codesavant 1.2.7 → 1.2.8

package/README.md

@@ -31,6 +31,7 @@ CodeSavant is a powerful AI coding assistant that runs directly in your terminal
 - **Privacy First**: Run locally with Ollama, or use any cloud provider
 - **Full Tooling**: Read, write, edit files, run commands, search codebases
 - **Session Persistence**: Continue conversations across terminal sessions
+- **Extensible**: Custom skills, MCP servers, and subagents
 
 ---
 
@@ -41,17 +42,24 @@ CodeSavant is a powerful AI coding assistant that runs directly in your terminal
 - [Supported Providers](#supported-providers)
 - [Usage](#usage)
   - [Interactive Mode](#interactive-mode)
-  - [Commands](#commands)
+  - [REPL Commands](#repl-commands)
   - [Multi-line Input](#multi-line-input)
-- [Configuration](#configuration)
-- [Project Memory (SAVANT.md)](#project-memory-savantmd)
+  - [Keyboard Shortcuts](#keyboard-shortcuts)
 - [Tools](#tools)
+- [Subagents](#subagents)
+- [Skills System](#skills-system)
 - [Permission System](#permission-system)
-- [Skills](#skills)
+- [Session Management](#session-management)
+- [Configuration](#configuration)
+- [Project Memory (SAVANT.md)](#project-memory-savantmd)
 - [MCP Integration](#mcp-integration)
-- [VS Code Extension](#vs-code-extension)
+- [Live Preview](#live-preview)
+- [CI/CD Fix Mode](#cicd-fix-mode)
+- [Checkpoints & Recovery](#checkpoints--recovery)
+- [Enterprise Features](#enterprise-features)
+- [Debug & Troubleshooting](#debug--troubleshooting)
+- [CLI Reference](#cli-reference)
 - [Environment Variables](#environment-variables)
-- [Troubleshooting](#troubleshooting)
 - [License](#license)
 
 ---
@@ -62,6 +70,7 @@ CodeSavant is a powerful AI coding assistant that runs directly in your terminal
 
 - Node.js 18.0.0 or higher
 - At least one AI provider API key (or Ollama installed locally)
+- [ripgrep](https://github.com/BurntSushi/ripgrep) (recommended for fast code search)
 
 ### Install via npm
 
@@ -73,6 +82,7 @@ npm install -g codesavant
 
 ```bash
 codesavant --version
+codesavant doctor  # Run diagnostic checks
 ```
 
 ---
@@ -90,7 +100,7 @@ export DEEPSEEK_API_KEY="your-api-key"
 # Groq (Fastest response times)
 export GROQ_API_KEY="your-api-key"
 
-# Google Gemini (Large context window)
+# Google Gemini (Large context window - 1M tokens)
 export GEMINI_API_KEY="your-api-key"
 
