AnchorCli/README.md

AnchorCli

An AI-powered coding assistant built as a .NET 10.0 console application, featuring the Hashline technique for safe, precise file editing.

What is Hashline?

AnchorCli's unique approach to file editing. Every line returned by file tools is prefixed with a content-derived hash anchor:

1:a3|  function hello() {
2:f1|    return "world";
3:0e|  }

When editing, you reference these line:hash anchors instead of reproducing old content. Before any mutation, both the line number and hash are validated — stale anchors are rejected immediately.

This eliminates:

• Whitespace/indentation reproduction errors
• Silent edits to the wrong line in large files
• Entire-file rewrites just to change one line

Features

• Interactive REPL: Chat with an AI model to edit files, manage directories, and execute commands
• Slash Commands: /setup, /help, /exit, /clear, /status, /compact
• Token Tracking: Real-time token usage and cost per response, plus session totals
• Model Pricing Display: Shows current model pricing from OpenRouter in the header
• Context Compaction: Automatic conversation history compression when approaching context limits, including stale tool result compaction
• Comprehensive Toolset: 15 tools for file operations, editing, directory management, and command execution
• AOT-Ready: Native AOT compilation for ~12 MB binaries with no .NET runtime dependency
• Rich CLI: Beautiful terminal output using Spectre.Console with tables, rules, and colored text
• Streaming Responses: Real-time AI response streaming in the terminal
• OpenAI-Compatible: Works with any OpenAI-compatible API (OpenAI, Ollama, Cerebras, Groq, OpenRouter, etc.)
• Ctrl+C Support: Cancel in-progress responses without exiting

Requirements

• .NET 10 SDK
• clang (for native AOT publish on Linux)

Quick Start

# Run the application
dotnet run --project AnchorCli

# First time? The app will prompt you to run /setup
# Or run it explicitly:
dotnet run --project AnchorCli
/setup

Native AOT Build

dotnet publish AnchorCli -r linux-x64 -c Release
./AnchorCli/bin/Release/net10.0/linux-x64/publish/anchor

The resulting binary is ~12 MB, has no .NET runtime dependency, and starts instantly.

Slash Commands

Command	Description
/setup	Run interactive TUI to configure API key and model (also accessible via anchor setup subcommand)
/help	Show available tools and commands
/exit	Exit the application
/clear	Clear the conversation history
/status	Show session token usage and cost
/compact	Manually trigger context compaction

Available Tools

File Operations:

• read_file - Read a file (or a window) with Hashline-tagged lines
• grep_file - Search a file by regex — results are pre-tagged for immediate editing
• grep_recursive - Search for a regex pattern across all files in a directory tree
• find_files - Search for files matching glob patterns
• get_file_info - Get detailed file information (size, permissions, etc.)

Edit Operations:

• replace_lines - Replace a range identified by line:hash anchors
• insert_after - Insert lines after an anchor
• delete_range - Delete a range between two anchors
• create_file - Create a new file with optional initial content
• delete_file - Delete a file permanently
• rename_file - Rename or move a file
• copy_file - Copy a file to a new location
• append_to_file - Append lines to the end of a file

Directory Operations:

• list_dir - List directory contents
• create_dir - Create a new directory (with parent directories)
• rename_dir - Rename or move a directory
• delete_dir - Delete a directory and all its contents

Command Execution:

• execute_command - Run shell commands (with user approval)

Project Structure

AnchorCli/
├── Program.cs              # Entry point + REPL loop + AI client setup
├── AnchorConfig.cs        # JSON file-based configuration (~APPDATA~\anchor\config.json)
├── ContextCompactor.cs    # Conversation history compression
├── AppJsonContext.cs      # Source-generated JSON context (AOT)
├── Hashline/
│   ├── HashlineEncoder.cs  # Adler-8 + position-seed hashing
│   └── HashlineValidator.cs # Anchor resolution + validation
├── Tools/
│   ├── FileTools.cs        # read_file, grep_file, grep_recursive, find_files, get_file_info
│   ├── EditTools.cs        # replace_lines, insert_after, delete_range, create/delete/rename/copy/append
│   ├── DirTools.cs         # list_dir, create_dir, rename_dir, delete_dir
│   └── CommandTool.cs      # execute_command
├── Commands/
│   ├── ExitCommand.cs      # /exit command
│   ├── HelpCommand.cs      # /help command
│   ├── ClearCommand.cs     # /clear command
│   ├── StatusCommand.cs    # /status command
│   └── CompactCommand.cs   # /compact command
├── OpenRouter/
│   └── PricingProvider.cs  # Fetch model pricing from OpenRouter
└── SetupTui.cs            # Interactive setup TUI

How It Works

1. Setup: Configure API credentials via the /setup command (or anchor setup subcommand)
2. REPL Loop: You interact with the AI through a conversational interface
3. Tool Calling: The AI can call any of the available tools to read/edit files, manage directories, or execute commands
4. Hashline Validation: All file edits are validated using the Hashline technique to ensure precision
5. Token Tracking: Responses show token usage and cost; session totals are maintained
6. Context Compaction: When approaching context limits, conversation history is automatically compressed
7. Safe Execution: Commands require explicit user approval before running

Supported Models

AnchorCli works with any OpenAI-compatible API endpoint, including:

• OpenAI (gpt-4o, gpt-4.1, etc.)
• Ollama (local models)
• Cerebras
• Groq
• OpenRouter (qwen3.5-27b, etc.)
• Any custom OpenAI-compatible server

License

MIT License - See LICENSE file for details.