massgen 0.1.1__tar.gz → 0.1.2__tar.gz

{massgen-0.1.1 → massgen-0.1.2}/CHANGELOG.md

@@ -7,17 +7,63 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## Recent Releases
 
+**v0.1.2 (October 2025)** - Intelligent Planning Mode & Model Updates
+Automatic irreversibility analysis for MCP tools, selective tool blocking, Claude 4.5 Haiku support, and Grok web search improvements.
+
 **v0.1.1 (October 2025)** - Custom Tools, Voting Controls & Documentation
 Custom Python function tools, voting sensitivity controls, interactive config builder, and comprehensive Sphinx documentation.
 
 **v0.1.0 (October 2025)** - PyPI Package & Documentation
 Official PyPI release with enhanced documentation and installation via `pip install massgen`.
 
-**v0.0.32 (October 2025)** - Docker Execution Mode
-Isolated command execution in Docker containers with resource limits and multi-agent support.
-
 ---
 
+## [0.1.2] - 2025-10-22
+
+### Added
+- **Claude 4.5 Haiku Support**: Added latest Claude Haiku model
+  - New model: `claude-haiku-4-5-20251001`
+  - Updated model registry in `backend/capabilities.py`
+
+### Changed
+- **Planning Mode Enhancement**: Intelligent automatic MCP tool blocking based on operation safety
+  - New `_analyze_question_irreversibility()` method in orchestrator analyzes questions to determine if MCP operations are reversible
+  - New `set_planning_mode_blocked_tools()`, `get_planning_mode_blocked_tools()`, and `is_mcp_tool_blocked()` methods in backend for selective tool control
+  - Dynamically enables/disables planning mode - read-only operations allowed during coordination, write operations blocked
+  - Planning mode supports different workspaces without conflicts
+  - Zero configuration required - works transparently
+
+
+- **Claude Model Priority**: Reorganized model list in capabilities registry
+  - Changed default model from `claude-sonnet-4-20250514` to `claude-sonnet-4-5-20250929`
+  - Moved `claude-opus-4-1-20250805` higher in priority order
+  - Updated in both Claude and Claude Code backends
+
+### Fixed
+- **Grok Web Search**: Resolved web search functionality in Grok backend
+  - Fixed `extra_body` parameter handling for Grok's Live Search API
+  - New `_add_grok_search_params()` method for proper search parameter injection
+  - Enhanced `_stream_with_custom_and_mcp_tools()` to support Grok-specific parameters
+  - Improved error handling for conflicting search configurations
+  - Better integration with Chat Completions API params handler
+
+### Documentations, Configurations and Resources
+
+- **Intelligent Planning Mode Case Study**: Complete feature documentation
+  - `docs/case_studies/INTELLIGENT_PLANNING_MODE.md`: Comprehensive guide for automatic planning mode
+  - Demonstrates automatic irreversibility detection
+  - Shows read/write operation classification
+  - Includes examples for Discord, filesystem, and Twitter operations
+
+- **Configuration Updates**: Enhanced YAML examples
+  - Updated 5 planning mode configurations in `configs/tools/planning/` with selective blocking examples
+  - Updated `three_agents_default.yaml` with Grok-4-fast model
+  - Test coverage in `test_intelligent_planning_mode.py`
+
+### Technical Details
+- **Major Focus**: Intelligent planning mode with selective tool blocking, model support enhancements
+- **Contributors**: @franklinnwren @ncrispino @qidanrui @sonichi @Henry-811 and the MassGen team
+
 ## [0.1.1] - 2025-10-20
 
 ### Added

{massgen-0.1.1 → massgen-0.1.2}/CONTRIBUTING.md

@@ -267,7 +267,7 @@ Create a `.env` file in the `massgen` directory as described in [README](README.
 
 ## 🔧 Development Workflow
 
-> **Important**: Our next version is v0.1.2. If you want to contribute, please contribute to the `dev/v0.1.2` branch.
+> **Important**: Our next version is v0.1.3. If you want to contribute, please contribute to the `dev/v0.1.3` branch.
 