 # OpenAI
@@ -172,9 +182,12 @@ codesavant --provider groq
 
 # Use a specific model
 codesavant --model gpt-4o
+
+# Use classic terminal UI (no Ink)
+codesavant --classic
 ```
 
-### Commands
+### REPL Commands
 
 Inside the CodeSavant REPL, use these slash commands:
 
@@ -188,11 +201,14 @@ Inside the CodeSavant REPL, use these slash commands:
 | `/providers` | Show available AI providers |
 | `/stats` | Show token usage and cost statistics |
 | `/compact` | Manually compact conversation context |
-| `/export` | Export conversation to file |
+| `/export [format]` | Export conversation (markdown, json, html) |
 | `/config` | Show current configuration |
 | `/doctor` | Diagnose configuration issues |
 | `/init` | Initialize CodeSavant in current project |
-| `/exit` | Exit CodeSavant |
+| `/preview` | Manage live preview servers |
+| `/status` | Show session status and statistics |
+| `/debug` | Debug logging controls |
+| `/exit` or `Ctrl+D` | Exit CodeSavant |
 
 ### Multi-line Input
 
@@ -210,367 +226,585 @@ Create a React component that:
 
 Press Enter after the closing `"""` to submit.
 
+### Keyboard Shortcuts
+
+| Shortcut | Action |
+|----------|--------|
+| `Tab` | Autocomplete commands |
+| `↑/↓` | Navigate command history |
+| `Ctrl+R` | Search command history |
+| `Ctrl+C` | Cancel current operation |
+| `Ctrl+D` | Exit CodeSavant |
+| `Shift+Tab` | Cycle permission modes |
+| `Esc Esc` | Rewind to last checkpoint |
+| `"""` | Enter multi-line mode |
+
 ---
 
-## Configuration
+## Tools
 
-### Configuration File
+CodeSavant has 17 built-in tools that the AI can use:
 
-CodeSavant stores configuration in `~/.codesavant/config.json`:
+### File Operations
 
-```json
-{
-  "provider": "deepseek",
-  "model": "deepseek-coder",
-  "maxTokens": 4096,
-  "temperature": 0.7,
-  "permissions": {
-    "mode": "default",
-    "allowedPaths": ["."],
-    "deniedPaths": ["node_modules", ".git", ".env"]
-  }
-}
-```
+| Tool | Description |
+|------|-------------|
+| **read_file** | Read file contents with line numbers |
+| **write_file** | Create or overwrite files |
+| **edit_file** | Make precise edits with search/replace |
+| **multi_edit** | Apply multiple atomic edits across files |
+| **list_directory** | List directory contents |
 
-### Configuration Commands
+### Search Operations
 
-```bash
-# View all configuration
-codesavant config
+| Tool | Description |
+|------|-------------|
+| **glob** | Find files using glob patterns |
+| **grep** | Search file contents with regex (ripgrep) |
 
-# View specific setting
-codesavant config get provider
+### System Operations
 
-# Set a value
-codesavant config set provider deepseek
-codesavant config set maxTokens 8192
+| Tool | Description |
+|------|-------------|
+| **bash** | Execute shell commands (120s timeout) |
+| **notebook_edit** | Edit Jupyter notebooks (.ipynb) |
+| **screenshot** | Capture screen screenshots |
+| **computer_use** | Control mouse and keyboard |
+| **preview** | Manage live preview of web projects |
 
-# Show available providers
-codesavant config --providers
-```
+### Network Operations
 
-### Directory Structure
+| Tool | Description |
+|------|-------------|
+| **web_fetch** | Fetch URLs and convert HTML to Markdown |
+| **web_search** | Search the web |
+
+### AI Operations
+
+| Tool | Description |
+|------|-------------|
+| **spawn_subagent** | Delegate tasks to specialized agents |
+| **todo_write** | Manage structured task lists |
+| **ask_user_question** | Ask user questions with choices |
+
+### Examples
 
 ```
-~/.codesavant/
-├── config.json      # Global configuration
-├── sessions/        # Saved conversation sessions
-├── skills/          # Custom skills
-└── SAVANT.md        # Global project memory
-```
+> Read the package.json file
 
----
+> Find all TypeScript files in src/
 
-## Project Memory (SAVANT.md)
+> Search for "TODO" comments in the codebase
 
-Create a `SAVANT.md` file in your project root to give CodeSavant context about your project. This file is automatically read when you start CodeSavant in that directory.
+> Run npm test
 
-### Example SAVANT.md
+> Create a new component at src/components/Button.tsx
+```
 
-```markdown
-# Project: MyApp
+---
 
-## Overview
-E-commerce platform built with Next.js and PostgreSQL.
+## Subagents
 
-## Tech Stack
-- Frontend: Next.js 14, React 18, TailwindCSS
-- Backend: Node.js, Express, Prisma ORM
-- Database: PostgreSQL
-- Testing: Jest, Playwright
+Specialized AI agents that can be spawned for focused tasks:
 
