📝 docs(readme): update documentation for LangGraph v0.6.6 integration and model configuration

- Clarify seamless integration with LangGraph Studio and update README badges
- Add LangGraph v0.6.6 features highlighting context-driven configuration API changes
- Provide detailed model configuration methods: runtime context, env vars, Studio assistant
- Expand API key setup instructions for OpenAI, Anthropic, Qwen, and OpenAI-compatible providers
- Introduce sample LangSmith execution traces with DeepWiki and web search examples
- Update MCP server examples to include Context7 documentation tools with usage tips
- Improve Chinese readme with corresponding updates and new configuration guidance
- Refine project descriptions and badge links for both English and Chinese docs

Author: webup

CLAUDE.md

@@ -82,7 +82,7 @@ make dev_ui                 # Start LangGraph development server with UI
 
 ## LangGraph Studio Integration
 
-This project is designed for LangGraph Studio. The `langgraph.json` config file defines:
+This project works seamlessly with LangGraph Studio. The `langgraph.json` config file defines:
 - Graph entry point: `./src/react_agent/graph.py:graph`
 - Environment file: `.env`
 - Dependencies: current directory (`.`)

README.md

@@ -1,14 +1,14 @@
 # LangGraph ReAct Agent Template
 
 [![Version](https://img.shields.io/badge/version-v0.1.0-blue.svg)](https://github.com/webup/langgraph-up-react)
+[![LangGraph](https://img.shields.io/badge/LangGraph-v0.6.6-blue.svg)](https://github.com/langchain-ai/langgraph)
 [![Build](https://github.com/webup/langgraph-up-react/actions/workflows/unit-tests.yml/badge.svg)](https://github.com/webup/langgraph-up-react/actions/workflows/unit-tests.yml)
 [![License](https://img.shields.io/badge/license-MIT-green.svg)](https://opensource.org/licenses/MIT)
-[![README EN](https://img.shields.io/badge/README-English-blue.svg)](./README.md)
 [![README CN](https://img.shields.io/badge/README-中文-red.svg)](./README_CN.md)
 [![DeepWiki](https://img.shields.io/badge/Powered_by-DeepWiki-blue.svg)](https://deepwiki.com/webup/langgraph-up-react)
 [![Twitter](https://img.shields.io/twitter/follow/zhanghaili0610?style=social)](https://twitter.com/zhanghaili0610)
 
-This template showcases a [ReAct agent](https://arxiv.org/abs/2210.03629) implemented using [LangGraph](https://github.com/langchain-ai/langgraph), designed for [LangGraph Studio](https://github.com/langchain-ai/langgraph-studio). ReAct agents are uncomplicated, prototypical agents that can be flexibly extended to many tools.
+This template showcases a [ReAct agent](https://arxiv.org/abs/2210.03629) implemented using [LangGraph](https://github.com/langchain-ai/langgraph), works seamlessly with [LangGraph Studio](https://docs.langchain.com/langgraph-platform/quick-start-studio#use-langgraph-studio). ReAct agents are uncomplicated, prototypical agents that can be flexibly extended to many tools.
 
 ![Graph view in LangGraph studio UI](./static/studio_ui.png)
 
@@ -18,28 +18,30 @@ The core logic, defined in `src/react_agent/graph.py`, demonstrates a flexible R
 
 ## Features
 
-### Dynamic Tool Loading
-- **Web Search**: Built-in Tavily search integration
-- **Documentation Tools**: DeepWiki MCP integration for GitHub repository documentation
-- **Extensible**: Easy to add custom tools via `src/common/tools.py`
-
 ### Multi-Provider Model Support
+- **Qwen Models**: Complete Qwen series support via `langchain-qwq` package, including Qwen-Plus, Qwen-Turbo, QwQ-32B, QvQ-72B
 - **OpenAI**: GPT-4o, GPT-4o-mini, etc.
   - **OpenAI-Compatible**: Any provider supporting OpenAI API format via custom API key and base URL
 - **Anthropic**: Claude 4 Sonnet, Claude 3.5 Haiku, etc.
-- **Qwen**: Qwen-Plus, Qwen-Turbo, QwQ-32B, QvQ-72B with regional API support
 
