docs: update README.md, create debugging_assistant.md docs

Author: maciejmajek

README.md

@@ -49,6 +49,7 @@ The RAI framework aims to:
 - [Features](#features)
 - [Setup](#setup)
 - [Usage examples (demos)](#simulation-demos)
+- [Debugging Assistant](#debugging-assistant)
 - [Developer resources](#developer-resources)
 
 ## Features
@@ -66,6 +67,7 @@ The RAI framework aims to:
 - [x] Improved Human-Robot Interaction with voice and text.
 - [x] Additional tooling such as GroundingDino.
 - [x] Support for at least 3 different AI vendors.
+- [x] Debugging assistant for ROS 2.
 - [ ] SDK for RAI developers.
 - [ ] UI for configuration to select features and tools relevant for your deployment.
 
@@ -153,6 +155,10 @@ Once you know your way around RAI, try the following challenges, with the aid th
 - Implement additional tools and use them in your interaction.
 - Try a complex, multi-step task for your robot, such as going to several points to perform observations!
 
+## Debugging Assistant
+
+Use the [debugging assistant](./docs/debugging_assistant.md) to inspect ROS 2 network state and troubleshoot issues.
+
 ### Simulation demos
 
 Try RAI yourself with these demos:

docs/debugging_assistant.md

@@ -0,0 +1,51 @@
+# ROS 2 Debugging Assistant
+
+The ROS 2 Debugging Assistant is an interactive tool that helps developers inspect and troubleshoot their ROS 2 systems using natural language. It provides a chat-like interface powered by Streamlit where you can ask questions about your ROS 2 setup and execute common debugging commands.
+
+![Debugging Assistant Interface](imgs/debugging_assistant.png)
+
+## Features
+
+- Interactive chat interface for debugging ROS 2 systems
+- Real-time streaming of responses and tool executions
+- Support for common ROS 2 debugging commands:
+  - Topic inspection and manipulation
+  - Service inspection
+  - Node information
+  - Action server details
+  - Interface inspection
+
+## Running the Assistant
+
+1. Make sure you have RAI installed and configured according to the [setup instructions](../README.md#setup)
+
+2. Launch the debugging assistant:
+
+```sh
+source setup_shell.sh
+streamlit run src/rai/rai/tools/debugging_assistant.py
+```
+
+## Usage Examples
+
+Here are some example queries you can try:
+
+- "What topics are currently available?"
+- "Show me the message type for /cmd_vel"
+- "List all active nodes"
+- "What services does the /robot_state_publisher node provide?"
+- "Show me information about the /navigate_to_pose action"
+
+## How it Works
+
+The debugging assistant uses RAI's conversational agent capabilities combined with ROS 2 debugging tools. The key components are:
+
+1. **Streamlit Interface**: Provides the chat UI and displays tool execution results
+2. **ROS 2 Tools**: Collection of debugging tools that wrap common ROS 2 CLI commands
+3. **Streaming Callbacks**: Real-time updates of LLM responses and tool executions
+
+## Limitations
+
+- The assistant can only execute safe, read-only commands by default
+- Some complex debugging scenarios may require manual intervention
+- Performance depends on the chosen LLM vendor and model