-## Project Structure
-- `/src/app` - Next.js app router pages
-- `/src/components` - Reusable React components
-- `/src/lib` - Utility functions and helpers
-- `/src/api` - API route handlers
-- `/prisma` - Database schema and migrations
+| Subagent | Description | Best For |
+|----------|-------------|----------|
+| **explore** | Codebase exploration specialist | Understanding code structure, finding patterns |
+| **plan** | Research and planning agent | Creating implementation plans, architecture |
+| **bash** | Command execution specialist | Git operations, system tasks |
+| **general-purpose** | Multi-tool agent | Complex multi-step tasks |
+| **test-runner** | Test execution specialist | Running and analyzing tests |
+| **build-validator** | Build verification | Fixing compilation errors |
+| **code-guide** | Documentation lookup | CodeSavant feature help |
 
-## Coding Conventions
-- Use TypeScript strict mode
-- Prefer functional components with hooks
-- Use async/await over promises
-- Run `npm run lint` before committing
+### Using Subagents
 
-## Common Commands
-- `npm run dev` - Start development server
-- `npm run build` - Build for production
-- `npm run test` - Run test suite
-- `npm run db:migrate` - Run database migrations
+The AI automatically uses subagents for appropriate tasks, or you can request them:
 
-## Important Notes
-- Never commit .env files
-- Always run tests before pushing
-- Use conventional commits format
+```
+> Explore this codebase and explain the architecture
+
+> Plan how to implement user authentication
+
+> Run the tests and fix any failures
 ```
 
 ---
 
-## Tools
+## Skills System
 
-CodeSavant has access to powerful tools for interacting with your codebase:
+Skills are pre-built or custom AI behaviors for common tasks.
 
-### File Operations
+### Built-in Skills
 
-| Tool | Description |
-|------|-------------|
-| **Read** | Read file contents |
-| **Write** | Create or overwrite files |
-| **Edit** | Make precise edits with search/replace |
-| **Glob** | Find files using glob patterns |
-| **Grep** | Search file contents with regex |
+| Skill | Description |
+|-------|-------------|
+| `/commit` | Generate a git commit message |
+| `/review` | Review code for issues |
+| `/test` | Generate tests for code |
+| `/explain` | Explain how code works |
+| `/fix` | Debug and fix issues |
 
-### System Operations
+### Using Skills
 
-| Tool | Description |
-|------|-------------|
-| **Bash** | Execute shell commands |
-| **ListDir** | List directory contents |
+```
+> /commit
 
-### Examples
+> /review src/auth.ts
 
+> /test src/utils/validation.ts
 ```
-> Read the package.json file
 
-> Find all TypeScript files in src/
+### Creating Custom Skills
 
-> Search for "TODO" comments in the codebase
+Create a `SKILL.md` file in `~/.codesavant/skills/` or `.codesavant/skills/`:
 
-> Run the test suite
+```yaml
+---
+name: document
+description: Generate documentation for code
+triggers: ['document', 'docs', 'jsdoc']
+allowedTools: ['read_file', 'write_file', 'edit_file']
+permissionMode: acceptEdits
+maxTurns: 10
+author: Your Name
+version: 1.0
+---
 
