{% extends "base.html" %} {% block title %}Patterns — clustertrace{% endblock %} {% block content %}

Failure patterns

clustertrace is a local-first debugger for LLM agents. Instead of scrolling through individual run logs, it groups failing runs by execution pattern — the order of functions and tool calls each run made — so two underlying bugs surface as two patterns instead of twelve scattered traces. Patterns below are ordered by how often they occur; the ones with red fail-rates are where the bugs are.

Summary

loading…

Functions involved in failures most often

loading…

Where failures share a path

The longest sequence of functions that every failing run starts with. When failures come from different agents the shared path is empty — check the per-agent breakdown below.

Patterns by frequency

loading…
Advanced: how patterns are matched
Two runs are in the same pattern if they ran the same functions in the same order. Switch modes if exact matching produces too many patterns.
{% endblock %}