massgen 0.1.5__tar.gz → 0.1.6__tar.gz

{massgen-0.1.5 → massgen-0.1.6}/CHANGELOG.md

@@ -7,17 +7,80 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## Recent Releases
 
+**v0.1.6 (November 2025)** - Framework Interoperability & Backend Refactoring
+External agent framework integration as tools (AG2, LangGraph, AgentScope, OpenAI Assistants, SmoLAgent), unified tool execution architecture, Gemini backend simplification, and comprehensive configuration validation.
+
 **v0.1.5 (October 2025)** - Memory System
 Long-term memory with semantic retrieval via mem0, automatic context compression, and memory sharing for multi-turn conversations.
 
 **v0.1.4 (October 2025)** - Multimodal Generation Tools & Binary File Protection
 Comprehensive generation tools for images, videos, audio, and documents with OpenAI APIs, binary file blocking for security, web crawling integration, and enhanced documentation infrastructure.
 
-**v0.1.3 (October 2025)** - Post-Evaluation Tools & Multimodal Understanding
-Post-evaluation workflow with submit/restart capabilities, custom multimodal understanding tools, Docker sudo mode, and enhanced config builder.
-
 ---
 
+## [0.1.6] - 2025-10-31
+
+### Added
+- **Framework Interoperability**: External agent framework integration as MassGen custom tools
+  - New `massgen/tool/_extraframework_agents/` module with 5 framework integrations
+  - **AG2 Lesson Planner Tool**: Nested chat functionality wrapped as custom tool for multi-agent lesson planning (supports streaming)
+  - **LangGraph Lesson Planner Tool**: LangGraph graph-based workflows integrated as tool
+  - **AgentScope Lesson Planner Tool**: AgentScope agent system wrapped for lesson creation
+  - **OpenAI Assistants Lesson Planner Tool**: OpenAI Assistants API integrated as tool
+  - **SmoLAgent Lesson Planner Tool**: HuggingFace SmoLAgent integration for lesson planning
+  - Enables MassGen agents to delegate tasks to specialized external frameworks
+  - Each framework runs autonomously and returns results to MassGen orchestrator
+  - Note: Only AG2 currently supports streaming; other frameworks return complete results
+
+- **Configuration Validator**: Comprehensive YAML configuration validation system
+  - New `ConfigValidator` class in `massgen/config_validator.py` for pre-flight validation
+  - Memory configuration validation with detailed error messages
+  - Pre-commit hook integration for automatic config validation
+  - Comprehensive test suite in `massgen/tests/test_config_validator.py`
+  - Validates agent configurations, backend parameters, tool settings, and memory options
+  - Provides actionable error messages with suggestions for common mistakes
+
+### Changed
+- **Backend Architecture Refactoring**: Unified tool execution with ToolExecutionConfig
+  - New `ToolExecutionConfig` dataclass in `base_with_custom_tool_and_mcp.py` for standardized tool handling
+  - Refactored `ResponseBackend` with unified tool execution flow
+  - Refactored `ChatCompletionsBackend` with unified tool execution flow
+  - Refactored `ClaudeBackend` with unified tool execution methods
+  - Eliminates duplicate code paths between custom tools and MCP tools
+  - Consistent error handling and status reporting across all tool types
+  - Improved maintainability and extensibility for future tool systems
+
+- **Gemini Backend Simplification**: Major architectural cleanup and consolidation
+  - Removed `gemini_mcp_manager.py` module
+  - Removed `gemini_trackers.py` module
+  - Refactored `gemini.py` to use manual tool execution via base class
+  - Streamlined tool handling and cleanup logic
+  - Removed continuation logic and duplicate code
+  - Updated `_gemini_formatter.py` for simplified tool conversion
+  - Net reduction of 1,598 lines through consolidation
+  - Improved maintainability and performance
+
+- **Custom Tool System Enhancement**: Improved tool management and execution
+  - Enhanced `ToolManager` with category management capabilities
+  - Improved tool registration and validation system
+  - Enhanced tool result handling and error reporting
+  - Better support for async tool execution
+  - Improved tool schema generation for LLM consumption
+
+### Documentations, Configurations and Resources
+
+- **Framework Interoperability Examples**: 8 new configuration files demonstrating external framework integration
+  - **AG2 Examples**: `ag2_lesson_planner_example.yaml`, `ag2_and_langgraph_lesson_planner.yaml`, `ag2_and_openai_assistant_lesson_planner.yaml`
+  - **LangGraph Examples**: `langgraph_lesson_planner_example.yaml`
+  - **AgentScope Examples**: `agentscope_lesson_planner_example.yaml`
+  - **OpenAI Assistants Examples**: `openai_assistant_lesson_planner_example.yaml`
+  - **SmoLAgent Examples**: `smolagent_lesson_planner_example.yaml`
+  - **Multi-Framework Examples**: `two_models_with_tools_example.yaml`
+
+### Technical Details
+- **Major Focus**: Framework interoperability for external agent integration, unified tool execution architecture, Gemini backend simplification, and configuration validation system
+- **Contributors**: @Eric-Shang @praneeth999 @ncrispino @qidanrui @sonichi @Henry-811 and the MassGen team
+
 ## [0.1.5] - 2025-10-29
 