-> Create a new component file at src/components/Button.tsx
+# Documentation Generator
+
+Generate comprehensive documentation for the specified code...
 ```
 
 ---
 
 ## Permission System
 
-CodeSavant asks for permission before potentially dangerous operations to keep your system safe.
+CodeSavant protects your system with a granular permission system.
 
 ### Permission Modes
 
 | Mode | Description |
 |------|-------------|
 | `default` | Ask for dangerous operations, auto-allow safe ones |
-| `strict` | Ask for all file writes and commands |
-| `permissive` | Auto-allow most operations (use with caution) |
+| `plan` | Read-only mode, no file modifications |
+| `acceptEdits` | Auto-approve file edits |
+| `strict` | Ask for all operations |
+| `yolo` | Auto-approve everything (dangerous!) |
+
+### Cycling Modes
 
-### Auto-Allowed Operations
-- Reading files
-- Searching with glob/grep
-- Git status, log, diff commands
-- npm/yarn info commands
+Press `Shift+Tab` in the REPL to cycle through permission modes, or use:
+
+```bash
+codesavant --mode plan
+codesavant --mode strict
+```
+
+### Interactive Prompts
+
+When prompted for permission:
+- `y` or `1` - Allow this once
+- `n` or `2` - Deny this once
+- `a` or `3` - Always allow (this session)
+- `v` or `4` - Never allow (this session)
 
 ### Auto-Denied Operations
+
 - `rm -rf /` and similar destructive commands
 - `sudo` commands
 - Writing to `.env` files
-- Commands with shell injection risks
+- Fork bombs and shell injection
 
-### Interactive Prompts
+---
+
+## Session Management
+
+Sessions persist conversations across terminal sessions.
+
+### Session Commands
+
+```bash
+# List all sessions
+codesavant sessions -l
+
+# Delete a session
+codesavant sessions -d <session-id>
+
+# Clean up old sessions (default: 30 days)
+codesavant sessions --cleanup [days]
+
+# Continue most recent session
+codesavant -c
+
+# Resume specific session
+codesavant -r <session-id>
+```
+
+### Session Features
 
-When prompted for permission, you can respond:
-- `y` or `yes` - Allow this once
-- `n` or `no` - Deny this once
-- `a` or `always` - Allow for this session
-- `never` - Deny for this session
+- **Atomic Writes**: Prevents data corruption
+- **Cost Tracking**: Per-message token usage and cost
+- **Checkpoints**: Save/restore conversation state
+- **Export**: Export to Markdown, JSON, or HTML
 
 ---
 
-## Skills
+## Configuration
 
-Skills are pre-built prompt templates for common tasks. Use them with the `/` prefix:
+### Configuration File
 
-| Skill | Description |
-|-------|-------------|
-| `/commit` | Generate a git commit message |
-| `/review` | Review code for issues |
-| `/test` | Generate tests for code |
-| `/explain` | Explain how code works |
-| `/refactor` | Suggest refactoring improvements |
+Location: `~/.codesavant/config.json`
 
-### Using Skills
+```json
+{
+  "defaultProvider": "deepseek",
+  "maxTokens": 8192,
+  "routingStrategy": "auto",
+  "providers": [
+    {
+      "name": "deepseek",
+      "model": "deepseek-chat",
+      "apiKey": "sk-...",
+      "costPerMToken": {"input": 0.14, "output": 0.28}
+    }
+  ],
+  "permissions": []
+}
+```
 
+### Configuration Commands
+
+```bash
+# View all configuration
+codesavant config --show
+
+# View available providers
+codesavant config --providers
+
+# Set a value
+codesavant config set defaultProvider deepseek
 ```
-> /commit
 
-> /review src/auth.ts
+### Directory Structure
 
-> /test src/utils/validation.ts
+```
+~/.codesavant/
+├── config.json      # Global configuration
+├── mcp.json         # MCP server configurations
+├── SAVANT.md        # Global memory
+├── sessions/        # Saved sessions
+├── checkpoints/     # Conversation checkpoints
+├── audit/           # Permission audit logs
+└── skills/          # Custom skills
+```
+
+---
+
+## Project Memory (SAVANT.md)
+
+CodeSavant uses a three-level memory hierarchy:
+
+| Level | File | Purpose |
+|-------|------|---------|
+| **User** | `~/.codesavant/SAVANT.md` | Global preferences |
+| **Project** | `./SAVANT.md` | Project-specific context |
+| **Local** | `./SAVANT.local.md` | Personal overrides (gitignored) |
+
+### Example SAVANT.md
+
+```markdown
+# Project: MyApp
+
+## Overview
+E-commerce platform built with Next.js and PostgreSQL.
+
+## Tech Stack
+- Frontend: Next.js 14, React 18, TailwindCSS
+- Backend: Node.js, Express, Prisma ORM
+- Database: PostgreSQL
+- Testing: Jest, Playwright
+
+## Project Structure
+- `/src/app` - Next.js app router pages
+- `/src/components` - Reusable React components
+- `/src/lib` - Utility functions
+- `/prisma` - Database schema
+
+## Coding Conventions
+- Use TypeScript strict mode
+- Prefer functional components
+- Run `npm run lint` before committing
+
+## Common Commands
+- `npm run dev` - Start dev server
+- `npm run build` - Build for production
+- `npm run test` - Run tests
 ```
 
 ---
 
 ## MCP Integration
 
-CodeSavant supports the Model Context Protocol (MCP) for extending functionality with external tools.
+CodeSavant supports the Model Context Protocol (MCP) for extending functionality.
 
 ### Configure MCP Servers
 
-Create `.codesavant/mcp.json` in your project:
+Create `~/.codesavant/mcp.json`:
 
