Merge pull request #5 from EuclidStellar/keployAI

feat: KeployAI code review action

Author: EuclidStellar

.github/workflows/ai-review.yml

@@ -0,0 +1,49 @@
+
+name: Build and Push Test Image
+
+on:
+    push:
+        branches:
+        - keployAI
+    workflow_dispatch:
+
+jobs:
+  build-and-push-test-image:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      packages: write
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Log in to the GitHub Container Registry
+        uses: docker/login-action@v3
+        with:
+          registry: ghcr.io
+          username: ${{ github.repository_owner }}
+          password: ${{ secrets.GB_TOKEN }}
+
+      # FIX: Use metadata-action to generate valid, lowercase tags automatically.
+      - name: Extract metadata (tags, labels) for Docker
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          # This will be automatically converted to lowercase: ghcr.io/euclidstellar/code-review-agent
+          images: ghcr.io/${{ github.repository }}
+          # For this workflow, we only want to generate a single tag: 'test'
+          tags: type=raw,value=test
+
+      - name: Build and push multi-platform image
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          push: true
+          platforms: linux/amd64,linux/arm64
+          # Use the valid tags generated by the metadata-action step
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}

.github/workflows/build-test-image.yml

@@ -1,3 +1,32 @@
+# name: Test Code Review Action
+
+# on:
+#   pull_request:
+#     types: [opened, synchronize, reopened]
+#   workflow_dispatch:  # Allows manual triggering
+
+# permissions:
+#   contents: read
+#   pull-requests: write
+
+# jobs:
+#   test-action:
+#     runs-on: ubuntu-latest
+#     steps:
+#       - name: Checkout Repository
+#         uses: actions/checkout@v4
+#         with:
+#           fetch-depth: 0  # Required for git diff operations
+          
+#       - name: Test Local Action
+#         uses: ./  # Now this will work
+#         with:
+#           github-token: ${{ secrets.GH_SECRET }}
+#           model: 'gpt-4o-mini'  # Fix: Use available model
+#           max-tokens: 6700
+#           temperature: 0.1
+#           ignore-patterns: '*.md,node_modules/**'
+
 name: Test Code Review Action
 
 on:
@@ -18,11 +47,16 @@ jobs:
         with:
           fetch-depth: 0  # Required for git diff operations
 
-      - name: Test Local Action
-        uses: ./  # Now this will work
+      - name: Test Pre-built Action from GHCR
+        # FIX: Instead of building locally with 'uses: ./', we now pull the pre-built
+        # image from the GitHub Container Registry, just like a real user would.
+        uses: docker://ghcr.io/euclidstellar/testtt:test
+        #uses: ./
         with:
+          # BEST PRACTICE: Use the built-in GITHUB_TOKEN. It's more secure
+          # and avoids potential formatting issues with custom secrets.
           github-token: ${{ secrets.GH_SECRET }}
-          model: 'gpt-4o-mini'  # Fix: Use available model
+          model: 'gpt-4o-mini'
           max-tokens: 6700
           temperature: 0.1
           ignore-patterns: '*.md,node_modules/**'

.github/workflows/test.yml

@@ -1,34 +1,36 @@
-# Smart AI Code Review Action
+# KeployAI Code Review Action
 
 [![GitHub Marketplace](https://img.shields.io/badge/Marketplace-Smart%20AI%20Code%20Review-blue.svg?colorA=24292e&colorB=0366d6&style=flat&longCache=true&logo=github)](https://github.com/marketplace/actions/smart-ai-code-review-action)
 
-An intelligent GitHub Action that provides automated, AI-powered code reviews on your pull requests. It features a resilient fallback system, using **GitHub Models** as the primary provider and **Ollama** for local models as a backup, ensuring you always get a review.
+An intelligent GitHub Action that provides automated, AI-powered code reviews on your pull requests. It features a resilient fallback system, visual summaries, and smart diff analysis to deliver professional-grade feedback.
 
 ## Key Features
 
+-   📊 **Visual PR Summary**: Each review starts with a Mermaid sequence diagram summarizing the changes.
 -   🧠 **Intelligent Diff Analysis**: Automatically prioritizes critical files in large pull requests to stay within token limits.
--   🔄 **Resilient Fallback System**: If GitHub Models API fails or is rate-limited, it seamlessly switches to a self-hosted Ollama model.
+-   🔄 **Resilient Fallback System**: If the primary GitHub Models API fails, it seamlessly switches to a self-hosted Ollama model.
 -   🤖 **Multi-Provider Support**: Natively supports GitHub Models and any model compatible with Ollama.
--   ✅ **Comprehensive Reviews**: Analyzes code for security vulnerabilities, performance bottlenecks, best practices, and style.
--   ⚙️ **Highly Configurable**: Fine-tune models, ignore specific files, and adjust AI parameters.
+-   ✅ **Comprehensive Reviews**: Analyzes code for security, performance, best practices, and style.
 -   🚀 **Zero-Setup Ready**: Works out of the box with the standard `GITHUB_TOKEN`.
 
-## How It Works
+## Usage
 
-1.  **GitHub Models First**: The action first attempts to generate a high-quality review using the specified GitHub Model (e.g., `gpt-4o-mini`).
-2.  **Ollama Fallback**: If the primary API call fails (due to errors, rate limits, etc.), the action automatically installs Ollama inside the runner, pulls your specified model (e.g., `qwen2:7b`), and generates the review.
-3.  **Static Fallback**: If both AI providers fail, a structured error report is posted, ensuring you are never left without feedback.
+### Workflow Permissions
 
-## Usage
+This action requires the following permissions in your workflow file to read code and post comments.
 
