Skip to main content

Hierarchical Embodied Autonomously Validating Evolution Network Tree REPL

Project description

HEAVEN Tree REPL

Hierarchical Embodied Autonomously Validating Evolution Network Tree REPL - A modular tree navigation system with persistent state, pathway recording, and agent management capabilities.

Features

  • Geometric Tree Navigation: Navigate through hierarchical structures using coordinate-based addressing (0.1.2.3)
  • Live Variable Persistence: Session variables persist throughout navigation and execution
  • Pathway Recording & Templates: Record navigation sequences and convert them to reusable templates
  • RSI Analysis: Pattern recognition, crystallization, and optimization insights
  • Agent Management: Support for both user-level and agent-level tree shells with approval workflows
  • Modular Architecture: Clean separation of concerns with mixin-based design

Installation

pip install heaven-tree-repl

Quick Start

from heaven_tree_repl import TreeShell

# Create a basic tree configuration
config = {
    "app_id": "my_app",
    "domain": "example",
    "role": "assistant",
    "nodes": {
        "root": {
            "type": "Menu",
            "prompt": "Main Menu",
            "description": "Root menu",
            "options": {
                "1": "math_ops"
            }
        },
        "math_ops": {
            "type": "Callable",
            "prompt": "Math Operations",
            "description": "Perform mathematical operations",
            "function_name": "_test_add",
            "args_schema": {"a": "int", "b": "int"}
        }
    }
}

# Initialize TreeShell
shell = TreeShell(config)

# Navigate and execute
response = shell.handle_command("1")  # Navigate to math_ops
response = shell.handle_command('1 {"a": 5, "b": 3}')  # Execute with args

Architecture

The system is built using a modular mixin architecture:

  • TreeShellBase: Core navigation and state management
  • MetaOperationsMixin: Variable management and session operations
  • PathwayManagementMixin: Recording, saving, and template analysis
  • CommandHandlersMixin: Navigation and interaction commands
  • RSIAnalysisMixin: Pattern recognition and crystallization
  • ExecutionEngineMixin: Core action execution
  • AgentManagementMixin: Agent and user tree repl classes

Agent Support

The system supports both user-level and agent-level interactions:

from heaven_tree_repl import UserTreeShell, AgentTreeShell

# User shell with approval capabilities
user_shell = UserTreeShell()

# Agent shell with quarantine restrictions
agent_shell = AgentTreeShell(config, session_id="agent_001", 
                            approval_callback=user_shell._receive_agent_approval_request)

Development Roadmap

See docs/DEVELOPMENT_ROADMAP.md for the complete phased development plan:

  1. Phase 1: Prompt Engineering Agent Prototype (Current)
  2. Phase 2: General Adaptor Layer
  3. Phase 3: Universal Agent App Generator
  4. Phase 4: Game Mechanics Integration
  5. Phase 5: Enhanced Base Library
  6. Phase 6: Advanced Integrations (MCP, Full HEAVEN)

Future game mechanics specifications are in docs/future_implementations/.

Development

# Clone the repository
git clone https://github.com/yourusername/heaven-tree-repl.git
cd heaven-tree-repl

# Install in development mode
pip install -e .[dev]

# Run tests
pytest

License

MIT License - see LICENSE file for details.

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.# Domain chain system implemented

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

heaven_tree_repl-0.1.37.tar.gz (152.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

heaven_tree_repl-0.1.37-py3-none-any.whl (144.4 kB view details)

Uploaded Python 3

File details

Details for the file heaven_tree_repl-0.1.37.tar.gz.

File metadata

  • Download URL: heaven_tree_repl-0.1.37.tar.gz
  • Upload date:
  • Size: 152.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for heaven_tree_repl-0.1.37.tar.gz
Algorithm Hash digest
SHA256 28a306cff669dd662f00ad601c1134c7c8290a4a9124d7f31da9bd4b996b5e8f
MD5 78ab177b9d36ba5a1814fafc2e292d93
BLAKE2b-256 22dd6fd6a5c0ad4d0549bcabcbd401c00d7b020588f3c73fa7caa4eee27cf2a3

See more details on using hashes here.

File details

Details for the file heaven_tree_repl-0.1.37-py3-none-any.whl.

File metadata

File hashes

Hashes for heaven_tree_repl-0.1.37-py3-none-any.whl
Algorithm Hash digest
SHA256 a697da962104700aa68a3e4e643fc7fec18d9a0c59e67e3186bd41c10e149355
MD5 0668b2210a5f1b8020d25c70e3b4cbd6
BLAKE2b-256 985b41a2e42170e30f105740e7564a0f725d5a6e76b7d529e1ec8550d39bf3ec

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page