 ```json
 {
   "servers": {
     "filesystem": {
+      "transport": "stdio",
       "command": "npx",
-      "args": ["-y", "@anthropic/mcp-server-filesystem", "/path/to/allowed/dir"]
+      "args": ["-y", "@anthropic/mcp-server-filesystem", "/path/to/dir"]
     },
     "github": {
+      "transport": "stdio",
       "command": "npx",
       "args": ["-y", "@anthropic/mcp-server-github"],
       "env": {
         "GITHUB_TOKEN": "${GITHUB_TOKEN}"
       }
     }
+  },
+  "settings": {
+    "defaultTimeout": 30000,
+    "maxConcurrent": 5
   }
 }
 ```
 
-### View MCP Status
+### MCP Commands
 
 ```bash
-codesavant mcp status
+codesavant mcp --list              # List configured servers
+codesavant mcp add name "command"  # Add a server
+codesavant mcp remove name         # Remove a server
 ```
 
+### Supported Transports
+
+- **stdio** - Standard input/output (local processes)
+- **http** - HTTP/HTTPS endpoints
+- **sse** - Server-Sent Events
+
 ---
 
-## VS Code Extension
+## Live Preview
 
-CodeSavant includes a VS Code extension for integrated development.
+Manage development server for web projects:
 
-### Features
-- Start CodeSavant chat from VS Code
-- Explain selected code
-- Fix code issues
-- Generate tests
-- Code review
+```
+> /preview start                    # Start dev server
+> /preview start --port 3000        # Specify port
+> /preview stop                     # Stop server
+> /preview status                   # Show status
+> /preview open                     # Open in browser
+> /preview list                     # List running servers
+```
+
+### Supported Frameworks
+
+- Next.js
+- Vite (React, Vue, Svelte)
+- Create React App
+- Angular
+- Nuxt
+- Astro
+- Gatsby
+
+---
+
+## CI/CD Fix Mode
 
-### Installation
+Automatically fix build and test failures:
 
