PyPI - massgen - Versions diffs - 0.1.0a3__py3-none-any.whl → 0.1.2__py3-none-any.whl - Mend - Supply Chain Defender

massgen 0.1.0a3py3-none-any.whl → 0.1.2py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Potentially problematic release.

This version of massgen might be problematic. Click here for more details.

Files changed (120) hide show

{massgen-0.1.0a3.dist-info → massgen-0.1.2.dist-info}/METADATA RENAMED Viewed

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: massgen
-Version: 0.1.0a3
+Version: 0.1.2
 Summary: Multi-Agent Scaling System - A powerful framework for collaborative AI
 Author-email: MassGen Team <contact@massgen.dev>
 License: Apache-2.0
@@ -8,9 +8,9 @@ Project-URL: Homepage, https://github.com/Leezekun/MassGen
 Project-URL: Repository, https://github.com/Leezekun/MassGen
 Project-URL: Bug Reports, https://github.com/Leezekun/MassGen/issues
 Project-URL: Source, https://github.com/Leezekun/MassGen
-Project-URL: Documentation, https://github.com/Leezekun/MassGen/blob/main/README.md
+Project-URL: Documentation, https://docs.massgen.ai/en/latest/
 Keywords: ai,multi-agent,collaboration,orchestration,llm,claude,gemini,gpt,xai
-Classifier: Development Status :: 3 - Alpha
+Classifier: Development Status :: 4 - Beta
 Classifier: Intended Audience :: Developers
 Classifier: Intended Audience :: Science/Research
 Classifier: Operating System :: OS Independent
@@ -48,6 +48,7 @@ Requires-Dist: pillow>=11.3.0
 Requires-Dist: ag2>=0.9.10
 Requires-Dist: pyautogen>=0.10.0
 Requires-Dist: vertexai>=1.71.1
+Requires-Dist: pytest>=8.4.2
 Provides-Extra: dev
 Requires-Dist: pytest>=7.0.0; extra == "dev"
 Requires-Dist: pytest-cov>=4.0.0; extra == "dev"
@@ -92,6 +93,9 @@ Dynamic: license-file
   <a href="LICENSE">
     <img src="https://img.shields.io/badge/license-Apache%202.0-blue.svg" alt="License" style="margin-right: 5px;">
   </a>
+  <a href="https://docs.massgen.ai">
+    <img src="https://img.shields.io/badge/docs-massgen.ai-blue.svg" alt="Documentation" style="margin-right: 5px;">
+  </a>
   <a href="https://discord.massgen.ai">
     <img src="https://img.shields.io/discord/1153072414184452236?color=7289da&label=chat&logo=discord&style=flat-square" alt="Join our Discord">
   </a>
@@ -134,7 +138,7 @@ This project started with the "threads of thought" and "iterative refinement" id
 <details open>
 <summary><h3>🆕 Latest Features</h3></summary>
-- [v0.1.0 Features](#-latest-features-v010)
+- [v0.1.2 Features](#-latest-features-v012)
 </details>
 <details open>
@@ -179,15 +183,15 @@ This project started with the "threads of thought" and "iterative refinement" id
 <summary><h3>🗺️ Roadmap</h3></summary>
 - Recent Achievements
-  - [v0.1.0](#recent-achievements-v010)
-  - [v0.0.3 - v0.0.32](#previous-achievements-v003---v0032)
+  - [v0.1.2](#recent-achievements-v012)
+  - [v0.0.3 - v0.1.1](#previous-achievements-v003---v011)
 - [Key Future Enhancements](#key-future-enhancements)
   - Bug Fixes & Backend Improvements
   - Advanced Agent Collaboration
   - Expanded Model, Tool & Agent Integrations
   - Improved Performance & Scalability
   - Enhanced Developer Experience
-- [v0.1.1 Roadmap](#v011-roadmap)
+- [v0.1.3 Roadmap](#v013-roadmap)
 </details>
 <details open>
@@ -212,27 +216,36 @@ This project started with the "threads of thought" and "iterative refinement" id
