Dorian
c28e6dd811
Foundation for the next-generation AI content surface UI: - 16 Cursor rules files covering philosophy, Vue conventions, design system, content surfaces, plugin system, AI integration, renderers, security, Bitcoin-only policy, dev/prod modes, accessibility, performance, animation, mobile UX, and git workflow - pnpm workspaces + Turborepo monorepo (@aiui/core, @aiui/app) - Vue 3 + Vite + TypeScript + Tailwind CSS 4 - Core type system: plugins, renderers, messages, content blocks - Plugin registry with renderer registration - 50 mock film fixtures with search/filter utilities - App shell with chat page layout - Environment config templates Made-with: Cursor
84 lines
2.8 KiB
Plaintext
84 lines
2.8 KiB
Plaintext
---
|
|
description: AI adapter patterns, streaming, tool calling, context injection
|
|
globs: "**/ai/**,**/plugins/ai-*/**"
|
|
alwaysApply: false
|
|
---
|
|
|
|
# AI Integration
|
|
|
|
## Universal AI Adapter
|
|
All AI providers connect through the `AIProviderAdapter` interface:
|
|
|
|
```typescript
|
|
interface AIProviderAdapter extends AIUIPlugin {
|
|
type: 'ai-provider'
|
|
chat(messages: Message[], options: ChatOptions): AsyncIterable<ChatChunk>
|
|
models(): Promise<Model[]>
|
|
supportsStreaming: boolean
|
|
supportsVision: boolean
|
|
supportsTools: boolean
|
|
supportsMultimodal: boolean
|
|
}
|
|
```
|
|
|
|
## Provider Hierarchy
|
|
1. **OpenAI-Compatible Adapter** — covers OpenRouter, Ollama, vLLM, llama.cpp, LocalAI, Mistral, DeepSeek, xAI, Qwen. Just change `baseURL` + API key.
|
|
2. **Anthropic Adapter** — Claude. Different tool_use format (content blocks vs tool_calls).
|
|
3. **Gemini Adapter** — Google. Different multimodal format.
|
|
4. **MCP Client** — connects to any MCP server for tools, resources, prompts.
|
|
|
|
## Streaming
|
|
- All AI responses use Server-Sent Events (SSE) over HTTP
|
|
- Pattern: `data: {"token": "Hello"}\n\n` with `data: [DONE]\n\n` termination
|
|
- Client: parse SSE stream, feed tokens to `StreamingTextRenderer`
|
|
- Always show a typing indicator while waiting for first token
|
|
- Handle connection drops gracefully (show error, offer retry)
|
|
|
|
## Tool Calling
|
|
AI can invoke tools. The adapter normalizes tool call formats:
|
|
```typescript
|
|
interface ToolCall {
|
|
id: string
|
|
name: string
|
|
arguments: Record<string, unknown>
|
|
}
|
|
|
|
interface ToolResult {
|
|
toolCallId: string
|
|
content: string | StructuredContent
|
|
isError: boolean
|
|
}
|
|
```
|
|
|
|
Normalize across providers:
|
|
- OpenAI: `tool_calls` in assistant message → `role: "tool"` result
|
|
- Claude: `type: "tool_use"` content block → `tool_result` in user message
|
|
- Map both to AIUI's unified `ToolCall` / `ToolResult` types
|
|
|
|
## Context Injection
|
|
The system prompt includes context about the user's environment:
|
|
- Connected media sources and their capabilities
|
|
- Available tools and plugins
|
|
- User preferences (language, theme, preferred wallet)
|
|
- In dev mode: mock data summaries
|
|
|
|
Never include sensitive data (API keys, passwords) in system prompts.
|
|
|
|
## Model Selection
|
|
Users can switch models within a conversation. The UI shows:
|
|
- Available models from all connected providers
|
|
- Model capabilities (vision, tools, streaming)
|
|
- Cost per token in sats (if applicable)
|
|
|
|
## Dev Mode
|
|
- `VITE_OPENROUTER_API_KEY` in `.env.local`
|
|
- Free models available (Llama, Mistral via OpenRouter)
|
|
- Mock tool responses available via dev fixtures
|
|
- Debug panel shows: raw messages, token count, latency
|
|
|
|
## Error Handling
|
|
- Rate limits: show user-friendly message, auto-retry with backoff
|
|
- Auth errors: prompt to check API key in settings
|
|
- Network errors: show offline indicator, queue message for retry
|
|
- Model errors: show error in chat, suggest alternative model
|