-### MCP Integration
-- **Model Context Protocol**: Dynamic external tool loading at runtime
-- **DeepWiki MCP Server**: Repository documentation access and Q&A capabilities
-- **Caching**: Optimized performance with client and tools caching
-- **Configurable**: Enable via environment variables or context parameters
+### Agent Tool Integration Ecosystem
+- **Model Context Protocol (MCP)**: Dynamic external tool loading at runtime
+- **DeepWiki MCP Server**: Optional MCP tools for GitHub repository documentation access and Q&A capabilities  
+- **Web Search**: Built-in traditional LangChain tools (Tavily) for internet information retrieval
+
+### LangGraph v0.6 Features
+
+> [!NOTE]
+> **New in LangGraph v0.6**: [LangGraph Context](https://docs.langchain.com/oss/python/context#context-overview) replaces the traditional `config['configurable']` pattern. Runtime context is now passed to the `context` argument of `invoke/stream`, providing a cleaner and more intuitive way to configure your agents.
 
-### Comprehensive Testing
-- **70+ Test Cases**: Unit, integration, and end-to-end testing
-- **MCP Integration Coverage**: Full testing of DeepWiki tool loading and execution
-- **ReAct Loop Validation**: Tests verify proper tool-model interactions
-- **Mock Support**: Reliable testing without external API calls
+- **Context-Driven Configuration**: Runtime context passed via `context` parameter instead of `config['configurable']`
+- **Simplified API**: Cleaner interface for passing runtime configuration to your agents
+- **Backward Compatibility**: Gradual migration path from the old configuration pattern
+
+### LangGraph Platform Development Support
+- **Local Development Server**: Complete LangGraph Platform development environment
+- **70+ Test Cases**: Unit, integration, and end-to-end testing coverage with complete DeepWiki tool loading and execution testing
+- **ReAct Loop Validation**: Ensures proper tool-model interactions
 
 ## What it Does
 
@@ -53,6 +55,13 @@ The ReAct agent:
 
 The agent comes with web search capabilities and optional DeepWiki MCP documentation tools, but can be easily extended with custom tools to suit various use cases.
 
+### Sample Execution Traces
+
+See these LangSmith traces to understand how the agent works in practice:
+
+- **[DeepWiki Documentation Query](https://smith.langchain.com/public/d0594549-7363-46a7-b1a2-d85b55aaa2bd/r)** - Shows agent using DeepWiki MCP tools to query GitHub repository documentation
+- **[Web Search Query](https://smith.langchain.com/public/6ce92fd2-c0e4-409b-9ce2-02499ae16800/r)** - Demonstrates Tavily web search integration and reasoning loop
+
 ## Getting Started
 
 ### Setup with uv (Recommended)
@@ -88,75 +97,61 @@ cp .env.example .env
 # Required: Web search functionality
 TAVILY_API_KEY=your-tavily-api-key
 
-# Model providers (choose at least one)
+# Required: If using Qwen models (default)
+DASHSCOPE_API_KEY=your-dashscope-api-key
+
+# Optional: OpenAI model service platform keys
 OPENAI_API_KEY=your-openai-api-key
+# Optional: If using OpenAI-compatible service platforms
+OPENAI_API_BASE=your-openai-base-url
+
+# Optional: If using Anthropic models
 ANTHROPIC_API_KEY=your-anthropic-api-key
-DASHSCOPE_API_KEY=your-dashscope-api-key  # For Qwen models
 
-# Optional: Regional API support for Qwen models
-REGION=international  # or 'prc' for China mainland
+# Optional: Regional API support for Qwen models  
+REGION=international  # or 'prc' for China mainland (default)
 