 ---
-## 🆕 Latest Features (v0.1.0)
-**🎉 Released: October 17, 2025**
+## 🆕 Latest Features (v0.1.2)
-**What's New in v0.1.0:**
-- **📦 PyPI Package** - Official pip installation: `pip install massgen`
-- **📖 Comprehensive Documentation** - Full Sphinx docs at [massgen.readthedocs.io](https://massgen.readthedocs.io)
-- **🎯 Interactive Setup Wizard** - Guided configuration for first-time users
-- **🚀 Simplified Commands** - Clean `massgen` CLI with `@examples/` prefix for built-in configs
+**🎉 Released: October 22, 2025**
-**Get Started with v0.1.0:**
-```bash
-# Install from PyPI
-pip install massgen
+**What's New in v0.1.2:**
+- **🧠 Intelligent Planning Mode** - Automatic question analysis for safe MCP tool blocking
+- **🎭 Claude 4.5 Haiku Support** - Access to latest Claude Haiku model
+- **🔍 Grok Web Search Fix** - Improved web search functionality in Grok backend
-# Run the interactive setup wizard
-massgen
+**Key Improvements:**
+- Automatically determines if questions require irreversible operations
+- Read-only MCP operations allowed during coordination for better decisions
+- Write operations automatically blocked for safety
+- Zero configuration required - works transparently
+- Enhanced model support with latest Claude 4.5 Haiku
-# Start using with example configurations
-massgen --config @examples/basic/multi/three_agents_default \
-  "Analyze the pros and cons of renewable energy"
+**Get Started with v0.1.2:**
+```bash
+# Install or upgrade from PyPI
+pip install --upgrade massgen
+# Try intelligent planning mode with MCP tools
+# (Please read the YAML file for required API keys: DISCORD_TOKEN, OPENAI_API_KEY, etc.)
+massgen --config @examples/tools/planning/five_agents_discord_mcp_planning_mode \
+  "Check recent messages in our development channel, summarize the discussion, and post a helpful response about the current topic."
+# Use latest Claude 4.5 Haiku model
+# (Requires ANTHROPIC_API_KEY in .env)
+massgen --model claude-haiku-4-5-20251001 \
+  "Summarize the latest AI developments"
 ```
 → [See full release history and examples](massgen/configs/README.md#release-history--examples)
@@ -282,7 +295,7 @@ This collaborative approach ensures that the final output leverages collective i
 ---
-> 📖 **Complete Documentation:** For comprehensive guides, API reference, and detailed examples, visit **[massgen.readthedocs.io](https://massgen.readthedocs.io)**
+> 📖 **Complete Documentation:** For comprehensive guides, API reference, and detailed examples, visit **[MassGen Official Documentation](https://docs.massgen.ai/)**
 ---
@@ -321,7 +334,7 @@ massgen "Your question here"
 massgen --config @examples/basic/multi/three_agents_default "Your question"
 ```
-→ See [Installation Guide](https://massgen.readthedocs.io/en/latest/quickstart/installation.html) for complete setup instructions.
+→ See [Installation Guide](https://docs.massgen.ai/en/latest/quickstart/installation.html) for complete setup instructions.
 **Method 2: Development Installation** (for contributors):
@@ -336,7 +349,7 @@ pip install -e .
 # Or with uv (faster)
 uv pip install -e .
-# Optional: AG2 framework integration
+# Optional: External framework integration
 pip install -e ".[external]"
 ```
@@ -367,13 +380,13 @@ git clone https://github.com/Leezekun/MassGen.git
 cd MassGen
 uv tool install -e .
