feat(openai): implement llm client interface #276

kasanatte · 2025-09-26T12:31:27Z

What type of PR is this?
/kind feature

What this PR does / why we need it:
This PR implements the interface for connecting to the OpenAI API. It provides helper functions to create a configured OpenAI client based on the application's settings. This is a core component for providing the LLM capabilities to the AI Assistant.

Which issue(s) this PR fixes:
Part of #273

Special notes for your reviewer:
It depends on the changes from PR #274

Does this PR introduce a user-facing change?:

NONE

gemini-code-assist · 2025-09-26T12:31:41Z

Summary of Changes

Hello @kasanatte, 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's Large Language Model (LLM) capabilities into the AI Assistant. It establishes a robust and thread-safe mechanism for configuring and accessing the OpenAI API, which is a critical prerequisite for all future LLM-powered features. The changes focus on setting up the core client and configuration management without introducing any user-facing functionality yet.

Highlights

New OpenAI Interface: Introduces a new pkg/openai package dedicated to managing connectivity and configuration for the OpenAI API.
Client Configuration and Retrieval: Provides helper functions, InitOpenAIConfig and GetOpenAIClient, to initialize and retrieve a properly configured OpenAI client based on application settings, including API key and endpoint.
Thread-Safe Access: Implements sync.RWMutex to ensure thread-safe access and modification of the global OpenAI configuration, preventing race conditions.
Model and Configuration Status: Includes functions GetOpenAIModel to retrieve the configured OpenAI model (with a default fallback) and IsOpenAIConfigured to check if the OpenAI integration is properly set up.

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 adds a new package to interface with the OpenAI API. The implementation is straightforward, using global variables and a mutex for configuration management. My review includes two main suggestions to improve the design. First, I recommend decoupling the new openai package from the application-specific options package by passing configuration primitives instead of the whole options struct. Second, for efficiency, I suggest caching the OpenAI client instance instead of creating a new one on every request. These changes will enhance the code's modularity, testability, and performance.

pkg/openai/config.go

warjiang · 2025-10-20T04:09:23Z

pkg/openai/config.go

+		return nil, errors.New("OpenAI not initialized, call InitOpenAIConfig first")
+	}
+
+	if globalOpenAIOptions.OpenAIAPIKey == "" {


rename the key for LLMAPIKey

warjiang · 2025-10-20T04:09:31Z

pkg/openai/config.go

+	}
+
+	config := openai.DefaultConfig(globalOpenAIOptions.OpenAIAPIKey)
+	if globalOpenAIOptions.OpenAIEndpoint != "" {


warjiang · 2025-10-20T04:11:43Z

pkg/openai/config.go

+)
+
+// InitOpenAIConfig initializes OpenAI configuration from Options.
+func InitOpenAIConfig(opts *options.Options) {


rm the opts *options.Options

kasanatte · 2025-10-21T14:14:17Z

/gemini review

gemini-code-assist

Code Review

This pull request introduces an interface for connecting to the OpenAI API, providing helper functions to create a configured OpenAI client based on the application's settings. The changes include renaming OpenAI to LLM to support more general LLMs, adding the go-openai library as a dependency, and implementing the core logic for initializing and retrieving the LLM client and model configuration. The code also includes unit and integration tests to ensure the functionality works as expected. I have identified some areas for improvement, primarily focusing on error handling and code clarity.

pkg/llm/client.go

pkg/llm/integration_test.go

warjiang · 2025-10-22T16:41:32Z

/assign

warjiang · 2025-10-22T16:42:18Z

@kasanatte it seems that there are some conflicts, plz resovle the conflicts first

pkg/llm/client.go

warjiang · 2025-10-28T16:56:22Z

pkg/llm/errors.go

+
+// Sentinel errors for LLM package.
+// These errors can be used with errors.Is() for error type checking.
+var (


good practice 👍

pkg/llm/integration_test.go

warjiang · 2025-10-28T17:23:53Z

pkg/mcpclient/test_mcp_server.go

-	arguments := request.Params.Arguments
-	message, ok := arguments["message"].(string)
-	if !ok {
+	message, err := request.RequireString("message")


cool ~ learn from that ~

warjiang · 2025-10-28T17:25:45Z

thank, I think this PR is ready to be merged after the issues be resolved @kasanatte

Signed-off-by: kasanatte <[email protected]>

warjiang · 2025-10-29T15:11:05Z

pkg/llm/config.go

+// Validate verifies that the configuration contains valid values.
+// It checks for required fields and validates the endpoint URL format.
+func (c *Config) Validate() error {
+	// Validate API key
+	if c.LLMAPIKey == "" {
+		return ErrLLMAPIKeyNotConfigured
+	}
+
+	// Validate endpoint URL if provided
+	if c.LLMEndpoint != "" {
+		if _, err := url.Parse(c.LLMEndpoint); err != nil {
+			return errors.Join(ErrInvalidEndpoint, err)
+		}
+	}
+
+	return nil
+}


it looks better now

warjiang · 2025-10-29T15:11:48Z

/retitle feat(openai): implement llm client interface

warjiang · 2025-10-29T15:12:53Z

thanks ~ let's move the PR forward

warjiang · 2025-10-29T15:12:57Z

/lgtm
/approve

karmada-bot · 2025-10-29T15:13:07Z

[APPROVALNOTIFIER] This PR is APPROVED

This pull-request has been approved by: warjiang

The full list of commands accepted by this bot can be found here.

