abstractcode 0.1.0__tar.gz → 0.2.0__tar.gz

{abstractcode-0.1.0 → abstractcode-0.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: abstractcode
-Version: 0.1.0
+Version: 0.2.0
 Summary: A clean terminal CLI for multi-agent agentic coding
 Author-email: Laurent-Philippe Albou <contact@abstractcore.ai>
 Maintainer-email: Laurent-Philippe Albou <contact@abstractcore.ai>
@@ -25,6 +25,7 @@ Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Requires-Python: >=3.8
 Description-Content-Type: text/markdown
 License-File: LICENSE
+Requires-Dist: prompt_toolkit>=3.0.0
 Provides-Extra: dev
 Requires-Dist: pytest>=7.0.0; extra == "dev"
 Requires-Dist: pytest-cov>=4.0.0; extra == "dev"
@@ -41,13 +42,15 @@ Dynamic: license-file
 
 ---
 
-## 🚧 Under Development
+## Status
 
-AbstractCode is currently under active development. This is a placeholder release to reserve the package name on PyPI.
+AbstractCode is under active development. A minimal interactive shell exists to support manual testing of AbstractAgent workflows.
+
+Note: the PyPI release may lag behind the monorepo. For the latest development version, install from source.
 
 ## What is AbstractCode?
 
-AbstractCode is a clean terminal CLI for multi-agent agentic coding, similar to Claude Code, Codex, and Gemini CLI. It leverages the Abstract Framework ecosystem to provide seamless AI-powered coding assistance directly in your terminal.
+AbstractCode is a clean terminal CLI for multi-agent agentic coding, similar to Claude Code, Codex, and Gemini CLI. It leverages the powerful Abstract Framework ecosystem to provide seamless AI-powered coding assistance directly in your terminal.
 
 ## The Abstract Framework
 
@@ -75,7 +78,34 @@ pip install abstractcode
 ## Quick Start
 
 ```bash
-# Coming soon!
+# Show options
+abstractcode --help
+
+# Durable resume is enabled by default (state file: ~/.abstractcode/state.json)
+# Override with:
+ABSTRACTCODE_STATE_FILE=.abstractcode.state.json abstractcode
+
+# Or disable persistence (in-memory only; cannot resume after quitting)
+abstractcode --no-state
+
+# Auto-approve tool calls (unsafe; bypasses interactive approvals)
+abstractcode --auto-approve
+
+# Limit agent iterations per task (default: 20)
+abstractcode --max-iterations 25
+```
+
+Notes:
+- Run resume state is stored next to the state file in `*.d/`.
+- Conversation history is stored in the run state (`RunState.vars["context"]["messages"]`) inside `*.d/`, and AbstractCode keeps the state file pointing at the most recent run so restarts can reload context.
+- In the interactive shell, commands are slash-prefixed (e.g. `/help`, `/status`, `/history`, `/task ...`).
+
+## Development (Monorepo)
+
+From the monorepo root:
+
+```bash
+pip install -e ./abstractcore -e ./abstractruntime -e ./abstractagent -e ./abstractcode
 abstractcode --help
 ```
 
@@ -112,3 +142,19 @@ MIT License - see LICENSE file for details.
 
 **AbstractCode** - Multi-agent agentic coding in your terminal, powered by the Abstract Framework.
 
+## Default Tools
+
+AbstractCode provides a curated set of 8 tools for coding tasks:
+
+| Tool | Description |
+|------|-------------|
+| `list_files` | Find and list files using glob patterns (case-insensitive) |
+| `search_files` | Search for text patterns inside files using regex |
+| `read_file` | Read file contents with optional line range |
+| `write_file` | Write content to files, creating directories as needed |
+| `edit_file` | Edit files by replacing text patterns (supports regex, line ranges, preview mode) |
+| `execute_command` | Execute shell commands with security controls |
+| `web_search` | Search the web via DuckDuckGo (no API key required) |
+| `self_improve` | Log improvement suggestions for later review |
+
+Additional tools are available via AbstractAgent for specialized use cases (execute_python, fetch_url).