 # Now run from any directory
-uv tool run massgen --config @examples/basic_multi "Question"
+uv tool run massgen --config @examples/basic/multi/three_agents_default "Question"
 ```
 **Backwards compatibility (uv run):**
 ```bash
 cd /path/to/MassGen
-uv run massgen --config @examples/basic_multi "Question"
+uv run massgen --config @examples/basic/multi/three_agents_default "Question"
 uv run python -m massgen.cli --config config.yaml "Question"
 ```
@@ -411,11 +424,11 @@ OPENROUTER_API_KEY=...
 MassGen automatically loads API keys from `.env` in your current directory.
-→ **Complete setup guide with all providers:** See [API Key Configuration](https://massgen.readthedocs.io/en/latest/quickstart/installation.html#api-key-configuration) in the docs
+→ **Complete setup guide with all providers:** See [API Key Configuration](https://docs.massgen.ai/en/latest/quickstart/installation.html#api-key-configuration) in the docs
 **Get API keys:**
  - [OpenAI](https://platform.openai.com/api-keys) | [Claude](https://docs.anthropic.com/en/api/overview) | [Gemini](https://ai.google.dev/gemini-api/docs) | [Grok](https://docs.x.ai/docs/overview)
- - [Azure OpenAI](https://learn.microsoft.com/en-us/azure/ai-services/openai/) | [Cerebras](https://inference-docs.cerebras.ai/introduction) | [More providers...](https://massgen.readthedocs.io/en/latest/reference/supported_models.html)
+ - [Azure OpenAI](https://learn.microsoft.com/en-us/azure/ai-services/openai/) | [Cerebras](https://inference-docs.cerebras.ai/introduction) | [More providers...](https://docs.massgen.ai/en/latest/reference/supported_models.html)
 ### 3. 🧩 Supported Models and Tools
@@ -446,7 +459,7 @@ The system currently supports multiple model providers with advanced capabilitie
   - Zero-cost usage reporting
   - Support for LLaMA, Mistral, Qwen and other open-weight models
-→ For complete model list and configuration details, see [Supported Models](https://massgen.readthedocs.io/en/latest/reference/supported_models.html)
+→ For complete model list and configuration details, see [Supported Models](https://docs.massgen.ai/en/latest/reference/supported_models.html)
 #### Tools
@@ -466,13 +479,13 @@ MassGen agents can leverage various tools to enhance their problem-solving capab
 **Note:** Audio/video multimodal support (NEW in v0.0.30) is available through Chat Completions-based providers like OpenRouter and Qwen API. See configuration examples: [`single_openrouter_audio_understanding.yaml`](massgen/configs/basic/single/single_openrouter_audio_understanding.yaml), [`single_qwen_video_understanding.yaml`](massgen/configs/basic/single/single_qwen_video_understanding.yaml)
-→ For detailed backend capabilities and tool integration guides, see [User Guide - Backends](https://massgen.readthedocs.io/en/latest/user_guide/backends.html)
+→ For detailed backend capabilities and tool integration guides, see [User Guide - Backends](https://docs.massgen.ai/en/latest/user_guide/backends.html)
 ---
 ### 4. 🏃 Run MassGen
-> **Complete Usage Guide:** For all usage modes, advanced features, and interactive multi-turn sessions, see [Running MassGen](https://massgen.readthedocs.io/en/latest/quickstart/running-massgen.html)
+> **Complete Usage Guide:** For all usage modes, advanced features, and interactive multi-turn sessions, see [Running MassGen](https://docs.massgen.ai/en/latest/quickstart/running-massgen.html)
 #### 🚀 Getting Started
@@ -636,7 +649,7 @@ agents:
 → [View more MCP examples](massgen/configs/tools/mcp/)
-→ For comprehensive MCP integration guide, see [MCP Integration](https://massgen.readthedocs.io/en/latest/user_guide/mcp_integration.html)
+→ For comprehensive MCP integration guide, see [MCP Integration](https://docs.massgen.ai/en/latest/user_guide/mcp_integration.html)
 #### **4. File System Operations & Workspace Management**
@@ -715,7 +728,7 @@ orchestrator:
 >
 > The agents will execute file operations without additional confirmation once permissions are granted.
