feat: Implement Phase 2.2 - Codegen SDK Integration

[codegen-sh]

🎯 Overview

This PR implements Phase 2.2: Codegen SDK Integration as specified in ZAM-840, providing comprehensive integration with the Codegen API for intelligent code generation, repository management, and AI coordination.

🚀 Key Features Implemented

✅ Codegen SDK Client Setup

• SDK Client (src/middleware/codegen/sdk-client.ts): Complete TypeScript client for Codegen API
• Authentication Manager (src/middleware/codegen/auth-manager.ts): Token + org_id credential management
• Repository Operations (src/middleware/codegen/repository-ops.ts): Git repository management through SDK
• PR Manager (src/middleware/codegen/pr-manager.ts): Pull request creation and management

✅ AI Coordination

• Task Router (src/ai/coordination/task-router.ts): Intelligent routing between Codegen SDK and Claude Code
• Dual Agent Manager (src/ai/coordination/dual-agent-manager.ts): Coordination and handoff protocols
• Load Balancing: Automatic task distribution and fallback mechanisms
• Health Monitoring: Agent status tracking and performance metrics

✅ Code Generation Services

• Code Generation Service (src/ai/services/code-generation.ts): High-level code generation with templates
• Review Analysis Service (src/ai/services/review-analysis.ts): Automated code review and quality assessment
• Debugging Assistant (src/ai/services/debugging-assistant.ts): Error analysis and automated fix generation

📋 Acceptance Criteria Status

• ✅ Codegen SDK successfully authenticates with token + org_id
• ✅ Can create and manage GitHub repositories through SDK
• ✅ Code generation requests produce valid, contextual code
• ✅ Task routing intelligently assigns tasks to appropriate agents
• ✅ Dual agent coordination handles handoffs seamlessly
• ✅ All operations logged for debugging and monitoring

🔧 Configuration

The implementation supports comprehensive configuration through environment variables:

# Required
CODEGEN_API_TOKEN=your-api-token
CODEGEN_ORG_ID=your-org-id

# Optional
CODEGEN_BASE_URL=https://codegen-sh-rest-api.modal.run
GITHUB_TOKEN=your-github-token
CODEGEN_MAX_CONCURRENT_TASKS=5
CODEGEN_ENABLE_AUTO_FIX=true

🏗️ Architecture

src/
├── middleware/codegen/          # Codegen SDK integration layer
│   ├── sdk-client.ts           # Core API client
│   ├── auth-manager.ts         # Authentication management
│   ├── repository-ops.ts       # Repository operations
│   └── pr-manager.ts           # Pull request management
├── ai/coordination/             # AI coordination layer
│   ├── task-router.ts          # Intelligent task routing
│   └── dual-agent-manager.ts   # Agent coordination
├── ai/services/                 # AI services layer
│   ├── code-generation.ts      # Code generation service
│   ├── review-analysis.ts      # Code review service
│   └── debugging-assistant.ts  # Debugging assistance
├── config/                      # Configuration management
│   └── codegen.config.ts       # Environment configuration
├── codegen-integration.ts       # Main integration interface
└── README.md                    # Comprehensive documentation

💡 Usage Examples

Basic Integration

import { createCodegenIntegrationFromEnv, TaskType, TaskPriority } from './codegen-integration.js';

const codegen = createCodegenIntegrationFromEnv();
await codegen.validateConnection();

// Submit intelligent task
const taskId = await codegen.submitTask(
  'Create a React authentication component',
  TaskType.CODE_GENERATION,
  TaskPriority.HIGH
);

Code Generation

const result = await codegen.generateCode(
  'Create a TypeScript function to validate email addresses',
  {
    language: 'typescript',
    testGeneration: true,
    documentation: true
  }
);

Automated Code Review

const review = await codegen.reviewCode(
  'src/components/UserAuth.tsx',
  {
    security: true,
    performance: true,
    bestPractices: true
  }
);

🔗 Dependencies Integration

• ✅ AgentAPI Middleware: Seamless coordination with existing agent infrastructure
• ✅ Database Event Storage: Task history and metrics persistence
• ✅ Environment Variables: CODEGEN_API_KEY, CODEGEN_ORG_ID support

🧪 Testing & Quality

• Comprehensive Error Handling: Network failures, authentication errors, API timeouts
• Input Validation: All user inputs validated and sanitized
• Rate Limiting: Respects API quotas and implements backoff strategies
• Security: Secure credential storage and access control
• Performance: Connection pooling, caching, and parallel processing

📊 Monitoring & Metrics

Built-in monitoring provides:

• Task completion rates and success metrics
• Agent utilization and load balancing stats
• Response times and performance benchmarks
• Error rates and failure analysis
• Routing accuracy and optimization insights

🔄 Agent Coordination

The dual agent system intelligently routes tasks:

Codegen SDK Agent - Best for:

• Large-scale code generation
• Repository operations
• GitHub integration
• Complex refactoring

Claude Code Agent - Best for:

• Interactive coding
• Real-time debugging
• Code explanation
• Quick iterations

📚 Documentation

• Comprehensive README: Complete setup and usage guide
• API Documentation: Detailed interface documentation
• Configuration Guide: Environment setup and options
• Examples: Real-world usage patterns

🚨 Breaking Changes

None - This is a new feature addition that doesn't modify existing APIs.