 ### Added

{massgen-0.1.5 → massgen-0.1.6}/CONTRIBUTING.md

@@ -95,9 +95,85 @@ To add support for a new model provider:
 2. Inherit from the base backend class in `massgen/backend/base.py`
 3. Implement the required methods for message processing and completion parsing
 4. Add the model mapping in `massgen/utils.py`
-5. Update configuration templates in `massgen/configs/`
-6. Add tests in `massgen/tests/`
-7. Update documentation
+5. **Add backend capabilities to `massgen/backend/capabilities.py`** - Required for config validation
+6. Update configuration templates in `massgen/configs/`
+7. Add tests in `massgen/tests/`
+8. **Update the config validator** - See [Updating the Config Validator](#updating-the-config-validator) below
+9. Update documentation
+
+### Updating the Config Validator
+
+**⚠️ IMPORTANT**: Whenever you add new configuration options, backends, or change the config schema, you MUST update the config validator.
+
+The config validator (`massgen/config_validator.py`) ensures users get helpful error messages when they make configuration mistakes. When you add a new feature:
+
+**1. Add to Backend Capabilities** (for new backends)
+```python
+# In massgen/backend/capabilities.py
+BACKEND_CAPABILITIES = {
+    # ...
+    "your_backend": BackendCapabilities(
+        backend_type="your_backend",
+        provider_name="Your Backend Name",
+        supported_capabilities={"mcp", "web_search", ...},
+        builtin_tools=[...],
+        filesystem_support="mcp",
+        models=["model-1", "model-2"],
+        default_model="model-1",
+        env_var="YOUR_API_KEY",
+        notes="Description of your backend",
+    ),
+}
+```
+
+**2. Update Validator Enums** (for new config options)
+```python
+# In massgen/config_validator.py
+# If adding new valid values for existing fields:
+VALID_PERMISSION_MODES = {"default", "acceptEdits", "bypassPermissions", "plan"}
+VALID_DISPLAY_TYPES = {"rich_terminal", "simple"}
+```
+
+**3. Add Validation Logic** (for new config fields)
+```python
+# In massgen/config_validator.py
+# Add validation in the appropriate _validate_* method
+def _validate_your_feature(self, config, result):
+    if "your_field" in config:
+        # Validate type
+        # Validate values
+        # Add helpful error messages
+```
+
+**4. Add Tests for Common Mistakes**
+```python
+# In massgen/tests/test_config_validator.py
+def test_invalid_your_feature(self):
+    """Test invalid your_feature value."""
+    config = {
+        "your_field": "invalid_value",
+        # ...
+    }
+    validator = ConfigValidator()
+    result = validator.validate_config(config)
+    assert not result.is_valid()
+    assert any("your helpful error message" in error.message for error in result.errors)
+```
+
+**5. Test Validation**
+```bash
+# Validate all example configs still pass
+uv run python scripts/validate_all_configs.py
+
+# Run validator tests
+uv run pytest massgen/tests/test_config_validator.py -v
+```
+
+**Why This Matters:**
+- Users get clear, actionable error messages instead of cryptic failures
+- Prevents common configuration mistakes
+- Makes the framework more accessible to new users
+- Pre-commit hooks automatically validate configs in `massgen/configs/`
 
 ## 🔒 API Stability & Versioning
 
@@ -269,7 +345,7 @@ Create a `.env` file in the `massgen` directory as described in [README](README.
 