-→ For comprehensive file operations guide, see [File Operations](https://massgen.readthedocs.io/en/latest/user_guide/file_operations.html)
+→ For comprehensive file operations guide, see [File Operations](https://docs.massgen.ai/en/latest/user_guide/file_operations.html)
 #### **5. Project Integration & User Context Paths (NEW in v0.0.21)**
@@ -841,9 +854,7 @@ agents:
       cwd: "workspace1"                 # → .massgen/workspaces/workspace1/
 ```
-→ [Learn more about project integration](massgen/mcp_tools/permissions_and_context_files.md)
-→ For comprehensive project integration guide, see [Project Integration](https://massgen.readthedocs.io/en/latest/user_guide/project_integration.html)
+→ For comprehensive project integration guide, see [Project Integration](https://docs.massgen.ai/en/latest/user_guide/project_integration.html)
 **Security Considerations:**
 - **Agent ID Safety**: Avoid using agent+incremental digits for IDs (e.g., `agent1`, `agent2`). This may cause ID exposure during voting
@@ -865,7 +876,7 @@ massgen --config @examples/tools/mcp/claude_mcp_example \
 **OpenAI (GPT-5 Series with MCP - v0.0.17+)**
 ```bash
 # GPT-5 with weather and external tools
-massgen --config @examples/tools/mcp/gpt5_mini_mcp_example \
+massgen --config @examples/tools/mcp/gpt5_nano_mcp_example \
   "What's the weather of Tokyo"
 ```
@@ -1053,14 +1064,14 @@ All sessions are automatically logged with detailed information for debugging an
 - **Agent Outputs** (`agent_outputs/`): Complete output history and final presentations from all agents
 - **Debug Log** (`massgen.log`): Complete system operations, API calls, tool usage, and error traces (use `--debug` for verbose logging)
-→ For comprehensive logging guide and debugging techniques, see [Logging & Debugging](https://massgen.readthedocs.io/en/latest/user_guide/logging.html)
+→ For comprehensive logging guide and debugging techniques, see [Logging & Debugging](https://docs.massgen.ai/en/latest/user_guide/logging.html)
 ## 💡 Case Studies
 To see how MassGen works in practice, check out these detailed case studies based on real session logs:
 - [**MassGen Case Studies**](docs/case_studies/README.md)
-- [**Case Studies Documentation**](https://massgen.readthedocs.io/en/latest/examples/case_studies.html) - Browse case studies online
+- [**Case Studies Documentation**](https://docs.massgen.ai/en/latest/examples/case_studies.html) - Browse case studies online
 ---
@@ -1071,90 +1082,45 @@ MassGen is currently in its foundational stage, with a focus on parallel, asynch
 ⚠️ **Early Stage Notice:** As MassGen is in active development, please expect upcoming breaking architecture changes as we continue to refine and improve the system.