-# Optional: Enable documentation tools
+# Optional: Always enable DeepWiki documentation tools
 ENABLE_DEEPWIKI=true
 ```
 
 The primary [search tool](./src/common/tools.py) uses [Tavily](https://tavily.com/). Create an API key [here](https://app.tavily.com/sign-in).
 
-## Model Setup
-
-The default model configuration is:
+## Model Configuration
 
-```yaml
-model: qwen:qwen-turbo
-```
+The template uses `qwen:qwen-turbo` as the default model, defined in [`src/common/context.py`](./src/common/context.py). You can configure different models in three ways:
 
-### OpenAI
+1. **Runtime Context** (recommended for programmatic usage)
+2. **Environment Variables** 
+3. **LangGraph Studio Assistant Configuration**
 
-To use OpenAI's chat models:
+### API Key Setup by Provider
 
-1. Sign up for an [OpenAI API key](https://platform.openai.com/signup)
-2. Add it to your `.env` file:
+#### OpenAI
 ```bash
-OPENAI_API_KEY=your-api-key
+OPENAI_API_KEY=your-openai-api-key
 ```
+Get your API key: [OpenAI Platform](https://platform.openai.com/api-keys)
 
-### Anthropic
-
-To use Anthropic's chat models:
-
-1. Sign up for an [Anthropic API key](https://console.anthropic.com/)
-2. Add it to your `.env` file:
+#### Anthropic  
 ```bash
-ANTHROPIC_API_KEY=your-api-key
+ANTHROPIC_API_KEY=your-anthropic-api-key
 ```
-3. Update the model in LangGraph Studio to `anthropic:claude-3-5-sonnet-20240620`
-
-### Qwen Models (Default)
+Get your API key: [Anthropic Console](https://console.anthropic.com/)
 
-For Alibaba's Qwen models (Qwen3, QwQ-32B, etc.):
-
-1. Sign up for a [DashScope API key](https://dashscope.console.aliyun.com/)
-2. Add it to your `.env` file:
+#### Qwen Models (Default)
 ```bash
-DASHSCOPE_API_KEY=your-api-key
+DASHSCOPE_API_KEY=your-dashscope-api-key
 REGION=international  # or 'prc' for China mainland
 ```
-3. Update the model in LangGraph Studio to `qwen:qwen3-32b` or `qwen:qwen-plus`
-
-### OpenAI-Compatible Providers
-
-For any OpenAI-compatible API (SiliconFlow, Together AI, Groq, etc.):
+Get your API key: [DashScope Console](https://dashscope.console.aliyun.com/)
 
-1. Get your API key from the provider
-2. Add to your `.env` file:
+#### OpenAI-Compatible Providers
 ```bash
-# Example for custom OpenAI-compatible provider
 OPENAI_API_KEY=your-provider-api-key
 OPENAI_API_BASE=https://your-provider-api-base-url/v1
 ```
-3. Update the model in LangGraph Studio to `openai:provider-model-name`
-
-This flexible architecture allows you to use any OpenAI-compatible API by simply providing the API key and base URL.
+Supports SiliconFlow, Together AI, Groq, and other OpenAI-compatible APIs.
 
 ## How to Customize
 
@@ -181,50 +176,78 @@ MCP_SERVERS = {
         "url": "https://mcp.deepwiki.com/mcp",
         "transport": "streamable_http",
     },
-    "your_mcp_server": {  # Add your MCP server
-        "url": "https://your-mcp-server.com/mcp",
-        "transport": "streamable_http",
-    }
+    # Example: Context7 for library documentation
+    "context7": {
+        "url": "https://mcp.context7.com/sse",
+        "transport": "sse",
+    },
 }
 ```
 
 2. **Add Server Function**:
 ```python
-async def get_your_mcp_tools() -> List[Callable[..., Any]]:
-    """Get tools from your MCP server."""
-    return await get_mcp_tools("your_mcp_server")
+async def get_context7_tools() -> List[Callable[..., Any]]:
+    """Get Context7 documentation tools."""
+    return await get_mcp_tools("context7")
 ```
 
-3. **Enable in Context** - Add context flag and load tools in `get_tools()` function.
+3. **Enable in Context** - Add context flag and load tools in `get_tools()` function:
+```python
+# In src/common/tools.py
+if context.enable_context7:
+    tools.extend(await get_context7_tools())
+```
 
