Codebase Chat - CodeAlive

Overview

Codebase Chat is an AI consultant that knows your entire codebase. Unlike semantic search which returns file locations and snippets, Codebase Chat provides synthesized, ready-to-use answers — architecture explanations, debugging analysis, implementation guidance, and code reviews grounded in your actual code. This is powered by CodeAlive’s GraphRAG approach: the AI has access to the full knowledge graph of your codebase, not just individual files.

How It Works

Ask a Question

Ask any question about your codebase in natural language. The AI retrieves relevant context from the knowledge graph before generating a response.

Get a Synthesized Answer

The response combines information from across your codebase — referencing multiple files, tracing data flows, and explaining architectural patterns.

Follow Up

Continue the conversation with follow-up questions. Each conversation maintains context, so you can drill deeper without repeating yourself.

Example Conversations

Architecture
Debugging
Implementation
Code Review

You: "Explain how the authentication system works in this project"

AI: The authentication system uses a JWT-based flow with three main components:
    1. AuthController (src/controllers/auth.ts) handles login/signup endpoints
    2. JwtService (src/services/jwt.ts) manages token generation and validation
    3. AuthMiddleware (src/middleware/auth.ts) protects routes...
    [continues with specific code references]

You: "Why might payments be failing intermittently?"

AI: Based on the payment processing code, there are several potential causes:
    1. Race condition in PaymentProcessor.process() (src/services/payment.ts:142)
       - The lock acquisition doesn't cover the full transaction...
    2. Timeout configuration mismatch between the gateway client and...
    [continues with specific code analysis]

You: "How should I add rate limiting to the API?"

AI: Based on your existing middleware pattern in src/middleware/:
    1. Create a new RateLimitMiddleware following the pattern in AuthMiddleware
    2. The existing Redis connection in src/config/redis.ts can be reused...
    3. Your API routes in src/routes/index.ts use the middleware chain pattern...
    [continues with implementation guidance matching your codebase patterns]

You: "Review the error handling in the user service"

AI: The UserService has inconsistent error handling:
    1. createUser() (line 45) catches all errors but only logs generic messages
    2. updateUser() (line 89) correctly throws typed errors
    3. deleteUser() (line 112) has no error handling at all...
    [continues with specific recommendations]

Access Methods

MCP Tool
REST API
Skill CLI

The chat tool is available through any CodeAlive-connected agent. The older codebase_consultant name still works as a deprecated alias:

Parameter	Required	Description
`question`	Yes	Your question about the codebase
`data_sources`	Yes	Repository or workspace names
`conversation_id`	No	Continue a previous conversation

Your AI agent may call this tool for synthesized analysis after search. For the highest reliability and depth, prefer semantic_search and grep_search first.

Chat directly via the CodeAlive API:

curl -X POST https://app.codealive.ai/api/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "messages": [{"role": "user", "content": "Explain the authentication flow"}],
    "datasources": ["my-backend"]
  }'

See the API Reference for full details.

If you have the CodeAlive skill installed:

python scripts/chat.py "Explain the authentication flow" my-backend
python scripts/chat.py "What about security considerations?" --continue CONV_ID

Conversation Continuity

Every chat response includes a conversation_id. Pass it in follow-up questions to maintain context:

# First question
python scripts/chat.py "How does authentication work?" my-backend
# Response includes conversation_id: abc123

# Follow-up (cheaper, preserves context)
python scripts/chat.py "What about the refresh token flow?" --continue abc123

This saves cost and provides better answers, since the AI doesn’t need to re-retrieve context for each question.

Best Practices

Search First

Use semantic_search and grep_search for locating code. Use chat when you need explanations or analysis — it’s more expensive per call and can take up to 30 seconds.

Use Follow-ups

Continue conversations with conversation_id instead of starting fresh each time

Be Specific

“Explain the payment retry logic” gets better results than “tell me about payments”

Scope by Repo

Target specific repositories for more focused, accurate answers

Semantic Search

Fast code search for finding file locations and snippets

Multi-Repository

Chat across multiple repositories and workspaces

MCP Integration

Connect chat to your AI assistant

API Reference

Chat API endpoint documentation

​Overview

​How It Works

​Example Conversations

​Access Methods

​Conversation Continuity

​Best Practices