 ## 🔧 Development Workflow
 
-> **Important**: Our next version is v0.1.6. If you want to contribute, please contribute to the `dev/v0.1.6` branch.
+> **Important**: Our next version is v0.1.7. If you want to contribute, please contribute to the `dev/v0.1.7` branch (or `main` if dev/v0.1.7 doesn't exist yet).
 
 ### 1. Create Feature Branch
 
@@ -277,8 +353,8 @@ 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/v0.1.6
-git checkout -b feature/your-feature-name upstream/dev/v0.1.6
+# Create feature branch from dev/v0.1.7 (or main if dev branch doesn't exist yet)
+git checkout -b feature/your-feature-name upstream/dev/v0.1.7
 ```
 
 ### 2. Make Your Changes
@@ -375,7 +451,7 @@ git push origin feature/your-feature-name
 ```
 
 Then create a pull request on GitHub:
-- Base branch: `dev/v0.1.6`
+- Base branch: `dev/v0.1.7` (or `main` if dev branch doesn't exist yet)
 - Compare branch: `feature/your-feature-name`
 - Add clear description of changes
 - Link any related issues
@@ -481,7 +557,7 @@ 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/v0.1.6` branch
+- [ ] PR targets `dev/v0.1.7` branch (or `main` if dev branch doesn't exist yet)
 
 ### PR Description Should Include
 
@@ -568,15 +644,20 @@ Every feature needs documentation! Here's how to decide where and what to write.
    - Location: `docs/source/quickstart/configuration.rst`
    - What to include: YAML examples, parameter descriptions
 
-3. ✅ **API Reference** - If feature changes Python API
+3. ✅ **Config Validator** - **REQUIRED if feature changes config schema**
+   - Location: `massgen/config_validator.py` and `massgen/backend/capabilities.py`
+   - What to include: Validation logic, error messages, tests
+   - **See**: [Updating the Config Validator](#updating-the-config-validator) section above
+
+4. ✅ **API Reference** - If feature changes Python API
    - Location: `docs/source/api/`
    - What to include: Docstrings, function signatures, examples
 
-4. ✅ **CHANGELOG.md** - What changed in this version
+5. ✅ **CHANGELOG.md** - What changed in this version
    - Location: Root directory
    - What to include: Brief description under "Added", "Changed", or "Fixed"
 
-5. ✅ **Examples** - **REQUIRED for every feature**
+6. ✅ **Examples** - **REQUIRED for every feature**
    - Location: `docs/source/examples/basic_examples.rst` or feature-specific example files
    - What to include: Runnable code showing feature in action
    - **Note**: Examples are ALWAYS required, even if you write a case study. Case studies showcase real-world usage; examples show basic functionality.
@@ -657,6 +738,7 @@ Every feature needs documentation! Here's how to decide where and what to write.
 |--------------|-------------|----------|-----------|
 | **User Guide** | Every feature | `docs/source/user_guide/` | ✅ Yes |
 | **Config Docs** | Config changes | `docs/source/quickstart/configuration.rst` | ✅ Yes |
+| **Config Validator** | Config schema changes | `massgen/config_validator.py` | ✅ Yes (if config changes) |
 | **API Docs** | API changes | `docs/source/api/` | ✅ Yes |
 | **CHANGELOG** | Every PR | `CHANGELOG.md` | ✅ Yes |
 | **Examples** | **Every feature** | `docs/source/examples/` | ✅ **ALWAYS** |