 ### 1. Create Feature Branch
 
@@ -275,8 +275,8 @@ Create a `.env` file in the `massgen` directory as described in [README](README.
 # Fetch latest changes from upstream
 git fetch upstream
 
-# Create feature branch from dev/v0.1.2
-git checkout -b feature/your-feature-name upstream/dev/v0.1.2
+# Create feature branch from dev/v0.1.3
+git checkout -b feature/your-feature-name upstream/dev/v0.1.3
 ```
 
 ### 2. Make Your Changes
@@ -479,7 +479,7 @@ Have a significant feature idea not covered by existing tracks?
 - [ ] Tests pass locally
 - [ ] Documentation is updated if needed
 - [ ] Commit messages follow convention
-- [ ] PR targets `dev/v0.1.2` branch
+- [ ] PR targets `dev/v0.1.3` branch
 
 ### PR Description Should Include
 

{massgen-0.1.1 → massgen-0.1.2}/MANIFEST.in

@@ -5,6 +5,7 @@ include CHANGELOG.md
 include requirements.txt
 recursive-include massgen/configs *.yaml *.yml
 include .env.example
+recursive-include assets *.png *.gif *.jpg *.jpeg *.ico
 recursive-exclude * __pycache__
 recursive-exclude * *.py[co]
 exclude .gitignore

{massgen-0.1.1 → massgen-0.1.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: massgen
-Version: 0.1.1
+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
@@ -83,7 +83,7 @@ Provides-Extra: all
 Dynamic: license-file
 
 <p align="center">
-  <img src="https://raw.githubusercontent.com/Leezekun/MassGen/main/assets/logo.png" alt="MassGen Logo" width="360" />
+  <img src="assets/logo.png" alt="MassGen Logo" width="360" />
 </p>
 
 <p align="center">
@@ -109,7 +109,7 @@ Dynamic: license-file
 
 <p align="center">
   <a href="https://www.youtube.com/watch?v=Dp2oldJJImw">
-    <img src="https://raw.githubusercontent.com/Leezekun/MassGen/main/assets/massgen-demo.gif" alt="MassGen case study -- Berkeley Agentic AI Summit Question" width="800">
+    <img src="assets/massgen-demo.gif" alt="MassGen case study -- Berkeley Agentic AI Summit Question" width="800">
   </a>
 </p>
 
@@ -138,7 +138,7 @@ This project started with the "threads of thought" and "iterative refinement" id
 <details open>
 <summary><h3>🆕 Latest Features</h3></summary>
 
-- [v0.1.1 Features](#-latest-features-v011)
+- [v0.1.2 Features](#-latest-features-v012)
 </details>
 
 <details open>
@@ -183,15 +183,15 @@ This project started with the "threads of thought" and "iterative refinement" id
 <summary><h3>🗺️ Roadmap</h3></summary>
 
 - Recent Achievements
-  - [v0.1.1](#recent-achievements-v011)
-  - [v0.0.3 - v0.1.0](#previous-achievements-v003---v010)
+  - [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
-- [v0.1.2 Roadmap](#v012-roadmap)
+- [v0.1.3 Roadmap](#v013-roadmap)
 </details>
 
 <details open>
@@ -216,36 +216,36 @@ This project started with the "threads of thought" and "iterative refinement" id
 
 ---
 
-## 🆕 Latest Features (v0.1.1)
+## 🆕 Latest Features (v0.1.2)
 
-**🎉 Released: October 20, 2025**
+**🎉 Released: October 22, 2025**
 
-**What's New in v0.1.1:**
-- **🔧 Custom Tools System** - Register your own Python functions as tools
-- **⚖️ Voting Sensitivity Controls** - Three-tier quality control for multi-agent consensus
-- **🎯 Configuration Builder** - Interactive wizard to create custom configs
-- **📊 Backend Capabilities Registry** - Centralized feature support tracking
-- **🔬 Self-Evolution Capability** - Agents autonomously analyze GitHub issues and market trends for feature prioritization
+**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
 
-[![MassGen v0.1.1 Custom Tools & Voting Demo](https://img.youtube.com/vi/eXK_oF177zY/0.jpg)](https://youtu.be/eXK_oF177zY)
+**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
 
-*Watch the v0.1.1 demo showcasing custom Python tool registration and three-tier voting sensitivity controls for multi-agent quality assurance*
-
-**Get Started with v0.1.1:**
+**Get Started with v0.1.2:**
 ```bash
 # Install or upgrade from PyPI
 pip install --upgrade massgen
 