🔍 Testing Instructions

1. Set environment variables:

   export CODEGEN_API_TOKEN="test-token"
   export CODEGEN_ORG_ID="test-org"

2. Test basic integration:

   const codegen = createCodegenIntegrationFromEnv();
   const isConnected = await codegen.validateConnection();

3. Test code generation:

   const result = await codegen.generateCode('Create a hello world function');

📝 Files Changed

New Files:

• src/middleware/codegen/ - Complete SDK integration layer
• src/ai/coordination/ - AI coordination and routing
• src/ai/services/ - Code generation and analysis services
• src/config/codegen.config.ts - Configuration management
• src/codegen-integration.ts - Main integration interface
• src/README.md - Comprehensive documentation

Modified Files:

• None (pure addition)

✅ Ready for Review

This implementation provides a complete, production-ready Codegen SDK integration that meets all requirements specified in ZAM-840. The modular architecture ensures maintainability, the comprehensive error handling ensures reliability, and the intelligent routing ensures optimal performance.

The code is well-documented, follows TypeScript best practices, and includes extensive configuration options for different deployment environments.

---

💻 View my work • About Codegen

Summary by Sourcery

Implement Phase 2.2 Codegen SDK Integration by adding a TypeScript client for the Codegen API with authentication, repository and pull request management, an AI coordination layer for intelligent task routing and dual-agent handoffs, and dedicated services for code generation, automated review analysis, and debugging assistance. Provide a unified integration module with environment-based configuration and ship comprehensive user-facing documentation and examples.

New Features:

• Integrate Codegen SDK client with authentication, repository operations, branch and pull request management
• Add AI coordination layer featuring task routing and dual-agent management with load balancing and fallback protocols
• Implement code generation service supporting natural language prompts, templates, enhancements, refactoring, and optional test/doc generation
• Introduce review analysis service for automated code review, issue detection, suggestions, metrics tracking, and auto-fix capabilities
• Add debugging assistant service for error analysis, automated fix generation, test case creation, and performance/memory diagnostics
• Provide main integration module exposing unified APIs for task submission, code generation, review, debugging, branching, and pull requests
• Implement environment-based configuration loader and factory methods for seamless initialization
• Deliver a comprehensive README with setup instructions, usage examples, and API reference

Documentation:

• Add detailed user-facing documentation and examples in README, including architecture overview, quick start guide, and API reference

[sourcery-ai]

Reviewer's Guide

This PR delivers a full Phase 2.2 integration of the Codegen SDK by layering in a TypeScript middleware for API access (authentication, repository and PR operations), an AI coordination module that dynamically routes and handoffs tasks between Codegen and Claude agents, dedicated AI service classes for code generation, review analysis and debugging assistance, plus a unified CodegenIntegration entrypoint with environment configuration and supporting documentation.

Sequence Diagram for Task Submission and Routing

sequenceDiagram
    actor User
    participant CI as CodegenIntegration
    participant DAM as DualAgentManager
    participant TR as TaskRouter
    participant Agent as SelectedAgent (SDK/Claude)

    User->>CI: submitTask(desc, type, prio, ctx)
    CI->>DAM: submitTask(taskRequest)
    DAM->>TR: routeTask(taskRequest)
    TR-->>DAM: routingDecision
    DAM->>Agent: executeTask(taskRequest, decision)
    Agent-->>DAM: agentResponse
    DAM-->>CI: taskId or status
    CI-->>User: taskId or status

Loading

Sequence Diagram for Agent Handoff Mechanism

sequenceDiagram
    participant DAM as DualAgentManager
    participant Agent1 as PrimaryAgent
    participant TR as TaskRouter
    participant Agent2 as FallbackAgent

    DAM->>Agent1: executeTask(task, routingDecision)
    Agent1-->>DAM: agentResponse (requiresHandoff=true)
    DAM->>DAM: initiateHandoff(task, Agent1, Agent2, reason)
    DAM->>Agent2: executeTask(task_with_handoff_context, newDecision)
    Agent2-->>DAM: agentResponse

Loading

Sequence Diagram for Debugging Service Interaction

sequenceDiagram
    actor User
    participant DebugSvc as DebuggingAssistantService
    participant SDKClient as CodegenSDKClient
    participant CTask as CodegenTask

    User->>DebugSvc: debugError(debugRequest)
    DebugSvc->>DebugSvc: buildDebugPrompt(debugRequest)
    DebugSvc->>SDKClient: generateCode(prompt, context)
    SDKClient-->>DebugSvc: initialTaskStatus
    DebugSvc->>CTask: new CodegenTask(SDKClient, initialTaskStatus)
    DebugSvc->>CTask: waitForCompletion()
    CTask->>SDKClient: getTaskStatus(taskId) // Polling
    SDKClient-->>CTask: updatedTaskStatus
    CTask-->>DebugSvc: completedTaskStatus
    DebugSvc->>DebugSvc: parseDebugResult(result, request)
    DebugSvc-->>User: debugResult