{massgen-0.1.5 → massgen-0.1.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: massgen
-Version: 0.1.5
+Version: 0.1.6
 Summary: Multi-Agent Scaling System - A powerful framework for collaborative AI
 Author-email: MassGen Team <contact@massgen.dev>
 License: Apache-2.0
@@ -49,6 +49,11 @@ Requires-Dist: ag2>=0.9.10
 Requires-Dist: pyautogen>=0.10.0
 Requires-Dist: vertexai>=1.71.1
 Requires-Dist: pytest>=8.4.2
+Requires-Dist: langchain-openai>=1.0.0
+Requires-Dist: langgraph>=1.0.0
+Requires-Dist: langchain-core>=1.0.0
+Requires-Dist: agentscope>=1.0.6
+Requires-Dist: smolagents[litellm]>=1.22.0
 Requires-Dist: python-docx>=1.2.0
 Requires-Dist: openpyxl>=3.1.5
 Requires-Dist: python-pptx>=1.0.2
@@ -127,7 +132,7 @@ Dynamic: license-file
 </p>
 
 <p align="center">
-  <i>Multi-agent scaling through intelligent collaboration in Grok Heavy style</i>
+  <i>Scaling AI with collaborative, continuously improving agents</i>
 </p>
 
 MassGen is a cutting-edge multi-agent system that leverages the power of collaborative AI to solve complex tasks. It assigns a task to multiple AI agents who work in parallel, observe each other's progress, and refine their approaches to converge on the best solution to deliver a comprehensive and high-quality result. The power of this "parallel study group" approach is exemplified by advanced systems like xAI's Grok Heavy and Google DeepMind's Gemini Deep Think.
@@ -151,7 +156,7 @@ This project started with the "threads of thought" and "iterative refinement" id
 <details open>
 <summary><h3>🆕 Latest Features</h3></summary>
 
-- [v0.1.5 Features](#-latest-features-v015)
+- [v0.1.6 Features](#-latest-features-v016)
 </details>
 
 <details open>
@@ -196,15 +201,15 @@ This project started with the "threads of thought" and "iterative refinement" id
 <summary><h3>🗺️ Roadmap</h3></summary>
 
 - Recent Achievements
-  - [v0.1.5](#recent-achievements-v015)
-  - [v0.0.3 - v0.1.4](#previous-achievements-v003---v014)
+  - [v0.1.6](#recent-achievements-v016)
+  - [v0.0.3 - v0.1.5](#previous-achievements-v003---v015)
 - [Key Future Enhancements](#key-future-enhancements)
   - Bug Fixes & Backend Improvements
   - Advanced Agent Collaboration
   - Expanded Model, Tool & Agent Integrations
   - Improved Performance & Scalability
   - Enhanced Developer Experience
-- [v0.1.6 Roadmap](#v016-roadmap)
+- [v0.1.7 Roadmap](#v017-roadmap)
 </details>
 
 <details open>
@@ -229,49 +234,54 @@ This project started with the "threads of thought" and "iterative refinement" id
 
 ---
 
-## 🆕 Latest Features (v0.1.5)
+## 🆕 Latest Features (v0.1.6)
 
-**🎉 Released: October 2025**
+**🎉 Released: October 31, 2025**
 
-**What's New in v0.1.5:**
-- **🧠 Long-Term Memory System** - Semantic memory with retrieval across sessions
-- **🗜️ Automatic Context Compression** - Smart compression when approaching token limits
-- **🔄 Memory Sharing for Multi-Turn Conversations** - Agents access knowledge from previous turns
+**What's New in v0.1.6:**
+- **🔗 Framework Interoperability** - Use agents from AG2, LangGraph, AgentScope, OpenAI Assistants, and SmoLAgent as tools
+- **✅ Configuration Validator** - Pre-flight YAML validation with detailed error messages and suggestions
+- **🔧 Unified Tool Execution** - Streamlined backend architecture with consistent tool handling
+- **⚡ Gemini Backend Simplification** - Major cleanup reducing codebase by 1,598 lines
 
 **Key Improvements:**
-- Persistent memory via mem0 integration with vector storage
-- Conversational memory for short-term context tracking
-- Context monitoring with real-time token usage tracking
-- Session management for memory isolation and continuation
-- Qdrant vector database integration for semantic search
+- External agent frameworks work as MassGen custom tools
+- Comprehensive config validation with pre-commit hooks
+- ToolExecutionConfig dataclass for standardized tool handling across backends
+- Simplified Gemini backend with improved maintainability
+- Enhanced ToolManager with category management
 