-### Recent Achievements (v0.1.0)
+### Recent Achievements (v0.1.2)
-**🎉 Released: October 17, 2025**
+**🎉 Released: October 22, 2025**
-#### PyPI Package Release
-- **Official Distribution**: MassGen now available via `pip install massgen`
-- **Simplified Installation**: No need to clone repository for standard usage
-- **Global Access**: Run `massgen` command from any directory after pip install
+#### Intelligent Planning Mode
+- **Automatic Question Analysis**: New `_analyze_question_irreversibility()` method in orchestrator determines if MCP operations are reversible
+- **Selective Tool Blocking**: Granular control with `set_planning_mode_blocked_tools()`, `get_planning_mode_blocked_tools()`, and `is_mcp_tool_blocked()` methods
+- **Dynamic Behavior**: Read-only MCP operations allowed during coordination, write operations blocked for safety
+- **Zero Configuration**: Works transparently without setup
+- **Multi-Workspace Support**: Planning mode works across different workspaces without conflicts
+- **Test Coverage**: Comprehensive tests in `massgen/tests/test_intelligent_planning_mode.py`
+- **Documentation**: Complete guide in `docs/case_studies/INTELLIGENT_PLANNING_MODE.md`
-#### Comprehensive Documentation
-- **Sphinx Documentation**: Full documentation site at [massgen.readthedocs.io](https://massgen.readthedocs.io)
-- **Complete User Guide**: Installation, configuration, usage modes, and API reference
-- **Case Studies**: Real-world examples with session logs and outcomes
-- **Structured Navigation**: Getting Started, User Guide, Reference, Examples, and Development sections
+#### Model Support & Improvements
+- **Claude 4.5 Haiku**: Added latest Claude Haiku model `claude-haiku-4-5-20251001`
+- **Model Priority Updates**: Reorganized Claude model list with updated defaults (`claude-sonnet-4-5-20250929`)
+- **Grok Web Search Fix**: Resolved `extra_body` parameter handling for Grok's Live Search API with new `_add_grok_search_params()` method
-#### Interactive Setup Wizard
-- **Guided Configuration**: Step-by-step wizard for first-time users
-- **Use Case Presets**: Research, Code, Q&A, Data Analysis, and more
-- **API Key Management**: Centralized configuration in `~/.config/massgen/`
-- **Smart Defaults**: Auto-configured tools based on selected use case
+#### Configuration Updates
+- **Planning Mode Configs**: Updated 5 configurations in `massgen/configs/tools/planning/` with selective blocking examples
+- **Default Configuration**: Updated `three_agents_default.yaml` with Grok-4-fast model
-#### Enhanced CLI Experience
-- **Simplified Commands**: Clean `massgen` command with intuitive syntax
-- **Built-in Examples**: `@examples/` prefix for instant access to configurations
-- **Backwards Compatibility**: Existing git clone workflows continue to work
+### Previous Achievements (v0.0.3 - v0.1.1)
-### Recent Achievements (v0.0.32)
+✅ **Custom Tools System (v0.1.1)**: User-defined Python function registration using `ToolManager` class in `massgen/tool/_manager.py`, cross-backend support alongside MCP servers, builtin/MCP/custom tool categories with automatic discovery, 40+ examples in `massgen/configs/tools/custom_tools/`, voting sensitivity controls with three-tier quality system (lenient/balanced/strict), answer novelty detection preventing duplicates
-**🎉 Released: October 15, 2025**
+✅ **Backend Enhancements (v0.1.1)**: Gemini architecture refactoring with extracted MCP management (`gemini_mcp_manager.py`), tracking (`gemini_trackers.py`), and utilities, new capabilities registry in `massgen/backend/capabilities.py` documenting feature support across backends
-#### Docker Execution Mode
-- **Container-Based Isolation**: Secure command execution in isolated Docker containers preventing host filesystem access
-- **Persistent State Management**: Packages and dependencies persist across conversation turns eliminating redundant setup
-- **Multi-Agent Support**: Each agent receives dedicated isolated container enabling safe parallel execution
-- **Configurable Security**: Resource limits (CPU, memory), network isolation modes, and read-only volume mounts
+✅ **PyPI Package Release (v0.1.0)**: Official distribution via `pip install massgen` with simplified installation, global `massgen` command accessible from any directory, comprehensive Sphinx documentation at [docs.massgen.ai](https://docs.massgen.ai/), interactive setup wizard with use case presets and API key management, enhanced CLI with `@examples/` prefix for built-in configurations