abstractcode-0.2.0/README.md

@@ -0,0 +1,125 @@
+# AbstractCode
+
+**A clean terminal CLI for multi-agent agentic coding**
+
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+[![Python 3.8+](https://img.shields.io/badge/python-3.8+-blue.svg)](https://www.python.org/downloads/)
+
+---
+
+## Status
+
+AbstractCode is under active development. A minimal interactive shell exists to support manual testing of AbstractAgent workflows.
+
+Note: the PyPI release may lag behind the monorepo. For the latest development version, install from source.
+
+## What is AbstractCode?
+
+AbstractCode is a clean terminal CLI for multi-agent agentic coding, similar to Claude Code, Codex, and Gemini CLI. It leverages the powerful Abstract Framework ecosystem to provide seamless AI-powered coding assistance directly in your terminal.
+
+## The Abstract Framework
+
+AbstractCode is built on top of the Abstract Framework, a comprehensive suite of tools for AI-powered development:
+
+- **[AbstractCore](https://github.com/lpalbou/abstractcore)** - Unified interface for multiple LLM providers
+- **[AbstractRuntime](https://github.com/lpalbou/abstractruntime)** - Runtime environment for AI agents
+- **[AbstractAgent](https://github.com/lpalbou/abstractagent)** - Multi-agent orchestration and coordination
+
+## Features (Coming Soon)
+
+- 🤖 **Multi-Agent Coding** - Coordinate multiple AI agents for complex coding tasks
+- 🔌 **Provider Agnostic** - Works with OpenAI, Anthropic, Ollama, and more
+- 💻 **Terminal Native** - Clean CLI interface for seamless workflow integration
+- 🎯 **Context Aware** - Understands your codebase and project structure
+- 🔄 **Iterative Development** - Collaborative coding with AI assistance
+- 🌐 **Offline Capable** - Works with local models via Ollama
+
+## Installation
+
+```bash
+pip install abstractcode
+```
+
+## Quick Start
+
+```bash
+# Show options
+abstractcode --help
+
+# Durable resume is enabled by default (state file: ~/.abstractcode/state.json)
+# Override with:
+ABSTRACTCODE_STATE_FILE=.abstractcode.state.json abstractcode
+
+# Or disable persistence (in-memory only; cannot resume after quitting)
+abstractcode --no-state
+
+# Auto-approve tool calls (unsafe; bypasses interactive approvals)
+abstractcode --auto-approve
+
+# Limit agent iterations per task (default: 20)
+abstractcode --max-iterations 25
+```
+
+Notes:
+- Run resume state is stored next to the state file in `*.d/`.
+- Conversation history is stored in the run state (`RunState.vars["context"]["messages"]`) inside `*.d/`, and AbstractCode keeps the state file pointing at the most recent run so restarts can reload context.
+- In the interactive shell, commands are slash-prefixed (e.g. `/help`, `/status`, `/history`, `/task ...`).
+
+## Development (Monorepo)
+
+From the monorepo root:
+
+```bash
+pip install -e ./abstractcore -e ./abstractruntime -e ./abstractagent -e ./abstractcode
+abstractcode --help
+```
+
+## Requirements
+
+- Python 3.8 or higher
+- AbstractCore
+- AbstractRuntime
+- AbstractAgent
+
+## Documentation
+
+Full documentation will be available at [abstractcore.ai](https://abstractcore.ai)
+
+## Development Status
+
+This project is in early development. Stay tuned for updates!
+
+## Contributing
+
+Contributions are welcome! Please check back soon for contribution guidelines.
+
+## Contact
+
+**Maintainer:** Laurent-Philippe Albou  
+📧 Email: contact@abstractcore.ai  
+🌐 Website: [abstractcore.ai](https://abstractcore.ai)
+
+## License
+
+MIT License - see LICENSE file for details.
+
+---
+
+**AbstractCode** - Multi-agent agentic coding in your terminal, powered by the Abstract Framework.
+
+## Default Tools
+
+AbstractCode provides a curated set of 8 tools for coding tasks:
+
+| Tool | Description |
+|------|-------------|
+| `list_files` | Find and list files using glob patterns (case-insensitive) |
+| `search_files` | Search for text patterns inside files using regex |
+| `read_file` | Read file contents with optional line range |
+| `write_file` | Write content to files, creating directories as needed |
+| `edit_file` | Edit files by replacing text patterns (supports regex, line ranges, preview mode) |
+| `execute_command` | Execute shell commands with security controls |
+| `web_search` | Search the web via DuckDuckGo (no API key required) |
+| `self_improve` | Log improvement suggestions for later review |
+
+Additional tools are available via AbstractAgent for specialized use cases (execute_python, fetch_url).