-# Create a configuration with the interactive builder
-massgen --setup
-
-# Try custom tools with agents
-massgen --config @examples/tools/custom_tools/claude_custom_tool_example \
-  "What's the sum of 123 and 456?"
+# 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 voting sensitivity controls for quality assurance
-massgen --config @examples/voting/gemini_gpt_voting_sensitivity \
-  "What are the pros and cons of renewable energy?"
+# 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)
@@ -1082,31 +1082,33 @@ 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 (v0.1.1)
+### Recent Achievements (v0.1.2)
+
+**🎉 Released: October 22, 2025**
+
+#### 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`
 
-**🎉 Released: October 20, 2025**
+#### 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
 
-#### Custom Tools System
-- **User-Defined Functions**: Register Python functions as tools using `ToolManager` class in `massgen/tool/_manager.py`
-- **Cross-Backend Support**: Works alongside MCP servers across all backends (Claude, Gemini, OpenAI, Chat Completions, Claude Code)
-- **Tool Categories**: Builtin, MCP, and custom tools with automatic discovery and conflict resolution
-- **40+ Examples**: Ready-to-use configurations in `massgen/configs/tools/custom_tools/`
+#### 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
 
-#### Voting Sensitivity & Answer Quality Controls
-- **Three-Tier System**: "lenient", "balanced", "strict" voting modes
-- **Answer Novelty Detection**: Prevents duplicate submissions with configurable similarity thresholds
-- **Quality Assurance**: Configurable `max_new_answers_per_agent` and token-based overlap detection
-- **Configuration**: `massgen/configs/voting/gemini_gpt_voting_sensitivity.yaml`
+### Previous Achievements (v0.0.3 - v0.1.1)
 
-#### Backend & Documentation Enhancements
-- **Gemini Refactoring**: Extracted MCP management (`gemini_mcp_manager.py`), tracking (`gemini_trackers.py`), and utilities
-- **Capabilities Registry**: New `massgen/backend/capabilities.py` documenting feature support across backends
-- **Documentation Updates**: Enhanced custom tools guide, reorganized case studies, updated configuration schema
-- **Case Studies**:
-  - `docs/case_studies/github-issue-market-analysis.md` - Custom tools with GitHub issue market analysis (v0.1.1)
-  - `docs/case_studies/universal-code-execution-mcp.md` - MCP code execution across backends (v0.0.31)
+✅ **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
 
-### Previous Achievements (v0.0.3 - v0.1.0)
+✅ **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
 
 ✅ **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
 
@@ -1206,21 +1208,19 @@ MassGen is currently in its foundational stage, with a focus on parallel, asynch
 
 We welcome community contributions to achieve these goals.
 
-### v0.1.2 Roadmap
+### v0.1.3 Roadmap
 
-Version 0.1.2 focuses on enterprise collaboration and intelligent agent workflows:
+Version 0.1.3 focuses on general interoperability and enterprise collaboration:
 
 #### Required Features
 - **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
-- **Memory Module - Phase 1**: Long-term memory implementation using mem0 for reasoning and document understanding
 
 Key technical approach:
 - **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
-- **Memory Module**: Session-based memory management with persistent context across conversations
 
-For detailed milestones and technical specifications, see the [full v0.1.2 roadmap](ROADMAP.md).
+For detailed milestones and technical specifications, see the [full v0.1.3 roadmap](ROADMAP.md).
 