-**⚠️ Docker Setup Required:**
-To use Docker execution mode, complete these steps before running:
-1. **Docker Engine 28.0.0+** installed and running (`docker ps` should work)
-2. **Python docker library**: `uv pip install -e ".[docker]"` or `pip install docker>=7.0.0`
-3. **Build Docker image**: `bash massgen/docker/build.sh` (from repository root)
-4. **📚 Full setup guide**: See `massgen/docker/README.md` for complete instructions
+✅ **Docker Execution Mode (v0.0.32)**: Container-based isolation with secure command execution in isolated Docker containers preventing host filesystem access, persistent state management with packages and dependencies persisting across conversation turns, multi-agent support with dedicated isolated containers for each agent, configurable security with resource limits (CPU, memory), network isolation modes, and read-only volume mounts
-#### MCP Architecture Refactoring
-- **Simplified Client**: Renamed `MultiMCPClient` to `MCPClient` reflecting streamlined architecture
-- **Code Consolidation**: Removed deprecated modules and consolidated duplicate MCP protocol handling
-- **Improved Maintainability**: Standardized type hints, enhanced error handling, cleaner code organization
+✅ **MCP Architecture Refactoring (v0.0.32)**: Simplified client with renamed `MultiMCPClient` to `MCPClient` reflecting streamlined architecture, code consolidation by removing deprecated modules and consolidating duplicate MCP protocol handling, improved maintainability with standardized type hints, enhanced error handling, and cleaner code organization
-#### Claude Code Docker Integration
-- **Automatic Tool Management**: Bash tool automatically disabled in Docker mode routing commands through execute_command
-- **MCP Auto-Permissions**: Automatic approval for MCP tools while preserving security validation
-- **Enhanced Guidance**: System messages prevent git repository confusion between host and container environments
+✅ **Claude Code Docker Integration (v0.0.32)**: Automatic tool management with Bash tool automatically disabled in Docker mode routing commands through execute_command, MCP auto-permissions with automatic approval for MCP tools while preserving security validation, enhanced guidance with system messages preventing git repository confusion between host and container environments
-#### Configuration and Testing
-- **Docker Documentation**: `massgen/docker/README.md` with setup guide and build scripts
-- **Example Configurations**: `docker_simple.yaml`, `docker_multi_agent.yaml`, `docker_with_resource_limits.yaml`, `docker_claude_code.yaml`, `docker_verification.yaml`
-- **Testing**: Comprehensive test suite validating Docker and local execution modes
+✅ **Universal Command Execution (v0.0.31)**: MCP-based execute_command tool works across Claude, Gemini, OpenAI, and Chat Completions providers, comprehensive security with permission management and command filtering, code execution in planning mode for safer coordination
-### Recent Achievements (v0.0.31)
-**🎉 Released: October 13, 2025**
-#### Universal Code Execution
-- **MCP-Based Tool**: New `execute_command` tool works across Claude, Gemini, OpenAI, and Chat Completions backends
-- **AG2-Inspired Security**: Permission management and command filtering (whitelist/blacklist patterns)
-- **Planning Mode Support**: Code execution in planning mode for safer coordination
-#### AG2 Group Chat Integration
-- **Multi-Agent Conversations**: Native support using AG2's GroupChat and GroupChatManager frameworks
-- **Smart Speaker Selection**: Automatic, round-robin, or manual selection powered by LLMs
-- **Enhanced Adapter**: AG2 adapter supporting native group chat coordination
-#### Audio & Video Generation
-- **Audio Tools**: Text-to-speech and transcription capabilities
-- **Video Generation**: Integration with OpenAI's Sora-2 API for video creation
-- **Multimodal Expansion**: Extended capabilities beyond text and images
-### Previous Achievements (v0.0.3 - v0.0.32)
-<div style="max-height: 600px; overflow-y: auto; transition: max-height 0.3s ease;">