abstractcode-0.2.0/abstractcode/__init__.py

@@ -0,0 +1,23 @@
+"""
+AbstractCode - A clean terminal CLI for multi-agent agentic coding
+
+This package provides a terminal-based interface for AI-powered coding assistance
+using multiple coordinated agents. Built on the Abstract Framework ecosystem.
+
+Author: Laurent-Philippe Albou
+Email: contact@abstractcore.ai
+Website: https://abstractcore.ai
+"""
+
+__version__ = "0.2.0"
+__author__ = "Laurent-Philippe Albou"
+__email__ = "contact@abstractcore.ai"
+__license__ = "MIT"
+
+def main(argv=None):
+    """Console entrypoint for `abstractcode`."""
+    from .cli import main as _main
+
+    return _main(argv)
+
+__all__ = ["__version__", "__author__", "__email__", "__license__", "main"]

abstractcode-0.2.0/abstractcode/cli.py

@@ -0,0 +1,110 @@
+from __future__ import annotations
+
+import argparse
+import os
+import sys
+from pathlib import Path
+from typing import Optional, Sequence
+
+from .react_shell import ReactShell
+
+
+def _default_state_file() -> str:
+    env = os.getenv("ABSTRACTCODE_STATE_FILE")
+    if env:
+        return env
+    return str(Path.home() / ".abstractcode" / "state.json")
+
+
+def _default_max_iterations() -> int:
+    env = os.getenv("ABSTRACTCODE_MAX_ITERATIONS")
+    if env:
+        try:
+            value = int(env)
+        except ValueError:
+            raise SystemExit("ABSTRACTCODE_MAX_ITERATIONS must be an integer.")
+        if value < 1:
+            raise SystemExit("ABSTRACTCODE_MAX_ITERATIONS must be >= 1.")
+        return value
+    return 25
+
+
+def _default_max_tokens() -> Optional[int]:
+    env = os.getenv("ABSTRACTCODE_MAX_TOKENS")
+    if env:
+        try:
+            value = int(env)
+        except ValueError:
+            raise SystemExit("ABSTRACTCODE_MAX_TOKENS must be an integer.")
+        if value < 1024:
+            raise SystemExit("ABSTRACTCODE_MAX_TOKENS must be >= 1024.")
+        return value
+    return 32768  # Default 32k context
+
+
+def build_parser() -> argparse.ArgumentParser:
+    parser = argparse.ArgumentParser(
+        prog="abstractcode",
+        description="AbstractCode: an interactive terminal shell for AbstractFramework agents (MVP).",
+    )
+    parser.add_argument(
+        "--agent",
+        choices=("react", "codeact"),
+        default=os.getenv("ABSTRACTCODE_AGENT", "react"),
+        help="Agent type to run (react|codeact).",
+    )
+    parser.add_argument("--provider", default="ollama", help="LLM provider (e.g. ollama, openai)")
+    parser.add_argument("--model", default="qwen3:1.7b-q4_K_M", help="Model name")
+    parser.add_argument(
+        "--state-file",
+        default=_default_state_file(),
+        help="Path to save the current run reference (enables durable file-backed stores).",
+    )
+    parser.add_argument(
+        "--no-state",
+        action="store_true",
+        help="Disable persistence (keeps run state in memory; cannot resume after quitting).",
+    )
+    parser.add_argument(
+        "--auto-approve",
+        "--auto-accept",
+        action="store_true",
+        dest="auto_approve",
+        help="Automatically approve tool calls (unsafe; disables interactive approvals).",
+    )
+    parser.add_argument(
+        "--max-iterations",
+        type=int,
+        default=_default_max_iterations(),
+        help="Maximum ReAct reasoning iterations per task (default: 25).",
+    )
+    parser.add_argument(
+        "--max-tokens",
+        type=int,
+        default=_default_max_tokens(),
+        help="Maximum context tokens for LLM calls (default: 32768).",
+    )
+    parser.add_argument("--no-color", action="store_true", help="Disable ANSI colors")
+    return parser
+
+
+def main(argv: Optional[Sequence[str]] = None) -> int:
+    args = build_parser().parse_args(list(argv) if argv is not None else None)
+    state_file = None if args.no_state else args.state_file
+
+    shell = ReactShell(
+        agent=str(args.agent),
+        provider=args.provider,
+        model=args.model,
+        state_file=state_file,
+        auto_approve=bool(args.auto_approve),
+        max_iterations=int(args.max_iterations),
+        max_tokens=args.max_tokens,
+        color=not bool(args.no_color),
+    )
+    shell.run()
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main(sys.argv[1:]))