feat(llm-bridge): google cloud vertex ai support global location

[fanweixiao]

update from aiplatform.googleapis.com/v1/ to aiplatform.googleapis.com/v1beta1/ as described at https://cloud.google.com/vertex-ai/generative-ai/docs/migrate/openai/overview

and, add support for global location support.

vertexai:
  project_id: PRJ_ID
  credentials_file: "./credential.json"
  model: gemini-2.5-pro
  location: global

[Copilot]

Pull Request Overview

The PR introduces support for Google Cloud Vertex AI's global location by updating the API endpoint from v1 to v1beta1 and adjusting the default model initialization.

• Updated API endpoint URL to v1beta1
• Added a conditional branch for handling the "global" location
• Changed the fallback model value

Comments suppressed due to low confidence (1)

pkg/bridge/ai/provider/vertexai/provider.go:49

• The fallback model is set to 'gemini-2.5-flash' which conflicts with the PR description that mentions 'gemini-2.5-pro'. Consider updating it for consistency.

		model = "gemini-2.5-flash"

[gemini-code-assist]

Summary of Changes

Hello @fanweixiao, 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 significantly improves the llm-bridge's integration with Google Cloud Vertex AI. It updates the underlying API version to v1beta1 for enhanced compatibility and introduces robust support for the global location, which is essential for accessing certain Vertex AI models. Additionally, it updates the default Gemini model to a more recent version.

Highlights

• Vertex AI API Version Upgrade: The Vertex AI API endpoint has been upgraded from v1 to v1beta1 to align with the latest generative AI recommendations from Google Cloud.
• Global Location Support: Added specific handling for the global location in Vertex AI configurations, allowing the llm-bridge to correctly connect to models deployed globally without region-specific prefixes.
• Default Gemini Model Update: The default Gemini model used when no specific model is provided has been updated from gemini-1.5-pro-002 to gemini-2.5-flash.

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 in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.

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 issue 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 is currently in preview and 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 to provide feedback.

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.

Footnotes

1. 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. ↩

[codecov]

Codecov Report

Attention: Patch coverage is 0% with 6 lines in your changes missing coverage. Please review.

Project coverage is 51.01%. Comparing base (63b1453) to head (76cc6c2).
Report is 1 commits behind head on master.

Files with missing lines	Patch %	Lines
pkg/bridge/ai/provider/vertexai/provider.go	0.00%	6 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##           master    #1109      +/-   ##
==========================================
- Coverage   51.44%   51.01%   -0.44%     
==========================================
  Files          92       92              
  Lines        6562     6565       +3     
==========================================
- Hits         3376     3349      -27     
- Misses       2980     3012      +32     
+ Partials      206      204       -2     

☔ 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.

[gemini-code-assist]

Code Review

The pull request updates the Vertex AI provider to use the v1beta1 API and adds support for the global location. The review identified areas for code cleanup and a minor inconsistency between the code and the pull request description.