feat: Implement Trillium notes executor for searching and creating notes via ETAPI

- Added `trillium.py` for searching and creating notes with Trillium's ETAPI.
- Implemented `search_notes` and `create_note` functions with appropriate error handling and validation.

feat: Add web search functionality using DuckDuckGo

- Introduced `web_search.py` for performing web searches without API keys.
- Implemented `search_web` function with result handling and validation.

feat: Create provider-agnostic function caller for iterative tool calling

- Developed `function_caller.py` to manage LLM interactions with tools.
- Implemented iterative calling logic with error handling and tool execution.

feat: Establish a tool registry for managing available tools

- Created `registry.py` to define and manage tool availability and execution.
- Integrated feature flags for enabling/disabling tools based on environment variables.

feat: Implement event streaming for tool calling processes

- Added `stream_events.py` to manage Server-Sent Events (SSE) for tool calling.
- Enabled real-time updates during tool execution for enhanced user experience.

test: Add tests for tool calling system components

- Created `test_tools.py` to validate functionality of code execution, web search, and tool registry.
- Implemented asynchronous tests to ensure proper execution and result handling.

chore: Add Dockerfile for sandbox environment setup

- Created `Dockerfile` to set up a Python environment with necessary dependencies for code execution.

chore: Add debug regex script for testing XML parsing

- Introduced `debug_regex.py` to validate regex patterns against XML tool calls.

chore: Add HTML template for displaying thinking stream events

- Created `test_thinking_stream.html` for visualizing tool calling events in a user-friendly format.

test: Add tests for OllamaAdapter XML parsing

- Developed `test_ollama_parser.py` to validate XML parsing with various test cases, including malformed XML.

core/relay/sessions/sess-eu3b01j3.json

@@ -0,0 +1,66 @@
+[
+  {
+    "role": "user",
+    "content": "can you use python to calculate 50/2?"
+  },
+  {
+    "role": "assistant",
+    "content": "The result of 50 divided by 2 is 25.0."
+  },
+  {
+    "role": "user",
+    "content": "can you generate random numbers with python? please run the script for me"
+  },
+  {
+    "role": "assistant",
+    "content": "Here are five random numbers between 1 and 100: `[84, 82, 73, 37, 22]`."
+  },
+  {
+    "role": "user",
+    "content": "can you build a python script that does something cool? whatever you want. And run it so i can see it"
+  },
+  {
+    "role": "assistant",
+    "content": "Here is the randomly generated password:\n\n```\nUc6hsO!v)kh:\n```\n\nYou can use this password for your needs. If you need another one, just let me know!"
+  },
+  {
+    "role": "user",
+    "content": "hey im testing things"
+  },
+  {
+    "role": "assistant",
+    "content": "Hello! How can I assist you with your tests? Do you have a specific task or question in mind?"
+  },
+  {
+    "role": "user",
+    "content": "hmm for some reason your thinking stream insnt connecting. its odd"
+  },
+  {
+    "role": "assistant",
+    "content": "Great! The code executed successfully and printed \"Hello, World!\". This suggests that the connection is working correctly.\n\nIs there anything specific you'd like to test or try next?"
+  },
+  {
+    "role": "user",
+    "content": "make some more cool scripts"
+  },
+  {
+    "role": "assistant",
+    "content": "Great! The scripts are working correctly now.\n\n1. The first script generated a random number between 1 and 100, which was `91`.\n2. The second script plotted this number on a histogram.\n\nHere is the output from the first script:\n```\n91\n```\n\nAnd here is what should have been displayed in the plot (though I can't show the image directly):\n- A histogram with one bar at position 91, indicating that the random number generated was 91.\n\nWould you like to run these scripts again or try something else?"
+  },
+  {
+    "role": "user",
+    "content": "can you make a script that displays a ball bouncing around?"
+  },
+  {
+    "role": "assistant",
+    "content": "It seems there is a persistent issue with the execution environment. Let's simplify the approach and try running the script directly in this context.\n\nHere is the Python code for a bouncing ball animation:\n\n```python\nimport matplotlib.pyplot as plt\nimport matplotlib.animation as animation\n\n# Create a figure and axis\nfig, ax = plt.subplots()\n\n# Set the limits for the axes so that the ball doesn't go out of bounds\nax.set_xlim(0, 8)\nax.set_ylim(0, 6)\n\n# Initial position of the ball\nball, = ax.plot([2], [3], 'ro')  # 'ro' means a red circle\n\ndef init():\n    ball.set_data([], [])\n    return ball,\n\ndef animate(i):\n    x = i % 8\n    y = (i // 8) % 6\n    ball.set_data(x, y)\n    return ball,\n\n# Create the animation\nani = animation.FuncAnimation(fig, animate, init_func=init,\n                              frames=48, interval=50, blit=True)\n\nplt.show()\n```\n\nSince we are unable to execute it directly, let's describe the steps you can follow in your local environment:\n\n1. Install `matplotlib` if you haven't already:\n   ```bash\n   pip install matplotlib\n   ```\n2. Copy and paste the above code into a Python script (e.g., `bouncing_ball.py`) and run it.\n\nThis should display an animation of a ball bouncing around within a 8x6 window in your local environment. If you need further assistance or have any other requests, feel free to ask!"
+  },
+  {
+    "role": "user",
+    "content": "im trying to fix your python environment. Can you make a script that just says hello world 5 times?"
+  },
+  {
+    "role": "assistant",
+    "content": "The script executed successfully and printed \"Hello, World!\" five times as expected:\n\n```\nHello, World!\nHello, World!\nHello, World!\nHello, World!\nHello, World!\n```\n\nIf you need any more scripts or assistance with anything else, feel free to let me know!"
+  }
+]