AI Chat & Analysis Guide

Complete guide to interactive chat, codebase analysis, and session management

Overview

Ada CLI provides powerful AI-powered development assistance through interactive chat sessions and intelligent codebase analysis. This guide covers chat operations, analysis features, and session management.

Interactive AI Chat

Starting Chat Sessions

bash

# Basic chat session
ada chat

# Chat with specific provider
ada chat --provider anthropic
ada chat --provider openai
ada chat --provider google

# Chat with specific model
ada chat --model claude-sonnet-4-6
ada chat --model gpt-4

# Chat with workspace context
ada chat --context workspace

Chat Features

Context Awareness

Workspace Context: Chat understands your current workspace and projects
Project Structure: Automatically analyzes project files and dependencies
Recent Changes: Incorporates recent git commits and modifications
Team Knowledge: Access to shared team knowledge and conversations

AI Provider Options

Anthropic Claude: Advanced reasoning and code understanding
OpenAI GPT: General development assistance and code generation
Google Gemini: Multi-modal analysis and broad knowledge
Local Models: Privacy-focused local AI models (Ollama)

Chat Interface

Interactive Commands

/help - Show available commands
/clear - Clear chat history
/context - Show current context
/provider - Switch AI provider
/export - Export conversation
/quit - Exit chat session

Context Commands

/analyze - Run codebase analysis
/workspace - Show workspace information
/files <pattern> - List files matching pattern
/git - Show recent git activity

Example Chat Session

You: Analyze the authentication flow in this codebase

AI: I can see this is a Next.js application with authentication. Let me analyze the auth flow:

1. **Login Component** (components/auth/LoginForm.tsx)
   - Uses React Hook Form for validation
   - Calls auth API endpoint on submission
   - Handles both email/password and OAuth flows

2. **Authentication API** (pages/api/auth/[...auth].js)
   - Auth configuration
   - Multiple providers: Google, GitHub, Email
   - JWT token handling with secure cookies

3. **Proxy** (proxy.ts)
   - Protects routes requiring authentication
   - Redirects unauthenticated users to login
   - Handles token refresh automatically

Would you like me to suggest improvements to any specific part?

You: What security improvements would you recommend?

AI: Based on the current implementation, here are key security improvements:

1. **Rate Limiting**
   - Add rate limiting to login endpoints
   - Implement progressive delays for failed attempts
   - Use libraries like `express-rate-limit`

2. **CSRF Protection**
   - Enable CSRF tokens in Auth config
   - Add custom CSRF validation for API routes
   - Configure secure cookie settings

3. **Session Security**
   - Implement session rotation on privilege changes
   - Add session invalidation on password changes
   - Use secure session storage

Would you like me to show code examples for any of these improvements?

Codebase Analysis

Analysis Commands

bash

# Full codebase analysis
ada analyze

# Analyze specific aspects
ada analyze --symbols
ada analyze --dependencies
ada analyze --architecture
ada analyze --security

# Analyze specific files or directories
ada analyze src/components/
ada analyze --files "*.ts,*.tsx"

# Analyze recent changes
ada analyze --diff
ada analyze --since "1 week ago"

Analysis Types

Symbol Analysis

bash

ada analyze --symbols

Provides:

Function and class definitions
Import/export relationships
Type definitions and interfaces
Component hierarchies
API endpoint mappings

Dependency Analysis

bash

ada analyze --dependencies

Provides:

Package dependency tree
Outdated packages identification
Security vulnerability scan
Bundle size analysis
Circular dependency detection

Architecture Analysis

bash

ada analyze --architecture

Provides:

Project structure overview
Design pattern identification
Component relationships
Data flow analysis
Architecture recommendations

Security Analysis

bash

ada analyze --security

Provides:

Security vulnerability detection
Code security best practices
Authentication flow analysis
Data handling security review
OWASP compliance check

Analysis Output

bash

# Different output formats
ada analyze --output table
ada analyze --output json
ada analyze --output summary

# Save analysis to file
ada analyze --output-file analysis-report.json

# Generate visual reports
ada analyze --visual --output-dir ./reports/

Integration with Chat

Analysis results are automatically available in chat context:

You: Based on the analysis, what are the main issues?

AI: From the recent codebase analysis, I identified several key areas for improvement:

**High Priority:**
1. **Security**: 3 dependencies with known vulnerabilities
2. **Performance**: Large bundle size (2.3MB) due to unused dependencies
3. **Architecture**: Circular dependencies in auth module

**Medium Priority:**
1. **Code Quality**: 12 functions exceeding complexity threshold
2. **Testing**: 45% code coverage, missing tests for critical paths
3. **Documentation**: API endpoints lack OpenAPI documentation

Would you like me to prioritize these issues or dive deeper into any specific area?