-### Configure Models
-Our key extended method `load_chat_model` in [`src/common/utils.py`](./src/common/utils.py) uses LangChain's [`init_chat_model`](https://python.langchain.com/api_reference/langchain/chat_models/langchain.chat_models.base.init_chat_model.html#init-chat-model) as the underlying utility.
+> [!TIP]
+> **Context7 Example**: The MCP configuration already includes a commented Context7 server setup. Context7 provides up-to-date library documentation and examples - simply uncomment the configuration and add the context flag to enable it.
 
-**Model String Format**: `provider:model-name` (follows LangChain's naming convention)
+### Model Configuration Methods
 
-**Examples**:
-```python
-# OpenAI models
-model = "openai:gpt-4o-mini"
-model = "openai:gpt-4o"
+#### 1. Runtime Context (Recommended)
 
-# Qwen models (with regional support)
-model = "qwen:qwen-turbo"    # Default model
-model = "qwen:qwen-plus"     # Balanced performance
-model = "qwen:qwq-32b-preview"  # Reasoning model
-model = "qwen:qvq-72b-preview"  # Multimodal reasoning
+Use the new LangGraph v0.6 context parameter to configure models at runtime:
 
-# Anthropic models
-model = "anthropic:claude-4-sonnet"
-model = "anthropic:claude-3.5-haiku"
+```python
+from common.context import Context
+from react_agent import graph
+
+# Configure model via context
+result = await graph.ainvoke(
+    {"messages": [("user", "Your question here")]},
+    context=Context(model="openai:gpt-4o-mini")
+)
 ```
 
-**Configuration**:
+#### 2. Environment Variables
+
+Set the `MODEL` environment variable in your `.env` file:
+
 ```bash
-# Set via environment variable
-MODEL=qwen:qwen-turbo
+MODEL=anthropic:claude-3.5-haiku
+```
 
-# Or in LangGraph Studio configurable settings
+#### 3. LangGraph Studio Assistant Configuration
+
+In LangGraph Studio, configure models through [Assistant management](https://docs.langchain.com/langgraph-platform/configuration-cloud#manage-assistants). Create or update assistants with different model configurations for easy switching between setups.
+
+### Supported Model Formats
+
+**Model String Format**: `provider:model-name` (follows LangChain [`init_chat_model`](https://python.langchain.com/api_reference/langchain/chat_models/langchain.chat_models.base.init_chat_model.html#init-chat-model) naming convention)
+
+```python
+# OpenAI models
+"openai:gpt-4o-mini"
+"openai:gpt-4o"
+
+# Qwen models (with regional support)
+"qwen:qwen-turbo"          # Default model
+"qwen:qwen-plus"           # Balanced performance
+"qwen:qwq-32b-preview"     # Reasoning model
+"qwen:qvq-72b-preview"     # Multimodal reasoning
+
+# Anthropic models
+"anthropic:claude-4-sonnet"
+"anthropic:claude-3.5-haiku"
 ```
 
 ### Customize Prompts
@@ -246,8 +269,8 @@ Runtime configuration is managed in [`src/common/context.py`](./src/common/conte
 
 ### Development Server
 ```bash
-make dev        # Start LangGraph development server
-make dev_ui     # Start with browser UI
+make dev        # Start LangGraph development server (uv run langgraph dev --no-browser)
+make dev_ui     # Start with LangGraph Studio Web UI in browser
 ```
 
 ### Testing
@@ -279,7 +302,7 @@ The template uses a modular architecture:
 - **`src/react_agent/`**: Core agent graph and state management
 - **`src/common/`**: Shared components (context, models, tools, prompts, MCP integration)
 - **`tests/`**: Comprehensive test suite with fixtures and MCP integration coverage
-- **`langgraph.json`**: LangGraph Studio configuration
+- **`langgraph.json`**: LangGraph Agent basic configuration settings
 
 Key components:
 - **`src/common/mcp.py`**: MCP client management for external documentation sources