevich · 2026-01-28T15:01:40Z

Let me setup the https://github.com/google/adk-go-community and return back here.

Let's keep and grow the stuff there with more models, tools, plugins etc.

Kenasvarghese · 2026-02-16T06:33:50Z

@dpasiukevich
Hi, Any update on the adk-go-community
or any other solutions to use openai models

YouChenJun · 2026-02-16T06:34:27Z

邮件已收到！我会尽快给您回复。

wjkoh · 2026-02-23T07:55:56Z

Let me setup the https://github.com/google/adk-go-community and return back here.

Gentle reminder: Is the adk-go-community repository still coming, or has the decision changed?

dharmjit · 2026-02-23T17:09:33Z

Any updates on the way forward?

marc1161 · 2026-02-27T11:01:50Z

Same here, any updates on this?

honky-tonk · 2026-03-05T06:45:12Z

Any updates? guys

gemini-code-assist bot reviewed Nov 10, 2025

View reviewed changes

model/openai/errors.go Outdated Show resolved Hide resolved

model/openai/openai.go Show resolved Hide resolved

model/openai/stream.go Show resolved Hide resolved

model/openai/request.go Show resolved Hide resolved

levigross force-pushed the main branch from 99b0083 to a4f8c34 Compare November 10, 2025 04:25

cpunion reviewed Nov 11, 2025

View reviewed changes

Add support for the OpenAPI models

f942078

This PR enables basic support for OpenAI models (and endpoints that expose a OpenAI API compatible API interface). I am stressing on *basic* support because we will leave tool calling to the next PR :)

levigross force-pushed the main branch from a4f8c34 to f942078 Compare November 11, 2025 14:35

gemini-code-assist bot reviewed Nov 12, 2025

View reviewed changes

dpasiukevich mentioned this pull request Nov 14, 2025

Is there plans to support Azure/Bedrock here? #289

Open

sammcj mentioned this pull request Nov 15, 2025

Support for any OpenAI compatible API provider / model #295

Closed

cpunion mentioned this pull request Nov 26, 2025

feat: add support for OpenAI-compatible third-party provider #342

Open

levigross and others added 2 commits December 2, 2025 15:11

Merge branch 'main' into main

b9c6ee4

Run go mod tidy

2846ff8

git-hulk mentioned this pull request Feb 17, 2026

Add support of the anthropic model #233

Open

	llm, err := NewModel(t.Context(), openai.ChatModelGPT4oMini, client)
	llm, err := NewModel(t.Context(), openai.ChatModelGPT4oMini, &client)

Conversation

levigross commented Nov 10, 2025

Uh oh!

gemini-code-assist bot commented Nov 10, 2025

Summary of Changes

Highlights

Footnotes

Uh oh!

gemini-code-assist bot left a comment

Choose a reason for hiding this comment

Code Review

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

cpunion Nov 11, 2025

Choose a reason for hiding this comment

Uh oh!

levigross commented Nov 12, 2025

Uh oh!

gemini-code-assist bot left a comment

Choose a reason for hiding this comment

Code Review

Uh oh!

gemini-code-assist bot Nov 12, 2025

Choose a reason for hiding this comment

Uh oh!

gemini-code-assist bot Nov 12, 2025

Choose a reason for hiding this comment

Uh oh!

gemini-code-assist bot Nov 12, 2025

Choose a reason for hiding this comment

Uh oh!

levigross commented Nov 18, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

YouChenJun commented Dec 2, 2025

Uh oh!

YouChenJun commented Dec 2, 2025

Uh oh!

dangkaka commented Dec 16, 2025

Uh oh!

yafengio commented Jan 21, 2026

Uh oh!

wjkoh commented Jan 28, 2026

Uh oh!

dpasiukevich commented Jan 28, 2026

Uh oh!

dpasiukevich commented Jan 28, 2026

Uh oh!

Kenasvarghese commented Feb 16, 2026

Uh oh!

YouChenJun commented Feb 16, 2026 via email

Uh oh!

wjkoh commented Feb 23, 2026

Uh oh!

dharmjit commented Feb 23, 2026

Uh oh!

marc1161 commented Feb 27, 2026

Uh oh!

honky-tonk commented Mar 5, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

11 participants

levigross commented Nov 18, 2025 •

edited

Loading