-**Get Started with v0.1.5:**
+**Try v0.1.6 Features:**
 ```bash
 # Install or upgrade from PyPI
 pip install --upgrade massgen
 
-# Multi-agent collaboration with context compression
-massgen --config @examples/memory/gpt5mini_gemini_context_window_management \
-  "Analyze the MassGen codebase comprehensively. Create an architecture document that explains: (1) Core components and their responsibilities, (2) How different modules interact, (3) Key design patterns used, (4) Main entry points and request flows. Read > 30 files to build a complete understanding."
+# Use AG2 agents as tools for lesson planning (supports streaming)
+# Requirements: pip install pyautogen, OPENAI_API_KEY must be set
+massgen --config massgen/configs/tools/custom_tools/ag2_lesson_planner_example.yaml "Create a lesson plan for photosynthesis"
 
-# Research-to-implementation workflow with memory persistence
-# Prerequisites: Start Qdrant and crawl4ai Docker containers
-docker run -d -p 6333:6333 -p 6334:6334 \
-  -v $(pwd)/.massgen/qdrant_storage:/qdrant/storage:z qdrant/qdrant
-docker run -d -p 11235:11235 --name crawl4ai --shm-size=1g unclecode/crawl4ai:latest
+# Use LangGraph workflows as tools
+# Requirements: pip install langgraph langchain-openai langchain-core, OPENAI_API_KEY must be set
+massgen --config massgen/configs/tools/custom_tools/langgraph_lesson_planner_example.yaml "Create a lesson plan for photosynthesis"
 
-# Session 1 - Research phase:
-massgen --config @examples/memory/gpt5mini_gemini_research_to_implementation \
-  "Use crawl4ai to research the latest multi-agent AI papers and techniques from 2025. Focus on: coordination mechanisms, voting strategies, tool-use patterns, and architectural innovations."
+# Use AgentScope multi-agent framework as tools
+# Requirements: pip install agentscope, OPENAI_API_KEY must be set
+massgen --config massgen/configs/tools/custom_tools/agentscope_lesson_planner_example.yaml "Create a lesson plan for photosynthesis"
 
-# Session 2 - Implementation analysis (continue in same session):
-# "Based on the multi-agent research from earlier, which techniques should we implement in MassGen to make it more state-of-the-art? Consider MassGen's current architecture and what would be most impactful."
+# Use OpenAI Assistants API as tools
+# Requirements: pip install openai, OPENAI_API_KEY must be set
+massgen --config massgen/configs/tools/custom_tools/openai_assistant_lesson_planner_example.yaml "Create a lesson plan for photosynthesis"
 
-→ See [Multi-Turn Persistent Memory Case Study](docs/source/examples/case_studies/multi-turn-persistent-memory.md) for detailed analysis
+# Use SmolAgent (HuggingFace) as tools
+# Requirements: pip install smolagents, OPENAI_API_KEY must be set
+massgen --config massgen/configs/tools/custom_tools/smolagent_lesson_planner_example.yaml "Create a lesson plan for photosynthesis"
 
-# Test automatic context compression
-massgen --config @examples/memory/single_agent_compression_test \
-  "Analyze the MassGen codebase comprehensively. Create an architecture document that explains: (1) Core components and their responsibilities, (2) How different modules interact, (3) Key design patterns used, (4) Main entry points and request flows. Read > 30 files to build a complete understanding."
+# Combine multiple frameworks - AG2 + LangGraph collaboration
+# Requirements: pip install pyautogen langgraph langchain-openai langchain-core, OPENAI_API_KEY must be set
+massgen --config massgen/configs/tools/custom_tools/ag2_and_langgraph_lesson_planner.yaml "Create a lesson plan for photosynthesis"
+
+# Validate your configuration before running
+python -m massgen.config_validator your_config.yaml
 ```
 