-✅ **Universal Command Execution (v0.0.31)**: MCP-based execute_command tool works across Claude, Gemini, OpenAI, and Chat Completions providers, AG2-inspired security with permission management and command filtering, code execution in planning mode for safer coordination
-✅ **AG2 Group Chat Integration (v0.0.31)**: Multi-agent conversations using AG2's GroupChat and GroupChatManager frameworks, smart speaker selection (automatic, round-robin, manual) powered by LLMs, enhanced AG2 adapter supporting native group chat coordination
+✅ **External Framework Integration (v0.0.31)**: Multi-agent conversations using external framework group chat patterns, smart speaker selection (automatic, round-robin, manual) powered by LLMs, enhanced adapter supporting native group chat coordination
 ✅ **Audio & Video Generation (v0.0.31)**: Audio tools for text-to-speech and transcription, video generation using OpenAI's Sora-2 API, multimodal expansion beyond text and images
@@ -1168,7 +1134,7 @@ To use Docker execution mode, complete these steps before running:
 ✅ **File Operation Safety (v0.0.29)**: Read-before-delete enforcement with `FileOperationTracker` class, `PathPermissionManager` integration with operation tracking methods, enhanced file operation safety mechanisms
-✅ **AG2 Framework Integration (v0.0.28)**: Adapter system for external agent frameworks, AG2 ConversableAgent and AssistantAgent support with async execution, code execution in multiple environments (Local, Docker, Jupyter, YepCode), 4 ready-to-use AG2 configurations
+✅ **External Framework Integration (v0.0.28)**: Adapter system for external agent frameworks with async execution, code execution in multiple environments (Local, Docker, Jupyter, YepCode), ready-to-use configurations for framework integration
 ✅ **Multimodal Support - Image Processing (v0.0.27)**: New `stream_chunk` module for multimodal content, image generation and understanding capabilities, file upload and search for document Q&A, Claude Sonnet 4.5 support, enhanced workspace multimodal tools
@@ -1232,8 +1198,6 @@ To use Docker execution mode, complete these steps before running:
 ✅ **Extended Provider Ecosystem**: Support for 15+ providers including Cerebras AI, Together AI, Fireworks AI, Groq, Nebius AI Studio, and OpenRouter
-</div>
 ### Key Future Enhancements
 -   **Bug Fixes & Backend Improvements:** Fixing image generation path issues and adding Claude multimodal support
@@ -1244,25 +1208,19 @@ To use Docker execution mode, complete these steps before running:
 We welcome community contributions to achieve these goals.
-### v0.1.1 Roadmap
+### v0.1.3 Roadmap
-Version 0.1.1 focuses on developer experience improvements and PyPI distribution:
+Version 0.1.3 focuses on general interoperability and enterprise collaboration:
 #### Required Features
-- **Configuration Builder CLI**: Interactive command-line tool for generating and validating MassGen configurations
-- **PyPI Package Release v0.1.0**: Official PyPI package representing new usage paradigm with easy pip installation
-#### Optional Features
-- **Nested Chat Integration**: Complete AG2 nested chat pattern support for hierarchical agent conversations
-- **DSPy Integration**: Framework integration for prompt optimization and systematic agent improvement
+- **General Interoperability**: Enable MassGen to orchestrate agents from multiple external frameworks with unified interface
+- **Final Agent Submit/Restart Tools**: Enable final agent to decide whether to submit or restart orchestration
 Key technical approach:
-- **Config Builder**: Interactive prompts, configuration templates, validation and error checking, preset support
-- **PyPI Package**: Production-ready distribution with proper dependencies, documentation, and migration guide
-- **Nested Chat**: AG2 integration for hierarchical conversations with parent-child agent relationships
-- **DSPy**: Prompt optimization, performance tuning, and systematic agent improvement workflows
+- **Framework Integration**: Multi-agent coordination supporting external agent frameworks with specialized agent roles (researcher, analyst, critic, synthesizer)
+- **Submit/Restart**: Multi-step task verification with access to previous agents' responses and workspaces
-For detailed milestones and technical specifications, see the [full v0.1.1 roadmap](ROADMAP.md).
+For detailed milestones and technical specifications, see the [full v0.1.3 roadmap](ROADMAP.md).
 ---