-Create a workflow file (e.g., `.github/workflows/code-review.yml`) in your repository.
+```yaml
+permissions:
+  contents: read
+  pull-requests: write
+```
 
 ### Basic Example
 
-This configuration uses the default settings and is the quickest way to get started.
+This configuration uses the default settings and is the quickest way to get started. Create a file like `.github/workflows/code-review.yml`:
 
 ```yaml
-name: AI Code Review
+name: KeployAI Code Review
 
 on:
   pull_request:
@@ -48,17 +50,17 @@ jobs:
           fetch-depth: 0 # Required to get the full git history for diffing
 
       - name: Run Smart AI Code Review
-        uses: euclidstellar/code-review-agent@v1 # Replace with your repo name
+        uses: euclidstellar/code-review-agent@v1
         with:
-          github-token: ${{ secrets.GITHUB_TOKEN }}
+          github-token: ${{ secrets.GH_TOKEN }}
 ```
 
 ### Advanced Example
 
 This configuration customizes the models, temperature, and file patterns.
 
 ```yaml
-name: Advanced AI Code Review
+name: Advanced KeployAI Code Review
 
 on:
   pull_request:
@@ -78,12 +80,12 @@ jobs:
           fetch-depth: 0
 
       - name: Run Smart AI Code Review
-        uses: euclidstellar/code-review-agent@v1 # Replace with your repo name
+        uses: euclidstellar/code-review-agent@v1
         with:
-          github-token: ${{ secrets.GITHUB_TOKEN }}
+          github-token: ${{ secrets.GH_TOKEN }}
           model: 'gpt-4o'
-          ollama-model: 'llama3:8b'
-          temperature: 0.5
+          ollama-model: 'gemma3n:e4b'
+          temperature: 0.1
           ignore-patterns: '*.md,*.lock,dist/**'
 ```
 

.golangci.yml

@@ -47,4 +47,4 @@ outputs:
 
 runs:
   using: 'docker'
-  image: 'Dockerfile'
+  image: 'docker://ghcr.io/euclidstellar/code-review-agent:v1'

README.md

@@ -118,6 +118,12 @@ func (c *GitHubModelsClient) buildPrompt(diff string) string {
 
 ## Code Review Summary
 Brief overview of changes and overall quality assessment.
+**Include a small Mermaid sequence diagram summarizing the PR.** 
+
+Example Mermaid Diagram:
+`+"```mermaid\n"+`sequenceDiagram
+    Mermaid code the diagram should show the concise logical changes in the codebase between old code and new code.
+`+"```\n"+`
 
 ## Critical Issues
 List high-priority issues requiring immediate attention with clear impact explanations.
@@ -155,8 +161,6 @@ Present corrected versions with detailed explanations.
 ## Testing Recommendations
 Specific test suggestions for the changes.
 
-## Documentation Notes
-Documentation improvements or additions needed.
 
 ---
 

action.yml

@@ -154,19 +154,68 @@ func (c *OllamaClient) GenerateReview(diff string) (string, error) {
 }
 
 func (c *OllamaClient) buildPrompt(diff string) string {
-    return fmt.Sprintf(`You are an expert code reviewer. Your task is to analyze the provided git diff, identify potential issues, suggest improvements, and summarize the key changes. Pay close attention to:
-- Readability and code style adherence
-- Potential bugs or edge cases  
-- Security vulnerabilities
-- Performance implications
-- Adherence to best practices
-- Missing tests or documentation
-
-Here is the git diff:
-` + "```diff\n" + diff + "\n```" + `
-
-Provide your review in a concise and actionable manner, using markdown formatting including code blocks where necessary. Start with a brief summary, then list specific findings and suggestions. Output only the review comments for the code changes. Do not include your reasoning or thinking process.
-End with a summary of the most critical issues found.`)
+    return fmt.Sprintf(`You are an expert code reviewer. Analyze the provided git diff and deliver a comprehensive, professional code review following the exact structure below.
+
+### FORMATTING REQUIREMENTS:
+- Use proper markdown with clear sections
+- Include specific code snippets with language tags
+- Provide concrete examples for improvements
+- Use tables for structured findings
+- Reference specific file locations
+- Professional tone, no emojis
+
+### REQUIRED STRUCTURE:
+
+## Code Review Summary
+Brief overview of changes and overall quality assessment.
+**Include a small Mermaid sequence diagram summarizing the PR.** 
+
+Example Mermaid Diagram:
+`+"```mermaid\n"+`sequenceDiagram
+    Mermaid code the diagram should show the concise logical changes in the codebase between old code and new code.
+`+"```\n"+`
+
+## Critical Issues
+List high-priority issues requiring immediate attention with clear impact explanations.
+
+## Code Quality Analysis
+
+### Security Concerns
+Identify security issues with code examples and explanations.
+
+### Performance Issues  
+Highlight performance problems with optimization suggestions.
+
+### Best Practices
+Note coding standard violations and improvement opportunities.
+
+## Detailed Findings
+
+<details>
+  <summary>📂 Click to expand issue table</summary>
+
+| Category | Issue Description | Location (File:Line) | Severity | Recommendation |
+|----------|-------------------|----------------------|----------|----------------|
+| Example  | Description here  | file.js:42           | High     | Specific fix   |
+
+</details>
+
+## Code Examples
+
+### Current Implementation
+Show problematic code snippets with explanations of why they're issues.
+
+### Suggested Improvements
+Present corrected versions with detailed explanations.
+
+## Testing Recommendations
+Specific test suggestions for the changes.
+
+
+---
+
+Here is the diff to review:
+` + "```diff\n" + diff + "\n```")
 }
 
 func (c *OllamaClient) cleanResponse(response string) string {