 → [See full release history and examples](massgen/configs/README.md#release-history--examples)
@@ -1115,43 +1125,60 @@ 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 (v0.1.5)
-
-**🎉 Released: October 2025**
-
-#### Memory System
-- **PersistentMemory**: Long-term semantic memory storage via mem0 integration with fact extraction and retrieval across sessions
-- **ConversationMemory**: Short-term verbatim message tracking for active conversation context
-- **Automatic Context Compression**: Smart compression when approaching token limits with configurable thresholds (trigger_threshold, target_ratio)
-- **Cross-Agent Memory Sharing**: Agents share memory with turn-aware filtering to prevent temporal information leakage
-- **Context Monitoring**: Real-time token usage tracking with automatic compression triggers
-- **Session Management**: Memory isolation and continuation across runs with session naming support
-- **Qdrant Integration**: Vector database support for efficient semantic search in both server and local modes
-- **Configurable Memory Providers**: Support for OpenAI, Anthropic, Groq, and other mem0-compatible LLM and embedding providers
-
-#### Memory Configuration
-- **Global and Per-Agent Control**: Enable/disable memory at system or individual agent level
-- **Compression Settings**: Configurable trigger thresholds and target ratios for context window management
-- **Retrieval Configuration**: Customizable retrieval limits and smart filtering to exclude recent messages
-- **Memory Persistence**: Session continuation with named sessions for cross-session memory access
+### Recent Achievements (v0.1.6)
+
+**🎉 Released: October 31, 2025**
+
+#### Framework Interoperability
+- **AG2 Integration**: Nested chat functionality wrapped as custom tool for multi-agent lesson planning (supports streaming)
+- **LangGraph Integration**: Graph-based workflows integrated as tools for structured task execution
+- **AgentScope Integration**: AgentScope agent system wrapped for collaborative task handling
+- **OpenAI Assistants Integration**: OpenAI Assistants API integrated as tools for specialized workflows
+- **SmoLAgent Integration**: HuggingFace SmoLAgent wrapped for flexible agent orchestration
+- **Cross-Framework Collaboration**: MassGen orchestrates agents from multiple frameworks seamlessly
+- **Tool Module**: New `massgen/tool/_extraframework_agents/` module with 5 framework integrations
+- **Streaming Support**: Only AG2 currently supports streaming; other frameworks return complete results
+
+#### Configuration Validator
+- **ConfigValidator Class**: Comprehensive YAML validation in `massgen/config_validator.py`
+- **Memory Validation**: Detailed validation for memory configuration parameters
+- **Pre-commit Integration**: Automatic configuration validation before commits
+- **Error Messaging**: Actionable error messages with suggestions for common mistakes
+- **Test Coverage**: Comprehensive test suite in `massgen/tests/test_config_validator.py`
+
+#### Backend Architecture Refactoring
+- **ToolExecutionConfig**: Unified tool execution with new dataclass in `base_with_custom_tool_and_mcp.py`
+- **ResponseBackend Refactoring**: Unified tool execution flow eliminating duplicate code paths
+- **ChatCompletionsBackend Refactoring**: Consistent tool handling across Chat Completions providers
+- **ClaudeBackend Refactoring**: Unified tool execution methods for Claude backend
+- **Consistent Error Handling**: Standardized status reporting across all tool types
+
+#### Gemini Backend Simplification
+- **Module Removal**: Removed `gemini_mcp_manager.py` and `gemini_trackers.py` modules
+- **Code Consolidation**: Refactored to use manual tool execution via base class
+- **Streamlined Logic**: Removed continuation logic and duplicate code
+- **Codebase Reduction**: Net reduction of 1,598 lines through consolidation
+- **Formatter Updates**: Updated `_gemini_formatter.py` for simplified tool conversion
+
+#### Custom Tool System Enhancement
+- **ToolManager Improvements**: Enhanced category management capabilities
+- **Registration System**: Improved tool registration and validation
+- **Result Handling**: Enhanced error reporting and async execution support
+- **Schema Generation**: Improved tool schema generation for LLM consumption
 