 ```bash
-cd vscode-extension
-npm install
-npm run compile
+# Auto-fix until CI passes (max 10 attempts)
+codesavant --fix-ci
+
+# Custom max attempts
+codesavant --fix-ci --fix-ci-max-attempts 5
+
+# Specify CI commands
+codesavant --fix-ci --fix-ci-commands "npm test,npm run build"
 ```
 
-Then press F5 in VS Code to launch in debug mode.
+CodeSavant will:
+1. Run CI commands
+2. Analyze failures
+3. Apply fixes
+4. Repeat until passing or max attempts reached
 
 ---
 
-## Environment Variables
+## Checkpoints & Recovery
 
-### API Keys
+### Automatic Checkpoints
 
-| Variable | Description |
-|----------|-------------|
-| `DEEPSEEK_API_KEY` | DeepSeek API key |
-| `GROQ_API_KEY` | Groq API key |
-| `GEMINI_API_KEY` | Google Gemini API key |
-| `OPENAI_API_KEY` | OpenAI API key |
-| `ANTHROPIC_API_KEY` | Anthropic API key |
-| `GOOGLE_APPLICATION_CREDENTIALS` | Path to GCP credentials for Vertex AI |
+CodeSavant automatically creates checkpoints:
+- Before file modifications
+- Periodically during long sessions
+- On graceful shutdown
 
-### Configuration
+### Rewind to Checkpoint
 
-| Variable | Description |
-|----------|-------------|
-| `CODESAVANT_PROVIDER` | Default AI provider |
-| `CODESAVANT_MODEL` | Default model to use |
-| `CODESAVANT_CONFIG_PATH` | Custom config file path |
+Press `Esc Esc` (double escape) to rewind to the last checkpoint, restoring:
+- Conversation state
+- Modified files
 
-### Shell Configuration
+### Session Recovery
 
-Add to your `~/.bashrc` or `~/.zshrc`:
+If a session crashes, CodeSavant can recover:
+- Detect crashed sessions
+- Restore conversation state
+- Retry failed operations
+
+---
+
+## Enterprise Features
+
+CodeSavant includes enterprise-grade features:
+
+| Feature | Description |
+|---------|-------------|
+| **Managed Policies** | Organization-wide tool/provider restrictions |
+| **SSO/SAML** | OAuth2 and SAML 2.0 authentication |
+| **Audit Logging** | Complete audit trail of all operations |
+| **Team Sharing** | Share sessions and workspaces |
+| **Budget Controls** | Token and cost limits per user/team |
+| **Admin Console** | Organization and user management |
+
+---
+
+## Debug & Troubleshooting
+
+### Debug Logging
 
 ```bash
-# API Keys
-export DEEPSEEK_API_KEY="your-key-here"
+# Enable specific debug categories
+codesavant --debug api,mcp,tool
 
-# Aliases
-alias cs="codesavant"
-alias csc="codesavant -c"
+# Enable all except MCP
+codesavant --debug all,!mcp
+
+# MCP protocol debugging
+codesavant --mcp-debug
+
+# Verbose output
+codesavant --verbose
 ```
 
----
+### Debug Categories
+
+`api`, `mcp`, `tool`, `provider`, `stream`, `session`, `context`, `permission`, `checkpoint`, `error`, `all`
+
+### Doctor Command
 
-## Troubleshooting
+```bash
+codesavant doctor
+```
+
+Checks:
+- Node.js version
+- Provider configurations
+- API key validity
+- ripgrep installation
+- File permissions
 
 ### Common Issues
 
 #### "No AI providers available"
 
 ```bash
-# Check which providers are configured
 codesavant config --providers
-
-# Verify API key is set
 echo $DEEPSEEK_API_KEY
 ```
 
-#### "Permission denied" errors
+#### npm permission errors
 
 ```bash
-# Run the doctor command
-codesavant doctor
-
-# Check file permissions
-ls -la ~/.codesavant/
+sudo chown -R $(whoami) ~/.npm
+npm cache clean --force
 ```
 
 #### Session not persisting
 
 ```bash
-# Check sessions directory exists
 ls ~/.codesavant/sessions/
-
-# List available sessions
-codesavant --list-sessions
+codesavant sessions -l
 ```
 
-#### Slow responses
-
-- Try a faster provider like Groq
-- Reduce `maxTokens` in config
-- Use `/compact` to reduce context size
+---
 
-### Debug Mode
+## CLI Reference
 
-```bash
-# Run with verbose logging
-DEBUG=codesavant* codesavant
 ```
+Usage: codesavant [options] [command] [prompt]
 
