AI Chat

AI Chat

The core of PandaNpc — a powerful multi-model AI conversation interface.

Multi-Model Support

Switch between different AI models in a single interface:

OpenAI: GPT-5.2, GPT-5.2 Codex, GPT-5, GPT-5 mini, GPT-5 nano
Anthropic: Claude Opus 4.6, Sonnet 4.5, Haiku 4.5, Claude Web
Google: Gemini 3 Pro, Gemini 3 Flash, Gemini Web
DeepSeek: DeepSeek-V3
Custom: Any OpenAI-compatible API

Streaming Response

AI responses are displayed in real-time as they are generated:

Watch the AI "think" — responses appear word by word
Start reading immediately without waiting for completion
A thinking indicator shows the AI's reasoning process (for models that support it)

Image Recognition

Drag and drop images directly into the chat:

Drag an image file into the chat input area
Or paste an image from clipboard (Ctrl+V / Cmd+V)
Add your question about the image
The AI will analyze and respond based on the image content

Supported models: GPT-5.2, Claude Opus 4.6, Gemini 3 Pro (and other vision-capable models)

Conversation Management

Create New Conversation

Click the + button in the chat sidebar to start a new conversation. Each conversation maintains its own context and model selection.

Message Folding

Long messages can be collapsed for easier browsing:

Click the fold icon on any message to collapse it
Code blocks can be folded independently
Folded messages show a preview of the first few lines

Code Highlighting

Code blocks in AI responses are automatically syntax-highlighted:

Supports 100+ programming languages
One-click copy button on each code block
Line numbers for easy reference

System Prompts

Customize the AI's behavior with system prompts:

Click the settings icon in the chat header
Enter your system prompt (e.g., "You are a Python expert")
The AI will follow your instructions for the entire conversation

Keyboard Shortcuts

Shortcut	Action
`Enter`	Send message
`Shift + Enter`	New line
`Ctrl/Cmd + N`	New conversation
`Ctrl/Cmd + L`	Clear conversation
`Esc`	Cancel streaming