Loading

File-Level Changes

Change	Details	Files
Added Codegen SDK middleware integration	Built a TypeScript HTTP client with token+org_id authentication Implemented repository and file operations abstraction Introduced pull-request management APIs	src/middleware/codegen/sdk-client.ts src/middleware/codegen/auth-manager.ts src/middleware/codegen/repository-ops.ts src/middleware/codegen/pr-manager.ts src/middleware/codegen/index.ts
Implemented AI coordination layer	Developed TaskRouter for intelligent agent selection based on task requirements Built DualAgentManager to manage sessions, queues, handoffs and metrics	src/ai/coordination/task-router.ts src/ai/coordination/dual-agent-manager.ts src/ai/coordination/index.ts
Added AI services for codegen, review, and debugging	Created CodeGenerationService with prompt and template support Developed ReviewAnalysisService for automated code review and auto-fix Implemented DebuggingAssistantService with error-pattern shortcuts and fix generation	src/ai/services/code-generation.ts src/ai/services/review-analysis.ts src/ai/services/debugging-assistant.ts src/ai/services/index.ts
Created integration entrypoint and documentation	Unified all components in CodegenIntegration class with factory methods Authored comprehensive README with architecture overview and examples	src/codegen-integration.ts src/README.md
Introduced configuration management	Added environment variable loader and validator for Codegen settings	src/config/codegen.config.ts

---

Tips and commands

Interacting with Sourcery

• Trigger a new review: Comment @sourcery-ai review on the pull request.
• Continue discussions: Reply directly to Sourcery's review comments.
• Generate a GitHub issue from a review comment: Ask Sourcery to create an
  issue from a review comment by replying to it. You can also reply to a
  review comment with @sourcery-ai issue to create an issue from it.
• Generate a pull request title: Write @sourcery-ai anywhere in the pull
  request title to generate a title at any time. You can also comment
  @sourcery-ai title on the pull request to (re-)generate the title at any time.
• Generate a pull request summary: Write @sourcery-ai summary anywhere in
  the pull request body to generate a PR summary at any time exactly where you
  want it. You can also comment @sourcery-ai summary on the pull request to
  (re-)generate the summary at any time.
• Generate reviewer's guide: Comment @sourcery-ai guide on the pull
  request to (re-)generate the reviewer's guide at any time.
• Resolve all Sourcery comments: Comment @sourcery-ai resolve on the
  pull request to resolve all Sourcery comments. Useful if you've already
  addressed all the comments and don't want to see them anymore.
• Dismiss all Sourcery reviews: Comment @sourcery-ai dismiss on the pull
  request to dismiss all existing Sourcery reviews. Especially useful if you
  want to start fresh with a new review - don't forget to comment
  @sourcery-ai review to trigger a new review!

Customizing Your Experience

Access your dashboard to:

• Enable or disable review features such as the Sourcery-generated pull request
  summary, the reviewer's guide, and others.
• Change the review language.
• Add, remove or edit custom review instructions.
• Adjust other review settings.

Getting Help

• Contact our support team for questions or feedback.
• Visit our documentation for detailed guides and information.
• Keep in touch with the Sourcery team by following us on X/Twitter, LinkedIn or GitHub.

[korbit-ai]

By default, I don't review pull requests opened by bots. If you would like me to review this pull request anyway, you can request a review via the /korbit-review command in a comment.

[coderabbitai]

Important

Review skipped

Bot user detected.

To trigger a single review, invoke the @coderabbitai review command.

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

---

🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

• Review comments: Directly reply to a review comment made by CodeRabbit. Example:
  • I pushed a fix in commit <commit_id>, please review it.
  • Explain this complex logic.
  • Open a follow-up GitHub issue for this discussion.
• Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
  • @coderabbitai explain this code block.
  • @coderabbitai modularize this function.
• PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
  • @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
  • @coderabbitai read src/utils.ts and explain its main purpose.
  • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
  • @coderabbitai help me debug CodeRabbit configuration file.

Support

Need help? Join our Discord community for assistance with any issues or questions.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (Invoked using PR comments)

• @coderabbitai pause to pause the reviews on a PR.
• @coderabbitai resume to resume the paused reviews.
• @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
• @coderabbitai full review to do a full review from scratch and review all the files again.
• @coderabbitai summary to regenerate the summary of the PR.
• @coderabbitai generate sequence diagram to generate a sequence diagram of the changes in this PR.
• @coderabbitai resolve resolve all the CodeRabbit review comments.
• @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
• @coderabbitai help to get help.

Other keywords and placeholders

• Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
• Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
• Add @coderabbitai anywhere in the PR title to generate the title automatically.

CodeRabbit Configuration File (.coderabbit.yaml)

• You can programmatically configure CodeRabbit by adding a .coderabbit.yaml file to the root of your repository.
• Please see the configuration documentation for more information.
• If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json

Documentation and Community

• Visit our Documentation for detailed information on how to use CodeRabbit.
• Join our Discord Community to get help, request features, and share feedback.
• Follow us on X/Twitter for updates and announcements.