Lumeo

ReasoningDisplay

Collapsible chain-of-thought block for AI reasoning traces.

Installation

dotnet add package Lumeo

One-time app setup (AddLumeo(), CSS & JS) is covered in the installation guide.

Usage

@using Lumeo

<ReasoningDisplay />

When to Use

  • Display reasoning traces from chain-of-thought models (e.g. Claude's extended thinking mode).
  • Show an intermediate thinking step collapsed by default to avoid cluttering the chat UI.
  • Use IsStreaming to animate while tokens are arriving, then set it to false when the trace is complete.
Reasoning

First, I need to consider the user's question carefully. The problem involves finding the optimal path through a weighted graph. I should apply Dijkstra's algorithm here, starting from the source node. Let me trace through the steps: initialize distances to infinity, process nodes by priority queue... After analyzing all edges, the shortest path from A to D is A → B → C → D with total weight 7.

Reasoned for 4.2s

First, I need to consider the user's question carefully. The problem involves finding the optimal path through a weighted graph. I should apply Dijkstra's algorithm here, starting from the source node. Let me trace through the steps: initialize distances to infinity, process nodes by priority queue... After analyzing all edges, the shortest path from A to D is A → B → C → D with total weight 7.

Reasoning

Analyzing the request...

Chain of thought

First, I need to consider the user's question carefully. The problem involves finding the optimal path through a weighted graph. I should apply Dijkstra's algorithm here, starting from the source node. Let me trace through the steps: initialize distances to infinity, process nodes by priority queue... After analyzing all edges, the shortest path from A to D is A → B → C → D with total weight 7.

Reasoning (markdown)

Let me break this down into steps:

  1. Parse the input graph
  2. Run Dijkstra from the source
  3. Return the shortest path

The result is A → B → C → D with total weight 7.

Switch variant to compare Default, Compact, and Detailed layouts.

Reasoned for 2.8s

First, I need to consider the user's question carefully. The problem involves finding the optimal path through a weighted graph. I should apply Dijkstra's algorithm here, starting from the source node. Let me trace through the steps: initialize distances to infinity, process nodes by priority queue... After analyzing all edges, the shortest path from A to D is A → B → C → D with total weight 7.

Switch size to compare Small, Medium, and Large text scaling.

Reasoning

First, I need to consider the user's question carefully. The problem involves finding the optimal path through a weighted graph. I should apply Dijkstra's algorithm here, starting from the source node. Let me trace through the steps: initialize distances to infinity, process nodes by priority queue... After analyzing all edges, the shortest path from A to D is A → B → C → D with total weight 7.

API Reference

ReasoningDisplay

Variant: Default renders the full block, Compact condenses the height, and Detailed expands with extra meta.

  • StreamingText — Token-by-token streaming text renderer for AI responses.
  • ToolCallCard — AI tool-invocation card showing call and result.