-### Reset Configuration
+Options:
+  -V, --version                    Output version number
+  --verbose                        Enable verbose logging
+  --debug <categories>             Enable debug logging (api,mcp,tool,...)
+  --mcp-debug                      Enable MCP protocol debugging
+  -p, --print                      Non-interactive print mode
+  -c, --continue                   Continue last session
+  -r, --resume <sessionId>         Resume specific session
+  --provider <provider>            Select provider (deepseek, groq, etc.)
+  --max-tokens <tokens>            Maximum tokens in response
+  -m, --mode <mode>                Permission mode (default, plan, strict)
+  -o, --output-format <format>     Output format (text, json, stream-json)
+  --system-prompt <prompt>         Override system prompt
+  --append-system-prompt <text>    Append to system prompt
+  --allowed-tools <tools>          Restrict to specific tools
+  --disallowed-tools <tools>       Block specific tools
+  --input-format <format>          Input format (text, stream-json)
+  --fix-ci                         CI/CD fix mode
+  --fix-ci-max-attempts <n>        Max fix attempts (default: 10)
+  --fix-ci-commands <commands>     CI commands to run
+  --max-turns <turns>              Maximum conversation turns
+  --dangerously-skip-permissions   Skip all permission checks
+  --no-mcp                         Disable MCP servers
+  --model <model>                  Specific model to use
+  --classic                        Use classic terminal UI
+  -h, --help                       Display help
 
-```bash
-# Remove config and start fresh
-rm -rf ~/.codesavant/config.json
-codesavant
+Commands:
+  config                           Manage configuration
+  sessions                         List and manage sessions
+  mcp                              Manage MCP servers
+  doctor                           Run diagnostic checks
+  upgrade                          Check for updates
 ```
 
 ---
 
-## CLI Reference
+## Environment Variables
 
-```
-Usage: codesavant [options] [prompt]
+### API Keys
 
-Options:
-  -V, --version          Output version number
-  -c, --continue         Continue last session
-  -r, --resume <id>      Resume specific session
-  -p, --provider <name>  Use specific provider
-  -m, --model <name>     Use specific model
-  --list-sessions        List all saved sessions
-  --no-memory            Disable project memory (SAVANT.md)
-  -h, --help             Display help
+| Variable | Description |
+|----------|-------------|
+| `DEEPSEEK_API_KEY` | DeepSeek API key |
+| `GROQ_API_KEY` | Groq API key |
+| `GEMINI_API_KEY` | Google Gemini API key |
+| `OPENAI_API_KEY` | OpenAI API key |
+| `ANTHROPIC_API_KEY` | Anthropic API key |
+| `GOOGLE_APPLICATION_CREDENTIALS` | Path to GCP credentials |
 
-Commands:
-  config                 Manage configuration
-  doctor                 Diagnose issues
-  init                   Initialize project
-  mcp                    Manage MCP servers
+### Shell Configuration
+
+Add to your `~/.bashrc` or `~/.zshrc`:
+
+```bash
+# API Keys
+export DEEPSEEK_API_KEY="your-key-here"
+
+# Aliases
+alias cs="codesavant"
+alias csc="codesavant -c"
 ```
 
 ---
@@ -596,8 +830,9 @@ MIT License - see the [LICENSE](LICENSE) file for details.
 ## Acknowledgments
 
 - Built with [Commander.js](https://github.com/tj/commander.js/)
-- Terminal UI powered by [Chalk](https://github.com/chalk/chalk) and [Ink](https://github.com/vadimdemedes/ink)
-- AI integrations via [OpenAI SDK](https://github.com/openai/openai-node) and [Google Generative AI](https://github.com/google/generative-ai-js)
+- Terminal UI powered by [Ink](https://github.com/vadimdemedes/ink) and [Chalk](https://github.com/chalk/chalk)
+- AI integrations via [OpenAI SDK](https://github.com/openai/openai-node)
+- Fast search with [ripgrep](https://github.com/BurntSushi/ripgrep)
 
 ---
 
@@ -605,6 +840,6 @@ MIT License - see the [LICENSE](LICENSE) file for details.
 
 **Made with love by [Vishal Aggarwal](https://github.com/burnisback)**
 
-[Report Bug](https://github.com/burnisback/code-savant-ai/issues) · [Request Feature](https://github.com/burnisback/code-savant-ai/issues)
+[Report Bug](https://github.com/burnisback/codesavant/issues) · [Request Feature](https://github.com/burnisback/codesavant/issues)
 
 </div>

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "codesavant",
-  "version": "1.2.7",
+  "version": "1.2.8",
   "description": "Multi-provider AI coding assistant for your terminal",
   "type": "module",
   "bin": {