The pull request process is described here

Needs approval from an approver in each of these files:

~~OWNERS~~ [warjiang]

Approvers can indicate their approval by writing /approve in a comment
Approvers can cancel approval by writing /approve cancel in a comment

karmada-bot added the kind/feature Categorizes issue or PR as related to a new feature. label Sep 26, 2025

karmada-bot requested review from devadapter and samzong September 26, 2025 12:31

karmada-bot added the size/M Denotes a PR that changes 30-99 lines, ignoring generated files. label Sep 26, 2025

gemini-code-assist bot reviewed Sep 26, 2025

View reviewed changes

pkg/openai/config.go Outdated Show resolved Hide resolved

pkg/openai/config.go Outdated Show resolved Hide resolved

kasanatte mentioned this pull request Sep 26, 2025

feat(api): add chat handler and integrate mcp/llm clients #277

Merged

kasanatte force-pushed the feature/openai-interface branch from caf8ef9 to 4e832b4 Compare September 27, 2025 17:05

warjiang reviewed Oct 20, 2025

View reviewed changes

kasanatte force-pushed the feature/openai-interface branch from 4e832b4 to 0e7dd31 Compare October 21, 2025 12:10

karmada-bot added size/XL Denotes a PR that changes 500-999 lines, ignoring generated files. and removed size/M Denotes a PR that changes 30-99 lines, ignoring generated files. labels Oct 21, 2025

kasanatte force-pushed the feature/openai-interface branch from 0e7dd31 to 7b34d74 Compare October 21, 2025 12:42

gemini-code-assist bot reviewed Oct 21, 2025

View reviewed changes

pkg/llm/client.go Outdated Show resolved Hide resolved

pkg/llm/client.go Outdated Show resolved Hide resolved

pkg/llm/client.go Show resolved Hide resolved

pkg/llm/client.go Show resolved Hide resolved

pkg/llm/integration_test.go Outdated Show resolved Hide resolved

kasanatte force-pushed the feature/openai-interface branch 2 times, most recently from fc76f61 to cea14b4 Compare October 22, 2025 04:36

karmada-bot assigned warjiang Oct 22, 2025

kasanatte force-pushed the feature/openai-interface branch 2 times, most recently from 9fc865d to d631d67 Compare October 23, 2025 03:53

warjiang reviewed Oct 28, 2025

View reviewed changes

pkg/llm/client.go Outdated Show resolved Hide resolved

warjiang reviewed Oct 28, 2025

View reviewed changes

pkg/llm/client.go Show resolved Hide resolved

warjiang reviewed Oct 28, 2025

View reviewed changes

pkg/llm/integration_test.go Show resolved Hide resolved

warjiang reviewed Oct 28, 2025

View reviewed changes

feat(openai): implement openai interface

d8f7515

Signed-off-by: kasanatte <[email protected]>

kasanatte force-pushed the feature/openai-interface branch from d631d67 to d8f7515 Compare October 29, 2025 13:06

karmada-bot added size/XXL Denotes a PR that changes 1000+ lines, ignoring generated files. and removed size/XL Denotes a PR that changes 500-999 lines, ignoring generated files. labels Oct 29, 2025

warjiang reviewed Oct 29, 2025

View reviewed changes

karmada-bot changed the title ~~feat(openai): implement openai interface~~ feat(openai): implement llm client interface Oct 29, 2025

karmada-bot added the lgtm Indicates that a PR is ready to be merged. label Oct 29, 2025

karmada-bot added the approved Indicates a PR has been approved by an approver from all required OWNERS files. label Oct 29, 2025

karmada-bot merged commit d87b0a5 into karmada-io:main Oct 29, 2025
10 checks passed

feat(openai): implement llm client interface #276

feat(openai): implement llm client interface #276

Uh oh!

Conversation

kasanatte commented Sep 26, 2025 • edited by RainbowMango Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

gemini-code-assist bot commented Sep 26, 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!

warjiang Oct 20, 2025

Choose a reason for hiding this comment

Uh oh!

warjiang Oct 20, 2025

Choose a reason for hiding this comment

Uh oh!

warjiang Oct 20, 2025

Choose a reason for hiding this comment

Uh oh!

kasanatte commented Oct 21, 2025

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!

Uh oh!

warjiang commented Oct 22, 2025

Uh oh!

warjiang commented Oct 22, 2025

Uh oh!

Uh oh!

Uh oh!

warjiang Oct 28, 2025

Choose a reason for hiding this comment

Uh oh!

Uh oh!

warjiang Oct 28, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

warjiang commented Oct 28, 2025

Uh oh!

warjiang Oct 29, 2025

Choose a reason for hiding this comment

Uh oh!

warjiang commented Oct 29, 2025

Uh oh!

warjiang commented Oct 29, 2025

Uh oh!

warjiang commented Oct 29, 2025

Uh oh!

karmada-bot commented Oct 29, 2025

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

kasanatte commented Sep 26, 2025 •

edited by RainbowMango

Loading

warjiang Oct 28, 2025 •

edited

Loading