 ---
 

{massgen-0.1.1 → massgen-0.1.2}/README.md

@@ -1,5 +1,5 @@
 <p align="center">
-  <img src="https://raw.githubusercontent.com/Leezekun/MassGen/main/assets/logo.png" alt="MassGen Logo" width="360" />
+  <img src="assets/logo.png" alt="MassGen Logo" width="360" />
 </p>
 
 <p align="center">
@@ -25,7 +25,7 @@
 
 <p align="center">
   <a href="https://www.youtube.com/watch?v=Dp2oldJJImw">
-    <img src="https://raw.githubusercontent.com/Leezekun/MassGen/main/assets/massgen-demo.gif" alt="MassGen case study -- Berkeley Agentic AI Summit Question" width="800">
+    <img src="assets/massgen-demo.gif" alt="MassGen case study -- Berkeley Agentic AI Summit Question" width="800">
   </a>
 </p>
 
@@ -54,7 +54,7 @@ This project started with the "threads of thought" and "iterative refinement" id
 <details open>
 <summary><h3>🆕 Latest Features</h3></summary>
 
-- [v0.1.1 Features](#-latest-features-v011)
+- [v0.1.2 Features](#-latest-features-v012)
 </details>
 
 <details open>
@@ -99,15 +99,15 @@ This project started with the "threads of thought" and "iterative refinement" id
 <summary><h3>🗺️ Roadmap</h3></summary>
 
 - Recent Achievements
-  - [v0.1.1](#recent-achievements-v011)
-  - [v0.0.3 - v0.1.0](#previous-achievements-v003---v010)
+  - [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
-- [v0.1.2 Roadmap](#v012-roadmap)
+- [v0.1.3 Roadmap](#v013-roadmap)
 </details>
 
 <details open>
@@ -132,36 +132,36 @@ This project started with the "threads of thought" and "iterative refinement" id
 
 ---
 
-## 🆕 Latest Features (v0.1.1)
+## 🆕 Latest Features (v0.1.2)
 
-**🎉 Released: October 20, 2025**
+**🎉 Released: October 22, 2025**
 
-**What's New in v0.1.1:**
-- **🔧 Custom Tools System** - Register your own Python functions as tools
-- **⚖️ Voting Sensitivity Controls** - Three-tier quality control for multi-agent consensus
-- **🎯 Configuration Builder** - Interactive wizard to create custom configs
-- **📊 Backend Capabilities Registry** - Centralized feature support tracking
-- **🔬 Self-Evolution Capability** - Agents autonomously analyze GitHub issues and market trends for feature prioritization
+**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
 
-[![MassGen v0.1.1 Custom Tools & Voting Demo](https://img.youtube.com/vi/eXK_oF177zY/0.jpg)](https://youtu.be/eXK_oF177zY)
+**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
 