Session Management

Session Operations

bash

# List all chat sessions
ada sessions

# List recent sessions
ada sessions --recent

# Search sessions
ada sessions search "authentication"
ada sessions search --tag security

# Browse sessions interactively
ada sessions browse

Resume Sessions

bash

# Resume most recent session
ada sessions resume

# Resume specific session
ada sessions resume session_12345

# Resume with different provider
ada sessions resume session_12345 --provider openai

Session Export

bash

# Export session to file
ada sessions export session_12345

# Export in different formats
ada sessions export session_12345 --format markdown
ada sessions export session_12345 --format json
ada sessions export session_12345 --format pdf

# Export multiple sessions
ada sessions export --tag security --format zip

Session Organization

bash

# Tag sessions
ada sessions tag session_12345 "authentication,security"

# Create session collections
ada sessions collection create "Security Review"
ada sessions collection add "Security Review" session_12345

# Share sessions with team
ada sessions share session_12345 --team development

Advanced Chat Features

Context Management

bash

# Add files to context
ada chat --files "src/auth/*"

# Add specific context types
ada chat --context workspace,git,issues

# Include external documentation
ada chat --docs "https://docs.example.com/api"

# Set context scope
ada chat --scope current-branch

Multi-Session Workflows

bash

# Start chat with session inheritance
ada chat --inherit session_12345

# Merge session contexts
ada chat --merge session_12345,session_67890

# Create session templates
ada sessions template create security-review
ada chat --template security-review

Collaborative Chat

bash

# Start team chat session
ada chat --team development

# Join existing team session
ada chat --join team_session_123

# Share live session
ada chat --share --real-time

Integration with Development Workflow

Git Integration

bash

# Chat with git context
ada chat --git-context

# Analyze specific commits
ada analyze --commit abc123

# Review pull request
ada chat --pr 456

Example Git Integration:

You: Review the changes in the latest commit

AI: I've analyzed commit abc123 "Add user authentication". Here's my review:

**Changes Overview:**
- Added UserAuth component (128 lines)
- Updated API routes for login/logout
- Added middleware for protected routes
- Updated tests for auth functionality

**Code Quality:**
✅ Good: Proper error handling and validation
✅ Good: Comprehensive test coverage
⚠️  Consider: Password hashing strength (current: bcrypt rounds 10, recommend 12+)
⚠️  Consider: Rate limiting on auth endpoints

**Security Review:**
✅ Secure: Proper JWT token handling
✅ Secure: HTTPS-only cookie configuration
🔴 Issue: Missing CSRF protection on auth endpoints

Would you like me to suggest fixes for the identified issues?

Issue Tracking Integration

bash

# Link chat to issues
ada chat --issue PROJ-123

# Create issues from chat
ada chat --create-issue "Security improvements needed"

# Update issues based on chat
ada sessions update-issue session_12345 PROJ-123

Documentation Generation

bash

# Generate docs from chat
ada sessions generate-docs session_12345

# Create API documentation
ada chat --generate-api-docs

# Generate team knowledge base
ada sessions knowledge-base --tag architecture

Performance Optimization

Chat Performance

bash

# Optimize chat for speed
lovelace config set chat.optimization speed

# Reduce context size
lovelace config set chat.context_limit 100

# Enable response caching
lovelace config set chat.cache_responses true

# Use faster models for quick questions
lovelace config set chat.quick_model claude-haiku-4-5

Analysis Performance

bash

# Incremental analysis
ada analyze --incremental

# Parallel analysis
ada analyze --parallel

# Cache analysis results
lovelace config set analysis.cache_results true

# Limit analysis scope
ada analyze --scope changed-files

Troubleshooting

Chat Issues

Connection Problems

bash

# Test AI provider connectivity
lovelace config test ai.anthropic.api_key

# Switch providers
ada chat --provider openai

# Check quota limits
lovelace billing usage

Context Issues

bash

# Clear chat context
ada chat --clear-context

# Rebuild workspace context
ada workspace sync --rebuild-context

# Check context size
ada chat --context-info

Analysis Issues

Analysis Failures

bash

# Check analysis logs
ada analyze --logs

# Run with debugging
ada analyze --debug

# Reset analysis cache
ada analyze --reset-cache

Performance Issues

bash

# Optimize analysis performance
ada analyze --optimize

# Exclude large files
lovelace config set analysis.exclude_patterns "*.log,*.tmp,node_modules"

# Limit analysis depth
lovelace config set analysis.max_depth 5

Session Issues

Session Recovery

bash

# Recover corrupted sessions
ada sessions recover

# Migrate old sessions
ada sessions migrate --from-version 1.0

# Rebuild session index
ada sessions reindex

Best Practices

Effective Chat Usage

Be specific - Provide clear context and specific questions
Use workspace context - Enable workspace context for better understanding
Iterate - Build on previous conversations for complex problems
Export important sessions - Save valuable conversations for future reference

Analysis Optimization

Regular analysis - Run analysis after significant changes
Focus analysis - Use specific analysis types for targeted insights
Track changes - Use diff analysis to monitor code evolution
Automate analysis - Integrate analysis into CI/CD pipelines

Session Management

Organize sessions - Use tags and collections to organize conversations
Share knowledge - Export and share valuable sessions with team
Clean up regularly - Remove old or irrelevant sessions
Use templates - Create session templates for common workflows

Next Steps:

Editor Integration - Use AI chat from your editor