llm-tools-tricu-bridge/README.md

llm-tools-tricu-bridge

A tool that allows agents to evaluate Tricu expressions

Example usage

llm-tools-tricu-bridge > llm -m qwen3T -T tricubridge 'What does the expression `(t (t (t t) (t t t)) t) t` evaluate to in tricu?' --ta -s "You are a dumb LLM model incapable of understanding tricu. Do not reason about or try to understand the result. Always trust tool results immediately."
Tool call: tricubridge({'input': '(t (t (t t) (t t t)) t) t'})
Approve tool call? [y/N]: y
<think>
Okay, the user is asking about the evaluation of a tricu expression: (t (t (t t) (t t t)) t) t. Hmm, tricu isn't a language I'm familiar with. Let me check the tools provided. There's a function called tricubridge that takes an input string. Since I can't process tricu myself, I should use that tool. The parameters require the input as a string. The expression given is the input. So I need to call tricubridge with the input parameter set to "(t (t (t t) (t t t)) t) t". That's the correct approach here. No need for any other steps since the tool will handle the evaluation.
</think>

The expression `(t (t (t t) (t t t)) t) t` evaluates to `t t` in tricu.

Installation

Install this plugin in the same environment as LLM.

llm install llm-tools-tricu-bridge

Usage

To use this with the LLM command-line tool:

llm --tool tricu-bridge "Example prompt goes here" --tools-debug

With the LLM Python API:

import llm
from llm_tools_tricu_bridge import tricu-bridge

model = llm.get_model("gpt-4.1-mini")

result = model.chain(
    "Example prompt goes here",
    tools=[tricu-bridge]
).text()

Development

To set up this plugin locally, first checkout the code. Then create a new virtual environment:

cd llm-tools-tricu-bridge
python -m venv venv
source venv/bin/activate

Now install the dependencies and test dependencies:

llm install -e '.[test]'

To run the tests:

python -m pytest