-*Watch the v0.1.1 demo showcasing custom Python tool registration and three-tier voting sensitivity controls for multi-agent quality assurance*
-
-**Get Started with v0.1.1:**
+**Get Started with v0.1.2:**
 ```bash
 # Install or upgrade from PyPI
 pip install --upgrade massgen
 
-# Create a configuration with the interactive builder
-massgen --setup
-
-# Try custom tools with agents
-massgen --config @examples/tools/custom_tools/claude_custom_tool_example \
-  "What's the sum of 123 and 456?"
+# 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 voting sensitivity controls for quality assurance
-massgen --config @examples/voting/gemini_gpt_voting_sensitivity \
-  "What are the pros and cons of renewable energy?"
+# 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)
@@ -998,31 +998,33 @@ 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 (v0.1.1)
+### Recent Achievements (v0.1.2)
+
+**🎉 Released: October 22, 2025**
+
+#### 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`
 
-**🎉 Released: October 20, 2025**
+#### 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
 
-#### Custom Tools System
-- **User-Defined Functions**: Register Python functions as tools using `ToolManager` class in `massgen/tool/_manager.py`
-- **Cross-Backend Support**: Works alongside MCP servers across all backends (Claude, Gemini, OpenAI, Chat Completions, Claude Code)
-- **Tool Categories**: Builtin, MCP, and custom tools with automatic discovery and conflict resolution
-- **40+ Examples**: Ready-to-use configurations in `massgen/configs/tools/custom_tools/`
+#### 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
 
-#### Voting Sensitivity & Answer Quality Controls
-- **Three-Tier System**: "lenient", "balanced", "strict" voting modes
-- **Answer Novelty Detection**: Prevents duplicate submissions with configurable similarity thresholds
-- **Quality Assurance**: Configurable `max_new_answers_per_agent` and token-based overlap detection
-- **Configuration**: `massgen/configs/voting/gemini_gpt_voting_sensitivity.yaml`
+### Previous Achievements (v0.0.3 - v0.1.1)
 
-#### Backend & Documentation Enhancements
-- **Gemini Refactoring**: Extracted MCP management (`gemini_mcp_manager.py`), tracking (`gemini_trackers.py`), and utilities
-- **Capabilities Registry**: New `massgen/backend/capabilities.py` documenting feature support across backends
-- **Documentation Updates**: Enhanced custom tools guide, reorganized case studies, updated configuration schema
-- **Case Studies**:
-  - `docs/case_studies/github-issue-market-analysis.md` - Custom tools with GitHub issue market analysis (v0.1.1)
-  - `docs/case_studies/universal-code-execution-mcp.md` - MCP code execution across backends (v0.0.31)
+✅ **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
 
-### Previous Achievements (v0.0.3 - v0.1.0)
+✅ **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
 
 ✅ **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
 
@@ -1122,21 +1124,19 @@ MassGen is currently in its foundational stage, with a focus on parallel, asynch
 
 We welcome community contributions to achieve these goals.
 
-### v0.1.2 Roadmap
+### v0.1.3 Roadmap
 
-Version 0.1.2 focuses on enterprise collaboration and intelligent agent workflows:
+Version 0.1.3 focuses on general interoperability and enterprise collaboration:
 
 #### Required Features
 - **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
-- **Memory Module - Phase 1**: Long-term memory implementation using mem0 for reasoning and document understanding
 
 Key technical approach:
 - **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
-- **Memory Module**: Session-based memory management with persistent context across conversations
 
-For detailed milestones and technical specifications, see the [full v0.1.2 roadmap](ROADMAP.md).
+For detailed milestones and technical specifications, see the [full v0.1.3 roadmap](ROADMAP.md).
 
 ---
 

{massgen-0.1.1 → massgen-0.1.2}/massgen/__init__.py

@@ -68,7 +68,7 @@ from .chat_agent import (
 from .message_templates import MessageTemplates, get_templates
 from .orchestrator import Orchestrator, create_orchestrator
 
-__version__ = "0.1.1"
+__version__ = "0.1.2"
 __author__ = "MassGen Contributors"
 
 

{massgen-0.1.1 → massgen-0.1.2}/massgen/api_params_handler/_chat_completions_api_params_handler.py

@@ -31,7 +31,13 @@ class ChatCompletionsAPIParamsHandler(APIParamsHandlerBase):
         """Get provider tools for Chat Completions format."""
         provider_tools = []
 