 #### Configuration Files
-- `gpt5mini_gemini_context_window_management.yaml` - Multi-agent with automatic context compression
-- `gpt5mini_gemini_research_to_implementation.yaml` - Research-to-implementation workflow with memory
-- `gpt5mini_high_reasoning_gemini.yaml` - High reasoning agents with memory integration
-- `gpt5mini_gemini_baseline_research_to_implementation.yaml` - Baseline research workflow for comparison
-- `single_agent_compression_test.yaml` - Single agent testing context compression behavior
-
-#### Documentation
-- Complete memory system user guide: `docs/source/user_guide/memory.rst`
-- Design decisions documentation explaining architectural choices
-- API reference for PersistentMemory, ConversationMemory, and ContextMonitor classes
-- Comprehensive troubleshooting guide and monitoring instructions
+- `ag2_lesson_planner_example.yaml` - AG2 nested chat as custom tool
+- `langgraph_lesson_planner_example.yaml` - LangGraph workflows integrated
+- `agentscope_lesson_planner_example.yaml` - AgentScope agent integration
+- `openai_assistant_lesson_planner_example.yaml` - OpenAI Assistants as tools
+- `smolagent_lesson_planner_example.yaml` - SmoLAgent integration
+- `ag2_and_langgraph_lesson_planner.yaml` - Multi-framework collaboration
+- `ag2_and_openai_assistant_lesson_planner.yaml` - AG2 + OpenAI Assistants combo
+- `two_models_with_tools_example.yaml` - Multiple models with custom tools
 
-#### Testing Infrastructure
-- Memory test suite: `test_agent_memory.py`, `test_conversation_memory.py`, `test_orchestrator_memory.py`, `test_persistent_memory.py`
+### Previous Achievements (v0.0.3 - v0.1.5)
 
-### Previous Achievements (v0.0.3 - v0.1.4)
+✅ **Memory System (v0.1.5)**: Long-term semantic memory via mem0 integration with fact extraction and retrieval across sessions, short-term conversational memory for active context, automatic context compression when approaching token limits, cross-agent memory sharing with turn-aware filtering, session management for memory isolation and continuation, Qdrant vector database integration for semantic search
 
 ✅ **Multimodal Generation Tools (v0.1.4)**: Create images from text via DALL-E API, generate videos from descriptions, text-to-speech with audio transcription support, document generation for PDF/DOCX/XLSX/PPTX formats, image transformation capabilities for existing images
 
@@ -1271,21 +1298,22 @@ MassGen is currently in its foundational stage, with a focus on parallel, asynch
 
 We welcome community contributions to achieve these goals.
 
-### v0.1.6 Roadmap
+### v0.1.7 Roadmap
 
-Version 0.1.6 focuses on backend code refactoring for improved maintainability and developer experience:
+Version 0.1.7 focuses on agent task planning and rate limiting for improved coordination and cost management:
 
 #### Planned Features
-- **Backend Code Refactoring**: Major code refactoring for improved maintainability and developer experience with better code organization, modularity, and architectural improvements
+- **Agent Task Planning System**: Enable agents to organize complex multi-step work with task plans, dependency tracking, and progress monitoring via 8 new MCP planning tools
+- **Gemini Rate Limiting System**: Multi-dimensional rate limiting (RPM, TPM, RPD) to prevent API spam and manage costs with model-specific limits and configurable thresholds
 
 Key technical approach:
-- **Code Architecture**: Enhanced code organization with improved modularity and separation of concerns
-- **Developer Experience**: Simplified backend extension points, improved API clarity, better error handling and debugging support
-- **Quality Assurance**: Comprehensive testing to ensure no functionality regressions
+- **Task Planning**: MCP-based planning tools with dependency graphs, status tracking, and maximum 100 tasks per plan safety limit
+- **Rate Limiting**: Sliding window tracking, external YAML configuration, optional CLI flag, mandatory cooldown periods after startup
+- **Configuration**: Both features are optional and configurable via flags (`enable_agent_task_planning`, `--rate-limit`)
 
-**Target Release**: November 1, 2025 (Friday @ 9am PT)
+**Target Release**: November 3, 2025 (Monday @ 9am PT)
 
-For detailed milestones and technical specifications, see the [full v0.1.6 roadmap](ROADMAP_v0.1.6.md).
+For detailed milestones and technical specifications, see the [full v0.1.7 roadmap](ROADMAP_v0.1.7.md).
 
 ---