slug-code/CLAUDE.md

Slug Code

FOSS Rust rewrite of Claude Code — an AI coding assistant with a pluggable LLM backend targeting OpenAI-compatible APIs (vLLM, Ollama, llama.cpp, OpenAI, etc.).

Project

• Binary: slug
• Package: slug-code
• Branch: rust-rewrite (orphan branch — master holds original TypeScript source as reference)
• Working directory: /home/bryan/Downloads/claude/src

Architecture

Module	Purpose
src/main.rs	CLI entry (clap), wires everything together
src/provider/	Provider trait + OpenAI-compatible streaming SSE impl
src/agent/	Core agent loop: stream → tool exec → repeat, SLUG.md injected per turn
src/tools/	Tool trait + bash, read, write, edit, glob, grep
src/tui/	Interactive REPL (basic stdin/stdout — ratatui TUI not yet built)
src/permissions/	ask/yolo/sandbox/allowEdits + glob allow/deny from settings.json
src/slugmd/	SLUG.md hierarchy loaded every turn (40K char budget)
src/session/	JSONL session persistence at ~/.slug/sessions/
src/hooks/	5 lifecycle events, command + prompt hook types
src/compact/	3 compaction strategies, /compact command
src/config/	TOML config + CLI overrides + env vars

Conventions

• Rust 2024 edition
• No unwrap() in non-test code — use ? or anyhow
• No analytics, telemetry, or Anthropic-internal features
• Provider trait is the abstraction boundary — new LLM backends implement it
• Permissions are checked in agent::execute_with_permission before any tool runs
• SLUG.md is never stored in self.messages — rebuilt from disk every turn

Completed Features

• OpenAI-compatible provider with streaming SSE
• 6 core tools: bash, read, write, edit, glob, grep
• Agent loop with tool use
• Permission system: ask / yolo / sandbox / allowEdits + glob patterns in ~/.slug/settings.json
• SLUG.md hierarchy (global/project/rules/local)
• Session persistence: --continue, --resume, --fork-session
• Hook system: PreToolUse, PostToolUse, UserPromptSubmit, SessionStart, SessionEnd
• Compaction: ToolResultTrim → Truncate, /compact command

Remaining Work (Prioritized)

High

• Proper ratatui TUI — markdown rendering, scrollback, syntax highlighting
• Retry system — exponential backoff + model fallback on repeated failures
• Clean interrupt — Escape aborts active stream without losing context
• Wire PreToolUse/PostToolUse hooks into agent tool execution
• Concurrent reads / serial writes (tool batching)

Medium

• Anthropic API provider (different format from OpenAI)
• Google Gemini provider
• MCP client support
• Subagent parallelism (fork/teammate/worktree models)

Low

• Computer use integration
• Session search
• Plugin system beyond hooks

Running

cargo build
./target/debug/slug --help

# Connect to local vLLM
slug -e http://localhost:8000/v1 -m qwen2.5-coder

# Connect to OpenAI
slug -e https://api.openai.com/v1 -k $OPENAI_API_KEY -m gpt-4o

# Resume last session
slug --continue

# Sandbox mode (auto-approve everything in current dir)
slug --sandbox .

# Skip all permissions
slug --yolo

Settings

Config file: ~/.slug/config.toml

endpoint = "http://localhost:8000/v1"
model = "qwen2.5-coder-32b"
max_tokens = 4096
permission_mode = { type = "ask" }

Permission rules: ~/.slug/settings.json or .slug/settings.json

{
  "permissions": {
    "allow": ["Bash(cargo *)", "Bash(git *)", "Edit(src/**)", "Write(src/**)"],
    "deny": ["Bash(rm -rf *)", "Bash(sudo *)"]
  }
}