-        if all_params.get("enable_web_search", False):
+        # Check if this is Grok backend - Grok uses extra_body.search_parameters instead of function tools
+        backend_provider = getattr(self.backend, "get_provider_name", lambda: "")()
+        is_grok = backend_provider.lower() == "grok"
+
+        # Add web_search function tool for non-Grok backends
+        # Grok handles web search via extra_body.search_parameters (set in grok.py)
+        if all_params.get("enable_web_search", False) and not is_grok:
             provider_tools.append(
                 {
                     "type": "function",

{massgen-0.1.1 → massgen-0.1.2}/massgen/backend/base.py

@@ -70,6 +70,11 @@ class LLMBackend(ABC):
         # Planning mode flag - when True, MCP tools should be blocked during coordination
         self._planning_mode_enabled: bool = False
 
+        # Selective tool blocking - list of specific MCP tools to block during planning mode
+        # When planning_mode is enabled, only these specific tools are blocked
+        # If empty, ALL MCP tools are blocked (backward compatible behavior)
+        self._planning_mode_blocked_tools: set = set()
+
         self.token_calculator = TokenCostCalculator()
 
         # Filesystem manager integration
@@ -465,6 +470,53 @@ class LLMBackend(ABC):
         """
         return self._planning_mode_enabled
 
+    def set_planning_mode_blocked_tools(self, tool_names: set) -> None:
+        """
+        Set specific MCP tools to block during planning mode.
+
+        This enables selective tool blocking - only the specified tools will be blocked
+        when planning mode is enabled, allowing other MCP tools to be used.
+
+        Args:
+            tool_names: Set of MCP tool names to block (e.g., {'mcp__discord__discord_send'})
+                       If empty set, ALL MCP tools are blocked (backward compatible)
+        """
+        self._planning_mode_blocked_tools = set(tool_names)
+
+    def get_planning_mode_blocked_tools(self) -> set:
+        """
+        Get the set of MCP tools currently blocked in planning mode.
+
+        Returns:
+            Set of blocked MCP tool names. Empty set means ALL MCP tools are blocked.
+        """
+        return self._planning_mode_blocked_tools.copy()
+
+    def is_mcp_tool_blocked(self, tool_name: str) -> bool:
+        """
+        Check if a specific MCP tool is blocked in planning mode.
+
+        Args:
+            tool_name: Name of the MCP tool to check (e.g., 'mcp__discord__discord_send')
+
+        Returns:
+            True if the tool should be blocked, False otherwise
+
+        Note:
+            - If planning mode is disabled, returns False (no blocking)
+            - If planning mode is enabled and blocked_tools is empty, returns True (block ALL)
+            - If planning mode is enabled and blocked_tools is set, returns True only if tool is in the set
+        """
+        if not self._planning_mode_enabled:
+            return False
+
+        # Empty set means block ALL MCP tools (backward compatible behavior)
+        if not self._planning_mode_blocked_tools:
+            return True
+
+        # Otherwise, block only if tool is in the blocked set
+        return tool_name in self._planning_mode_blocked_tools
+
     async def _cleanup_client(self, client: Any) -> None:
         """Clean up OpenAI client resources."""
         try:

{massgen-0.1.1 → massgen-0.1.2}/massgen/backend/base_with_custom_tool_and_mcp.py

@@ -533,10 +533,10 @@ class CustomToolAndMCPBackend(LLMBackend):
         max_retries: int = 3,
     ) -> Tuple[str, Any]:
         """Execute MCP function with exponential backoff retry logic."""
-        # Check if planning mode is enabled - block MCP tool execution during planning
-        if self.is_planning_mode_enabled():
-            logger.info(f"[MCP] Planning mode enabled - blocking MCP tool execution: {function_name}")
-            error_str = "🚫 [MCP] Planning mode active - MCP tools blocked during coordination"
+        # Check if this specific MCP tool is blocked by planning mode
+        if self.is_mcp_tool_blocked(function_name):
+            logger.info(f"[MCP] Planning mode enabled - blocking MCP tool: {function_name}")
+            error_str = f"🚫 [MCP] Tool '{function_name}' blocked during coordination (planning mode active)"
             return error_str, {"error": error_str, "blocked_by": "planning_mode", "function_name": function_name}
 
         # Convert JSON string to dict for shared utility