feat: add support to custom providers - #1
Merged
Conversation
ramonpaolo
force-pushed
the
feat/add-support-to-custom-providers
branch
from
January 14, 2026 03:14
fa6ca20 to
14f241a
Compare
ramonpaolo
force-pushed
the
feat/add-support-to-custom-providers
branch
from
January 14, 2026 03:20
14f241a to
ccb43f5
Compare
There was a problem hiding this comment.
🎯 Core Changes
This PR adds support for custom AI providers (like MiniMax M2.1, Ollama, llama.cpp) to the AI Code Review action. The changes include:
.github/workflows/code_review.yml: Updated workflow to use the new custom provider branch with MiniMax configuration instead of the local action with OpenAIaction.yml:- Added
AI_BASE_URLinput for custom provider endpoints - Made
AI_API_KEYoptional (previously required) - Updated
AI_PROVIDERdescription to include "custom" option - Upgraded Node.js runtime from
node20tonode24
- Added
⚠️ Concerns
- Missing documentation: The PR description doesn't mention that users need to add the
AI_API_KEYsecret when using custom providers. Consider documenting this requirement. - API key optionality: Making
AI_API_KEYoptional inaction.ymlmay cause confusing errors if a provider requires authentication but the user doesn't provide a key. Consider adding validation or clearer error messages. - Node 24 runtime: Using
node24(which may not be fully stable) instead of the widely-usednode20could cause compatibility issues in some runner environments.
Verdict
The changes implement the stated feature correctly. The concerns above are minor and don't prevent merging. The PR author should consider documenting the new AI_API_KEY secret requirement for custom providers.
Suggested Action: comment
Confidence: 95
Code review performed by CUSTOM - MiniMax-M2.1.
ramonpaolo
force-pushed
the
feat/add-support-to-custom-providers
branch
from
January 14, 2026 03:22
ccb43f5 to
180ad95
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Description
This PR add the functionality to use custom providers/models to do the code review.
This PR allow the integration with local models, like Ollama, llama.cpp; and another providers/models like MiniMax M2.1
Type of Change
Checklist
Related Issues
N/A
Additional Context
N/A